Traditional Chinese villages,vital carriers of traditional culture,have faced significant alterations due to urbanization in recent years,urgently necessitating artificial intelligence data updates.This study integrat...Traditional Chinese villages,vital carriers of traditional culture,have faced significant alterations due to urbanization in recent years,urgently necessitating artificial intelligence data updates.This study integrates high spatial resolution remote sensing imagery with deep learning techniques,proposing a novel method for identifying rooftops of traditional Chinese village buildings using high-definition remote sensing images.Using 0.54 m spatial resolution imagery of traditional village areas as the data source,this method analyzes the geometric and spectral image characteristics of village building rooftops.It constructs a deep learning feature sample library tailored to the target types.Employing a semantically enhanced version of the improved Mask R-CNN(Mask Region-based Convolutional Neural Network)for building recognition,the study conducts experiments on localized imagery from different regions.The results demonstrated that the modified Mask R-CNN effectively identifies traditional village building rooftops,achieving an of 0.7520 and an of 0.7400.It improves the current problem of misidentification and missed detection caused by feature heterogeneity.This method offers a viable and effective approach for industrialized data monitoring of traditional villages,contributing to their sustainable development.展开更多
In the field of satellite imagery, remote sensing image captioning(RSIC) is a hot topic with the challenge of overfitting and difficulty of image and text alignment. To address these issues, this paper proposes a visi...In the field of satellite imagery, remote sensing image captioning(RSIC) is a hot topic with the challenge of overfitting and difficulty of image and text alignment. To address these issues, this paper proposes a vision-language aligning paradigm for RSIC to jointly represent vision and language. First, a new RSIC dataset DIOR-Captions is built for augmenting object detection in optical remote(DIOR) sensing images dataset with manually annotated Chinese and English contents. Second, a Vision-Language aligning model with Cross-modal Attention(VLCA) is presented to generate accurate and abundant bilingual descriptions for remote sensing images. Third, a crossmodal learning network is introduced to address the problem of visual-lingual alignment. Notably, VLCA is also applied to end-toend Chinese captions generation by using the pre-training language model of Chinese. The experiments are carried out with various baselines to validate VLCA on the proposed dataset. The results demonstrate that the proposed algorithm is more descriptive and informative than existing algorithms in producing captions.展开更多
To create a green and healthy living environment,people have put forward higher requirements for the refined management of ecological resources.A variety of technologies,including satellite remote sensing,Internet of ...To create a green and healthy living environment,people have put forward higher requirements for the refined management of ecological resources.A variety of technologies,including satellite remote sensing,Internet of Things,artificial intelligence,and big data,can build a smart environmental monitoring system.Remote sensing image classification is an important research content in ecological environmental monitoring.Remote sensing images contain rich spatial information andmulti-temporal information,but also bring challenges such as difficulty in obtaining classification labels and low classification accuracy.To solve this problem,this study develops a transductive transfer dictionary learning(TTDL)algorithm.In the TTDL,the source and target domains are transformed fromthe original sample space to a common subspace.TTDL trains a shared discriminative dictionary in this subspace,establishes associations between domains,and also obtains sparse representations of source and target domain data.To obtain an effective shared discriminative dictionary,triple-induced ordinal locality preserving term,Fisher discriminant term,and graph Laplacian regularization termare introduced into the TTDL.The triplet-induced ordinal locality preserving term on sub-space projection preserves the local structure of data in low-dimensional subspaces.The Fisher discriminant term on dictionary improves differences among different sub-dictionaries through intra-class and inter-class scatters.The graph Laplacian regularization term on sparse representation maintains the manifold structure using a semi-supervised weight graphmatrix,which can indirectly improve the discriminative performance of the dictionary.The TTDL is tested on several remote sensing image datasets and has strong discrimination classification performance.展开更多
The semantic segmentation methods based on CNN have made great progress,but there are still some shortcomings in the application of remote sensing images segmentation,such as the small receptive field can not effectiv...The semantic segmentation methods based on CNN have made great progress,but there are still some shortcomings in the application of remote sensing images segmentation,such as the small receptive field can not effectively capture global context.In order to solve this problem,this paper proposes a hybrid model based on ResNet50 and swin transformer to directly capture long-range dependence,which fuses features through Cross Feature Modulation Module(CFMM).Experimental results on two publicly available datasets,Vaihingen and Potsdam,are mIoU of 70.27%and 76.63%,respectively.Thus,CFM-UNet can maintain a high segmentation performance compared with other competitive networks.展开更多
To address the issue of imbalanced detection performance and detection speed in current mainstream object detection algorithms for optical remote sensing images,this paper proposes a multi-scale object detection model...To address the issue of imbalanced detection performance and detection speed in current mainstream object detection algorithms for optical remote sensing images,this paper proposes a multi-scale object detection model for remote sensing images on complex backgrounds,called DI-YOLO,based on You Only Look Once v7-tiny(YOLOv7-tiny).Firstly,to enhance the model’s ability to capture irregular-shaped objects and deformation features,as well as to extract high-level semantic information,deformable convolutions are used to replace standard convolutions in the original model.Secondly,a Content Coordination Attention Feature Pyramid Network(CCA-FPN)structure is designed to replace the Neck part of the original model,which can further perceive relationships between different pixels,reduce feature loss in remote sensing images,and improve the overall model’s ability to detect multi-scale objects.Thirdly,an Implicitly Efficient Decoupled Head(IEDH)is proposed to increase the model’s flexibility,making it more adaptable to complex detection tasks in various scenarios.Finally,the Smoothed Intersection over Union(SIoU)loss function replaces the Complete Intersection over Union(CIoU)loss function in the original model,resulting in more accurate prediction of bounding boxes and continuous model optimization.Experimental results on the High-Resolution Remote Sensing Detection(HRRSD)dataset demonstrate that the proposed DI-YOLO model outperforms mainstream target detection algorithms in terms of mean Average Precision(mAP)for optical remote sensing image detection.Furthermore,it achieves Frames Per Second(FPS)of 138.9,meeting fast and accurate detection requirements.展开更多
Semantic segmentation of remote sensing images is one of the core tasks of remote sensing image interpretation.With the continuous develop-ment of artificial intelligence technology,the use of deep learning methods fo...Semantic segmentation of remote sensing images is one of the core tasks of remote sensing image interpretation.With the continuous develop-ment of artificial intelligence technology,the use of deep learning methods for interpreting remote-sensing images has matured.Existing neural networks disregard the spatial relationship between two targets in remote sensing images.Semantic segmentation models that combine convolutional neural networks(CNNs)and graph convolutional neural networks(GCNs)cause a lack of feature boundaries,which leads to the unsatisfactory segmentation of various target feature boundaries.In this paper,we propose a new semantic segmentation model for remote sensing images(called DGCN hereinafter),which combines deep semantic segmentation networks(DSSN)and GCNs.In the GCN module,a loss function for boundary information is employed to optimize the learning of spatial relationship features between the target features and their relationships.A hierarchical fusion method is utilized for feature fusion and classification to optimize the spatial relationship informa-tion in the original feature information.Extensive experiments on ISPRS 2D and DeepGlobe semantic segmentation datasets show that compared with the existing semantic segmentation models of remote sensing images,the DGCN significantly optimizes the segmentation effect of feature boundaries,effectively reduces the noise in the segmentation results and improves the segmentation accuracy,which demonstrates the advancements of our model.展开更多
Remote sensing image(RSI)classifier roles a vital play in earth observation technology utilizing Remote sensing(RS)data are extremely exploited from both military and civil fields.More recently,as novel DL approaches ...Remote sensing image(RSI)classifier roles a vital play in earth observation technology utilizing Remote sensing(RS)data are extremely exploited from both military and civil fields.More recently,as novel DL approaches develop,techniques for RSI classifiers with DL have attained important breakthroughs,providing a new opportunity for the research and development of RSI classifiers.This study introduces an Improved Slime Mould Optimization with a graph convolutional network for the hyperspectral remote sensing image classification(ISMOGCN-HRSC)model.The ISMOGCN-HRSC model majorly concentrates on identifying and classifying distinct kinds of RSIs.In the presented ISMOGCN-HRSC model,the synergic deep learning(SDL)model is exploited to produce feature vectors.The GCN model is utilized for image classification purposes to identify the proper class labels of the RSIs.The ISMO algorithm is used to enhance the classification efficiency of the GCN method,which is derived by integrating chaotic concepts into the SMO algorithm.The experimental assessment of the ISMOGCN-HRSC method is tested using a benchmark dataset.展开更多
The exploration of building detection plays an important role in urban planning,smart city and military.Aiming at the problem of high overlapping ratio of detection frames for dense building detection in high resoluti...The exploration of building detection plays an important role in urban planning,smart city and military.Aiming at the problem of high overlapping ratio of detection frames for dense building detection in high resolution remote sensing images,we present an effective YOLOv3 framework,corner regression-based YOLOv3(Correg-YOLOv3),to localize dense building accurately.This improved YOLOv3 algorithm establishes a vertex regression mechanism and an additional loss item about building vertex offsets relative to the center point of bounding box.By extending output dimensions,the trained model is able to output the rectangular bounding boxes and the building vertices meanwhile.Finally,we evaluate the performance of the Correg-YOLOv3 on our self-produced data set and provide a comparative analysis qualitatively and quantitatively.The experimental results achieve high performance in precision(96.45%),recall rate(95.75%),F1 score(96.10%)and average precision(98.05%),which were 2.73%,5.4%,4.1%and 4.73%higher than that of YOLOv3.Therefore,our proposed algorithm effectively tackles the problem of dense building detection in high resolution images.展开更多
A method to remove stripes from remote sensing images is proposed based on statistics and a new image enhancement method.The overall processing steps for improving the quality of remote sensing images are introduced t...A method to remove stripes from remote sensing images is proposed based on statistics and a new image enhancement method.The overall processing steps for improving the quality of remote sensing images are introduced to provide a general baseline.Due to the differences in satellite sensors when producing images,subtle but inherent stripes can appear at the stitching positions between the sensors.These stitchingstripes cannot be eliminated by conventional relative radiometric calibration.The inherent stitching stripes cause difficulties in downstream tasks such as the segmentation,classification and interpretation of remote sensing images.Therefore,a method to remove the stripes based on statistics and a new image enhancement approach are proposed in this paper.First,the inconsistency in grayscales around stripes is eliminated with the statistical method.Second,the pixels within stripes are weighted and averaged based on updated pixel values to enhance the uniformity of the overall image radiation quality.Finally,the details of the images are highlighted by a new image enhancement method,which makes the whole image clearer.Comprehensive experiments are performed,and the results indicate that the proposed method outperforms the baseline approach in terms of visual quality and radiation correction accuracy.展开更多
Based on low-altitude remote sensing images,this paper established sample set of typical river vegetation elements and proposed river vegetation extraction technical solution to adaptively extract typical vegetation e...Based on low-altitude remote sensing images,this paper established sample set of typical river vegetation elements and proposed river vegetation extraction technical solution to adaptively extract typical vegetation elements of river basins.The main research of this paper were as follows:(1)a typical vegetation extraction sample set based on low-altitude remote sensing images was established.(2)A low-altitude remote sensing image vegetation extraction model based on the focus perception module was designed to realize the end-to-end automatic extraction of different types of vegetation areas of low-altitude remote sensing images to fully learn the spectral spatial texture information and deep semantic information of the images.(3)By comparison with the baseline method,baseline method with embedded focus perception module showed an improvement in the precision by 7.37%and mIoU by 49.49%.Through visual interpretation and quantitative calculation analysis,the typical river vegetation adaptive extraction network has effectiveness and generalization ability,consistent with the needs of practical applications of vegetation extraction.展开更多
A numerical algorithm of principal component analysis (PCA) is proposed and its application in remote sensing image processing is introduced: (1) Multispectral image compression;(2) Multi-spectral image noise cancella...A numerical algorithm of principal component analysis (PCA) is proposed and its application in remote sensing image processing is introduced: (1) Multispectral image compression;(2) Multi-spectral image noise cancellation;(3) Information fusion of multi-spectral images and spot panchromatic images. The software experiments verify and evaluate the effectiveness and accuracy of the proposed algorithm.展开更多
Maize tassel detection is essential for future agronomic management in maize planting and breeding,with application in yield estimation,growth monitoring,intelligent picking,and disease detection.However,detecting mai...Maize tassel detection is essential for future agronomic management in maize planting and breeding,with application in yield estimation,growth monitoring,intelligent picking,and disease detection.However,detecting maize tassels in the field poses prominent challenges as they are often obscured by widespread occlusions and differ in size and morphological color at different growth stages.This study proposes the SEYOLOX-tiny Model that more accurately and robustly detects maize tassels in the field.Firstly,the data acquisition method ensures the balance between the image quality and image acquisition efficiency and obtains maize tassel images from different periods to enrich the dataset by unmanned aerial vehicle(UAV).Moreover,the robust detection network extends YOLOX by embedding an attention mechanism to realize the extraction of critical features and suppressing the noise caused by adverse factors(e.g.,occlusions and overlaps),which could be more suitable and robust for operation in complex natural environments.Experimental results verify the research hypothesis and show a mean average precision(mAP_(@0.5)) of 95.0%.The mAP_(@0.5),mAP_(@0.5-0.95),mAP_(@0.5-0.95(area=small)),and mAP_(@0.5-0.95(area=medium)) average values increased by 1.5,1.8,5.3,and 1.7%,respectively,compared to the original model.The proposed method can effectively meet the precision and robustness requirements of the vision system in maize tassel detection.展开更多
Hyperspectral remote sensing/imaging spectroscopy is a novel approach to reaching a spectrum from all the places of a huge array of spatial places so that several spectral wavelengths are utilized for making coherent ...Hyperspectral remote sensing/imaging spectroscopy is a novel approach to reaching a spectrum from all the places of a huge array of spatial places so that several spectral wavelengths are utilized for making coherent images.Hyperspectral remote sensing contains acquisition of digital images from several narrow,contiguous spectral bands throughout the visible,Thermal Infrared(TIR),Near Infrared(NIR),and Mid-Infrared(MIR)regions of the electromagnetic spectrum.In order to the application of agricultural regions,remote sensing approaches are studied and executed to their benefit of continuous and quantitativemonitoring.Particularly,hyperspectral images(HSI)are considered the precise for agriculture as they can offer chemical and physical data on vegetation.With this motivation,this article presents a novel Hurricane Optimization Algorithm with Deep Transfer Learning Driven Crop Classification(HOADTL-CC)model onHyperspectralRemote Sensing Images.The presentedHOADTL-CC model focuses on the identification and categorization of crops on hyperspectral remote sensing images.To accomplish this,the presentedHOADTL-CC model involves the design ofHOAwith capsule network(CapsNet)model for generating a set of useful feature vectors.Besides,Elman neural network(ENN)model is applied to allot proper class labels into the input HSI.Finally,glowworm swarm optimization(GSO)algorithm is exploited to fine tune the ENNparameters involved in this article.The experimental result scrutiny of the HOADTL-CC method can be tested with the help of benchmark dataset and the results are assessed under distinct aspects.Extensive comparative studies stated the enhanced performance of the HOADTL-CC model over recent approaches with maximum accuracy of 99.51%.展开更多
The Internet of Things(IoT)offers a new era of connectivity,which goes beyond laptops and smart connected devices for connected vehicles,smart homes,smart cities,and connected healthcare.The massive quantity of data g...The Internet of Things(IoT)offers a new era of connectivity,which goes beyond laptops and smart connected devices for connected vehicles,smart homes,smart cities,and connected healthcare.The massive quantity of data gathered from numerous IoT devices poses security and privacy concerns for users.With the increasing use of multimedia in communications,the content security of remote-sensing images attracted much attention in academia and industry.Image encryption is important for securing remote sensing images in the IoT environment.Recently,researchers have introduced plenty of algorithms for encrypting images.This study introduces an Improved Sine Cosine Algorithm with Chaotic Encryption based Remote Sensing Image Encryption(ISCACE-RSI)technique in IoT Environment.The proposed model follows a three-stage process,namely pre-processing,encryption,and optimal key generation.The remote sensing images were preprocessed at the initial stage to enhance the image quality.Next,the ISCACERSI technique exploits the double-layer remote sensing image encryption(DLRSIE)algorithm for encrypting the images.The DLRSIE methodology incorporates the design of Chaotic Maps and deoxyribonucleic acid(DNA)Strand Displacement(DNASD)approach.The chaotic map is employed for generating pseudorandom sequences and implementing routine scrambling and diffusion processes on the plaintext images.Then,the study presents three DNASD-related encryption rules based on the variety of DNASD,and those rules are applied for encrypting the images at the DNA sequence level.For an optimal key generation of the DLRSIE technique,the ISCA is applied with an objective function of the maximization of peak signal to noise ratio(PSNR).To examine the performance of the ISCACE-RSI model,a detailed set of simulations were conducted.The comparative study reported the better performance of the ISCACE-RSI model over other existing approaches.展开更多
Recently,the convolutional neural network(CNN)has been dom-inant in studies on interpreting remote sensing images(RSI).However,it appears that training optimization strategies have received less attention in relevant ...Recently,the convolutional neural network(CNN)has been dom-inant in studies on interpreting remote sensing images(RSI).However,it appears that training optimization strategies have received less attention in relevant research.To evaluate this problem,the author proposes a novel algo-rithm named the Fast Training CNN(FST-CNN).To verify the algorithm’s effectiveness,twenty methods,including six classic models and thirty archi-tectures from previous studies,are included in a performance comparison.The overall accuracy(OA)trained by the FST-CNN algorithm on the same model architecture and dataset is treated as an evaluation baseline.Results show that there is a maximal OA gap of 8.35%between the FST-CNN and those methods in the literature,which means a 10%margin in performance.Meanwhile,all those complex roadmaps,e.g.,deep feature fusion,model combination,model ensembles,and human feature engineering,are not as effective as expected.It reveals that there was systemic suboptimal perfor-mance in the previous studies.Most of the CNN-based methods proposed in the previous studies show a consistent mistake,which has made the model’s accuracy lower than its potential value.The most important reasons seem to be the inappropriate training strategy and the shift in data distribution introduced by data augmentation(DA).As a result,most of the performance evaluation was conducted based on an inaccurate,suboptimal,and unfair result.It has made most of the previous research findings questionable to some extent.However,all these confusing results also exactly demonstrate the effectiveness of FST-CNN.This novel algorithm is model-agnostic and can be employed on any image classification model to potentially boost performance.In addition,the results also show that a standardized training strategy is indeed very meaningful for the research tasks of the RSI-SC.展开更多
Preserving biodiversity and maintaining ecological balance is essential in current environmental conditions.It is challenging to determine vegetation using traditional map classification approaches.The primary issue i...Preserving biodiversity and maintaining ecological balance is essential in current environmental conditions.It is challenging to determine vegetation using traditional map classification approaches.The primary issue in detecting vegetation pattern is that it appears with complex spatial structures and similar spectral properties.It is more demandable to determine the multiple spectral ana-lyses for improving the accuracy of vegetation mapping through remotely sensed images.The proposed framework is developed with the idea of ensembling three effective strategies to produce a robust architecture for vegetation mapping.The architecture comprises three approaches,feature-based approach,region-based approach,and texture-based approach for classifying the vegetation area.The novel Deep Meta fusion model(DMFM)is created with a unique fusion frame-work of residual stacking of convolution layers with Unique covariate features(UCF),Intensity features(IF),and Colour features(CF).The overhead issues in GPU utilization during Convolution neural network(CNN)models are reduced here with a lightweight architecture.The system considers detailing feature areas to improve classification accuracy and reduce processing time.The proposed DMFM model achieved 99%accuracy,with a maximum processing time of 130 s.The training,testing,and validation losses are degraded to a significant level that shows the performance quality with the DMFM model.The system acts as a standard analysis platform for dynamic datasets since all three different fea-tures,such as Unique covariate features(UCF),Intensity features(IF),and Colour features(CF),are considered very well.展开更多
Check dams are widely used on the Loess Plateau in China to control soil and water losses,develop agricultural land,and improve watershed ecology.Detailed information on the number and spatial distribution of check da...Check dams are widely used on the Loess Plateau in China to control soil and water losses,develop agricultural land,and improve watershed ecology.Detailed information on the number and spatial distribution of check dams is critical for quantitatively evaluating hydrological and ecological effects and planning the construction of new dams.Thus,this study developed a check dam detection framework for broad areas from high-resolution remote sensing images using an ensemble approach of deep learning and geospatial analysis.First,we made a sample dataset of check dams using GaoFen-2(GF-2)and Google Earth images.Next,we evaluated five popular deep-learning-based object detectors,including Faster R-CNN,You Only Look Once(version 3)(YOLOv3),Cascade R-CNN,YOLOX,and VarifocalNet(VFNet),to identify the best one for check dam detection.Finally,we analyzed the location characteristics of the check dams and used geographical constraints to optimize the detection results.Precision,recall,average precision at intersection over union(IoU)threshold of 0.50(AP_(50)),IoU threshold of 0.75(AP_(75)),and average value for 10 IoU thresholds ranging from 0.50-0.95 with a 0.05 step(AP_(50-95)),and inference time were used to evaluate model performance.All the five deep learning networks could identify check dams quickly and accurately,with AP_(50-95),AP_(50),and AP_(75)values higher than 60.0%,90.0%,and 70.0%,respectively,except for YOLOv3.The VFNet had the best performance,followed by YOLOX.The proposed framework was tested in the Yanhe River Basin and yielded promising results,with a recall rate of 87.0%for 521 check dams.Furthermore,the geographic analysis deleted about 50%of the false detection boxes,increasing the identification accuracy of check dams from 78.6%to 87.6%.Simultaneously,this framework recognized 568 recently constructed check dams and small check dams not recorded in the known check dam survey datasets.The extraction results will support efficient watershed management and guide future studies on soil erosion in the Loess Plateau.展开更多
Desert lakes are important wetland resources in the blown-sand area of western China and play a significant role in maintain-ing the regional ecological environment.However,large-scale coal mining in recent years has ...Desert lakes are important wetland resources in the blown-sand area of western China and play a significant role in maintain-ing the regional ecological environment.However,large-scale coal mining in recent years has considerably impacted the deposition condition of several lakes.Rapid and accurate extraction of lake information based on satellite images is crucial for developing protective measures against desertification.However,the spatial resolution of these images often leads to mixed pixels near water boundaries,affecting extraction precision.Traditional pixel unmixing methods mainly obtain water coverage information in a mixed pixel,making it difficult to accurately describe the spatial distribution.In this paper,the cellular automata(CA)model was adopted in order to realize lake information extraction at a sub-pixel level.A mining area in Shenmu City,Shaanxi Province,China is selected as the research region,using the image of Sentinel-2 as the data source and the high spatial resolution UAV image as the reference.First,water coverage of mixed pixels in the Sentinel-2 image was calculated with the dimidiate pixel model and the fully constrained least squares(FCLS)method.Second,the mixed pixels were subdivided to form the cellular space at a sub-pixel level and the transition rules are constructed based on the water coverage information and spatial correlation.Lastly,the process was implemented using Python and IDL,with the ArcGIS and ENVI software being used for validation.The experiments show that the CA model can improve the sub-pixel positioning accuracy for lake bodies in mixed pixel image and improve classification accuracy.The FCLS-CA model has a higher accuracy and is able to identify most water bodies in the study area,and is therefore suitable for desert lake monitor-ing in mining areas.展开更多
Over the past decade,the significant growth of the convolutional neural network(CNN)based on deep learning(DL)approaches has greatly improved the machine learning(ML)algorithm’s performance on the semantic scene clas...Over the past decade,the significant growth of the convolutional neural network(CNN)based on deep learning(DL)approaches has greatly improved the machine learning(ML)algorithm’s performance on the semantic scene classification(SSC)of remote sensing images(RSI).However,the unbalanced attention to classification accuracy and efficiency has made the superiority of DL-based algorithms,e.g.,automation and simplicity,partially lost.Traditional ML strategies(e.g.,the handcrafted features or indicators)and accuracy-aimed strategies with a high trade-off(e.g.,the multi-stage CNNs and ensemble of multi-CNNs)are widely used without any training efficiency optimization involved,which may result in suboptimal performance.To address this problem,we propose a fast and simple training CNN framework(named FST-EfficientNet)for RSI-SSC based on an EfficientNetversion2 small(EfficientNetV2-S)CNN model.The whole algorithm flow is completely one-stage and end-to-end without any handcrafted features or discriminators introduced.In the implementation of training efficiency optimization,only several routine data augmentation tricks coupled with a fixed ratio of resolution or a gradually increasing resolution strategy are employed,so that the algorithm’s trade-off is very cheap.The performance evaluation shows that our FST-EfficientNet achieves new state-of-the-art(SOTA)records in the overall accuracy(OA)with about 0.8%to 2.7%ahead of all earlier methods on the Aerial Image Dataset(AID)and Northwestern Poly-technical University Remote Sensing Image Scene Classification 45 Dataset(NWPU-RESISC45D).Meanwhile,the results also demonstrate the importance and indispensability of training efficiency optimization strategies for RSI-SSC by DL.In fact,it is not necessary to gain better classification accuracy by completely relying on an excessive trade-off without efficiency.Ultimately,these findings are expected to contribute to the development of more efficient CNN-based approaches in RSI-SSC.展开更多
Outbreaks of Ulva prolifera have continued in the South Yellow Sea of China(SYS)since 2007,becoming a serious marine ecological disaster.Large amounts of U.prolifera drift to the coast of the Shandong Peninsula to dis...Outbreaks of Ulva prolifera have continued in the South Yellow Sea of China(SYS)since 2007,becoming a serious marine ecological disaster.Large amounts of U.prolifera drift to the coast of the Shandong Peninsula to dissipate under the action of southeast monsoons and ocean surface currents.This causes serious harm to the ecological environment and economic activities of coastal cities.To investigate the impact of U.prolifera dissipation,this study extracted the spatiotemporal distribution of U.prolifera in the SYS from 2012 to 2020 based on the Google Earth Engine.The outbreak cycle of U.prolifera was determined by fitting analysis of outbreak time and coverage area through MATLAB.This study also looked at the effect of U.prolifera dissipation on water quality through field monitoring data.The results showed that the growth curve of the U.prolifera has a significant Gaussian distribution.The U.prolifera dissipates in Haiyang,China,in July and August every year and affects the offshore environment.Water quality parameters of seawater at different depths had significant differences after the U.prolifera dissipation.Changes in pH,chemical oxygen demand,nitrite nitrogen,nitrate nitrogen,ammonia nitrogen,chlorophyll a,total phosphorus,and suspended solids were more significant in surface seawater than in deeper water.Changes in the concentrations of dissolved oxygen and total nitrogen were more significant in the deep seawater(1.63 and 1.1 times higher than those in the surface seawater,respectively).The dissipation of U.prolifera releases a large amount of carbon and nitrogen into the seawater,which provides rich nutrients for phytoplankton and may cause secondary disasters such as red tide.These findings are useful for further understanding the rules of U.prolifera dissipation,as well as preventing and controlling green tide disasters.展开更多
文摘Traditional Chinese villages,vital carriers of traditional culture,have faced significant alterations due to urbanization in recent years,urgently necessitating artificial intelligence data updates.This study integrates high spatial resolution remote sensing imagery with deep learning techniques,proposing a novel method for identifying rooftops of traditional Chinese village buildings using high-definition remote sensing images.Using 0.54 m spatial resolution imagery of traditional village areas as the data source,this method analyzes the geometric and spectral image characteristics of village building rooftops.It constructs a deep learning feature sample library tailored to the target types.Employing a semantically enhanced version of the improved Mask R-CNN(Mask Region-based Convolutional Neural Network)for building recognition,the study conducts experiments on localized imagery from different regions.The results demonstrated that the modified Mask R-CNN effectively identifies traditional village building rooftops,achieving an of 0.7520 and an of 0.7400.It improves the current problem of misidentification and missed detection caused by feature heterogeneity.This method offers a viable and effective approach for industrialized data monitoring of traditional villages,contributing to their sustainable development.
基金supported by the National Natural Science Foundation of China (61702528,61806212)。
文摘In the field of satellite imagery, remote sensing image captioning(RSIC) is a hot topic with the challenge of overfitting and difficulty of image and text alignment. To address these issues, this paper proposes a vision-language aligning paradigm for RSIC to jointly represent vision and language. First, a new RSIC dataset DIOR-Captions is built for augmenting object detection in optical remote(DIOR) sensing images dataset with manually annotated Chinese and English contents. Second, a Vision-Language aligning model with Cross-modal Attention(VLCA) is presented to generate accurate and abundant bilingual descriptions for remote sensing images. Third, a crossmodal learning network is introduced to address the problem of visual-lingual alignment. Notably, VLCA is also applied to end-toend Chinese captions generation by using the pre-training language model of Chinese. The experiments are carried out with various baselines to validate VLCA on the proposed dataset. The results demonstrate that the proposed algorithm is more descriptive and informative than existing algorithms in producing captions.
基金This research was funded in part by the Natural Science Foundation of Jiangsu Province under Grant BK 20211333by the Science and Technology Project of Changzhou City(CE20215032).
文摘To create a green and healthy living environment,people have put forward higher requirements for the refined management of ecological resources.A variety of technologies,including satellite remote sensing,Internet of Things,artificial intelligence,and big data,can build a smart environmental monitoring system.Remote sensing image classification is an important research content in ecological environmental monitoring.Remote sensing images contain rich spatial information andmulti-temporal information,but also bring challenges such as difficulty in obtaining classification labels and low classification accuracy.To solve this problem,this study develops a transductive transfer dictionary learning(TTDL)algorithm.In the TTDL,the source and target domains are transformed fromthe original sample space to a common subspace.TTDL trains a shared discriminative dictionary in this subspace,establishes associations between domains,and also obtains sparse representations of source and target domain data.To obtain an effective shared discriminative dictionary,triple-induced ordinal locality preserving term,Fisher discriminant term,and graph Laplacian regularization termare introduced into the TTDL.The triplet-induced ordinal locality preserving term on sub-space projection preserves the local structure of data in low-dimensional subspaces.The Fisher discriminant term on dictionary improves differences among different sub-dictionaries through intra-class and inter-class scatters.The graph Laplacian regularization term on sparse representation maintains the manifold structure using a semi-supervised weight graphmatrix,which can indirectly improve the discriminative performance of the dictionary.The TTDL is tested on several remote sensing image datasets and has strong discrimination classification performance.
基金Young Innovative Talents Project of Guangdong Ordinary Universities(No.2022KQNCX225)School-level Teaching and Research Project of Guangzhou City Polytechnic(No.2022xky046)。
文摘The semantic segmentation methods based on CNN have made great progress,but there are still some shortcomings in the application of remote sensing images segmentation,such as the small receptive field can not effectively capture global context.In order to solve this problem,this paper proposes a hybrid model based on ResNet50 and swin transformer to directly capture long-range dependence,which fuses features through Cross Feature Modulation Module(CFMM).Experimental results on two publicly available datasets,Vaihingen and Potsdam,are mIoU of 70.27%and 76.63%,respectively.Thus,CFM-UNet can maintain a high segmentation performance compared with other competitive networks.
基金Funding for this research was provided by 511 Shaanxi Province’s Key Research and Development Plan(No.2022NY-087).
文摘To address the issue of imbalanced detection performance and detection speed in current mainstream object detection algorithms for optical remote sensing images,this paper proposes a multi-scale object detection model for remote sensing images on complex backgrounds,called DI-YOLO,based on You Only Look Once v7-tiny(YOLOv7-tiny).Firstly,to enhance the model’s ability to capture irregular-shaped objects and deformation features,as well as to extract high-level semantic information,deformable convolutions are used to replace standard convolutions in the original model.Secondly,a Content Coordination Attention Feature Pyramid Network(CCA-FPN)structure is designed to replace the Neck part of the original model,which can further perceive relationships between different pixels,reduce feature loss in remote sensing images,and improve the overall model’s ability to detect multi-scale objects.Thirdly,an Implicitly Efficient Decoupled Head(IEDH)is proposed to increase the model’s flexibility,making it more adaptable to complex detection tasks in various scenarios.Finally,the Smoothed Intersection over Union(SIoU)loss function replaces the Complete Intersection over Union(CIoU)loss function in the original model,resulting in more accurate prediction of bounding boxes and continuous model optimization.Experimental results on the High-Resolution Remote Sensing Detection(HRRSD)dataset demonstrate that the proposed DI-YOLO model outperforms mainstream target detection algorithms in terms of mean Average Precision(mAP)for optical remote sensing image detection.Furthermore,it achieves Frames Per Second(FPS)of 138.9,meeting fast and accurate detection requirements.
基金funded by the Major Scientific and Technological Innovation Project of Shandong Province,Grant No.2022CXGC010609.
文摘Semantic segmentation of remote sensing images is one of the core tasks of remote sensing image interpretation.With the continuous develop-ment of artificial intelligence technology,the use of deep learning methods for interpreting remote-sensing images has matured.Existing neural networks disregard the spatial relationship between two targets in remote sensing images.Semantic segmentation models that combine convolutional neural networks(CNNs)and graph convolutional neural networks(GCNs)cause a lack of feature boundaries,which leads to the unsatisfactory segmentation of various target feature boundaries.In this paper,we propose a new semantic segmentation model for remote sensing images(called DGCN hereinafter),which combines deep semantic segmentation networks(DSSN)and GCNs.In the GCN module,a loss function for boundary information is employed to optimize the learning of spatial relationship features between the target features and their relationships.A hierarchical fusion method is utilized for feature fusion and classification to optimize the spatial relationship informa-tion in the original feature information.Extensive experiments on ISPRS 2D and DeepGlobe semantic segmentation datasets show that compared with the existing semantic segmentation models of remote sensing images,the DGCN significantly optimizes the segmentation effect of feature boundaries,effectively reduces the noise in the segmentation results and improves the segmentation accuracy,which demonstrates the advancements of our model.
文摘Remote sensing image(RSI)classifier roles a vital play in earth observation technology utilizing Remote sensing(RS)data are extremely exploited from both military and civil fields.More recently,as novel DL approaches develop,techniques for RSI classifiers with DL have attained important breakthroughs,providing a new opportunity for the research and development of RSI classifiers.This study introduces an Improved Slime Mould Optimization with a graph convolutional network for the hyperspectral remote sensing image classification(ISMOGCN-HRSC)model.The ISMOGCN-HRSC model majorly concentrates on identifying and classifying distinct kinds of RSIs.In the presented ISMOGCN-HRSC model,the synergic deep learning(SDL)model is exploited to produce feature vectors.The GCN model is utilized for image classification purposes to identify the proper class labels of the RSIs.The ISMO algorithm is used to enhance the classification efficiency of the GCN method,which is derived by integrating chaotic concepts into the SMO algorithm.The experimental assessment of the ISMOGCN-HRSC method is tested using a benchmark dataset.
基金National Natural Science Foundation of China(No.41871305)National Key Research and Development Program of China(No.2017YFC0602204)+2 种基金Fundamental Research Funds for the Central Universities,China University of Geosciences(Wuhan)(No.CUGQY1945)Open Fund of Key Laboratory of Geological Survey and Evaluation of Ministry of Education and the Fundamental Research Funds for the Central Universities(No.GLAB2019ZR02)Open Fund of Laboratory of Urban Land Resources Monitoring and Simulation,Ministry of Natural Resources,China(No.KF-2020-05-068)。
文摘The exploration of building detection plays an important role in urban planning,smart city and military.Aiming at the problem of high overlapping ratio of detection frames for dense building detection in high resolution remote sensing images,we present an effective YOLOv3 framework,corner regression-based YOLOv3(Correg-YOLOv3),to localize dense building accurately.This improved YOLOv3 algorithm establishes a vertex regression mechanism and an additional loss item about building vertex offsets relative to the center point of bounding box.By extending output dimensions,the trained model is able to output the rectangular bounding boxes and the building vertices meanwhile.Finally,we evaluate the performance of the Correg-YOLOv3 on our self-produced data set and provide a comparative analysis qualitatively and quantitatively.The experimental results achieve high performance in precision(96.45%),recall rate(95.75%),F1 score(96.10%)and average precision(98.05%),which were 2.73%,5.4%,4.1%and 4.73%higher than that of YOLOv3.Therefore,our proposed algorithm effectively tackles the problem of dense building detection in high resolution images.
文摘A method to remove stripes from remote sensing images is proposed based on statistics and a new image enhancement method.The overall processing steps for improving the quality of remote sensing images are introduced to provide a general baseline.Due to the differences in satellite sensors when producing images,subtle but inherent stripes can appear at the stitching positions between the sensors.These stitchingstripes cannot be eliminated by conventional relative radiometric calibration.The inherent stitching stripes cause difficulties in downstream tasks such as the segmentation,classification and interpretation of remote sensing images.Therefore,a method to remove the stripes based on statistics and a new image enhancement approach are proposed in this paper.First,the inconsistency in grayscales around stripes is eliminated with the statistical method.Second,the pixels within stripes are weighted and averaged based on updated pixel values to enhance the uniformity of the overall image radiation quality.Finally,the details of the images are highlighted by a new image enhancement method,which makes the whole image clearer.Comprehensive experiments are performed,and the results indicate that the proposed method outperforms the baseline approach in terms of visual quality and radiation correction accuracy.
文摘Based on low-altitude remote sensing images,this paper established sample set of typical river vegetation elements and proposed river vegetation extraction technical solution to adaptively extract typical vegetation elements of river basins.The main research of this paper were as follows:(1)a typical vegetation extraction sample set based on low-altitude remote sensing images was established.(2)A low-altitude remote sensing image vegetation extraction model based on the focus perception module was designed to realize the end-to-end automatic extraction of different types of vegetation areas of low-altitude remote sensing images to fully learn the spectral spatial texture information and deep semantic information of the images.(3)By comparison with the baseline method,baseline method with embedded focus perception module showed an improvement in the precision by 7.37%and mIoU by 49.49%.Through visual interpretation and quantitative calculation analysis,the typical river vegetation adaptive extraction network has effectiveness and generalization ability,consistent with the needs of practical applications of vegetation extraction.
文摘A numerical algorithm of principal component analysis (PCA) is proposed and its application in remote sensing image processing is introduced: (1) Multispectral image compression;(2) Multi-spectral image noise cancellation;(3) Information fusion of multi-spectral images and spot panchromatic images. The software experiments verify and evaluate the effectiveness and accuracy of the proposed algorithm.
基金supported by the Chinese Universities Scientific Fund (2022TC169)。
文摘Maize tassel detection is essential for future agronomic management in maize planting and breeding,with application in yield estimation,growth monitoring,intelligent picking,and disease detection.However,detecting maize tassels in the field poses prominent challenges as they are often obscured by widespread occlusions and differ in size and morphological color at different growth stages.This study proposes the SEYOLOX-tiny Model that more accurately and robustly detects maize tassels in the field.Firstly,the data acquisition method ensures the balance between the image quality and image acquisition efficiency and obtains maize tassel images from different periods to enrich the dataset by unmanned aerial vehicle(UAV).Moreover,the robust detection network extends YOLOX by embedding an attention mechanism to realize the extraction of critical features and suppressing the noise caused by adverse factors(e.g.,occlusions and overlaps),which could be more suitable and robust for operation in complex natural environments.Experimental results verify the research hypothesis and show a mean average precision(mAP_(@0.5)) of 95.0%.The mAP_(@0.5),mAP_(@0.5-0.95),mAP_(@0.5-0.95(area=small)),and mAP_(@0.5-0.95(area=medium)) average values increased by 1.5,1.8,5.3,and 1.7%,respectively,compared to the original model.The proposed method can effectively meet the precision and robustness requirements of the vision system in maize tassel detection.
基金the Deanship of Scientific Research at King Khalid University for funding this work through Large Groups Project under Grant Number(25/43)Princess Nourah bint Abdulrahman University Researchers Supporting Project Number(PNURSP2022R303)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.The authors would like to thank the Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:22UQU4340237DSR28.
文摘Hyperspectral remote sensing/imaging spectroscopy is a novel approach to reaching a spectrum from all the places of a huge array of spatial places so that several spectral wavelengths are utilized for making coherent images.Hyperspectral remote sensing contains acquisition of digital images from several narrow,contiguous spectral bands throughout the visible,Thermal Infrared(TIR),Near Infrared(NIR),and Mid-Infrared(MIR)regions of the electromagnetic spectrum.In order to the application of agricultural regions,remote sensing approaches are studied and executed to their benefit of continuous and quantitativemonitoring.Particularly,hyperspectral images(HSI)are considered the precise for agriculture as they can offer chemical and physical data on vegetation.With this motivation,this article presents a novel Hurricane Optimization Algorithm with Deep Transfer Learning Driven Crop Classification(HOADTL-CC)model onHyperspectralRemote Sensing Images.The presentedHOADTL-CC model focuses on the identification and categorization of crops on hyperspectral remote sensing images.To accomplish this,the presentedHOADTL-CC model involves the design ofHOAwith capsule network(CapsNet)model for generating a set of useful feature vectors.Besides,Elman neural network(ENN)model is applied to allot proper class labels into the input HSI.Finally,glowworm swarm optimization(GSO)algorithm is exploited to fine tune the ENNparameters involved in this article.The experimental result scrutiny of the HOADTL-CC method can be tested with the help of benchmark dataset and the results are assessed under distinct aspects.Extensive comparative studies stated the enhanced performance of the HOADTL-CC model over recent approaches with maximum accuracy of 99.51%.
基金Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R319)PrincessNourah bint Abdulrahman University,Riyadh,Saudi Arabia.The authors would like to thank the Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:(22UQU4210118DSR48).
文摘The Internet of Things(IoT)offers a new era of connectivity,which goes beyond laptops and smart connected devices for connected vehicles,smart homes,smart cities,and connected healthcare.The massive quantity of data gathered from numerous IoT devices poses security and privacy concerns for users.With the increasing use of multimedia in communications,the content security of remote-sensing images attracted much attention in academia and industry.Image encryption is important for securing remote sensing images in the IoT environment.Recently,researchers have introduced plenty of algorithms for encrypting images.This study introduces an Improved Sine Cosine Algorithm with Chaotic Encryption based Remote Sensing Image Encryption(ISCACE-RSI)technique in IoT Environment.The proposed model follows a three-stage process,namely pre-processing,encryption,and optimal key generation.The remote sensing images were preprocessed at the initial stage to enhance the image quality.Next,the ISCACERSI technique exploits the double-layer remote sensing image encryption(DLRSIE)algorithm for encrypting the images.The DLRSIE methodology incorporates the design of Chaotic Maps and deoxyribonucleic acid(DNA)Strand Displacement(DNASD)approach.The chaotic map is employed for generating pseudorandom sequences and implementing routine scrambling and diffusion processes on the plaintext images.Then,the study presents three DNASD-related encryption rules based on the variety of DNASD,and those rules are applied for encrypting the images at the DNA sequence level.For an optimal key generation of the DLRSIE technique,the ISCA is applied with an objective function of the maximization of peak signal to noise ratio(PSNR).To examine the performance of the ISCACE-RSI model,a detailed set of simulations were conducted.The comparative study reported the better performance of the ISCACE-RSI model over other existing approaches.
基金Hunan University of Arts and Science provided doctoral research funding for this study (grant number 16BSQD23)Fund of Geography Subject ([2022]351)also provided funding.
文摘Recently,the convolutional neural network(CNN)has been dom-inant in studies on interpreting remote sensing images(RSI).However,it appears that training optimization strategies have received less attention in relevant research.To evaluate this problem,the author proposes a novel algo-rithm named the Fast Training CNN(FST-CNN).To verify the algorithm’s effectiveness,twenty methods,including six classic models and thirty archi-tectures from previous studies,are included in a performance comparison.The overall accuracy(OA)trained by the FST-CNN algorithm on the same model architecture and dataset is treated as an evaluation baseline.Results show that there is a maximal OA gap of 8.35%between the FST-CNN and those methods in the literature,which means a 10%margin in performance.Meanwhile,all those complex roadmaps,e.g.,deep feature fusion,model combination,model ensembles,and human feature engineering,are not as effective as expected.It reveals that there was systemic suboptimal perfor-mance in the previous studies.Most of the CNN-based methods proposed in the previous studies show a consistent mistake,which has made the model’s accuracy lower than its potential value.The most important reasons seem to be the inappropriate training strategy and the shift in data distribution introduced by data augmentation(DA).As a result,most of the performance evaluation was conducted based on an inaccurate,suboptimal,and unfair result.It has made most of the previous research findings questionable to some extent.However,all these confusing results also exactly demonstrate the effectiveness of FST-CNN.This novel algorithm is model-agnostic and can be employed on any image classification model to potentially boost performance.In addition,the results also show that a standardized training strategy is indeed very meaningful for the research tasks of the RSI-SC.
文摘Preserving biodiversity and maintaining ecological balance is essential in current environmental conditions.It is challenging to determine vegetation using traditional map classification approaches.The primary issue in detecting vegetation pattern is that it appears with complex spatial structures and similar spectral properties.It is more demandable to determine the multiple spectral ana-lyses for improving the accuracy of vegetation mapping through remotely sensed images.The proposed framework is developed with the idea of ensembling three effective strategies to produce a robust architecture for vegetation mapping.The architecture comprises three approaches,feature-based approach,region-based approach,and texture-based approach for classifying the vegetation area.The novel Deep Meta fusion model(DMFM)is created with a unique fusion frame-work of residual stacking of convolution layers with Unique covariate features(UCF),Intensity features(IF),and Colour features(CF).The overhead issues in GPU utilization during Convolution neural network(CNN)models are reduced here with a lightweight architecture.The system considers detailing feature areas to improve classification accuracy and reduce processing time.The proposed DMFM model achieved 99%accuracy,with a maximum processing time of 130 s.The training,testing,and validation losses are degraded to a significant level that shows the performance quality with the DMFM model.The system acts as a standard analysis platform for dynamic datasets since all three different fea-tures,such as Unique covariate features(UCF),Intensity features(IF),and Colour features(CF),are considered very well.
基金This research was supported by the National Natural Science Foundation of China(41977064)the National Key R&D Program of China(2021YFD1900700).
文摘Check dams are widely used on the Loess Plateau in China to control soil and water losses,develop agricultural land,and improve watershed ecology.Detailed information on the number and spatial distribution of check dams is critical for quantitatively evaluating hydrological and ecological effects and planning the construction of new dams.Thus,this study developed a check dam detection framework for broad areas from high-resolution remote sensing images using an ensemble approach of deep learning and geospatial analysis.First,we made a sample dataset of check dams using GaoFen-2(GF-2)and Google Earth images.Next,we evaluated five popular deep-learning-based object detectors,including Faster R-CNN,You Only Look Once(version 3)(YOLOv3),Cascade R-CNN,YOLOX,and VarifocalNet(VFNet),to identify the best one for check dam detection.Finally,we analyzed the location characteristics of the check dams and used geographical constraints to optimize the detection results.Precision,recall,average precision at intersection over union(IoU)threshold of 0.50(AP_(50)),IoU threshold of 0.75(AP_(75)),and average value for 10 IoU thresholds ranging from 0.50-0.95 with a 0.05 step(AP_(50-95)),and inference time were used to evaluate model performance.All the five deep learning networks could identify check dams quickly and accurately,with AP_(50-95),AP_(50),and AP_(75)values higher than 60.0%,90.0%,and 70.0%,respectively,except for YOLOv3.The VFNet had the best performance,followed by YOLOX.The proposed framework was tested in the Yanhe River Basin and yielded promising results,with a recall rate of 87.0%for 521 check dams.Furthermore,the geographic analysis deleted about 50%of the false detection boxes,increasing the identification accuracy of check dams from 78.6%to 87.6%.Simultaneously,this framework recognized 568 recently constructed check dams and small check dams not recorded in the known check dam survey datasets.The extraction results will support efficient watershed management and guide future studies on soil erosion in the Loess Plateau.
基金supported by the Shaanxi Province Soft Science Research Program (2022KRM034).
文摘Desert lakes are important wetland resources in the blown-sand area of western China and play a significant role in maintain-ing the regional ecological environment.However,large-scale coal mining in recent years has considerably impacted the deposition condition of several lakes.Rapid and accurate extraction of lake information based on satellite images is crucial for developing protective measures against desertification.However,the spatial resolution of these images often leads to mixed pixels near water boundaries,affecting extraction precision.Traditional pixel unmixing methods mainly obtain water coverage information in a mixed pixel,making it difficult to accurately describe the spatial distribution.In this paper,the cellular automata(CA)model was adopted in order to realize lake information extraction at a sub-pixel level.A mining area in Shenmu City,Shaanxi Province,China is selected as the research region,using the image of Sentinel-2 as the data source and the high spatial resolution UAV image as the reference.First,water coverage of mixed pixels in the Sentinel-2 image was calculated with the dimidiate pixel model and the fully constrained least squares(FCLS)method.Second,the mixed pixels were subdivided to form the cellular space at a sub-pixel level and the transition rules are constructed based on the water coverage information and spatial correlation.Lastly,the process was implemented using Python and IDL,with the ArcGIS and ENVI software being used for validation.The experiments show that the CA model can improve the sub-pixel positioning accuracy for lake bodies in mixed pixel image and improve classification accuracy.The FCLS-CA model has a higher accuracy and is able to identify most water bodies in the study area,and is therefore suitable for desert lake monitor-ing in mining areas.
基金This research has been supported by Doctoral Research funding from Hunan University of Arts and Science,Grant Number E07016033.
文摘Over the past decade,the significant growth of the convolutional neural network(CNN)based on deep learning(DL)approaches has greatly improved the machine learning(ML)algorithm’s performance on the semantic scene classification(SSC)of remote sensing images(RSI).However,the unbalanced attention to classification accuracy and efficiency has made the superiority of DL-based algorithms,e.g.,automation and simplicity,partially lost.Traditional ML strategies(e.g.,the handcrafted features or indicators)and accuracy-aimed strategies with a high trade-off(e.g.,the multi-stage CNNs and ensemble of multi-CNNs)are widely used without any training efficiency optimization involved,which may result in suboptimal performance.To address this problem,we propose a fast and simple training CNN framework(named FST-EfficientNet)for RSI-SSC based on an EfficientNetversion2 small(EfficientNetV2-S)CNN model.The whole algorithm flow is completely one-stage and end-to-end without any handcrafted features or discriminators introduced.In the implementation of training efficiency optimization,only several routine data augmentation tricks coupled with a fixed ratio of resolution or a gradually increasing resolution strategy are employed,so that the algorithm’s trade-off is very cheap.The performance evaluation shows that our FST-EfficientNet achieves new state-of-the-art(SOTA)records in the overall accuracy(OA)with about 0.8%to 2.7%ahead of all earlier methods on the Aerial Image Dataset(AID)and Northwestern Poly-technical University Remote Sensing Image Scene Classification 45 Dataset(NWPU-RESISC45D).Meanwhile,the results also demonstrate the importance and indispensability of training efficiency optimization strategies for RSI-SSC by DL.In fact,it is not necessary to gain better classification accuracy by completely relying on an excessive trade-off without efficiency.Ultimately,these findings are expected to contribute to the development of more efficient CNN-based approaches in RSI-SSC.
基金The National Natural Science Foundation of China under contract No.42071385the Shandong Natural Science Foundation under contract No.ZR2019MD041+1 种基金the Open Project Program of Shandong Marine Aerospace Equipment Technological Innovation Center,Ludong University under contract No.MAETIC2021-12the Yantai Science and Technology Innovation Development Plan Project under contract No.2022MSGY062。
文摘Outbreaks of Ulva prolifera have continued in the South Yellow Sea of China(SYS)since 2007,becoming a serious marine ecological disaster.Large amounts of U.prolifera drift to the coast of the Shandong Peninsula to dissipate under the action of southeast monsoons and ocean surface currents.This causes serious harm to the ecological environment and economic activities of coastal cities.To investigate the impact of U.prolifera dissipation,this study extracted the spatiotemporal distribution of U.prolifera in the SYS from 2012 to 2020 based on the Google Earth Engine.The outbreak cycle of U.prolifera was determined by fitting analysis of outbreak time and coverage area through MATLAB.This study also looked at the effect of U.prolifera dissipation on water quality through field monitoring data.The results showed that the growth curve of the U.prolifera has a significant Gaussian distribution.The U.prolifera dissipates in Haiyang,China,in July and August every year and affects the offshore environment.Water quality parameters of seawater at different depths had significant differences after the U.prolifera dissipation.Changes in pH,chemical oxygen demand,nitrite nitrogen,nitrate nitrogen,ammonia nitrogen,chlorophyll a,total phosphorus,and suspended solids were more significant in surface seawater than in deeper water.Changes in the concentrations of dissolved oxygen and total nitrogen were more significant in the deep seawater(1.63 and 1.1 times higher than those in the surface seawater,respectively).The dissipation of U.prolifera releases a large amount of carbon and nitrogen into the seawater,which provides rich nutrients for phytoplankton and may cause secondary disasters such as red tide.These findings are useful for further understanding the rules of U.prolifera dissipation,as well as preventing and controlling green tide disasters.
