Aiming at the problem of low accuracy of traditional target detection methods for target detection in endoscopes in substation environments, a CNN-based real-time detection method for masked targets is proposed. The m...Aiming at the problem of low accuracy of traditional target detection methods for target detection in endoscopes in substation environments, a CNN-based real-time detection method for masked targets is proposed. The method adopts the overall design of backbone network, detection network and algorithmic parameter optimisation method, completes the model training on the self-constructed occlusion target dataset, and adopts the multi-scale perception method for target detection. The HNM algorithm is used to screen positive and negative samples during the training process, and the NMS algorithm is used to post-process the prediction results during the detection process to improve the detection efficiency. After experimental validation, the obtained model has the multi-class average predicted value (mAP) of the dataset. It has general advantages over traditional target detection methods. The detection time of a single target on FDDB dataset is 39 ms, which can meet the need of real-time target detection. In addition, the project team has successfully deployed the method into substations and put it into use in many places in Beijing, which is important for achieving the anomaly of occlusion target detection.展开更多
Timely acquisition of rescue target information is critical for emergency response after a flood disaster.Unmanned Aerial Vehicles(UAVs)equipped with remote sensing capabilities offer distinct advantages,including hig...Timely acquisition of rescue target information is critical for emergency response after a flood disaster.Unmanned Aerial Vehicles(UAVs)equipped with remote sensing capabilities offer distinct advantages,including high-resolution imagery and exceptional mobility,making them well suited for monitoring flood extent and identifying rescue targets during floods.However,there are some challenges in interpreting rescue information in real time from flood images captured by UAVs,such as the complexity of the scenarios of UAV images,the lack of flood rescue target detection datasets and the limited real-time processing capabilities of the airborne on-board platform.Thus,we propose a real-time rescue target detection method for UAVs that is capable of efficiently delineating flood extent and identifying rescue targets(i.e.,pedestrians and vehicles trapped by floods).The proposed method achieves real-time rescue information extraction for UAV platforms by lightweight processing and fusion of flood extent extraction model and target detection model.The flood inundation range is extracted by the proposed method in real time and detects targets such as people and vehicles to be rescued based on this layer.Our experimental results demonstrate that the Intersection over Union(IoU)for flood water extraction reaches an impressive 80%,and the IoU for real-time flood water extraction stands at a commendable 76.4%.The information on flood stricken targets extracted by this method in real time can be used for flood emergency rescue.展开更多
To address the challenges of high complexity,poor real-time performance,and low detection rates for small target vehicles in existing vehicle object detection algorithms,this paper proposes a real-time lightweight arc...To address the challenges of high complexity,poor real-time performance,and low detection rates for small target vehicles in existing vehicle object detection algorithms,this paper proposes a real-time lightweight architecture based on You Only Look Once(YOLO)v5m.Firstly,a lightweight upsampling operator called Content-Aware Reassembly of Features(CARAFE)is introduced in the feature fusion layer of the network to maximize the extraction of deep-level features for small target vehicles,reducing the missed detection rate and false detection rate.Secondly,a new prediction layer for tiny targets is added,and the feature fusion network is redesigned to enhance the detection capability for small targets.Finally,this paper applies L1 regularization to train the improved network,followed by pruning and fine-tuning operations to remove redundant channels,reducing computational and parameter complexity and enhancing the detection efficiency of the network.Training is conducted on the VisDrone2019-DET dataset.The experimental results show that the proposed algorithmreduces parameters and computation by 63.8% and 65.8%,respectively.The average detection accuracy improves by 5.15%,and the detection speed reaches 47 images per second,satisfying real-time requirements.Compared with existing approaches,including YOLOv5m and classical vehicle detection algorithms,our method achieves higher accuracy and faster speed for real-time detection of small target vehicles in edge computing.展开更多
The real-time detection and instance segmentation of strawberries constitute fundamental components in the development of strawberry harvesting robots.Real-time identification of strawberries in an unstructured envi-r...The real-time detection and instance segmentation of strawberries constitute fundamental components in the development of strawberry harvesting robots.Real-time identification of strawberries in an unstructured envi-ronment is a challenging task.Current instance segmentation algorithms for strawberries suffer from issues such as poor real-time performance and low accuracy.To this end,the present study proposes an Efficient YOLACT(E-YOLACT)algorithm for strawberry detection and segmentation based on the YOLACT framework.The key enhancements of the E-YOLACT encompass the development of a lightweight attention mechanism,pyramid squeeze shuffle attention(PSSA),for efficient feature extraction.Additionally,an attention-guided context-feature pyramid network(AC-FPN)is employed instead of FPN to optimize the architecture’s performance.Furthermore,a feature-enhanced model(FEM)is introduced to enhance the prediction head’s capabilities,while efficient fast non-maximum suppression(EF-NMS)is devised to improve non-maximum suppression.The experimental results demonstrate that the E-YOLACT achieves a Box-mAP and Mask-mAP of 77.9 and 76.6,respectively,on the custom dataset.Moreover,it exhibits an impressive category accuracy of 93.5%.Notably,the E-YOLACT also demonstrates a remarkable real-time detection capability with a speed of 34.8 FPS.The method proposed in this article presents an efficient approach for the vision system of a strawberry-picking robot.展开更多
The advancement of navigation systems for the visually impaired has significantly enhanced their mobility by mitigating the risk of encountering obstacles and guiding them along safe,navigable routes.Traditional appro...The advancement of navigation systems for the visually impaired has significantly enhanced their mobility by mitigating the risk of encountering obstacles and guiding them along safe,navigable routes.Traditional approaches primarily focus on broad applications such as wayfinding,obstacle detection,and fall prevention.However,there is a notable discrepancy in applying these technologies to more specific scenarios,like identifying distinct food crop types or recognizing faces.This study proposes a real-time application designed for visually impaired individuals,aiming to bridge this research-application gap.It introduces a system capable of detecting 20 different food crop types and recognizing faces with impressive accuracies of 83.27%and 95.64%,respectively.These results represent a significant contribution to the field of assistive technologies,providing visually impaired users with detailed and relevant information about their surroundings,thereby enhancing their mobility and ensuring their safety.Additionally,it addresses the vital aspects of social engagements,acknowledging the challenges faced by visually impaired individuals in recognizing acquaintances without auditory or tactile signals,and highlights recent developments in prototype systems aimed at assisting with face recognition tasks.This comprehensive approach not only promises enhanced navigational aids but also aims to enrich the social well-being and safety of visually impaired communities.展开更多
Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance o...Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance of robotic applications in terms of accuracy and speed.This research proposed a real-time indoor camera localization system based on a recurrent neural network that detects scene change during the image sequence.An annotated image dataset trains the proposed system and predicts the camera pose in real-time.The system mainly improved the localization performance of indoor cameras by more accurately predicting the camera pose.It also recognizes the scene changes during the sequence and evaluates the effects of these changes.This system achieved high accuracy and real-time performance.The scene change detection process was performed using visual rhythm and the proposed recurrent deep architecture,which performed camera pose prediction and scene change impact evaluation.Overall,this study proposed a novel real-time localization system for indoor cameras that detects scene changes and shows how they affect localization performance.展开更多
Traffic sign detection in real scenarios is challenging due to their complexity and small size,often preventing existing deep learning models from achieving both high accuracy and real-time performance.An improved YOL...Traffic sign detection in real scenarios is challenging due to their complexity and small size,often preventing existing deep learning models from achieving both high accuracy and real-time performance.An improved YOLOv8 model for traffic sign detection is proposed.Firstly,by adding Coordinate Attention(CA)to the Backbone,the model gains location information,improving detection accuracy.Secondly,we also introduce EIoU to the localization function to address the ambiguity in aspect ratio descriptions by calculating the width-height difference based on CIoU.Additionally,Focal Loss is incorporated to balance sample difficulty,enhancing regression accuracy.Finally,the model,YOLOv8-CE(YOLOv8-Coordinate Attention-EIoU),is tested on the Jetson Nano,achieving real-time street scene detection and outperforming the Raspberry Pi 4B.Experimental results show that YOLOv8-CE excels in various complex scenarios,improving mAP by 2.8%over the original YOLOv8.The model size and computational effort remain similar,with the Jetson Nano achieving an inference time of 96 ms,significantly faster than the Raspberry Pi 4B.展开更多
Under the influence of air humidity,dust,aerosols,etc.,in real scenes,haze presents an uneven state.In this way,the image quality and contrast will decrease.In this case,It is difficult to detect the target in the ima...Under the influence of air humidity,dust,aerosols,etc.,in real scenes,haze presents an uneven state.In this way,the image quality and contrast will decrease.In this case,It is difficult to detect the target in the image by the universal detection network.Thus,a dual subnet based on multi-task collaborative training(DSMCT)is proposed in this paper.Firstly,in the training phase,the Gated Context Aggregation Network(GCANet)is used as the supervisory network of YOLOX to promote the extraction of clean information in foggy scenes.In the test phase,only the YOLOX branch needs to be activated to ensure the detection speed of the model.Secondly,the deformable convolution module is used to improve GCANet to enhance the model’s ability to capture details of non-homogeneous fog.Finally,the Coordinate Attention mechanism is introduced into the Vision Transformer and the backbone network of YOLOX is redesigned.In this way,the feature extraction ability of the network for deep-level information can be enhanced.The experimental results on artificial fog data set FOG_VOC and real fog data set RTTS show that the map value of DSMCT reached 86.56%and 62.39%,respectively,which was 2.27%and 4.41%higher than the current most advanced detection model.The DSMCT network has high practicality and effectiveness for target detection in real foggy scenes.展开更多
Addressing the challenges in detecting surface floating litter in artificial lakes,including complex environments,uneven illumination,and susceptibility to noise andweather,this paper proposes an efficient and lightwe...Addressing the challenges in detecting surface floating litter in artificial lakes,including complex environments,uneven illumination,and susceptibility to noise andweather,this paper proposes an efficient and lightweight Ghost-YOLO(You Only Look Once)v8 algorithm.The algorithmintegrates advanced attention mechanisms and a smalltarget detection head to significantly enhance detection performance and efficiency.Firstly,an SE(Squeeze-and-Excitation)mechanism is incorporated into the backbone network to fortify the extraction of resilient features and precise target localization.This mechanism models feature channel dependencies,enabling adaptive adjustment of channel importance,thereby improving recognition of floating litter targets.Secondly,a 160×160 small-target detection layer is designed in the feature fusion neck to mitigate semantic information loss due to varying target scales.This design enhances the fusion of deep and shallow semantic information,improving small target feature representation and enabling better capture and identification of tiny floating litter.Thirdly,to balance performance and efficiency,the GhostConv module replaces part of the conventional convolutions in the feature fusion neck.Additionally,a novel C2fGhost(CSPDarknet53 to 2-Stage Feature Pyramid Networks Ghost)module is introduced to further reduce network parameters.Lastly,to address the challenge of occlusion,a newloss function,WIoU(Wise Intersection over Union)v3 incorporating a flexible and non-monotonic concentration approach,is adopted to improve detection rates for surface floating litter.The outcomes of the experiments demonstrate that the Ghost-YOLO v8 model proposed in this paper performs well in the dataset Marine,significantly enhances precision and recall by 3.3 and 7.6 percentage points,respectively,in contrast with the base model,mAP@0.5 and mAP 0.5:0.95 improve by 5.3 and 4.4 percentage points and reduces the computational volume by 1.88MB,the FPS value hardly decreases,and the efficient real-time identification of floating debris on the water’s surface can be achieved costeffectively.展开更多
In this paper,a comprehensive overview of radar detection methods for low-altitude targets in maritime environments is presented,focusing on the challenges posed by sea clutter and multipath scattering.The performance...In this paper,a comprehensive overview of radar detection methods for low-altitude targets in maritime environments is presented,focusing on the challenges posed by sea clutter and multipath scattering.The performance of the radar detection methods under sea clutter,multipath,and combined conditions is categorized and summarized,and future research directions are outlined to enhance radar detection performance for low-altitude targets in maritime environments.展开更多
This paper expounds upon a novel target detection methodology distinguished by its elevated discriminatory efficacy,specifically tailored for environments characterized by markedly low luminance levels.Conventional me...This paper expounds upon a novel target detection methodology distinguished by its elevated discriminatory efficacy,specifically tailored for environments characterized by markedly low luminance levels.Conventional methodologies struggle with the challenges posed by luminosity fluctuations,especially in settings characterized by diminished radiance,further exacerbated by the utilization of suboptimal imaging instrumentation.The envisioned approach mandates a departure from the conventional YOLOX model,which exhibits inadequacies in mitigating these challenges.To enhance the efficacy of this approach in low-light conditions,the dehazing algorithm undergoes refinement,effecting a discerning regulation of the transmission rate at the pixel level,reducing it to values below 0.5,thereby resulting in an augmentation of image contrast.Subsequently,the coiflet wavelet transform is employed to discern and isolate high-discriminatory attributes by dismantling low-frequency image attributes and extracting high-frequency attributes across divergent axes.The utilization of CycleGAN serves to elevate the features of low-light imagery across an array of stylistic variances.Advanced computational methodologies are then employed to amalgamate and conflate intricate attributes originating from images characterized by distinct stylistic orientations,thereby augmenting the model’s erudition potential.Empirical validation conducted on the PASCAL VOC and MS COCO 2017 datasets substantiates pronounced advancements.The refined low-light enhancement algorithm yields a discernible 5.9%augmentation in the target detection evaluation index when compared to the original imagery.Mean Average Precision(mAP)undergoes enhancements of 9.45%and 0.052%in low-light visual renditions relative to conventional YOLOX outcomes.The envisaged approach presents a myriad of advantages over prevailing benchmark methodologies in the realm of target detection within environments marked by an acute scarcity of luminosity.展开更多
Object detection finds wide application in various sectors,including autonomous driving,industry,and healthcare.Recent studies have highlighted the vulnerability of object detection models built using deep neural netw...Object detection finds wide application in various sectors,including autonomous driving,industry,and healthcare.Recent studies have highlighted the vulnerability of object detection models built using deep neural networks when confronted with carefully crafted adversarial examples.This not only reveals their shortcomings in defending against malicious attacks but also raises widespread concerns about the security of existing systems.Most existing adversarial attack strategies focus primarily on image classification problems,failing to fully exploit the unique characteristics of object detectionmodels,thus resulting in widespread deficiencies in their transferability.Furthermore,previous research has predominantly concentrated on the transferability issues of non-targeted attacks,whereas enhancing the transferability of targeted adversarial examples presents even greater challenges.Traditional attack techniques typically employ cross-entropy as a loss measure,iteratively adjusting adversarial examples to match target categories.However,their inherent limitations restrict their broad applicability and transferability across different models.To address the aforementioned challenges,this study proposes a novel targeted adversarial attack method aimed at enhancing the transferability of adversarial samples across object detection models.Within the framework of iterative attacks,we devise a new objective function designed to mitigate consistency issues arising from cumulative noise and to enhance the separation between target and non-target categories(logit margin).Secondly,a data augmentation framework incorporating random erasing and color transformations is introduced into targeted adversarial attacks.This enhances the diversity of gradients,preventing overfitting to white-box models.Lastly,perturbations are applied only within the specified object’s bounding box to reduce the perturbation range,enhancing attack stealthiness.Experiments were conducted on the Microsoft Common Objects in Context(MS COCO)dataset using You Only Look Once version 3(YOLOv3),You Only Look Once version 8(YOLOv8),Faster Region-based Convolutional Neural Networks(Faster R-CNN),and RetinaNet.The results demonstrate a significant advantage of the proposed method in black-box settings.Among these,the success rate of RetinaNet transfer attacks reached a maximum of 82.59%.展开更多
In this paper,a detection method combining Cameron decomposition based on polarization scattering characteristics in sea clutter background is proposed.Firstly,the Cameron decomposition is exploited to fuse the radar ...In this paper,a detection method combining Cameron decomposition based on polarization scattering characteristics in sea clutter background is proposed.Firstly,the Cameron decomposition is exploited to fuse the radar echoes of full polarization channels at the data level.Due to the artificial material structure on the surface of the target,it can be shown that the non-reciprocity of the target cell is stronger than that of the clutter cell.Then,based on the analysis of the decomposition results,a new feature with scattering geometry characteristics in polarization domain,denoted as Cameron polarization decomposition scattering weight(CPD-SW),is extracted as the test statistic,which can achieve more detailed descriptions of the clutter scattering characteristics utilizing the difference between their scattering types.Finally,the superiority of the proposed CPD-SW detector over traditional detectors in improving detection performance is verified by the IPIX measured dataset,which has strong stability under short-time observation in threshold detection and can also improve the separability of feature space zin anomaly detection.展开更多
In order to address the problem of high false alarm rate and low probabilities of infrared small target detection in complex low-altitude background,an infrared small target detection method based on improved weighted...In order to address the problem of high false alarm rate and low probabilities of infrared small target detection in complex low-altitude background,an infrared small target detection method based on improved weighted local contrast is proposed in this paper.First,the ratio information between the target and local background is utilized as an enhancement factor.The local contrast is calculated by incorporating the heterogeneity between the target and local background.Then,a local product weighted method is designed based on the spatial dissimilarity between target and background to further enhance target while suppressing background.Finally,the location of target is obtained by adaptive threshold segmentation.As experimental results demonstrate,the method shows superior performance in several evaluation metrics compared with six existing algorithms on different datasets containing targets such as unmanned aerial vehicles(UAV).展开更多
Infrared small target detection technology plays a pivotal role in critical military applications,including early warning systems and precision guidance for missiles and other defense mechanisms.Nevertheless,existing ...Infrared small target detection technology plays a pivotal role in critical military applications,including early warning systems and precision guidance for missiles and other defense mechanisms.Nevertheless,existing traditional methods face several significant challenges,including low background suppression ability,low detection rates,and high false alarm rates when identifying infrared small targets in complex environments.This paper proposes a novel infrared small target detection method based on a transformed Gaussian filter kernel and clustering approach.The method provides improved background suppression and detection accuracy compared to traditional techniques while maintaining simplicity and lower computational costs.In the first step,the infrared image is filtered by a new filter kernel and the results of filtering are normalized.In the second step,an adaptive thresholding method is utilized to determine the pixels in small targets.In the final step,a fuzzy C-mean clustering algorithm is employed to group pixels in the same target,thus yielding the detection results.The results obtained from various real infrared image datasets demonstrate the superiority of the proposed method over traditional approaches.Compared with the traditional method of state of the arts detection method,the detection accuracy of the four sequences is increased by 2.06%,0.95%,1.03%,and 1.01%,respectively,and the false alarm rate is reduced,thus providing a more effective and robust solution.展开更多
To address the challenges of missed detections in water surface target detection using solely visual algorithms in unmanned surface vehicle(USV)perception,this paper proposes a method based on the fusion of visual and...To address the challenges of missed detections in water surface target detection using solely visual algorithms in unmanned surface vehicle(USV)perception,this paper proposes a method based on the fusion of visual and LiDAR point-cloud projection for water surface target detection.Firstly,the visual recognition component employs an improved YOLOv7 algorithmbased on a self-built dataset for the detection of water surface targets.This algorithm modifies the original YOLOv7 architecture to a Slim-Neck structure,addressing the problemof excessive redundant information during feature extraction in the original YOLOv7 network model.Simultaneously,this modification simplifies the computational burden of the detector,reduces inference time,and maintains accuracy.Secondly,to tackle the issue of sample imbalance in the self-built dataset,slide loss function is introduced.Finally,this paper replaces the original Complete Intersection over Union(CIoU)loss function with the Minimum Point Distance Intersection over Union(MPDIoU)loss function in the YOLOv7 algorithm,which accelerates model learning and enhances robustness.To mitigate the problem of missed recognitions caused by complex water surface conditions in purely visual algorithms,this paper further adopts the fusion of LiDAR and camera data,projecting the threedimensional point-cloud data from LiDAR onto a two-dimensional pixel plane.This significantly reduces the rate of missed detections for water surface targets.展开更多
This paper focuses on the adaptive detection of range and Doppler dual-spread targets in non-homogeneous and nonGaussian sea clutter.The sea clutter from two polarimetric channels is modeled as a compound-Gaussian mod...This paper focuses on the adaptive detection of range and Doppler dual-spread targets in non-homogeneous and nonGaussian sea clutter.The sea clutter from two polarimetric channels is modeled as a compound-Gaussian model with different parameters,and the target is modeled as a subspace rangespread target model.The persymmetric structure is used to model the clutter covariance matrix,in order to reduce the reliance on secondary data of the designed detectors.Three adaptive polarimetric persymmetric detectors are designed based on the generalized likelihood ratio test(GLRT),Rao test,and Wald test.All the proposed detectors have constant falsealarm rate property with respect to the clutter texture,the speckle covariance matrix.Experimental results on simulated and measured data show that three adaptive detectors outperform the competitors in different clutter environments,and the proposed GLRT detector has the best detection performance under different parameters.展开更多
In order to solve the problems that the current synthetic aperture radar(SAR)image target detection method cannot adapt to targets of different sizes,and the complex image background leads to low detection accuracy,an...In order to solve the problems that the current synthetic aperture radar(SAR)image target detection method cannot adapt to targets of different sizes,and the complex image background leads to low detection accuracy,an improved SAR image small target detection method based on YOLOv7 was proposed in this study.The proposed method improved the feature extraction network by using Switchable Around Convolution(SAConv)in the backbone network to help the model capture target information at different scales,thus improving the feature extraction ability for small targets.Based on the attention mechanism,the DyHead module was embedded in the target detection head to reduce the impact of complex background,and better focus on the small targets.In addition,the NWD loss function was introduced and combined with CIoU loss.Compared to the CIoU loss function typically used in YOLOv7,the NWD loss function pays more attention to the processing of small targets,so as to further improve the detection ability of small targets.The experimental results on the HRSID dataset indicate that the proposed method achieved mAP@0.5 and mAP@0.95 scores of 93.5%and 71.5%,respectively.Compared to the baseline model,this represents an increase of 7.2%and 7.6%,respectively.The proposed method can effectively complete the task of SAR image small target detection.展开更多
The detection of hypersonic targets usually confronts range migration(RM)issue before coherent integration(CI).The traditional methods aiming at correcting RM to obtain CI mainly considers the narrow-band radar condit...The detection of hypersonic targets usually confronts range migration(RM)issue before coherent integration(CI).The traditional methods aiming at correcting RM to obtain CI mainly considers the narrow-band radar condition.However,with the increasing requirement of far-range detection,the time bandwidth product,which is corresponding to radar’s mean power,should be promoted in actual application.Thus,the echo signal generates the scale effect(SE)at large time bandwidth product situation,influencing the intra and inter pulse integration performance.To eliminate SE and correct RM,this paper proposes an effective algorithm,i.e.,scaled location rotation transform(ScLRT).The ScLRT can remove SE to obtain the matching pulse compression(PC)as well as correct RM to complete CI via the location rotation transform,being implemented by seeking the actual rotation angle.Compared to the traditional coherent detection algorithms,Sc LRT can address the SE problem to achieve better detection/estimation capabilities.At last,this paper gives several simulations to assess the viability of ScLRT.展开更多
The Unintentional Insider Threat (UIT) concept highlights that insider threats might not always stem from malicious intent and can occur across various domains. This research examines how individuals with medical or p...The Unintentional Insider Threat (UIT) concept highlights that insider threats might not always stem from malicious intent and can occur across various domains. This research examines how individuals with medical or psychological issues might unintentionally become insider threats due to their perception of being targeted. Insights from the survey A Survey of Unintentional Medical Insider Threat Category indicate that such perceptions can be linked to underlying health conditions. The study Emotion Analysis Based on Belief of Targeted Individual Supporting Insider Threat Detection reveals that anger is a common emotion among these individuals. The findings suggest that UITs are often linked to medical or psychological issues, with anger being prevalent. To mitigate these risks, it is recommended that Insider Threat programs integrate expertise from medicine, psychology, and cybersecurity. Additionally, handwriting analysis is proposed as a potential tool for detecting insider threats, reflecting the evolving nature of threat assessment methodologies.展开更多
文摘Aiming at the problem of low accuracy of traditional target detection methods for target detection in endoscopes in substation environments, a CNN-based real-time detection method for masked targets is proposed. The method adopts the overall design of backbone network, detection network and algorithmic parameter optimisation method, completes the model training on the self-constructed occlusion target dataset, and adopts the multi-scale perception method for target detection. The HNM algorithm is used to screen positive and negative samples during the training process, and the NMS algorithm is used to post-process the prediction results during the detection process to improve the detection efficiency. After experimental validation, the obtained model has the multi-class average predicted value (mAP) of the dataset. It has general advantages over traditional target detection methods. The detection time of a single target on FDDB dataset is 39 ms, which can meet the need of real-time target detection. In addition, the project team has successfully deployed the method into substations and put it into use in many places in Beijing, which is important for achieving the anomaly of occlusion target detection.
基金National Natural Science Foundation of China(No.42271416)Guangxi Science and Technology Major Project(No.AA22068072)Shennongjia National Park Resources Comprehensive Investigation Research Project(No.SNJNP2023015).
文摘Timely acquisition of rescue target information is critical for emergency response after a flood disaster.Unmanned Aerial Vehicles(UAVs)equipped with remote sensing capabilities offer distinct advantages,including high-resolution imagery and exceptional mobility,making them well suited for monitoring flood extent and identifying rescue targets during floods.However,there are some challenges in interpreting rescue information in real time from flood images captured by UAVs,such as the complexity of the scenarios of UAV images,the lack of flood rescue target detection datasets and the limited real-time processing capabilities of the airborne on-board platform.Thus,we propose a real-time rescue target detection method for UAVs that is capable of efficiently delineating flood extent and identifying rescue targets(i.e.,pedestrians and vehicles trapped by floods).The proposed method achieves real-time rescue information extraction for UAV platforms by lightweight processing and fusion of flood extent extraction model and target detection model.The flood inundation range is extracted by the proposed method in real time and detects targets such as people and vehicles to be rescued based on this layer.Our experimental results demonstrate that the Intersection over Union(IoU)for flood water extraction reaches an impressive 80%,and the IoU for real-time flood water extraction stands at a commendable 76.4%.The information on flood stricken targets extracted by this method in real time can be used for flood emergency rescue.
基金funded by the General Project of Key Research and Develop-ment Plan of Shaanxi Province(No.2022NY-087).
文摘To address the challenges of high complexity,poor real-time performance,and low detection rates for small target vehicles in existing vehicle object detection algorithms,this paper proposes a real-time lightweight architecture based on You Only Look Once(YOLO)v5m.Firstly,a lightweight upsampling operator called Content-Aware Reassembly of Features(CARAFE)is introduced in the feature fusion layer of the network to maximize the extraction of deep-level features for small target vehicles,reducing the missed detection rate and false detection rate.Secondly,a new prediction layer for tiny targets is added,and the feature fusion network is redesigned to enhance the detection capability for small targets.Finally,this paper applies L1 regularization to train the improved network,followed by pruning and fine-tuning operations to remove redundant channels,reducing computational and parameter complexity and enhancing the detection efficiency of the network.Training is conducted on the VisDrone2019-DET dataset.The experimental results show that the proposed algorithmreduces parameters and computation by 63.8% and 65.8%,respectively.The average detection accuracy improves by 5.15%,and the detection speed reaches 47 images per second,satisfying real-time requirements.Compared with existing approaches,including YOLOv5m and classical vehicle detection algorithms,our method achieves higher accuracy and faster speed for real-time detection of small target vehicles in edge computing.
基金funded by Anhui Provincial Natural Science Foundation(No.2208085ME128)the Anhui University-Level Special Project of Anhui University of Science and Technology(No.XCZX2021-01)+1 种基金the Research and the Development Fund of the Institute of Environmental Friendly Materials and Occupational Health,Anhui University of Science and Technology(No.ALW2022YF06)Anhui Province New Era Education Quality Project(Graduate Education)(No.2022xscx073).
文摘The real-time detection and instance segmentation of strawberries constitute fundamental components in the development of strawberry harvesting robots.Real-time identification of strawberries in an unstructured envi-ronment is a challenging task.Current instance segmentation algorithms for strawberries suffer from issues such as poor real-time performance and low accuracy.To this end,the present study proposes an Efficient YOLACT(E-YOLACT)algorithm for strawberry detection and segmentation based on the YOLACT framework.The key enhancements of the E-YOLACT encompass the development of a lightweight attention mechanism,pyramid squeeze shuffle attention(PSSA),for efficient feature extraction.Additionally,an attention-guided context-feature pyramid network(AC-FPN)is employed instead of FPN to optimize the architecture’s performance.Furthermore,a feature-enhanced model(FEM)is introduced to enhance the prediction head’s capabilities,while efficient fast non-maximum suppression(EF-NMS)is devised to improve non-maximum suppression.The experimental results demonstrate that the E-YOLACT achieves a Box-mAP and Mask-mAP of 77.9 and 76.6,respectively,on the custom dataset.Moreover,it exhibits an impressive category accuracy of 93.5%.Notably,the E-YOLACT also demonstrates a remarkable real-time detection capability with a speed of 34.8 FPS.The method proposed in this article presents an efficient approach for the vision system of a strawberry-picking robot.
基金supported by theKorea Industrial Technology Association(KOITA)Grant Funded by the Korean government(MSIT)(No.KOITA-2023-3-003)supported by the MSIT(Ministry of Science and ICT),Korea,under the ITRC(Information Technology Research Center)Support Program(IITP-2024-2020-0-01808)Supervised by the IITP(Institute of Information&Communications Technology Planning&Evaluation)。
文摘The advancement of navigation systems for the visually impaired has significantly enhanced their mobility by mitigating the risk of encountering obstacles and guiding them along safe,navigable routes.Traditional approaches primarily focus on broad applications such as wayfinding,obstacle detection,and fall prevention.However,there is a notable discrepancy in applying these technologies to more specific scenarios,like identifying distinct food crop types or recognizing faces.This study proposes a real-time application designed for visually impaired individuals,aiming to bridge this research-application gap.It introduces a system capable of detecting 20 different food crop types and recognizing faces with impressive accuracies of 83.27%and 95.64%,respectively.These results represent a significant contribution to the field of assistive technologies,providing visually impaired users with detailed and relevant information about their surroundings,thereby enhancing their mobility and ensuring their safety.Additionally,it addresses the vital aspects of social engagements,acknowledging the challenges faced by visually impaired individuals in recognizing acquaintances without auditory or tactile signals,and highlights recent developments in prototype systems aimed at assisting with face recognition tasks.This comprehensive approach not only promises enhanced navigational aids but also aims to enrich the social well-being and safety of visually impaired communities.
文摘Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance of robotic applications in terms of accuracy and speed.This research proposed a real-time indoor camera localization system based on a recurrent neural network that detects scene change during the image sequence.An annotated image dataset trains the proposed system and predicts the camera pose in real-time.The system mainly improved the localization performance of indoor cameras by more accurately predicting the camera pose.It also recognizes the scene changes during the sequence and evaluates the effects of these changes.This system achieved high accuracy and real-time performance.The scene change detection process was performed using visual rhythm and the proposed recurrent deep architecture,which performed camera pose prediction and scene change impact evaluation.Overall,this study proposed a novel real-time localization system for indoor cameras that detects scene changes and shows how they affect localization performance.
基金supported by Heilongjiang Provincial Natural Science Foundation of China(LH2023E055)the National Key R&D Program of China(2021YFB2600502).
文摘Traffic sign detection in real scenarios is challenging due to their complexity and small size,often preventing existing deep learning models from achieving both high accuracy and real-time performance.An improved YOLOv8 model for traffic sign detection is proposed.Firstly,by adding Coordinate Attention(CA)to the Backbone,the model gains location information,improving detection accuracy.Secondly,we also introduce EIoU to the localization function to address the ambiguity in aspect ratio descriptions by calculating the width-height difference based on CIoU.Additionally,Focal Loss is incorporated to balance sample difficulty,enhancing regression accuracy.Finally,the model,YOLOv8-CE(YOLOv8-Coordinate Attention-EIoU),is tested on the Jetson Nano,achieving real-time street scene detection and outperforming the Raspberry Pi 4B.Experimental results show that YOLOv8-CE excels in various complex scenarios,improving mAP by 2.8%over the original YOLOv8.The model size and computational effort remain similar,with the Jetson Nano achieving an inference time of 96 ms,significantly faster than the Raspberry Pi 4B.
基金This work was jointly supported by the Special Fund for Transformation and Upgrade of Jiangsu Industry and Information Industry-Key Core Technologies(Equipment)Key Industrialization Projects in 2022(No.CMHI-2022-RDG-004):“Key Technology Research for Development of Intelligent Wind Power Operation and Maintenance Mothership in Deep Sea”.
文摘Under the influence of air humidity,dust,aerosols,etc.,in real scenes,haze presents an uneven state.In this way,the image quality and contrast will decrease.In this case,It is difficult to detect the target in the image by the universal detection network.Thus,a dual subnet based on multi-task collaborative training(DSMCT)is proposed in this paper.Firstly,in the training phase,the Gated Context Aggregation Network(GCANet)is used as the supervisory network of YOLOX to promote the extraction of clean information in foggy scenes.In the test phase,only the YOLOX branch needs to be activated to ensure the detection speed of the model.Secondly,the deformable convolution module is used to improve GCANet to enhance the model’s ability to capture details of non-homogeneous fog.Finally,the Coordinate Attention mechanism is introduced into the Vision Transformer and the backbone network of YOLOX is redesigned.In this way,the feature extraction ability of the network for deep-level information can be enhanced.The experimental results on artificial fog data set FOG_VOC and real fog data set RTTS show that the map value of DSMCT reached 86.56%and 62.39%,respectively,which was 2.27%and 4.41%higher than the current most advanced detection model.The DSMCT network has high practicality and effectiveness for target detection in real foggy scenes.
基金Supported by the fund of the Henan Province Science and Technology Research Project(No.242102210213).
文摘Addressing the challenges in detecting surface floating litter in artificial lakes,including complex environments,uneven illumination,and susceptibility to noise andweather,this paper proposes an efficient and lightweight Ghost-YOLO(You Only Look Once)v8 algorithm.The algorithmintegrates advanced attention mechanisms and a smalltarget detection head to significantly enhance detection performance and efficiency.Firstly,an SE(Squeeze-and-Excitation)mechanism is incorporated into the backbone network to fortify the extraction of resilient features and precise target localization.This mechanism models feature channel dependencies,enabling adaptive adjustment of channel importance,thereby improving recognition of floating litter targets.Secondly,a 160×160 small-target detection layer is designed in the feature fusion neck to mitigate semantic information loss due to varying target scales.This design enhances the fusion of deep and shallow semantic information,improving small target feature representation and enabling better capture and identification of tiny floating litter.Thirdly,to balance performance and efficiency,the GhostConv module replaces part of the conventional convolutions in the feature fusion neck.Additionally,a novel C2fGhost(CSPDarknet53 to 2-Stage Feature Pyramid Networks Ghost)module is introduced to further reduce network parameters.Lastly,to address the challenge of occlusion,a newloss function,WIoU(Wise Intersection over Union)v3 incorporating a flexible and non-monotonic concentration approach,is adopted to improve detection rates for surface floating litter.The outcomes of the experiments demonstrate that the Ghost-YOLO v8 model proposed in this paper performs well in the dataset Marine,significantly enhances precision and recall by 3.3 and 7.6 percentage points,respectively,in contrast with the base model,mAP@0.5 and mAP 0.5:0.95 improve by 5.3 and 4.4 percentage points and reduces the computational volume by 1.88MB,the FPS value hardly decreases,and the efficient real-time identification of floating debris on the water’s surface can be achieved costeffectively.
基金supported by the National Natural Science Foundation of China(62171447)。
文摘In this paper,a comprehensive overview of radar detection methods for low-altitude targets in maritime environments is presented,focusing on the challenges posed by sea clutter and multipath scattering.The performance of the radar detection methods under sea clutter,multipath,and combined conditions is categorized and summarized,and future research directions are outlined to enhance radar detection performance for low-altitude targets in maritime environments.
基金supported by National Sciences Foundation of China Grants(No.61902158).
文摘This paper expounds upon a novel target detection methodology distinguished by its elevated discriminatory efficacy,specifically tailored for environments characterized by markedly low luminance levels.Conventional methodologies struggle with the challenges posed by luminosity fluctuations,especially in settings characterized by diminished radiance,further exacerbated by the utilization of suboptimal imaging instrumentation.The envisioned approach mandates a departure from the conventional YOLOX model,which exhibits inadequacies in mitigating these challenges.To enhance the efficacy of this approach in low-light conditions,the dehazing algorithm undergoes refinement,effecting a discerning regulation of the transmission rate at the pixel level,reducing it to values below 0.5,thereby resulting in an augmentation of image contrast.Subsequently,the coiflet wavelet transform is employed to discern and isolate high-discriminatory attributes by dismantling low-frequency image attributes and extracting high-frequency attributes across divergent axes.The utilization of CycleGAN serves to elevate the features of low-light imagery across an array of stylistic variances.Advanced computational methodologies are then employed to amalgamate and conflate intricate attributes originating from images characterized by distinct stylistic orientations,thereby augmenting the model’s erudition potential.Empirical validation conducted on the PASCAL VOC and MS COCO 2017 datasets substantiates pronounced advancements.The refined low-light enhancement algorithm yields a discernible 5.9%augmentation in the target detection evaluation index when compared to the original imagery.Mean Average Precision(mAP)undergoes enhancements of 9.45%and 0.052%in low-light visual renditions relative to conventional YOLOX outcomes.The envisaged approach presents a myriad of advantages over prevailing benchmark methodologies in the realm of target detection within environments marked by an acute scarcity of luminosity.
文摘Object detection finds wide application in various sectors,including autonomous driving,industry,and healthcare.Recent studies have highlighted the vulnerability of object detection models built using deep neural networks when confronted with carefully crafted adversarial examples.This not only reveals their shortcomings in defending against malicious attacks but also raises widespread concerns about the security of existing systems.Most existing adversarial attack strategies focus primarily on image classification problems,failing to fully exploit the unique characteristics of object detectionmodels,thus resulting in widespread deficiencies in their transferability.Furthermore,previous research has predominantly concentrated on the transferability issues of non-targeted attacks,whereas enhancing the transferability of targeted adversarial examples presents even greater challenges.Traditional attack techniques typically employ cross-entropy as a loss measure,iteratively adjusting adversarial examples to match target categories.However,their inherent limitations restrict their broad applicability and transferability across different models.To address the aforementioned challenges,this study proposes a novel targeted adversarial attack method aimed at enhancing the transferability of adversarial samples across object detection models.Within the framework of iterative attacks,we devise a new objective function designed to mitigate consistency issues arising from cumulative noise and to enhance the separation between target and non-target categories(logit margin).Secondly,a data augmentation framework incorporating random erasing and color transformations is introduced into targeted adversarial attacks.This enhances the diversity of gradients,preventing overfitting to white-box models.Lastly,perturbations are applied only within the specified object’s bounding box to reduce the perturbation range,enhancing attack stealthiness.Experiments were conducted on the Microsoft Common Objects in Context(MS COCO)dataset using You Only Look Once version 3(YOLOv3),You Only Look Once version 8(YOLOv8),Faster Region-based Convolutional Neural Networks(Faster R-CNN),and RetinaNet.The results demonstrate a significant advantage of the proposed method in black-box settings.Among these,the success rate of RetinaNet transfer attacks reached a maximum of 82.59%.
基金supported by the National Natural Science Foundation of China(62201251)the Natural Science Foundation of the Jiangsu Higher Education Institutions of China(22KJB510024)the Open Fund for the Hangzhou Institute of Technology Academician Workstation at Xidian University(XH-KY-202306-0291)。
文摘In this paper,a detection method combining Cameron decomposition based on polarization scattering characteristics in sea clutter background is proposed.Firstly,the Cameron decomposition is exploited to fuse the radar echoes of full polarization channels at the data level.Due to the artificial material structure on the surface of the target,it can be shown that the non-reciprocity of the target cell is stronger than that of the clutter cell.Then,based on the analysis of the decomposition results,a new feature with scattering geometry characteristics in polarization domain,denoted as Cameron polarization decomposition scattering weight(CPD-SW),is extracted as the test statistic,which can achieve more detailed descriptions of the clutter scattering characteristics utilizing the difference between their scattering types.Finally,the superiority of the proposed CPD-SW detector over traditional detectors in improving detection performance is verified by the IPIX measured dataset,which has strong stability under short-time observation in threshold detection and can also improve the separability of feature space zin anomaly detection.
基金supported by the National Natural Science Foundation of China (No.U1833203),the National Natural Science Foundation of China (No.62301036)the Aviation Science Foundation (No.2020Z019055001)China Postdoctoral Science Foundation Funded Project (No.2022M720446)。
文摘In order to address the problem of high false alarm rate and low probabilities of infrared small target detection in complex low-altitude background,an infrared small target detection method based on improved weighted local contrast is proposed in this paper.First,the ratio information between the target and local background is utilized as an enhancement factor.The local contrast is calculated by incorporating the heterogeneity between the target and local background.Then,a local product weighted method is designed based on the spatial dissimilarity between target and background to further enhance target while suppressing background.Finally,the location of target is obtained by adaptive threshold segmentation.As experimental results demonstrate,the method shows superior performance in several evaluation metrics compared with six existing algorithms on different datasets containing targets such as unmanned aerial vehicles(UAV).
基金supported by the Funding of Jiangsu University of Science and Technology,under the grant number:1132921208.
文摘Infrared small target detection technology plays a pivotal role in critical military applications,including early warning systems and precision guidance for missiles and other defense mechanisms.Nevertheless,existing traditional methods face several significant challenges,including low background suppression ability,low detection rates,and high false alarm rates when identifying infrared small targets in complex environments.This paper proposes a novel infrared small target detection method based on a transformed Gaussian filter kernel and clustering approach.The method provides improved background suppression and detection accuracy compared to traditional techniques while maintaining simplicity and lower computational costs.In the first step,the infrared image is filtered by a new filter kernel and the results of filtering are normalized.In the second step,an adaptive thresholding method is utilized to determine the pixels in small targets.In the final step,a fuzzy C-mean clustering algorithm is employed to group pixels in the same target,thus yielding the detection results.The results obtained from various real infrared image datasets demonstrate the superiority of the proposed method over traditional approaches.Compared with the traditional method of state of the arts detection method,the detection accuracy of the four sequences is increased by 2.06%,0.95%,1.03%,and 1.01%,respectively,and the false alarm rate is reduced,thus providing a more effective and robust solution.
基金supported by the National Natural Science Foundation of China(No.51876114)the Shanghai Engineering Research Center of Marine Renewable Energy(Grant No.19DZ2254800).
文摘To address the challenges of missed detections in water surface target detection using solely visual algorithms in unmanned surface vehicle(USV)perception,this paper proposes a method based on the fusion of visual and LiDAR point-cloud projection for water surface target detection.Firstly,the visual recognition component employs an improved YOLOv7 algorithmbased on a self-built dataset for the detection of water surface targets.This algorithm modifies the original YOLOv7 architecture to a Slim-Neck structure,addressing the problemof excessive redundant information during feature extraction in the original YOLOv7 network model.Simultaneously,this modification simplifies the computational burden of the detector,reduces inference time,and maintains accuracy.Secondly,to tackle the issue of sample imbalance in the self-built dataset,slide loss function is introduced.Finally,this paper replaces the original Complete Intersection over Union(CIoU)loss function with the Minimum Point Distance Intersection over Union(MPDIoU)loss function in the YOLOv7 algorithm,which accelerates model learning and enhances robustness.To mitigate the problem of missed recognitions caused by complex water surface conditions in purely visual algorithms,this paper further adopts the fusion of LiDAR and camera data,projecting the threedimensional point-cloud data from LiDAR onto a two-dimensional pixel plane.This significantly reduces the rate of missed detections for water surface targets.
基金supported by the National Natural Science Foundation of China(62371382,62071346)the Science,Technology&Innovation Project of Xiong’an New Area(2022XAGG0181)the Special Funds for Creative Research(2022C61540)。
文摘This paper focuses on the adaptive detection of range and Doppler dual-spread targets in non-homogeneous and nonGaussian sea clutter.The sea clutter from two polarimetric channels is modeled as a compound-Gaussian model with different parameters,and the target is modeled as a subspace rangespread target model.The persymmetric structure is used to model the clutter covariance matrix,in order to reduce the reliance on secondary data of the designed detectors.Three adaptive polarimetric persymmetric detectors are designed based on the generalized likelihood ratio test(GLRT),Rao test,and Wald test.All the proposed detectors have constant falsealarm rate property with respect to the clutter texture,the speckle covariance matrix.Experimental results on simulated and measured data show that three adaptive detectors outperform the competitors in different clutter environments,and the proposed GLRT detector has the best detection performance under different parameters.
文摘In order to solve the problems that the current synthetic aperture radar(SAR)image target detection method cannot adapt to targets of different sizes,and the complex image background leads to low detection accuracy,an improved SAR image small target detection method based on YOLOv7 was proposed in this study.The proposed method improved the feature extraction network by using Switchable Around Convolution(SAConv)in the backbone network to help the model capture target information at different scales,thus improving the feature extraction ability for small targets.Based on the attention mechanism,the DyHead module was embedded in the target detection head to reduce the impact of complex background,and better focus on the small targets.In addition,the NWD loss function was introduced and combined with CIoU loss.Compared to the CIoU loss function typically used in YOLOv7,the NWD loss function pays more attention to the processing of small targets,so as to further improve the detection ability of small targets.The experimental results on the HRSID dataset indicate that the proposed method achieved mAP@0.5 and mAP@0.95 scores of 93.5%and 71.5%,respectively.Compared to the baseline model,this represents an increase of 7.2%and 7.6%,respectively.The proposed method can effectively complete the task of SAR image small target detection.
基金supported by the National Natural Science Foundation of China(62101099)the Chinese Postdoctoral Science Foundation(2021M690558,2022T150100,2018M633352,2019T120825)+3 种基金the Young Elite Scientist Sponsorship Program(YESS20200082)the Aeronautical Science Foundation of China(2022Z017080001)the Open Foundation of Science and Technology on Electronic Information Control Laboratorythe Natural Science Foundation of Sichuan Province(2023NSFSC1386)。
文摘The detection of hypersonic targets usually confronts range migration(RM)issue before coherent integration(CI).The traditional methods aiming at correcting RM to obtain CI mainly considers the narrow-band radar condition.However,with the increasing requirement of far-range detection,the time bandwidth product,which is corresponding to radar’s mean power,should be promoted in actual application.Thus,the echo signal generates the scale effect(SE)at large time bandwidth product situation,influencing the intra and inter pulse integration performance.To eliminate SE and correct RM,this paper proposes an effective algorithm,i.e.,scaled location rotation transform(ScLRT).The ScLRT can remove SE to obtain the matching pulse compression(PC)as well as correct RM to complete CI via the location rotation transform,being implemented by seeking the actual rotation angle.Compared to the traditional coherent detection algorithms,Sc LRT can address the SE problem to achieve better detection/estimation capabilities.At last,this paper gives several simulations to assess the viability of ScLRT.
文摘The Unintentional Insider Threat (UIT) concept highlights that insider threats might not always stem from malicious intent and can occur across various domains. This research examines how individuals with medical or psychological issues might unintentionally become insider threats due to their perception of being targeted. Insights from the survey A Survey of Unintentional Medical Insider Threat Category indicate that such perceptions can be linked to underlying health conditions. The study Emotion Analysis Based on Belief of Targeted Individual Supporting Insider Threat Detection reveals that anger is a common emotion among these individuals. The findings suggest that UITs are often linked to medical or psychological issues, with anger being prevalent. To mitigate these risks, it is recommended that Insider Threat programs integrate expertise from medicine, psychology, and cybersecurity. Additionally, handwriting analysis is proposed as a potential tool for detecting insider threats, reflecting the evolving nature of threat assessment methodologies.
