Longwall mining continues to remain the most efficient method for underground coal recovery. A key aspect in achieving safe and productive longwall mining is to ensure that the shearer is always correctly positioned w...Longwall mining continues to remain the most efficient method for underground coal recovery. A key aspect in achieving safe and productive longwall mining is to ensure that the shearer is always correctly positioned within the coal seam. At present, this machine positioning task is the role of longwall personnel who must simultaneously monitor the longwall coal face and the shearer's cutting drum position to infer the geological trends of the coal seam. This is a labour intensive task which has negative impacts on the consistency and quality of coal production. As a solution to this problem, this paper presents a sensing method to automatically track geological coal seam features on the longwall face, known as marker bands, using thermal infrared imaging. These non-visible marker bands are geological features that link strongly to the horizontal trends present in layered coal seams. Tracking these line-like features allows the generation of a vertical datum that can be used to maintain the shearer in a position for optimal coal extraction. Details on the theory of thermal infrared imaging are given, as well as practical aspects associated with machine-based implementation underground. The feature detection and tracking tasks are given with real measurements to demonstrate the efficacy of the approach. The outcome is important as it represents a new selective mining capability to help address a long-standing limitation in longwall mining operations.展开更多
Although compressive measurements save data storage and bandwidth usage, they are difficult to be used directly for target tracking and classification without pixel reconstruction. This is because the Gaussian random ...Although compressive measurements save data storage and bandwidth usage, they are difficult to be used directly for target tracking and classification without pixel reconstruction. This is because the Gaussian random matrix destroys the target location information in the original video frames. This paper summarizes our research effort on target tracking and classification directly in the compressive measurement domain. We focus on one particular type of compressive measurement using pixel subsampling. That is, original pixels in video frames are randomly subsampled. Even in such a special compressive sensing setting, conventional trackers do not work in a satisfactory manner. We propose a deep learning approach that integrates YOLO (You Only Look Once) and ResNet (residual network) for multiple target tracking and classification. YOLO is used for multiple target tracking and ResNet is for target classification. Extensive experiments using short wave infrared (SWIR), mid-wave infrared (MWIR), and long-wave infrared (LWIR) videos demonstrated the efficacy of the proposed approach even though the training data are very scarce.展开更多
A high precision, high antijamming multipoint infrared telemetry system was developed to measure the piston temperature in internal combustion engine. The temperature at the measuring point is converted into correspon...A high precision, high antijamming multipoint infrared telemetry system was developed to measure the piston temperature in internal combustion engine. The temperature at the measuring point is converted into corresponding voltage signal by the thermo-couple first. Then after the V/F stage, the voltage signal is converted into the frequency signal to drive the infrared light-emitting diode to transmit infrared pulses. At the receiver end, a photosensitive audion receives the infrared pulses. After conversion, the voltage recorded by the receiver stands for the magnitude of temperature at the measuring point. Test results of the system indicate that the system is practical and the system can perform multipoint looping temperature measurements for the piston.展开更多
While several studies have documented the large-scale, seasonal movements of horseshoe crabs, little is known about their fine-scale, daily movement patterns. In this study we used a fixed array ultrasonic telemetry s...While several studies have documented the large-scale, seasonal movements of horseshoe crabs, little is known about their fine-scale, daily movement patterns. In this study we used a fixed array ultrasonic telemetry system to track the movements of 12 male and 16 female horseshoe crabs in the Great Bay estuary, New Hampshire. Data were obtained during the mating season, as well as during the remainder of the summer and fall, in the years 2005-2008. During the mating season animals were often, but not always, active during the high tides when they were approaching and leaving the spawning beaches. On average, both males and females approached mating beaches during 33% of the high tides they experienced and they most often made the tran- sition from being inactive to active during the last two hours of an incoming tide. From April-October horseshoe crabs were significantly more active during high tide periods vs low tide periods, with no clear preference for diurnal vs nocturnal activity. After the mating season ended horseshoe crabs continued to move into shallower water at high tide and then return to deeper water at low tide. Observations by SCUBA divers suggest that during these excursions into the mudflats horseshoe crabs were digging pits in the sediment while foraging for food. Thus, the tidal rhythm of activity that has been so well documented during the mating season probably persists into the fall, and primarily involves foraging activities展开更多
Pixel-wise Code Exposure (PCE) camera is one type of compressive sensing camera that has low power consumption and high compression ratio. Moreover, a PCE camera can control individual pixel exposure time that can ena...Pixel-wise Code Exposure (PCE) camera is one type of compressive sensing camera that has low power consumption and high compression ratio. Moreover, a PCE camera can control individual pixel exposure time that can enable high dynamic range. Conventional approaches of using PCE camera involve a time consuming and lossy process to reconstruct the original frames and then use those frames for target tracking and classification. In this paper, we present a deep learning approach that directly performs target tracking and classification in the compressive measurement domain without any frame reconstruction. Our approach has two parts: tracking and classification. The tracking has been done using YOLO (You Only Look Once) and the classification is achieved using Residual Network (ResNet). Extensive experiments using mid-wave infrared (MWIR) and long-wave infrared (LWIR) videos demonstrated the efficacy of our proposed approach.展开更多
A pair of synchronous line-tracking robots based on STM32 are designed. Each robot is actually a small intelligent car with seven reflective infrared photoelectric sensors ST188 installed in the front to track the lin...A pair of synchronous line-tracking robots based on STM32 are designed. Each robot is actually a small intelligent car with seven reflective infrared photoelectric sensors ST188 installed in the front to track the line. Two rear wheels each driven by a moter are the driving wheels, while each rooter is driven by an H-bridge circuit. The running direction is con- trolled by the turning of a servo fastened to the front wheel and the adjustment of speed difference between the rear wheels. Besides, the light-adaptive line-tracking can be performed. The speeds of the motors are controlled by adjusting pulse-width modulation （PWM） values and an angular displacement transducer is used to detect the relative position of the cars in real time. Thus, the speeds of the cars can be adjusted in time so that the synchronism of the cars can be achieved. Through ex-periments, the fast and accurate synchronous tracking can be well realized.展开更多
In autonomous driving,target tracking is essential to environmental perception.The study of target tracking algorithms can improve the accuracy of an autonomous driving vehicle’s perception,which is of great signific...In autonomous driving,target tracking is essential to environmental perception.The study of target tracking algorithms can improve the accuracy of an autonomous driving vehicle’s perception,which is of great significance in ensuring the safety of autonomous driving and promoting the landing of technical applications.This study focuses on the fusion tracking algorithm based on visible and infrared images.The proposed approach utilizes a feature-level image fusion method,dividing the tracking process into two components:image fusion and target tracking.An unsupervised network,Visible and Infrared image Fusion Network(VIF-net),is employed for visible and infrared image fusion in the image fusion part.In the target tracking part,Siamese Region Proposal Network(SiamRPN),based on deep learning,tracks the target with fused images.The fusion tracking algorithm is trained and evaluated on the visible infrared image dataset RGBT234.Experimental results demonstrate that the algorithm outperforms training networks solely based on visible images,proving that the fusion of visible and infrared images in the target tracking algorithm can improve the accuracy of the target tracking even if it is like tracking-based visual images.This improvement is also attributed to the algorithm’s ability to extract infrared image features,augmenting the target tracking accuracy.展开更多
针对红外图像纹理弱及多目标遮挡导致跟踪精度低的问题,构建了基于改进YOLOv7模型和多目标跟踪算法DeepSort的融合红外目标跟踪模型MSB-YOLOv7-DeepSort。采用SE(squeeze and excitation)通道注意力机制和双向特征金字塔网络提高红外目...针对红外图像纹理弱及多目标遮挡导致跟踪精度低的问题,构建了基于改进YOLOv7模型和多目标跟踪算法DeepSort的融合红外目标跟踪模型MSB-YOLOv7-DeepSort。采用SE(squeeze and excitation)通道注意力机制和双向特征金字塔网络提高红外目标的特征提取质量;利用轻量化网络MobileNetV3替换YOLOv7骨干网络,提升融合模型的推理速度。实验结果表明,MSB-YOLOv7-DeepSort模型在跟踪准确度、跟踪精确度、正确目标跟踪比例和帧率等方面均具有较好的性能。展开更多
基金the Australian Coal Association Research Program(ACARP)for their invaluable support that enabled new research and development into longwall shearer automation
文摘Longwall mining continues to remain the most efficient method for underground coal recovery. A key aspect in achieving safe and productive longwall mining is to ensure that the shearer is always correctly positioned within the coal seam. At present, this machine positioning task is the role of longwall personnel who must simultaneously monitor the longwall coal face and the shearer's cutting drum position to infer the geological trends of the coal seam. This is a labour intensive task which has negative impacts on the consistency and quality of coal production. As a solution to this problem, this paper presents a sensing method to automatically track geological coal seam features on the longwall face, known as marker bands, using thermal infrared imaging. These non-visible marker bands are geological features that link strongly to the horizontal trends present in layered coal seams. Tracking these line-like features allows the generation of a vertical datum that can be used to maintain the shearer in a position for optimal coal extraction. Details on the theory of thermal infrared imaging are given, as well as practical aspects associated with machine-based implementation underground. The feature detection and tracking tasks are given with real measurements to demonstrate the efficacy of the approach. The outcome is important as it represents a new selective mining capability to help address a long-standing limitation in longwall mining operations.
文摘Although compressive measurements save data storage and bandwidth usage, they are difficult to be used directly for target tracking and classification without pixel reconstruction. This is because the Gaussian random matrix destroys the target location information in the original video frames. This paper summarizes our research effort on target tracking and classification directly in the compressive measurement domain. We focus on one particular type of compressive measurement using pixel subsampling. That is, original pixels in video frames are randomly subsampled. Even in such a special compressive sensing setting, conventional trackers do not work in a satisfactory manner. We propose a deep learning approach that integrates YOLO (You Only Look Once) and ResNet (residual network) for multiple target tracking and classification. YOLO is used for multiple target tracking and ResNet is for target classification. Extensive experiments using short wave infrared (SWIR), mid-wave infrared (MWIR), and long-wave infrared (LWIR) videos demonstrated the efficacy of the proposed approach even though the training data are very scarce.
文摘A high precision, high antijamming multipoint infrared telemetry system was developed to measure the piston temperature in internal combustion engine. The temperature at the measuring point is converted into corresponding voltage signal by the thermo-couple first. Then after the V/F stage, the voltage signal is converted into the frequency signal to drive the infrared light-emitting diode to transmit infrared pulses. At the receiver end, a photosensitive audion receives the infrared pulses. After conversion, the voltage recorded by the receiver stands for the magnitude of temperature at the measuring point. Test results of the system indicate that the system is practical and the system can perform multipoint looping temperature measurements for the piston.
基金supported by NSF IOB 0517229 and NSF IOS 0920342 grants to WHW Ⅲ and CCC
文摘While several studies have documented the large-scale, seasonal movements of horseshoe crabs, little is known about their fine-scale, daily movement patterns. In this study we used a fixed array ultrasonic telemetry system to track the movements of 12 male and 16 female horseshoe crabs in the Great Bay estuary, New Hampshire. Data were obtained during the mating season, as well as during the remainder of the summer and fall, in the years 2005-2008. During the mating season animals were often, but not always, active during the high tides when they were approaching and leaving the spawning beaches. On average, both males and females approached mating beaches during 33% of the high tides they experienced and they most often made the tran- sition from being inactive to active during the last two hours of an incoming tide. From April-October horseshoe crabs were significantly more active during high tide periods vs low tide periods, with no clear preference for diurnal vs nocturnal activity. After the mating season ended horseshoe crabs continued to move into shallower water at high tide and then return to deeper water at low tide. Observations by SCUBA divers suggest that during these excursions into the mudflats horseshoe crabs were digging pits in the sediment while foraging for food. Thus, the tidal rhythm of activity that has been so well documented during the mating season probably persists into the fall, and primarily involves foraging activities
文摘Pixel-wise Code Exposure (PCE) camera is one type of compressive sensing camera that has low power consumption and high compression ratio. Moreover, a PCE camera can control individual pixel exposure time that can enable high dynamic range. Conventional approaches of using PCE camera involve a time consuming and lossy process to reconstruct the original frames and then use those frames for target tracking and classification. In this paper, we present a deep learning approach that directly performs target tracking and classification in the compressive measurement domain without any frame reconstruction. Our approach has two parts: tracking and classification. The tracking has been done using YOLO (You Only Look Once) and the classification is achieved using Residual Network (ResNet). Extensive experiments using mid-wave infrared (MWIR) and long-wave infrared (LWIR) videos demonstrated the efficacy of our proposed approach.
文摘A pair of synchronous line-tracking robots based on STM32 are designed. Each robot is actually a small intelligent car with seven reflective infrared photoelectric sensors ST188 installed in the front to track the line. Two rear wheels each driven by a moter are the driving wheels, while each rooter is driven by an H-bridge circuit. The running direction is con- trolled by the turning of a servo fastened to the front wheel and the adjustment of speed difference between the rear wheels. Besides, the light-adaptive line-tracking can be performed. The speeds of the motors are controlled by adjusting pulse-width modulation （PWM） values and an angular displacement transducer is used to detect the relative position of the cars in real time. Thus, the speeds of the cars can be adjusted in time so that the synchronism of the cars can be achieved. Through ex-periments, the fast and accurate synchronous tracking can be well realized.
基金The National Natural Science Foundation of China funded this research(Grant Nos.52072214 and 52242213).
文摘In autonomous driving,target tracking is essential to environmental perception.The study of target tracking algorithms can improve the accuracy of an autonomous driving vehicle’s perception,which is of great significance in ensuring the safety of autonomous driving and promoting the landing of technical applications.This study focuses on the fusion tracking algorithm based on visible and infrared images.The proposed approach utilizes a feature-level image fusion method,dividing the tracking process into two components:image fusion and target tracking.An unsupervised network,Visible and Infrared image Fusion Network(VIF-net),is employed for visible and infrared image fusion in the image fusion part.In the target tracking part,Siamese Region Proposal Network(SiamRPN),based on deep learning,tracks the target with fused images.The fusion tracking algorithm is trained and evaluated on the visible infrared image dataset RGBT234.Experimental results demonstrate that the algorithm outperforms training networks solely based on visible images,proving that the fusion of visible and infrared images in the target tracking algorithm can improve the accuracy of the target tracking even if it is like tracking-based visual images.This improvement is also attributed to the algorithm’s ability to extract infrared image features,augmenting the target tracking accuracy.
文摘针对红外图像纹理弱及多目标遮挡导致跟踪精度低的问题,构建了基于改进YOLOv7模型和多目标跟踪算法DeepSort的融合红外目标跟踪模型MSB-YOLOv7-DeepSort。采用SE(squeeze and excitation)通道注意力机制和双向特征金字塔网络提高红外目标的特征提取质量;利用轻量化网络MobileNetV3替换YOLOv7骨干网络,提升融合模型的推理速度。实验结果表明,MSB-YOLOv7-DeepSort模型在跟踪准确度、跟踪精确度、正确目标跟踪比例和帧率等方面均具有较好的性能。
