To solve the problems in online target detection on the embedded platform,such as high missed detection rate,low accuracy,and slow speed,a lightweight target recognition method of MobileNetV3-CenterNet is proposed.Thi...To solve the problems in online target detection on the embedded platform,such as high missed detection rate,low accuracy,and slow speed,a lightweight target recognition method of MobileNetV3-CenterNet is proposed.This method combines the anchor-free Centernet network with the MobileNetV3 small network and is trained on the University at Albany Detection and Tracking(UA-DETRAC)and the Pattern Analysis,Statical Modeling and Computational Learn-ing Visual Object Classes(PASCAL VOC)07+12 standard datasets.While reducing the scale of the network model,the MobileNetV3-CenterNet model shows a good balance in the accuracy and speed of target recognition and effectively solves the problems of missing detection of dense and small targets in online detection.To verify the recognition performance of the model,it is tested on 2683 images of the UA-DETRAC and PASCAL VOC 07+12 datasets,and compared with the analysis results of CenterNet-Deep Layer Aggregation(DLA)34,CenterNet-Residual Network(ResNet)18,CenterNet-MobileNetV3-large,You Only Look Once vision 3(YOLOv3),MobileNetV2-YOLOv3,Single Shot Multibox Detector(SSD),MobileNetV2-SSD and Faster region convolutional neural network(RCNN)models.The results show that the MobileNetV3-CenterNet model accurately rec-ognized the dense targets and small targets missed by other methods,and obtained a recognition accuracy of 99.4%with a running speed at 53(on a server)and 14(on an ipad)frame/s,respectively.The MobileNetV3-CenterNet lightweight target recognition method will provide effective technical support for the target recognition of deep learning networks in embedded platforms and online detection.展开更多
The three-dimensional sensor networks are supposed to be deployed for many applications. So it is signifi-cant to do research on the problems of coverage and target detection in three-dimensional sensor networks. In t...The three-dimensional sensor networks are supposed to be deployed for many applications. So it is signifi-cant to do research on the problems of coverage and target detection in three-dimensional sensor networks. In this paper, we introduced Clifford algebra in 3D Euclidean space, developed the coverage model of 3D sensor networks based on Clifford algebra, and proposed a method for detecting target moving. With Clif-ford Spinor, calculating the target moving formulation is easier than traditional methods in sensor node’s coverage area.展开更多
Object detection plays an important role in the sorting process of mechanical fasteners.Although object detection has been studied for many years,it has always been an industrial problem.Edge-based model matching is o...Object detection plays an important role in the sorting process of mechanical fasteners.Although object detection has been studied for many years,it has always been an industrial problem.Edge-based model matching is only suitable for a small range of illumination changes,and the matching accuracy is low.The optical flow method and the difference method are sensitive to noise and light,and camshift tracking is less effective in complex backgrounds.In this paper,an improved target detection method based on YOLOv3-tiny is proposed.The redundant regression box generated by the prediction network is filtered by soft nonmaximum suppression(NMS)instead of the hard decision NMS algorithm.This not only increases the size of the network structure by 52×52 and improves the detection accuracy of small targets but also uses the basic structure block MobileNetv2 in the feature extraction network,which enhances the feature extraction ability with the increased network layer and improves network performance.The experimental results show that the improved YOLOv3-tiny target detection algorithm improves the detection ability of bolts,nuts,screws and gaskets.The accuracy of a single type has been improved,which shows that the network greatly enhances the ability to learn objects with slightly complex features.The detection result of single shape features is slightly improved,which is higher than the recognition accuracy of other types.The average accuracy is increased from 0.813 to 0.839,an increase of two percentage points.The recall rate is increased from 0.804 to 0.821.展开更多
The purpose of this paper is to develop a high speed detection scheme for moving and / or stationary point targets in a multitarget environment as registered in an IR image sequence. An iterative approximate 3-D line ...The purpose of this paper is to develop a high speed detection scheme for moving and / or stationary point targets in a multitarget environment as registered in an IR image sequence. An iterative approximate 3-D line searching algorithm based upon the geometric representation of lines (for non-maneuvering targets in space) in a 3-D space is derived. The convergency of the algorithm is proved. An analysis is performed of the theoretical detection performance of the algorithm. The statistical experiment results show high effectiveness and computational efficiency of the algorithm in the case of low SNR. The idea may be employed to satisfy the real-time processing requirement of an IR system.展开更多
The paper designs a peripheral maximum gray differ-ence(PMGD)image segmentation method,a connected-compo-nent labeling(CCL)algorithm based on dynamic run length(DRL),and a real-time implementation streaming processor ...The paper designs a peripheral maximum gray differ-ence(PMGD)image segmentation method,a connected-compo-nent labeling(CCL)algorithm based on dynamic run length(DRL),and a real-time implementation streaming processor for DRL-CCL.And it verifies the function and performance in space target monitoring scene by the carrying experiment of Tianzhou-3 cargo spacecraft(TZ-3).The PMGD image segmentation method can segment the image into highly discrete and simple point tar-gets quickly,which reduces the generation of equivalences greatly and improves the real-time performance for DRL-CCL.Through parallel pipeline design,the storage of the streaming processor is optimized by 55%with no need for external me-mory,the logic is optimized by 60%,and the energy efficiency ratio is 12 times than that of the graphics processing unit,62 times than that of the digital signal proccessing,and 147 times than that of personal computers.Analyzing the results of 8756 images completed on-orbit,the speed is up to 5.88 FPS and the target detection rate is 100%.Our algorithm and implementation method meet the requirements of lightweight,high real-time,strong robustness,full-time,and stable operation in space irradia-tion environment.展开更多
Recently,video-based fire detection technology has become an important research topic in the field of machine vision.This paper proposes a method of combining the classification model and target detection model in dee...Recently,video-based fire detection technology has become an important research topic in the field of machine vision.This paper proposes a method of combining the classification model and target detection model in deep learning for fire detection.Firstly,the depthwise separable convolution is used to classify fire images,which saves a lot of detection time under the premise of ensuring detection accuracy.Secondly,You Only Look Once version 3(YOLOv3)target regression function is used to output the fire position information for the images whose classification result is fire,which avoids the problem that the accuracy of detection cannot be guaranteed by using YOLOv3 for target classification and position regression.At the same time,the detection time of target regression for images without fire is greatly reduced saved.The experiments were tested using a network public database.The detection accuracy reached 98%and the detection rate reached 38fps.This method not only saves the workload of manually extracting flame characteristics,reduces the calculation cost,and reduces the amount of parameters,but also improves the detection accuracy and detection rate.展开更多
Complete and efficient detection of unknown targets is the most popular application of UAV swarms. Under most situations, targets have directional characteristics so that they can only be successfully detected within ...Complete and efficient detection of unknown targets is the most popular application of UAV swarms. Under most situations, targets have directional characteristics so that they can only be successfully detected within specific angles. In such cases, how to coordinate UAVs and allocate optimal paths for them to efficiently detect all the targets is the primary issue to be solved. In this paper, an intelligent target detection method is proposed for UAV swarms to achieve real-time detection requirements. First, a target-feature-information-based disintegration method is built up to divide the search space into a set of cubes. Theoretically, when the cubes are traversed, all the targets can be detected. Then, a Kuhn-Munkres(KM)-algorithm-based path planning method is proposed for UAVs to traverse the cubes. Finally, to further improve search efficiency, a 3 D realtime probability map is established over the search space which estimates the possibility of detecting new targets at each point. This map is adopted to modify the weights in KM algorithm, thereby optimizing the UAVs’ paths during the search process. Simulation results show that with the proposed method, all targets, with detection angle limitations, can be found by UAVs. Moreover, by implementing the 3 D probability map, the search efficiency is improved by 23.4%–78.1%.展开更多
This paper presents the cooperative strategies for salvo attack of multiple missiles based on the classical proportional navigation(PN) algorithm.The three-dimensional(3-D) guidance laws are developed in a quite s...This paper presents the cooperative strategies for salvo attack of multiple missiles based on the classical proportional navigation(PN) algorithm.The three-dimensional(3-D) guidance laws are developed in a quite simple formulation that consists of a PN component for target capture and a coordination component for simultaneous arrival.The centralized algorithms come into effect when the global information of time-to-go estimation is obtained, whereas the decentralized algorithms have better performance when each missile can only collect information from neighbors.Numerical simulations demonstrate that the proposed coordination algorithms are feasible to perform the cooperative engagement of multiple missiles against both stationary and maneuvering targets.The effectiveness of the 3-D guidance laws is also discussed.展开更多
Using the spatial coordinates of detection stations and the time of arrival of lightning wave, the observation equations can be expressed. For the large lightning detection network, the least square method is used to ...Using the spatial coordinates of detection stations and the time of arrival of lightning wave, the observation equations can be expressed. For the large lightning detection network, the least square method is used to process the adjustment of observation data to find the most probable value of lightning position, and the result is assessed by the mean error and dilution of precision. Lightning location precision is affected by figure factor. The conclusion can be used in the design of location network, data processing, and data analysis.展开更多
The image segmentation difficulties of small objects which are much smaller than their background often occur in target detection and recognition. The existing threshold segmentation methods almost fail under the circ...The image segmentation difficulties of small objects which are much smaller than their background often occur in target detection and recognition. The existing threshold segmentation methods almost fail under the circumstances. Thus, a threshold selection method is proposed on the basis of area difference between background and object and intra-class variance. The threshold selection formulae based on one-dimensional (1-D) histogram, two-dimensional (2-D) histogram vertical segmentation and 2-D histogram oblique segmentation are given. A fast recursive algorithm of threshold selection in 2-D histogram oblique segmentation is derived. The segmented images and processing time of the proposed method are given in experiments. It is compared with some fast algorithms, such as Otsu, maximum entropy and Fisher threshold selection methods. The experimental results show that the proposed method can effectively segment the small object images and has better anti-noise property.展开更多
基金supported by Research and Development Project of Key Core Technology and Common Technology in Shanxi Province(No.2020XXX009).
文摘To solve the problems in online target detection on the embedded platform,such as high missed detection rate,low accuracy,and slow speed,a lightweight target recognition method of MobileNetV3-CenterNet is proposed.This method combines the anchor-free Centernet network with the MobileNetV3 small network and is trained on the University at Albany Detection and Tracking(UA-DETRAC)and the Pattern Analysis,Statical Modeling and Computational Learn-ing Visual Object Classes(PASCAL VOC)07+12 standard datasets.While reducing the scale of the network model,the MobileNetV3-CenterNet model shows a good balance in the accuracy and speed of target recognition and effectively solves the problems of missing detection of dense and small targets in online detection.To verify the recognition performance of the model,it is tested on 2683 images of the UA-DETRAC and PASCAL VOC 07+12 datasets,and compared with the analysis results of CenterNet-Deep Layer Aggregation(DLA)34,CenterNet-Residual Network(ResNet)18,CenterNet-MobileNetV3-large,You Only Look Once vision 3(YOLOv3),MobileNetV2-YOLOv3,Single Shot Multibox Detector(SSD),MobileNetV2-SSD and Faster region convolutional neural network(RCNN)models.The results show that the MobileNetV3-CenterNet model accurately rec-ognized the dense targets and small targets missed by other methods,and obtained a recognition accuracy of 99.4%with a running speed at 53(on a server)and 14(on an ipad)frame/s,respectively.The MobileNetV3-CenterNet lightweight target recognition method will provide effective technical support for the target recognition of deep learning networks in embedded platforms and online detection.
文摘The three-dimensional sensor networks are supposed to be deployed for many applications. So it is signifi-cant to do research on the problems of coverage and target detection in three-dimensional sensor networks. In this paper, we introduced Clifford algebra in 3D Euclidean space, developed the coverage model of 3D sensor networks based on Clifford algebra, and proposed a method for detecting target moving. With Clif-ford Spinor, calculating the target moving formulation is easier than traditional methods in sensor node’s coverage area.
基金The authors gratefully acknowledge the support provided by the National Natural Science Foundation of China(No.U20A20265)。
文摘Object detection plays an important role in the sorting process of mechanical fasteners.Although object detection has been studied for many years,it has always been an industrial problem.Edge-based model matching is only suitable for a small range of illumination changes,and the matching accuracy is low.The optical flow method and the difference method are sensitive to noise and light,and camshift tracking is less effective in complex backgrounds.In this paper,an improved target detection method based on YOLOv3-tiny is proposed.The redundant regression box generated by the prediction network is filtered by soft nonmaximum suppression(NMS)instead of the hard decision NMS algorithm.This not only increases the size of the network structure by 52×52 and improves the detection accuracy of small targets but also uses the basic structure block MobileNetv2 in the feature extraction network,which enhances the feature extraction ability with the increased network layer and improves network performance.The experimental results show that the improved YOLOv3-tiny target detection algorithm improves the detection ability of bolts,nuts,screws and gaskets.The accuracy of a single type has been improved,which shows that the network greatly enhances the ability to learn objects with slightly complex features.The detection result of single shape features is slightly improved,which is higher than the recognition accuracy of other types.The average accuracy is increased from 0.813 to 0.839,an increase of two percentage points.The recall rate is increased from 0.804 to 0.821.
文摘The purpose of this paper is to develop a high speed detection scheme for moving and / or stationary point targets in a multitarget environment as registered in an IR image sequence. An iterative approximate 3-D line searching algorithm based upon the geometric representation of lines (for non-maneuvering targets in space) in a 3-D space is derived. The convergency of the algorithm is proved. An analysis is performed of the theoretical detection performance of the algorithm. The statistical experiment results show high effectiveness and computational efficiency of the algorithm in the case of low SNR. The idea may be employed to satisfy the real-time processing requirement of an IR system.
文摘The paper designs a peripheral maximum gray differ-ence(PMGD)image segmentation method,a connected-compo-nent labeling(CCL)algorithm based on dynamic run length(DRL),and a real-time implementation streaming processor for DRL-CCL.And it verifies the function and performance in space target monitoring scene by the carrying experiment of Tianzhou-3 cargo spacecraft(TZ-3).The PMGD image segmentation method can segment the image into highly discrete and simple point tar-gets quickly,which reduces the generation of equivalences greatly and improves the real-time performance for DRL-CCL.Through parallel pipeline design,the storage of the streaming processor is optimized by 55%with no need for external me-mory,the logic is optimized by 60%,and the energy efficiency ratio is 12 times than that of the graphics processing unit,62 times than that of the digital signal proccessing,and 147 times than that of personal computers.Analyzing the results of 8756 images completed on-orbit,the speed is up to 5.88 FPS and the target detection rate is 100%.Our algorithm and implementation method meet the requirements of lightweight,high real-time,strong robustness,full-time,and stable operation in space irradia-tion environment.
基金This work was supported by Liaoning Provincial Science Public Welfare Research Fund Project(No.2016002006)Liaoning Provincial Department of Education Scientific Research Service Local Project(No.L201708).
文摘Recently,video-based fire detection technology has become an important research topic in the field of machine vision.This paper proposes a method of combining the classification model and target detection model in deep learning for fire detection.Firstly,the depthwise separable convolution is used to classify fire images,which saves a lot of detection time under the premise of ensuring detection accuracy.Secondly,You Only Look Once version 3(YOLOv3)target regression function is used to output the fire position information for the images whose classification result is fire,which avoids the problem that the accuracy of detection cannot be guaranteed by using YOLOv3 for target classification and position regression.At the same time,the detection time of target regression for images without fire is greatly reduced saved.The experiments were tested using a network public database.The detection accuracy reached 98%and the detection rate reached 38fps.This method not only saves the workload of manually extracting flame characteristics,reduces the calculation cost,and reduces the amount of parameters,but also improves the detection accuracy and detection rate.
文摘Complete and efficient detection of unknown targets is the most popular application of UAV swarms. Under most situations, targets have directional characteristics so that they can only be successfully detected within specific angles. In such cases, how to coordinate UAVs and allocate optimal paths for them to efficiently detect all the targets is the primary issue to be solved. In this paper, an intelligent target detection method is proposed for UAV swarms to achieve real-time detection requirements. First, a target-feature-information-based disintegration method is built up to divide the search space into a set of cubes. Theoretically, when the cubes are traversed, all the targets can be detected. Then, a Kuhn-Munkres(KM)-algorithm-based path planning method is proposed for UAVs to traverse the cubes. Finally, to further improve search efficiency, a 3 D realtime probability map is established over the search space which estimates the possibility of detecting new targets at each point. This map is adopted to modify the weights in KM algorithm, thereby optimizing the UAVs’ paths during the search process. Simulation results show that with the proposed method, all targets, with detection angle limitations, can be found by UAVs. Moreover, by implementing the 3 D probability map, the search efficiency is improved by 23.4%–78.1%.
基金supported by the National Natural Science Foundation of China (Nos.61273349, 61203223)
文摘This paper presents the cooperative strategies for salvo attack of multiple missiles based on the classical proportional navigation(PN) algorithm.The three-dimensional(3-D) guidance laws are developed in a quite simple formulation that consists of a PN component for target capture and a coordination component for simultaneous arrival.The centralized algorithms come into effect when the global information of time-to-go estimation is obtained, whereas the decentralized algorithms have better performance when each missile can only collect information from neighbors.Numerical simulations demonstrate that the proposed coordination algorithms are feasible to perform the cooperative engagement of multiple missiles against both stationary and maneuvering targets.The effectiveness of the 3-D guidance laws is also discussed.
基金Supported by the National Key Technologies R&D Program of China (2008BAC36B00)
文摘Using the spatial coordinates of detection stations and the time of arrival of lightning wave, the observation equations can be expressed. For the large lightning detection network, the least square method is used to process the adjustment of observation data to find the most probable value of lightning position, and the result is assessed by the mean error and dilution of precision. Lightning location precision is affected by figure factor. The conclusion can be used in the design of location network, data processing, and data analysis.
基金Sponsored by The National Natural Science Foundation of China(60872065)Science and Technology on Electro-optic Control Laboratory and Aviation Science Foundation(20105152026)State Key Laboratory Open Fund of Novel Software Technology,Nanjing University(KFKT2010B17)
文摘The image segmentation difficulties of small objects which are much smaller than their background often occur in target detection and recognition. The existing threshold segmentation methods almost fail under the circumstances. Thus, a threshold selection method is proposed on the basis of area difference between background and object and intra-class variance. The threshold selection formulae based on one-dimensional (1-D) histogram, two-dimensional (2-D) histogram vertical segmentation and 2-D histogram oblique segmentation are given. A fast recursive algorithm of threshold selection in 2-D histogram oblique segmentation is derived. The segmented images and processing time of the proposed method are given in experiments. It is compared with some fast algorithms, such as Otsu, maximum entropy and Fisher threshold selection methods. The experimental results show that the proposed method can effectively segment the small object images and has better anti-noise property.