基于视觉的手部位姿估计技术应用于诸多领域,具备着广泛的国际应用市场前景和巨大发展潜力。然而,手部自身存在检测目标过小、手指高自由度以及手部自遮挡等问题。通过对目前存在的难点分析,将手部位姿估计任务分为手部检测和手部关键...基于视觉的手部位姿估计技术应用于诸多领域,具备着广泛的国际应用市场前景和巨大发展潜力。然而,手部自身存在检测目标过小、手指高自由度以及手部自遮挡等问题。通过对目前存在的难点分析,将手部位姿估计任务分为手部检测和手部关键点检测,提出基于改进的Faster R-CNN的手部位姿估计方法。首先提出基于改进的Faster R-CNN手部检测网络,将传统Faster R-CNN网络中的对ROI(regional of interest)的最大值池化,更改为ROI Align,并增加损失函数用于区分左右手。在此基础上增加了头网络分支用以训练输出MANO(hand model with articulated and non-rigid deformations)手部模型的姿态参数和形状参数,得到手部关键点三维坐标,最终得到手部的三维位姿估计结果。实验表明,手部检测结果中存在的自遮挡和尺度问题得到了解决,并且检测结果的准确性有所提高,本文手部检测算法准确率为85%,比传统Faster R-CNN算法提升13%。手部关键点提取算法在MSRA、ICVL、NYU三个数据集分别取得关键点坐标的均方误差值(key-point mean square error,KMSE)为7.50、6.32、8.50的结果。展开更多
Ocean internal waves appear as irregular bright and dark stripes on synthetic aperture radar(SAR)remote sensing images.Ocean internal waves detection in SAR images consequently constituted a difficult and popular rese...Ocean internal waves appear as irregular bright and dark stripes on synthetic aperture radar(SAR)remote sensing images.Ocean internal waves detection in SAR images consequently constituted a difficult and popular research topic.In this paper,ocean internal waves are detected in SAR images by employing the faster regions with convolutional neural network features(Faster R-CNN)framework;for this purpose,888 internal wave samples are utilized to train the convolutional network and identify internal waves.The experimental results demonstrate a 94.78%recognition rate for internal waves,and the average detection speed is 0.22 s/image.In addition,the detection results of internal wave samples under different conditions are analyzed.This paper lays a foundation for detecting ocean internal waves using convolutional neural networks.展开更多
针对扶梯运行时光照的变化、阴影、背景中固定对象的移动等因素严重影响机器视觉检测精度问题,为了提高对扶梯乘客位姿目标的检测精度和效率,采用VGG16卷积神经网络作为Faster-RCNN(Faster-Regions with CNN features)的基础网络,提出...针对扶梯运行时光照的变化、阴影、背景中固定对象的移动等因素严重影响机器视觉检测精度问题,为了提高对扶梯乘客位姿目标的检测精度和效率,采用VGG16卷积神经网络作为Faster-RCNN(Faster-Regions with CNN features)的基础网络,提出基于改进Faster R-CNN的扶梯乘客异常位姿实时检测改进算法。首先Faster R-CNN对视频图像进行全卷积操作得到特征图,再通过RPN层得到被测对象的类别分数以及对象物体所在原图中所在的位置,利用Faster R-CNN算法处理后的图像得到扶梯上乘客诸如下蹲、身体弯曲等异常位姿,从而判断乘客是否处于危险状态。实验结果表明:FasterR-CNN的检测算法能准确实时地识别出扶梯乘客的危险位姿,从而实现控制系统及时做出相应的安全保护措施,提高自动扶梯运行的安全性能。展开更多
In order to solve the problem of small objects detection in unmanned aerial vehicle(UAV)aerial images with complex background,a general detection method for multi-scale small objects based on Faster region-based convo...In order to solve the problem of small objects detection in unmanned aerial vehicle(UAV)aerial images with complex background,a general detection method for multi-scale small objects based on Faster region-based convolutional neural network(Faster R-CNN)is proposed.The bird’s nest on the high-voltage tower is taken as the research object.Firstly,we use the improved convolutional neural network ResNet101 to extract object features,and then use multi-scale sliding windows to obtain the object region proposals on the convolution feature maps with different resolutions.Finally,a deconvolution operation is added to further enhance the selected feature map with higher resolution,and then it taken as a feature mapping layer of the region proposals passing to the object detection sub-network.The detection results of the bird’s nest in UAV aerial images show that the proposed method can precisely detect small objects in aerial images.展开更多
Rod insulators are vital parts of the catenary of high speed railways(HSRs).There are many different catenary insulators,and the background of the insulator image is complicated.It is difficult to recognise insulators...Rod insulators are vital parts of the catenary of high speed railways(HSRs).There are many different catenary insulators,and the background of the insulator image is complicated.It is difficult to recognise insulators and detect defects automatically.In this paper,we propose a catenary intelligent defect detection algorithm based on Mask region-convolutional neural network(R-CNN)and an image processing model.Vertical projection technology is used to achieve single shed positioning and precise cutting of the insulator.Gradient,texture,and gray feature fusion(GTGFF)and a K-means clustering analysis model(KCAM)are proposed to detect broken insulators,dirt,foreign bodies,and flashover.Using this model,insulator recognition and defect detection can achieve a high recall rate and accuracy,and generalized defect detection.The algorithm is tested and verified on a dataset of realistic insulator images,and the accuracy and reliability of the algorithm satisfy current requirements for HSR catenary automatic inspection and intelligent maintenance.展开更多
This study aims to detect and prevent greening disease in citrus trees using a deep neural network.The process of collecting data on citrus greening disease is very difficult because the vector pests are too small.In ...This study aims to detect and prevent greening disease in citrus trees using a deep neural network.The process of collecting data on citrus greening disease is very difficult because the vector pests are too small.In this paper,since the amount of data collected for deep learning is insufficient,we intend to use the efficient feature extraction function of the neural network based on the Transformer algorithm.We want to use the Cascade Region-based Convolutional Neural Networks(Cascade R-CNN)Swin model,which is a mixture of the transformer model and Cascade R-CNN model to detect greening disease occurring in citrus.In this paper,we try to improve model safety by establishing a linear relationship between samples using Mixup and Cutmix algorithms,which are image processing-based data augmentation techniques.In addition,by using the ImageNet dataset,transfer learning,and stochastic weight averaging(SWA)methods,more accuracy can be obtained.This study compared the Faster Region-based Convolutional Neural Networks Residual Network101(Faster R-CNN ResNet101)model,Cascade Regionbased Convolutional Neural Networks Residual Network101(Cascade RCNN-ResNet101)model,and Cascade R-CNN Swin Model.As a result,the Faster R-CNN ResNet101 model came out as Average Precision(AP)(Intersection over Union(IoU)=0.5):88.2%,AP(IoU=0.75):62.8%,Recall:68.2%,and the Cascade R-CNN ResNet101 model was AP(IoU=0.5):91.5%,AP(IoU=0.75):67.2%,Recall:73.1%.Alternatively,the Cascade R-CNN Swin Model showed AP(IoU=0.5):94.9%,AP(IoU=0.75):79.8%and Recall:76.5%.Thus,the Cascade R-CNN Swin Model showed the best results for detecting citrus greening disease.展开更多
In order to improve the accuracy of threaded hole object detection,combining a dual camera vision system with the Hough transform circle detection,we propose an object detection method of artifact threaded hole based ...In order to improve the accuracy of threaded hole object detection,combining a dual camera vision system with the Hough transform circle detection,we propose an object detection method of artifact threaded hole based on Faster region-ased convolutional neural network(Faster R-CNN).First,a dual camera image acquisition system is established.One industrial camera placed at a high position is responsible for collecting the whole image of the workpiece,and the suspected screw hole position on the workpiece can be preliminarily selected by Hough transform detection algorithm.Then,the other industrial camera is responsible for collecting the local images of the suspected screw holes that have been detected by Hough transform one by one.After that,ResNet50-based Faster R-CNN object detection model is trained on the self-built screw hole data set.Finally,the local image of the threaded hole is input into the trained Faster R-CNN object detection model for further identification and location.The experimental results show that the proposed method can effectively avoid small object detection of threaded holes,and compared with the method that only uses Hough transform or Faster RCNN object detection alone,it has high recognition and positioning accuracy.展开更多
The automatic localization of the left ventricle(LV)in short-axis magnetic resonance(MR)images is a required step to process cardiac images using convolutional neural networks for the extraction of a region of interes...The automatic localization of the left ventricle(LV)in short-axis magnetic resonance(MR)images is a required step to process cardiac images using convolutional neural networks for the extraction of a region of interest(ROI).The precise extraction of the LV’s ROI from cardiac MRI images is crucial for detecting heart disorders via cardiac segmentation or registration.Nevertheless,this task appears to be intricate due to the diversities in the size and shape of the LV and the scattering of surrounding tissues across different slices.Thus,this study proposed a region-based convolutional network(Faster R-CNN)for the LV localization from short-axis cardiac MRI images using a region proposal network(RPN)integrated with deep feature classification and regression.Themodel was trained using images with corresponding bounding boxes(labels)around the LV,and various experiments were applied to select the appropriate layers and set the suitable hyper-parameters.The experimental findings showthat the proposed modelwas adequate,with accuracy,precision,recall,and F1 score values of 0.91,0.94,0.95,and 0.95,respectively.This model also allows the cropping of the detected area of LV,which is vital in reducing the computational cost and time during segmentation and classification procedures.Therefore,itwould be an ideal model and clinically applicable for diagnosing cardiac diseases.展开更多
X-ray inspection equipment is divided into small baggage inspection equipment and large cargo inspection equipment.In the case of inspection using X-ray scanning equipment,it is possible to identify the contents of go...X-ray inspection equipment is divided into small baggage inspection equipment and large cargo inspection equipment.In the case of inspection using X-ray scanning equipment,it is possible to identify the contents of goods,unauthorized transport,or hidden goods in real-time by-passing cargo through X-rays without opening it.In this paper,we propose a system for detecting dangerous objects in X-ray images using the Cascade Region-based Convolutional Neural Network(Cascade R-CNN)model,and the data used for learning consists of dangerous goods,storage media,firearms,and knives.In addition,to minimize the overfitting problem caused by the lack of data to be used for artificial intelligence(AI)training,data samples are increased by using the CP(copy-paste)algorithm on the existing data.It also solves the data labeling problem by mixing supervised and semi-supervised learning.The four comparative models to be used in this study are Faster Regionbased Convolutional Neural Networks Residual2 Network-101(Faster R-CNN_Res2Net-101)supervised learning,Cascade R-CNN_Res2Net-101_supervised learning,Cascade Region-based Convolutional Neural Networks Composite Backbone Network V2(CBNetV2)Network-101(Cascade R-CNN_CBNetV2Net-101)_supervised learning,and Cascade RCNN_CBNetV2-101_semi-supervised learning which are then compared and evaluated.As a result of comparing the performance of the four models in this paper,in case of Cascade R-CNN_CBNetV2-101_semi-supervised learning,Average Precision(AP)(Intersection over Union(IoU)=0.5):0.7%,AP(IoU=0.75):1.0%than supervised learning,Recall:0.8%higher.展开更多
This paper help with leguminous seeds detection and smart farming. There are hundreds of kinds of seeds and itcan be very difficult to distinguish between them. Botanists and those who study plants, however, can ident...This paper help with leguminous seeds detection and smart farming. There are hundreds of kinds of seeds and itcan be very difficult to distinguish between them. Botanists and those who study plants, however, can identifythe type of seed at a glance. As far as we know, this is the first work to consider leguminous seeds images withdifferent backgrounds and different sizes and crowding. Machine learning is used to automatically classify andlocate 11 different seed types. We chose Leguminous seeds from 11 types to be the objects of this study. Thosetypes are of different colors, sizes, and shapes to add variety and complexity to our research. The images datasetof the leguminous seeds was manually collected, annotated, and then split randomly into three sub-datasetstrain, validation, and test (predictions), with a ratio of 80%, 10%, and 10% respectively. The images consideredthe variability between different leguminous seed types. The images were captured on five different backgrounds: white A4 paper, black pad, dark blue pad, dark green pad, and green pad. Different heights and shootingangles were considered. The crowdedness of the seeds also varied randomly between 1 and 50 seeds per image.Different combinations and arrangements between the 11 types were considered. Two different image-capturingdevices were used: a SAMSUNG smartphone camera and a Canon digital camera. A total of 828 images wereobtained, including 9801 seed objects (labels). The dataset contained images of different backgrounds, heights,angles, crowdedness, arrangements, and combinations. The TensorFlow framework was used to construct theFaster Region-based Convolutional Neural Network (R-CNN) model and CSPDarknet53 is used as the backbonefor YOLOv4 based on DenseNet designed to connect layers in convolutional neural. Using the transfer learningmethod, we optimized the seed detection models. The currently dominant object detection methods, Faster RCNN, and YOLOv4 performances were compared experimentally. The mAP (mean average precision) of the FasterR-CNN and YOLOv4 models were 84.56% and 98.52% respectively. YOLOv4 had a significant advantage in detection speed over Faster R-CNN which makes it suitable for real-time identification as well where high accuracy andlow false positives are needed. The results showed that YOLOv4 had better accuracy, and detection ability, as wellas faster detection speed beating Faster R-CNN by a large margin. The model can be effectively applied under avariety of backgrounds, image sizes, seed sizes, shooting angles, and shooting heights, as well as different levelsof seed crowding. It constitutes an effective and efficient method for detecting different leguminous seeds incomplex scenarios. This study provides a reference for further seed testing and enumeration applications.展开更多
乘务排班计划是城市轨道交通运营管理中的重要环节,为了解决目前乘务排班效率低下的问题,对乘务排班计划进行优化。在考虑便乘的情况下,以乘务排班计划总接续时间最小及总运营成本最小为目标建立地铁乘务排班计划编制的双目标优化模型...乘务排班计划是城市轨道交通运营管理中的重要环节,为了解决目前乘务排班效率低下的问题,对乘务排班计划进行优化。在考虑便乘的情况下,以乘务排班计划总接续时间最小及总运营成本最小为目标建立地铁乘务排班计划编制的双目标优化模型。在满足相关约束条件的基础上,将乘务作业段按照早、白、夜班分成3组,以乘务作业段为顶点,乘务作业段之间的接续关系为弧构建早、白、夜班的网络图,并形成乘务作业段接续时间矩阵,将乘务排班转化为最短路问题。运用相关最短路算法进行求解,该算法采用动态优化逼近的方法,一条最短路径即为一个乘务任务。以成都地铁5号线为例进行乘务排班计划编制,对模型和算法进行测试。研究结果表明:在求得的乘务排班计划中,早班乘务任务个数为53个,任务时长为280 h 34 min 57 s;白班乘务任务个数为41个,任务时长为199 h 54 min 51 s;夜班乘务任务个数为49个,任务时长为215 h 25 min 37 s。总乘务任务个数为143个,总工作时长为695 h 55 min 25 s。与手工编制结果相比,降低了乘务排班计划的总成本及接续时间,提高了求解效率。展开更多
文摘基于视觉的手部位姿估计技术应用于诸多领域,具备着广泛的国际应用市场前景和巨大发展潜力。然而,手部自身存在检测目标过小、手指高自由度以及手部自遮挡等问题。通过对目前存在的难点分析,将手部位姿估计任务分为手部检测和手部关键点检测,提出基于改进的Faster R-CNN的手部位姿估计方法。首先提出基于改进的Faster R-CNN手部检测网络,将传统Faster R-CNN网络中的对ROI(regional of interest)的最大值池化,更改为ROI Align,并增加损失函数用于区分左右手。在此基础上增加了头网络分支用以训练输出MANO(hand model with articulated and non-rigid deformations)手部模型的姿态参数和形状参数,得到手部关键点三维坐标,最终得到手部的三维位姿估计结果。实验表明,手部检测结果中存在的自遮挡和尺度问题得到了解决,并且检测结果的准确性有所提高,本文手部检测算法准确率为85%,比传统Faster R-CNN算法提升13%。手部关键点提取算法在MSRA、ICVL、NYU三个数据集分别取得关键点坐标的均方误差值(key-point mean square error,KMSE)为7.50、6.32、8.50的结果。
基金Supported by the National Natural Science Foundation of China(No.61471136)the Special Project for Global Change and Air-sea Interaction of Ministry of Natural Resources(No.GASI-02-SCS-YGST2-04)the Chinese Association of Ocean Mineral Resources R&D(No.DY135-E2-4)
文摘Ocean internal waves appear as irregular bright and dark stripes on synthetic aperture radar(SAR)remote sensing images.Ocean internal waves detection in SAR images consequently constituted a difficult and popular research topic.In this paper,ocean internal waves are detected in SAR images by employing the faster regions with convolutional neural network features(Faster R-CNN)framework;for this purpose,888 internal wave samples are utilized to train the convolutional network and identify internal waves.The experimental results demonstrate a 94.78%recognition rate for internal waves,and the average detection speed is 0.22 s/image.In addition,the detection results of internal wave samples under different conditions are analyzed.This paper lays a foundation for detecting ocean internal waves using convolutional neural networks.
基金National Defense Pre-research Fund Project(No.KMGY318002531)。
文摘In order to solve the problem of small objects detection in unmanned aerial vehicle(UAV)aerial images with complex background,a general detection method for multi-scale small objects based on Faster region-based convolutional neural network(Faster R-CNN)is proposed.The bird’s nest on the high-voltage tower is taken as the research object.Firstly,we use the improved convolutional neural network ResNet101 to extract object features,and then use multi-scale sliding windows to obtain the object region proposals on the convolution feature maps with different resolutions.Finally,a deconvolution operation is added to further enhance the selected feature map with higher resolution,and then it taken as a feature mapping layer of the region proposals passing to the object detection sub-network.The detection results of the bird’s nest in UAV aerial images show that the proposed method can precisely detect small objects in aerial images.
基金supported by the National Natural Science Foundation of China(Nos.51677171,51637009,51577166 and 51827810)the National Key R&D Program of China(No.2018YFB0606000)+2 种基金the China Scholarship Council(No.201708330502)the Fund of Shuohuang Railway Development Limited Liability Company(No.SHTL-2020-13)the Fund of State Key Laboratory of Industrial Control Technology(No.ICT2022B29),China。
文摘Rod insulators are vital parts of the catenary of high speed railways(HSRs).There are many different catenary insulators,and the background of the insulator image is complicated.It is difficult to recognise insulators and detect defects automatically.In this paper,we propose a catenary intelligent defect detection algorithm based on Mask region-convolutional neural network(R-CNN)and an image processing model.Vertical projection technology is used to achieve single shed positioning and precise cutting of the insulator.Gradient,texture,and gray feature fusion(GTGFF)and a K-means clustering analysis model(KCAM)are proposed to detect broken insulators,dirt,foreign bodies,and flashover.Using this model,insulator recognition and defect detection can achieve a high recall rate and accuracy,and generalized defect detection.The algorithm is tested and verified on a dataset of realistic insulator images,and the accuracy and reliability of the algorithm satisfy current requirements for HSR catenary automatic inspection and intelligent maintenance.
基金This research was supported by the Honam University Research Fund,2021.
文摘This study aims to detect and prevent greening disease in citrus trees using a deep neural network.The process of collecting data on citrus greening disease is very difficult because the vector pests are too small.In this paper,since the amount of data collected for deep learning is insufficient,we intend to use the efficient feature extraction function of the neural network based on the Transformer algorithm.We want to use the Cascade Region-based Convolutional Neural Networks(Cascade R-CNN)Swin model,which is a mixture of the transformer model and Cascade R-CNN model to detect greening disease occurring in citrus.In this paper,we try to improve model safety by establishing a linear relationship between samples using Mixup and Cutmix algorithms,which are image processing-based data augmentation techniques.In addition,by using the ImageNet dataset,transfer learning,and stochastic weight averaging(SWA)methods,more accuracy can be obtained.This study compared the Faster Region-based Convolutional Neural Networks Residual Network101(Faster R-CNN ResNet101)model,Cascade Regionbased Convolutional Neural Networks Residual Network101(Cascade RCNN-ResNet101)model,and Cascade R-CNN Swin Model.As a result,the Faster R-CNN ResNet101 model came out as Average Precision(AP)(Intersection over Union(IoU)=0.5):88.2%,AP(IoU=0.75):62.8%,Recall:68.2%,and the Cascade R-CNN ResNet101 model was AP(IoU=0.5):91.5%,AP(IoU=0.75):67.2%,Recall:73.1%.Alternatively,the Cascade R-CNN Swin Model showed AP(IoU=0.5):94.9%,AP(IoU=0.75):79.8%and Recall:76.5%.Thus,the Cascade R-CNN Swin Model showed the best results for detecting citrus greening disease.
文摘In order to improve the accuracy of threaded hole object detection,combining a dual camera vision system with the Hough transform circle detection,we propose an object detection method of artifact threaded hole based on Faster region-ased convolutional neural network(Faster R-CNN).First,a dual camera image acquisition system is established.One industrial camera placed at a high position is responsible for collecting the whole image of the workpiece,and the suspected screw hole position on the workpiece can be preliminarily selected by Hough transform detection algorithm.Then,the other industrial camera is responsible for collecting the local images of the suspected screw holes that have been detected by Hough transform one by one.After that,ResNet50-based Faster R-CNN object detection model is trained on the self-built screw hole data set.Finally,the local image of the threaded hole is input into the trained Faster R-CNN object detection model for further identification and location.The experimental results show that the proposed method can effectively avoid small object detection of threaded holes,and compared with the method that only uses Hough transform or Faster RCNN object detection alone,it has high recognition and positioning accuracy.
基金supported by the Ministry of Higher Education(MOHE)through the Fundamental Research Grant Scheme(FRGS)(FRGS/1/2020/TK0/UTHM/02/16)the Universiti Tun Hussein Onn Malaysia(UTHM)through an FRGS Research Grant(Vot K304).
文摘The automatic localization of the left ventricle(LV)in short-axis magnetic resonance(MR)images is a required step to process cardiac images using convolutional neural networks for the extraction of a region of interest(ROI).The precise extraction of the LV’s ROI from cardiac MRI images is crucial for detecting heart disorders via cardiac segmentation or registration.Nevertheless,this task appears to be intricate due to the diversities in the size and shape of the LV and the scattering of surrounding tissues across different slices.Thus,this study proposed a region-based convolutional network(Faster R-CNN)for the LV localization from short-axis cardiac MRI images using a region proposal network(RPN)integrated with deep feature classification and regression.Themodel was trained using images with corresponding bounding boxes(labels)around the LV,and various experiments were applied to select the appropriate layers and set the suitable hyper-parameters.The experimental findings showthat the proposed modelwas adequate,with accuracy,precision,recall,and F1 score values of 0.91,0.94,0.95,and 0.95,respectively.This model also allows the cropping of the detected area of LV,which is vital in reducing the computational cost and time during segmentation and classification procedures.Therefore,itwould be an ideal model and clinically applicable for diagnosing cardiac diseases.
文摘X-ray inspection equipment is divided into small baggage inspection equipment and large cargo inspection equipment.In the case of inspection using X-ray scanning equipment,it is possible to identify the contents of goods,unauthorized transport,or hidden goods in real-time by-passing cargo through X-rays without opening it.In this paper,we propose a system for detecting dangerous objects in X-ray images using the Cascade Region-based Convolutional Neural Network(Cascade R-CNN)model,and the data used for learning consists of dangerous goods,storage media,firearms,and knives.In addition,to minimize the overfitting problem caused by the lack of data to be used for artificial intelligence(AI)training,data samples are increased by using the CP(copy-paste)algorithm on the existing data.It also solves the data labeling problem by mixing supervised and semi-supervised learning.The four comparative models to be used in this study are Faster Regionbased Convolutional Neural Networks Residual2 Network-101(Faster R-CNN_Res2Net-101)supervised learning,Cascade R-CNN_Res2Net-101_supervised learning,Cascade Region-based Convolutional Neural Networks Composite Backbone Network V2(CBNetV2)Network-101(Cascade R-CNN_CBNetV2Net-101)_supervised learning,and Cascade RCNN_CBNetV2-101_semi-supervised learning which are then compared and evaluated.As a result of comparing the performance of the four models in this paper,in case of Cascade R-CNN_CBNetV2-101_semi-supervised learning,Average Precision(AP)(Intersection over Union(IoU)=0.5):0.7%,AP(IoU=0.75):1.0%than supervised learning,Recall:0.8%higher.
文摘This paper help with leguminous seeds detection and smart farming. There are hundreds of kinds of seeds and itcan be very difficult to distinguish between them. Botanists and those who study plants, however, can identifythe type of seed at a glance. As far as we know, this is the first work to consider leguminous seeds images withdifferent backgrounds and different sizes and crowding. Machine learning is used to automatically classify andlocate 11 different seed types. We chose Leguminous seeds from 11 types to be the objects of this study. Thosetypes are of different colors, sizes, and shapes to add variety and complexity to our research. The images datasetof the leguminous seeds was manually collected, annotated, and then split randomly into three sub-datasetstrain, validation, and test (predictions), with a ratio of 80%, 10%, and 10% respectively. The images consideredthe variability between different leguminous seed types. The images were captured on five different backgrounds: white A4 paper, black pad, dark blue pad, dark green pad, and green pad. Different heights and shootingangles were considered. The crowdedness of the seeds also varied randomly between 1 and 50 seeds per image.Different combinations and arrangements between the 11 types were considered. Two different image-capturingdevices were used: a SAMSUNG smartphone camera and a Canon digital camera. A total of 828 images wereobtained, including 9801 seed objects (labels). The dataset contained images of different backgrounds, heights,angles, crowdedness, arrangements, and combinations. The TensorFlow framework was used to construct theFaster Region-based Convolutional Neural Network (R-CNN) model and CSPDarknet53 is used as the backbonefor YOLOv4 based on DenseNet designed to connect layers in convolutional neural. Using the transfer learningmethod, we optimized the seed detection models. The currently dominant object detection methods, Faster RCNN, and YOLOv4 performances were compared experimentally. The mAP (mean average precision) of the FasterR-CNN and YOLOv4 models were 84.56% and 98.52% respectively. YOLOv4 had a significant advantage in detection speed over Faster R-CNN which makes it suitable for real-time identification as well where high accuracy andlow false positives are needed. The results showed that YOLOv4 had better accuracy, and detection ability, as wellas faster detection speed beating Faster R-CNN by a large margin. The model can be effectively applied under avariety of backgrounds, image sizes, seed sizes, shooting angles, and shooting heights, as well as different levelsof seed crowding. It constitutes an effective and efficient method for detecting different leguminous seeds incomplex scenarios. This study provides a reference for further seed testing and enumeration applications.
文摘乘务排班计划是城市轨道交通运营管理中的重要环节,为了解决目前乘务排班效率低下的问题,对乘务排班计划进行优化。在考虑便乘的情况下,以乘务排班计划总接续时间最小及总运营成本最小为目标建立地铁乘务排班计划编制的双目标优化模型。在满足相关约束条件的基础上,将乘务作业段按照早、白、夜班分成3组,以乘务作业段为顶点,乘务作业段之间的接续关系为弧构建早、白、夜班的网络图,并形成乘务作业段接续时间矩阵,将乘务排班转化为最短路问题。运用相关最短路算法进行求解,该算法采用动态优化逼近的方法,一条最短路径即为一个乘务任务。以成都地铁5号线为例进行乘务排班计划编制,对模型和算法进行测试。研究结果表明:在求得的乘务排班计划中,早班乘务任务个数为53个,任务时长为280 h 34 min 57 s;白班乘务任务个数为41个,任务时长为199 h 54 min 51 s;夜班乘务任务个数为49个,任务时长为215 h 25 min 37 s。总乘务任务个数为143个,总工作时长为695 h 55 min 25 s。与手工编制结果相比,降低了乘务排班计划的总成本及接续时间,提高了求解效率。
