基于深度学习的变电站环境下行人检测方法研究Research on Substation Pedestrian Detection Method Based on Deep Learning
林磊,钱平,董毅,陈志伟
LIN Lei,QIAN Ping,DONG Yi,CHEN Zhiwei
摘要(Abstract)：
变电站监控是确保电能长距离安全稳定运输的重要举措之一。在充分考虑和调研变电站环境下行人检测任务难点的基础上,针对变电站行人检测的实际需求,提出将目前计算机视觉领域最先进的深度学习技术应用于变电站环境下行人检测问题中,并通过实验对其思路和方法的有效性和可行性进行验证与分析。
Substation monitoring is a key measure to maintain safe and stable transmission of electric energy from long distance. Based on the difficulties of substation pedestrian detection, the paper proposes the application of deep learning, the most advanced technology in computer vision, in substation pedestrian detection.The feasibility and effectiveness of idea and the method are verified and analyzed through experiment.
关键词(KeyWords)：
变电站;行人检测;深度学习;安全监控;实时
substation;pedestrian detection;deep learning;safety monitoring;real-time
基金项目(Foundation):
作者(Author):
林磊,钱平,董毅,陈志伟
LIN Lei,QIAN Ping,DONG Yi,CHEN Zhiwei
DOI: 10.19585/j.zjdl.201807012
参考文献(References)：
- [1]陈杰.工业企业变电站监控系统的应用研究[D].北京:北京邮电大学,2009.
- [2]李静.变电站安全运行监控系统研究[D].武汉:华中科技大学,2005.
- [3]TIAN Y,LUO P,WANG X,et al.Deep Learning Strong Parts for Pedestrian Detection[C]//IEEE International Conference on Computer Vision.IEEE,2016:1904-1912.
- [4]OUYANG W,WANG X.Joint Deep Learning for Pedestrian Detection[C]//IEEE International Conference on Computer Vision.IEEE,2014:2056-2063.
- [5]TIAN Y,LUO P,WANG X,et al.Pedestrian detection aided by deep learning semantic tasks[C]//IEEE International Conference on Computer Vision.IEEE,2015:5079-5087.
- [6]ZENG X,OUYANG W,WANG X.Multi-stage Contextual Deep Learning for Pedestrian Detection[C]//IEEE International Conference on Computer Vision.IEEE,2013:21-128.
- [7]ORG W I.Pedestrian Detection:A Survey of Methodologies,Techniques and Current Advancements[J].IJSRET,2015(4):31-36.
- [8]DOLLAR P,WOJEK C,SCHIELE B,et al.Pedestrian detection:A benchmark[C]//IEEE International Conference on Computer Vision.IEEE,2009:304-311.
- [9]PAN S J,YANG Q.A Survey on Transfer Learning[J].IEEE Transactions on Knowledge&Data Engineering,2010,22(10):1345-1359.
- [10]WEISS K,KHOSHGOFTAAR T M,WANG D D.A survey of transfer learning[J].Journal of Big Data,2016,3(1):9.
- [11]SIMONYAN K,ZISSERMAN A.Very Deep Convolutional Networks for Large-Scale Image Recognition[J].Computer Science,2014,20(12):136-145.
- [12]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2017,39(6):1137-1149.
- [13]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single Shot Multi Box Detector[C]//European Conference on Computer Vision.Springer,Cham,2016:21-37.
- [14]REDON J,DIVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-Time Object Detection[C]//IEEEInternational Conference on Computer Vision.IEEE,2015:779-788.
- [15]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Image Recognition[C]//Computer Vision and Pattern Recognition.IEEE,2016:770-778.
- [16]DOLLAR P,WOJEK C,SCHIELE B,et al.Pedestrian De tection:An Evaluation of the State of the Art[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2012,34(4):743-761.
- [17]NAMIN S T,NAJAFI M,SALZMANN M,et al.A Multimodal Graphical Model for Scene Analysis[C]//Applications of Computer Vision.IEEE,2015:1006-1013.
- [18]ESS A,LEIBE B,SCHINDLER K,et al.A mobile vision system for robust multi-person tracking[C]//Computer Vision and Pattern Recognition,2008.CVPR 2008.IEEEConference on.IEEE,2008:1-8.
- [19]FLOHR F,GAVRILA D.Ped Cut:an iterative framework for pedestrian segmentation combining shape models and multiple data cues[C]//British Machine Vision Conference.2013:1-11.
- [20]JIA Y,SHELHAMER E,DONAHUE J,et al.Caffe:Con vo lutional Architecture for Fast Feature Embedding[C]//ACMInternational Conference on Multimedia.ACM,2014:675-678.