Safety Supervision Method for Power Operation Site Based on Machine Learning and Image Recognition

doi:10.11930/j.issn.1004-9649.201811057

Abstract

Abstract: Aiming at the safety supervision of power operation site, a research is carried out on personnel intrusion detection. It is proposed to use the histogram of oriented gradient (HOG) and support vector machine (SVM) for full frame personnel detection, and then the OpenCV-based image processing technology is used to determine any personnel intrusion into the alert area. Through the images of the work site captured by video monitoring equipment, the above-said methods are used to identify the on-site personnel and their dangerous behaviors in real time, and to issue an alarm signal. The experimental results show that the accuracy of the detecting results reaches 92%, and the automatic safety supervision of power operation site is realized, which greatly improves the safety level of the power operation site.

Key words: histogram of oriented gradient, support vector machine, intrusion detection, power operation site, safety supervision

CHANG Zhengwei, PENG Qian, CHEN Ying. Safety Supervision Method for Power Operation Site Based on Machine Learning and Image Recognition[J]. Electric Power, 2020, 53(4): 155-160.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.201811057

https://www.electricpower.com.cn/EN/Y2020/V53/I4/155

References

[1] 陈勇. 电力生产作业安全管理中的问题及对策[J]. 中国新技术新产品, 2018(12): 138–139
[2] 陈满通. 加强电力安全监督检查的有效性思考[J]. 中外企业家, 2018(11): 224, 226
[3] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceedings-2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005). IEEE, 2005: 886-893.
[4] FELZENSZWALB P, MCALLESTER D, RAMANAN D. A discriminatively trained, multiscale, deformable part model[C]//2008 IEEE Conference on Computer Vision and Pattern Recognition, June 23−28, 2008. Anchorage, AK, USA. IEEE, 2008, 8: 1−8.
[5] FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D. Cascade object detection with deformable part models[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 13-18, 2010. San Francisco, CA, USA. IEEE, 2010: 2241−2248.
[6] FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al. Object detection with discriminatively trained part-based models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627–1645.
[7] BENENSON R, MATHIAS M, TIMOFTE R, et al. Pedestrian detection at 100 frames per second[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, 2012: 2903−2910.
[8] SABZMEYDANI P, MORI G. Detecting pedestrians by learning shapelet features[C]//2007 IEEE Conference on Computer Vision and Pattern Recognition, June 17-22, 2007. Minneapolis, MN, USA. IEEE, 2007: 1−8.
[9] 杨萌. 基于支持向量机的行人检测技术研究[D]. 北京: 中国科学院大学, 2018.
YANG Meng. Research on pedestrian detection technology based on support vector machine[D]. Beijing: University of Chinese Academy of Sciences, 2018.
[10] 王江涛, 杨静宇. 红外图像中人体实时检测研究[J]. 系统仿真学报, 2007, 19(19): 4490–4494
WANG Jiangtao, YANG Jingyu. Research on real time pedestrian detection in infrared images[J]. Journal of System Simulation, 2007, 19(19): 4490–4494
[11] 李海龙. 基于区域卷积神经网络的行人检测问题研究[D]. 杭州: 杭州电子科技大学, 2017.
LI Hailong. Research on the pedestrian detection based on region of convolution neural network[D]. Hangzhou: Hangzhou Dianzi University, 2017.
[12] REN X, BO L, FOX D. RGB-(D) scene labeling: Features and algorithms[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition, June 16-21, 2012. Providence, RI. IEEE, 2012: 2759−2766.
[13] BENENSON R, MATHIAS M, TUYTELAARS T, et al. Seeking the strongest rigid detector[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2013. Portland, OR, USA. IEEE, 2013: 3666-3673.
[14] 周志华. 机器学习[M]. 北京: 清华大学出版社, 2016.
[15] WATANABE T, ITO S, YOKOI K. Co-occurrence histograms of oriented gradients for pedestrian detection[C]//Advances in Image and Video Technology. Berlin, Heidelberg: Springer Berlin Heidelberg, 2009: 37−47.
[16] KATAOKA H, TAMURA K, IWATA K, et al. Extended feature descriptor and vehicle motion model with tracking-by-detection for pedestrian active safety[J]. IEICE Transactions on Information and Systems, 2014, E97. D(2): 296–304.
[17] 刘威, 段成伟, 遇冰, 等. 基于后验HOG特征的多姿态行人检测[J]. 电子学报, 2015, 43(2): 217–224
LIU Wei, DUAN Chengwei, YU Bing, et al. Multi-pose pedestrian detection based on posterior HOG feature[J]. Acta Electronica Sinica, 2015, 43(2): 217–224
[18] 武光利, 王绵沼. 基于HOG特征与SVM分类器的行人检测研究[J]. 中国有线电视, 2017(12): 1413–1415
WU Guangli, WANG Mianzhao. Research on pedestrian detection based on HOG and SVM[J]. China Digital Cable TV, 2017(12): 1413–1415
[19] BAY H, TUYTELAARS T, VAN GOOL L. SURF: speeded up robust features[C]//Computer Vision-ECCV 2006. Berlin, Heidelberg: Springer Berlin Heidelberg, 2006: 404-417.
[20] 刘方园, 王水花, 张煜东. 支持向量机模型与应用综述[J]. 计算机系统应用, 2018, 27(4): 1–9
LIU Fangyuan, WANG Shuihua, ZHANG Yudong. Overview on models and applications of support vector machine[J]. Computer Systems & Applications, 2018, 27(4): 1–9
[21] 白羽. 基于智能视频监控的入侵危险区域算法研究[J]. 科技创新与生产力, 2014(11): 45–47, 49
BAI Yu. Research on algorithm of intrusion dangerous region based on the intelligent video monitoring[J]. Sci-Tech Innovation and Productivity, 2014(11): 45–47, 49