An Illegal Dress Recognition Algorithm Based on Key-point Detection and Attention Mechanism and Its Application

被引：0
|
作者：
He G. [1 ]
Qi D. [1 ]
Yan Y. [1 ]
机构：
[1] College of Electrical Engineering, Zhejiang University, Hangzhou
来源：
Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering | 2022年 / 42卷 / 05期
基金：
中国国家自然科学基金;
关键词：
Attention mechanism; Deep learning; Illegal dress recognition; Key-point detection;
D O I：
10.13334/j.0258-8013.pcsee.210282
中图分类号：
学科分类号：
摘要：
Existing illegal dress recognition algorithms mainly locate and extract the image features of helmets and work clothes based on the proportion of human body structure, and cannot accurately recognize large postures such as bending, squatting, and climbing. Aiming at the above problems, an illegal dress recognition algorithm based on key-point detection and attention mechanism was proposed, which could be applied to a variety of human postures and different shooting angles, with good performance. Based on pedestrian detection, a single-person key-point detection model was designed, and a region localization strategy was proposed to accurately locate the pedestrian's head, upper body and bottom body areas, which reduced background interference and made dress feature extraction easier. In addition, the attention mechanism was introduced into the basic image classification model to further improve the accuracy of the identification of illegal dress. Experimental results based on human body posture images in substation work scenes verify the effectiveness of the algorithm. © 2022 Chin. Soc. for Elec. Eng.
引用
收藏
页码：1826 / 1836
页数：10
相关论文
共 28 条
  • [1] LIU Xiaoliang, The detection and discrimination processing of the target image in the scene monitoring system, (2008)
  • [2] BIAN Xiaoxu, XIE Qiang, Fragility analysis of substation equipment based on ground motion clustering, Proceedings of the CSEE, 41, 8, pp. 2671-2681, (2021)
  • [3] LIU Xiaohui, YE Xining, Skin color detection and Hu moments in helmet recognition research, Journal of East China University of Science and Technology: Natural Science Edition, 40, 3, pp. 365-370, (2014)
  • [4] SHI Hui, CHEN Xianqiao, YANG Ying, Safety helmet wearing detection method of improved YOLO v3, Computer Engineering and Applications, 55, 11, pp. 213-220, (2019)
  • [5] CHEN Jian, Analysis and recognition of human body dress based on performance characteristics, (2009)
  • [6] LI Cong, HU Jinlei, ZHOU Junhuang, Et al., Dressing image recognition algorithm for substation operators based on sensitivity radial basis function neural network, Guangdong Electric Power, 32, 9, pp. 124-130, (2019)
  • [7] YUAN Yidan, Research on standardized detection technology of Staff Wear based on image recognition, (2019)
  • [8] WU Hui, LI Mingjun, YANG Yingyi, Et al., An object detection method and its optimization for substation video surveillance terminals, Guangdong Electric Power, 32, 9, pp. 62-68, (2019)
  • [9] CHEN Xi, HAN Yifeng, YAN Yunfeng, Et al., A unified algorithm for object tracking and segmentation and its application on intelligent video surveillance for transformer substation, Proceedings of the CSEE, 40, 23, pp. 7578-7587, (2020)
  • [10] YANG Yan, YANG Zhifang, YU Juan, Et al., Fast analysis of N-1 contingency screening with uncertainty scenarios based on deep learning, Proceedings of the CSEE, 41, 8, pp. 2716-2724, (2021)
123