[Oral Presentation]A Violation Behaviors Detection Method for Substation Operators based on YOLOv5 And Pose Estimation - Presentation details

A Violation Behaviors Detection Method for Substation Operators based on YOLOv5 And Pose Estimation
ID:172 View Protection:ATTENDEE Updated Time:2022-10-12 21:03:49 Hits:259 Oral Presentation

Start Time:Pending (Asia/Shanghai)

Duration:Pending

Session:[No Session] [No Session Block]

Video No Permission Presentation File

Tips: The file permissions under this presentation are only for participants. You have not logged in yet and cannot view it temporarily.

Abstract
Violation behaviors of substation operators remain obstacle to power safety production. Previous work mostly relies on detecting objects such as helmets in the image to judge the behavior of substation operators, rather than extracting characteristics of substation operators’ behavior. In this work,violation behaviors are divided into two categories. One can be characterized by absence of tools, such as not wearing safety helmets and not wearing working clothes. The other violation behaviors such as falling on the ground, climbing or crossing do not have specific tools features. Thus, a violation behaviors detection strategy which can accurately identify two kinds of violation behaviors is developed by combining object detection model based on YOLOv5, pose estimation model based on HRNet and skeleton-based action recognition model based on ST-GCN. The location of substation operators and the violation behaviors including not wearing safety helmets, not wearing working clothes and smoking can be detected at the same time in detection model based on YOLOv5. On the basis of location of substation operators, the 17 keypoints and the skeleton graph can be obtained by pose estimation model based on HRNet. Furthermore, ST-GCN base on skeleton graphs is adopted to recognize falling on the ground, climbing or crossing.The results of experimental verification on data from a substation prove the effectiveness of the proposed strategy.
 
Keywords
Speaker
Jing Wang
NARI Technology Development Co. Ltd

Jing Wang received the M.S. degree in Control science and Engineering from Zhejiang University, Hangzhou, China, in 2019. She is currently working in NARI Technology Development Co. Ltd, Nanjing, China. Her research interests include substation intelligent inspection, defect detection of substation equipment and power systems.

Comment submit
Verification code Change another
All comments
Log in Sign up Registration Submit