[Poster Presentation]Safety Compliance Monitoring in Power Work under Adverse Image Conditions

Safety Compliance Monitoring in Power Work under Adverse Image Conditions
ID:23 Submission ID:26 View Protection:ATTENDEE Updated Time:2025-11-03 11:18:02 Hits:75 Poster Presentation

Start Time:2025-11-09 09:02 (Asia/Shanghai)

Duration:1min

Session:[P] Poster presentation » [P6] 6.AI-driven technology

No files

Abstract
确保电力系统现场工作人员穿着反光背心和其他个人防护装备对于维护作安全和合规性至关重要。然而,对此类安全装备的基于图像的识别可能会受到视觉干扰(如运动模糊和照明不足)的显着影响,这些干扰在现实世界的户外监控环境中很常见。为了增强复杂条件下检测的鲁棒性,本研究提出了一种针对电力运行场景的图像增强策略。具体而言,采用高斯模糊和亮度降低技术来模拟运动引起的模糊、阴天和夜间照明等不利条件。增强后的图像被纳入模型训练和评估中。实验结果表明,所提方法有效提高了各种视觉条件下安全合规性的识别准确性,显示出较强的适应性和实用价值。该方法为户外电力系统运行中的智能监控和安全管理提供了技术支持。
Keywords
Electric power operation, Image augmentation, Personal protective equipment, Reflective vest detection, YOLOv8
Speaker
Yuqing Luo
Huazhong University of Science and Technology

Submission Author
雨晴 罗 华中科技大学
YONG YANG Huazhong University of Science and Technology
李 传 华中科技大学
Comment submit
Verification code Change another
All comments

Contact us

CIYCEE 2025 Official E-mail:

ciycee2025@163.com

 

WeChat public account: 

IEEE IAS SWJTU Student Branch