基于实例分割的填埋场渗漏源检测算法研究

打开文本图片集

中图分类号：：TP391.41 文献标志码：A

本文引用格式：，.基于实例分割的填埋场渗漏源检测算法研究[J].华东交通大学学报，2025，42（2）：103-109

Research on the Detection Algorithm for Landfill Leakage Based on Instance Segmentation

Chen Qianghua，Li Ming

（SchoolofElectronic Information Engineering，ShanghaiDianjiUniversity，Shanghai 2O3o6，China）

Abstract： Leakage detection is a critical measure to ensure the proper operation of hazardous waste landfils. Traditional manual visual inspections are inefficient，and hazardous waste can afect the health of workers.A method based on instance segmentation is proposed to detect leakage.The method uses a camera mounted on an inspection robot to capture video images，the YOLOSeg-EViT network performs instance segmentation.Experimental results show that the algorithm achieves a mean average precision of 75.7% ，and when detecting with a pixel resolution video，the detection is 54.4 frames per second. On an edge computing platform， the algorithm reaches mean average precision 75.1% and 33.1 frames per second. The leakage detection algorithm effectively identifies leakage，improves the detection eficiency，and prevents workers from being exposed to hazardous substances， making it highly practical.

Key words： landfilleakage; defect detection; instance segmentation;deep learning; lightweight deployment Citation format： CHENQH，LIM.Research on the detection algorithm for landfillleakage based on instance segmentation[J]. Journal of East China Jiaotong University， 2025，42（2）： 103-109.

危险废物填埋场是处置危险废物的一种陆地组分向环境和人体迁移的途径，从而安全处置危险废物[]。（剩余10194字）