基于實(shí)例分割的填埋場滲漏源檢測算法研究

打開文本圖片集

中圖分類號：：TP391.41 文獻(xiàn)標(biāo)志碼：A

本文引用格式：，.基于實(shí)例分割的填埋場滲漏源檢測算法研究[J].華東交通大學(xué)學(xué)報，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.

危險廢物填埋場是處置危險廢物的一種陸地組分向環(huán)境和人體遷移的途徑，從而安全處置危險廢物[]。（剩余10194字）