Using Improved YOLOv5 and SegFormer to Extract Tailings Ponds from Multi-Source Data

Photogrammetric Engineering & Remote Sensing Pub Date : 2024-04-01 DOI:10.14358/pers.23-00066r2

Zhenhui Sun, Ying Xu, Dongchuan Wang, Qingyan Meng, Yunxiao Sun

引用次数: 0

Abstract

This paper proposes a framework that combines the improved "You Only Look Once" version 5 (YOLOv5) and SegFormer to extract tailings ponds from multi-source data. Points of interest (POIs) are crawled to capture potential tailings pond regions. Jeffries–Matusita distance is used to evaluate the optimal band combination. The improved YOLOv5 replaces the backbone with the PoolFormer to form a PoolFormer backbone. The neck introduces the CARAFE operator to form a CARAFE feature pyramid network neck (CRF-FPN). The head is substituted with an efficiency decoupled head. POIs and classification data optimize improved YOLOv5 results. After that, the SegFormer is used to delineate the boundaries of tailings ponds. Experimental results demonstrate that the mean average precision of the improved YOLOv5s has increased by 2.78% compared to the YOLOv5s, achieving 91.18%. The SegFormer achieves an intersection over union of 88.76% and an accuracy of 94.28%.

查看原文本刊更多论文

使用改进的 YOLOv5 和 SegFormer 从多源数据中提取尾矿池

本文提出的框架结合了改进的 "你只看一次 "第 5 版（YOLOv5）和 SegFormer，可从多源数据中提取尾矿库。通过抓取兴趣点 (POI) 来捕捉潜在的尾矿库区域。Jeffries-Matusita 距离用于评估最佳波段组合。改进后的 YOLOv5 用 PoolFormer 取代了骨干网，形成了 PoolFormer 骨干网。颈部引入 CARAFE 算子，形成 CARAFE 特征金字塔网络颈（CRF-FPN）。头部由效率解耦头部替代。POI 和分类数据优化了 YOLOv5 的改进结果。之后，使用 SegFormer 划定尾矿库的边界。实验结果表明，改进后的 YOLOv5 平均精度比 YOLOv5 提高了 2.78%，达到 91.18%。SegFormer 的交集大于联合率达到 88.76%，精确度达到 94.28%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Photogrammetric Engineering & Remote Sensing

自引率

0.00%

发文量