文献类型：期刊文献

英文题名：Intelligent Flood Scene Understanding Using Computer Vision-Based Multi-Object Tracking

作者：Yan, Xuzhong[1];Zhu, Yiqiao[2];Wang, Zeli[3];Xu, Bin[4];He, Liu[5];Xia, Rong[6]

机构：[1]Zhejiang Univ Technol, Sch Management, Hangzhou 310023, Peoples R China;[2]Zhejiang Coll Construct, Engn Management Sch, Hangzhou 311231, Peoples R China;[3]East China Univ Sci & Technol, Dept Management Sci & Engn, Shanghai 200030, Peoples R China;[4]Zhejiang Prov Sanjian Construction Grp Co Ltd, Hangzhou 310012, Peoples R China;[5]Zhejiang Construction Investment Grp Co Ltd, Hangzhou 310012, Peoples R China;[6]Zhejiang Univ, Coll Civil Engn & Architecture, Hangzhou 310058, Peoples R China

年份：2025

卷号：17

期号：14

外文期刊名：WATER

收录：;EI(收录号：20253018860754);WOS:【SCI-EXPANDED(收录号:WOS:001539643800001)】；

基金：This research was funded by the National Natural Science Foundation of China, grant number 72201247.

语种：英文

外文关键词：intelligent flood scene understanding; computer vision; multi-object tracking; disaster response

摘要：Understanding flood scenes is essential for effective disaster response. Previous research has primarily focused on computer vision-based approaches for analyzing flood scenes, capitalizing on their ability to rapidly and accurately cover affected regions. However, most existing methods emphasize static image analysis, with limited attention given to dynamic video analysis. Compared to image-based approaches, video analysis in flood scenarios offers significant advantages, including real-time monitoring, flow estimation, object tracking, change detection, and behavior recognition. To address this gap, this study proposes a computer vision-based multi-object tracking (MOT) framework for intelligent flood scene understanding. The proposed method integrates an optical-flow-based module for short-term undetected mask estimation and a deep re-identification (ReID) module to handle long-term occlusions. Experimental results demonstrate that the proposed method achieves state-of-the-art performance across key metrics, with a HOTA of 69.57%, DetA of 67.32%, AssA of 73.21%, and IDF1 of 89.82%. Field tests further confirm its improved accuracy, robustness, and generalization. This study not only addresses key practical challenges but also offers methodological insights, supporting the application of intelligent technologies in disaster response and humanitarian aid.