Integrating Appearance and Spatial-Temporal Information for Multi-Camera People Tracking

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Pub Date : 2023-06-01 DOI:10.1109/CVPRW59228.2023.00554

Wenjie Yang, Zhe Xie, Yaoming Wang, Yang Zhang, Xiao Ma, Bing Hao

{"title":"Integrating Appearance and Spatial-Temporal Information for Multi-Camera People Tracking","authors":"Wenjie Yang, Zhe Xie, Yaoming Wang, Yang Zhang, Xiao Ma, Bing Hao","doi":"10.1109/CVPRW59228.2023.00554","DOIUrl":null,"url":null,"abstract":"Multi-Camera People Tracking (MCPT) is a crucial task in intelligent surveillance systems. However, it presents significant challenges due to issues such as heavy occlusion and variations in appearance that arise from multiple camera perspectives and congested scenarios. In this paper, we propose an effective system that integrates both appearance and spatial-temporal information to address these problems, consisting of three specially designed modules: (1) A Multi-Object Tracking (MOT) method that minimizes ID-switch errors and generates accurate trajectory appearance features for MCPT. (2) A robust intra-camera association method that leverages both appearance and spatial-temporal information. (3) An effective post-processing module comprising multi-step processing. Our proposed system is evaluated on the test set of Track1 for the 2023 AI CITY CHALLENGE, and the experimental results demonstrate its effectiveness, achieving an IDF1 score of 93.31% and ranking 3rd on the leaderboard.","PeriodicalId":355438,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CVPRW59228.2023.00554","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

Abstract

Multi-Camera People Tracking (MCPT) is a crucial task in intelligent surveillance systems. However, it presents significant challenges due to issues such as heavy occlusion and variations in appearance that arise from multiple camera perspectives and congested scenarios. In this paper, we propose an effective system that integrates both appearance and spatial-temporal information to address these problems, consisting of three specially designed modules: (1) A Multi-Object Tracking (MOT) method that minimizes ID-switch errors and generates accurate trajectory appearance features for MCPT. (2) A robust intra-camera association method that leverages both appearance and spatial-temporal information. (3) An effective post-processing module comprising multi-step processing. Our proposed system is evaluated on the test set of Track1 for the 2023 AI CITY CHALLENGE, and the experimental results demonstrate its effectiveness, achieving an IDF1 score of 93.31% and ranking 3rd on the leaderboard.

查看原文本刊更多论文

融合外观和时空信息的多相机人物跟踪

多摄像机人员跟踪是智能监控系统中的一项重要任务。然而，由于多重相机视角和拥挤场景引起的严重遮挡和外观变化等问题，它提出了重大挑战。在本文中，我们提出了一个有效的集成外观和时空信息的系统来解决这些问题，该系统由三个专门设计的模块组成:(1)多目标跟踪(MOT)方法，该方法可以最大限度地减少MCPT的id切换误差并生成准确的轨迹外观特征。(2)利用图像外观和时空信息的鲁棒相机内关联方法。(3)包含多步处理的有效后处理模块。我们提出的系统在2023 AI CITY CHALLENGE的Track1测试集上进行了评估，实验结果证明了它的有效性，实现了93.31%的IDF1得分，在排行榜上排名第三。

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

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

自引率

0.00%

发文量