基于时空的上下文融合视频异常检测

Chao Hu, Weibin Qiu, Weijie Wu, Liqiang Zhu
{"title":"基于时空的上下文融合视频异常检测","authors":"Chao Hu, Weibin Qiu, Weijie Wu, Liqiang Zhu","doi":"10.1109/PRMVIA58252.2023.00037","DOIUrl":null,"url":null,"abstract":"Video anomaly detection (VAD) detects target objects such as people and vehicles to discover abnormal events in videos. There are abundant spatio-temporal context information in different objects of videos. Most existing methods pay more attention to temporal context than spatial context in VAD. The spatial context information represents the relationship between the detection target and surrounding targets. Anomaly detection makes a lot of sense. To this end, a video anomaly detection algorithm based on target spatio-temporal context fusion is proposed. Firstly, the target in the video frame is extracted through the target detection network to reduce background interference. Then the optical flow map of two adjacent frames is calculated. Motion features are used multiple targets in the video frame to construct spatial context simultaneously, re-encoding the target appearance and motion features, and finally reconstructing the above features through the spatiotemporal dual-stream network, and using the reconstruction error to represent the abnormal score. The algorithm achieves frame-level AUCs of 98.5% on UCSDped2 and 86.3% on Avenue datasets. On UCSDped2 dataset, the spatio-temporal dual-stream network improves frames by 5.1% and 0.3%, respectively, compared to the temporal and spatial stream networks. After using spatial context encoding, the frame-level AUC is enhanced by 1%, which verifies the method’s effectiveness.","PeriodicalId":221346,"journal":{"name":"2023 International Conference on Pattern Recognition, Machine Vision and Intelligent Algorithms (PRMVIA)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2001-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"25","resultStr":"{\"title\":\"Spatio-Temporal-based Context Fusion for Video Anomaly Detection\",\"authors\":\"Chao Hu, Weibin Qiu, Weijie Wu, Liqiang Zhu\",\"doi\":\"10.1109/PRMVIA58252.2023.00037\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Video anomaly detection (VAD) detects target objects such as people and vehicles to discover abnormal events in videos. There are abundant spatio-temporal context information in different objects of videos. Most existing methods pay more attention to temporal context than spatial context in VAD. The spatial context information represents the relationship between the detection target and surrounding targets. Anomaly detection makes a lot of sense. To this end, a video anomaly detection algorithm based on target spatio-temporal context fusion is proposed. Firstly, the target in the video frame is extracted through the target detection network to reduce background interference. Then the optical flow map of two adjacent frames is calculated. Motion features are used multiple targets in the video frame to construct spatial context simultaneously, re-encoding the target appearance and motion features, and finally reconstructing the above features through the spatiotemporal dual-stream network, and using the reconstruction error to represent the abnormal score. The algorithm achieves frame-level AUCs of 98.5% on UCSDped2 and 86.3% on Avenue datasets. On UCSDped2 dataset, the spatio-temporal dual-stream network improves frames by 5.1% and 0.3%, respectively, compared to the temporal and spatial stream networks. After using spatial context encoding, the frame-level AUC is enhanced by 1%, which verifies the method’s effectiveness.\",\"PeriodicalId\":221346,\"journal\":{\"name\":\"2023 International Conference on Pattern Recognition, Machine Vision and Intelligent Algorithms (PRMVIA)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2001-05-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"25\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 International Conference on Pattern Recognition, Machine Vision and Intelligent Algorithms (PRMVIA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/PRMVIA58252.2023.00037\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 International Conference on Pattern Recognition, Machine Vision and Intelligent Algorithms (PRMVIA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/PRMVIA58252.2023.00037","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 25

摘要

视频异常检测(Video anomaly detection, VAD)是指对视频中的目标对象(如人、车辆等)进行检测,发现视频中的异常事件。在视频的不同对象中存在着丰富的时空语境信息。现有的VAD研究方法大多注重时间背景而不是空间背景。空间上下文信息表示检测目标与周围目标之间的关系。异常检测很有意义。为此,提出了一种基于目标时空上下文融合的视频异常检测算法。首先,通过目标检测网络提取视频帧中的目标,降低背景干扰;然后计算相邻两帧的光流图。运动特征是利用视频帧中的多个目标同时构建空间上下文,对目标外观和运动特征进行重新编码,最后通过时空双流网络对上述特征进行重构,并用重构误差表示异常分数。该算法在UCSDped2和Avenue数据集上的帧级auc分别达到98.5%和86.3%。在UCSDped2数据集上,时空双流网络比时空双流网络分别提高了5.1%和0.3%的帧数。采用空间上下文编码后,帧级AUC提高了1%,验证了该方法的有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Spatio-Temporal-based Context Fusion for Video Anomaly Detection
Video anomaly detection (VAD) detects target objects such as people and vehicles to discover abnormal events in videos. There are abundant spatio-temporal context information in different objects of videos. Most existing methods pay more attention to temporal context than spatial context in VAD. The spatial context information represents the relationship between the detection target and surrounding targets. Anomaly detection makes a lot of sense. To this end, a video anomaly detection algorithm based on target spatio-temporal context fusion is proposed. Firstly, the target in the video frame is extracted through the target detection network to reduce background interference. Then the optical flow map of two adjacent frames is calculated. Motion features are used multiple targets in the video frame to construct spatial context simultaneously, re-encoding the target appearance and motion features, and finally reconstructing the above features through the spatiotemporal dual-stream network, and using the reconstruction error to represent the abnormal score. The algorithm achieves frame-level AUCs of 98.5% on UCSDped2 and 86.3% on Avenue datasets. On UCSDped2 dataset, the spatio-temporal dual-stream network improves frames by 5.1% and 0.3%, respectively, compared to the temporal and spatial stream networks. After using spatial context encoding, the frame-level AUC is enhanced by 1%, which verifies the method’s effectiveness.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信