{"title":"The anomaly behavior detection algorithm with video-packet attention in transportation surveillance videos","authors":"Liyuan Wang, S. Yu, Ling Ding, Yuanxu Wu, Yu Chen, Jinsheng Xiao","doi":"10.1117/12.2671205","DOIUrl":null,"url":null,"abstract":"This paper proposes an end-to-end abnormal behavior detection network to detect strenuous movements in slow moving crowds, such as running, bicycling in transportation surveillance videos. The algorithm forms continuous video frames into a video packet and use the video packet feature extractor to obtain the spatio-temporal information. The implicit vector-based attention mechanism will work on the extracted video packet features to highlight the important features. We use fully connected layers to transform the space and reduce the computation. Finally, the packet-pooling maps the processed video packet features to the abnormal scores. The network input is flexible to cope with the form of video streams, and the network output is the abnormal score. The designed compound loss function will help the model improve the classification performance. This paper arranges several commonly used anomaly detection datasets and tests the algorithms on the integrated dataset. The experiment results show that the proposed algorithm has significant advantages in many objective metrics comparing with other anomaly detection algorithms.","PeriodicalId":227528,"journal":{"name":"International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1117/12.2671205","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
This paper proposes an end-to-end abnormal behavior detection network to detect strenuous movements in slow moving crowds, such as running, bicycling in transportation surveillance videos. The algorithm forms continuous video frames into a video packet and use the video packet feature extractor to obtain the spatio-temporal information. The implicit vector-based attention mechanism will work on the extracted video packet features to highlight the important features. We use fully connected layers to transform the space and reduce the computation. Finally, the packet-pooling maps the processed video packet features to the abnormal scores. The network input is flexible to cope with the form of video streams, and the network output is the abnormal score. The designed compound loss function will help the model improve the classification performance. This paper arranges several commonly used anomaly detection datasets and tests the algorithms on the integrated dataset. The experiment results show that the proposed algorithm has significant advantages in many objective metrics comparing with other anomaly detection algorithms.