{"title":"Unsupervised video anomaly detection in UAVs: a new approach based on learning and inference","authors":"Gang Liu, Lisheng Shu, Yuhui Yang, Chen Jin","doi":"10.3389/frsc.2023.1197434","DOIUrl":null,"url":null,"abstract":"In this paper, an innovative approach to detecting anomalous occurrences in video data without supervision is introduced, leveraging contextual data derived from visual characteristics and effectively addressing the semantic discrepancy that exists between visual information and the interpretation of atypical incidents. Our work incorporates Unmanned Aerial Vehicles (UAVs) to capture video data from a different perspective and to provide a unique set of visual features. Specifically, we put forward a technique for discerning context through scene comprehension, which entails the construction of a spatio-temporal contextual graph to represent various aspects of visual information. These aspects encompass the manifestation of objects, their interrelations within the spatio-temporal domain, and the categorization of the scenes captured by UAVs. To encode context information, we utilize Transformer with message passing for updating the graph's nodes and edges. Furthermore, we have designed a graph-oriented deep Variational Autoencoder (VAE) approach for unsupervised categorization of scenes, enabling the extraction of the spatio-temporal context graph across diverse settings. In conclusion, by utilizing contextual data, we ascertain anomaly scores at the frame-level to identify atypical occurrences. We assessed the efficacy of the suggested approach by employing it on a trio of intricate data collections, specifically, the UCF-Crime, Avenue, and ShanghaiTech datasets, which provided substantial evidence of the method's successful performance.","PeriodicalId":33686,"journal":{"name":"Frontiers in Sustainable Cities","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2023-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Sustainable Cities","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/frsc.2023.1197434","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
In this paper, an innovative approach to detecting anomalous occurrences in video data without supervision is introduced, leveraging contextual data derived from visual characteristics and effectively addressing the semantic discrepancy that exists between visual information and the interpretation of atypical incidents. Our work incorporates Unmanned Aerial Vehicles (UAVs) to capture video data from a different perspective and to provide a unique set of visual features. Specifically, we put forward a technique for discerning context through scene comprehension, which entails the construction of a spatio-temporal contextual graph to represent various aspects of visual information. These aspects encompass the manifestation of objects, their interrelations within the spatio-temporal domain, and the categorization of the scenes captured by UAVs. To encode context information, we utilize Transformer with message passing for updating the graph's nodes and edges. Furthermore, we have designed a graph-oriented deep Variational Autoencoder (VAE) approach for unsupervised categorization of scenes, enabling the extraction of the spatio-temporal context graph across diverse settings. In conclusion, by utilizing contextual data, we ascertain anomaly scores at the frame-level to identify atypical occurrences. We assessed the efficacy of the suggested approach by employing it on a trio of intricate data collections, specifically, the UCF-Crime, Avenue, and ShanghaiTech datasets, which provided substantial evidence of the method's successful performance.