{"title":"An algorithm for abnormal behavior recognition based on sharing human target tracking features","authors":"","doi":"10.1007/s41315-024-00329-y","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> <p>Human behavior recognition is a hot research topic in the field of computer vision, and a complete behavior recognition usually includes human detection, human tracking and behavior recognition. At present, the two tasks of human tracking and abnormal behavior recognition based on deep learning are mostly executed separately, and the related feature information in the two tasks cannot be fully utilized, resulting in high time cost and resource consumption of the final abnormal behavior recognition algorithm. The problem greatly limits the widespread application of abnormal behavior recognition. In order to improve the performance of the algorithm a novel model for abnormal behaviors recognition based on human target tracking is proposed, which implements the process of recognizing abnormal behaviors after human target tracking through feature sharing. First, the real-time multi-domain convolutional neural network is improved by introducing a spatial attention mechanism to improve its tracking of a particular human body in a video series. Then the output of the convolutional layer in MDnet is used as the input of the abnormal behavior recognition network, and these features are combined with CNN and LSTM to realize human abnormal behavior recognition. During the network training process, a multi-task learning approach was used to train a model for human tracking and behaviour recognition. Six types of abnormal behaviors selected on the CASIA Behavioural Analytics dataset and 12 types of behaviours selected on the NTU database are used to train and test the network model. According to test results, the proposed model is capable of tracking human targets precisely and in real time (26 frames per second). The proposed model can also distinguish abnormal behaviors of tracking targets with a recognition rate of 92.1%. The human features obtained in the tracking model is used as the input of the abnormal behavior recognition network, so the feature sharing of tracking and recognition is achieved, and a complete abnormal behavior recognition framework including target tracking, feature extraction, and behavior recognition is established. There is great practical significance to the proposed method.</p>","PeriodicalId":44563,"journal":{"name":"International Journal of Intelligent Robotics and Applications","volume":null,"pages":null},"PeriodicalIF":2.1000,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Intelligent Robotics and Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s41315-024-00329-y","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ROBOTICS","Score":null,"Total":0}
引用次数: 0
Abstract
Human behavior recognition is a hot research topic in the field of computer vision, and a complete behavior recognition usually includes human detection, human tracking and behavior recognition. At present, the two tasks of human tracking and abnormal behavior recognition based on deep learning are mostly executed separately, and the related feature information in the two tasks cannot be fully utilized, resulting in high time cost and resource consumption of the final abnormal behavior recognition algorithm. The problem greatly limits the widespread application of abnormal behavior recognition. In order to improve the performance of the algorithm a novel model for abnormal behaviors recognition based on human target tracking is proposed, which implements the process of recognizing abnormal behaviors after human target tracking through feature sharing. First, the real-time multi-domain convolutional neural network is improved by introducing a spatial attention mechanism to improve its tracking of a particular human body in a video series. Then the output of the convolutional layer in MDnet is used as the input of the abnormal behavior recognition network, and these features are combined with CNN and LSTM to realize human abnormal behavior recognition. During the network training process, a multi-task learning approach was used to train a model for human tracking and behaviour recognition. Six types of abnormal behaviors selected on the CASIA Behavioural Analytics dataset and 12 types of behaviours selected on the NTU database are used to train and test the network model. According to test results, the proposed model is capable of tracking human targets precisely and in real time (26 frames per second). The proposed model can also distinguish abnormal behaviors of tracking targets with a recognition rate of 92.1%. The human features obtained in the tracking model is used as the input of the abnormal behavior recognition network, so the feature sharing of tracking and recognition is achieved, and a complete abnormal behavior recognition framework including target tracking, feature extraction, and behavior recognition is established. There is great practical significance to the proposed method.
期刊介绍:
The International Journal of Intelligent Robotics and Applications (IJIRA) fosters the dissemination of new discoveries and novel technologies that advance developments in robotics and their broad applications. This journal provides a publication and communication platform for all robotics topics, from the theoretical fundamentals and technological advances to various applications including manufacturing, space vehicles, biomedical systems and automobiles, data-storage devices, healthcare systems, home appliances, and intelligent highways. IJIRA welcomes contributions from researchers, professionals and industrial practitioners. It publishes original, high-quality and previously unpublished research papers, brief reports, and critical reviews. Specific areas of interest include, but are not limited to:Advanced actuators and sensorsCollective and social robots Computing, communication and controlDesign, modeling and prototypingHuman and robot interactionMachine learning and intelligenceMobile robots and intelligent autonomous systemsMulti-sensor fusion and perceptionPlanning, navigation and localizationRobot intelligence, learning and linguisticsRobotic vision, recognition and reconstructionBio-mechatronics and roboticsCloud and Swarm roboticsCognitive and neuro roboticsExploration and security roboticsHealthcare, medical and assistive roboticsRobotics for intelligent manufacturingService, social and entertainment roboticsSpace and underwater robotsNovel and emerging applications