Pedestrian Attribute Recognition in Surveillance Scenario:A Survey and Future Perspectives on Frame vs.Video Based Methods
Pedestrian attribute recognition aims to predict the predefined attributes of a target pedestrian,gen-erating a structured description of the pedestrian,which includes semantic information like age,gender,cloth-ing,accessories and other levels of semantic information.Due to its wide application in the field of video sur-veillance and security,pedestrian attribute recognition has been widely concerned by researchers.With the rapid development of deep learning,researchers have proposed many methods to recognize pedestrian attrib-utes in order to obtain more accurate results.In view of the challenges faced by this task in complex scenes,such as unclear surveillance scenes,pedestrian status change,occlusion,etc.,this paper reviews frame-based and video-based pedestrian attribute recognition methods in surveillance scenario.First,the research back-ground and the concept of pedestrian attribute recognition are introduced,and the problems and challenges faced by the current research are pointed out.The pedestrian attribute recognition methods are classified ac-cording to two different sample types of"single frame"and"sequential frames captured from video".The newly proposed methods are summarized on the basis of techniques and ideas adopted in the attribute recogni-tion process.Then the current commonly employed datasets and experimental results are analyzed.Finally,from the four aspects of state-guided pedestrian attribute recognition,tri-dimensional attribute,multi-task fusion and new data set construction,the future direction of this field is prospected.
deep learningintelligent visual surveillancemulti-label classificationpedestrian attribute recogni-tiondatasets analysis
万方数据
维普
