文献类型：期刊文献

中文题名：Survey of Pedestrian Action Recognition Techniques for Autonomous Driving

英文题名：Survey of Pedestrian Action Recognition Techniques for Autonomous Driving

作者：Li Chen[1];Nan Ma[1];Patrick Wang[2];Jiahong Li[1];Pengfei Wang[3];Guilin Pang[4];Xiaojun Shi[4]

机构：[1]Beijing Key Laboratory of Information Service Engineering,College of Robotics,Beijing Union University,Beijing 100101,China;[2]Northeastern University,Boston,MA 02115,USA;[3]the Communication and Information Center of Ministry of Emergency Management of the People’s Republic of China,Beijing 100013,China;[4]the College of Robotics,Beijing Union University,Beijing 100101,China

第一机构：北京联合大学机器人学院|北京联合大学北京市信息服务工程重点实验室

年份：2020

卷号：0

期号：4

起止页码：458-470

中文期刊名：清华大学学报：自然科学版（英文版）

收录：Scopus;CSCD:【CSCD2019_2020】；PubMed;

基金：partially funded by the National Natural Science Foundation of China(Nos.61871038,61803034,and 61672178);Beijing Natural Science Foundation(No.4182022);Beijing Union University Graduate Funding Project.

语种：英文

中文关键词：autonomous;driving;pedestrian;action;recognition;action;datasets;two-stream;network

外文关键词：autonomous driving;pedestrian action recognition;action datasets;two-stream network

摘要：The development of autonomous driving has brought with it requirements for intelligence,safety,and stability.One example of this is the need to construct effective forms of interactive cognition between pedestrians and vehicles in dynamic,complex,and uncertain environments.Pedestrian action detection is a form of interactive cognition that is fundamental to the success of autonomous driving technologies.Specifically,vehicles need to detect pedestrians,recognize their limb movements,and understand the meaning of their actions before making appropriate decisions in response.In this survey,we present a detailed description of the architecture for pedestrian action recognition in autonomous driving,and compare the existing mainstream pedestrian action recognition techniques.We also introduce several commonly used datasets used in pedestrian motion recognition.Finally,we present several suggestions for future research directions.
The development of autonomous driving has brought with it requirements for intelligence, safety, and stability.One example of this is the need to construct effective forms of interactive cognition between pedestrians and vehicles in dynamic, complex, and uncertain environments.Pedestrian action detection is a form of interactive cognition that is fundamental to the success of autonomous driving technologies.Specifically, vehicles need to detect pedestrians, recognize their limb movements, and understand the meaning of their actions before making appropriate decisions in response.In this survey, we present a detailed description of the architecture for pedestrian action recognition in autonomous driving, and compare the existing mainstream pedestrian action recognition techniques.We also introduce several commonly used datasets used in pedestrian motion recognition.Finally, we present several suggestions for future research directions.