摘要
行为识别的过程很大程度上可以看作特征提取与分类器相结合,故特征提取方法的优劣直接影响最终识别效果。与静态图像物体识别相比,视频中人体行为识别特征提取更易受到动态背景、采集设备运动、视角和光照等因素影响人体,从而对研究人员的工作提出了很大挑战。为此,综合了近几年对行为识别特征提取系统分类和不同类型行为识别特征提取方法以及常用行为识别数据库等领域研究的最新进展,探讨了目前研究难点,阐述了与未来可能的研究发展方向。
The process of behavior recognition can be regarded as the combination of feature extraction and classifier to a large extent.Compared to static image object recognition,video feature extraction of human behavior recognition is more susceptible to such factors as dynamic background,acquisition device motion,perspective and illumination,so it poses great challenges to researchers.Based on the systematic classification of behavior recognition feature extraction,according to the different types of behavior recognition feature extraction methods and common behavior recognition database,the behavior recognition feature extraction is systematically classified to expound the latest research progress.And the current research difficulties and possible future research directions are discussed.
作者
张会珍
刘云麟
任伟建
刘欣瑜
ZHANG Huizhen;LIU Yunlin;REN Weijian;LIU Xinyu(School of Electrical Engineering&Information,Northeast Petroleum University,Daqing 163318,China;Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control,Northeast Petroleum University,Daqing 163318,China;Information Management Office,Sinopec Marketing Shanghai Company,Shanghai 200002,China)
出处
《吉林大学学报(信息科学版)》
CAS
2020年第3期360-370,共11页
Journal of Jilin University(Information Science Edition)
基金
黑龙江省自然科学基金资助项目(F2018004)。
关键词
计算机视觉
行为识别
特征提取
行为识别数据集
computer vision
behavior recognition
feature extraction
behavior identification dataset