典型文献
Human steering angle estimation in video based on key point detection and Kalman filter
文献摘要：
Human pose recognition and estimation in video is pervasive. However, the process noise and local occlusion bring great challenge to pose recognition. In this paper, we introduce the Kalman fi lter into pose recognition to reduce noise and solve local occlusion problem. The core of pose recognition in video is the fast detection of key points and the calculation of human steering angles. Thus, we fi rst build a human key point detection model. Frame skipping is performed based on the Hamming distance of the hash value of every two adjacent frames in video. Noise reduction is performed on key point coordinates with the Kalman fi lter. To calculate the human steering angle, current state information of key points is predicted using the optimal estimation of key points at the previous time. Then human steering angle can be calculated based on current and previous state information. The improved SENet, NLNet and GCNet modules are integrated into key point detection model for improving accuracy. Tests are also given to illustrate the effectiveness of the proposed algorithm.
文献关键词：
中图分类号：
作者姓名：
Yanpeng Hu;Yuxuan Liu;Yanguang Xu;Yinghui Wang
作者机构：
School of Automation and Electrical Engineering,University of Science and Technology Beijing,Beijing 100083,China;KE Holdings Inc.,Beijing 100085,China
文献出处：
引用格式：
[1]Yanpeng Hu;Yuxuan Liu;Yanguang Xu;Yinghui Wang-.Human steering angle estimation in video based on key point detection and Kalman filter)[J].控制理论与技术（英文版）,2022(03):408-417
A类：
lter,NLNet
B类：
Human,steering,estimation,video,key,detection,Kalman,filter,recognition,pervasive,However,process,noise,local,occlusion,bring,great,challenge,In,this,paper,introduce,into,reduce,solve,problem,core,fast,points,calculation,human,angles,Thus,rst,build,model,Frame,skipping,performed,Hamming,distance,hash,value,every,two,adjacent,frames,Noise,reduction,coordinates,To,current,state,information,predicted,using,optimal,previous,Then,can,be,calculated,improved,SENet,GCNet,modules,are,integrated,improving,accuracy,Tests,also,given,illustrate,effectiveness,proposed,algorithm
AB值：
0.472155
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
