文献类型：会议论文

英文题名：RECOGNIZING HUMAN ACTIONS FROM LOW-RESOLUTION VIDEOS BY REGION-BASED MIXTURE MODELS

作者：Zhao, Ying[1,2,3];Di, Huijun[1];Zhang, Jian[2];Lu, Yao[1];Lv, Feng[1]

第一作者：赵英;Zhao, Ying

通讯作者：Lu, Y[1]

机构：[1]Beijing Inst Technol, Beijing Lab Intelligent Informat Technol, Beijing, Peoples R China;[2]Univ Technol Sydney, Adv Analyt Inst, Sydney, NSW, Australia;[3]Beijing Union Univ, Teachers Coll, Beijing, Peoples R China

第一机构：Beijing Inst Technol, Beijing Lab Intelligent Informat Technol, Beijing, Peoples R China

通讯机构：[1]corresponding author), Beijing Inst Technol, Beijing Lab Intelligent Informat Technol, Beijing, Peoples R China.

会议论文集：IEEE International Conference on Multimedia & Expo (ICME)

会议日期：JUL 11-15, 2016

会议地点：Seattle, WA

语种：英文

外文关键词：Low-resolution(LR); Action Recognition; Elastic Motion Tracking; Mixture Model

摘要：Recognizing human action from low-resolution (LR) videos is essential for many applications including large-scale video surveillance, sports video analysis and intelligent aerial vehicles. Currently, state-of-the-art performance in action recognition is achieved by the use of dense trajectories which are extracted by optical flow algorithms. However, the optical flow algorithms are far from perfect in LR videos. In addition, the spatial and temporal layout of features is a powerful cue for action discrimination. While, most existing methods encode the layout by previously segmenting body parts which is not feasible in LR videos. Addressing the problems, we adopt the Layered Elastic Motion Tracking (LEMT) method to extract a set of long-term motion trajectories and a long-term common shape from each video sequence, where the extracted trajectories are much denser than those of sparse interest points(SIPs); then we present a hybrid feature representation to integrate both of the shape and motion features; and finally we propose a Region-based Mixture Model (RMM) to be utilized for action classification. The RMM models the spatial layout of features without any needs of body parts segmentation. Experiments are conducted on two publicly available LR human action datasets. Among which, the UT-Tower dataset is very challenging because the average height of human figures is only about 20 pixels. The proposed approach attains near-perfect accuracy on both of the datasets