基于本征关节的高效3D行为识别外文翻译.docxVIP

电子科技大学学士学位论文 外文资料原文 PAGE 52 PAGE 53 外文资料原文 外文资料原文 Effective 3D Action Recognition Using EigenJoints Xiaodong Yang and YingLi Tian Department of Electrical Engineering The City College of New York, CUNY {xyang02, ytian}@ccny.cuny.edu Abstract — In this paper, we propose an effective method to recognize human actions using 3D skeleton joints recovered from 3D depth data of RGBD cameras. We design a new action feature descriptor for action recognition based on differences of skeleton joints, i.e., EigenJoints which combine action information including static posture, motion property, and overall dynamics. Accumulated Motion Energy (AME) is then proposed to perform informative frameselection, which is able to remove noisy frames and reduce computational cost.We employ non-parametric Na?ve-Bayes-Nearest-Neighbor (NBNN) to classify multiple actions. The experimental results on several challenging datasets demonstrate that our approach outperforms the state-of-the-art methods. In addition, we investigate how many frames are necessary for our method to perform classification in the scenario of online action recognition. We observe that the first 30% to 40% frames are sufficient to achieve comparable results to that using the entire video sequences on the MSR Action3D dataset. Keywords — action recognition, RGBD camera, depth data, skeleton joints, 3D action feature representation 1. Introduction Automatic human action recognition has been widely applied in a number of real-world applications, e.g., video surveillance, content-based video search, human-computer interaction, and health-care [5, 16, 18, 27, 29, 31]. Traditional research mainly concentrates on action recognition of video sequences captured by RGB cameras [2, 3, 6, 9, 10, 12, 30]. In this case, a video is a sequence of 2D frames with RGB images in chronological order. There has been extensive research in the literature on action recognition for such 2D videos. The spatio-temporal volume-based methods h