期刊
2019 5TH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTING & COMMUNICATION SYSTEMS (ICACCS)
卷 -, 期 -, 页码 1012-1016出版社
IEEE
DOI: 10.1109/icaccs.2019.8728473
关键词
Action Recognition; Human Object Boundary Detection; Optical Flow; Support Vector Machine (SVM)
资金
- Digital India Corporation under Visvesvaraya Ph.D. Scheme for Electronics and IT under the department of MeitY government of India [PhD-MLA/4(13)/2015-16]
Human action recognition is an active research topic which is having real time challenges. Some of the challenges are speed of action, background noise and shape of the performing action. To handle these problem, in this paper the following works are proposed. By the help of optical flow, Bag of Bag of histogram of optical flow (BoHOF) is proposed which is useful to differentiate actions varying with speed of action. BoHOF features are calculated from segmented human objects. To remove the shadow effect, sobel edge filter is used combingly in horizontal and vertical direction. Median filtering is applied to suppress background noise. Histogram of oriented gradients (HOG) features are extracted from 3D projected planes and combined with BoHOF to extract maximum advantages of both the features. Finally, the multi-class SVM-based classifier with radial basis kernel is applied to recognize different human actions. The experiments are conducted on the benchmark KTH dataset and the experimental findings concludes that the proposed HAR technique provides better performance compared to the state-of-the-art techniques.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据