20 August 2010 Classifying human activities using feature points
Author Affiliations +
Proceedings Volume 7820, International Conference on Image Processing and Pattern Recognition in Industrial Engineering; 78203S (2010) https://doi.org/10.1117/12.867443
Event: International Conference on Image Processing and Pattern Recognition in Industrial Engineering, 2010, Xi'an, China
Abstract
This paper presents a new classification method for single person's motion, which is represented by Haar wavelet transform and classified by Hidden Markov Models. What it solves is that the feature points are detected by Haar wavelet transform. We extract binary silhouette and segment them by cycle after creating the background model. Then the low-level features are detected by Haar wavelet transform and principal vectors are determined by Principal Component Analysis. We utilize Hidden Markov Models to train and classify cycle sequences, and demonstrate the usability. Compared with others, our approach is simple and effective in feature point detection, as the advantages of Haar wavelet transform detector lying in computational complexity. So the video surveillance based on these is practicable in (but not limited to) many scenarios where the background is known.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hao Zhang, Hao Zhang, Zhijing Liu, Zhijing Liu, Qing Wei, Qing Wei, Haiyong Zhao, Haiyong Zhao, Weihua Wang, Weihua Wang, } "Classifying human activities using feature points", Proc. SPIE 7820, International Conference on Image Processing and Pattern Recognition in Industrial Engineering, 78203S (20 August 2010); doi: 10.1117/12.867443; https://doi.org/10.1117/12.867443
PROCEEDINGS
7 PAGES


SHARE
RELATED CONTENT


Back to Top