Sensors 2013, 13(11), 14398-14416; doi:10.3390/s131114398
Article

A Generalized Pyramid Matching Kernel for Human Action Recognition in Realistic Videos

Received: 6 September 2013; in revised form: 30 September 2013 / Accepted: 5 October 2013 / Published: 24 October 2013
(This article belongs to the Section Physical Sensors)
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract: Human action recognition is an increasingly important research topic in the fields of video sensing, analysis and understanding. Caused by unconstrained sensing conditions, there exist large intra-class variations and inter-class ambiguities in realistic videos, which hinder the improvement of recognition performance for recent vision-based action recognition systems. In this paper, we propose a generalized pyramid matching kernel (GPMK) for recognizing human actions in realistic videos, based on a multi-channel “bag of words” representation constructed from local spatial-temporal features of video clips. As an extension to the spatial-temporal pyramid matching (STPM) kernel, the GPMK leverages heterogeneous visual cues in multiple feature descriptor types and spatial-temporal grid granularity levels, to build a valid similarity metric between two video clips for kernel-based classification. Instead of the predefined and fixed weights used in STPM, we present a simple, yet effective, method to compute adaptive channel weights of GPMK based on the kernel target alignment from training data. It incorporates prior knowledge and the data-driven information of different channels in a principled way. The experimental results on three challenging video datasets (i.e., Hollywood2, Youtube and HMDB51) validate the superiority of our GPMK w.r.t. the traditional STPM kernel for realistic human action recognition and outperform the state-of-the-art results in the literature.
Keywords: video analysis; human action recognition; pyramid matching kernel; kernel-based classification method
PDF Full-text Download PDF Full-Text [1724 KB, Updated Version, uploaded 21 June 2014 09:52 CEST]
The original version is still available [1732 KB, uploaded 21 June 2014 09:52 CEST]

Export to BibTeX |
EndNote


MDPI and ACS Style

Zhu, J.; Zhou, Q.; Zou, W.; Zhang, R.; Zhang, W. A Generalized Pyramid Matching Kernel for Human Action Recognition in Realistic Videos. Sensors 2013, 13, 14398-14416.

AMA Style

Zhu J, Zhou Q, Zou W, Zhang R, Zhang W. A Generalized Pyramid Matching Kernel for Human Action Recognition in Realistic Videos. Sensors. 2013; 13(11):14398-14416.

Chicago/Turabian Style

Zhu, Jun; Zhou, Quan; Zou, Weijia; Zhang, Rui; Zhang, Wenjun. 2013. "A Generalized Pyramid Matching Kernel for Human Action Recognition in Realistic Videos." Sensors 13, no. 11: 14398-14416.

Sensors EISSN 1424-8220 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert