Next Article in Journal
Behaviour of Zinc Complexes and Zinc Sulphide Nanoparticles Revealed by Using Screen Printed Electrodes and Spectrometry
Previous Article in Journal
Alignment of the Measurement Scale Mark during Immersion Hydrometer Calibration Using an Image Processing System
Article Menu

Export Article

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

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

1
Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
2
College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
*
Author to whom correspondence should be addressed.
Received: 6 September 2013 / Revised: 30 September 2013 / Accepted: 5 October 2013 / Published: 24 October 2013
(This article belongs to the Section Physical Sensors)
View Full-Text   |   Download PDF [1724 KB, 21 June 2014; original version 21 June 2014]   |  

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. View Full-Text
Keywords: video analysis; human action recognition; pyramid matching kernel; kernel-based classification method video analysis; human action recognition; pyramid matching kernel; kernel-based classification method
This is an open access article distributed under the Creative Commons Attribution License (CC BY 3.0).

Scifeed alert for new publications

Never miss any articles matching your research from any publisher
  • Get alerts for new papers matching your research
  • Find out the new papers from selected authors
  • Updated daily for 49'000+ journals and 6000+ publishers
  • Define your Scifeed now

SciFeed Share & Cite This Article

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.

Show more citation formats Show less citations formats

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Sensors EISSN 1424-8220 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top