Variations of a Hough-Voting Action Recognition System

This paper presents two variations of a Hough-voting framework used for action recognition and shows classification results for low-resolution video and videos depicting human interactions. For low-resolution videos, where people performing actions are around 30 pixels, we adopt low-level features s...

Full description

Saved in:
Bibliographic Details
Published inRecognizing Patterns in Signals, Speech, Images and Videos pp. 306 - 312
Main Authors Waltisberg, Daniel, Yao, Angela, Gall, Juergen, Van Gool, Luc
Format Book Chapter
LanguageEnglish
Japanese
Published Berlin, Heidelberg Springer Berlin Heidelberg 2010
SeriesLecture Notes in Computer Science
Subjects
activity recognition
group action recognition
Hough-voting
human action recognition
low-resolution video
video analysis
Online AccessGet full text
ISBN9783642177101
3642177107
ISSN0302-9743
1611-3349
DOI10.1007/978-3-642-17711-8_31

Cover

More Information
Summary:This paper presents two variations of a Hough-voting framework used for action recognition and shows classification results for low-resolution video and videos depicting human interactions. For low-resolution videos, where people performing actions are around 30 pixels, we adopt low-level features such as gradients and optical flow. For group actions with human-human interactions, we take the probabilistic action labels from the Hough-voting framework for single individuals and combine them into group actions using decision profiles and classifier combination.
ISBN:9783642177101
3642177107
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-642-17711-8_31