Human Activity Recognition

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

A fundamental goal of work in recognition is to discover easily-computed visual features which are efficient indices of members of the class which is to be recognized. The hypothesis behind work in motion-based recognition is that features describing motion in the input can be efficient indices for large classes of objects and activities of interest to the computer vision and biological vision communities. Motion-based recognition encompasses the recognition of objects, object movements, situations, etc., when motion information is used as the primary cue for recognition. For example, optic flow can be used to recognize an imminent collision situation, without any prior recognition of objects or how they are moving. Similarly, objects could be recognized using characteristic motion parameters without prior determination of shape, texture, etc.
Original languageEnglish
Title of host publicationMotion-Based Recognition
Subtitle of host publicationPart I
EditorsMubarak Shah, Ramesh Jain
Place of PublicationDordrecht
PublisherSpringer
Pages147-170
Number of pages24
ISBN (Electronic)978-94-015-8935-2
ISBN (Print)978-90-481-4870-7
DOIs
Publication statusPublished - 1997

Publication series

NameComputational Imaging and Vision
PublisherSpringer Netherlands
Volume9
ISSN (Print)1381-6446

Fingerprint

Dive into the research topics of 'Human Activity Recognition'. Together they form a unique fingerprint.

Cite this