Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Grouping Sensory Primitives for Object Recognition and Tracking

Published

Author(s)

Rajmohan Madhavan, M Foedissch, Tommy Chang, Tsai Hong Hong

Abstract

In this paper, we describe our recent efforts in grouping sensory data into meaningful entities. Our grouping philosophy is based on perceptual organization principles using gestalt hypotheses where we impose structural regularity on sensory primitives stemming from a common underlying cause. We present results using field data from UGVs and outline the utility of our research in object recognition and tracking for autonomous vehicle navigation. In addition, we show how the grouping efforts can be useful for constructing symbolic topological maps when data from different sensing modalities are fused in a bottom-up and top-down fashion.
Conference Dates
October 19-21, 2005
Conference Location
Washington, DC
Conference Title
Applied Imagery Pattern Recognition (AIPR) 2005

Keywords

grouping, 4D/RCS, perceptual organization, gestalt psychology

Citation

Madhavan, R. , Foedissch, M. , Chang, T. and , T. (2007), Grouping Sensory Primitives for Object Recognition and Tracking, Applied Imagery Pattern Recognition (AIPR) 2005, Washington, DC, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=824592 (Accessed April 24, 2024)
Created December 3, 2007, Updated February 19, 2017