Cognition Models for Visual Target Discrimination
Abstract
This paper reports the results of a Phase 1 SBIR project to identify image processing algorithms for use in modeling human visual discrimination of military ground vehicles. The approach assumes that the front end of human visual perception is modeled by two stage luminance and color opponent processing, followed by multi-resolution spatial filtering. The report examines candidate algorithms for texture and intensity segmentation, shape perception, and subsequent target categorization in the target discrimination process.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 21, 1997
- Accession Number
- ADA371141
Entities
People
- Gary Witus