Multi-sensor Image Interpretation Using Laser Radar and Thermal Images
Abstract
This paper presents a knowledge-based system to interpret registered laser radar and thermal images. The object is to detect and recognize man-made objects at kilometer range in outdoor scenes. The multisensor fusion approach is applied to various sensing modalities (range, intensity, velocity, and thermal) to improve both image segmentation and interpretation. The ability to use multiple sensors greatly helps an intelligent platform to understand and interact with its environment. The knowledge-based interpretation system, AIMS, is constructed using KEE and Lisp. Low-level attributes of image segments (regions) are computed by the segmentation modules and then converted into the KEE format. The interpretation system applies forward chaining in a bottom-up fashion to derive object-level interpretations from data bases generated by low- level processing modules. Segments are grouped into objects and then objects are classified into pre-defined categories. AIMS employs a two-tiered software structure. The efficiency of AIMS is enhanced by transferring non-symbolic processing tasks to a concurrent service manager (program). Therefore, tasks with different characteristics are executed using different software tools and methodologies.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 1991
- Accession Number
- ADA238245
Entities
People
- Chen-chau Chu
- J. K. Aggarwal
Organizations
- University of Texas at Austin