This paper describes a method for using color images for highly effective ground-level ATR. Although extensive tests on the Ft. Carson data and at the live UGV Demo-C have been successful, and in some instances, better than IR-based ATR, we do not intend to recommend that color be used in exclusion of other ATR technologies. This work demonstrates that the color-based method described can be used as an effective, yet inexpensive addition to existing systems. The number of false alarms indicates that the method is more useful as a focus-of- attention mechanism, than for full-fledged recognition. The learning and classification method described in this paper has been applied, with similar success, to other problems such as road/lane detection, skin recognition, detection of wildlife in aerial imagery, ground-level terrain detection and landmark recognition. The images and results from the Ft. Carson tests are available at the following world-wide-web address:
http://vis-www.cs.umass.edu/projects/learning/mdt.html.
Shashi Buluswar