EVALUATION OF A CLASS OF SEGMENTERS FOR IR IMAGERY

Authors
  1. Sevigny, L.
Corporate Authors
Defence Research Establishment Valcartier, Valcartier QUE (CAN)
Abstract
The report presents an evaluation of the performance of 6 algorithms dedicated to segmentation of targets in IR imagery. These segmentation algorithms or segmenters are based on the single assumption that the targets display a larger thermal signature than the background. The experimental results show that the intensity, contrast and variance features are the most effective in discriminating the targets from the nontargets. The classification results one can expect from these features together with the segmenter that proves to be the best amount to a detection rate in excess of 90% with a false alarm rate not greater than 3%.
Report Number
DREV-4172/80 —
Date of publication
15 May 1980
Number of Pages
78
DSTKIM No
80-02900
CANDIS No
90583
Format(s):
Hardcopy;Originator's fiche received by DSIS

Permanent link

Document 1 of 1

Date modified: