Figure 4: Post-classification binary image (left), with target boundaries extracted (right).
A decision tree for the camouflaged targets is built by providing sample pixels of the targets and background (e.g., vegetation, sky, rocks, etc.) from images taken under various conditions. After the decision tree is built, the next step is to build a lookup table for real-time ATR classification. This is accomplished by classifying (off-line) every possible RGB color value into target and background classes. Thereafter, given a color image, each pixel can be classified from the lookup table in real-time. The result of pixel classification is a binary image, in which all suspected target pixels are on (white), and the background pixels off (black). Figure 4 (left) shows the binary post-classification image for the scene from figure 1.
From the binary image, the clusters of target pixels are grouped, and bounding rectangles then extracted. Finally, overlapping bounding rectangles are merged, to produce a region-of-interest image, with the boxes drawn around the targets; figure 4 shows the result of grouping and extracting target regions from the corresponding binary image.