Efficient approach to segment man-made targets from unmanned aerial vehicle imagery

A typical target recognition system usually involves three stages: image en hancement, image segmentation, and object identification. We propose an eff icient image segmentation approach to segment man-made targets from unmanne d aerial vehicle (UAV) imagery using curvature information derived from ima ge histogram smoothed by Bezier splines. The experimental results show that by enhancing the histogram instead of the original image, similar segmenta tion results can be obtained in a more efficient way. Algorithm complexity is analyzed. Segmentation results from images enhanced by variants of diffu sion methods are also presented for comparison. Real-time automatic target recognition (ATR) is the main objective of the proposed approach. (C) 2000 Society of Photo-Optical instrumentation Engineers. [S0091-3286(00)01905-X] .