Research On Hyperspectral Image Target Detection Algorithms

With the ordinary target detection algorithm based on high spatial resolution remote sensing image is different, the target detection of hyperspectral image is mainly based on the differences of the goals and ground features spectral characteristics. Generally, due to the lower spatial resolution of hyperspectral image, and the effect of the target size and complex features, make the interested target in hyperspectral images often in a state of subpixel or weak information. Therefore, the traditional manual visual interpretation methods based on spatial form cannot achieve the detection of this kind of targets. This research aimed at applying the image fusion and pattern recognition methods, fully excavating the spectral and spatial information of hyperspectral data, to realize the effective detection of interested target.For traditional orthogonal subspace projection method, before performing target detection, we must acquire the background spectrum vectors. However, in many cases, we cannot obtain the prior knowledge of the background spectrum accurately. While the constrained energy minimization algorithm detect targets without a priori information of background spectrum, but the algorithm has a poor performance on the big target detection and cannot effectively extract the target contour. For this reason, we propose a sample weighted orthogonal subspace projection algorithm, by defining the weighted autocorrelation matrix to estimation background, and then use the orthogonal subspace projection method to detect the targets. The improved algorithm effectively reduces the proportion of target pixels in the sample autocorrelation matrix, and has better inhibitory effect to the background. It overcomes the inherent defects of orthogonal subspace projection and constrained energy minimization, the experimental results shows better detection effect.