Improved collaborative representation model with multitask learning using spatial support for target detection in hyperspectral imagery

We propose an improved collaborative representation model with multitask learning using spatial support (ICRTD-MTL) for target detection (TD) in hyperspectral imagery. The proposed model consists of the following aspects. First, multiple features are extracted from the hyperspectral image to represent pixels from different perspectives. Next, we apply these features into the unified CRTD-MTL to acquire a collaborative vector for each feature. To adjust the contribution of each feature, a weight coefficient is included in the optimization problem. Once the collaborative vector is obtained, the class of the test sample can be determined by the characteristics of the collaborative vector on reconstruction. Finally, the spatial correlation and spectral similarity of adjacent neighboring pixels are incorporated into each feature to improve the detection accuracy. The experimental results suggest that the proposed algorithm obtains an excellent performance.