Target detection of hyperspectral image has always been a hot research topic, especially due to its important applications in military and civilian remote sensing. This paper employs the idea of classification and proposes a novel detection framework which incorporates dictionary learning and discriminative information. Due to the fact that target pixels lie in different subspace with background pixels, a novel detection model is proposed. In addition, a linear kernel is applied to project the image data into high-dimensional space, separating the target pixels and background pixels. Synthetic image and popular real hyperspectral image are used to evaluate our algorithm. Experimental results indicate that our proposed detector outperforms the traditional detection methods.
After years of development, military camouflage has formed a set of theoretical and technical systems represented by color camouflage. At present, a large number of camouflage technology research has been carried out for multispectral reconnaissance of visible and near-infrared. In order to better detect and identify the camouflage target, it is necessary to expand the new reconnaissance band and improve the spectral resolution of the reconnaissance instrument. In this paper, the research on camouflage target recognition technology is carried out through short-wave infrared hyperspectral imaging technology, and the camouflage target is identified by SAM, ACM and CEM algorithms respectively, and the characteristics of three methods in short-wave infrared camouflage target recognition are verified. This research can improve the ability to detect and identify camouflage targets and provide a new means for modern battlefield reconnaissance.