Target recognition of ground armor based on combinatorial part model

Target recognition is a key technology in guided weapon systems. In this paper, an algorithm of target recognition based on local part is presented for the armored target in complex background. By constructing a variable target model to identify the local part of the target, the latent support vector machine is used to find the position of the part, and the position of the whole target is identified. The recognition rate is higher compared with the traditional method of identifying the whole feature of the target.