Artificial bee colony (ABC) optimized edge potential function (EPF) approach to target recognition for low-altitude aircraft

This paper describes a novel shape-matching approach to visual target recognition for aircraft at low altitude. An artificial bee colony (ABC) algorithm with edge potential function (EPF) is proposed to accomplish the target recognition task for aircraft. EPF is adopted to provide a type of attractive pattern for a matching contour, which can be exploited by ABC algorithm conveniently. In this way, the best match can be obtained when the sketch image translates, reorients and scales itself to maximize the potential value. In addition, the convergence proof and computational complexity for the ABC algorithm are also given in detail. Series of experimental results demonstrate the feasibility and effectiveness of our proposed approach over the traditional genetic algorithm (GA). The proposed method can also be applied to solve the target recognition problems in mobile robots, industry production lines, and transportations.