The Research Of Moving Small Target Tracking In Infrared Images

The technology of moving objects tracking is a meaningful subject in computer vision, It has a lot of applications in many fields such as missile controlling-and-guiding, video surveillance, medical treatment, traffic control, etc. Since IR imaging possesses many advantages, it has become the trend and direction for current development and study of tracking technologies worldwide. In this paper, we study the technology of real time small moving objects tracking in IR image sequences. The main achievements of this paper are as follows: The technique of background suppression in IR image is discussed and studied principally. Based on the outcomes developed, an algorithm of small target detection based on pattern lateral inhibition is proposed. Experiments results demonstrate the approach proposed to be effective in detecting small target in clutter. On the basis of former work, mainly studies the methods for IR small target tracking in high clutter background. The problems of track initiation, deletion and data association are briefly discussed. A data association algorithm based on multiple features of target is proposed. A method for the realization of intelligent multi-algorithm is proposed. The condition of judgement for the changeover of the tracking algorithm are worked out, so that the tracker can choose the optimal mode automatically and intelligently, and by which it ensures that the targets are tracked steadily. A real time infrared target tracking system based on ADSP140610 is discussed. The fast matching algorithms are adopted in soft design of this system. In hardware, a parallel structure with two ADSP14060 is adopted, and the problem of algorithm distribution is discussed.