Investigation Of Moving Targets Detecting And Tracking In Infrared Image Sequences

With the development of precision guided weapons, the requirements on information processing techniques for precision guidance is becoming higher and higher. This has become a key factor, which restricts the development of the weapon. At the same time, moving targets detection and tracking is one of the most important issues in image processing and computer vision. On the basis of the fundamental characteristics of IR imaging guidance, the current development status of guidance information processing methods, the main problems existed as well as the basic requirements on its practical engineering applications. This paper has made systematic in depth studies on various aspects as preprocessing of IR images, global movement estimating, moving targets detecting and tracking.The rnajor work and achievement of this paper are presented as follows:(1) Aimed at the problem of infrared image pre-progressing, first we compare several familiar method about background restraining, then some improvements were made on them.(2) According to the continuity of continuous frame in infrared image sequences, a algorithm which based on adaptive model matching is bringed forward, aimed at global movement estimating. Several improvements were made on the traditional model matching algorithm, such as model updating and matching rules, then we made movement equalizating for continuous frame in infrared image sequences.(3) A algorithm of moving targets detecting, which based on discontinous frame difference multiplication, is presented in the base of infrared image pre-progressing, global movement estimating and movement equalizating. Then we make a simulation using real infrared image sequences, whose result shows that the algorithm have a preferable effect of moving targets detecting.(4) Based on the analysis of movement's characteristic of target, movement status of moving targets were filterred by using IMM Kalman filter, which gain preferable effect of moving targets tracking.The simulation result shows that the approach presented by this paper is available and effective for solving the problem of small moving targets detecting and tracking in infrared image sequences with less resource expending.