Real-time detection of rapid moving infrared target on variation background

For the condition where monitor point and target move rapidly simultaneously, a real-time target detection algorithm is proposed in this paper. The algorithm is based on a region theory which fuses four region algorithms, i.e., region of interest (ROI) algorithm, region enhancement algorithm, region growing algorithm and sequence image interframe region algorithm. It obtains ROI by analyzing infrared target and locally enhances ROI on the basis of histogram statistic to extract target region. Then it segments the target by region growing algorithm. Finally, it determines the target by the characteristics of sequence image interframe and pattern matching. Experiment results in vehicle infrared navigation system show that the algorithm based on the region theory is very efficient and real-time to detect rapid moving target on variation background.