SMALL TARGET DETECTION BASED ON INFRARED IMAGE ADAPTIVE

This paper studies the multi-resolution analysis of infrared image preprocessing method based on wavelet transform, wavelet transform infrared image of small target for pretreatment, after pretreatment suppressed image background clutter, improved signal to noise ratio. On this basis, studies based on infrared image sequences generated background Kalman filter and target detection algorithm, given the principle of the algorithm, time-domain method for generating fading background and moving object extraction methods such as recursive least squares method, and the experimental results show that the algorithm capable of detecting small targets in infrared images, with good results. based pretreatment small target motion continuity characteristics studied image sequences small moving target detection algorithm based on weighted dynamic programming, dynamic programming algorithm principle is given, analysis of the direct method and the accumulation of gray dynamic programming algorithm based on similar likelihood function for dynamic programming problems arise energy diffusion gives improved dynamic programming algorithm: weighted dynamic programming algorithm, the algorithm implementation steps, testing and experimental structure the results were analyzed, the results show that the algorithm for small moving target detection with good results. Finally, this paper studied the infrared image reject false target trajectory get the real target trajectory correlation method, so as to improve the detection rate and reduce the false alarm rate the purpose.