Research On The Algorithm Of Moving Small Dim Targets Detection Based On Energy Difference Between Frames

The detection and tracking of dim small targets in the optical and infrared images has been the subject of intense investigation for the more then two decades. The optical and infrared sensors are passive sensors, which are valued for their strong survival capacity in battlefields, but their maximum detection range is critical. Thereof, object detection involves verifying the presence of an object in image sequences and then segmenting it precisely; object tracking is to locate the object in the different location of image sequences, so to find the information of targets'speed and trace. Object detection and tracking are too closely relative processes, these years, finitude is more and more blurred in the two processes of researching on dim small targets.According to the character of lacking texture and the lowing signal-to-noise ratio on dim small targets, this paper brings out a self-adaptive moving detection model based on the energy difference comparison algorithm of temporal-frames, and brings it in a planar motive event, to accomplish estimation on moving vector and trace tracking.The major work and achievement of this paper are presented as follows:1,A self-adaptive anisotropic more-parameters moving detection function model is brought forward by this paper. This detection model compares motion energy difference between two temporal frames in a image sequence, to get the moving target. The detection algorithm is an analyzing process based on moving pixels, it reduces problems of"missing detection"and"false alarm"effectively in the traditional moving detection algorithm.2,According to analyzing the dynamic range and sensitive degree on the detection model, we research on this more-parameters moving detection model , and put forward a strategy on optimizing and selecting more-parameters of the detection model, and accomplish evaluating this strategy in the case of ideality.3,We research on the object tracking firstly, and bring the detection model into the object tracking, finally according to the analyze of tracking-error, validate that the optimized strategy is credible to the tracking in the fact.Experimental results show that the algorithm based on energy difference comparing between frames which is brought out by this paper is effective and practical to moving dim small targets detection and tracking.