Homogeneous background prediction algorithm for detection of point target

An algorithm for detection of point target using novel background prediction technique in infrared image that contains drifting and evolving clutter is presented in this paper. It is shown that the better detection performance can be achieved when the background prediction could be done more accurately. From this point of view, the model of the homogeneous background prediction algorithm (HBPA) is developed. This approach makes edge detection first, and then the background is segmented into different areas with different gray distribution features. The probable target pixels in static background are determined by the deviation of the pixels' intensity from the gray distribution features of the background. Only the selected pixels in the static background and the pixels on the cloud edge are predicted and all of the participation pixels are homogeneous under the weight matrix. The intensity of the unselected pixels in predicted image remains the same as those in original image. Finally, the threshold value is used to make detection in the error image which is the difference between the original image and the predicted image. Experimental results indicated that the method can efficiently suppress the background clutter, protect image details, reduce the adverse influence of heterogeneity backgrounds, and improve the detection performance at low SCR.