The Optimized Design and Application of Circular Morphological Filter

With an optimized structure, morphological filter is more effective to detect moving spot target in infrared image sequences. Based on the real convex figure, morphological filter with circular structure is designed in this paper. The neural network is introduced to optimize the filter element. The adaptive detection threshold is built based on the statistical characters. Experimental results to real data show that the detection probability of images (SNRap2) can reach more than 98% with 1% false alarm with the optimized circular morphological filter, which detection probability is better than that with fixed element morphological filter and square morphological filter.