Infrared small target detection is part of the key technologies in infrared precision-guided, search and track system.
Resulting from the relative distance of the infrared image system and the target is far, the target becomes small, faint and
obscure. Furthermore, the interference of background clutter and system noise is intense. To solve the problem of
infrared small target detection in a complex background, this paper proposes a bilateral filtering algorithm based on
similarity judgments for infrared image background prediction. The algorithm introduces gradient factor and similarity
judgment factor into traditional bilateral filtering. The two factors can enhance the accuracy of the algorithm for smooth
region. At the same time, spatial proximity coefficients and gray similarity coefficient in the bilateral filtering are all
expressed by the first two of McLaughlin expansion, which aiming at reducing the time overhead. Simulation results
show that the proposed algorithm can effectively suppress complex background clutter in the infrared image and enhance
target signal compared with the improved bilateral filtering algorithm, and it also can improve the signal to noise ratio
(SNR) and contrast. Besides, this algorithm can reduce the computation time. In a word, this algorithm has a good
background rejection performance.