Detecting for the aerial small target in infrared image based on the correlation coefficients of nonsubsampled contourlet transform

In order to solve the practical problem of the infrared small target´s detecting in the sky, a detecting algorithm based on NSCT (nonsubsampled contourlet transform) is proposed. Firstly, taking advantage of the excellent property of the transform, this algorithm analyses the different property of the NSCT coefficients of noise, background edge and signal, then computes the normalized correlation coefficients between scales for the transform coefficients. Subsequently, according to the adaptive method of threshold, the coefficients of background edge and noise are suppressed and then the image which includes the enhanced target is acquired by the inverse transform. In the end, taking the target area into account, the reconstructed image is segmented and the final detecting result is acquired by considering the position correlation of the target between frames. Experimental results show that the method given by this paper can detect small target accurately. Compared with some traditional method, it has certain advantage in background suppressing and can acquire high SNR (signal noise ratio) value.