Small target detection of infrared image based on energy features

A slowly moving small target detection method based on target energy feature of infrared image is proposed in this paper. Mathematical morphology is used to estimate background image. By use of original image minus estimated background image, we get the estimated noise plus target image. The spatial target signature is an optical blur dominated by the optics point spread function. The energy of the area around the location of target often shows intensity maximum or local energy maximum. Based on the knowledge, a target detection algorithm is presented. According to the detection results to real infrared image sequences and Monte Carlo simulation data, it is shown that the method has good detection performance.

[1]  Zhanghong,et al.  A real-time effective method for infrared point-target detection in spatially varying clutter , 2001, 2001 CIE International Conference on Radar Proceedings (Cat No.01TH8559).

[2]  Zhenkang Shen,et al.  Detecting dim point targets in infrared image sequences using probabilistic neural networks , 1994, Defense, Security, and Sensing.

[3]  Zhao Bao.  The Real-Time Detection of Infrared Weak Targets Under Comples Background , 2001 .

[4]  Yan Huang,et al.  Adaptive multichannel discrete wavelet transforms for automated subpixel target detection , 2001, IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No.01CH37217).

[5]  Zhenkang Shen,et al.  Detecting dim point target in infrared image sequences using probalilistic neural network , 1994, Proceedings of National Aerospace and Electronics Conference (NAECON'94).

[6]  Steven D. Blostein,et al.  Detection of small moving objects in image sequences using multistage hypothesis testing , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

[7]  Steven D. Blostein,et al.  A tree search algorithm for target detection in image sequences , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Joseph Ronsin,et al.  Some statistical properties of mathematical morphology , 1995, IEEE Trans. Signal Process..