Small target detection based on difference accumulation and Gaussian curvature under complex conditions

Abstract Small target detection is a significant subject in infrared search and track and other photoelectric imaging systems. The small target is imaged under complex conditions, which contains clouds, horizon and bright part. In this paper, a novel small target detection method is proposed based on difference accumulation, clustering and Gaussian curvature. Difference accumulation varies from regions. Therefore, after obtaining difference accumulations, clustering is applied to determine whether the pixel belongs to the heterogeneous region, and eliminate heterogeneous region. Then Gaussian curvature is used to separate target from the homogeneous region. Experiments are conducted for verification, along with comparisons to several other methods. The experimental results demonstrate that our method has an advantage of 1–2 orders of magnitude on SCRG and BSF than others. Given that the false alarm rate is 1, the detection probability can be approximately 0.9 by using proposed method.

[1]  Yuan Cao,et al.  Automatically detect and track infrared small targets with kernel Fukunaga-Koontz transform and Kalman prediction. , 2007, Applied optics.

[2]  Angelo Chianese,et al.  Small target detection using wavelets , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[3]  Meng Hwa Er,et al.  Max-mean and max-median filters for detection of small targets , 1999, Optics & Photonics.

[4]  Yao Zhao,et al.  Bilateral two-dimensional least mean square filter for infrared small target detection , 2014 .

[5]  Kyu-Ik Sohng,et al.  Small Target Detection Using Bilateral Filter Based on Edge Component , 2010 .

[6]  Sheng Zheng,et al.  Multiscale facet model for infrared small target detection , 2014 .

[7]  Yao Zhao,et al.  Principal curvature for infrared small target detection , 2015 .

[8]  Xin Tian,et al.  Directional support value of Gaussian transformation for infrared small target detection. , 2015, Applied optics.

[9]  Mohammad Reza Mosavi,et al.  Infrared dim small target detection with high reliability using saliency map fusion , 2016, IET Image Process..

[10]  Caroline Fossati,et al.  Improvement of small target detection based on tensorial filtering , 2015 .

[11]  Manfredo P. do Carmo,et al.  Differential geometry of curves and surfaces , 1976 .

[12]  Shiyin Qin,et al.  Adaptive detection method of infrared small target based on target-background separation via robust principal component analysis , 2015 .

[13]  Tao Zhou,et al.  Learning to detect small target: A local kernel method , 2015 .

[14]  Jun Xu,et al.  An improved infrared dim and small target detection algorithm based on the contrast mechanism of human visual system , 2012 .

[15]  D. J. Salmond,et al.  A particle filter for track-before-detect , 2001, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[16]  Kyu-Ik Sohng,et al.  Small target detection using cross product based on temporal profile in infrared image sequences , 2010, Comput. Electr. Eng..

[17]  Qian Chen,et al.  Robust infrared small target detection via non-negativity constraint-based sparse representation. , 2016, Applied optics.

[18]  Qiang Wu,et al.  Small target detection based on accumulated center-surround difference measure , 2014 .

[19]  Wei Meng,et al.  Adaptive method of dim small object detection with heavy clutter. , 2013, Applied optics.

[20]  Mohammad Vali Arbabmir,et al.  Improving night sky star image processing algorithm for star sensors. , 2014, Journal of the Optical Society of America. A, Optics, image science, and vision.

[21]  David W. Thomas,et al.  The two-dimensional adaptive LMS (TDLMS) algorithm , 1988 .