Dim Targets Detection and Tracking by Self-adaptive Segmentation and Particle Filter in Starry Images

ABSTRACT An effective method for dim and small multi-targets detection and tracking through successive CCD images in complex starry background is put forward in this paper. Optical starry background images contain a lot of interference noise besides the moving targets. Firstly, self-adaptive threshold segmentation can play an important role in eliminating noise and improving detection rate. Furthermore, back neighborhood frame correlation (BNFC) is proposed to detect and locate the target, which is sheltered by bigger interfered stars. After detection framework acquiring the location of moving targets, particle filter which has nonlinear filtering feature is applied to track the trajectories for multi-targets in real-time. Experimental results show that by using the adaptive target detection and improved particle filter, the trajectories could be achieved at a relative low signal to noise ratio (SNR 3.5) in the case of multi-targets detection and tracking in real time. The method has good prospect for engineering application.

[1]  Tarak Gandhi,et al.  Performance characterization of the dynamic programming obstacle detection algorithm , 2006, IEEE Transactions on Image Processing.

[2]  Jing Hu,et al.  Small and dim target detection by background estimation , 2015 .

[3]  G. E. Smith,et al.  The inception of charge-coupled devices , 1976, IEEE Transactions on Electron Devices.

[4]  J.C. Patra,et al.  A fast neural network-based detection and tracking of dim moving targets in FLIR imagery , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[5]  Raúl Rojas,et al.  Particle filter in vision tracking , 2007 .

[6]  Feng Duan,et al.  A New Starry Images Matching Method in Dim and Small Space Target Detection , 2009, 2009 Fifth International Conference on Image and Graphics.

[7]  A. Hamdulla,et al.  A Particle Filter Based Algorithm for State Estimation of Dim Moving Point Target in IR Image Sequence , 2008, IITA 2008.

[8]  Wu Sentang,et al.  Tracking of infrared radiation dim target based on mean-shift and particle filter , 2014, Proceedings of 2014 IEEE Chinese Guidance, Navigation and Control Conference.

[9]  Steven D. Blostein,et al.  Detecting small, moving objects in image sequences using sequential hypothesis testing , 1991, IEEE Trans. Signal Process..

[10]  Andreas E. Savakis,et al.  On the accuracy of PSF representation in image restoration , 1993, IEEE Trans. Image Process..

[11]  钱惟贤 Qian Weixian,et al.  A Detection Algorithm for Dim and Small Infrared Target Based on the Optical Flow Estimation and the Adaptive Background Suppression , 2011 .