Small and dim target detection by background estimation

Abstract An effective method for small and dim moving target detection in complicated background is proposed. The proposed approach takes advantage of the Non-local means filter, and applies a novel weight calculation model based on circular mask to the original background estimation pattern. By associating similarity of grayscale distribution of the images with temporal information, the extended method estimates the complicated background precisely and extracts point target successfully. To compare existing target detection methods and the proposed one, signal-to-clutter ratio gain (SCRG) and background suppression factor (BSF) are employed for spatial performance comparison and receiver operating characteristics (ROC) is used for detection-performance comparison of the target trajectory. Experimental results demonstrate good performance of the proposed method for infrared images in complicated scene, especially for images with low signal-to-noise ratio.

[1]  Jean-Michel Morel,et al.  Image Denoising Methods. A New Nonlocal Principle , 2010, SIAM Rev..

[2]  Fei Zhang,et al.  Edge directional 2D LMS filter for infrared small target detection , 2012 .

[3]  Fei Zhao,et al.  Complex background suppression based on fusion of morphological Open filter and nucleus similar pixels bilateral filter , 2012 .

[4]  F Goudail,et al.  Statistical techniques for target detection in polarization diversity images. , 2001, Optics letters.

[5]  G J Brakenhoff,et al.  Improved axial resolution by point-spread autocorrelation function imaging. , 1996, Optics letters.

[6]  Weiping Lu,et al.  Detection and tracking of small moving objects in image sequences by use of nonlinear spatiotemporal optical systems. , 2004, Optics letters.

[7]  Yuan Yan Tang,et al.  A Local Contrast Method for Small Infrared Target Detection , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Guoyou Wang,et al.  A novel infrared small target detection method based on BEMD and local inverse entropy , 2014 .

[9]  Qingyu Hou,et al.  Background suppression for cloud clutter using temporal difference projection , 2014 .

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

[11]  Wensheng Wang,et al.  Target recognition in clutter scene based on wavelet transform , 2009 .

[12]  Laure Genin,et al.  Background first- and second-order modeling for point target detection. , 2012, Applied optics.

[13]  Jie Ma,et al.  Robust method for infrared small-target detection based on Boolean map visual theory. , 2014, Applied optics.

[14]  Xuelong Li,et al.  Track infrared point targets based on projection coefficient templates and non-linear correlation combined with Kalman prediction , 2013 .

[15]  Fei Zhang,et al.  Detecting and tracking dim moving point target in IR image sequence , 2005 .

[16]  Frédéric Champagnat,et al.  Point object detection using a NL-means type filter , 2011, 2011 18th IEEE International Conference on Image Processing.