Neural-network-based single-frame detection of dim spot target in infrared images

Infrared (IR) images derived from cloudy skies are always too spatially varied for tiny targets to be detected, especially for single-frame detection. Using the neural networks (NN) nonlinear regression, discrimination, and self-leaning capability, an NN-based method is proposed for tiny point target detection in single-frame IR images with high background clutter. First, the background was estimated by an improved NN-based morphologic filter, the structure element of which was optimized by a two-layer NN. Second, noise characteristics were well studied, and thus a two-level segmentation is presented to delete noises as well as to further remove remaining background components. Last, images with several potential targets were fed to a BP NN that predicted the identity of the input, which was either a target or a pseudo-target. It is these two neural networks that separate target from background and pseudo-target, respectively, with different training destinations, thus avoiding the over-training problem. Results on real data indicate that, given the false alarm probability, the detection probability by this method reaches 98.3%, which is improved by 11.02% compared to the traditional approach with fixed SE and without trained NN.

[1]  Oh-Jin Kwon,et al.  Video shot boundary detection using relative difference between frames , 2003 .

[2]  Paul D. Gader,et al.  Automatic target detection using entropy optimized shared-weight neural networks , 2000, IEEE Trans. Neural Networks Learn. Syst..

[3]  James C. Candy,et al.  Transmitting television as clusters of frame-to-frame differences , 1971 .

[4]  Allan Hanbury,et al.  Morphological operators on the unit circle , 2001, IEEE Trans. Image Process..

[5]  Anil K. Bera,et al.  A test for normality of observations and regression residuals , 1987 .

[6]  P. Jackway Improved morphological top-hat , 2000 .

[7]  I. Reed,et al.  A Detection Algorithm for Optical Targets in Clutter , 1987, IEEE Transactions on Aerospace and Electronic Systems.

[8]  Leonid I. Perlovsky,et al.  Model-based neural network for target detection in SAR images , 1997, IEEE Trans. Image Process..

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

[10]  Stanley C. Ahalt,et al.  Competitive learning algorithms for vector quantization , 1990, Neural Networks.

[11]  Benjamin Friedlander,et al.  A Frequency Domain Algorithm for Multiframe Detection and Estimation of Dim Targets , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  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..

[13]  Leon O. Chua,et al.  Neural networks for nonlinear programming , 1988 .

[14]  Jesmin F. Khan,et al.  Target detection in cluttered forward-looking infrared imagery , 2005 .

[15]  N. C. Mohanty Computer Tracking of Moving Point Targets in Space , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Sandor Z. Der,et al.  Multistage infrared target detection , 2003 .

[17]  M. W. Roth Neural networks for extraction of weak targets in high clutter environments , 1989, International 1989 Joint Conference on Neural Networks.

[18]  Henry Leung,et al.  Small target detection in clutter using recursive nonlinear prediction , 2000, IEEE Trans. Aerosp. Electron. Syst..

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