The infrared target recognition at sea background based on visual attention computational model and level set methodology

Infrared images at sea background are notorious for the low signal-to-noise ratio, therefore, the target recognition of infrared image through traditional methods is very difficult. In this paper, we present a novel target recognition method based on the integration of visual attention computational model and level set methodology. The two distinct techniques for image processing are combined in a manner to utilize the strengths of both. The visual attention searches the salient regions automatically, and represented them by a set of winner points, at the same time, demonstrated the salient regions in terms of circles centered at these winner points. This provides a priori knowledge for level set method, the initial level set function could be constructed based on the winner points, in this way, an automatic initialization of level set evolution can be obtained, and the boundaries of the targets can be obtained. The cost time does not depend on the size of the image but the salient regions, therefore the consumed time is greatly reduced. At the same time, this algorithm discards the re-initialization procedure and force the level set function to be close to a distance function, therefore reduces the side effects of re-initialization, The method is used in the recognition of several kinds of real infrared images, and the experimental results reveal the effectiveness of the algorithm presented in this paper.

[1]  Y. Li.  Applications of moment invariants to neurocomputing for pattern recognition , 1990 .

[2]  Mark J. T. Smith,et al.  Target Recognition Based on Directional Filter Banks and Higher-Order Neural Networks , 2000, Digit. Signal Process..

[3]  William T. Freeman,et al.  Presented at: 2nd Annual IEEE International Conference on Image , 1995 .

[4]  Gao Shang.  Recognition of infrared image in sea level by moment invariants , 2007 .

[5]  Bir Bhanu,et al.  Stochastic models for recognition of occluded targets , 2003, Pattern Recognit..

[6]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[7]  Roberto Manduchi,et al.  Efficient deformable filter banks , 1998, IEEE Trans. Signal Process..

[8]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[9]  Pietro Perona,et al.  Selective visual attention enables learning and recognition of multiple objects in cluttered scenes , 2005, Comput. Vis. Image Underst..

[10]  Guangzhi Shi,et al.  Target recognition study using SVM, ANNs and expert knowledge , 2008, 2008 IEEE International Conference on Automation and Logistics.

[11]  Fang Yang-yu.  Target-on-Sea Recognition Based on Wavelet Moment Invariants , 2007 .

[12]  Engin Avci,et al.  Intelligent target recognition based on wavelet packet neural network , 2005, Expert Syst. Appl..

[13]  Zhu Bing,et al.  Knowledge based recognition of harbor target , 2006 .

[14]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[15]  Fred Stentiford,et al.  An evolutionary programming approach to the simulation of visual attention , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[16]  Chunming Li,et al.  Level set evolution without re-initialization: a new variational formulation , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[17]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[18]  Andrew R. Webb.  Gamma mixture models for target recognition , 2000, Pattern Recognit..