Adaptive target detection in forward-looking infrared imagery using the eigenspace separation transform and principal component analysis

An adaptive target detection algorithm for forward-looking infrared (FLIR) imagery is proposed, which is based on measuring differences between structural information within a target and its surrounding background. At each pixel in the image a dual window is opened, where the inner window (inner image vector) represents a possible target signature and the outer window (consisting of a number of outer image vectors) represents the surrounding scene. These image vectors are then preprocessed by two directional highpass filters to obtain the corresponding image gradient vectors. The target detection problem is formulated as a statistical hypotheses testing problem by mapping these image gradient vectors into two linear transformations, P1 and P2, via principal component analysis (PCA) and eigenspace separation transform (EST), respectively. The first transformation P1 is only a function of the inner image gradient vector. The second transformation P2 is a function of both the inner and outer image gradient vectors. For the hypothesis H1 (target), the difference of the two functions is small. For the hypothesis H0 (clutter), the difference of the two functions is large. Results of testing the proposed target detection algorithm on two large FLIR image databases are presented.

[1]  J. Krauskopf.  Effect of retinal image stabilization on the appearance of heterochromatic targets. , 1963, Journal of the Optical Society of America.

[2]  Bir Bhanu,et al.  Automatic Target Recognition: State of the Art Survey , 1986, IEEE Transactions on Aerospace and Electronic Systems.

[3]  Leandre Sevigny,et al.  Wavelet transform-based filtering for the enhancement of dim targets in FLIR images , 1994, Defense, Security, and Sensing.

[4]  J. M. Lloyd,et al.  Thermal Imaging Systems , 1975 .

[5]  Sandor Z. Der,et al.  Neural-network-based target detection system for FLIR imagery , 1998, Electronic Imaging.

[6]  Yi-Tong Zhou,et al.  Contrast, size, and orientation-invariant target detection in infrared imagery , 1991, Defense, Security, and Sensing.

[7]  Steven K. Rogers,et al.  COMPLETE AUTOMATIC TARGET CUER/RECOGNITION SYSTEM FOR TACTICAL FORWARD-LOOKING INFRARED IMAGES , 1997 .

[8]  David Casasent,et al.  Quadratic Gabor filters for object detection , 2001, IEEE Trans. Image Process..

[9]  Rama Chellappa,et al.  A multi-fractal formalism for stabilization, object detection and tracking in FLIR sequences , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[10]  Tianxu Zhang,et al.  Segmentation of FLIR images by Hopfield neural network with edge constraint , 2001, Pattern Recognit..

[11]  Guangxi Zhu,et al.  Recognition of low-contrast FLIR tank object based on multiscale fractal character vector , 1996, Defense, Security, and Sensing.

[12]  B. Bhanu,et al.  Image understanding research for automatic target recognition , 1993, IEEE Aerospace and Electronic Systems Magazine.

[13]  Don J. Torrieri.  The eigenspace separation transform for neural-network classifiers , 1999, Neural Networks.

[14]  J.A. Ratches,et al.  Target acquisition performance modeling of infrared imaging systems: past, present, and future , 2001, IEEE Sensors Journal.

[15]  M. W. Roth.  Survey of neural network technology for automatic target recognition , 1990, IEEE Trans. Neural Networks.

[16]  Mark J. T. Smith,et al.  Multidimensional wavelets for target detection and recognition , 1996, Defense + Commercial Sensing.

[17]  Sivasubramaniam Ramanan,et al.  pRAM nets for detection of small targets in sequences of infra-red images , 1995, Neural Networks.

[18]  HyunWook Park,et al.  Segmentation of forward-looking infrared image using fuzzy thresholding and edge detection , 2001 .