Automatic target recognition by matching oriented edge pixels

This paper describes techniques to perform efficient and accurate target recognition in difficult domains. In order to accurately model small, irregularly shaped targets, the target objects and images are represented by their edge maps, with a local orientation associated with each edge pixel. Three dimensional objects are modeled by a set of two-dimensional (2-D) views of the object. Translation, rotation, and scaling of the views are allowed to approximate full three-dimensional (3-D) motion of the object. A version of the Hausdorff measure that incorporates both location and orientation information is used to determine which positions of each object model are reported as possible target locations. These positions are determined efficiently through the examination of a hierarchical cell decomposition of the transformation space. This allows large volumes of the space to be pruned quickly. Additional techniques are used to decrease the computation time required by the method when matching is performed against a catalog of object models. The probability that this measure will yield a false alarm and efficient methods for estimating this probability at run time are considered in detail. This information can be used to maintain a low false alarm rate or to rank competing hypotheses based on their likelihood of being a false alarm. Finally, results of the system recognizing objects in infrared and intensity images are given.

[1]  Azriel Rosenfeld,et al.  Sequential Operations in Digital Picture Processing , 1966, JACM.

[2]  Robert C. Bolles,et al.  Parametric Correspondence and Chamfer Matching: Two New Techniques for Image Matching , 1977, IJCAI.

[3]  H. Edelsbrunner,et al.  Efficient algorithms for agglomerative hierarchical clustering methods , 1984 .

[4]  Gunilla Borgefors,et al.  Distance transformations in digital images , 1986, Comput. Vis. Graph. Image Process..

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

[6]  Gunilla Borgefors,et al.  Hierarchical Chamfer Matching: A Parametric Edge Matching Algorithm , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  C. W. Swonger,et al.  A prospectus for automatic target recognition , 1989 .

[8]  Steven K. Rogers,et al.  Artificial neural networks for automatic target recognition , 1990, Defense, Security, and Sensing.

[9]  Firooz A. Sadjadi.  Object recognition using coding schemes , 1991, Defense, Security, and Sensing.

[10]  Edmund G. Zelnio.  ATR paradigm comparison with emphasis on model-based vision , 1992, Other Conferences.

[11]  Jacques Verly,et al.  Model-based system for automatic target recognition from forward-looking laser-radar imagery , 1992 .

[12]  David W. Paglieroni,et al.  Distance transforms: Properties and machine vision applications , 1992, CVGIP Graph. Model. Image Process..

[13]  G. A. Baraghimian,et al.  Artificial neural networks for automatic target recognition , 1992 .

[14]  Daniel P. Huttenlocher,et al.  A multi-resolution technique for comparing images using the Hausdorff distance , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Daniel P. Huttenlocher,et al.  Comparing Images Using the Hausdorff Distance , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

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

[17]  Gary E. Ford,et al.  The Position-Orientation Masking Approach to Parametric Search for Template Matching , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  William Rucklidge,et al.  Locating objects using the Hausdorff distance , 1995, Proceedings of IEEE International Conference on Computer Vision.

[19]  D. Huttenlocher,et al.  Recognition by matching dense, oriented edge pixels , 1995, Proceedings of International Symposium on Computer Vision - ISCV.

[20]  D. Huttenlocher,et al.  Recognition by Matching With Edge Location and Orientation , 1996 .

[21]  PixelsClark,et al.  Determining the Probability of a False Positive When MatchingChains of Oriented , 1996 .