Email this article 
Open Access
Subscription or Fee Access
Feature based Obstacle Detection using Phase - based Correspondence Matching and Image Declivity
Abstract
This paper proposes a 2D feature based obstacledetection and calculating depth map by the disparity usingphase-based correspondence matching and Image declivity. The phaseinformation obtained from cross phase spectrum using 2D DFT(Discrete Fourier Transform) of images contains importantinformation of image point similarity and dissimilarity. Level by levelblock matching using phase only correlation i.e. phase basedcorrespondence search is used to find the correspondence pointbetween input image and registered image using image declivity.Image registration is automatic, very fast, self adaptive segmentationtechnique as compare to other segmentation technique. I proposedreference point selection method based on image declivity which usedfor block matching and numbers of references point generated byimage declivity is controlled according to application. Thephase-based image matching is successfully applied to registeredimage for obstacle detection tasks for computer vision applications.
Keywords
References
J. Weng, T. Huang, and N. Ahuja, “Motion and structure from two
perspective views: Algorithms, error analysis, and error estimation,”IEEE
Trans. on Pattern Analysis and Machine Intelligence, vol. 11, no. 5, pp.
–476, 1989.
R. Hartley and A. Zisserman, Multiple views in computer vision.
Cambridge University Press, 2000.
R. Deriche, Z. Zhang, Q.-T. Luong, and O. Faugeras,“Robust recovery of
the epipolar geometry for an uncelebrated stereo rig,” in Proc. European
Conf. on computer Vision, Stockholm, Sweden, 1994
Z. Zhang, “Determining the epipolar geometry and its uncertainty – a
review,” Int. Journal of Computer Vision, vol. 27, no. 2, pp.
–195, 1998.
C. D. Kuglin and D. C. Hines. The phase correlation image alignment
method. Proc. Int. Conf. Cybernetics and Society, pages 163–165, 1975.
M. A. Muquit, T Shibahara, and T. Aoki, “A high- accuracy passive 3D
measurement system using phase-based image matching,”IEICE Trans.
Fundamentals, vol. E89-A, no. 3, pp. 686–697, Mar. 2006.
K. Takita, T. Aoki, Y. Sasaki, T. Higuchi, and K. Kobayashi.
Highaccuracy subpixel image registration based on phase-only
correlation. IEICE Trans. Fundamentals, E86-A(8):1925–1934, Aug.
K. Takita, M. A. Muquit, T. Aoki, and T. Higuchi. A sub- pixel
correspondence search technique for computer vision applications.
IEICE Trans. Fundamentals, E87-A(8):1913– 1923, Aug. 2004.
B. D. Lucas and T. Kanade, "An iterative image registration
technique with an application to stereo vision", in Proceeding on Image
Understanding workshop, pp 121130, 1981.
Pierre MICHE* ,Roland DEBRIE*, fast and self adaptive image
segmentation using extended declivity Ann,Telicommumn.,5,n0
,3-4,1995..
J. Canny: “A Computational Approach to Edge Detection”,
IEEE Transactions on Pattern Analysis and Machine intelligence, 1986.
Feet, D., Jespson, A.and Jekin, M. (1991) Phase Based disparity
Measurement. CVGIP: Image Under- standing53; 198-210.
Jenkin, M. and Jepson, A. (1988) The measurement of binocular
disparity in computational process in Human Vision,(ed.) Z. Pylyshyn,
Ablex Press, NJ.
Sanger, T. (1988) Stereo Disparity Computation using Gabor Filter
.Biological cybernetics 59:405-418.
Wenj, J. (1994) Image Matching using windowed Fourier phase. Int. J.
Computer. Vision 11:211-236.
Trucco, E; Verri, A. "Introductory Techniques for 3-D Computer Vision."
Prentice Hall, 1998.
Hartley, R; Zisserman, A. "Multiple View Geometry in Computer
Vision." Cambridge University Press, 2003.
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.