IMAGE MATCHING USING DYNAMIC PROGRAMMING APPLICATION TO STEREOVISION AND IMAGE INTERPOLATION

This paper presents an original algorithm called the Or thogonal Algorithm for image matching using dynamic pro gramming and experimental results from its application to stereovision and image interpolation The algorithm provides a dense continuous and di er entiable eld of bidimensional displacements like classical optical ow detection algorithms It is based on an itera tive search for a displacement eld that minimizes the L or L distance between two images Both images are sliced into parallel and overlapping strips Corresponding strips are aligned using dynamic programming exactly as D rep resentations of speech signal are with the DTW algorithm Two passes are performed using orthogonal slicing direc tions This process is iterated in a pyramidal fashion while reducing the spacing and width of the strips Very good results have been obtained for stereovision and image inter polation

[1]  B. Zavidovique,et al.  Dynamic programming for region based pattern recognition , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Michael D. Brown,et al.  An algorithm for connected word recognition , 1982, ICASSP.

[3]  Hans-Hellmut Nagel,et al.  On the Estimation of Optical Flow: Relations between Different Approaches and Some New Results , 1987, Artif. Intell..

[4]  G. M. Quenot.  The 'orthogonal algorithm' for optical flow detection using dynamic programming , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  R. Haralick,et al.  The Facet Approach to Optic Flow , 1983 .

[6]  B. Zavidovique,et al.  Pattern Recognition Through Dynamic Programming , 1985, Optics & Photonics.

[7]  Takeo Kanade,et al.  Stereo by Intra- and Inter-Scanline Search Using Dynamic Programming , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.