Abstract
In this paper we present parallel implementations of two vision tasks; stereo matching and image matching. Linear features are used as matching primitives. These implementations are performed on a fixed size mesh array and achieve processor-time optimal performance. For stereo matching, we proposeO(Nn 3/P 2) time algorithm on aP ×P processor mesh array, whereN is the number of line segments in one image,n is the number of line segments in a window determined by the object size, andP ⩽n. The sequential algorithm takesO(Nn 3) time. For image matching, a partitioned parallel implementation is developed.O[((nm/P 2) +P)nm] time performance is achieved on aP ×P processor mesh array, whereP 2 ⩽nm. This leads to a processor-time optimal solution forP ⩽ (nm)1/3.
Similar content being viewed by others
References
Clark C, Luk A, McNary C 1978 Feature based scene analysis and model matching.Proc. of NATO Advanced Study Inst. for Pattern Recognition and Signal Processing, France
Dhond U, Aggarwal J K 1989 Structure from stereo — A review.IEEE Trans. Syst., Man Cybern. 19: 1489–1510
Khokhar A, Lin W, Prasanna V K 1992 Stereo and image matching on fixed size linear arrays.IEEE Trans. Pattern Anal. Mach. Intell. pami (submitted)
Lin W 1991Mapping image algorithms onto window architectures, PhD thesis, Dept. of EE-Systems, University of Southern California, Los Angeles
Lin W, Prasanna Kumar V K 1991 Parallel algorithms and architectures for discrete relaxation technique.Proc. of IEEE Conference on Vision and Pattern Recognition (New York: IEEE)
Medioni G, Nevatia R 1984 Matching images using linear features.IEEE Trans. Pattern Recogn. Image Process. PAMI-6: 675–685
Medioni G, Nevatia R 1985 Segment-based stereo matching.Computer Vision, Graph Image Process. 31: 2–18
Prasanna Kumar V K 1991Parallel algorithms and architectures for image understanding (Boston: Academic Press)
Price K 1982 Symbolic matching of images and scene models.Proc. of IEEE Workshop on Computer Vision (New York: IEEE)
Shapiro L, Haralick R 1981 Structural description and inexact matching.IEEE Trans. Pattern Anal. Mach. Intell. PAMI 3: 504–519
Author information
Authors and Affiliations
Additional information
This research was supported in part bynsf under grantiri-9145810 and in part bydarpa andafosr contracts F-49260-89-C-0126 and F-49620-90-C-0078.
Rights and permissions
About this article
Cite this article
Khokhar, A., Prasanna, V.K. Mapping stereo and image matching algorithms onto parallel architectures. Sadhana 18, 209–221 (1993). https://doi.org/10.1007/BF02742658
Issue Date:
DOI: https://doi.org/10.1007/BF02742658