Abstract
Corner detection is a low-level feature detection operator that is of great use in image processing applications, for example, optical flow and structure from motion by image correspondence. The detection of corners is a computationally intensive operation. Past implementations of corner detection techniques have been restricted to software. In this paper we propose an efficient very large-scale integration (VLSI) architecture for detection of corners in images. The corner detection technique is based on the half-edge concept and the first directional derivative of Gaussian. Apart from the location of the corner points, the algorithm also computes the corner orientation and the corner angle and outputs the edge map of the image. The symmetrical properties of the masks are utilized to reduce the number of convolutions effectively, from eight to two. Therefore, the number of multiplications required per pixel is reduced from 1800 to 392. Thus, the proposed architecture yields a speed-up factor of 4.6 over conventional convolution architectures. The architecture uses the principles of pipelining and parallelism and can be implemented in VLSI.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Batali J (1981) A vision chip. MIT AI Memo 869, May
Canny JF (1986) A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 679–698, November
Dreschler L, Nagel H (1981) Volumetric model and 3-D trajectory of a moving car derived from monocular TV-frame sequence of a street scene. In: Proceedings of International Journal of Computer AI pp 692–697
Fang JQ, Huang TS (1982) A corner finding algorithm for image analysis and registration. In: Proceedings of AAAI Conference, pp 46–49
Gennert MA (1986) Detecting half-edges and vertices in images. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp 552–557, June
Giardano A (1982) A VLSI-based systolic architecture for fast Gaussian convolution. Optical engineering 63–68, January
Haralick RM (1984) Digital step edges from zero crossing of second directional derivatives. IEEE Transactions on Pattern Analysis and Machine Intelligence 6(1):58–68, January
Huertas, A (1981) Corner detection for finding buildings in aerial images. USCIPI Report 1050, University of Southern California, pp 61–68
Kitchen L, Rosenfeld A (1982) Gray level corner detection. Pattern Recognition Letters 1:95–102
Kung HT Why systolic architectures. IEEE Computer 37–46, January
Marr DC, Hildreth (1980) Theory of edge detection. In: Proceedings of the Royal Society of London B207:187–217
Mehrotra R Nichani S, Ranganathan N (1990) Corner detection. Pattern Recognition 23(11): 1223–1233
Nichani S, Ranganathan N (1990) SAP: Design of a systolic array processor for computations in vision. In: Proceedings of IEEE International Conference on Computer Design, Cambridge, Mass., September 17–19, pp 315–318
Rangarajan K, Shah M, Brackle DV (1988) Optimal corner detector. In: Proceedings of the 2nd International Converence on Computer Vision pp 90–94
Ranganathan N, Mehrotra R (1991) A VLSI architecture for dynamic scene analysis. Computer Vision, Graphics, and Image Processing: Image Understanding 53:189–197
Ranganathan N, Shah M (1988) A VLSI architecture for scale space computation. Computer Vision Graphics and Image processing 43:178–204, August
Rutkowski WS, Rosenfeld R (1977) A comparison of corner detection techniques for chain coded curves. Technical Report No. 263, University of Maryland
Ruetz PA, Brodersen RW (1986) A custom chip set for real-time image processing. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Tokyo, Japan, April 7–11, pp 801–804
Shah M, Jain R (1984) Time-varying corner detector. In: Proceedings of International Conference on Pattern Recognition, pp 2–5, August
Zuniga AO, Haralick R (1983) Corner detection using the facet model. Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition pp. 30–37
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Ranganathan, N., Nichani, S.J. & Mehrotra, R. A VLSI architecture for a half-edge-based corner detector. Machine Vis. Apps. 4, 165–181 (1991). https://doi.org/10.1007/BF01230199
Issue Date:
DOI: https://doi.org/10.1007/BF01230199