Abstract
A motion vision system is developed in which a moving object can be detected and image displacement can be estimated based on human visual characteristics and use of a multiresolution image. The system consists of four parts: (1) Temporal gradient, logic AND, and dynamic thresholding operations are used to obtain the primary mask. (2) A region growing algorithm is applied. (3) A hierarchical object detection algorithm is used to identify image patterns. (4) Displacement of the image is estimated by breaking each frame of the motion sequence into local regions (edges). A search is undertaken to discover how the image pattern within a given region appears displaced. This search takes the form of motion channels, the output of which are used to obtain the estimation of displacement. A correlative measure is proposed to match the patterns.
Similar content being viewed by others
References
Burt PJ (1981) Fast filter transform for image processing. Computer Graphics Image Processing, 16:20–51
Burt PJ (1984) The pyramid as an efficient computation structure. In: Multiresolution Image Processing and Analysis (Ed. A Rosenfeld). Springer-Verlag, New York
Burt PJ, Adelson EH (1984) The Laplacian pyramid as a compact image code. IEEE Transactions on Communications, 31(4): 532–540
Burt PJ, Yen C, Xu X (1982) Local correlation measures for motion analysis, A comparative study. In: Proceedings of the Conference on Pattern Recognition and Image Processing, June, pp. 269–274
Burt PJ, Yen C, Xu X (1983) Multiresolution flowthrough motion analysis. In: Proceedings of the Conference on Computer Vision, Pattern Recognition and Image Processing, pp. 246–252
Kelly MD (1971) Edge detection by computer using planning. Machine Intelligence 6:397–409
Minor LG, Sklansky J (1981) Detection and segmentation of blobs in infrared image. IEEE Transactions, SMC11:194–201
Sankar PU, Sklansky J (1982) A gestalt-guided heuristic boundary follower for X-ray image of lung nodules. IEEE Transactions, PAM-4(3):320–331
Sklansky J, Petkovic D (1984) Two-resolution detection of lung tumors in chest radiograph. In: Multiresolution Image Processing and Analysis (Ed. A Rosenfeld). Springer-Verlag, New York
Song S, Liao M, Qin J (1989) Intelligent object detection in multiresolution environment. ASME 12(3): 9–16
Song S, Liao M, Qin J (1988) Multiresolution image dynamic thresholding. Paper presented at IAPR Workshop on Computer Vision, Tokyo, October
Tamura S, Yata K, Matsumoto M (1987) Plan-based boundary extraction and 3-D reconstruction for orthogonal 2-D echocardiography. Pattern Recognition, 20(2): 155–162
Tanimoto SL, Pavlidis T (1975) A hierarchical data structure for picture processing. Computer Graphics Image Processing, 4:104–119
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Song, S., Liao, M. & Qin, J. Multiresolution image motion detection and displacement estimation. Machine Vis. Apps. 3, 17–20 (1990). https://doi.org/10.1007/BF01211449
Issue Date:
DOI: https://doi.org/10.1007/BF01211449