Abstract
In this paper we present an algorithm that integrates spatial and temporal information for the tracking of moving nonrigid objects. In addition, we obtain outlines of the moving objects.
Three basic ingredients are employed in the proposed algorithm, namely, the background primal sketch, the threshold, and outlier maps. The background primal sketch is an edge map of the background without moving objects. If the background primal sketch is known, then edges of moving objects can be determined by comparing the edge map of the input image with the background primal sketch. A moving edge point is modeled as an outlier, that is, a pixel with an edge value differing from the background edge value in the background primal sketch by an amount larger than the threshold in the threshold map at the same physical location. The map that contains all the outliers is called the outlier map. In this paper we present techniques based on robust statistics for determining the background primal sketch, the threshold, and outlier maps.
In an ideal situation the outlier map would contain the complete outlines of the moving objects. In practice, the outliers do not form closed contours. The final step of the algorithm employs an edge-guided morphological approach to generate closed outlines of the moving objects. The proposed approach has been tested on sequences of moving human blood cells (neutrophil) as well as of human body motion with encouraging results.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Amini AA, Tehrani S, Weymouth E (1988) Using dynamic programming for minimizing the energy of active contours in the presence of hard constraints. IEEE Proceedings of the 2nd International Conference on Computer Vision, December, pp 95–99
Bouthemy P (1989) A maximum likelihood framework for determining moving edges. IEEE Transactions on Pattern Analysis and Machine Intelligence 11:499–511
Ferrie FP, Levine MD, Zucker SW (1982) Cell tracking: A modelling and minimization approach. IEEE Transactions on Pattern Analysis and Machine Intelligence 4:277–291
Hampel FR, Ronchetti EM, Rousseeuw PJ, Stahel WA (1986) Robust statistics—The approach based on influence functions. Wiley, New York
Huang TS, Blostein SD, Werkheiser A, McDonnell M, Lew M (1986) Motion detection and estimation from stereo image sequences. IEEE Proceedings of the Workshop on Motion: Representation and Analysis, May, pp 45–46
Jain R (1981) Extraction of motion information from peripheral processes. IEEE Transactions on Pattern Analysis and Machine Intelligence 3:489–503
Karmann KP, von Brandt A (1989) Detection and tracking of moving objects by adaptive background extraction. Proceedings of the 6th Scandinavian Conference on Image Analysis, Oulu, Finland, June 19–22, pp 1051–1058
Kass M, Witkin A, Terzopoulos D (1987) Snakes: Active contour models. IEEE Proceedings of the 1st International Conference on Computer Vision, June, pp 259–268
Kundu A (1989) Robust edge detection. IEEE Proceedings of the Conference on Computer Vision and Pattern Recognition, June, pp 11–18
Lee YH, Kassam SA (1985) Generalized median filtering and related nonlinear filtering techniques. IEEE Transactions on Acoustics, Speech and Signal Processing, 33:672–683
Leung MK, Yang YH (1987a) Human body motion segmentation in a complex scene. Pattern Recognition 20:55–64
Leung MK, Yang YH (1987b) A region based approach for human body motion analysis. Pattern Recognition 20:321–339
Levine MD, Noble PB, Youssef YM (1983) Understanding blood cell motion. Computer Graphics and Image Processing 21:58–84
Levine MD (1985) Vision in man and machine. McGraw-Hill, New York
Leymarie F (1990) Tracking and describing deformable objects using active contour models. M.Eng. thesis, CIM-90-9, McGill Research Centre for Intelligent Machines, McGill University, Montreal, Canada, February
Leymarie F, Levine MD (1989) Snakes and skeletons. CIM-89-3, McGill Research Centre for Intelligent Machines, McGill University, Montreal, Canada, January
Long W, Yang YH (1990) Stationary background generation: An alternative to the difference of two images. Pattern Recognition 23:1351–1359
Marr D (1982) Vision. W. H. Freeman, New York
Noble PB, Levine MD (1986) Computer assisted analyses of cell locomotion and chemotaxis. CRC Press, Boca Raton, FL
Roth G, Levine MD (1990) Segmentation of geometric signals using robust fitting. Proceedings of the 10th International Conference on Pattern Recognition. Atlantic City, NJ, June, pp 826–831
Rousseeuw PJ, Leroy AM (1987) Robust regression and outlier detection. Wiley, New York
Serra J (1982) Image analysis and mathematical morphology. Academic Press, New York
Staib LH, Duncan JS (1989) Parametrically deformable contour models. IEEE Proceedings of the Conference on Computer Vision and Pattern Recognition, June, pp 98–103
Tirumalai A, Schunck BG (1989) Robust surface approximation using least median squares regression. Technical Report CSE-TR-13-89, Dept. of Electrical Engineering and Computer Science, The University of Michigan, Ann Arbor, MI
Yuille AL, Cohen DS, Hallinan PW (1989) Feature extraction from faces using deformable templates. IEEE Proceedings of the Conference on Computer Vision and Pattern Recognition, June, pp 104–107
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Yang, YH., Levine, M.D. The background primal sketch: An approach for tracking moving objects. Machine Vis. Apps. 5, 17–34 (1992). https://doi.org/10.1007/BF01213527
Issue Date:
DOI: https://doi.org/10.1007/BF01213527