Abstract
The aim of motion detection is to decide whether a given part of an image belongs to a moving object or to the static background. This paper proposes an automatic decision rule for the detection of moving regions. The proposed framework is derived from a perceptual grouping principle, namely the Helmholtz principle. This principle basically states that perceptually relevant events are perceived because they deviate from a model of complete randomness. Detections are then said to be performed a contrario: moving regions appear as low probability events in a model corresponding to the absence of moving objects in the scene. A careful design of the events considered under the hypothesis of absence of moving objects results in a general and robust motion detection algorithm. No posterior parameter tuning is necessary. Furthermore, a confidence level is attached to each detected region.
Similar content being viewed by others
References
Almansa, A., Desolneux, A., and Vamech, S. 2003. Vanishing point detection without any a priori information. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(4):502–507.
Aach, T. and Kaup, A. 1995. Bayesian algorithms for change detection in image sequences using Markov random fields. Signal Processing: Image Communication, 7(2):147–160.
Attneave, F. 1954. Some informational aspects of visual perception. Psychological Review.
Canny, J. 1986. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6):679–698.
Cao, F. 2004. Application of the Gestalt principles to the detection of good continuations and corners in image level lines. Computing and Visualization in Science, 7:3–13.
Csurka, G. and Bouthemy, P. 1999. Direct identification of moving objects and background from 2D motion models. In 7th International Conference on Computer Vision, Kerkyra, Greece, pp. 566–571.
Caselles, V., Coll, T., and Morel, J.M. 1999. Topographic maps and local contrast changes in natural images. International Journal of Computer Vision, 33(1):5–27.
Desolneux, A., Moisan, L., and Morel, J.M. 2000. Meaningful alignments. International Journal of Computer Vision, 40(1):7– 23.
Desolneux, A., Moisan, L., and Morel, J.M. 2001. Edge detection by Helmholtz principle. Journal of Mathematical Imaging and Vision, 14(3):271–284.
Desolneux, A., Moisan, L., and Morel, J.M. 2003. A grouping principle and four applications. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(4):508–513.
Desolneux, A.,Moisan, L., and Morel, J.M. 2005. A theory of digital image analysis. Lecture Notes in Mathematics.
Fablet, R., Bouthemy, P., and Gelgon, M. 1999. Moving object detection in color image sequences using region-level graph labeling. In IEEE International Conference on Image Processing, ICIP'99, Kobe, Japan.
Hsu, Y.Z., Nagel, H.H., and Rekers, G. 1984. New likelihood test methods for change detection in image sequences. Computer Vision, Graphics, and Image Processing, 26:73–106.
Hoeffding, W. 1963. Probability inequalities for sum of bounded random variables. Journal of the American Statistical Association, (58):13–30.
Kanizsa, G. 1996. La Grammaire du Voir, Diderot, Original title: Grammatica del vedere, French translation from Italian.
Konrad. J. 2000. Motion detection and estimation. In Handbook of Image and Video Processing, A.C. Bovik, (Ed.), Academic Press.
Lowe, D.G. 1985. Perceptual Organization and Visual Recognition. Kluwer Academic.
Moscheni, F., Bhattacharjee, S., and Kunt, M. 1998. Spatiotemporal segmentation based on region merging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(9):897– 915.
Mansouri, A.-R. and Konrad, J. 2003. Multiple motion segmentation with level sets. IEEE Transactions on Image Processing, 12(2):201–220.
Musé, P., Sur, F., Cao, F., and Gousseau, Y. 2003. Unsupervised thresholds for shape matching. In IEEE International Conference on Image Processing, Barcelona.
Odobez, J.M. and Bouthemy, P. 1995. Robust multiresolution estimation of parametric motion models. Journal of Visual Communication and Image Representation, 6(4):348–365.
Odobez, J.M. and Bouthemy, P. 1997. Separation of moving regions from background in an image sequence acquired with a mobile camera. In Video Data Compression for Multimedia Computing, H.H. Li, S. Sun, and H. Derin, (Eds.), Kluwer Academic Publisher, chap. 8, pp. 283–311.
Paragios, N. and Deriche, R. 2000. Geodesic active contour and level sets for the detection and tracking of moving objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(3):266–280.
Rosin, P.L. 2002. Thresholding for change detection. Computer Vision and Image Understanding, 86:79–95.
Stewart. C.V. 1995. Minpran: A new robust estimator for computer vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(10):925–937.
Veit, T., Cao, F., and Bouthemy, P. 2004a. An a contrario framework for motion detection. Technical Report 5313, INRIA, September
Veit, T., Cao, F., and Bouthemy, P. 2004b. Probabilistic parameter-free motion detection. In IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Veit, T., Cao, F. & Bouthemy, P. An a contrario Decision Framework for Region-Based Motion Detection. Int J Comput Vision 68, 163–178 (2006). https://doi.org/10.1007/s11263-006-6661-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11263-006-6661-2