Download:
by Thomas Veit, Frédéric Cao, Patrick Bouthemy
IEEE Conf. Computer Vision and Pattern Recognition, CVPR’04, Washington DC
http://www.ercim.org/pub/bscw.cgi/0/../d28380/2004_cvpr_veit.pdf
Add To MetaCart
Abstract:
We propose an original probabilistic parameter-free method for the detection of independently moving objects in an image sequence. We apply a probabilistic perceptual principle, the Helmholtz principle, whose main advantage is the automatization of the detection decision, by providing a tight control of the number of false alarms. Not only does this method localize the moving objects but it also answers the preliminary question of the presence of motion. In particular, the method works even when no assumption on motion presence is made. The algorithm is composed of three independent steps: estimation of the dominant image motion, spatial segmentation of object boundaries and independent motion detection itself. We emphasize that none of these steps needs any parameter tuning. Results on real image sequences are reported and validate the proposed approach. 1.
Citations
|
1044
|
Determining Optical Flow
– Horn, Schunck
- 1981
|
|
176
|
Robust multiresolution estimation of parametric motion models
– Odobez, Bouthemy
- 1995
|
|
110
|
2000, ‘Geodesic active contours and level sets for the detection and tracking of moving objects
– Paragios, Deriche
|
|
103
|
Detecting and tracking multiple moving objects using temporal integration
– Irani, Rousso, et al.
- 1992
|
|
76
|
A unified approach to moving object detection in 2D and 3D scenes
– Irani, Anandan
- 1998
|
|
48
|
MINPRAN, a new robust estimator for computer vision
– Stewart
- 1995
|
|
36
|
Detecting and tracking moving objects for video surveillance
– Cohen, Médioni
- 1999
|
|
26
|
Edge detection by Helmholtz principle
– Desolneux, Moisan, et al.
- 2001
|
|
21
|
Perceptual organisation and visual recognition
– Lowe
- 1985
|
|
18
|
A grouping principle and four applications
– Desolneux, Moisan, et al.
- 2003
|
|
12
|
Detection of multiple moving objects using multiscale mrf with camera motion compensation
– Odobez, Bouthemy
- 1994
|
|
12
|
Motion detection and estimation
– Konrad
- 2000
|
|
9
|
Bayesian algorithms for change detection in image sequences using Markov random fields
– Aach, Kaup
- 1995
|
|
6
|
Probability inequalities for sums of bounded variables
– Hoeffding
- 1963
|
|
3
|
Detection of major changes in satellite images
– Lisani, Morel
- 2003
|
|
2
|
Qualitative detection of motion by a moving observer, International journal of computer vision
– Nelson
- 1991
|
|
1
|
Motion detection and estimation - multiple motion segmentation with level sets
– Mansouri, Konrad
- 2003
|
|
1
|
Detecting moving objects,” Int
– Thompson, Pong
- 1990
|
