What Energy Functions Can Be Minimized via Graph Cuts?
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation
International Journal of Computer Vision
Stereo Vision in Structured Environments by Consistent Semi-Global Matching
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Efficient Dense Scene Flow from Sparse or Dense Stereo Data
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Detectability of moving objects using correspondences over two and three frames
Proceedings of the 29th DAGM conference on Pattern recognition
High accuracy optical flow serves 3-d pose tracking: exploiting contour and flow based constraints
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Probabilistic multi-class scene flow segmentation for traffic scenes
Proceedings of the 32nd DAGM conference on Pattern recognition
Stereoscopic Scene Flow Computation for 3D Motion Understanding
International Journal of Computer Vision
Illumination-robust dense optical flow using census signatures
DAGM'11 Proceedings of the 33rd international conference on Pattern recognition
Mid-level segmentation and segment tracking for long-range stereo analysis
PSIVT'11 Proceedings of the 5th Pacific Rim conference on Advances in Image and Video Technology - Volume Part I
Hi-index | 0.00 |
We present an approach for identifying and segmenting independently moving objects from dense scene flow information, using a moving stereo camera system. The detection and segmentation is challenging due to camera movement and non-rigid object motion. The disparity, change in disparity, and the optical flow are estimated in the image domain and the three-dimensional motion is inferred from the binocular triangulation of the translation vector. Using error propagation and scene flow reliability measures, we assign dense motion likelihoods to every pixel of a reference frame. These likelihoods are then used for the segmentation of independently moving objects in the reference image. In our results we systematically demonstrate the improvement using reliability measures for the scene flow variables. Furthermore, we compare the binocular segmentation of independently moving objects with a monocular version, using solely the optical flow component of the scene flow.