Inherent Ambiguities in Recovering 3-D Motion and Structure from a Noisy Flow Field
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Computer Vision
Subspace methods for recovering rigid motion I: algorithm and implementation
International Journal of Computer Vision
Qualitative detection of motion by a moving observer
International Journal of Computer Vision
Segmentation of moving objects by robust motion parameter estimation over multiple frames
ECCV '94 Proceedings of the third European conference on Computer Vision (Vol. II)
ECCV '94 Proceedings of the third European conference on Computer Vision (Vol. II)
A Unified Approach to Moving Object Detection in 2D and 3D Scenes
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Computer Vision - Special issue on image-based servoing
Independent Motion Detection in 3D Scenes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Structure from Motion: Beyond the Epipolar Constraint
International Journal of Computer Vision
Rigid Body Segmentation and Shape Description from Dense Optical Flow Under Weak Perspective
IEEE Transactions on Pattern Analysis and Machine Intelligence
Motion Segmenation and Depth Ordering Based on Morphological Segmentation
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Smoothness in Layers: Motion segmentation using nonparametric mixture estimation.
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
A multi-body factorization method for motion analysis
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Closing the loop on multiple motions
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
MRF-based motion segmentation exploiting a 2D motion model robust estimation
ICIP '95 Proceedings of the 1995 International Conference on Image Processing (Vol. 3)-Volume 3 - Volume 3
The compositional character of visual correspondence
The compositional character of visual correspondence
An FFT-based technique for translation, rotation, and scale-invariant image registration
IEEE Transactions on Image Processing
Motion segmentation using inertial sensors
Proceedings of the 2006 ACM international conference on Virtual reality continuum and its applications
A Roadmap to the Integration of Early Visual Modules
International Journal of Computer Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Occlusion Boundaries from Motion: Low-Level Detection and Mid-Level Reasoning
International Journal of Computer Vision
Inverse perspective mapping and optic flow: A calibration method and a quantitative analysis
Image and Vision Computing
GVE '07 Proceedings of the IASTED International Conference on Graphics and Visualization in Engineering
CAIP'07 Proceedings of the 12th international conference on Computer analysis of images and patterns
Local occlusion detection under deformations using topological invariants
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Motion segmentation using an occlusion detector
WDV'05/WDV'06/ICCV'05/ECCV'06 Proceedings of the 2005/2006 international conference on Dynamical vision
Detachable object detection with efficient model selection
EMMCVPR'11 Proceedings of the 8th international conference on Energy minimization methods in computer vision and pattern recognition
Towards space-time semantics in two frames
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Hi-index | 0.14 |
We examine the key role of occlusions in finding independently moving objects instantaneously in a video obtained by a moving camera with a restricted field of view. In this problem, the image motion is caused by the combined effect of camera motion (egomotion), structure (depth), and the independent motion of scene entities. For a camera with a restricted field of view undergoing a small motion between frames, there exists, in general, a set of 3D camera motions compatible with the observed flow field even if only a small amount of noise is present, leading to ambiguous 3D motion estimates. If separable sets of solutions exist, motion-based clustering can detect one category of moving objects. Even if a single inseparable set of solutions is found, we show that occlusion information can be used to find ordinal depth, which is critical in identifying a new class of moving objects. In order to find ordinal depth, occlusions must not only be known, but they must also be filled (grouped) with optical flow from neighboring regions. We present a novel algorithm for filling occlusions and deducing ordinal depth under general circumstances. Finally, we describe another category of moving objects which is detected using cardinal comparisons between structure from motion and structure estimates from another source (e.g., stereo).