Search For:

Displaying 1-4 out of 4 total
Kinecting the dots: Particle based scene flow from depth sensors
Found in: Computer Vision, IEEE International Conference on
By Simon Hadfield,Richard Bowden
Issue Date:November 2011
pp. 2290-2295
The motion field of a scene can be used for object segmentation and to provide features for classification tasks like action recognition. Scene flow is the full 3D motion field of the scene, and is more difficult to estimate than it's 2D counterpart, optic...
Long-Term Tracking through Failure Cases
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Karel Lebeda,Simon Hadfield,Jiri Matas,Richard Bowden
Issue Date:December 2013
pp. 153-160
Long term tracking of an object, given only a single instance in an initial frame, remains an open problem. We propose a visual tracking algorithm, robust to many of the difficulties which often occur in real-world scenes. Correspondences of edge-based fea...
Scene Particles: Unregularized Particle-Based Scene Flow Estimation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Simon Hadfield,Richard Bowden
Issue Date:March 2014
pp. 564-576
In this paper, an algorithm is presented for estimating scene flow, which is a richer, 3D analog of optical flow. The approach operates orders of magnitude faster than alternative techniques and is well suited to further performance gains through paralleli...
Hollywood 3D: Recognizing Actions in 3D Natural Scenes
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Simon Hadfield,Richard Bowden
Issue Date:June 2013
pp. 3398-3405
Action recognition in unconstrained situations is a difficult task, suffering from massive intra-class variations. It is made even more challenging when complex 3D actions are projected down to the image plane, losing a great deal of information. The recen...