The computation of optical flow
ACM Computing Surveys (CSUR)
Image Processing in Catadioptric Planes: Spatiotemporal Derivatives and Optical Flow Computation
OMNIVIS '02 Proceedings of the Third Workshop on Omnidirectional Vision
An Algorithm for Total Variation Minimization and Applications
Journal of Mathematical Imaging and Vision
Non-local Regularization of Inverse Problems
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
A duality based approach for realtime TV-L1 optical flow
Proceedings of the 29th DAGM conference on Pattern recognition
A Variational Framework for Structure from Motion in Omnidirectional Image Sequences
Journal of Mathematical Imaging and Vision
| Hi-index | 0.00 |
This paper deals with the problem of efficiently computing the optical flow of image sequences acquired by omnidirectional (nearly full field of view) cameras. We formulate the problem in the natural spherical geometry associated with these devices and extend a recent TV-L1 variational formulation for computing the optical flow [1]. The discretization of differential operators occurring in this formulation turns out to be an extremely sensitive point, in particular for the TV part of our algorithm. We show that these difficulties can be very efficiently overcome using a graph-based formulation of TV denoising, which we solve by introducing a graph version of Chambolle's algorithm [2]. A slight modification of the original framework allows us to solve the depth from motion problem using the same techniques. In both cases, our graphbased algorithms provide computationally efficient solutions and significantly outperform naive implementations based on direct discretization of the operators, or on neglecting the influence of geometry.