Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods
International Journal of Computer Vision
Accurate optical flow computation under non-uniform brightness variations
Computer Vision and Image Understanding
Highly Accurate Optic Flow Computation with Theoretically Justified Warping
International Journal of Computer Vision
Over-Parameterized Variational Optical Flow
International Journal of Computer Vision
Accurate optical flow computation under non-uniform brightness variations
Computer Vision and Image Understanding
A Comparison Study on Implementing Optical Flow and Digital Communications on FPGAs and GPUs
ACM Transactions on Reconfigurable Technology and Systems (TRETS)
Two-frame motion estimation based on polynomial expansion
SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
Representing local structure using tensors II
SCIA'11 Proceedings of the 17th Scandinavian conference on Image analysis
Revisiting the brightness constraint: probabilistic formulation and algorithms
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Multiple target tracking with motion priors
MICAI'11 Proceedings of the 10th international conference on Artificial Intelligence: advances in Soft Computing - Volume Part II
Palm+Act: operation by visually captured 3D force on palm
SIGGRAPH Asia 2013 Emerging Technologies
| Hi-index | 0.00 |
Motion estimation in image sequences is an important step in many computer vision and image processing applications. Several methods for solving this problem have been proposed, but very few manage to achieve a high level of accuracy without sacrificing processing speed. This paper presents a novel motion estimation algorithm, which gives excellent results on both counts. The algorithm starts by computing 3D orientation tensors from the image sequence. These are combined under the constraints of a parametric motion model to produce velocity estimates. Evaluated on the well-known Yosemite sequence, the algorithm shows an accuracy, which is substantially better than for previously, published methods. Computationally the algorithm is simple and can be implemented by means of sep-arable convolutions, which makes it fast.