Skip to Main content Skip to Navigation
Journal articles

Aggregation of local parametric candidates with exemplar-based occlusion handling for optical flow

Abstract : Handling all together large displacements, motion details and occlusions remains an open issue for reliable computation of optical flow in a video sequence. We propose a two-step aggregation paradigm to address this problem. The idea is to supply local motion candidates at every pixel in a first step, and then to combine them to determine the global optical flow field in a second step. We exploit local parametric estimations combined with patch correspondences and we experimentally demonstrate that they are sufficient to produce highly accurate motion candidates. The aggregation step is designed as the discrete optimization of a global regularized energy. The occlusion map is estimated jointly with the flow field throughout the two steps. We propose a generic exemplar-based approach for occlusion filling with motion vectors. We achieve state-of-the-art results in computer vision benchmarks, with particularly significant improvements in the case of large displacements and occlusions.
Document type :
Journal articles
Complete list of metadatas

https://hal.inria.fr/hal-01001758
Contributor : Denis Fortun <>
Submitted on : Monday, July 21, 2014 - 11:06:39 PM
Last modification on : Thursday, March 15, 2018 - 9:36:02 AM
Long-term archiving on: : Thursday, November 20, 2014 - 4:09:17 PM

Files

document.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01001758, version 1
  • ARXIV : 1407.5759

Citation

Denis Fortun, Patrick Bouthemy, Charles Kervrann. Aggregation of local parametric candidates with exemplar-based occlusion handling for optical flow. IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2014, pp.27. ⟨hal-01001758v1⟩

Share

Metrics

Record views

133

Files downloads

135