Aggregation Framework and Patch-Based Image Representation for Optical Flow

Abstract : This thesis is concerned with dense motion estimation in image sequences, also known as optical flow. Usual approaches exploit either local parametrization or global regularization of the motion field. We explore several ways to combine these two strategies, to overcome their respective limitations. We first address the problem in a global variational framework, and consider local filtering of the data term. We design a spatially adaptive filtering optimized jointly with motion, to prevent over-smoothing induced by the spatially constant approach. In a second part, we propose a generic two-step aggregation framework for optical flow estimation. The most general form is a local computation of motion candidates, combined in the aggregation step through a global model. Large displacements and motion discontinuities are efficiently recovered with this scheme. We also develop a generic exemplar-based occlusion handling to deal with large displacements. Our method is validated with extensive experiments in computer vision benchmarks. We demonstrate the superiority of our method over state-of-the-art on sequences with large displacements. Finally, we adapt the previous methods to biological imaging issues. Estimation and compensation of large local intensity changes frequently occurring in fluorescence imaging are efficiently estimated and compensated with an adaptation of our aggregation framework. We also propose a variational method with local filtering dedicated to the case of diffusive motion of particles.
Complete list of metadatas

https://tel.archives-ouvertes.fr/tel-01104056
Contributor : Charles Kervrann <>
Submitted on : Friday, January 16, 2015 - 12:04:56 AM
Last modification on : Wednesday, April 11, 2018 - 1:54:03 AM
Long-term archiving on : Saturday, April 15, 2017 - 6:22:45 PM

Identifiers

  • HAL Id : tel-01104056, version 1

Collections

Citation

Denis Fortun. Aggregation Framework and Patch-Based Image Representation for Optical Flow. Image Processing [eess.IV]. Universite Rennes 1, 2014. English. ⟨tel-01104056⟩

Share

Metrics

Record views

322

Files downloads

606