Real-Time Quasi Dense Two-Frames Depth Map for Autonomous Guided Vehicles

Abstract : This paper presents a real-time and dense structure from motion approach, based on an efficient planar parallax motion decomposition, and also proposes several optimizations to improve the optical flow firstly computed. Later, it is estimated using our own GPU implementation of the well-known pyramidal algorithm of Lucas and Kanade. Then, each pair of points previously matched is evaluated according to the spatial continuity constraint provided by the Tensor Voting framework applied in the 4-D joint space of image coordinates and motions. Thus, assuming the ground locally planar, the homography corresponding to its image motion is robustly and quickly estimated using RANSAC on designated well-matched pairwise by the prior Tensor Voting process. Depth map is finally computed from the parallax motion decomposition. The initialization of successive runs is also addressed, providing noticeable enhancement, as well as the hardware integration using the CUDA technology.
Document type :
Conference papers
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/inria-00612341
Contributor : Nathalie Gaudechoux <>
Submitted on : Wednesday, December 4, 2013 - 3:51:38 PM
Last modification on : Friday, May 25, 2018 - 12:02:03 PM
Long-term archiving on : Tuesday, March 4, 2014 - 10:05:50 PM

File

Ducrot-all-IV01-2011.pdf
Files produced by the author(s)

Identifiers

Citation

André Ducrot, Yann Dumortier, Isabelle Herlin, Vincent Ducrot. Real-Time Quasi Dense Two-Frames Depth Map for Autonomous Guided Vehicles. IV'11 - Intelligent Vehicles Symposium, Jun 2011, Baden-Baden, Germany. pp.497-503, ⟨10.1109/IVS.2011.5940507⟩. ⟨inria-00612341⟩

Share

Metrics

Record views

669

Files downloads

618