Stereoscopic scene flow computation for 3D motion understanding

Andreas Wedel, Thomas Brox, Tobi Vaudrey, Clemens Rabe, Uwe Franke, Daniel Cremers

Research output: Contribution to journalArticlepeer-review

139 Scopus citations

Abstract

Building upon recent developments in optical flow and stereo matching estimation, we propose a variational framework for the estimation of stereoscopic scene flow, i.e., the motion of points in the three-dimensional world from stereo image sequences. The proposed algorithm takes into account image pairs from two consecutive times and computes both depth and a 3D motion vector associated with each point in the image. In contrast to previous works, we partially decouple the depth estimation from the motion estimation, which has many practical advantages. The variational formulation is quite flexible and can handle both sparse or dense disparity maps. The proposed method is very efficient; with the depth map being computed on an FPGA, and the scene flow computed on the GPU, the proposed algorithm runs at frame rates of 20 frames per second on QVGA images (320×240 pixels). Furthermore, we present solutions to two important problems in scene flow estimation: violations of intensity consistency between input images, and the uncertainty measures for the scene flow result.

Original languageEnglish
Pages (from-to)29-51
Number of pages23
JournalInternational Journal of Computer Vision
Volume95
Issue number1
DOIs
StatePublished - Oct 2011

Keywords

  • 3D motion
  • 3D reconstruction
  • Motion segmentation
  • Scene flow
  • Structure from motion

Fingerprint

Dive into the research topics of 'Stereoscopic scene flow computation for 3D motion understanding'. Together they form a unique fingerprint.

Cite this