Efficient Dense Scene Flow from Sparse or Dense Stereo Data

Authors:
Andreas Wedel;Clemens Rabe;Tobi Vaudrey;Thomas Brox;Uwe Franke;Daniel Cremers
Affiliations:
Daimler Group Research, and University of Bonn,;Daimler Group Research,;University of Auckland,;University of Dresden,;Daimler Group Research,;University of Bonn,
Venue:
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Year:
2008

Citing 9
Cited 23

A compact algorithm for rectification of stereo pairs

Machine Vision and Applications
Three-Dimensional Scene Flow

IEEE Transactions on Pattern Analysis and Machine Intelligence
Stereo Vision in Structured Environments by Consistent Semi-Global Matching

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Edge-preserving Simultaneous Joint Motion-Disparity Estimation

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 02
Multi-View Stereo Reconstruction and Scene Flow Estimation with a Global Image-Based Matching Score

International Journal of Computer Vision
A duality based approach for realtime TV-L1 optical flow

Proceedings of the 29th DAGM conference on Pattern recognition
Dense motion and disparity estimation via loopy belief propagation

ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part II
Discontinuity-preserving computation of variational optic flow in real-time

Scale-Space'05 Proceedings of the 5th international conference on Scale Space and PDE Methods in Computer Vision
Dense estimation and object-based segmentation of the optical flow with robust techniques

IEEE Transactions on Image Processing

Detection and Segmentation of Independently Moving Objects from Dense Scene Flow

EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
3D mean-shift tracking of human body parts and recognition of working actions in an industrial environment

HBU'10 Proceedings of the First international conference on Human behavior understanding
A globally optimal approach for 3D elastic motion estimation from stereo sequences

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Joint estimation of motion, structure and geometry from stereo sequences

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Dense, robust, and accurate motion field estimation from stereo image sequences in real-time

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Estimation of 3D object structure, motion and rotation based on 4D affine optical flow using a multi-camera array

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
3D pose estimation and motion analysis of the articulated human hand-forearm limb in an industrial production environment

3D Research
Probabilistic multi-class scene flow segmentation for traffic scenes

Proceedings of the 32nd DAGM conference on Pattern recognition
Feature-assisted dense spatio-temporal reconstruction from binocular sequences

ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part IV
Stereoscopic Scene Flow Computation for 3D Motion Understanding

International Journal of Computer Vision
A probabilistic framework for learning kinematic models of articulated objects

Journal of Artificial Intelligence Research
Dense and accurate spatio-temporal multi-view stereovision

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II
Mid-level segmentation and segment tracking for long-range stereo analysis

PSIVT'11 Proceedings of the 5th Pacific Rim conference on Advances in Image and Video Technology - Volume Part I
Lightweight binocular facial performance capture under uncontrolled lighting

ACM Transactions on Graphics (TOG) - Proceedings of ACM SIGGRAPH Asia 2012
A loop-consistency measure for dense correspondences in multi-view video

Image and Vision Computing
Spatiotemporal descriptor for wide-baseline stereo reconstruction of non-rigid and ambiguous scenes

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
A tensor voting approach for multi-view 3d scene flow estimation and refinement

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
Adasens advanced driver assistance systems live demo

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Multi-view Scene Flow Estimation: A View Centered Variational Approach

International Journal of Computer Vision
Consistent Binocular Depth and Scene Flow with Chained Temporal Profiles

International Journal of Computer Vision
Local scene flow by tracking in intensity and depth

Journal of Visual Communication and Image Representation
Variational Recursive Joint Estimation of Dense Scene Structure and Camera Motion from Monocular High Speed Traffic Sequences

International Journal of Computer Vision
Estimating scene flow using an interconnected patch surface model with belief-propagation inference

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a technique for estimating the three-dimensional velocity vector field that describes the motion of each visible scene point (scene flow). The technique presented uses two consecutive image pairs from a stereo sequence. The main contribution is to decouple the position and velocity estimation steps, and to estimate dense velocities using a variational approach. We enforce the scene flow to yield consistent displacement vectors in the left and right images. The decoupling strategy has two main advantages: Firstly, we are independent in choosing a disparity estimation technique, which can yield either sparse or dense correspondences, and secondly, we can achieve frame rates of 5 fps on standard consumer hardware. The approach provides dense velocity estimates with accurate results at distances up to 50 meters.