Towards direct recovery of shape and motion parameters from image sequences

Authors:
Stephen Benoit;Frank P. Ferrie
Affiliations:
McGill University, Department of Electrical and Computer Engineering and the McGill Centre for Intelligent Machines, 3480 University St., Montréal, Que., Canada H3A 2A7;McGill University, Department of Electrical and Computer Engineering and the McGill Centre for Intelligent Machines, 3480 University St., Montréal, Que., Canada H3A 2A7
Venue:
Computer Vision and Image Understanding
Year:
2007

Citing 16
Cited 2

Performance of optical flow techniques

International Journal of Computer Vision
Estimating the heading direction using normal flow

International Journal of Computer Vision
Using Discriminant Eigenfeatures for Image Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape Ambiguities in Structure From Motion

IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient Region Tracking With Parametric Models of Geometry and Illumination

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learned Models for Estimation of Rigid and ArticulatedHuman Motion from Stationary or Moving Camera

International Journal of Computer Vision
Measuring the Affine Transform Using Gaussian Filters

ECCV '94 Proceedings of the Third European Conference-Volume II on Computer Vision - Volume II
Generalized Image Matching: Statistical Learning of Physically-Based Deformations

ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Accurate Dense Optical Flow Estimation Using Adaptive Structure Tensors and a Parametric Model

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
Motion without Structure

ICPR '96 Proceedings of the 1996 International Conference on Pattern Recognition (ICPR '96) Volume I - Volume 7270
Direct Estimation of Structure and Motion from Multiple Frames

Direct Estimation of Structure and Motion from Multiple Frames
Direct methods for estimation of structure and motion from three views

Direct methods for estimation of structure and motion from three views
What Can Projections of Flow Fields Tell Us About the Visual Motion

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Towards Direct Recovery of Shape and Motion Parameters from Image Sequences

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Steerable Kernels for Arbitrarily-Sampled Spaces

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Is appearance-based structure from motion viable?

3DIM'99 Proceedings of the 2nd international conference on 3-D digital imaging and modeling

Field Testing of an Integrated Surface/Subsurface Modeling Technique for Planetary Exploration

International Journal of Robotics Research
Adjustable linear models for optic flow based obstacle avoidance

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel procedure is presented to construct image-domain filters (receptive fields) that directly recover local motion and shape parameters. These receptive fields are derived from training on image deformations that best discriminate between different shape and motion parameters. Beginning with the construction of 1-D receptive fields that detect local surface shape and motion parameters within cross sections, we show how the recovered model parameters are sufficient to produce local estimates of optical flow, focus of expansion, and time to collision. The theory is supported by a series of experiments on well-known image sequences for which ground truth is available. Comparisons against published results are quite competitive, which we believe to be significant given the local, feed-forward nature of the resulting algorithms.