a measure for accuracy disparity maps evaluation

14
A Measure for Accuracy Disparity Maps Evaluation Ivan Cabezas, Victor Padilla and Maria Trujillo [email protected] November 16 th 2011 16 th Iberoamerican Congress on Pattern Recognition, CIARP 2011, Pucón, Chile

Upload: ivan-mauricio-cabezas-troyano

Post on 27-Jun-2015

939 views

Category:

Documents


0 download

DESCRIPTION

An error measure for evaluating disparity maps is presented. It offers advantages over conventional ground-truth based error measures.Cabezas, I.; Padilla, V. & Trujillo, M. (2011), A Measure for Accuracy Disparity Maps Evaluation., in César San Martín & Sang-Woon Kim, ed., 'CIARP' , Springer, , pp. 223-231 .

TRANSCRIPT

Page 1: A Measure for Accuracy Disparity Maps Evaluation

A Measure for Accuracy

Disparity Maps Evaluation

Ivan Cabezas, Victor Padilla and Maria Trujillo

[email protected]

November 16th 2011

16th Iberoamerican Congress on Pattern Recognition, CIARP 2011, Pucón, Chile

Page 2: A Measure for Accuracy Disparity Maps Evaluation

Slide 2

Multimedia and Vision Laboratory

MMV is a research group of the Universidad del Valle in Colombia

A Measure for Accuracy Disparity Maps Evaluation, CIARP 2011

Page 3: A Measure for Accuracy Disparity Maps Evaluation

Slide 3

Content

Multimedia and Vision Laboratory

Stereo Vision

Disparity

Disparity Maps Evaluation

Error Measures

Problem Statement

Illustration of the BMP

The Sigma Z Error Measure

Illustration of the SZE

Impact on Evaluation Results

Final Remarks

A Measure for Accuracy Disparity Maps Evaluation, CIARP 2011

Page 4: A Measure for Accuracy Disparity Maps Evaluation

Slide 4

Stereo Vision

The stereo vision problem is to recover the 3D structure of a scene using

two or more images

A Measure for Accuracy Disparity Maps Evaluation, CIARP 2011

3D Model

Stereo Images

Disparity Map

Left Right

Correspondence Algorithm

Reconstruction Algorithm

Camera System

3D World

2D Images

Inverse Problem

Optics Problem

Yang Q. et al., Stereo Matching with Color-Weighted Correlation, Hierarchical Belief Propagation, and Occlusion Handling, IEEE PAMI 2009

Page 5: A Measure for Accuracy Disparity Maps Evaluation

Slide 5

Disparity

Disparity is the distance between corresponding points

A Measure for Accuracy Disparity Maps Evaluation, CIARP 2011

Trucco, E. and Verri A., Introductory Techniques for 3D Computer Vision, Prentice Hall 1998

Page 6: A Measure for Accuracy Disparity Maps Evaluation

Slide 6

Disparity Maps Evaluation

The evaluation of stereo correspondence algorithms is based on obtained

disparity maps

A Measure for Accuracy Disparity Maps Evaluation, CIARP 2011

Scharstein, D. and Szeliski, R., A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms, IJCV 2002

Scharstein, D. and Szeliski, R., High-accuracy Stereo Depth Maps using Structured Light, CVPR 2003

Mei, X., et al., On Building an Accurate Stereo Matching System on Graphics Hardware, GPUCV 2011

Cabezas, I. and Trujillo M., A Non-Linear Quantitative Evaluation Approach for Disparity Estimation, VISAPP 2011

Ground-truth Map Error Criteria

nonocc all disc

Page 7: A Measure for Accuracy Disparity Maps Evaluation

Slide 7

Error Measures

The selection of an error measure has an impact on evaluation results

A Measure for Accuracy Disparity Maps Evaluation, CIARP 2011

Van der Mark, W., Gavrila, D., Real-time Dense Stereo for Intelligent Vehicles IEEE Trans. on Intelligent Transportation Systems, 2006

Page 8: A Measure for Accuracy Disparity Maps Evaluation

Slide 8

Problem Statement

Conventional error measures have different drawbacks:

The use of the mean, which is sensitive to extreme values

Ignoring the inverse relation between depth and disparity

• Disparity errors of the same magnitude may have different impacts on

depth reconstruction

• Small disparities are difficult to estimate and sensitive to errors

In particular, the BMP measure, which is widely used:

It ignores the error magnitude

It is sensitive to the error threshold selection

It measures the quantity of errors

A Measure for Accuracy Disparity Maps Evaluation, CIARP 2011

Page 9: A Measure for Accuracy Disparity Maps Evaluation

Slide 9

Illustration of the BMP

A low percentage of disparity estimation errors does not imply an

accurate depth recovering

A Measure for Accuracy Disparity Maps Evaluation, CIARP 2011

Scharstein, D. and Szeliski, R., A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms, IJCV 2002

Scharstein, D. and Szeliski, R., High-accuracy Stereo Depth Maps using Structured Light, CVPR 2003

Page 10: A Measure for Accuracy Disparity Maps Evaluation

Slide 10

The Sigma Z Error Measure

We propose the Sigma Z Error (SZE) measure

The proposed measure has the following properties:

It is inherently related to depth reconstruction in a

stereo system

It is based on the inverse relation between depth and

disparity

It considers the magnitude of the estimation error

It is threshold free

A Measure for Accuracy Disparity Maps Evaluation, CIARP 2011

Page 11: A Measure for Accuracy Disparity Maps Evaluation

Slide 11

Illustration of the SZE

The SZE measures the impact of disparity estimation errors in terms of

distance along the Z axis of the stereo system

A Measure for Accuracy Disparity Maps Evaluation, CIARP 2011

ADCensus Cones ADCensus Teddy RDP Teddy RDP Cones

Mei, X., et al., On Building an Accurate Stereo Matching System on Graphics Hardware, GPUCV 2011

Sun, X., et al., Stereo Matching with Reliable Disparity Propagation, 3DIMPVT 2011

Page 12: A Measure for Accuracy Disparity Maps Evaluation

Slide 12

Impact on Evaluation Results

Two different evaluation models were used in the experimental validation

A Measure for Accuracy Disparity Maps Evaluation, CIARP 2011

Cabezas, I. and Trujillo M., A Non-Linear Quantitative Evaluation Approach for Disparity Estimation, VISAPP 2011

Scharstein, D. and Szeliski, R., http://vision.middlebury.edu/stereo/, 2011

Page 13: A Measure for Accuracy Disparity Maps Evaluation

Slide 13

Final Remarks

The SZE offers advantages over conventional error

measures such as the BMP since it considers the inverse

relation between depth and disparity

A better judging of algorithms behaviour is obtained using

the SZE

The SZE is suited to evaluate disparity estimations in

different application domains, such as: robotics, unmanned

navigation, and automatic inspection, among others

A Measure for Accuracy Disparity Maps Evaluation, CIARP 2011

Page 14: A Measure for Accuracy Disparity Maps Evaluation

A Measure for Accuracy

Disparity Maps Evaluation

Ivan Cabezas, Victor Padilla and Maria Trujillo

[email protected]

November 16th 2011

16th Iberoamerican Congress on Pattern Recognition, CIARP 2011, Pucón, Chile