A novel performance evaluation method of local detectors on non-planar scenes

Authors:
Friedrich Fraundorfer;Horst Bischof
Affiliations:
Graz University of Technology;Graz University of Technology
Venue:
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops - Volume 03
Year:
2005

Citing 0
Cited 14

A model-based approach to junction detection using radial energy

Pattern Recognition
Performance evaluation of local colour invariants

Computer Vision and Image Understanding
ASN: Image Keypoint Detection from Adaptive Shape Neighborhood

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Salient region filtering for background subtraction

VISUAL'07 Proceedings of the 9th international conference on Advances in visual information systems
A new approach of mesh watermarking based on maximally stable meshes detection

NTMS'09 Proceedings of the 3rd international conference on New technologies, mobility and security
New error measures to evaluate features on three-dimensional scenes

ICIAP'11 Proceedings of the 16th international conference on Image analysis and processing: Part I
A comparative evaluation of feature detectors on historic repeat photography

ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part II
Toward accurate feature detectors performance evaluation

ICVS'11 Proceedings of the 8th international conference on Computer vision systems
Interesting Interest Points

International Journal of Computer Vision
Viewpoint induced deformation statistics and the design of viewpoint invariant features: singularities and occlusions

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
A Robust Embedding Scheme and an Efficient Evaluation Protocol for 3D Meshes Watermarking

International Journal of Computer Vision and Image Processing
Feature point detection under extreme lighting conditions

Proceedings of the 28th Spring Conference on Computer Graphics
Evaluation of two-view geometry methods with automatic ground-truth generation

Image and Vision Computing
Video stabilization using maximally stable extremal region features

Multimedia Tools and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new method for performance evaluation of local detectors on non-planar scenes. The framework extends the detector evaluation of Mikolajczyk and Schmid to non-planar scenes. The basic idea for establishing ground truth information on 3D scenes is the use of the trifocal tensor and the point transfer property. The repeatability and matching scores (using the SIFT descriptor) for the currently most popular local detectors are compared for increasing viewpoint change. In addition, detector combinations are evaluated by estimating the diversity of regions produced by the different detectors. The experiments reveal that the results differ from that of previous evaluations on planar scenes, especially that repeatability and matching scores will be much lower in real applications as suggested by previous evaluations.