Evaluation of Features Detectors and Descriptors Based on 3D Objects

Authors:
Pierre Moreels;Pietro Perona
Affiliations:
California Institute of Technology;California Institute of Technology
Venue:
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Year:
2005

Citing 0
Cited 19

Evaluation of Features Detectors and Descriptors based on 3D Objects

International Journal of Computer Vision
A comprehensive review of current local features for computer vision

Neurocomputing
Contrast context histogram-An efficient discriminating local descriptor for object recognition and image matching

Pattern Recognition
Local invariant feature detectors: a survey

Foundations and Trends® in Computer Graphics and Vision
A Comparison of Region Detectors for Tracking

Proceedings of the 30th DAGM symposium on Pattern Recognition
Description of interest regions with local binary patterns

Pattern Recognition
Performance evaluation of local colour invariants

Computer Vision and Image Understanding
Video shots retrieval using local invariant features

IMCE '09 Proceedings of the 1st international workshop on Interactive multimedia for consumer electronics
Spatio-temporal constraints for on-line 3D object recognition in videos

Computer Vision and Image Understanding
An efficient near-duplicate video shot detection method using shot-based interest points

IEEE Transactions on Multimedia
Interactive learning of visually symmetric objects

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Definition of a model-based detector of curvilinear regions

CAIP'07 Proceedings of the 12th international conference on Computer analysis of images and patterns
Object re-detection using SIFT and MPEG-7 color descriptors

MCAM'07 Proceedings of the 2007 international conference on Multimedia content analysis and mining
Salient region filtering for background subtraction

VISUAL'07 Proceedings of the 9th international conference on Advances in visual information systems
Using multi-modal 3D contours and their relations for vision and robotics

Journal of Visual Communication and Image Representation
Segmentation and modeling of visually symmetric objects by robot actions

International Journal of Robotics Research
Self-calibration with two views using the scale-invariant feature transform

ISVC'06 Proceedings of the Second international conference on Advances in Visual Computing - Volume Part I
Fast Local Self-Similarity for describing interest regions

Pattern Recognition Letters
A hardware architecture for real-time object detection using depth and edge information

ACM Transactions on Embedded Computing Systems (TECS)

Quantified Score

Hi-index	0.00

Visualization

Abstract

We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on intersecting epipolar constraints, for providing ground truth correspondence automatically. We collect a database of 100 objects viewed from 144 calibrated viewpoints under three different lighting conditions. We find that the combination of Hessian-affine feature finder and SIFT features is most robust to viewpoint change. Harris-affine combined with SIFT and Hessian-affine combined with shape context descriptors were best respectively for lighting changes and scale changes. We also find that no detector-descriptor combination performs well with viewpoint changes of more than 25-30°.