Paper Info
Title
Local Image Feature Matching Improvements for Omnidirectional Camera Systems
Abstract
The matching of oriented local image feature descriptors like SIFT, SURF or ORB often includes the refinement and filtering of matches based on the relative orientation of the features. This is important since the computational cost for subsequent tasks like camera pose estimation or object detection increases dramatically with the number of outliers. Simple 2D orientation descriptions are unsuitable for Omni directional images because of image distortions and non-monotonic mapping from camera rotations to image rotations. In this work we introduce 3D orientation descriptors which, unlike 2D descriptors, are suitable for match refinement on Omni directional images and improve matching results on images from cameras and camera rigs with a wide field of view. We evaluate different match refinement strategies based on 2D and 3D orientations and show the fundamental advantages of our approach.
Year
DOI
Venue
2014
10.1109/ICPR.2014.168
Pattern Recognition
Keywords
Field
DocType
cameras,distortion,feature extraction,image matching,object detection,pose estimation,2D orientation descriptions,ORB,SIFT,SURF,camera pose estimation,image distortions,image rotations,local image feature matching,match filtering,match refinement,nonmonotonic mapping,object detection,omnidirectional camera systems,oriented local image feature descriptors
Omnidirectional camera,Scale-invariant feature transform,Computer vision,Object detection,Pattern recognition,Feature detection (computer vision),Computer science,Feature (computer vision),Filter (signal processing),Pose,Feature extraction,Artificial intelligence
Conference
ISSN
Citations 
PageRank 
1051-4651
0
0.34
References 
Authors
8
3
Name
Order
Citations
PageRank
Benjamin Resch162.10
Lang, J.233423.88
Hendrik P. A. Lensch3147196.59