Efficient non-consecutive feature tracking for structure-from-motion

Authors:
Guofeng Zhang;Zilong Dong;Jiaya Jia;Tien-Tsin Wong;Hujun Bao
Affiliations:
State Key Lab of CAD&CG, Zhejiang University;State Key Lab of CAD&CG, Zhejiang University;The Chinese University of Hong Kong;The Chinese University of Hong Kong;State Key Lab of CAD&CG, Zhejiang University
Venue:
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Year:
2010

Citing 16
Cited 6

Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
Multiple View Geometry in Computer Vision

Multiple View Geometry in Computer Vision
Video Google: A Text Retrieval Approach to Object Matching in Videos

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Recognising Panoramas

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Automated location matching in movies

Computer Vision and Image Understanding - Special isssue on video retrieval and summarization
Point Matching under Large Image Deformations and Illumination Changes

IEEE Transactions on Pattern Analysis and Machine Intelligence
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
A Sparse Texture Representation Using Local Affine Regions

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Performance Evaluation of Local Descriptors

IEEE Transactions on Pattern Analysis and Machine Intelligence
Photo tourism: exploring photo collections in 3D

ACM SIGGRAPH 2006 Papers
Scalable Recognition with a Vocabulary Tree

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Detecting Loop Closure with Scene Sequences

International Journal of Computer Vision
Detailed Real-Time Urban 3D Reconstruction from Video

International Journal of Computer Vision
Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
An iterative image registration technique with an application to stereo vision

IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
ASIFT: A New Framework for Fully Affine Invariant Image Comparison

SIAM Journal on Imaging Sciences

Unsupervised learning for improving efficiency of dense three-dimensional scene recovery in corridor mapping

SCIA'11 Proceedings of the 17th Scandinavian conference on Image analysis
Feature trajectory retrieval with application to accurate structure and motion recovery

ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part I
3D reconstruction of dynamic scenes with multiple handheld cameras

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Video enhancement leveraging high-quality depth maps

Proceedings of the 11th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry
Learning object appearance from occlusions using structure and motion recovery

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Persistent tracking of static scene features using geometry

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

Structure-from-motion (SfM) is an important computer vision problem and largely relies on the quality of feature tracking. In image sequences, if disjointed tracks caused by objects moving in and out of the view, occasional occlusion, or image noise, are not handled well, the corresponding SfM could be significantly affected. In this paper, we address the non-consecutive feature point tracking problem and propose an effective method to match interrupted tracks. Our framework consists of steps of solving the feature 'dropout' problem when indistinctive structures, noise or even large image distortion exist, and of rapidly recognizing and joining common features located in different subsequences. Experimental results on several challenging and large-scale video sets show that our method notably improves SfM.