Camera Pose Estimation in Dynamic Scenes with Background Tracking
This paper presents a method for robustly estimating camera pose in dynamic scenes. The main contribution of it is to use a background tracking method to ensure the accurately tracking of the moving background, thus to increase the robustness of the camera pose estimation. It has three innovations o...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
IFSA Publishing, S.L.
2013-02-01
|
Series: | Sensors & Transducers |
Subjects: | |
Online Access: | http://www.sensorsportal.com/HTML/DIGEST/february_2013/P_SI_310.pdf |
id |
doaj-ae44f1f7ac55463fb7bb433b930f8202 |
---|---|
record_format |
Article |
spelling |
doaj-ae44f1f7ac55463fb7bb433b930f82022020-11-25T00:59:35ZengIFSA Publishing, S.L.Sensors & Transducers2306-85151726-54792013-02-0119Special Issue2533Camera Pose Estimation in Dynamic Scenes with Background TrackingDong ZHANG 0Ping LI1Department of Control Science and Engineering, Zhejiang University, 38 Zheda Road, Hangzhou, Zhejiang, 310027, ChinaDepartment of Control Science and Engineering, Zhejiang University, 38 Zheda Road, Hangzhou, Zhejiang, 310027, ChinaThis paper presents a method for robustly estimating camera pose in dynamic scenes. The main contribution of it is to use a background tracking method to ensure the accurately tracking of the moving background, thus to increase the robustness of the camera pose estimation. It has three innovations over existing methods. First, it uses a fast model initialization method to get the sparse model of the background; Second, it utilizes the newly developed 3-D motion segmentation method to segment the consecutive frames into different motions and uses an on-line model updating method to track the sparse model of the background; Third, it employs a model selection method to effectively connect the dynamic scenes with static scenes for an accurate estimation result. The method is tested on synthetic data and real-world image sequences and results show that it outperforms the existing methods. http://www.sensorsportal.com/HTML/DIGEST/february_2013/P_SI_310.pdfCamera pose estimationMotion detectionMultiple view geometryDynamic vision |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Dong ZHANG Ping LI |
spellingShingle |
Dong ZHANG Ping LI Camera Pose Estimation in Dynamic Scenes with Background Tracking Sensors & Transducers Camera pose estimation Motion detection Multiple view geometry Dynamic vision |
author_facet |
Dong ZHANG Ping LI |
author_sort |
Dong ZHANG |
title |
Camera Pose Estimation in Dynamic Scenes with Background Tracking |
title_short |
Camera Pose Estimation in Dynamic Scenes with Background Tracking |
title_full |
Camera Pose Estimation in Dynamic Scenes with Background Tracking |
title_fullStr |
Camera Pose Estimation in Dynamic Scenes with Background Tracking |
title_full_unstemmed |
Camera Pose Estimation in Dynamic Scenes with Background Tracking |
title_sort |
camera pose estimation in dynamic scenes with background tracking |
publisher |
IFSA Publishing, S.L. |
series |
Sensors & Transducers |
issn |
2306-8515 1726-5479 |
publishDate |
2013-02-01 |
description |
This paper presents a method for robustly estimating camera pose in dynamic scenes. The main contribution of it is to use a background tracking method to ensure the accurately tracking of the moving background, thus to increase the robustness of the camera pose estimation. It has three innovations over existing methods. First, it uses a fast model initialization method to get the sparse model of the background; Second, it utilizes the newly developed 3-D motion segmentation method to segment the consecutive frames into different motions and uses an on-line model updating method to track the sparse model of the background; Third, it employs a model selection method to effectively connect the dynamic scenes with static scenes for an accurate estimation result. The method is tested on synthetic data and real-world image sequences and results show that it outperforms the existing methods.
|
topic |
Camera pose estimation Motion detection Multiple view geometry Dynamic vision |
url |
http://www.sensorsportal.com/HTML/DIGEST/february_2013/P_SI_310.pdf |
work_keys_str_mv |
AT dongzhang cameraposeestimationindynamicsceneswithbackgroundtracking AT pingli cameraposeestimationindynamicsceneswithbackgroundtracking |
_version_ |
1725217578574413824 |