A Comprehensive Motion Estimation Technique for the Improvement of EIS Methods Based on the SURF Algorithm and Kalman Filter
Video stabilization is an important technology for removing undesired motion in videos. This paper presents a comprehensive motion estimation method for electronic image stabilization techniques, integrating the speeded up robust features (SURF) algorithm, modified random sample consensus (RANSAC),...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2016-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/16/4/486 |
id |
doaj-db52e5ddc3b2408d96aa82fdd4e2bb42 |
---|---|
record_format |
Article |
spelling |
doaj-db52e5ddc3b2408d96aa82fdd4e2bb422020-11-25T00:39:11ZengMDPI AGSensors1424-82202016-04-0116448610.3390/s16040486s16040486A Comprehensive Motion Estimation Technique for the Improvement of EIS Methods Based on the SURF Algorithm and Kalman FilterXuemin Cheng0Qun Hao1Mengdi Xie2Graduate School at Shenzhen, Tsinghua University, Shenzhen 518055, ChinaBeijing Key Lab. for Precision Optoelectronic Measurement Instrument and Technology, School of Optoelectronics, Beijing Institute of Technology, Beijing 100081, ChinaGraduate School at Shenzhen, Tsinghua University, Shenzhen 518055, ChinaVideo stabilization is an important technology for removing undesired motion in videos. This paper presents a comprehensive motion estimation method for electronic image stabilization techniques, integrating the speeded up robust features (SURF) algorithm, modified random sample consensus (RANSAC), and the Kalman filter, and also taking camera scaling and conventional camera translation and rotation into full consideration. Using SURF in sub-pixel space, feature points were located and then matched. The false matched points were removed by modified RANSAC. Global motion was estimated by using the feature points and modified cascading parameters, which reduced the accumulated errors in a series of frames and improved the peak signal to noise ratio (PSNR) by 8.2 dB. A specific Kalman filter model was established by considering the movement and scaling of scenes. Finally, video stabilization was achieved with filtered motion parameters using the modified adjacent frame compensation. The experimental results proved that the target images were stabilized even when the vibrating amplitudes of the video become increasingly large.http://www.mdpi.com/1424-8220/16/4/486vehicle platformdigital stabilizationSURFRANSACcascade parametersKalman filter |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xuemin Cheng Qun Hao Mengdi Xie |
spellingShingle |
Xuemin Cheng Qun Hao Mengdi Xie A Comprehensive Motion Estimation Technique for the Improvement of EIS Methods Based on the SURF Algorithm and Kalman Filter Sensors vehicle platform digital stabilization SURF RANSAC cascade parameters Kalman filter |
author_facet |
Xuemin Cheng Qun Hao Mengdi Xie |
author_sort |
Xuemin Cheng |
title |
A Comprehensive Motion Estimation Technique for the Improvement of EIS Methods Based on the SURF Algorithm and Kalman Filter |
title_short |
A Comprehensive Motion Estimation Technique for the Improvement of EIS Methods Based on the SURF Algorithm and Kalman Filter |
title_full |
A Comprehensive Motion Estimation Technique for the Improvement of EIS Methods Based on the SURF Algorithm and Kalman Filter |
title_fullStr |
A Comprehensive Motion Estimation Technique for the Improvement of EIS Methods Based on the SURF Algorithm and Kalman Filter |
title_full_unstemmed |
A Comprehensive Motion Estimation Technique for the Improvement of EIS Methods Based on the SURF Algorithm and Kalman Filter |
title_sort |
comprehensive motion estimation technique for the improvement of eis methods based on the surf algorithm and kalman filter |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2016-04-01 |
description |
Video stabilization is an important technology for removing undesired motion in videos. This paper presents a comprehensive motion estimation method for electronic image stabilization techniques, integrating the speeded up robust features (SURF) algorithm, modified random sample consensus (RANSAC), and the Kalman filter, and also taking camera scaling and conventional camera translation and rotation into full consideration. Using SURF in sub-pixel space, feature points were located and then matched. The false matched points were removed by modified RANSAC. Global motion was estimated by using the feature points and modified cascading parameters, which reduced the accumulated errors in a series of frames and improved the peak signal to noise ratio (PSNR) by 8.2 dB. A specific Kalman filter model was established by considering the movement and scaling of scenes. Finally, video stabilization was achieved with filtered motion parameters using the modified adjacent frame compensation. The experimental results proved that the target images were stabilized even when the vibrating amplitudes of the video become increasingly large. |
topic |
vehicle platform digital stabilization SURF RANSAC cascade parameters Kalman filter |
url |
http://www.mdpi.com/1424-8220/16/4/486 |
work_keys_str_mv |
AT xuemincheng acomprehensivemotionestimationtechniquefortheimprovementofeismethodsbasedonthesurfalgorithmandkalmanfilter AT qunhao acomprehensivemotionestimationtechniquefortheimprovementofeismethodsbasedonthesurfalgorithmandkalmanfilter AT mengdixie acomprehensivemotionestimationtechniquefortheimprovementofeismethodsbasedonthesurfalgorithmandkalmanfilter AT xuemincheng comprehensivemotionestimationtechniquefortheimprovementofeismethodsbasedonthesurfalgorithmandkalmanfilter AT qunhao comprehensivemotionestimationtechniquefortheimprovementofeismethodsbasedonthesurfalgorithmandkalmanfilter AT mengdixie comprehensivemotionestimationtechniquefortheimprovementofeismethodsbasedonthesurfalgorithmandkalmanfilter |
_version_ |
1725294685348429824 |