Filtering Based Adaptive Visual Odometry Sensor Framework Robust to Blurred Images
Visual odometry (VO) estimation from blurred image is a challenging problem in practical robot applications, and the blurred images will severely reduce the estimation accuracy of the VO. In this paper, we address the problem of visual odometry estimation from blurred images, and present an adaptive...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2016-07-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/16/7/1040 |
id |
doaj-7b253aa1947a4dcd9050f3da08c4820b |
---|---|
record_format |
Article |
spelling |
doaj-7b253aa1947a4dcd9050f3da08c4820b2020-11-24T21:51:20ZengMDPI AGSensors1424-82202016-07-01167104010.3390/s16071040s16071040Filtering Based Adaptive Visual Odometry Sensor Framework Robust to Blurred ImagesHaiying Zhao0Yong Liu1Xiaojia Xie2Yiyi Liao3Xixi Liu4Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou 310027, ChinaInstitute of Cyber-Systems and Control, Zhejiang University, Hangzhou 310027, ChinaInstitute of Cyber-Systems and Control, Zhejiang University, Hangzhou 310027, ChinaInstitute of Cyber-Systems and Control, Zhejiang University, Hangzhou 310027, ChinaInstitute of Cyber-Systems and Control, Zhejiang University, Hangzhou 310027, ChinaVisual odometry (VO) estimation from blurred image is a challenging problem in practical robot applications, and the blurred images will severely reduce the estimation accuracy of the VO. In this paper, we address the problem of visual odometry estimation from blurred images, and present an adaptive visual odometry estimation framework robust to blurred images. Our approach employs an objective measure of images, named small image gradient distribution (SIGD), to evaluate the blurring degree of the image, then an adaptive blurred image classification algorithm is proposed to recognize the blurred images, finally we propose an anti-blurred key-frame selection algorithm to enable the VO robust to blurred images. We also carried out varied comparable experiments to evaluate the performance of the VO algorithms with our anti-blur framework under varied blurred images, and the experimental results show that our approach can achieve superior performance comparing to the state-of-the-art methods under the condition with blurred images while not increasing too much computation cost to the original VO algorithms.http://www.mdpi.com/1424-8220/16/7/1040visual odometryblurred imageadaptive classificationkey-frame selectionimage gradient distribution |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Haiying Zhao Yong Liu Xiaojia Xie Yiyi Liao Xixi Liu |
spellingShingle |
Haiying Zhao Yong Liu Xiaojia Xie Yiyi Liao Xixi Liu Filtering Based Adaptive Visual Odometry Sensor Framework Robust to Blurred Images Sensors visual odometry blurred image adaptive classification key-frame selection image gradient distribution |
author_facet |
Haiying Zhao Yong Liu Xiaojia Xie Yiyi Liao Xixi Liu |
author_sort |
Haiying Zhao |
title |
Filtering Based Adaptive Visual Odometry Sensor Framework Robust to Blurred Images |
title_short |
Filtering Based Adaptive Visual Odometry Sensor Framework Robust to Blurred Images |
title_full |
Filtering Based Adaptive Visual Odometry Sensor Framework Robust to Blurred Images |
title_fullStr |
Filtering Based Adaptive Visual Odometry Sensor Framework Robust to Blurred Images |
title_full_unstemmed |
Filtering Based Adaptive Visual Odometry Sensor Framework Robust to Blurred Images |
title_sort |
filtering based adaptive visual odometry sensor framework robust to blurred images |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2016-07-01 |
description |
Visual odometry (VO) estimation from blurred image is a challenging problem in practical robot applications, and the blurred images will severely reduce the estimation accuracy of the VO. In this paper, we address the problem of visual odometry estimation from blurred images, and present an adaptive visual odometry estimation framework robust to blurred images. Our approach employs an objective measure of images, named small image gradient distribution (SIGD), to evaluate the blurring degree of the image, then an adaptive blurred image classification algorithm is proposed to recognize the blurred images, finally we propose an anti-blurred key-frame selection algorithm to enable the VO robust to blurred images. We also carried out varied comparable experiments to evaluate the performance of the VO algorithms with our anti-blur framework under varied blurred images, and the experimental results show that our approach can achieve superior performance comparing to the state-of-the-art methods under the condition with blurred images while not increasing too much computation cost to the original VO algorithms. |
topic |
visual odometry blurred image adaptive classification key-frame selection image gradient distribution |
url |
http://www.mdpi.com/1424-8220/16/7/1040 |
work_keys_str_mv |
AT haiyingzhao filteringbasedadaptivevisualodometrysensorframeworkrobusttoblurredimages AT yongliu filteringbasedadaptivevisualodometrysensorframeworkrobusttoblurredimages AT xiaojiaxie filteringbasedadaptivevisualodometrysensorframeworkrobusttoblurredimages AT yiyiliao filteringbasedadaptivevisualodometrysensorframeworkrobusttoblurredimages AT xixiliu filteringbasedadaptivevisualodometrysensorframeworkrobusttoblurredimages |
_version_ |
1725879081948413952 |