An improved point feature‐based sparse stereo vision
Abstract Since the limitation on the onboard equipment, the sparse stereo vision is becoming a suitable choice for the deployment of micro air vehicles (MAV) and small robots. However, for the point feature‐based sparse stereo, most of the current stereo algorithms ignore the similarity between feat...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-10-01
|
| Series: | IET Image Processing |
| Online Access: | https://doi.org/10.1049/ipr2.12564 |
| _version_ | 1828366393644417024 |
|---|---|
| author | Changhao Chen Bifeng Song Shuhui Bu Lei He |
| author_facet | Changhao Chen Bifeng Song Shuhui Bu Lei He |
| author_sort | Changhao Chen |
| collection | DOAJ |
| description | Abstract Since the limitation on the onboard equipment, the sparse stereo vision is becoming a suitable choice for the deployment of micro air vehicles (MAV) and small robots. However, for the point feature‐based sparse stereo, most of the current stereo algorithms ignore the similarity between feature points, so it is hard to achieve high accuracy. In addition, the problem of clustered feature distribution will still affect the performance of point feature‐based algorithms in the application. To make up for these deficiencies, the authors propose an improved features from accelerated segment test (FAST) feature detector to suppress the point detection in complex texture regions. Most importantly, the authors present a novel census transform (CT)‐based algorithm that contains two encoders ‘texture orientation’ and ‘texture gradient’ to get a more efficient census bit string for the feature point. Instead of randomly selecting pixels to calculate the bit string, we combine the texture characteristics of the census windows where feature points are located. Compared with the original CT, the processing speed of our method is improved, and the average error of our method is reduced by 18.05%. The evaluation results show the presented improved point feature‐based sparse stereo algorithm has a great value in engineering applications. |
| first_indexed | 2024-04-14T05:44:27Z |
| format | Article |
| id | doaj.art-f7bef72166c84aa081d25d53ae7f6026 |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-14T05:44:27Z |
| publishDate | 2022-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-f7bef72166c84aa081d25d53ae7f60262022-12-22T02:09:20ZengWileyIET Image Processing1751-96591751-96672022-10-0116123284329910.1049/ipr2.12564An improved point feature‐based sparse stereo visionChanghao Chen0Bifeng Song1Shuhui Bu2Lei He3School of Aeronautics Northwestern Polytechnical University Xi'an ChinaSchool of Aeronautics Northwestern Polytechnical University Xi'an ChinaSchool of Aeronautics Northwestern Polytechnical University Xi'an ChinaSchool of Aeronautics Northwestern Polytechnical University Xi'an ChinaAbstract Since the limitation on the onboard equipment, the sparse stereo vision is becoming a suitable choice for the deployment of micro air vehicles (MAV) and small robots. However, for the point feature‐based sparse stereo, most of the current stereo algorithms ignore the similarity between feature points, so it is hard to achieve high accuracy. In addition, the problem of clustered feature distribution will still affect the performance of point feature‐based algorithms in the application. To make up for these deficiencies, the authors propose an improved features from accelerated segment test (FAST) feature detector to suppress the point detection in complex texture regions. Most importantly, the authors present a novel census transform (CT)‐based algorithm that contains two encoders ‘texture orientation’ and ‘texture gradient’ to get a more efficient census bit string for the feature point. Instead of randomly selecting pixels to calculate the bit string, we combine the texture characteristics of the census windows where feature points are located. Compared with the original CT, the processing speed of our method is improved, and the average error of our method is reduced by 18.05%. The evaluation results show the presented improved point feature‐based sparse stereo algorithm has a great value in engineering applications.https://doi.org/10.1049/ipr2.12564 |
| spellingShingle | Changhao Chen Bifeng Song Shuhui Bu Lei He An improved point feature‐based sparse stereo vision IET Image Processing |
| title | An improved point feature‐based sparse stereo vision |
| title_full | An improved point feature‐based sparse stereo vision |
| title_fullStr | An improved point feature‐based sparse stereo vision |
| title_full_unstemmed | An improved point feature‐based sparse stereo vision |
| title_short | An improved point feature‐based sparse stereo vision |
| title_sort | improved point feature based sparse stereo vision |
| url | https://doi.org/10.1049/ipr2.12564 |
| work_keys_str_mv | AT changhaochen animprovedpointfeaturebasedsparsestereovision AT bifengsong animprovedpointfeaturebasedsparsestereovision AT shuhuibu animprovedpointfeaturebasedsparsestereovision AT leihe animprovedpointfeaturebasedsparsestereovision AT changhaochen improvedpointfeaturebasedsparsestereovision AT bifengsong improvedpointfeaturebasedsparsestereovision AT shuhuibu improvedpointfeaturebasedsparsestereovision AT leihe improvedpointfeaturebasedsparsestereovision |