Direct line guidance odometry
Modern visual odometry algorithms utilize sparse point-based features for tracking due to their low computational cost. Current state-of-the-art methods are split between indirect methods that process features extracted from the image, and indirect methods that deal directly on pixel intensities. In...
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference item |
| Published: |
Institute of Electrical and Electronics Engineers
2018
|
| _version_ | 1826305861827428352 |
|---|---|
| author | Li, S-J Ren, B Liu, Y Cheng, M-M Frost, D Prisacariu, VA |
| author_facet | Li, S-J Ren, B Liu, Y Cheng, M-M Frost, D Prisacariu, VA |
| author_sort | Li, S-J |
| collection | OXFORD |
| description | Modern visual odometry algorithms utilize sparse point-based features for tracking due to their low computational cost. Current state-of-the-art methods are split between indirect methods that process features extracted from the image, and indirect methods that deal directly on pixel intensities. In recent years, line-based features have been used in SLAM and have shown an increase in performance albeit with an increase in computational cost. In this paper, we propose an extension to a point-based direct monocular visual odometry method. Here we that uses lines to guide keypoint selection rather than acting as features. Points on a line are treated as stronger keypoints than those in other parts of the image, steering point-selection away from less distinctive points and thereby increasing efficiency. By combining intensity and geometry information from a set of points on a line, accuracy may also be increased. |
| first_indexed | 2024-03-07T06:39:17Z |
| format | Conference item |
| id | oxford-uuid:f8b6d16e-07b4-4432-bc6e-6dddccaca511 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T06:39:17Z |
| publishDate | 2018 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | oxford-uuid:f8b6d16e-07b4-4432-bc6e-6dddccaca5112022-03-27T12:52:31ZDirect line guidance odometryConference itemhttp://purl.org/coar/resource_type/c_5794uuid:f8b6d16e-07b4-4432-bc6e-6dddccaca511Symplectic Elements at OxfordInstitute of Electrical and Electronics Engineers2018Li, S-JRen, BLiu, YCheng, M-MFrost, DPrisacariu, VAModern visual odometry algorithms utilize sparse point-based features for tracking due to their low computational cost. Current state-of-the-art methods are split between indirect methods that process features extracted from the image, and indirect methods that deal directly on pixel intensities. In recent years, line-based features have been used in SLAM and have shown an increase in performance albeit with an increase in computational cost. In this paper, we propose an extension to a point-based direct monocular visual odometry method. Here we that uses lines to guide keypoint selection rather than acting as features. Points on a line are treated as stronger keypoints than those in other parts of the image, steering point-selection away from less distinctive points and thereby increasing efficiency. By combining intensity and geometry information from a set of points on a line, accuracy may also be increased. |
| spellingShingle | Li, S-J Ren, B Liu, Y Cheng, M-M Frost, D Prisacariu, VA Direct line guidance odometry |
| title | Direct line guidance odometry |
| title_full | Direct line guidance odometry |
| title_fullStr | Direct line guidance odometry |
| title_full_unstemmed | Direct line guidance odometry |
| title_short | Direct line guidance odometry |
| title_sort | direct line guidance odometry |
| work_keys_str_mv | AT lisj directlineguidanceodometry AT renb directlineguidanceodometry AT liuy directlineguidanceodometry AT chengmm directlineguidanceodometry AT frostd directlineguidanceodometry AT prisacariuva directlineguidanceodometry |