CNN-SVO: improving the mapping in semi-direct visual odometry using single-image depth prediction
Reliable feature correspondence between frames is a critical step in visual odometry (VO) and visual simultaneous localization and mapping (V-SLAM) algorithms. In comparison with existing VO and V-SLAM algorithms, semi-direct visual odometry (SVO) has two main advantages that lead to state-of-the-ar...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
IEEE
2019
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/36196/ http://psasir.upm.edu.my/id/eprint/36196/1/CNN-SVO%20improving%20the%20mapping%20in%20semi-direct%20visual%20odometry%20using%20single-image%20depth%20prediction.pdf |
| _version_ | 1848848264619622400 |
|---|---|
| author | Loo, Shing Yan Amiri, Ali Jahani Mashohor, Syamsiah Tang, Sai Hong Zhang, Hong |
| author_facet | Loo, Shing Yan Amiri, Ali Jahani Mashohor, Syamsiah Tang, Sai Hong Zhang, Hong |
| author_sort | Loo, Shing Yan |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Reliable feature correspondence between frames is a critical step in visual odometry (VO) and visual simultaneous localization and mapping (V-SLAM) algorithms. In comparison with existing VO and V-SLAM algorithms, semi-direct visual odometry (SVO) has two main advantages that lead to state-of-the-art frame rate camera motion estimation: direct pixel correspondence and efficient implementation of probabilistic mapping method. This paper improves the SVO mapping by initializing the mean and the variance of the depth at a feature location according to the depth prediction from a single-image depth prediction network. By significantly reducing the depth uncertainty of the initialized map point (i.e., small variance centred about the depth prediction), the benefits are twofold: reliable feature correspondence between views and fast convergence to the true depth in order to create new map points. We evaluate our method with two outdoor datasets: KITTI dataset and Oxford Robotcar dataset. The experimental results indicate that improved SVO mapping results in increased robustness and camera tracking accuracy. The implementation of this work is available at https://github.com/yan99033/CNN-SVO. |
| first_indexed | 2025-11-15T09:31:44Z |
| format | Conference or Workshop Item |
| id | upm-36196 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T09:31:44Z |
| publishDate | 2019 |
| publisher | IEEE |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-361962020-06-15T07:30:14Z http://psasir.upm.edu.my/id/eprint/36196/ CNN-SVO: improving the mapping in semi-direct visual odometry using single-image depth prediction Loo, Shing Yan Amiri, Ali Jahani Mashohor, Syamsiah Tang, Sai Hong Zhang, Hong Reliable feature correspondence between frames is a critical step in visual odometry (VO) and visual simultaneous localization and mapping (V-SLAM) algorithms. In comparison with existing VO and V-SLAM algorithms, semi-direct visual odometry (SVO) has two main advantages that lead to state-of-the-art frame rate camera motion estimation: direct pixel correspondence and efficient implementation of probabilistic mapping method. This paper improves the SVO mapping by initializing the mean and the variance of the depth at a feature location according to the depth prediction from a single-image depth prediction network. By significantly reducing the depth uncertainty of the initialized map point (i.e., small variance centred about the depth prediction), the benefits are twofold: reliable feature correspondence between views and fast convergence to the true depth in order to create new map points. We evaluate our method with two outdoor datasets: KITTI dataset and Oxford Robotcar dataset. The experimental results indicate that improved SVO mapping results in increased robustness and camera tracking accuracy. The implementation of this work is available at https://github.com/yan99033/CNN-SVO. IEEE 2019 Conference or Workshop Item PeerReviewed text en http://psasir.upm.edu.my/id/eprint/36196/1/CNN-SVO%20improving%20the%20mapping%20in%20semi-direct%20visual%20odometry%20using%20single-image%20depth%20prediction.pdf Loo, Shing Yan and Amiri, Ali Jahani and Mashohor, Syamsiah and Tang, Sai Hong and Zhang, Hong (2019) CNN-SVO: improving the mapping in semi-direct visual odometry using single-image depth prediction. In: 2019 International Conference on Robotics and Automation (ICRA), 20-24 May 2019, Montreal, Canada. (pp. 5218-5223). 10.1109/ICRA.2019.8794425 |
| spellingShingle | Loo, Shing Yan Amiri, Ali Jahani Mashohor, Syamsiah Tang, Sai Hong Zhang, Hong CNN-SVO: improving the mapping in semi-direct visual odometry using single-image depth prediction |
| title | CNN-SVO: improving the mapping in semi-direct visual odometry using single-image depth prediction |
| title_full | CNN-SVO: improving the mapping in semi-direct visual odometry using single-image depth prediction |
| title_fullStr | CNN-SVO: improving the mapping in semi-direct visual odometry using single-image depth prediction |
| title_full_unstemmed | CNN-SVO: improving the mapping in semi-direct visual odometry using single-image depth prediction |
| title_short | CNN-SVO: improving the mapping in semi-direct visual odometry using single-image depth prediction |
| title_sort | cnn-svo: improving the mapping in semi-direct visual odometry using single-image depth prediction |
| url | http://psasir.upm.edu.my/id/eprint/36196/ http://psasir.upm.edu.my/id/eprint/36196/ http://psasir.upm.edu.my/id/eprint/36196/1/CNN-SVO%20improving%20the%20mapping%20in%20semi-direct%20visual%20odometry%20using%20single-image%20depth%20prediction.pdf |