DK-SLAM: Monocular Visual SLAM with Deep Keypoint Learning, Tracking and Loop-Closing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929398305783808 |
|---|---|
| author | Qu, Hao Zhang, Lilian Mao, Jun Tie, Junbo He, Xiaofeng Hu, Xiaoping Shi, Yifei Chen, Changhao |
| author_facet | Qu, Hao Zhang, Lilian Mao, Jun Tie, Junbo He, Xiaofeng Hu, Xiaoping Shi, Yifei Chen, Changhao |
| contents | The performance of visual SLAM in complex, real-world scenarios is often compromised by unreliable feature extraction and matching when using handcrafted features. Although deep learning-based local features excel at capturing high-level information and perform well on matching benchmarks, they struggle with generalization in continuous motion scenes, adversely affecting loop detection accuracy. Our system employs a Model-Agnostic Meta-Learning (MAML) strategy to optimize the training of keypoint extraction networks, enhancing their adaptability to diverse environments. Additionally, we introduce a coarse-to-fine feature tracking mechanism for learned keypoints. It begins with a direct method to approximate the relative pose between consecutive frames, followed by a feature matching method for refined pose estimation. To mitigate cumulative positioning errors, DK-SLAM incorporates a novel online learning module that utilizes binary features for loop closure detection. This module dynamically identifies loop nodes within a sequence, ensuring accurate and efficient localization. Experimental evaluations on publicly available datasets demonstrate that DK-SLAM outperforms leading traditional and learning based SLAM systems, such as ORB-SLAM3 and LIFT-SLAM. These results underscore the efficacy and robustness of our DK-SLAM in varied and challenging real-world environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_09160 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DK-SLAM: Monocular Visual SLAM with Deep Keypoint Learning, Tracking and Loop-Closing Qu, Hao Zhang, Lilian Mao, Jun Tie, Junbo He, Xiaofeng Hu, Xiaoping Shi, Yifei Chen, Changhao Robotics Computer Vision and Pattern Recognition The performance of visual SLAM in complex, real-world scenarios is often compromised by unreliable feature extraction and matching when using handcrafted features. Although deep learning-based local features excel at capturing high-level information and perform well on matching benchmarks, they struggle with generalization in continuous motion scenes, adversely affecting loop detection accuracy. Our system employs a Model-Agnostic Meta-Learning (MAML) strategy to optimize the training of keypoint extraction networks, enhancing their adaptability to diverse environments. Additionally, we introduce a coarse-to-fine feature tracking mechanism for learned keypoints. It begins with a direct method to approximate the relative pose between consecutive frames, followed by a feature matching method for refined pose estimation. To mitigate cumulative positioning errors, DK-SLAM incorporates a novel online learning module that utilizes binary features for loop closure detection. This module dynamically identifies loop nodes within a sequence, ensuring accurate and efficient localization. Experimental evaluations on publicly available datasets demonstrate that DK-SLAM outperforms leading traditional and learning based SLAM systems, such as ORB-SLAM3 and LIFT-SLAM. These results underscore the efficacy and robustness of our DK-SLAM in varied and challenging real-world environments. |
| title | DK-SLAM: Monocular Visual SLAM with Deep Keypoint Learning, Tracking and Loop-Closing |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.09160 |