Multimodal Foundational Models for Unsupervised 3D General Obstacle Detection
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_ | 1866929469724295168 |
|---|---|
| author | Matuszka, Tamás Hajas, Péter Szeghy, Dávid |
| author_facet | Matuszka, Tamás Hajas, Péter Szeghy, Dávid |
| contents | Current autonomous driving perception models primarily rely on supervised learning with predefined categories. However, these models struggle to detect general obstacles not included in the fixed category set due to their variability and numerous edge cases. To address this issue, we propose a combination of multimodal foundational model-based obstacle segmentation with traditional unsupervised computational geometry-based outlier detection. Our approach operates offline, allowing us to leverage non-causality, and utilizes training-free methods. This enables the detection of general obstacles in 3D without the need for expensive retraining. To overcome the limitations of publicly available obstacle detection datasets, we collected and annotated our dataset, which includes various obstacles even in distant regions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12322 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multimodal Foundational Models for Unsupervised 3D General Obstacle Detection Matuszka, Tamás Hajas, Péter Szeghy, Dávid Computer Vision and Pattern Recognition Current autonomous driving perception models primarily rely on supervised learning with predefined categories. However, these models struggle to detect general obstacles not included in the fixed category set due to their variability and numerous edge cases. To address this issue, we propose a combination of multimodal foundational model-based obstacle segmentation with traditional unsupervised computational geometry-based outlier detection. Our approach operates offline, allowing us to leverage non-causality, and utilizes training-free methods. This enables the detection of general obstacles in 3D without the need for expensive retraining. To overcome the limitations of publicly available obstacle detection datasets, we collected and annotated our dataset, which includes various obstacles even in distant regions. |
| title | Multimodal Foundational Models for Unsupervised 3D General Obstacle Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.12322 |