Time-Series Optimization Models Based on MVL-Fusion for Low-Resolution 3D LiDAR
低解像度3D LiDARのためのMVL-Fusionに基づく時系列最適化モデル
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.)：￥1,100 Members (tax incl.)：￥880
- Publication code
- 20225009
- Paper/Info type
- Proceedings (Spring)
No.2-22
- Pages
- 1-6(Total 6 p)
- Date of publication
- May 2022
- Publisher
- JSAE
- Language
- Japanese
- Event
- 2022 JSAE Annual Congress (Spring)
Detailed Information
| Author(J) | 1) 沈 舜聡, 2) 齊藤 真衣, 3) 伊東 敏夫 |
|---|---|
| Author(E) | 1) Shuncong Shen, 2) Mai Saito, 3) Toshio Ito |
| Affiliation(J) | 1) 芝浦工業大学, 2) 芝浦工業大学, 3) 芝浦工業大学 |
| Affiliation(E) | 1) Shibaura Institute of Technology, 2) Shibaura Institute of Technology, 3) Shibaura Institute of Technology |
| Abstract(J) | レーザスキャナは自律走行システムなどの外界認識センサとして搭載される。特に、高い信頼性を持つLiDARは不可欠な存在である。しかし、遠距離で性能が低下する。これに対し、単眼カメラとのフュージョン手法を提案する。時系列フィルタリングを適用させ、異なる対象物体や非線形モデルなどの精度とロバスト性を向上させる。 Translation |
| Abstract(E) | The laser scanner has been integrated into sensing systems of many mobile devices, autonomous driving and robot system, which LiDAR as the primary sensor due to its stable and reliable in collecting 3D information. Since the degradation is appears in number and quality of point cloud at long distances, we present an enhance method via fuse monocular vision image and LiDAR point cloud data. The method also including application the time-series filtering models to improve the fusion accuracy in tracking different objects, and robustness of the fusion system, especially under non-linear dynamic scenarios. |
