SPARSE POINT CLOUD INTERPOLATION METHOD USING SENSOR FUSION WITH VIRTUAL GRADIENT
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.):¥1,100 Members (tax incl.):¥880
- Publication code
- 20219041
- Paper/Info type
- Other International Conferences
- Pages
- 1-3(Total 3 p)
- Date of publication
- Sep 2021
- Publisher
- JSAE
- Language
- English
Detailed Information
Author(E) | 1) Shuncong Shen, 2) Mai Saito, 3) Toshio Ito |
---|---|
Affiliation(E) | 1) Shibaura Institute of Technology, 2) Shibaura Institute of Technology, 3) Shibaura Institute of Technology |
Abstract(E) | For automated driving, accurate detection and recognition of the surrounding environment are essential to ensure the safety driving. Light Detection And Ranging (LiDAR) has been used as an external recognition sensor, which plays a role in obstacle recognition, mapping, tracking, etc. LiDAR senses the environment by using laser light and provides excellent range information, however is also limited by distance. This paper proposes a method to obtain the depth information of feature points from objects motion by utilizing the conventional optical flow and using the virtual gradient method to increase the density, finally fuse them with the LiDAR point cloud data. Experimental results show that this method can solve the sparse data problem and the effectiveness for improving LiDAR point cloud density is discussed. |