search

l1997i / DurLAR

(3DV 2021) A High-fidelity 128-channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-modal Autonomous Driving Applications
MIT License
29 stars 1 forks source link

How ambient images are generated？ #6

Closed yscani closed 1 year ago

yscani commented 1 year ago

Hi, thanks for sharing this dataset.

I would like to know how the ambient images in the data set are generated, and which sensor data is used to generate them.

Thanks.

l1997i commented 1 year ago

Hi @yscani,

ambient and reflectivity panoramic imagery all come from OS1-128 LiDAR. The dimension of the panoramic imagery is $j \times k \times 1$, where $j$ represents the number of beams emitted (for DurLAR, KITTI and nuScenes, $j=128, 64$ and $32$ respectively) and $k$ represents the number of times measurement in one scan cycle [1]. You can refer to [1] for more details getting panoramic imagery (range image) from 3D point cloud.

[1] Fan, Lue, Xuan Xiong, Feng Wang, Naiyan Wang, and Zhaoxiang Zhang. "Rangedet: In defense of range view for lidar-based 3d object detection." In Proceedings of the International Conference on Computer Vision (ICCV), IEEE. 2021.

Cheers, Luis

yscani commented 1 year ago

I get it, Thank you very much @l1997i .