Accelerating map_pointcloud_to_image by loading LIDAR data only once
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 390
- Forks
- 99
- PR merge metrics
- No merged PRs in 30d
Description
This following function performs a pretty expensive computation:
https://github.com/lyft/nuscenes-devkit/blob/e4efd52a9630959a5b890e1575b58cab145e2441/lyft_dataset_sdk/lyftdataset.py#L653-L715
I am curious: does this function take so much time to run because of the process of loading the lidar cloud points, or transforming the 3D coordinates into 2D for a specific camera?
I am personally using this function in my [public kernel for the Kaggle competition](https://www.kaggle.com/xhlulu/lyft-eda-animations-generating-csvs/edit), and I realized that running this for all cameras, and across multiple timestamps takes a considerable amount of time, which could be partially caused by the data loading, I could cache it so that the lidar data is not redundantly loaded for every camera for a single timestamp.
Thanks!
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with lyft_dataset_sdk/lyftdataset.py lines 653-715 and inspect map_pointcloud_to_image. Profile the function across multiple cameras and timestamps to distinguish LIDAR loading from 3D-to-2D transformation. Done means avoiding redundant LIDAR loading for cameras sharing a timestamp while preserving the projected output.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, performance
- Issue type
- Refactor
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100