-
Notifications
You must be signed in to change notification settings - Fork 10
Lane detection code using CLRerNet model #237
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: s2025
Are you sure you want to change the base?
Conversation
…he lane detection
krishauser
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
"lanes" is not a valid output to the state. I am not sure how this even ran. The use of "RoadgraphSimpleLane" rather than RoadgraphLane is also not justified. PR not approved.
… my customized RoadgraphSimpleLane
|
@krishauser Hi, Professor Hause, since it is not good to use my customized in-house-used-only "RoadgraphSimpleLane" and "lanes" output (for the "lanes" output to be used, I need to coordinate with other team's codes). I upload the offboard code that I used to test the model on the output images recorded from the front camera of the G4 vehicle to the offboard folder and include the README.md that instructs how to use it. |
… my customized RoadgraphSimpleLane
… my customized RoadgraphSimpleLane
|


I used the code and model to test the performance of the lane detection which is a bounty task. Although, due to that the pretrained model was not suitable for detection of the narrow lane in high-bay, it could detect the lanes in real street.