Skip to content
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

Lane type detection #434

Open
pranavboyapati opened this issue Sep 24, 2024 · 5 comments
Open

Lane type detection #434

pranavboyapati opened this issue Sep 24, 2024 · 5 comments
Assignees
Labels
Feature Something new to be added

Comments

@pranavboyapati
Copy link

pranavboyapati commented Sep 24, 2024

This should be able to detect all the lanes that are available on the road and should also determine lane type (e.g. left turn only, right turn only, straight, etc.)

@pranavboyapati pranavboyapati converted this from a draft issue Sep 24, 2024
@pranavboyapati pranavboyapati added the Feature Something new to be added label Sep 24, 2024
@pranavboyapati
Copy link
Author

11/11/2024 Update:

  • Status: Just picked up this task today
  • Next Steps: Plan out completion and conduct research on useful resources
  • Projected Completion: Monday, November 18
  • Update: I will plan out the completion of this task and research useful resources for completing this task by next Monday.

@pranavboyapati pranavboyapati self-assigned this Nov 11, 2024
@pranavboyapati pranavboyapati moved this from ✏️ Todo to 🛠️ In-Progress in 🧭 Navigator Nov 11, 2024
@pranavboyapati
Copy link
Author

11/18/2024 Update:

  • Status: Finished planning and research
  • Next Steps: Build a dataset of images to use for making the classification model
  • Projected Completion: Monday, November 25
  • Update: I finished planning out how to complete this task and also conducted research to find helpful resources for completing this task. The next step is to make a custom dataset of images to use for training the model. I need to create a custom dataset because there isn't a pre-existing dataset that works for this use case. This step will be finished in one week.

@pranavboyapati
Copy link
Author

12/02/2024 Update:

  • Status: Created dataset of images for training the model
  • Next Steps: Annotate all of the images
  • Projected Completion: Monday, December 9
  • Update: I created a dataset of images that contain all of the possible lane markings that could be encountered while driving. The next step is to annotate these images so that I can use them for training the classification model.

@pranavboyapati
Copy link
Author

01/27/2025 Update:

  • Status: Annotated all images
  • Next Steps: Train the YOLO model to make detections
  • Projected Completion: 1-2 weeks
  • Update: The dataset of lane type markings has been annotated. The next step is to train the YOLO model to detect lane type markings. I am expecting this to take 1-2 weeks, but not sure about it since I've never done this before.

@pranavboyapati
Copy link
Author

02/03/2025 Update:

  • Status: Finished training YOLO model
  • Next Steps: Make the ROS node
  • Projected Completion: Monday, February 10
  • Update: I trained a YOLO 11 model for detecting lane types and tested it. The next step is to integrate this into a ROS node, which will be done by next week.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Feature Something new to be added
Projects
Status: 🛠️ In-Progress
Development

No branches or pull requests

1 participant