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

[TASK] Pipeline detection #4

Closed
3 tasks
jorgenfj opened this issue Sep 20, 2024 · 3 comments
Closed
3 tasks

[TASK] Pipeline detection #4

jorgenfj opened this issue Sep 20, 2024 · 3 comments
Assignees
Labels
enhancement New feature or request large ~ a couple days to complete perception Perception team responsible

Comments

@jorgenfj
Copy link
Contributor

jorgenfj commented Sep 20, 2024

Description of task

We need some way to detect the pipeline during the pipeline inspection mission under TACC.
This problem is just another version of the lane detection and following problem faced in autonomous driving.

This will be just be a prototype to test how applicable the traditional openCV implementation of lane detection is to our use case. However, if you want to take a deep-dive into a possible final solution you are also free to do that.

If you do choose do go the deep-learning route here are some relevant resources:
Lane Detection: The 3 types of Deep Learning (non-OpenCV) algorithms
Git Repo for Deployment of Deep Learning on Jetson (Jetson AGX Orin is the computer we will use on Orca)
Here is an example of Segmentation using SegNet which looks applicable for our task

We have a previous concept of how to solve this task, but I don't think the end product was properly tested/finished.

Suggested Workflow

  • Look into the openCV Lane Detection &
    Another Lane Detection Example
  • Use the rosbags uploaded on Teams of the mission run from this summer to test your implementation.
  • Look into this concept on the Wiki and its implementation in the vortec-cv repo
  • Look into the disadvantages/challenges of the previous implementation and see how the lane detection example can solve them.
  • Alternatively research how to solve this task using deep learning

Specifications

  • Should output required heading to stay on course
  • Visualize detected pipe and/or path

Contacts

@jorgenfj

Code Quality

  • Every function in header files are documented (inputs/returns/exceptions)
  • The project has automated tests that cover MOST of the functions and branches in functions (pytest/gtest)
  • The code is documented on the wiki (provide link)
@jorgenfj jorgenfj added enhancement New feature or request large ~ a couple days to complete perception Perception team responsible labels Sep 20, 2024
@Sam1-2 Sam1-2 self-assigned this Sep 25, 2024
@christopherbjorge christopherbjorge self-assigned this Sep 25, 2024
@Jekta8 Jekta8 self-assigned this Sep 25, 2024
@Jekta8 Jekta8 removed their assignment Sep 25, 2024
@jorgenfj
Copy link
Contributor Author

@jorgenfj
Copy link
Contributor Author

jorgenfj commented Jan 6, 2025

moved to another repo vortexntnu/vortex-pipeline-detection#2

@jorgenfj jorgenfj closed this as completed Jan 6, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request large ~ a couple days to complete perception Perception team responsible
Projects
None yet
Development

No branches or pull requests

6 participants