[TASK] Pipeline detection #4
Labels
enhancement
New feature or request
large
~ a couple days to complete
perception
Perception team responsible
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
Another Lane Detection Example
Specifications
Contacts
@jorgenfj
Code Quality
The text was updated successfully, but these errors were encountered: