ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange
Ask Your Question
0

How to identify lines on the ground when mapping?

asked 2020-04-17 13:13:59 -0500

willzoe gravatar image

I have an idea that when mapping, let the robot recognize the lane line or parking frame on the ground. Then, set the position of the lane line or parking frame as an obstacle (such as a virtual wall) to allow the robot to move at a certain distance (such as 1 meter) from the line.

Is there any way to achieve this or similar functions?

edit retag flag offensive close merge delete

Comments

Or which forum is more suitable for asking this question?

willzoe gravatar image willzoe  ( 2020-04-17 13:15:53 -0500 )edit

Hi, did you find the solution for your question? I am currently working on something similar. In my project, the lines drawn on the floor are from a circuit for a RC-car. And the lines should act as limits so the car doesn't get out of the circuit.

MrRivi gravatar image MrRivi  ( 2020-09-06 03:29:43 -0500 )edit

1 Answer

Sort by ยป oldest newest most voted
1

answered 2020-04-25 14:58:55 -0500

pring gravatar image

I'd suggest looking into Hough Lines, as that's how Autonomous Vehicles currently detect lines.

In terms of setting the lines as an obstacle ... it depends on the use case. If you're using move_base to move a robot, then you would need obstacles yes. .. at any rate, you would need a camera to detect the lines. I'd suggest using a depth camera: use the color image to get your lines and then get the 3D points of those pixels by 'overlaying' them with the depth image. With those 3D points you can create obstacles. You'll likely need to look more into move_base to see how that could be done. I can see a shortcut where you just fake the obstacle by publishing to '/scan' so that move_base will see those points as lidar scans and thus avoid them.

Good luck

edit flag offensive delete link more

Comments

In other words, I need to write a node or package to subscribe to the color images and depth images of the depth camera, and perform the Hough detection before publishing the virtual scan topic. Are there some examples I can refer to?

willzoe gravatar image willzoe  ( 2020-04-25 21:00:52 -0500 )edit

Question Tools

3 followers

Stats

Asked: 2020-04-17 13:13:59 -0500

Seen: 450 times

Last updated: Apr 25 '20