Obstacle avoidance with pure Vision approach?

asked 2018-02-13 21:23:09 -0600

Astronaut gravatar image

Hi

I would like to do obstacle avoidance using pure Vision approach. I will use ROS and Ubuntu as a framework. The application is in construction industry so would like to detect the material winch is handling by the crane to perform obstacle avoidance . My question is , if its possible to use only vision approach for obstacle avoidance where the distance form the camera to the object can be 30-40m. I will use the zoom for better approach. If its possible to use only Vision camera any starting algorithm to look at it?

Thanks

edit retag flag offensive close merge delete

Comments

Well stereo camera setup is pure vision based , yes you can construct a disparity map which could then be used for depth . Depth can be used for the purpose of mapping while performing path planing keeping obstacle avoidance in mind .

chris_sunny gravatar image chris_sunny  ( 2018-02-13 23:04:46 -0600 )edit

https://www.stereolabs.com/

Check out this stereo camera , cost wise its a little on the higher side , but a lot can be achieved using this device .

chris_sunny gravatar image chris_sunny  ( 2018-02-13 23:06:46 -0600 )edit

I know this ZED camera. But the distance is quite long, as for some high rise buildings can be over 50 m easily and the depth information from the camera in that case can not be used. So is the distance a problem for pure vision approach?

Astronaut gravatar image Astronaut  ( 2018-02-14 00:14:16 -0600 )edit

What do you mean by "pure vision based approach"? No 3D information?

gvdhoorn gravatar image gvdhoorn  ( 2018-02-14 01:56:40 -0600 )edit

I mean only using Machine Vision Camera, no other sensors.

Astronaut gravatar image Astronaut  ( 2018-02-14 03:01:24 -0600 )edit

You need good contrast in order for stereo cameras to give you good depth information.

Kurt Leucht gravatar image Kurt Leucht  ( 2018-02-14 13:28:20 -0600 )edit

but if the distance is far , let say more then 50m how can be provided the depth information?

Astronaut gravatar image Astronaut  ( 2018-02-14 20:32:38 -0600 )edit

And is there any code using ROS, Neural Networks or Deep Learning, Machine Vision based obstacle avoidance code? Just o start it as Im beginner in this

Astronaut gravatar image Astronaut  ( 2018-02-14 20:51:50 -0600 )edit