ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | Q&A
Ask Your Question

Enabling multiple cameras in Autoware(with LGSVL)

asked 2020-07-16 16:24:01 -0600

SenRamakri gravatar image

Hello!, Is there any documentation/pointers on how to enable multiple cameras on(for example: with LGSVL) Autoware.AI? Thanks.

edit retag flag offensive close merge delete

1 Answer

Sort by ยป oldest newest most voted

answered 2020-07-18 18:33:55 -0600

Josh Whitley gravatar image

I'm not sure what you mean by "enabling" multiple cameras. Autoware.AI uses a decentralized sensor processing architecture so the data from each sensor is processed independently into abstract items like "objects" or" obstacles" before being used.

If you want to use multiple cameras to, for example, detect objects, each camera will have its own object detection pipeline and you'll have to come up with a way to combine the objects detected by all of the cameras before they are used, for example, in the obstacle avoidance node. The object fusion functionality is not available out-of-the-box but it shouldn't be too difficult to implement.

edit flag offensive delete link more



@josh-whitley - Sorry I was not clear. Yes, the question was to use multiple cameras to have larger field of view around the vehicle. And your answer really helped in terms how to support that use-case, Thanks.

SenRamakri gravatar image SenRamakri  ( 2020-07-18 18:48:41 -0600 )edit

Please remember to accept the answer if it answered your question (the checkmark under the score buttons).

Josh Whitley gravatar image Josh Whitley  ( 2020-07-18 18:51:44 -0600 )edit

Ah yes, thanks for pointing that out. (I'm kind of new to this group :-).)

SenRamakri gravatar image SenRamakri  ( 2020-07-18 18:54:19 -0600 )edit

Your Answer

Please start posting anonymously - your entry will be published after you log in or create a new account.

Add Answer

Question Tools

1 follower


Asked: 2020-07-16 16:24:01 -0600

Seen: 223 times

Last updated: Jul 18 '20