MATLAB: How to use an USB 3 Basler cameras with the GPU Coder on the Nvidia Jetson TX2

GPU CoderImage Acquisition Toolboxmatlab codernvidia jetson tx2

I have problems to use an USB3 basler camera on the Nvidia Jetson TX2. I would like to generate the CUDA code with the Matlab GPU Coder.

Unfortunatly I can't see the cameras in the webcamlist.

hwobj = drive('drive-px2-name','ubuntu','ubuntu'); 
hwobj.webcamlist
ans =
     []

Is it only possible with webcams and not with industrial cameras?

Thank you for some hints.

Best Answer

Hi Caludio,

For accessing Jetson from MATLAB you should use jetson class, for E.g

hwobj = jetson('IPAddress','UserName','Password');

You are using the drive class for accessing the Jetson hardware.

Coming to your question,

Currently, "GPU Coder support package for NVIDIA GPUs" can only providing accessing webcam devices listed under /dev (i.e /dev/video*). These Basler cameras can not be listed since they use a proprietary driver from Basler.

we will register this requirement and try to enhance our software.

Thanks for using MathWorks Products.

Related Solutions

MATLAB: Is Matlab/ Simulink supporting Nvidia external GPU Systems/Thunderbold 3 for Machine Learning and Deep Learning projects including embedded systems like Jetson TX2

Yes, it's supported. This isn't really a question of MATLAB's system requirements; if the CUDA driver can interact with your card then so can MATLAB. You will notice a considerable increase in latency due to the dramatically reduced bandwidth to get data on and off the card, so you need to minimize the amount of CPU/GPU communication.

MATLAB: SDL error with NVIDIA Jetson & GPU Coder

Hi Hermann,

I am assuming that you are having Jetpack version > 3.3 on the target board.This issue is regarding the change of the display environment value on the target board for Jetpack version > 3.3. For this version of Jetpack, before running the application on the target board, you should set the display environment in MATLAB using hwobj.setDisplayEnvironment('value') (hwobj is the object of jetson or drive class). This setting is available from R2019a version of MATLAB, as you are using R2019b MATLAB, you will have this.

To obtain the display environment value, please log in to the target board and run the below command.

$ echo $DISPLAY

expected output: "0.0" for Jetpack <= 3.3 and "1.0" for Jetpack > 3.3.

Create a hardware object for the target board.

hwobj = jetson('ip address','user name','password');

Set the target display environment in MATLAB using

hwobj.setDisplayEnvironment('1.0')

Run the application on target board using

hwobj.runApplication('function name').

You will be able to see the display window on target monitor.

Cheers.

Best Answer

Related Solutions

MATLAB: Is Matlab/ Simulink supporting Nvidia external GPU Systems/Thunderbold 3 for Machine Learning and Deep Learning projects including embedded systems like Jetson TX2

MATLAB: SDL error with NVIDIA Jetson & GPU Coder

Related Question