Camera

Capture video from a USB or CSI camera connected to the NVIDIA target

• Library:

• NVIDIA Jetson and NVIDIA DRIVE / Audio and Video

• 

Description

Capture live video from a USB or CSI camera. The output is in row major format. During simulation, the model outputs a moving colorbar image.

Install the GStreamer library, V4L2 library, and V4L2 utilities on the target. You must also install the development packages for these libraries. For more information, see Install and Setup Prerequisites for NVIDIA Boards

Ports

Output

R — Red component of the output video stream

matrix

This port outputs the red component of each pixel.

Data Types: uint8

G — Green component of the output video stream

matrix

This port outputs the green component of each pixel.

Data Types: uint8

B — Blue component of the output video stream

matrix

This port outputs the blue component of each pixel.

Data Types: uint8

Parameters

Name — Name of connected video device

My Camera (default)

Enter the path and name of the video device.

The Linux^® kernel creates a video device file when you connect a supported USB or CSI video camera to the target hardware. To see the list of video device files, open a command line session with the target hardware and enter: ls -al /dev/video*.

Programmatic Use

Block Parameter: CameraName

Type: character vector

Values: valid name|

Default: 'My Camera'

Image size — Display resolution

[320, 240] (default) | [width, height]

Specify the display resolution of the image to be captured, in pixels.

Programmatic Use

Block Parameter: ImageSize

Type: character vector

Values: [width, height]|

Default: '[320, 240]'

Sample time — Frequency at which a new image is captured

0.1 (default) | scalar | vector

Select the sample time of the video device.

Smaller values require the processor to complete the same number of instructions in less time, which can cause task overruns.

Programmatic Use

Block Parameter: SampleTime

Type: character vector

Values: scalar | vector

Default: '0.1'

Model Examples

Deploy and Classify Webcam Images on NVIDIA Jetson TX2 Platform from Simulink

Deploy a Simulink® model on the NVIDIA® Jetson TX2 board for classifying webcam images. This example classifies images from a webcam in real-time by using the pretrained deep convolutional neural network, ResNet-50. The Simulink model in the example uses the camera and display blocks from the MATLAB® Coder™ Support Package for NVIDIA Jetson and NVIDIA DRIVE Platforms to capture the live video stream from a webcam and display the prediction results on a monitor connected to the Jetson platform.