Deep Learning Streamer – Change the Video Input

Reading Time: 2 minutes

The ADLINK Edge® App Deep Learning Streamer includes a link to a video as the default input for inferencing. You can change this input to any of the following:

This article explains how to change the output to a webcam on the deep learning streamer. The webcam should be plugged directly into your Vizi-AI. Ensure you have already set up your Vizi-AI with Deep Learning Streamer, refer to Vizi-AI with Deep Learning Streamer.

Update Deep Learning Streamer to use a Webcam

  1. Within Edge Profile Builder open the project and profile that contain the Deep Learning Streamer application.
  2. Select the ‘Deep Learning Streamer’ app and the Configuration tab.
  3. From the inputsOption drop-down, select ‘v4L2’, in device enter ‘/dev/video0’ and click Save Changes.
  1. To map the device to a container, select the Docker tab, change the contents of the docker create options box to the following:
{
    "NetworkingConfig": {
        "EndpointsConfig": {
            "host": {}
        }
    },
    "HostConfig": {
        "NetworkMode": "host",
        "Privileged": true,
        "Binds": [
            "/dev:/dev"
        ]
    }
}
  1. Click Save Changes and then click Close.
  2. The changes must now be deployed to the Vizi-AI, click Deploy, if your device is registered locally, select Deploy directly to a device, click Next choose the device and click Deploy. If your device is registered with Azure IoT Edge, select to Upload to a cloud service, click Next, choose the service to upload to and click Upload.

View the Results

To view the inference results, use a third party video streaming application, for example, VLC Media Player. The RTSP address is “rtsp://<DEVICE IP ADDRESS>:8554/intelDemoStream” where the <DEVICE IP ADDRESS> is the IP address of your Vizi-AI, for example: “rtsp://192.168.0.66:8554/intelDemoStream”.

In VLC Media Player select Media and Open Network Stream, enter the RTSP address and click Play.