Detect People with a Webcam

Add a new machine in the Viam app by providing a name in the New machine field and clicking Add machine.

Click the name of a machine to go to that machine’s page, where you’ll find a variety of tools for working with your machine.

Navigate to the CONFIGURE tab of your machine’s page in the Viam app. Click the + icon next to your machine part in the left-hand menu and select Component. Select the camera type, then select the webcam model. Enter a name or use the suggested name for your camera and click Create.

Click the Save button in the top right corner of the page to save your configuration. Go to the CONTROL tab and expand the camera’s remote control card to test the camera stream. If you don’t see an image stream, you need to configure the video_path attribute.

For more detailed information, including optional attribute configuration, see the webcam docs.

Navigate to the CONFIGURE tab of your machine’s page in the Viam app. Click the + icon next to your machine part in the left-hand menu and select Service. Select the ML model type, then select the TFLite CPU model. Enter a name or use the suggested name for your service and click Create.

In the resulting ML model service configuration pane, ensure that Deploy model on machine is selected for the Deployment field.

Click on Select models to open a dropdown with all of the ML models available to you. Select the ml-models-scuttle:people model (the people model by ml-models-scuttle) to deploy an object detection TFLite model that has been trained to be able to detect a person.

Click the Save button in the top right corner of the page to save your configuration.

For more detailed information, including optional attribute configuration, see the tflite_cpu docs.

Navigate to the CONFIGURE tab of your machine’s page in the Viam app. Click the + icon next to your machine part in the left-hand menu and select Service. Select the vision type, then select the ML model model. Enter a name or use the suggested name for your service and click Create.

Select the ML model service your person detector model is deployed on (which you created in step 4) from the ML Model dropdown. Then, click {} (Switch to advanced) in the top right corner of the configuration pane. Add the following JSON to the JSON configuration to set the default_minimum_confidence of the detector:

"default_minimum_confidence": 0.82

This optional attribute simplifies your detections output (which you’ll view in step 6) by filtering out detections below the threshold of 82% confidence. You can adjust this attribute as necessary.

Click the Save button in the top right corner of the page to save your configuration.

For more detailed information, including optional attribute configuration, see the mlmodel docs.

Now, test your person detection with the computer vision service’s remote control card.

Navigate to the CONTROL tab in the Viam app. Click on the vision service’s card to expand it.

Click Refresh to refresh the image stream and see detections as labeled boxes on the images along with position, dimension, class and confidence data. Detections in class Person with a high confidence score show positive person detections, but the ML model can also detect other objects:

You can view detections with a lower confidence score from the vision control card, like in the above screenshot, by lowering the "default_minimum_confidence" attribute.