# USB camera
Source: [https://docs.qualcomm.com/doc/80-70022-50/topic/usb-camera.html](https://docs.qualcomm.com/doc/80-70022-50/topic/usb-camera.html)
The **gst-ai-usb-camera-app** streams video from a USB webcam connected to the
Qualcomm EVK. This webcam should be accessible as a /dev/videoX device.
While you can perform object detection and preview the results, this procedure allows you to
process the input from the USB camera without performing AI inferencing.
The AI USB camera application uses the
/etc/config/config-usb-camera-app.json file to read the input
parameters.
You can choose to run this application with and without AI inferencing. To run this
application with AI inferencing, see [AI USB camera](https://docs.qualcomm.com/doc/80-70022-50/topic/ai-usb-camera.html).
The following figures show a pipeline, which processes the input from the USB camera to
generate various outputs.
For more information about the plugins used in these pipelines, see [Pipeline flow](https://docs.qualcomm.com/doc/80-70022-50/topic/usb-camera.html#use-camera__section_sy3_wd2_ncc).
Figure : gst-usb-single-camera-app pipeline
## Run the application
Before running the application, complete the [Prerequisites](https://docs.qualcomm.com/doc/80-70022-50/topic/download-model-and-label-files.html).
1. In the terminal of the target device, do the following to run this sample
application without the AI inferencing:
1. Use the config-usb-camera-app.json file from
`/etc/configs/` directory.
2. In the config-usb-camera-app.json file, set
`enable-object-detection` to `FALSE`.
3. Run the gst-ai-usb-camera-app
application:
gst-ai-usb-camera-app --config-file=/etc/config/config-usb-camera-app.jsonCopy to clipboard
2. To stop the use case, use CTRL +
C.
3. In the terminal of the target device, run the following command in the SSH shell
to display the available help
options:
gst-ai-usb-camera-app -hCopy to clipboard
## Expected output
The following table lists the expected output for each use case:
Table : Expected output for gst-ai-usb-single-camera-app–without AI
| Use case | Output |
| :--- | :--- |
| Preview | Preview of the camera stream. See the [Figure : Expected output for gst-usb-single-camera-app application - Preview](https://docs.qualcomm.com/doc/80-70022-50/topic/usb-camera.html#use-camera__fig_ihh_tqq_5bc). |
| Save the MP4 and YUV data | Save the output to a file at /etc/media/ folder path. |
| RTSP | View the output on a remote display. |
Figure : Expected output for gst-usb-single-camera-app application - Preview
## Pipeline flow
The following table lists the plugins used in the USB camera streaming
pipeline:| Pipeline | Description |
| --- | --- |
| Dump the camera YUV to a filesink |
Capsfilter is applied to enforce constraints on the raw video data.
v4l2h264enc is used to encode the video using the H.264 format.
H264parse is used to parse the video.
qtirtspbin is used to load the stream to RTSP.
|
**Parent Topic:** [Run sample applications for a camera](https://docs.qualcomm.com/doc/80-70022-50/topic/camera-sample-applications.html)
Last Published: Feb 20, 2026
[Previous Topic
Single camera streaming](https://docs.qualcomm.com/bundle/publicresource/80-70022-50/topics/gst-camera-single-stream-example.md) [Next Topic
Multi-camera streaming](https://docs.qualcomm.com/bundle/publicresource/80-70022-50/topics/gst-multi-camera-stream-example.md)