# Camera encode, object detection, and display Source: [https://docs.qualcomm.com/doc/80-70020-50/topic/camera-encode-file-detection-yolov8-overlay-display.html](https://docs.qualcomm.com/doc/80-70020-50/topic/camera-encode-file-detection-yolov8-overlay-display.html) The **gst-camera-two-stream-encode-file-detection-display.py** application encodes the camera stream and saves it to a file. The application uses a YOLOv8 LiteRT model to identify the objects in a scene from a camera stream. The application overlays the bounding boxes over the detected objects and displays the results. Note: For Ubuntu Server, this sample application isn't supported on Dragonwing IQ-8275. Figure : Pipeline for camera encode and object detection For information about the plugins used in this pipeline, see [Pipeline flow](https://docs.qualcomm.com/doc/80-70020-50/topic/camera-encode-file-detection-yolov8-overlay-display.html#camera-encode-file-detection-yolov8-overlay-display__section_mty_hyk_bdc). ## Run the application on the target device 1. Ensure that you complete the [Prerequisites](https://docs.qualcomm.com/doc/80-70020-50/topic/prerequisites-for-python-sample-applications.html). 2. Export the YOLOv8 model and update the model name in the commands with the appropriate model name as downloaded through AI Hub. 3. Run the camera encode and object detection script on the target device: gst-camera-two-stream-encode-file-detection-display.pyCopy to clipboard 4. To display the available help options, run the following command: gst-camera-two-stream-encode-file-detection-display.py -hCopy to clipboard The following are the default files in the Python script: Table : Default model and label files for gst-camera-two-stream-encode-file-detection-display.py | Files | Directory | | :--- | :--- | | Detection model (YOLOv8) | /etc/models/YoloV8N\_Detection\_Quantized.tflite | | Detection labels (same for both models) | /etc/labels/yolov8n.labels | ## Expected output The output is saved at /etc/media/test.mp4. ## Pipeline flow | Process | Description | | --- | --- | | [qtiqmmfsrc](https://docs.qualcomm.com/doc/80-70020-50/topic/qtiqmmfsrc.html) | Collects two video streams from the camera:

One stream is saved to a file.

The second stream is used for detection. It's split using
tee and sent to the following:
- qtimetamux to retain the video stream.
- qtimlvconverter to convert the video stream to input
  tensors for the classification inference.

Receives the video stream on its sink pad.

Performs preprocessing:
- Color conversion
- Scaling down/up
- Normalization on the stream data when the model
  expects the floating point values as an input

Converts the video stream to a tensor stream on its source
pad.
The object detection model uses this tensor
stream for inferencing.

Loads the model.

Modifies the graph for the chosen delegate.

Receives the tensor stream on its sinkpad.

Runs the inference and produces a tensor stream with the
inference results on its source pad.

| | **Postprocessing** | **Postprocessing** | | [qtimlvdetection](https://docs.qualcomm.com/doc/80-70020-50/topic/qtimlvdetection.html) |

Receives the inference tensors from the object detection
model.

Converts the inference tensors on its sinkpad into formats
such as video or text that the multimedia plugins can
process later.

Applies the threshold to the chosen number of results.

Loads the corresponding modules for detection models.
In
this use case, qtimlvdetection does the following:
1. Loads the YOLOv8 submodule.
2. Produces results as structures of text.
3. Sends them to the sinkpad of qtimetamux.

| | [qtimetamux](https://docs.qualcomm.com/doc/80-70020-50/topic/qtimetamux.html) |

Receives video stream and text stream with bounding box
results corresponding to the video stream on its
sinkpads.

Produces GST buffers with contents of the video stream from
its sink pad.

Adds bounding boxes as GstVideoRegionOfInterest from data
sinkpad to GST buffers meta (meta muxing) on its source
pad.

| | [qtivoverlay](https://docs.qualcomm.com/doc/80-70020-50/topic/qtioverlay.html) |

Receives the multiplexed stream.

Overlays the bounding boxes on the VideoFrame using CL.

Produces GST buffers with overlays in its source pad.

Receives the video in its sinkpad

Submits the video stream to Weston.

Weston renders the video stream on a local display
device.

| ## Related information [Object detection](https://docs.qualcomm.com/doc/80-70020-50/topic/gst-ai-object-detection.html) **Parent Topic:** [Python applications](https://docs.qualcomm.com/doc/80-70020-50/topic/python-sample-applications.html) Last Published: Jan 30, 2026 [Previous Topic Transform and encode a camera stream](https://docs.qualcomm.com/bundle/publicresource/80-70020-50/topics/camera-transform-downscale-and-rotate-encode.md) [Next Topic Object detection, classification, and segmentation](https://docs.qualcomm.com/bundle/publicresource/80-70020-50/topics/object-detection-classification-and-segmentation-python-sample-app.md)