# Object detection and display
Source: [https://docs.qualcomm.com/doc/80-70017-50/topic/camera-detection-display.html](https://docs.qualcomm.com/doc/80-70017-50/topic/camera-detection-display.html)
The **gst-ai-object-detection.py** application enables you to detect objects in
the camera stream or a file stream and display the results or save the output to a
file.
Figure : Pipeline for object detection and preview
For information on the plugins used in this pipeline, see [Pipeline flow](https://docs.qualcomm.com/doc/80-70017-50/topic/camera-detection-display.html#camera-detection-display__section_jbz_cbk_bdc).
## Run the application
1. Ensure that you complete the [Prerequisites](https://docs.qualcomm.com/doc/80-70017-50/topic/python-sample-applications.html#python-sample-applications__section_gm5_s5j_bdc).
2. Run various use cases:
Table : Sample model and label files for object detection and display python
application
| Runtime | Models | Labels |
| :--- | :--- | :--- |
| LiteRT |
yolonas.tflite
yolov8.tflite
|
yolonas.labels
yolov8.labels
|
| Qualcomm Neural Processing SDK | yolonas.dlc | yolonas.labels |
- Display with the primary and secondary cameras respectively:
- python3 /usr/bin/gst-ai-object-detection.py -c 0 -f 2 -m /opt/yolov8.tflite -l /opt/yolov8.labels -ml "yolov8" -k "YOLOv8,q-offsets=<-107.0, -128.0, 0.0>,q-scales=<3.093529462814331, 0.00390625, 1.0>"Copy to clipboard
- python3 /usr/bin/gst-ai-object-detection.py -c 1 -f 2 -m /opt/yolov8.tflite -l /opt/yolov8.labels -ml "yolov8" -k "YOLOv8,q-offsets=<-107.0, -128.0, 0.0>,q-scales=<3.093529462814331, 0.00390625, 1.0>"Copy to clipboard
- Display with input from a video
file:
python3 /usr/bin/gst-ai-object-detection.py -s /path/to/input/video.mp4 -f 2 -m /opt/yolov8.tflite -l /opt/yolov8.labels -ml "yolov8" -k "YOLOv8,q-offsets=<-107.0, -128.0, 0.0>,q-scales=<3.093529462814331, 0.00390625, 1.0>"Copy to clipboard
- YOLO-NAS with
LiteRT:
python3 /usr/bin/gst-ai-object-detection.py -f 2 -m /opt/yolonas.tflite -l /opt/yolonas.labels -ml "yolo-nas" -k "YOLO-NAS,q-offsets=<37.0, 0.0, 0.0>,q-scales=<3.416602611541748, 0.00390625, 1.0>"Copy to clipboard
- YOLO-NAS with Qualcomm Neural Processing SDK
runtime:
python3 /usr/bin/gst-ai-object-detection.py -f 1 -m /opt/yolonas.dlc -l /opt/yolonas.labels -ml "yolo-nas" --layers="/heads/Mul,/heads/Sigmoid"Copy to clipboard
- YOLOv8 with
LiteRT:
python3 /usr/bin/gst-ai-object-detection.py -f 2 -m /opt/yolov8.tflite -l /opt/yolov8.labels -ml "yolov8" -k "YOLOv8,q-offsets=<-107.0, -128.0, 0.0>,q-scales=<3.093529462814331, 0.00390625, 1.0>"Copy to clipboard
To display the available help options, run the following command:
python3 gst-ai-object-detection.py --helpCopy to clipboard
## Expected output
Figure : Expected output for object detection and display application –
Preview
## Pipeline flow
| Process | Description |
| --- | --- |
| [qtiqmmfsrc](https://docs.qualcomm.com/doc/80-70017-50/topic/qtiqmmfsrc.html) |
Collects the video stream (source) and creates two copies of the source:
One stream is sent to the qtimetamux plugin to retain the video stream.
The other stream is sent to an ML inferencing pipeline.
|
| filesrc | Reads the video data. |
| **Preprocessing** | **Preprocessing** |
| [qtimlvconverter](https://docs.qualcomm.com/doc/80-70017-50/topic/qtimlvconverter.html) |
Receives the video stream on its sinkpad.
Performs preprocessing:
Color conversion
Scaling down/up
Normalization on the stream data when the model expects the floating point values as input
Converts the video stream to a tensor stream on its source pad.
The object detection model uses this tensor stream for inferencing.
Weston renders the video stream and bounding boxes generated for the objects in that scene on a local display device.
|
| Filesink | Writes the video to a file. |
**Parent Topic:** [Python applications](https://docs.qualcomm.com/doc/80-70017-50/topic/python-sample-applications.html)
**Related Resources**
- [Object detection](https://docs.qualcomm.com/doc/80-70017-50/topic/gst-ai-object-detection.html)
Last Published: Oct 01, 2026
[Previous Topic
Multi-camera streaming using Python](https://docs.qualcomm.com/bundle/publicresource/80-70017-50/topics/multi-camera-streaming-python-sample-app.md) [Next Topic
Decode and object detection using RTSP stream](https://docs.qualcomm.com/bundle/publicresource/80-70017-50/topics/rts-decode-ai-detection-yolo-v8-overlay-display.md)