# Object detection

Before executing the pipeline command for a model, make sure to follow the required [Prerequisites](https://docs.qualcomm.com/doc/80-70017-15B/topic/ai-hub-qualcomm-im-sdk.html#prerequisites).

Run the following command to ensure your result is displayed on the connected display.

export XDG_RUNTIME_DIR=/dev/socket/weston && export WAYLAND_DISPLAY=wayland-1
    Copy to clipboard

## Yolo-V7 Quantized

- Model: [Yolo-v7-Quantized.tflite](https://aihub.qualcomm.com/iot/models/yolov7_quantized)
- Label: [coco_labels.txt](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/labels/coco_labels.txt)

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/opt/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=5 output-io-mode=5 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer ! queue ! waylandsink fullscreen=true \
    split. ! queue ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/opt/Yolo-v7-Quantized.tflite ! queue ! \
    qtimlvdetection threshold=50.0 results=10 module=yolov8 labels=/opt/coco_labels.txt constants="YOLOv7,q-offsets=<35.0, 0.0, 0.0>,q-scales=<3.4220554, 0.0023370725102722645, 1.0>;" ! \
    video/x-raw,format=BGRA,width=640,height=360 ! queue ! mixer.
    Copy to clipboard

## Yolov8-Detection-Quantized

- Model: [YOLOv8-Detection-Quantized.tflite](https://aihub.qualcomm.com/iot/models/yolov8_det_quantized)
- Label: [coco_labels.txt](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/labels/coco_labels.txt)

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/opt/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=5 output-io-mode=5 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer ! queue ! waylandsink fullscreen=true \
    split. ! queue ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp,htp_device_id=(string)0,htp_performance_mode=(string)2,htp_precision=(string)1;" model=/opt/YOLOv8-Detection-Quantized.tflite ! queue ! \
    qtimlvdetection threshold=50.0 results=10 module=yolov8 labels=/opt/coco_labels.txt constants="YOLOv8,q-offsets=<21.0, 0.0, 0.0>,q-scales=<3.093529462814331, 0.00390625, 1.0>;" ! \
    video/x-raw,format=BGRA,width=640,height=360 ! queue ! mixer.
    Copy to clipboard

Note

Adding `htp_device_id=(string)0,htp_performance_mode=(string)2,htp_precision=(string)1` to the `external-delegate-options` in the above command allows the model to be run in
High Performance mode on HTP.

High Performance mode can be enabled for all other pipelines in the same way.

## Yolo-nas-Quantized

- Model: [Yolo-NAS-Quantized.tflite](https://aihub.qualcomm.com/iot/models/yolonas_quantized)
- Label: [coco_labels.txt](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/labels/coco_labels.txt)

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/opt/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=5 output-io-mode=5 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer ! queue ! waylandsink fullscreen=true \
    split. ! queue ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/opt/Yolo-NAS-Quantized.tflite ! queue ! \
    qtimlvdetection threshold=50.0 results=10 module=yolov8 labels=/opt/coco_labels.txt constants="yolo-nas,q-offsets=<37.0,0.0, 0.0>,q-scales=<3.416602611541748, 0.00390625, 1.0>;" ! \
    video/x-raw,format=BGRA,width=640,height=360 ! queue ! mixer.
    Copy to clipboard

Last Published: Jan 21, 2026

[Previous Topic
WideResNet50-Quantized](https://docs.qualcomm.com/bundle/publicresource/80-70017-15B/topics/image-classification.md) [Next Topic
Semantic segmentation](https://docs.qualcomm.com/bundle/publicresource/80-70017-15B/topics/semantic-segmentation.md)