# Image segmentation and display with Neural Processing SDK Source: [https://docs.qualcomm.com/doc/80-70015-50/topic/single-camera-stream-with-image-segmentation-and-display-with-deeplabv3-quantized.html](https://docs.qualcomm.com/doc/80-70015-50/topic/single-camera-stream-with-image-segmentation-and-display-with-deeplabv3-quantized.html) The use case uses the DeepLab v3 model with the Qualcomm Neural Processing SDK runtime to identify the semantic segmentations in a scene from a camera stream, compose the semantics and the video stream together using qtivcomposer, and then display the results. ## Use qtivcomposer to mix original frame with segmentation mask Run the use case: gst-launch-1.0 -e --gst-debug=2 \ qtiqmmfsrc name=camsrc ! video/x-raw\(memory:GBM\),format=NV12,width=1920,height=1080,framerate=30/1,compression=ubwc ! queue ! tee name=split \ split. ! queue ! qtivcomposer name=mixer sink_1::dimensions="<1920,1080>" sink_1::alpha=0.5 ! queue ! waylandsink fullscreen=true \ split. ! queue ! qtimlvconverter ! queue ! qtimlsnpe delegate=dsp model=/opt/deeplabv3_resnet50.dlc ! queue ! qtimlvsegmentation module=deeplab-argmax labels=/opt/deeplabv3_resnet50.labels ! video/x-raw,width=640,height=360 ! queue ! mixer. Copy to clipboard To stop the use case, press CTRL + C. Figure : Pipeline for segmentation with qtivcomposer  The figure shows the flow of the use case execution: 1. Identify scenes from a video stream coming through a camera source. 2. Compose semantic segmentation and video stream using qtivcomposer. 3. Display the results. The table provides the sequential processing stages of the pipeline execution: | Process | Description | | --- | --- | | [qtiqmmfsrc](https://docs.qualcomm.com/doc/80-70015-50/topic/qtiqmmfsrc.html) |
The segmentation model uses this tensor stream
for inferencing.
In this use case, qtimlvsegmentation does the
following: