# Image classification and encode with LiteRT Source: [https://docs.qualcomm.com/doc/80-70020-50/topic/single-camera-stream-with-image-classification-and-encode.html](https://docs.qualcomm.com/doc/80-70020-50/topic/single-camera-stream-with-image-classification-and-encode.html) The use cases use the InceptionV3 LiteRT model to classify scenes from a single camera stream and either overlay or compose the classification labels, and then encode the stream. Note: For Ubuntu Server, `sudo` access is necessary to write the encoded stream to the `/etc/media` folder. ## Use qtivoverlay plugin to apply classification overlay Run the use case on the target device: gst-launch-1.0 -e qtiqmmfsrc name=camsrc ! video/x-raw,format=NV12_Q08C,width=1280,height=720,framerate=30/1 ! queue ! tee name=split split. ! \ queue ! qtimetamux name=metamux ! queue ! qtivoverlay ! queue ! v4l2h264enc capture-io-mode=4 output-io-mode=5 ! \ h264parse ! queue ! mp4mux ! queue ! filesink location=/etc/media/video.mp4 split. ! queue ! qtimlvconverter ! queue ! \ qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp;" \ model=/etc/models/inception_v3_quantized.tflite ! queue ! qtimlvclassification threshold=40.0 results=2 module=mobilenet \ labels=/etc/labels/classification.labels constants="Inceptionv3,q-offsets=<38.0>,q-scales=<0.17039915919303894>;" ! text/x-raw ! queue ! metamux.Copy to clipboard To stop the use case, use CTRL + C. The following figure shows the flow of the use case execution: 1. Identify the stream coming through a camera source. 2. Overlay the classification labels using overlaylib. 3. Encode the stream as a H.264 bitstream. 4. Multiplex the stream in an MP4 container and stored as an MP4 file. Figure : Pipeline for classification overlay and encode The following table provides the sequential processing stages of the pipeline execution: | Process | Description | | --- | --- | | [qtiqmmfsrc](https://docs.qualcomm.com/doc/80-70020-50/topic/qtiqmmfsrc.html) |

  1. The video stream is collected from a camera source plugin
    and two copies are created:


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

  1. Receives the video stream on its sink pad.


  2. Performs preprocessing:


  3. Converts the video stream to a tensor stream on its source
    pad.

    The classification model uses this tensor stream
    for inferencing.




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

  1. Loads the classification model.


  2. Modifies the graph for the chosen delegate.


  3. Receives the tensor stream on its sinkpad.


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


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

  1. Receives the inference tensors from a classification model
    on its sinkpad.


  2. Converts the tensors into formats such as video or text that
    the multimedia plugins can process later.


  3. Applies the threshold to the chosen number of results.


  4. Loads the corresponding modules of the classification
    models.

    In this use case, qtimlvclassification does the
    following:


    1. Loads the InceptionV3 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) |

  1. Receives the video stream and text stream with
    classification results corresponding to video stream on its
    sinkpads.


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


  3. Adds classification result from data sinkpad to GST buffer
    meta (meta muxing) on its source pad.


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

  1. Receives the multiplexed stream.


  2. Overlays the classification labels on the VideoFrame using
    CL.


  3. Produces GST buffers with overlays in its source pad.


| | [v4l2h264enc](https://docs.qualcomm.com/doc/80-70020-50/topic/v4l2h264enc.html) |

  1. Applies parameters to each frame of the video stream it's
    receiving on its sinkpad.


  2. Encodes it into bitstream and sends it over its
    sourcepad.


| | h264parse | Adds more information about the bitstream to the GStreamer buffer
meta. | | mp4mux | Receives these buffers and creates containers with format
specification buffers. | | **Output** | **Output** | | Filesink | Stores the resulting stream in a
/opt/video.mp4 file. | | Playback | Pull video.mp4 from the host computer and
play it on a media player:
`scp root@ target device>:/opt/ directory>` | ## Use qtivcomposer to mix original frame with classification mask Run the use case on the target device: gst-launch-1.0 -e --gst-debug=2 qtiqmmfsrc name=camsrc ! video/x-raw,format=NV12_Q08C,width=1280,height=720,framerate=30/1 ! queue ! tee name=split split. ! \ queue ! qtivcomposer name=mixer sink_1::position="<30, 30>" sink_1::dimensions="<320, 180>" ! queue ! video/x-raw,format=NV12,width=1920,height=1080,interlace-mode=progressive,colorimetry=bt601 ! \ v4l2h264enc capture-io-mode=4 output-io-mode=5 ! h264parse ! queue ! mp4mux ! queue ! filesink location=/etc/media/video.mp4 split. ! queue ! qtimlvconverter ! queue ! \ qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp;" \ model=/etc/models/inception_v3_quantized.tflite ! queue ! qtimlvclassification threshold=40.0 results=2 module=mobilenet \ labels=/etc/labels/classification.labels constants="Inceptionv3,q-offsets=<38.0>,q-scales=<0.17039915919303894>;" ! video/x-raw,format=BGRA,width=640,height=360 ! queue ! mixer.Copy to clipboard To stop the use case, use CTRL + C. The following figure shows the flow of the use case execution: 1. Identify the stream coming through a camera source. 2. Compose the classification labels and video stream using qtivcomposer. 3. Encode the stream as an H.264 bitstream. 4. Multiplex the stream in an MP4 container and store it as an MP4 file. Figure : Pipeline for classification and encode with qtivcomposer The following table provides the sequential processing stages of the pipeline execution: | Process | Description | | --- | --- | | [qtiqmmfsrc](https://docs.qualcomm.com/doc/80-70020-50/topic/qtiqmmfsrc.html) |

  1. Collects the video stream (source) from a camera 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.





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

  1. Receives the video stream on its sink pad.


  2. Performs preprocessing:

    • Color conversion


    • Scaling down/up


    • Normalization on the stream data when the model
      expects the floating point values as an input





  3. Converts the video stream to a tensor stream on its source
    pad.

    The classification model uses the tensor stream
    for inferencing.




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

  1. Loads the classification model.


  2. Modifies the graph for the chosen delegate.


  3. Receives the tensor stream on its sinkpad.


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


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

  1. Receives the inference tensors from a classification model
    on its sinkpad.


  2. Converts the tensors into formats such as video or text that
    the multimedia plugins can process later.


  3. Applies the threshold to the chosen number of results.


  4. Loads the corresponding modules of the classification
    models.

    In this use case, qtimlvclassification does the
    following:


    1. Loads InceptionV3 submodule.


    2. Produces results as video frames with classification
      labels.


    3. Sends them to the sinkpad of qtivcomposer.





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

  1. Receives the original video stream with classification
    results on its sinkpads.


  2. On its sourcepad, produces GST buffers with contents
    composed of video streams from its sinkpads.


| | [v4l2h264enc](https://docs.qualcomm.com/doc/80-70020-50/topic/v4l2h264enc.html) |

  1. Applies parameters to each frame of the video stream it's
    receiving on its sinkpad.


  2. Encodes it into bitstream and sends it over its
    sourcepad.


| | h264parse | Adds more information about the bitstream to the GStreamer buffer
meta. | | mp4mux | Receives these buffers and creates containers with format
specification buffers. | | **Output** | **Output** | | Filesink | Stores the resulting stream in a
/etc/media/video.mp4 file. | | Playback | Pull video.mp4 from the host computer and
play it on a media player:
`scp root@ target device>:/etc/ directory>` | **Parent Topic:** [LiteRT use cases](https://docs.qualcomm.com/doc/80-70020-50/topic/tensorflow-lite-use-cases.html) Last Published: Jan 30, 2026 [Previous Topic Image classification and display with LiteRT](https://docs.qualcomm.com/bundle/publicresource/80-70020-50/topics/single-camera-stream-with-image-classification-and-display-with-litert.md) [Next Topic Audio classification decode and display with LiteRT](https://docs.qualcomm.com/bundle/publicresource/80-70020-50/topics/audio-classification-with-litert.md)