# Four stream batching with LiteRT Source: [https://docs.qualcomm.com/doc/80-70023-50/topic/four-stream-batching-with-litert.html](https://docs.qualcomm.com/doc/80-70023-50/topic/four-stream-batching-with-litert.html) This command line shows a four stream batched AI inference, that is, object detection use case from a video file. Run the use case on the target device gst-launch-1.0 qtivcomposer sink_0::position="<0, 0>" sink_0::dimensions="<640, 360>" name=mixer \ sink_1::position="<640, 0>" sink_1::dimensions="<640, 360>" \ sink_2::position="<0, 360>" sink_2::dimensions="<640, 360>" \ sink_3::position="<640, 360>" sink_3::dimensions="<640, 360>" \ sink_4::position="<0, 0>" sink_4::dimensions="<640, 360>" sink_4::alpha=0.5 \ sink_5::position="<640, 0>" sink_5::dimensions="<640, 360>" sink_5::alpha=0.5 \ sink_6::position="<0, 360>" sink_6::dimensions="<640, 360>" sink_6::alpha=0.5 \ sink_7::position="<640, 360>" sink_7::dimensions="<640, 360>" sink_7::alpha=0.5 \ mixer. ! queue name=vcompsrcq ! fpsdisplaysink signal-fps-measurements=true text-overlay=true sync=false video-sink="waylandsink fullscreen=true sync=true" \ qtimltflite name=tflite_bs4_1 delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/opt/yolo_batch4.tflite \ qtibatch name=batch_1 ! queue name=batchsrcq ! qtimlvconverter ! tflite_bs4_1. tflite_bs4_1. ! qtimldemux name=mldemux_1 \ filesrc location=/etc/media/video.mp4 ! qtdemux ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! tee name=split_1 ! queue name=batch_sink1 ! batch_1. split_1. ! queue name=vcomp_sink1 ! mixer. \ filesrc location=/etc/media/video.mp4 ! qtdemux ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! tee name=split_2 ! queue name=batch_sink2 ! batch_1. split_2. ! queue name=vcomp_sink2 ! mixer. \ filesrc location=/etc/media/video.mp4 ! qtdemux ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! tee name=split_3 ! queue name=batch_sink3 ! batch_1. split_3. ! queue name=vcomp_sink3 ! mixer. \ filesrc location=/etc/media/video.mp4 ! qtdemux ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! tee name=split_4 ! queue name=batch_sink4 ! batch_1. split_4. ! queue name=vcomp_sink4 ! mixer. \ mldemux_1. ! queue name=dq_0 ! qtimlpostprocess settings="{\"confidence\": 75.0}" results=10 module=yolov8 labels=/etc/labels/yolov8.json ! video/x-raw,width=640,height=360 ! mixer. \ mldemux_1. ! queue name=dq_1 ! qtimlpostprocess settings="{\"confidence\": 75.0}" results=10 module=yolov8 labels=/etc/labels/yolov8.json ! video/x-raw,width=640,height=360 ! mixer. \ mldemux_1. ! queue name=dq_2 ! qtimlpostprocess settings="{\"confidence\": 75.0}" results=10 module=yolov8 labels=/etc/labels/yolov8.json ! video/x-raw,width=640,height=360 ! mixer. \ mldemux_1. ! queue name=dq_3 ! qtimlpostprocess settings="{\"confidence\": 75.0}" results=10 module=yolov8 labels=/etc/labels/yolov8.json ! video/x-raw,width=640,height=360 ! mixer.Copy to clipboard To stop the use case, use CTRL + C. The following figure shows the flow of the use case execution: 1. Identifies object scenes in the scene from a video stream, which is coming through a camera source. 2. Composes the following using qtivcomposer: 1. Bounding boxes over objects detected. 2. Original video stream. 3. Displays the results. Figure : Pipeline for four stream batching use case with LiteRT Qualcomm Open source qtivcomposer tee filesrc qtdemux h264parse V4l2h264dec tee filesrc qtdemux h264parse V4l2h264dec tee filesrc qtdemux h264parse V4l2h264dec tee filesrc qtdemux h264parse V4l2h264dec qtimlvconverter qtimltflite/qtimlsnpe/qtimlqnn qtibatch qtimldemux qtimlpostprocess Waylandsink The following table provides the sequential processing stages of the pipeline execution: | Plugin | Description | | --- | --- | | File source: filesrc | | | h264parse | Parses the H.264 video. | | [v4l2h264dec](https://docs.qualcomm.com/doc/80-70023-50/topic/v4l2h264dec.html) | Decodes the video. | | [qtibatch](https://docs.qualcomm.com/doc/80-70023-50/topic/qtibatch.html) | | | [qtimlvconverter](https://docs.qualcomm.com/doc/80-70023-50/topic/qtimlvconverter.html) |

  1. Receives the batched video streams on its sink pad.


  2. Performs the following preprocessing on the stream data. This
    preprocessing is done when the model expects floating-point
    values as input.

    1. Color conversion


    2. Scaling (up or down)


    3. Normalization








The tensor stream is used for inferencing in the later stages of the
pipeline. | | [qtimltflite](https://docs.qualcomm.com/doc/80-70023-50/topic/qtimltflite.html) |

  1. After the inference runtime receives the tensor stream on its
    sink pad, it runs the inference.


  2. Produces a tensor stream with the inference results on its
    source pad.


| | qtimldemux |

  1. Demultiplexes the batched output.


  2. Splits the output corresponding to the input streams.


| | Postprocessing plugins | qtimlpostprocess converts the inference tensors that are received on
the sink pad into video formats the multimedia plugins can use for
further processing. | | [qtivcomposer](https://docs.qualcomm.com/doc/80-70023-50/topic/qtivcomposer.html) |

  1. Composes frames with contents from its sink pads.


  2. Pushes the GStreamer buffers containing these composed frames to
    its source pad.


| | [Waylandsink](https://docs.qualcomm.com/doc/80-70023-50/topic/waylandsink.html) |

  1. Waylandsink submits the video stream received on its sink pad to
    Weston.


  2. Weston renders the video stream on a local display.


| **Parent Topic:** [LiteRT use cases](https://docs.qualcomm.com/doc/80-70023-50/topic/tensorflow-lite-use-cases.html) Last Published: Mar 27, 2026 [Previous Topic Single stream from camera to RTSP with ML detection](https://docs.qualcomm.com/bundle/publicresource/80-70023-50/topics/single-stream-from-camera-to-rtsp-with-ml-detection.md) [Next Topic Object detection using USB camera source](https://docs.qualcomm.com/bundle/publicresource/80-70023-50/topics/object-detection-using-usb-camera-source.md)