# Monodepth from video The **gst-ai-monodepth** application allows you to infer depth of a source feed from a live camera stream, file, or an RTSP stream. The following figure shows the pipeline, which captures feed from the source, preprocesses it, and runs inferences using the AI hardware. For information about the plugins used in the pipeline, see Pipeline flow. Qualcomm Open source File (default) Camera (optional) RTSP (optional) rtspsrc rtph264 depay h264parse V4l2h264dec Waylandsink sink_1 sink_0 qtimlvconverter qtimltflite/qtimlsnpe/ qtimlqnn qtimlpostprocess qtivtransform qtimlvconverter qtimltflite/qtimlsnpe/ qtimlqnn qtimlpostprocess qtivtransform sink_1 sink_1 sink_0 qtimlvconverter qtimltflite/qtimlsnpe/ qtimlqnn qtimlpostprocess qtivtransform qtiqmmfsrc sink_0 filesrc qtdemux h264parse V4l2h264dec **Figure : gst-ai-monodepth pipeline** ## Input and output capabilities The following table summarizes the input and output capabilities supported by the sample application: Table : Supported input and output formats | Config | Input | Input | Input | Input | Output | Output | Output | | --- | --- | --- | --- | --- | --- | --- | --- | | File src | RTSP | USB camera | MIPI camera | File | Display | RTSP | | Config #1 | Yes | Yes | No | No | No | Yes | No | | Config #2 | Yes | Yes | No | Yes | No | Yes | No | ## Sample model and label files Table : Sample model and label files for gst-ai-monodepth | Runtime | Model files | Label files | | --- | --- | --- | | Qualcomm Neural Processing SDK | *midasv2.dlc* | *monodepth.json* | | LiteRT | *midas\_quantized.tflite* | | Qualcomm AI Engine direct | *midas\_quantized.bin* | ## Run the application on the target device The sample application uses the `/etc/configs/config_monodepth.json` file to read the input parameters. To create your own config JSON file, use [config_monodepth.json](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/blob/imsdk.lnx.2.0.0.r2-rel/gst-sample-apps/gst-ai-monodepth/config_monodepth.json?ref_type=heads) as a reference. 1. Ensure that you complete the Prerequisites. 2. Update the config JSON file based on the model, input stream, and other properties. For more information, see Config JSON field description. 3. Use the following format of the `config_monodepth.json` file: { "file-path": "", "ml-framework": "", "model": "", "labels": "", "runtime": "" } Copy to clipboard An example format file for Config #2 and Config #1 is as follows: For example, run the application using the LiteRT model and DSP runtime, with input from a video file, and custom model and label paths: { "file-path": "/etc/media/video.mp4", "ml-framework": "tflite", "model": "/etc/models/midas_quantized.tflite", "labels": "/etc/labels/monodepth.json", "runtime": "dsp" } Copy to clipboard For example, run the application using the LiteRT model and CPU runtime, with input from a video file, and custom model and label paths: { "file-path": "/etc/media/video.mp4", "ml-framework": "tflite", "model": "/etc/models/midas_quantized.tflite", "labels": "/etc/labels/monodepth.json", "runtime": "cpu" } Copy to clipboard Note Config #1 supports only LiteRT models and the CPU runtime. 4. Run the gst-ai-monodepth application: gst-ai-monodepth --config-file=/etc/configs/config_monodepth.json Copy to clipboard 5. To display the available help options, run the following command in the SSH shell: gst-ai-monodepth -h Copy to clipboard 6. To stop the use case, use **CTRL + C**. ## Expected output The overlaid model output stream is shown side by side with the live feed. ![../../_images/gst-ai-monodepth-expected-output.png](data:image/png;base64,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) **Figure : Expected output for gst-ai-monodepth application** ## Pipeline flow The following table lists the plugins used in the mono depth pipeline: | Plugin | Description | | --- | --- | | Camera source: [qtiqmmfsrc](https://docs.qualcomm.com/doc/80-80022-50/topic/qtiqmmfsrc.html) |

  • Captures the live stream from camera.


  • Uses tee to split the stream for inferencing.


| | File source: filesrc |

  • Captures the video stream using filesrc, followed by qtdemux, which demultiplexes the stream.


  • Uses tee to split the stream for inferencing.


| | RTSP source: rtspsrc |

  • Captures the RTSP stream using rtspsrc, followed by rtph264depay for video extraction.


  • Uses tee to split the stream for inferencing.


| | h264parse | Parses the H.264 video. | | [v4l2h264dec](https://docs.qualcomm.com/doc/80-80022-50/topic/v4l2h264dec.html) | Decodes the video. | | [qtimlvconverter](https://docs.qualcomm.com/doc/80-80022-50/topic/qtimlvconverter.html) | Used by AI processing stream for preprocessing:

  1. Receives the video stream 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




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




The tensor stream is used for inferencing in the later stages of the pipeline. | | Inferencing plugins: [qtimlsnpe](https://docs.qualcomm.com/doc/80-80022-50/topic/qtimlsnpe.html), [qtimltflite](https://docs.qualcomm.com/doc/80-80022-50/topic/qtimltflite.html), and [qtimlqnn](https://docs.qualcomm.com/doc/80-80022-50/topic/qtimlqnn.html) | Uses the Midasv2 model for monodepth.

  1. The inference runtime receives the tensor stream on its sink pad.


  2. The runtime runs the inference.


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




The postprocessing plugin for processing the inference comes from the Midasv2 model. | | [qtimlpostprocess](https://docs.qualcomm.com/doc/80-80022-50/topic/qtimlpostprocess.html) | Converts the inference tensors that it receives on its sink pad into video formats that the multimedia plugins can use for further processing. | | [qtivtransform](https://docs.qualcomm.com/doc/80-80022-50/topic/qtivtransform.html) | Converts the buffers on its source pad. These buffers are for composition on Waylandsink. | | [waylandsink](https://docs.qualcomm.com/doc/80-80022-50/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.


| ## Config JSON field description The different parameters available to configure the JSON file and run the use case are as follows: Table : Field description–config_monodepth.json file | Field | Values/description | | --- | --- | | **ml-framework** | Enable and use one of the following models:

  • snpe: Qualcomm Neural Processing SDK.


  • tflite: LiteRT.


  • qnn: Qualcomm AI Engine direct.


| | **runtime** | Enable and use one of the following runtimes:

  • cpu


  • gpu


  • dsp


| | **Input source** | Enable and use one of the following input sources:

  • camera: Primary (0) or secondary (1).


  • file-path: The directory path to the video file.


  • rtsp-ip-port: The address of the RTSP stream: rtsp://<ip>:<port>/<stream>


| ## Related information Image segmentation Last Published: May 17, 2026 Previous Topic Daisy chain detection and pose estimation Next Topic Video super-resolution