# Image classification The **gst-ai-classification** application allows you to identify the subject in an image. The use cases are implemented using the Qualcomm Neural Processing SDK, LiteRT, or Qualcomm AI Engine direct models. The following figure shows the pipeline, which receives a video stream from a camera, file source, USB source, or Real-Time Streaming Protocol (RTSP), preprocesses it, and runs the inference on AI hardware. The results are either displayed on the screen, saved as an encoded MP4 file, or streamed over the RTSP server. For information about the plugins used for classification, see [Pipeline flow](https://docs.qualcomm.com/doc/80-80021-50/topic/gst-ai-classification.html#section-j5t-2jq-nbc). Qualcomm Open source File (default) Camera (optional) tee qtdemux h264parse V4l2h264dec qtimlvconverter qtimltflite/qtimlsnpe/ qtimlqnn qtimlpostprocess sink_1 sink_0 filesrc qtimlvconverter qtimltflite/qtimlsnpe/ qtimlqnn qtimlpostprocess sink_1 sink_0 qtiqmmfsrc RTSP (optional) sink_0 rtph264 depay h264parse V4l2h264dec tee qtimlvconverter qtimltflite/qtimlsnpe/ qtimlqnn qtimlpostprocess sink_1 rtspsrc USB camera (Optional) tee qtimlvconverter qtimltflite/qtimlsnpe/ qtimlqnn qtimlpostprocess sink_1 sink_0 v4l2src_caps v4l2src qtivcomposer or or Waylandsink qtirtspbin filesink **Figure : gst-ai-classification pipeline** ## Input and output capabilities The following table summarizes the input and output capabilities supported by the sample application: | Config | Input | Input | Input | Input | Output | Output | Output | | --- | --- | --- | --- | --- | --- | --- | --- | | Config | File src | RTSP | USB camera | MIPI camera | File | Display | RTSP | | Config #1 | Yes | Yes | No | No | Yes | Yes | Yes | | Config #2 | Yes | Yes | No | Yes | Yes | Yes | Yes | | | | | | | | | | ## Sample model and label files | Runtime | Model files | Label files | | --- | --- | --- | | Qualcomm Neural Processing SDK | *inceptionv3.dlc* | *classification.json* | | LiteRT | *inception\_v3\_quantized.tflite* | *classification.json* | | Qualcomm AI Engine direct | *inception\_v3\_quantized.bin* | *classification.json* | | | | | | | | | ## Run the application on the target device The sample application uses the `/etc/configs/config_classification.json` file to read the input parameters. To create your own config JSON file, use [config_classification.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-classification/config_classification.json?ref_type=heads) as a reference. 1. Ensure that you complete the [Prerequisites](https://docs.qualcomm.com/doc/80-80021-50/topic/download-model-and-label-files.html). 2. Update the config JSON file based on the model, input stream, and other properties. For more information, see [Config JSON field description](https://docs.qualcomm.com/doc/80-80021-50/topic/gst-ai-classification.html#section-lcw-2zj-32c). 3. Use the following format of the `config_classification.json` file. { "file-path": "", "ml-framework": "", "model": "", "labels": "", "threshold": , "runtime": "", "output-type": "waylandsink or filesink or rtspsink" } Copy to clipboard > > > An example format file for Config #2 and Config #1 is as follows: > > > > > > > > > Tab Config #2 > > Tab Config #1 > > > > For example, run the application using input from a file, LiteRT model, DSP runtime, and custom threshold value on Config #2: > > > > > > { > > "file-path": "/etc/media/video.mp4", > > "ml-framework": "tflite", > > "model": "/etc/models/inception_v3_quantized.tflite", > > "labels": "/etc/labels/classification.json", > > "threshold": 40, > > "runtime": "dsp", > > "output-type": "waylandsink" > > } > > Copy to clipboard > > > > For example, run the application using input from a file, LiteRT model, CPU runtime, and custom threshold value on Config #1: > > > > > > { > > "file-path": "/etc/media/video.mp4", > > "ml-framework": "tflite", > > "model": "/etc/models/inception_v3_quantized.tflite", > > "labels": "/etc/labels/classification.json", > > "threshold": 40, > > "runtime": "cpu", > > "output-type": "waylandsink" > > } > > Copy to clipboard > > > > > > Note > > > > > > ConfigĀ #1 supports only LiteRT models and the CPU runtime. 4. Run the gst-ai-classification application: gst-ai-classification --config-file=/etc/configs/config_classification.json Copy to clipboard Note For USB camera input, set the `video-format`, `resolution`, and `framerate` parameters in the configuration file to match the capabilities of the camera. To check the camera capabilities, see [Configure USB camera](https://docs.qualcomm.com/bundle/publicresource/topics/80-80021-8/usb.html#configure-usb-camera). 5. To display the available help options, run the following command in the SSH shell: gst-ai-classification -h Copy to clipboard 6. To stop the use case, use **CTRL + C**. ## Expected output The classified object is displayed on the local display. ![../../_images/classification-output.png](data:image/png;base64,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) **Figure : Expected output for gst-ai-classification application** ## Pipeline flow | Plugin | Description | | --- | --- | | Camera source:[qtiqmmfsrc](https://docs.qualcomm.com/doc/80-80021-50/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.


| | USB camera source: v4l2src |

  • Captures the live stream from USB camera.


  • Uses tee to split the stream for inferencing.


| | h264parse | Parses the H.264 video. | | [v4l2h264dec](https://docs.qualcomm.com/doc/80-80021-50/topic/v4l2h264dec.html) | Decodes the video. | | [qtimlvconverter](https://docs.qualcomm.com/doc/80-80021-50/topic/qtimlvconverter.html) |

  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



  1. 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:
|

  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.


| | [qtimlpostprocess](https://docs.qualcomm.com/doc/80-80021-50/topic/qtimlpostprocess.html) | Handles inference results from any classification model.
1. Applies a threshold to the chosen number of results.
2. Loads the MobileNet-softmax postprocessing module.
3. Produces results as video frames with classification labels.
4. Sends these processed results to the sink pad of qtivcomposer. | | [qtivcomposer](https://docs.qualcomm.com/doc/80-80021-50/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/80-80021-50/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.


| | filesink | Takes the video stream that it receives on its sink pad and saves it as an H.264-encoded MP4 file. | | qtirtspbin |

  1. Serves as a network sink.


  2. Transmits UDP packets to the network.


| The following table lists the plugins used in the object classification pipeline: ## Config JSON field description The different parameters available to configure the JSON file and run the use case are as follows: | Field | Values/description | | --- | --- | | **ml-framework** | Use one of the following models:

  • snpe: Qualcomm Neural Processing SDK


  • tflite: LiteRT


  • qnn: Qualcomm AI Engine direct


| | **runtime** | Use one of the following runtimes:

  • cpu


  • gpu


  • dsp


| | **output-ip-address** | Output server IP address. | | **port** | Output server port. | | **USB camera video-format and resolution** | Use one of the following video-formats:

  • nv12


  • yuy2


  • mjpeg




Use the following resolution parameters:

  • width: Input USB camera source resolution width.


  • height: Input USB camera source resolution height.


  • framerate: Input USB camera source framerate.


| | **output-file** | Name of the output file. The default output file is `output_classification.mp4`. | | **output-type** | Use one of the following output-type:

  • waylandsink: To display output on Wayland.


  • filesink: To store output in file.


  • rtspsink: To stream output on server.


| | **Input source** | 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://:/.


  • usb-camera: Set enable-usb-camera as TRUE to use USB camera as input source.


| ## Known issues Tab Config #2 Tab Config #1 - Lag is observed in image classification with camera source and file source as quantized models aren't supported in the TFlite IM SDK framework. - The application may intermittently hang during the `gst_deinit` phase. - The GPU delegate doesn't function in the QNN and TFLite IM SDK frameworks. USB camera input isn't supported. ## Related information - [Image classification and display with LiteRT](https://docs.qualcomm.com/doc/80-80021-50/topic/single-camera-stream-with-image-classification-and-display-with-litert.html) - [Image classification and encode with LiteRT](https://docs.qualcomm.com/doc/80-80021-50/topic/single-camera-stream-with-image-classification-and-encode.html) - [Image classification and display with Neural Processing SDK](https://docs.qualcomm.com/doc/80-80021-50/topic/single-camera-stream-with-image-classification-and-display-with-mobilenet-v1.html) - [Image classification and encode with Neural Processing SDK](https://docs.qualcomm.com/doc/80-80021-50/topic/single-camera-stream-with-image-classification-and-encode-with-mobilenet-v1.html) Last Published: Mar 26, 2026 [Previous Topic Prerequisites](https://docs.qualcomm.com/bundle/publicresource/80-80021-50/topics/download-model-and-label-files.md) [Next Topic Object detection](https://docs.qualcomm.com/bundle/publicresource/80-80021-50/topics/gst-ai-object-detection.md) Source: [https://docs.qualcomm.com/doc/80-80021-50/topic/gst-ai-classification.html](https://docs.qualcomm.com/doc/80-80021-50/topic/gst-ai-classification.html)