AI - Qualcomm Intelligent Multimedia SDK

This section covers Python-based AI sample applications that demonstrate vision and multi-model inference on Qualcomm platforms. The following tables list all available Python AI applications and their platform support. Select the appropriate configuration tab for your setup.

Config #1
Config #2

None of the Python AI applications are supported in Config #1 of the QLI 2.1 GA release. Select the Config #2 tab.

Application	Source code	Description	Input sources	Runtime	QCS6490 / IQ-8275 / IQ-9075	IQ-X7181/IQ-X5121	IQ-615 / IQ-2390
Object detection and display	`gst-ai-object-detection.py`	Object detection with bounding box overlay on the display.	Camera, file	dsp	✓	✓	×
Decode and object detection using RTSP stream	`gst-rtspsrc-detection-display.py`	Object detection on a decoded RTSP stream.	RTSP	dsp	✓	✓	×
Object detection and classification	`gst-camera-two-stream-detection-and-classification-side-by-side.py`	Detection and classification displayed side by side.	Camera	dsp	✓	✓	×
Object detection, classification, and segmentation	`gst-filesrc-2detection-classification-segmentation-side-by-side.py`	Detection, classification, and segmentation displayed side by side.	File	dsp	✓	✓	×
Camera encode, object detection, and display	`gst-camera-two-stream-encode-file-detection-display.py`	Encodes the camera stream to a file while running object detection.	Camera	dsp	✓	✓	×
Parallel inference using Python	`gst-parallel-inference.py`	Four-channel parallel inference: classification, detection, pose, and segmentation.	Camera, file, RTSP	dsp	✓	✓	×
Daisy chain detection and pose detection using Python	`gst-daisychain-detection-pose.py`	Cascaded object detection and pose detection.	Camera, file, RTSP	dsp	✓	✓	×

Prerequisites

Try me

Some of the steps in the pre-requisties will be removed from future releases once the necessary fixes are mainlined.

Set up Wi-Fi

Connect to the Wireless Access Point (Wi-Fi Router):

nmcli dev wifi connect <WiFi-SSID> password <WiFi-password>

Check the connection and device status:

nmcli -p device

Login to the target deviceLocate the IP address of the device according to the type of network connection, using the device shell on the Linux host:

ip address show

Use the IP address from the Linux host to establish an SSH connection to the device:

ssh root@<ip-address>

Example:

ssh root@192.168.0.222

Connect to the SSH shell using the following password:

oelinux123

Download Models and Artifacts

On the target device, obtain the download_artifacts.sh script, set executable permissions, and run it to download the model, media, and label files:

cd /tmp/
curl -L -O https://raw.githubusercontent.com/qualcomm/sample-apps-for-qualcomm-linux/refs/heads/main/qualcomm-linux/scripts/download_artifacts_2.x.sh    
chmod +x download_artifacts_2.x.sh
./download_artifacts_2.x.sh

On Qualcomm Ubuntu, run the above command with sudo.

Enable qticamsrc

In the terminal of the target device, run the following command to enable the qticamsrc on Config #2:

echo -n "camx" > /var/data
efivar -n 882f8c2b-9646-435f-8de5-f208ff80c1bd-VendorDtbOverlays -w -f /var/data
efivar -n 882f8c2b-9646-435f-8de5-f208ff80c1bd-VendorDtbOverlays -p
sync
reboot

Enable Audio and GPU Delegate

In the terminal of the target device, run the following command to enable audio:

systemctl stop pipewire wireplumber pipewire.socket pipewire-manager.socket
chmod 777 /dev/dma_heap/system
adsprpcd audiopd &
systemctl start pipewire wireplumber
wpctl status

To set the default devices for sink and source, get the device numbers from wpctl status and run the following command:

wpctl set-default <device ID>

In the terminal of the target device, run the following command to enable the GPU delegate and backend:

mount -o rw,remount /usr

export OCL_ICD_FILENAMES=/usr/lib/libOpenCL_adreno.so.1

AI Vision Applications

Object Detection and Display

The gst-ai-object-detection.py script receives an RTSP stream as a source, decodes it, uses YOLOv8 LiteRT model to identify the object in a scene from the camera stream and overlay the bounding boxes over the detected objects. The results are shown on the display. For information about the plugins used in this pipeline, see Pipeline flow.

This application isn’t supported in Config #1 of Qualcomm Linux because CPU runtime is not supported.

Application: gst-ai-object-detection.py

Try me

Sample Model and Label Files

Runtime	Model file	Label file
LiteRT	`yolov8_det_w8a8.tflite`, `yolox_quantized.tflite`	`yolov8.json`, `yolox.json`
Qualcomm Neural Processing SDK	`yolonas.dlc`	`yolonas.json`

Run the application on the target device

Download artifacts

Ensure that you complete the Prerequisites. This downloads all required artifacts to the target device.

Run the application

Run any of the following use cases:

Display with the primary and secondary cameras respectively:

gst-ai-object-detection.py -c 0 -f 2 -m ${HOME}/Downloads/qimsdk_samples/models/yolox_quantized.tflite -l ${HOME}/Downloads/qimsdk_samples/labels/yolox.json -ml "yolov8"

gst-ai-object-detection.py -c 1 -f 2 -m ${HOME}/Downloads/qimsdk_samples/models/yolox_quantized.tflite -l ${HOME}/Downloads/qimsdk_samples/labels/yolox.json -ml "yolov8"

Display with input from a video file:

gst-ai-object-detection.py -s ${HOME}/Downloads/qimsdk_samples/media/video.mp4 -f 2 -m ${HOME}/Downloads/qimsdk_samples/models/yolox_quantized.tflite -l ${HOME}/Downloads/qimsdk_samples/labels/yolox.json -ml "yolov8"

YOLOv8 with LiteRT:

gst-ai-object-detection.py -f 2 -m ${HOME}/Downloads/qimsdk_samples/models/yolov8_det_w8a8.tflite -l ${HOME}/Downloads/qimsdk_samples/labels/yolov8.json -ml "yolov8"

Both yolox_quantized.tflite and yolov8_det_w8a8.tflite model files use the Yolov8 module.

To display all available options:

gst-ai-object-detection.py -h

To stop the use case, press CTRL + C.

Expected Output

Detected objects with bounding boxes and labels are overlaid on the video and displayed on the local display.

Pipeline Flow

The following table lists the plugins used in the object detection pipeline:

Process	Description
`qticamsrc`	1. Collects the video stream (source) 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.
`filesrc`	Reads the video data.
`qtimlvconverter`	1. Receives the video stream on its sinkpad. 2. Performs preprocessing: color conversion, scaling, normalization. 3. Converts the video stream to a tensor stream on its source pad.
`qtimltflite`	Loads the object detection model, runs inference, and produces a tensor stream with detection results.
`qtimlpostprocess`	Converts inference tensors into bounding boxes and labels. Loads the YOLOv8 submodule and sends results to `qtimetamux`.
`qtimetamux`	Synchronizes video and bounding box metadata streams. Attaches bounding boxes as `GstVideoRegionOfInterest` metadata.
`qtivoverlay`	Overlays bounding boxes on the video frame using CL.
`waylandsink`	Renders the video stream on a local display via Weston.
`filesink`	Writes the video to a file.

Decode and Object Detection Using RTSP Stream

The gst-rtspsrc-detection-display.py script receives an RTSP stream as a source, decodes it, uses YOLOv8 LiteRT model to identify the object in a scene from the camera stream and overlay the bounding boxes over the detected objects. The results are shown on the display. For information about the plugins used in this pipeline, see Pipeline flow.

This application isn’t supported in Config #1 of Qualcomm Linux because CPU runtime is not supported.

Application: gst-rtspsrc-detection-display.py

Try me

Sample Model and Label Files

Runtime	Model file	Label file
LiteRT	`yolox_quantized.tflite`	`yolox.json`

Run the application on the target device

Download artifacts

Ensure that you complete the Prerequisites. This downloads all required artifacts to the target device.

Run the application

Run the object detection script on the target device:Console 1 — start the RTSP server:

gst-launch-1.0 -e qticamsrc camera=0 ! v4l2h264enc capture-io-mode=4 output-io-mode=5 ! h264parse config-interval=1 ! qtirtspbin

Console 2 — run the detection script:

gst-rtspsrc-detection-display.py

To display all available options:

gst-rtspsrc-detection-display.py -h

The default paths for model and label files are provided in the help section.

To stop the use case, press CTRL + C.

Expected Output

Pipeline Flow

The following table lists the plugins used in the rtsp detection pipeline:

Process	Description
`rtspsrc`	Receives the RTSP stream from `rtsp://<ip>:<port>/live`.
`rtph264depay`	Extracts the video data from the RTSP stream.
`h264parse`	Parses the H.264 video.
`v4l2h264dec`	Decodes the video.
`qtimlvconverter`	Preprocesses frames (color conversion, scaling, normalization) and converts to tensor stream.
`qtimltflite`	Runs object detection inference.
`qtimlpostprocess`	Converts inference tensors into bounding boxes and labels.
`qtimetamux`	Synchronizes video and metadata streams.
`qtivoverlay`	Overlays bounding boxes on the video frame.
`waylandsink`	Renders the video stream on a local display.

Object Detection and Classification

The gst-camera-two-stream-detection-and-classification-side-by-side.py application uses a YOLOX LiteRT model to detect and inception_v3 to classify objects in the scene displayed by the AI overlay composer. For information about the plugins used in this pipeline, see Pipeline flow.

This application isn’t supported in Config #1 of Qualcomm Linux because CPU runtime is not supported.

Application: gst-camera-two-stream-detection-and-classification-side-by-side.py

Try me

Sample Model and Label Files

Runtime	Model file	Label file
LiteRT	detection: `yolox_quantized.tflite` classification: `inception_v3_quantized.tflite`	detection: `yolox.json` classification: `classification.json`

Run the application on the target device

Download artifacts

Ensure that you complete the Prerequisites. This downloads all required artifacts to the target device.

Run the application

gst-camera-two-stream-detection-and-classification-side-by-side.py

To display all available options:

gst-camera-two-stream-detection-and-classification-side-by-side.py -h

The default paths for model and label files are provided in the help section.

To stop the use case, press CTRL + C.

Expected Output

Detection and classification display are shown side-by-side.

Pipeline Flow

The following table lists the plugins used in the detection and classification pipeline:

Process	Description
`qticamsrc`	Collects two video streams — one for detection, one for classification — each split via `tee`.
`qtimlvconverter`	Preprocesses frames for each branch (color conversion, scaling, normalization).
`qtimltflite`	Runs detection (YOLOX) and classification (InceptionV3) inference sequentially.
`qtimlpostprocess` (detection)	Converts detection tensors to bounding boxes and labels.
`qtimlpostprocess` (classification)	Converts classification tensors to label overlay frames.
`qtimetamux`	Synchronizes video and metadata for the detection branch.
`qtivoverlay`	Overlays bounding boxes on the detection stream.
`qtivcomposer`	Composes the detection and classification streams side by side.
`waylandsink`	Renders the composed output on a local display.

Known Issues

Config #2

Output labels are blurred.

Object Detection, Classification, and Segmentation

The gst-filesrc-2detection-classification-segmentation-side-by-side.py script identifies objects, classifies scenes, and produces semantic segmentation from a video file. The output is displayed side by side. For information about the plugins used in this pipeline, see Pipeline flow.

This application isn’t supported in Config #1 of Qualcomm Linux because CPU runtime is not supported.

Application: gst-filesrc-2detection-classification-segmentation-side-by-side.py

Try me

Sample Model and Label Files

Runtime	Model file	Label file
LiteRT	detection: `yolox_quantized.tflite` classification: `inception_v3_quantized.tflite` segmentation: `deeplabv3_plus_mobilenet_quantized.tflite`	detection: `yolox.json` classification: `classification.json` segmentation: `deeplabv3_resnet50.json`

Run the application on the target device

Download artifacts

Ensure that you complete the Prerequisites. This downloads all required artifacts to the target device.

Run the application

gst-filesrc-2detection-classification-segmentation-side-by-side.py

The default input video for classification, segmentation, and detection is at $/Downloads/qimsdk_samples/media/video.mp4`.

To display all available options:

gst-filesrc-2detection-classification-segmentation-side-by-side.py -h

The default paths for model and label files are provided in the help section.

To stop the use case, press CTRL + C.

Expected Output

The four streams are previewed side by side on a local display.

Pipeline Flow

The following table lists the plugins used in the detection, classification and segmentation pipeline:

Process	Description
`filesrc`	Reads the video data from a file.
`qtdemux`	Demultiplexes the video data.
`h264parse`	Parses H.264 video.
`v4l2h264dec`	Decodes the H.264 video.
`qtimlvconverter`	Preprocesses frames for each inference branch.
`qtimltflite`	Runs detection, classification, and segmentation inference.
`qtimlpostprocess` (detection)	Produces bounding boxes and labels.
`qtimlpostprocess` (classification)	Produces classification label frames.
`qtimlpostprocess` (segmentation)	Produces segmentation mask frames via `deeplab-argmax`.
`qtimetamux`	Synchronizes video and metadata for the detection branch.
`qtivoverlay`	Overlays bounding boxes on the detection stream.
`qtivcomposer`	Composes all four streams side by side.
`waylandsink`	Renders the composed output on a local display.

Camera Encode, Object Detection, and Display

The gst-camera-two-stream-encode-file-detection-display.py application encodes the camera stream to a file while simultaneously running YOLOX object detection and displaying results. For information about the plugins used in this pipeline, see Pipeline flow.

This application isn’t supported in Config #1 of Qualcomm Linux because CPU runtime is not supported.

Application: gst-camera-two-stream-encode-file-detection-display.py

Try me

Sample Model and Label Files

Runtime	Model file	Label file
LiteRT	`yolox_quantized.tflite`	`yolox.json`

Run the application on the target device

Download artifacts

Ensure that you complete the Prerequisites. This downloads all required artifacts to the target device.

Run the application

gst-camera-two-stream-encode-file-detection-display.py

To display all available options:

gst-camera-two-stream-encode-file-detection-display.py -h

The default paths for model and label files are provided in the help section.

To stop the use case, press CTRL + C.

Expected Output

The camera encode output is saved at ${HOME}/Downloads/qimsdk_samples/media/test.mp4.The object detection output is rendered on the display.

Pipeline Flow

The following table lists the plugins used in the camera encode detection pipeline:

Process	Description
`qticamsrc`	Collects two streams — one for detection, one for encoding.
`v4l2h264enc`	Encodes H.264 video.
`h264parse`	Parses H.264 video.
`mp4mux`	Multiplexes video into MP4.
`qtimlvconverter`	Preprocesses frames for detection inference.
`qtimltflite`	Runs YOLOX object detection inference.
`qtimlpostprocess`	Produces bounding boxes and labels.
`qtimetamux`	Synchronizes video and metadata.
`qtivoverlay`	Overlays bounding boxes on the video frame.
`filesink`	Saves the encoded video to a file.
`waylandsink`	Renders the detection output on a local display.

Parallel Inference Using Python

The gst-parallel-inference.py application receives a video input from a camera, file, or RTSP stream and runs four-channel parallel AI inference (classification, object detection, pose detection, and segmentation). For information about the plugins used in this pipeline, see Pipeline flow.

This application isn’t supported in Config #1 of Qualcomm Linux because CPU runtime is not supported.

Application: gst-parallel-inference.py

Try me

Sample Model and Label Files

Runtime	Model file	Label file
LiteRT	detection: `yolox_quantized.tflite` classification: `inception_v3_quantized.tflite` segmentation: `deeplabv3_plus_mobilenet_quantized.tflite` pose: `hrnet_pose_quantized.tflite`	detection: `yolox.json` classification: `classification.json` segmentation: `deeplabv3_resnet50.json` pose: `hrnet_pose.json`, `hrnet_settings.json`

Run the application on the target device

Download artifacts

Ensure that you complete the Prerequisites. This downloads all required artifacts to the target device.

Run the application

Input from the camera:

gst-parallel-inference.py --camera

Input from a file:

gst-parallel-inference.py --file "${HOME}/Downloads/qimsdk_samples/media/video.mp4"

Input from an RTSP stream:

gst-parallel-inference.py --rtsp "rtsp://<ip>:<port>/<stream>"

To display all available options:

gst-parallel-inference.py -h

The default paths for model and label files are provided in the help section.

To stop the use case, press CTRL + C.

Expected Output

The four inference results are displayed side by side on the screen.

Pipeline Flow

The following table lists the plugins used in the parallel inference pipeline:

Process	Description
`qticamsrc` / `filesrc` / `rtspsrc`	Captures stream from camera, file, or RTSP.
`v4l2h264dec`	Decodes H.264 video.
`qtimlvconverter`	Preprocesses frames for each of the four inference branches.
`qtimltflite`	Runs detection, classification, segmentation, and pose inference in parallel.
`qtimlpostprocess` (detection)	Produces bounding boxes and labels.
`qtimlpostprocess` (classification)	Produces classification label frames.
`qtimlpostprocess` (segmentation)	Produces segmentation mask frames.
`qtimlpostprocess` (pose)	Produces pose key point frames via HRNet module.
`qtimetamux`	Synchronizes video and metadata for the detection branch.
`qtivoverlay`	Overlays bounding boxes on the detection stream.
`qtivcomposer`	Composes all four output streams side by side.
`waylandsink`	Renders the composed output on a local display.

Daisy Chain Detection and Pose Detection Using Python

The gst-ai-daisychain-detection-pose.py application performs cascaded object detection and pose detection with input from a camera, file, or RTSP stream. For information about the plugins used in this pipeline, see Pipeline flow.

This application isn’t supported in Config #1 of Qualcomm Linux because CPU runtime is not supported.

Application: gst-ai-daisychain-detection-pose.py

Try me

Sample Model and Label Files

Runtime	Model file	Label file
LiteRT	detection: `yolox_quantized.tflite` pose: `hrnet_pose_quantized.tflite`	detection: `yolox.json` pose: `hrnet_pose.json`, `hrnet_settings.json`

Run the application on the target device

Download artifacts

Ensure that you complete the Prerequisites. This downloads all required artifacts to the target device.

Run the application

Input from the camera:

gst-daisychain-detection-pose.py --camera

Input from a file:

gst-daisychain-detection-pose.py --file ${HOME}/Downloads/qimsdk_samples/media/video.mp4

Input from an RTSP stream:

gst-daisychain-detection-pose.py --rtsp "rtsp://<ip>:<port>/<stream>"

To display all available options:

gst-daisychain-detection-pose.py -h

The default paths for model and label files are provided in the help section.

To stop the use case, press CTRL + C.

Expected Output

Pipeline Flow

The following table lists the plugins used in the daisychain detection and pose pipeline:

Process	Description
`qticamsrc` / `filesrc` / `rtspsrc`	Captures stream from camera, file, or RTSP.
`v4l2h264dec`	Decodes H.264 video.
`qtivsplit`	Crops full frame into smaller frames based on detected bounding boxes (maximum 4).
`qtimlvconverter`	Preprocesses frames for detection (stage 1) and pose estimation (stage 2).
`qtimltflite`	Runs detection and pose inference sequentially.
`qtimlpostprocess` (detection)	Produces bounding boxes. Loads YOLOv8 submodule.
`qtimlpostprocess` (pose)	Produces pose key point frames. Loads HRNet module.
`qtimetamux`	Synchronizes video and metadata.
`qtivcomposer`	Composes the final output stream.
`waylandsink`	Renders the output on a local display.

Troubleshooting

Model not available after running the download script?

If any model isn’t available after downloading the script file, you can download the model manually from IoT — Qualcomm AI Hub and push it to the target device:

scp <model filename> root@<ip addr of the target device>:${HOME}/Downloads/qimsdk_samples/models

For example:

scp mobilenet_v2_quantized.tflite root@<ip addr of the target device>:${HOME}/Downloads/qimsdk_samples/models

Running sample applications from the UART shell

Remount the file system with read/write permissions:For Qualcomm Linux:

mount -o remount,rw /usr

Cannot locate the qticamsrc plugin?

If you cannot locate the qticamsrc plugin, ensure that the camera server is running and clear the GStreamer cache using the following commands:

ps -ef | grep cam-server

rm ~/.cache/gstreamer-1.0/registry.aarch64.bin

GStreamer logging and debugging

To enable basic GStreamer logging, run the following before launching the application:

export GST_DEBUG=2

To increase verbosity for specific plugins, use a comma-separated list with log levels (1–7):

export GST_DEBUG=3,qticamsrc:5,qtimlvconverter:5,qtimltflite:5

To redirect logs to a file for offline analysis:

export GST_DEBUG=3 
export GST_DEBUG_FILE=/tmp/gst_classification_debug.log 

​Prerequisites

​AI Vision Applications

​Object Detection and Display

​Sample Model and Label Files

​Run the application on the target device

​Expected Output

Pipeline Flow

​Decode and Object Detection Using RTSP Stream

​Sample Model and Label Files

​Run the application on the target device

​Expected Output

Pipeline Flow

​Object Detection and Classification

​Sample Model and Label Files

​Run the application on the target device

​Expected Output

Pipeline Flow

​Known Issues

​Object Detection, Classification, and Segmentation

​Sample Model and Label Files

​Run the application on the target device

​Expected Output

Pipeline Flow

​Camera Encode, Object Detection, and Display

​Sample Model and Label Files

​Run the application on the target device

​Expected Output

Pipeline Flow

​Parallel Inference Using Python

​Sample Model and Label Files

​Run the application on the target device

​Expected Output

Pipeline Flow

​Daisy Chain Detection and Pose Detection Using Python

​Sample Model and Label Files

​Run the application on the target device

​Expected Output

Pipeline Flow

​Troubleshooting

Prerequisites

AI Vision Applications

Object Detection and Display

Sample Model and Label Files

Run the application on the target device

Expected Output

Decode and Object Detection Using RTSP Stream

Sample Model and Label Files

Run the application on the target device

Expected Output

Object Detection and Classification

Sample Model and Label Files

Run the application on the target device

Expected Output

Known Issues

Object Detection, Classification, and Segmentation

Sample Model and Label Files

Run the application on the target device

Expected Output

Camera Encode, Object Detection, and Display

Sample Model and Label Files

Run the application on the target device

Expected Output

Parallel Inference Using Python

Sample Model and Label Files

Run the application on the target device

Expected Output

Daisy Chain Detection and Pose Detection Using Python

Sample Model and Label Files

Run the application on the target device

Expected Output

Troubleshooting