Detect faces with sample_face_detection - Qualcomm Dragonwing Documentation

The sample_face_detection sample application detects faces and locates facial landmarks from images using the Python-based ROS 2 node sample_face_detection, which uses Qualcomm® AI Engine Direct SDK (QNN) for model inference. The models are sourced from Qualcomm AI-hub. It captures the face_image.jpg as input and publishes the result to the /mediaface_det_image topic.

Note

For model information, see MediaPipe-Face-Detection - Qualcomm AI Hub.
For details about the sample application, see sample_fact_detection on GitHub

Figure: Sample effects of sample_face_detection

Pipeline flow for `sample_face_detection`

Figure: Pipeline flow for sample_face_detection

ROS nodes used in `sample_face_detection`

ROS node	Description
`qrb_ros_face_detector`	The `qrb_ros_face_detector` is a Python-based ROS 2 jazzy package that processes face images. This ROS node subscribes to an image topic, and publishes the face image result topic after pre/post processing.
`image_publisher`	`image_publisher` is a ROS 2 Jazzy package. It publishes the `image` ROS topic with a local path. For more information, see image_publisher.
`qrb_ros_nn_inference`	`qrb_ros_nn_inference` is a ROS 2 package that performs neural network model, providing AI-based perception for robotics applications. For more information, see qrb_ros_nn_inference.
`qrb ros camera`	`qrb ros camera` is a ROS 2 package that captures images with parameters and publishes them to ROS topics. For more information, see qrb_ros_camera.

ROS topics used in `sample_face_detection`

ROS Topic	Type	Published By
`/mediaface_det_image`	`sensor_msgs.msg.Image`	`qrb_ros_face_detector`
`/image_raw`	`sensor_msgs.msg.Image`	`image_publisher`
`/face_detector_input_tensor`	`qrb_ros_tensor_list_msgs.msg.TensorList`	`qrb_ros_face_detector`
`/face_detector_output_tensor`	`qrb_ros_tensor_list_msgs.msg.TensorList`	`qrb_ros_nn_inference`
`/face_landmark_input_tensor`	`qrb_ros_tensor_list_msgs.msg.TensorList`	`qrb_ros_face_detector`
`/face_landmark_output_tensor`	`qrb_ros_tensor_list_msgs.msg.TensorList`	`qrb_ros_nn_inference`

Prerequisites

You have completed the settings in Set up the environment for running sample applications.

Run out-of-the-box `sample_face_detection`

Try me

Run the sample on the development kit

Select the input source of the pipeline, and then complete the steps in the corresponding tab.

Image publisher
qrb_ros_camera

Set up the runtime environment.

SSH Session

# Set up the runtime environment
source /usr/share/qirp-setup.sh -m
# Set the ROS_DOMAIN_ID
export ROS_DOMAIN_ID=xx # Value range of ROS_DOMAIN_ID: [0, 232]

Launch the sample with image_publisher. You can replace image_path with the path to your desired image.
SSH Session
ros2 launch sample_face_detection launch_with_image_publisher.py \ image_path:=/usr/ros/jazzy/share/sample_face_detection/face_image.jpg
NoteThis sample application supports JPG images only. You can test it using one of your own images with a different filename.

Ensure that you have connected a camera to the development kit and set it up according to Set up the camera. The launch file starts the qrb_ros_camera node with camera ID 0 and a 640 × 480 stream, so you don’t need to run qrb_ros_camera separately.

Set up the runtime environment.

SSH Session

# Set up the runtime environment
source /usr/share/qirp-setup.sh -m
# Set the ROS_DOMAIN_ID
export ROS_DOMAIN_ID=xx # Value range of ROS_DOMAIN_ID: [0, 232]

Launch the sample with qrb_ros_camera.

SSH Session

ros2 launch sample_face_detection launch_with_qrb_ros_camera.py

View the results on the host computer

Start the rqt.

SSH Session

# YOUR_HOST_IP is the IP address of the Host where you want to view the sample output.
export DISPLAY=YOUR_HOST_IP:0
export ROS_DOMAIN_ID=xx # same as the preceding ID
rqt

Select the following buttons in sequence: Plugins —> Visualization —> Image View
Select mediaface_det_image to see the results.

Build and run `sample_face_detection`

The following steps build the sample_face_detection package using Dragonwing IQ-9075 Evaluation Kit as an example.

Try me

Build and package on the host computer

Build the sample application project.

cd <decompressed_workspace>/images/iq-9075-evk/qirpsdk_artifacts/iq-9075-evk/
tar -zxvf qirp-sdk_<qirp_version>.tar.gz
cd qirp-sdk
source setup.sh
# build sample
cd <qirp_decompressed_path>/qirp-samples/ai_vision/sample_face_detection
colcon build

Package and push the sample application to the device.

# package and push build result of sample
cd <qirp_decompressed_path>/qirp-samples/ai_vision/sample_face_detection/install/sample_face_detection
tar -czvf sample_face_detection.tar.gz lib share
scp sample_face_detection.tar.gz root@[ip-addr]:/opt/

Install and run on the development kit

Install the sample application.

SSH Session

# Install sample package
tar --no-overwrite-dir --no-same-owner -zxf /opt/sample_face_detection.tar.gz -C /usr/ros/jazzy/

Run the sample application with the steps in Run out-of-the-box sample_face_detection.

Robotics SDK(Linux)

​Pipeline flow for sample_face_detection

​ROS nodes used in sample_face_detection

​ROS topics used in sample_face_detection

​Prerequisites

​Run out-of-the-box sample_face_detection

​Build and run sample_face_detection

Pipeline flow for `sample_face_detection`

ROS nodes used in `sample_face_detection`

ROS topics used in `sample_face_detection`

Prerequisites

Run out-of-the-box `sample_face_detection`

Build and run `sample_face_detection`