Estimate human poses with sample_hrnet_pose_estimation

The sample_hrnet_pose_estimation sample application provides high-precision human pose estimation using ROS 2 nodes. It uses Qualcomm® AI Engine Direct SDK (QNN) for model inference. It processes input images and publishes the following ROS 2 topics:

/pose_estimation_results: Output images with visualized pose keypoints.
/pose_estimation_points: Raw keypoint coordinates in a structured message format.

Note

For model information, see HRNetPose - Qualcomm AI Hub.
For more information, see sample_hrnet_pose_estimation on GitHub.

Figure: Sample effects of sample_hrnet_pose_estimation

Pipeline flow for `sample_hrnet_pose_estimation`

Figure: Pipeline flow for sample_hrnet_pose_estimation

ROS nodes used in `sample_hrnet_pose_estimation`

ROS node	Description
qrb_ros_camera	Qualcomm ROS 2 package that captures images with parameters and publishes them to ROS topics.
qrb_ros_nn_inference	Loads a trained AI model, receives preprocessed images, performs inference, and publishes results.
image_publisher	ROS 2 Jazzy package that publishes the image ROS topic with a local path.
`hrnet_pose_estimation_node`	Subscribes to `/image_raw` for image input, performs pose estimation, and publishes results to `/pose_estimation_results` and `/pose_estimation_points`.

ROS topics used in `sample_hrnet_pose_estimation`

ROS Topic	Type	Published By
`/image_raw`	`sensor_msgs.msg.Image`	`qrb_ros_camera`
`/qrb_inference_input_tensor`	`qrb_ros_tensor_list_msgs.msg.TensorList`	`hrnet_pose_estimation_node`
`/qrb_inference_output_tensor`	`qrb_ros_tensor_list_msgs.msg.TensorList`	`qrb_ros_nn_inference`
`/pose_estimation_results`	`sensor_msgs.msg.Image`	`hrnet_pose_estimation_node`
`/pose_estimation_points`	`geometry_msgs.msg.PolygonStamped`	`hrnet_pose_estimation_node`

Note/pose_estimation_points contains the coordinates of 17 key points on the original image. Developers can subscribe to this topic for secondary development. The key points include: nose, left eye, and right eye. The specific correspondence is as follows:

ID	Body part	ID	Body part
1	Nose	10	Right wrist
2	Right eye	11	Left wrist
3	Left eye	12	Right hip
4	Right ear	13	Left hip
5	Left ear	14	Right knee
6	Right shoulder	15	Left knee
7	Left shoulder	16	Right ankle
8	Right elbow	17	Left ankle
9	Left elbow

Prerequisites

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

Run out-of-the-box `sample_hrnet_pose_estimation`

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=123

Launch the sample with image_publisher. You can replace image_path with the path to your desired image.

SSH Session

ros2 launch sample_hrnet_pose_estimation launch_with_image_publisher.py \
    image_path:=/usr/ros/jazzy/share/sample_hrnet_pose_estimation/input_image.jpg

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=123

Launch the sample with qrb_ros_camera.

SSH Session

ros2 launch sample_hrnet_pose_estimation 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=123
rqt

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

Open a new terminal and run the following command to view the /pose_estimation_points topic.

SSH Session

source /usr/share/qirp-setup.sh -m
export ROS_DOMAIN_ID=123
ros2 topic echo /pose_estimation_points

Build and run `sample_hrnet_pose_estimation`

The following steps build the sample_hrnet_pose_estimation 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_hrnet_pose_estimation
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_hrnet_pose_estimation/install/sample_hrnet_pose_estimation
tar -czvf sample_hrnet_pose_estimation.tar.gz lib share
scp sample_hrnet_pose_estimation.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_hrnet_pose_estimation.tar.gz -C /usr/ros/jazzy/

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

Robotics SDK(Linux)

​Pipeline flow for sample_hrnet_pose_estimation

​ROS nodes used in sample_hrnet_pose_estimation

​ROS topics used in sample_hrnet_pose_estimation

​Prerequisites

​Run out-of-the-box sample_hrnet_pose_estimation

​Build and run sample_hrnet_pose_estimation

Pipeline flow for `sample_hrnet_pose_estimation`

ROS nodes used in `sample_hrnet_pose_estimation`

ROS topics used in `sample_hrnet_pose_estimation`

Prerequisites

Run out-of-the-box `sample_hrnet_pose_estimation`

Build and run `sample_hrnet_pose_estimation`