-
ROS index logo ROS Index
  1. Home
  2. Packages
  3. image_recognition_openpose
 
No version for distro humble. Known supported distros are highlighted in the buttons above.
No version for distro iron. Known supported distros are highlighted in the buttons above.
No version for distro jazzy. Known supported distros are highlighted in the buttons above.
No version for distro rolling. Known supported distros are highlighted in the buttons above.
No version for distro noetic. Known supported distros are highlighted in the buttons above.
No version for distro ardent. Known supported distros are highlighted in the buttons above.
No version for distro bouncy. Known supported distros are highlighted in the buttons above.
No version for distro crystal. Known supported distros are highlighted in the buttons above.
No version for distro eloquent. Known supported distros are highlighted in the buttons above.
No version for distro dashing. Known supported distros are highlighted in the buttons above.
No version for distro galactic. Known supported distros are highlighted in the buttons above.
No version for distro foxy. Known supported distros are highlighted in the buttons above.
No version for distro lunar. Known supported distros are highlighted in the buttons above.
No version for distro jade. Known supported distros are highlighted in the buttons above.
No version for distro indigo. Known supported distros are highlighted in the buttons above.
No version for distro hydro. Known supported distros are highlighted in the buttons above.

image_recognition_openpose package from image_recognition repo

image_recognition image_recognition_age_gender image_recognition_analysis image_recognition_color_extractor image_recognition_face_recognition image_recognition_footwear image_recognition_jetson image_recognition_msgs image_recognition_openface image_recognition_openpose image_recognition_pose_estimation image_recognition_rqt image_recognition_segment_anything image_recognition_skybiometry image_recognition_tensorflow image_recognition_tensorflow_rqt image_recognition_util

API Docs
Browse Code

Package Summary

Tags No category tags.
Version 0.0.5
License MIT
Build type CATKIN
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/tue-robotics/image_recognition.git
VCS Type git
VCS Version master
Last Updated 2024-05-05
Dev Status DEVELOPED
CI status No Continuous Integration
Released RELEASED
Tags No category tags.
Contributing Help Wanted (0)
Good First Issues (0)
Pull Requests to Review (0)

Package Description

ROS Wrapper for the openpose software package. Exposes a service and topic interface.

Additional Links

No additional links.

Maintainers

  • Rein Appeldoorn

Authors

No additional authors.
image_recognition_openpose/README.md

Openpose image recognition

ROS Wrapper for openpose https://github.com/CMU-Perceptual-Computing-Lab/openpose

Installation notes

This ROS wrapper makes use of the Openpose python interface. Please follow the installation manual and ensure that the BUILD_PYTHON flag is turned on while running CMake. Also make sure that you install a release instead of the latest master version with CUDA8 since Torch (image_recognition_openface) cannot handle CUDA10.

export OPENPOSE_INSTALL_PATH=~/openpose && \
mkdir -p $OPENPOSE_INSTALL_PATH && \
wget https://github.com/CMU-Perceptual-Computing-Lab/openpose/archive/v1.4.0.tar.gz -O /tmp/v1.4.0.tar.gz && \
tar -xvf /tmp/v1.4.0.tar.gz -C /tmp/ && cp -r /tmp/openpose-1.4.0/* $OPENPOSE_INSTALL_PATH  && \
$OPENPOSE_INSTALL_PATH/ubuntu/install_cuda.sh && \
$OPENPOSE_INSTALL_PATH/ubuntu/install_cudnn.sh && \
wget https://github.com/CMU-Perceptual-Computing-Lab/caffe/archive/1.0.tar.gz -O /tmp/1.0.tar.gz && \
tar -xvf /tmp/1.0.tar.gz -C /tmp/ && cp -r /tmp/caffe-1.0/* $OPENPOSE_INSTALL_PATH/3rdparty/caffe && \
cd $OPENPOSE_INSTALL_PATH && mkdir -p build && cd build && \
cmake .. -DBUILD_PYTHON=1 -DCUDA_TOOLKIT_ROOT_DIR=/usr/local/cuda && \
make -j`nproc` && \
sudo make install

Scripts

detect_poses

Example for the following picture:

Example

rosrun image_recognition_openpose detect_poses image `rospack find image_recognition_openpose`/doc/example.jpg

Output:

Example result

It also works with a webcam stream, usage:

usage: detect_poses [-h] [--pose_model POSE_MODEL]
                    [--net_input_size NET_INPUT_SIZE]
                    [--net_output_size NET_OUTPUT_SIZE]
                    [--num_scales NUM_SCALES] [--scale_gap SCALE_GAP]
                    [--num_gpu_start NUM_GPU_START]
                    [--overlay_alpha OVERLAY_ALPHA]
                    [--python_path PYTHON_PATH]
                    model_folder {image,cam} ...

Detect poses in an image

positional arguments:
  model_folder          Path where the models are stored
  {image,cam}           Mode
    image               Use image mode
    cam                 Use cam mode

optional arguments:
  -h, --help            show this help message and exit
  --pose_model POSE_MODEL
                        What pose model to use (default: BODY_25)
  --net_input_size NET_INPUT_SIZE
                        Net input size (default: -1x368)
  --net_output_size NET_OUTPUT_SIZE
                        Net output size (default: -1x-1)
  --num_scales NUM_SCALES
                        Num scales (default: 1)
  --scale_gap SCALE_GAP
                        Scale gap (default: 0.3)
  --num_gpu_start NUM_GPU_START
                        What GPU support (default: 0)
  --overlay_alpha OVERLAY_ALPHA
                        Overlay alpha for the output image (default: 0.6)
  --python_path PYTHON_PATH
                        Python path where Openpose is stored (default:
                        /usr/local/python/)

openpose_node

How-to

Run the image_recognition_openpose node in one terminal, e.g.:

rosrun image_recognition_openpose openpose_node

Next step is starting the image_recognition_Rqt test gui (https://github.com/tue-robotics/image_recognition_rqt)

rosrun image_recognition_rqt test_gui

Configure the service you want to call with the gear-wheel in the top-right corner of the screen. If everything is set-up, draw a rectangle in the image and ask the service for detections:

Test

You will see that the result of the detection will prompt in a dialog combo box. Also the detections will be drawn on the image. The ROS node also published the result image, you can easily view this image using rqt_image_view.

CHANGELOG

Changelog for package image_recognition_openpose

0.0.5 (2019-06-08)

  • Working openpose python wrapper
  • refactor package xml to 2.0
  • rename ROS pkgs with image_recognition_prefix
  • Contributors: Arpit Aggarwal, Loy van Beek, Rein Appeldoorn

Wiki Tutorials

This package does not provide any links to tutorials in it's rosindex metadata. You can check on the ROS Wiki Tutorials page for the package.

Package Dependencies

Deps Name
catkin
cv_bridge
diagnostic_updater
image_recognition_msgs
image_recognition_util
rospy
sensor_msgs
python-sphinx-autoapi-pip
python-sphinx-rtd-theme-pip
catkin_lint_cmake

System Dependencies

Name
python3-setuptools
python3-opencv
python3-sphinx
python3-yaml

Dependant Packages

No known dependants.

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged image_recognition_openpose at Robotics Stack Exchange

No version for distro melodic. Known supported distros are highlighted in the buttons above.