Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
O
openpose_ros
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Container Registry
Model registry
Operate
Environments
Monitor
Incidents
Service Desk
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
perception
openpose_ros
Commits
d1df70fc
Commit
d1df70fc
authored
7 years ago
by
MiguelARD
Committed by
GitHub
7 years ago
Browse files
Options
Downloads
Patches
Plain Diff
Delete README.md
parent
9ffade45
No related branches found
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
README.md
+0
-61
0 additions, 61 deletions
README.md
with
0 additions
and
61 deletions
README.md
deleted
100644 → 0
+
0
−
61
View file @
9ffade45
# openpose_ros
My ROS Wrapper for openpose https://github.com/CMU-Perceptual-Computing-Lab/openpose
(see commit number
`a1e0a5f4136e702b5731a268c2993fb75ca4753c`
)

# Installing and Testing the Openpose ROS Wrapper
1.
Install openpose and its dependencies then enable the package by running
````
./install_openpose_and_enable_package.sh
````
2.
If everything succeeds, run
`catkin build`
, source your workspace then:
````
roscd openpose_ros_pkg/../openpose
rosrun openpose_ros_pkg openpose_ros --image_dir examples/media/
````
3.
To test with your ROS sensor_msgs::Image topic, go to
`src/openpose_ros_node_firephinx.cpp`
and edit the lines:
````
// Camera Topic
DEFINE_string(camera_topic, "/multisense/left/image_rect_color_rotated_180", "Image topic that OpenPose will process.");
````
Change the string accordingly. camera_topic should be the ros sensor_msgs::Image topic you subscribe to. For example
`"/camera/image_raw"`
Run
`catkin build`
and source your workspace again then run:
````
rosrun openpose_ros_pkg openpose_ros_node_firephinx
````
If this works, you should see an openCV visualization open up:

4.
You may change the image resolution output by going back to
`src/openpose_ros_node_firephinx.cpp`
and change the parameters
````
#define OUTPUT_RES_X 1280 // Display Resolution Output Width
#define OUTPUT_RES_Y 720 // Display Resolution Output Height
````
## Example Service Code
1.
To start the ros service run:
````
rosrun openpose_ros_pkg openpose_ros_node
````
2.
To test if the service is working run:
````
rosrun openpose_ros_pkg test_openpose_ros_service_call
````
and subscribe to
`/openpose_ros/input_image`
for the input image and
`/openpose_ros/detected_poses_image`
for the output image
# Similar packages
Naturally,
`openpose`
is quite popular and similar packages for ros can be found at
*
https://github.com/tue-robotics/openpose_ros
*
https://github.com/firephinx/openpose_ros
# System
*
Ubuntu 14.04.5 LTS 64-bit
*
NVIDIA Titan XP (Proprietary Driver 381.09)
*
CUDA 8.0
*
cuDNN
*
ROS Indigo
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment