https://github.com/ros2/detection_visualizer

ROS 2 package with a node that draws bound boxes for debugging computer vision nodes.
https://github.com/ros2/detection_visualizer

Last synced: about 1 month ago
JSON representation

ROS 2 package with a node that draws bound boxes for debugging computer vision nodes.

• Host: GitHub
• URL: https://github.com/ros2/detection_visualizer
• Owner: ros2
• License: apache-2.0
• Created: 2019-10-03T23:37:29.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2023-06-05T17:15:05.000Z (over 1 year ago)
• Last Synced: 2023-08-14T03:11:08.101Z (over 1 year ago)
• Language: Python
• Size: 751 KB
• Stars: 4
• Watchers: 3
• Forks: 7
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Detection Visualizer

This package provides a ROS 2 node for visualizing computer vision detections.

It subscribes to an image topic and a detections topic, and outputs an image with bounding boxes drawn on it.

The output topic can be visualized in rviz.

![Example image with bounding boxes created using darknet and the yolov3-tiny network](doc/example_darknet_yolov3-tiny.png)

# Topics

* `~/images` (Type `sensor_msgs/msg/Image`) - Input topic with images that have been given to a computer vision node

* `~/detections` (Type `vision_msgs/msg/Detection2DArray`) - Input topic with detections on the given image

* `~/dbg_image` (Type `sensor_msgs/msg/Image`) - Output topic which has bounding boxes drawn on it

It is assumed the image message and detections message have identical timestamps.