Today we are releasing many of our perception-related libraries for ROS: image_common, image_pipeline, laser_pipeline, and opencv. All of these releases are 0.1 releases, which means that they are currently being user-tested for potential improvements.
- image_common provides lower-level image-related dependencies, including image_transport, which provides a plugin architecture for transporting raw and compressed image data.
- image_pipeline and laser_pipeline have very similar capabilities. laser_pipeline processes sensor data from laser range finders and can turn it into 3D point clouds. image_pipeline processes sensor data from mono and stereo cameras and can perform common image-processing tasks, like rectification and color processing. In the case of stereo, it can output 3D disparity images. These 3D representations can then be used in higher-level libraries.
- opencv is a ROS wrapper for the popular OpenCV computer vision toolkit. OpenCV is heavily used in higher-level libraries to perform many common perception-related tasks. The version we are using in ROS is a pre-release version of the upcoming OpenCV 2.0 release.