PCL presents an advanced and extensive approach to the subject of 3D perception, and it’s meant to provide support for all the common 3D building blocks that applications need. Written from a perspective of online sensor data processing, PCL deals with point cloud data acquired from real sensing devices including laser scanners, stereo cameras, and TOF cameras.
PCL is a fully templated, modern C++ library, with efficient backends for modern CPUs (SSE optimized), and GPUs (CUDA). The plethora of state-of-the-art algorithms implemented is large, with many new ones added on a weekly to monthly basis – acquisition, filtering, feature estimation, surface reconstruction, registration, model fitting, and segmentation, are just a few of the many topics covered by PCL.
The project is supported by an international community of robotics and perception researchers, and would not exist without the contributions of many people and companies. We thank everyone for their support!
The following overview presentation was given at the ROS Fall School at TUM in November 2010.