News Articles

New Object Segmentation Algorithms

There are several tools available in PCL trunk that may be useful to the upcoming mobile manipulation challenge. Tools for segmentation of organized point cloud data (as from a Kinect or Xtion) have been added in pcl::OrganizedConnectedComponentSegmentation and pcl::OrganizedMultiPlaneSegmentation. These can be used for fast segmentation of all planes in the scene or euclidean clustering. It can also be extended with your own comparison functions for other segmentation tasks.

An example of how to use the plane segmentation is:

// Segment planes
pcl::OrganizedMultiPlaneSegmentation< PointT, pcl::Normal, pcl::Label > mps;
mps.setMinInliers (10000);
mps.setAngularThreshold (0.017453 * 2.0); // 2 degrees
mps.setDistanceThreshold (0.02); // 2cm
mps.setInputNormals (normal_cloud);
mps.setInputCloud (cloud);
std::vector< pcl::PlanarRegion< PointT > > regions;
mps.segmentAndRefine (regions);

for (size_t i = 0; i < regions.size (); i++)
{
  Eigen::Vector3f centroid = regions[i].getCentroid ();
  Eigen::Vector4f model = regions[i].getCoefficients ();
  pcl::PointCloud boundary_cloud;
  boundary_cloud.points = regions[i].getContour ();
  printf ("Centroid: (%f, %f, %f)\n  Coefficients:…

PCL-NVCS kickstart!

PCL-NVCS is ready to start! The sprint will cover 3D algorithmic work for human body recognition, deformable object modeling, and real-time visualization on Tegra3 platforms. Here's a list of the PCL developers working on the sprint:

  • Pat Marion, a member of the scientific visualization group at Kitware, will be working on point cloud streaming to Tegra3 devices for mobile visualization. Pat brings in years of experience by having had worked on large 3D visualization engines such as VTK, ParaView, and VES.
  • Koen Buys from Katholieke Universiteit Leuven, will be working on human body tracking from point cloud data. Koen is already a PCL developer and has been working on body tracking using GPUs as part of his doctoral research.
  • Martin Saelzle from Technische Universitaet Muenchen, will be working on deformable object modeling for PCL. Martin acquired extensive experience in point cloud registration using Kinect sensors while working in Prof. Nassir Navab's group at TUM.

We would like to thank all the other candidates for their excellent proposals! We already started…

PCL - Google Summer of Code 2012

We are very proud to announce that the Point Cloud Library has been accepted for the second time in the Google Summer of Code program. This is a great opportunity to have new people joining the thriving community of open-source 3D perception.

The webpage where you will find our list of ideas We are very flexible with the project ideas, and we are accepting interesting and solid (!!!) project proposals on our official event mailing list: gsoc2012@pointclouds.org or for more direct communication on IRC: irc.oftc.net, channel #pcl.

In order to apply, please follow the instruction on the official GSoC website and our custom student application requirements.

PCL-SRCS kickstart!

PCL-SRCS is ready to start! The sprint will cover 3D algorithmic work for surface reconstruction and large scale mapping for PCL. Our developers are:

PCL-HRCS kickstart!

PCL-HRCS is ready to start! The two developers that will be working on 3D technologies for driver-assistance systems are:

  • Aitor Aldoma, from Vienna University of Technology, will be working on 3D face orientation. Aitor has been working on techniques for object recognition and 6DOF pose alignment out of point cloud data for PCL in the past, such as CVFH.
  • Alex Trevor, from Georgia Institute of Technology, will be working on non-ground extraction from point cloud data. Alex has developed various real-time segmentation methods for planar components as part of PCL.

We would like to thank all the other candidates for their excellent proposals! We already started following up with each of them individually, as there are many more sprints to come!

[Note: the new blogging page for HRCS will be up within the next few days at http://pointclouds.org/blog/hrcs/.]

PCL and Sandia Robotics Code Sprint 2012

Sandia Robotics

It is our immense pleasure to announce the beginning of a new PCL Code Sprint sponsored by Sandia Robotics group: PCL-SRCS!

PCL Code Sprints are intended to rapidly advance the capabilities of the Point Cloud Library in a certain area/subject by offering stipends to talented student developers and pairing them with knowledgeable mentors for several months of accelerated software development. Projects will run for an initial period of 3 months, and all of the code produced will be BSD-licensed open source.

For this spring's PCL-Sandia Robotics Code Sprint, we have identified the following important areas for further development in PCL, and we are therefore searching for outstanding candidates (and mentors) to work on the following projects:

  1. Kinect Fusion extensions to large scale environments: the purpose of this project is to extend techniques such as Kinect Fusion to larger scale environments with CUDA. A goal would be to combine it with a segmentation algorithm in order to be able to create specific object models. CUDA/GPGPU programming knowledge is…

PCL and NVidia Code Sprint 2012

NVidia

It is our immense pleasure to announce the beginning of a new PCL Code Sprint sponsored by NVidia: PCL-NVCS!

PCL Code Sprints are intended to rapidly advance the capabilities of the Point Cloud Library in a certain area/subject by offering stipends to talented student developers and pairing them with knowledgeable mentors for several months of accelerated software development. Projects will run for an initial period of 3 months, and all of the code produced will be BSD-licensed open source.

For this spring's PCL-NVidia Code Sprint, we have identified the following important areas for further development in PCL, and we are therefore searching for outstanding candidates (and mentors) to work on the following projects:

  1. Human Body tracking: The high-level purpose of this project is to implement and analyze various techniques for extracting humans body poses in dense 3D data at high speed with CUDA. The applications are numerous, from gaming to gesture interfacing. The code sprint component will be a focused implementation that produces fast and reusable code. Some possible code sprint project specifications…

2nd ICRA Workshop on Semantic Perception, Mapping and Exploration (SPME 2012)


St. Paul, Minnesota, USA, May 14, 2011
http://www.spme.ws/

Important Dates

Submissions Due:01 April 2012
Notification of Acceptance:16 April 2012
Final Papers Due:01 May 2012
Workshop at ICRA:14 May 2012

Motivation and Objectives

As robots and autonomous systems move away from laboratory setups towards complex real-world scenarios, both the perception capabilities of these systems and their abilities to acquire and model semantic information must become more powerful. The autonomous acquisition of information, the extraction of semantic models, and exploration strategies for deciding where and how to acquire the most relevant information pertinent to a specific semantic model are the research foci of an annual series of workshops at ICRA, called Semantic Perception, Mapping and Exploration (SPME).

Semantic perception for intelligent systems such as robots has seen a lot of progress recently, with many new and interesting techniques being developed in parallel by different research groups. Moreover, with the advent of inexpensive and accurate 3D imaging sensors, there has been an explosion of interest in 3D point clouds across a broad range of people.…



PCL and Honda Research Institute Code Sprint 2012

Honda Research Institute

It is our immense pleasure to announce the beginning of a new PCL Code Sprint sponsored by Honda Research Institute: PCL-HRCS!

PCL Code Sprints are intended to rapidly advance the capabilities of the Point Cloud Library in a certain area/subject by offering stipends to talented student developers and pairing them with knowledgeable mentors for several months of accelerated software development. Projects will run for an initial period of 3 months, and all of the code produced will be BSD-licensed open source.

For this spring's PCL-Honda Research Institute Code Sprint, we have identified the following important area for further development in PCL, and we are therefore searching for outstanding candidates (and mentors) to work on the following projects:

  1. Non-ground extraction from point cloud data: given a point cloud data sequence, develop a method for determining a planar drivable area (i.e., identify pixels in the image that correspond to the drivable zone), then classify the remaining areas in non-drivable or unknown.
  2. Face orientation: given a point…

PCL-URCS kickstart!

PCL-URCS is ready to start! The integration of Urban Robotics's out-of-core octree into PCL will be performed by Stephen D. Fox, from Fordham University Robotics and Computer Vision Lab, NY. Stephen has been working on numerous projects involving laser sensors, and stereo cameras, and has been part of our community since PCL 1.0.

We would like to thank all the other candidates for their excellent proposals! We already started following up with each of them individually, as this is just our third code sprint and there are many more to come!

[Note: the new blogging page for URCS will be up within the next few days at http://pointclouds.org/blog/urcs/.]

  • First
  • <<
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • >>
  • Last
  • Latest Posts

    Latest Comments