Mesh Toolbox is a set of software libraries and executables for
manipulating triangular surface meshes. It contains functions for
smoothing, registering, integrating, recognizing and displaying
surface meshes
Accurate
Estimation of Rought Terrain with Space-Carving Kernels |
This software implements the terrain estimation algorithms described in the
paper "Accurate Estimation of Rough Terrain with Space-Carving Kernels,"
which was published in Robotics: Science and Systems, 2009.
Structured Prediction for Smoothed Labeling Tasks |
A library for training Max-Margin Markov Networks with (Robust) Pott's
potentials, over arbitrary-sized cliques.
This is an extended C++ implementation of the algorithm presented in the paper:
D. Munoz, J. A. Bagnell, N. Vandapel, H. Hebert,
"Contextual Classification with Functional Max-Margin Markov Networks",
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2009.
[project page]
Fully labeled point clouds of urban scenes around the CMU campus;
dataset published in the above CVPR 2009 publication.
Moving object
detection, modeling, and tracking |
This is research code for detecting and tracking moving objects using the
combination of a single line LIDAR and imagery.
This is research code for using LIDAR data to improve dense stereo estimation
Matlab laser
calibration toolbox |
This toolbox allows the external calibration of a camera to a laser rangefinder.
- Documentation | Code | Test data set
The VMR
Lab is part of the Vision and
Autonomous Systems Center within the Robotics Institute in the School of Computer Science, Carnegie Mellon University.