Using EM to Learn 3D Models of Indoor Environments with Mobile Robots
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Real-Time Detection of Independent Motion using Stereo
WACV-MOTION '05 Proceedings of the IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2 - Volume 02
Real-time Localization in Outdoor Environments using Stereo Vision and Inexpensive GPS
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Cognitive maps for mobile robots-an object based approach
Robotics and Autonomous Systems
Supervised semantic labeling of places using information extracted from sensor data
Robotics and Autonomous Systems
Hi-index | 0.00 |
We report our first experiences with Leaving Flatland, an exploratory project which studies the key challenges in closing the loop on autonomous perception and action in challenging terrain. A primary objective of the project is to demonstrate the acquisition and processing of robust 3D geometric model maps from stereo data and Visual Odometry techniques. The 3D geometric model is used to infer different terrain types and construct a 3D semantic model which can be used for path planning or teleoperation. This paper presents the set of methods and techniques used for building such a model, and provides insight on the mathematical optimizations used for obtaining realtime processing. To validate our approach, we show results obtained on multiple datasets and perform a comparison with other similar initiatives.