Computational geometry: an introduction
Computational geometry: an introduction
SIAM Journal on Computing
Network flows: theory, algorithms, and applications
Network flows: theory, algorithms, and applications
Improved Algorithms for Bipartite Network Flow
SIAM Journal on Computing
LEDA: a platform for combinatorial and geometric computing
LEDA: a platform for combinatorial and geometric computing
A Maximum-Flow Formulation of the N-Camera Stereo Correspondence Problem
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
| Hi-index | 0.00 |
The ability to cope with rapidly changing, dynamic environments is an important requirement for autonomous robots to become valuable assistants in everyday life. In this paper we focus on the task of tracking moving objects in such environments. Objects are extracted from laser range finder images and correspondence between successive scan images is established using network flow algorithms. This approach is implemented on a robotic wheelchair and allows it to follow a guiding person and to perform some simplistic reasoning about deliberate obstructions of it, these two applications requiring robust tracking of humans in the robot's vicinity.