Multi-sensor Detection and Tracking of Humans for Safe Operations with Unmanned Ground Vehicles - Robotics Institute Carnegie Mellon University

Multi-sensor Detection and Tracking of Humans for Safe Operations with Unmanned Ground Vehicles

Susan M. Thornton, Mike Hoffelder, and Daniel D. Morris
Workshop Paper, Proceedings of 1st IEEE Workshop on Human Detection from Mobile Platforms, May, 2008

Abstract

This paper details an approach for the automatic detection and tracking of humans using multi-sensor modalities including 3D Ladar and long wave infrared (LWIR) video. By combining data from these sensors, we can detect individuals regardless of whether they are erect, crouched, prone, or partially occluded by other obstacles. Such algorithms are integral to the development and fielding of future "intelligent" unmanned ground vehicles (UGVs). In order for robots to be integrated effectively into small combat teams in the operational environment, the autonomous vehicles must maneuver safely among our troops and therefore must be capable of detecting stationary and moving people in cluttered scenes.

BibTeX

@workshop{Thornton-2008-9950,
author = {Susan M. Thornton and Mike Hoffelder and Daniel D. Morris},
title = {Multi-sensor Detection and Tracking of Humans for Safe Operations with Unmanned Ground Vehicles},
booktitle = {Proceedings of 1st IEEE Workshop on Human Detection from Mobile Platforms},
year = {2008},
month = {May},
}