Human Body Detection and Geolocalization for UAV Search and Rescue Missions Using Color and Thermal Imagery
Linköping University, Department of Computer and Information Science, KPLAB - Knowledge Processing Lab
Linköping University, The Institute of Technology
Conference paper (Refereed)
Proceedings of the IEEE Aerospace Conference
The IEEE Aerospace Conference, March 1-8, Big Sky, Montana, USA
Aerospace Conference Proceedings, ISSN 1095-323X; 2008
Recent advances in the field of Unmanned Aerial Vehicles (UAVs) make flying robots suitable platforms for carrying sensors and computer systems capable of performing advanced tasks. This paper presents a technique which allows detecting humans at a high frame rate on standard hardware onboard an autonomous UAV in a real-world outdoor environment using thermal and color imagery. Detected human positions are geolocated and a map of points of interest is built. Such a saliency map can, for example, be used to plan medical supply delivery during a disaster relief effort. The technique has been implemented and tested on-board the UAVTech1 autonomous unmanned helicopter platform as a part of a complete autonomous mission. The results of flight- tests are presented and performance and limitations of the technique are discussed.