The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-2/W6
https://doi.org/10.5194/isprs-archives-XLII-2-W6-127-2017
https://doi.org/10.5194/isprs-archives-XLII-2-W6-127-2017
23 Aug 2017
 | 23 Aug 2017

OBSTACLE DETECTION SYSTEM INVOLVING FUSION OF MULTIPLE SENSOR TECHNOLOGIES

C. Giannì, M. Balsi, S. Esposito, and P. Fallavollita

Keywords: Obstacle avoidance, UAV, Data fusion

Abstract. Obstacle detection is a fundamental task for Unmanned Aerial Vehicles (UAV) as a part of a Sense and Avoid system. In this study, we present a method of multi-sensor obstacle detection that demonstrated good results on different kind of obstacles. This method can be implemented on low-cost platforms involving a DSP or small FPGA. In this paper, we also present a study on the typical targets that can be tough to detect because of their characteristics of reflectivity, form factor, heterogeneity and show how data fusion can often overcome the limitations of each technology.