Using ANN and UAV for Terrain Surveillance : A Case Study for Urban Areas Observation

Luiz F. Felizardo (1) , Rodrigo L. Mota (1) , Elcio H. Shiguemori (2) , Marcos T. Neves (1) , Alexandre Carlos Brandao-Ramos (1) , Felix Mora-Camino (3)

1 Institute of Mathematics and Computing
2 Institute of Advanced Studies
3 MAIAA - ENAC - Laboratoire de Mathématiques Appliquées, Informatique et Automatique pour l'Aérien

Autonomous Unmanned Aerial Vehicles (UAVs) provide an effective alternative for surveillance in urban areas due to their cost and safety when compared to other traditional methods. The objective of this study is to report the development of a system capable of analyzing digital images of the terrain and identifying potential invasion, unauthorized changes in land and deforestation in some special urban areas. Images are captured by a camera attached to an autonomous helicopter, flying it around the area. For processing the images, an Artificial Neural Network (ANN) technique called Self Organizing Map (SOM) is used.

Mots clés: pattern recognition; surveillance; UAV; autonomous helicopter; Kohonen SOM

Domaines: Sciences de l'ingénieur [physics]; Automatique / Robotique

Luiz F. Felizardo, Rodrigo L. Mota, Elcio H. Shiguemori, Marcos T. Neves, Alexandre Carlos Brandao-Ramos, et al.. Using ANN and UAV for Terrain Surveillance : A Case Study for Urban Areas Observation. HIS 2013, 13th International Conference on Hybrid Intelligent Systems, Dec 2013, Gammarth, Tunisia. ⟨10.1109/HIS.2013.6920414⟩. ⟨hal-01078501⟩