Observatorio de I+D+i UPM

Descripción
This paper presents an approach towards au- tonomous aerial power line inspection. In particular, the pre- sented work focuses on real-time autonomous detection, local- ization and tracking of electric towers. A strategy which com- bines classic computer vision and machine learning techniques, is proposed. A generalized detection and localization approach is presented, where a two-class multilayer perceptron (MLP) neural network was trained for Tower-Background classifica- tion. This MLP is applied over sliding windows for each camera frame until a tower is detected. The detection of a tower triggers the tracker. A hierarchical tracking methodology, especially designed for tracking towers in real-time, is presented. This methodology is based on the Hierarchical Multi-Parametric and Multi-Resolution Inverse Compositional Algorithm [1], and is proposed to be used for tracking and maintaining the tower in the field of view (FOV). The proposed strategy, which is the combination of the tower detector and the tracker, is evaluated on videos from several real manned helicopter inspections. Overall, the results show that the proposed strategy performs very well at detecting and tracking various types of electric towers in diverse environmental settings.
Internacional	Si
Nombre congreso	International Conference on Unmanned Aircraft Systems
Tipo de participación	960
Lugar del congreso	Orlando, FL
Revisores	Si
ISBN o ISSN
DOI	10.1109/ICUAS.2014.6842267
Fecha inicio congreso	27/05/2014
Fecha fin congreso	30/05/2014
Desde la página
Hasta la página
Título de las actas

Esta actividad pertenece a memorias de investigación

• Autor: Carol Viviana Martinez Luna (UPM)
• Autor: Carlos Sampedro Perez (UPM)
• Autor: Aneesh Chauhan . (UPM)
• Autor: Pascual Campoy Cervera (UPM)

• Creador: Centro o Instituto I+D+i: Centro de Automática y Robótica (CAR). Centro Mixto UPM-CSIC
• Departamento: Automática, Ingeniería Eléctrica y Electrónica e Informática Industrial