Towards autonomous detection and tracking of electric towers for aerial power line inspection

Carol Martinez, Carlos Sampedro, Aneesh Chauhan, Pascual Campoy

Research output: Chapter in Book/Report/Conference proceedingConference paperAcademicpeer-review

84 Citations (Scopus)

Abstract

This paper presents an approach towards autonomous aerial power line inspection. In particular, the presented work focuses on real-time autonomous detection, localization and tracking of electric towers. A strategy which combines 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 classification. 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.

Original languageEnglish
Title of host publication2014 International Conference on Unmanned Aircraft Systems, ICUAS 2014 - Conference Proceedings
PublisherIEEE
Pages284-295
Number of pages12
ISBN (Print)9781479923762
DOIs
Publication statusPublished - Jun 2014
Externally publishedYes
Event2014 International Conference on Unmanned Aircraft Systems, ICUAS 2014 - Orlando, FL, United States
Duration: 27 May 201430 May 2014

Publication series

Name2014 International Conference on Unmanned Aircraft Systems, ICUAS 2014 - Conference Proceedings

Conference

Conference2014 International Conference on Unmanned Aircraft Systems, ICUAS 2014
Country/TerritoryUnited States
CityOrlando, FL
Period27/05/1430/05/14

Fingerprint

Dive into the research topics of 'Towards autonomous detection and tracking of electric towers for aerial power line inspection'. Together they form a unique fingerprint.

Cite this