Open Access Open Access  Restricted Access Subscription or Fee Access

A machine learning method for reducing the false positives in power line detection

Alexander Cerón, Flavio Prieto

Abstract



Most of the line detection methods used for power line detection are not able to differentiate the power lines from the different background lines present at a real scene in images taken from a top down view. For this reason a method for improving the power line detection is proposed. This method uses a combination of the conventional line detection methods and the HOG descriptor in a machine learning approach based on Support Vector Machine (SVM). This method is validated with real images taken from an Unmanned Aerial Vehicle (UAV). The experimental results show that our method of power line detection can reduce substantially the number of false positives in power line detection using images taken from a top down view.

Keywords


aerial image, machine learning, power line detection, UAV.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.