Open Access Open Access  Restricted Access Subscription or Fee Access

Evaluation of 2D descriptors for 3D reconstruction of electrical infrastructure

Johan M. Agudelo, Alexander Ceron, Flavio Prieto

Abstract



Electric energy transport networks as an important part in the process of supply to the points of consumption must be monitored continuously, a task that demands large periods of time and high costs. With the investigation of automated inspection methods using unmanned aerial vehicle (UAV), is proposed to create a 3D model using the techniques of structure from motion (SFM). Currently there are different algorithms that detect and
describe keypoints as a first step in the reconstruction process. The most popular one is the descriptor SIFT (DoG); however, this is too computationally intensive to be used in three-dimensional reconstruction outdoor image. There are other feature descriptors such as ORB, BRISK, and FREAK that can accelerate the reconstruction process. This paper presents the evaluation of three-dimensional model of electrical infraestructure, using the different mentioned descriptors in combination whit the geometrical theory of structure from motion.

Keywords


2D feature descriptors, Structure from motion, point clouds, transmission tower, 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.