In this paper, we present an image based plane extractionmethod well suited for real-time operations. Our approach exploits theassumption that the surrounding scene is mainly composed by planesdisposed in known directions. Planes are detected from a single imageexploiting a voting scheme that takes into account the vanishing lines.Then, candidate planes are validated and merged using a region grow-ing based approach to detect in real-time planes inside an unknown in-door environment. Using the related plane homographies is possible toremove the perspective distortion, enabling standard place recognitionalgorithms to work in an invariant point of view setup. Quantitative Ex-periments performed with real world images show the effectiveness of ourapproach compared with a very popular method.
Plane extraction for indoor place recognition
BLOISI, Domenico Daniele;
2015-01-01
Abstract
In this paper, we present an image based plane extractionmethod well suited for real-time operations. Our approach exploits theassumption that the surrounding scene is mainly composed by planesdisposed in known directions. Planes are detected from a single imageexploiting a voting scheme that takes into account the vanishing lines.Then, candidate planes are validated and merged using a region grow-ing based approach to detect in real-time planes inside an unknown in-door environment. Using the related plane homographies is possible toremove the perspective distortion, enabling standard place recognitionalgorithms to work in an invariant point of view setup. Quantitative Ex-periments performed with real world images show the effectiveness of ourapproach compared with a very popular method.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
