D-LSD: A Distorted Line Segment Detector for Calibrated Images

Autor:	Francisco-Angel Moreno, David Zuñiga-Noël, Javier Gonzalez-Jimenez
Rok vydání:	2021
Předmět:	business.industry Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Regular polygon Real image Line segment Rectification Line (geometry) Computer vision Image rectification Artificial intelligence Omnidirectional antenna business Projection (set theory)
Zdroj:	Computer Analysis of Images and Patterns ISBN: 9783030891305 CAIP (2)
DOI:	10.1007/978-3-030-89131-2_39
Popis:	In this paper, we present an algorithm for the detection of line segments directly on the original, distorted images captured by calibrated wide-angle, fisheye and omnidirectional cameras. Distorted line segments are detected as convex polygonal chains of connected straight lines and then validated as the projection of 3D lines. This last validation step is our main contribution, which is formulated in a generic way in order to allow the detection of line segments from calibrated central projection vision systems and without requiring the rectification of the whole image. We evaluate our method with real images from a publicly available dataset and compare it with state-of-the-art alternatives, achieving comparable line detection performance without requiring image rectification. Additionally, we provide an open source reference implementation.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::67b1d02be400411f73a768143f4c59b2 https://doi.org/10.1007/978-3-030-89131-2_39 Zobrazit plný text záznamu