Abstract : We propose a multiscale extension of a well-known line segment detector, LSD. We show that its multiscale nature makes it much less susceptible to over-segmentation and more robust to low contrast and less sensitive to noise, while keeping the parameter-less advantage of LSD and still being fast. We also present here a dense gradient filter that disregards regions in which lines are likely to be irrelevant. As it reduces line mismatches, this filter improves the robustness of the application to structure-from-motion. It also yields a faster detection.
https://hal-enpc.archives-ouvertes.fr/hal-01571615
Contributeur : Pascal Monasse <>
Soumis le : jeudi 3 août 2017 - 10:11:49 Dernière modification le : mercredi 3 février 2021 - 07:54:27
Yohann Salaün, Renaud Marlet, Pascal Monasse. The Multiscale Line Segment Detector. 1st Workshop on Reproducible Research in Pattern Recognition, Dec 2016, Cancun, Mexico. pp.167 - 178, ⟨10.1007/978-3-319-56414-2_12⟩. ⟨hal-01571615⟩