2014/06/01 by Fabio Remondino, Maria Grazia Spera, Erica Nocerino +2 · 2 citations
Earth and Planetary Sciences · Engineering · Environmental Science · #3D Surveying and Cultural Heritage #Remote Sensing and LiDAR Applications #Robotics and Sensor-Based Localization
paper · doi:10.1111/phor.12063
crossref issued 2014/06/01 · crossref published 2014/06/01 · crossref published-print 2014/06/01 · openalex publication_date 2014/06/01 · crossref published-online 2014/06/15 · crossref created 2014/06/16 · crossref deposited 2023/10/01 · openalex created_date 2025/10/10 · crossref indexed 2026/07/29 · openalex updated_date 2026/08/01
Abstract Image matching has a history of more than 50 years, with the first experiments performed with analogue procedures for cartographic and mapping purposes. The recent integration of computer vision algorithms and photogrammetric methods is leading to interesting procedures which have increasingly automated the entire image‐based 3D modelling process. Image matching is one of the key steps in 3D modelling and mapping. This paper presents a critical review and analysis of four dense image‐matching algorithms, available as open‐source and commercial software, for the generation of dense point clouds. The eight datasets employed include scenes recorded from terrestrial and aerial blocks, acquired with convergent and normal (parallel axes) images, and with different scales. Geometric analyses are reported in which the point clouds produced with each of the different algorithms are compared with one another and also to ground‐truth data.