Home // CSRF 2024, The First International Conference on Sustainable and Regenerative Farming // View article
Authors:
Daniel Diaz
Paula Gonzalez
Izar Azpiroz
Giovanni Paolini
Mikel Maiza
Keywords: Point Cloud Fusion; Digital Surface Model (DSM); Multi-Date Stereo Images; Terrain Representation.
Abstract:
This paper presents a novel methodology for generating high-quality Digital Surface Models (DSMs) through the fusion of point clouds obtained from multi-date stereo images. By applying a custom fusion algorithm to the point clouds generated by the Context-Aware Reconstruction of Scenes (CARS) software, the proposed approach enhances DSM quality in terms of completeness and error metrics compared to the original DSM. The fusion process effectively integrates multiple DSMs, resulting in a more comprehensive and accurate terrain representation. This method addresses challenges such as shadow occlusions and temporal variations, demonstrating significant improvements. The technique shows potential for applications in precision agriculture and other fields requiring detailed terrain models. Validation using the Intelligence Advanced Research Projects Activity (IARPA) challenge dataset highlights the method's robustness in mixed terrains, offering a notable increase in completeness and solving issues related to data gaps in shadowed areas.
Pages: 5 to 10
Copyright: Copyright (c) IARIA, 2024
Publication date: November 17, 2024
Published in: conference
ISBN: 978-1-68558-323-1
Location: Valencia, Spain
Dates: from November 17, 2024 to November 21, 2024