Abstract
Abstract. The integration of computer vision and photogrammetry to generate three-dimensional (3D) information from images has contributed to a wider use of point clouds, for mapping purposes. Large-scale topographic map production requires 3D data with high precision and accuracy to represent the real conditions of the earth surface. Apart from LiDAR point clouds, the image-based matching is also believed to have the ability to generate reliable and detailed point clouds from multiple-view images. In order to examine and analyze possible fusion of LiDAR and image-based matching for large-scale detailed mapping purposes, point clouds are generated by Semi Global Matching (SGM) and by Structure from Motion (SfM). In order to conduct comprehensive and fair comparison, this study uses aerial photos and LiDAR data that were acquired at the same time. Qualitative and quantitative assessments have been applied to evaluate LiDAR and image-matching point clouds data in terms of visualization, geometric accuracy, and classification result. The comparison results conclude that LiDAR is the best data for large-scale mapping.
Highlights
Faithful 3D reconstruction of urban environments represents a topic of great interest in photogrammetry, remote sensing and computer vision expertise, as it provides an important prerequisite for applications such as city modelling, scene interpretation or urban accessibility analysis (Weinmann and Jutzi, 2015)
This study investigates the characteristics of different point clouds and identifies the advantages and limitations to help
The Semi Global Matching (SGM) stereo method is based on the idea of pixel-wise matching cost of Mutual Information (MI) for compensating the radiometric differences of input images and uses a smoothness constraint
Summary
Faithful 3D reconstruction of urban environments represents a topic of great interest in photogrammetry, remote sensing and computer vision expertise, as it provides an important prerequisite for applications such as city modelling, scene interpretation or urban accessibility analysis (Weinmann and Jutzi, 2015). Progressive development in 3D point clouds creates various option to generate 3D point clouds data especially in the image-based matching construction This attracts the map producer to use these as an alternative to accelerate the base map provision in efficient and effective way, compliant with the map standard. LiDAR data acquired from the Airborne Laser Scanning (ALS) system has many benefits with its capability to penetrate the dense canopies and produce accurate geometric 3D position of huge point datasets. This method able to measure in the shadow areas where photogrammetric might difficult to observe. By using different point clouds that have no time gap, this study is expected to resume a comprehensive, fair, and reliable comparison based on qualitative and quantitative analysis
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
