Abstract
This research is concerned with a methodology for automated generation of polyhedral building models for complex structures, whose rooftops are bounded by straight lines. The process starts by utilizing LiDAR data for building hypothesis generation and derivation of individual planar patches constituting building rooftops. Initial boundaries of these patches are then refined through the integration of LiDAR and photogrammetric data and hierarchical processing of the planar patches. Building models for complex structures are finally produced using the refined boundaries. The performance of the developed methodology is evaluated through qualitative and quantitative analysis of the generated building models from real data.
Highlights
Nowadays, there are increasing demands for up-to-date three-dimensional building models in various applications such as urban design and planning, 3D city modeling, disaster management, realestate industry, and military training
This paper proposes a new methodology for automated Digital Building Model (DBM) generation while overcoming the problems in the previous research
The reported planimetric mean, standard deviation, and Root Mean Squared Error (RMSE) values in the third column are quite close to the results provided by the two operators, which indicates very high accuracy of the derived coordinates
Summary
There are increasing demands for up-to-date three-dimensional building models in various applications such as urban design and planning, 3D city modeling, disaster management, realestate industry, and military training. Several researchers have focused on the integration of LiDAR data and aerial imagery to acquire a higher level of automation and more reliable DBM [9,16,17,18,19,20]. The initial building models are refined by integrating LiDAR data with imagery These approaches are limited to buildings with either simple or pre-defined shapes. In [20], coarse building boundaries from LiDAR data with the assistance of color segmentation in a single aerial image were derived. Other approaches have utilized linear features derived from only a single image without taking the advantage of available stereo-imagery and the incorporated LiDAR data as a constraint.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have