12 September 2023 in ISPRS Journal of Photogrammetry and Remote Sensing
24 August 2024 in ISPRS Journal of Photogrammetry and Remote Sensing
10 September 2025 in ISPRS Journal of Photogrammetry and Remote Sensing
25 January 2024 in IEEE Transactions on Geoscience and Remote Sensing
Developments in three-dimensional real worlds promote the integration of geoinformation and building information models (BIM) known as GeoBIM. Light detection and ranging (LiDAR) integrated with global navigation satellite systems can provide geo-referenced information at the urban scale. However, constructing detailed urban GeoBIM poses challenges in terms of LiDAR data quality. BIM models designed from software are fine on geometrical information but are often located in local coordinates and limited at an individual building level. In this study, we propose a complementary strategy to solve the contradiction between fine and large-scale construction of GeoBIM in urban scenes. A deep learning framework and graph theory are combined for LiDAR point cloud segmentation. Then, a coarse-to-fine matching program is developed to integrate building point clouds with corresponding BIM models. Results show the overall segmentation accuracy of LiDAR datasets reaches up to 90%, and average positioning accuracies of building BIM models are 0.156 m, demonstrating the effectiveness of the method in segmentation and matching processes. This work offers a practical solution for rapid and accurate urban GeoBIM construction.
15 August 2019 in IEEE Geoscience and Remote Sensing Letters
Semantic labeling is a fundamental task that can provide useful semantics for many other 3-D processing tasks. To tackle the challenge of airborne laser scanning (ALS) point cloud classification, current state-of-the-art methods leverage the capabilities of deep learning. However, they are limited due to the weaknesses of the isolated use of individual representations of point clouds. To address this issue, this letter presents a novel network, VPNet, which ensembles voxel and pixel representation-based networks, to predict class probabilities for each light detection and ranging (LiDAR) point. A fully connected conditional random field-based global refinement is then performed over each point in the point cloud to produce a fine-grained classification result. On the ISPRS 3-D Semantic Labeling Contest, our solution sets a new state of the art by improving the highest average F1-score and the highest average per-class accuracy from 69.3% to 73.9%, and 69.0% to 74.9%, respectively. The overall accuracy of our approach is 84.0%.
8 March 2024 in Geo-spatial Information Science