Building extraction from LiDAR data has been an active research area, but it is difficult to discriminate between buildings and vegetation in complex urban scenes. A building extraction method from LiDAR data based on minimum cut (min-cut) and improved post-processing is proposed. To discriminate building points on the intersecting roof planes from vegetation, a point feature based on the variance of normal vectors estimated via low-rank subspace clustering (LRSC) technique is proposed, and non-ground points are separated into two subsets based on min-cut after filtering. Then, the results of building extraction are refined via improved post-processing using restricted region growing and the constraints of height, the maximum intersection angle and consistency. The maximum intersection angle constraint removes large non-building point clusters with narrow width, such as greenbelt along streets. Contextual information and consistency constraint are both used to eliminate inhomogeneity. Experiments of seven datasets, including five datasets provided by the International Society for Photogrammetry and Remote Sensing (ISPRS), one dataset with high-density point data and one dataset with dense buildings, verify that most buildings, even with curved roofs, are successfully extracted by the proposed method, with over 94.1% completeness and a minimum 89.8% correctness at the per-area level. In addition, the proposed point feature significantly outperforms the comparison alternative and is less sensitive to feature threshold in complex scenes. Hence, the extracted building points can be used in various applications.
In Airborne Light Detection and Ranging (LiDAR) data acquisition practice, discrepancies exist between adjacent strips even though careful system calibrations have been performed. A strip adjustment method using planar features acquired by the Minimum Hausdorff Distance (MHD) is proposed to eliminate these discrepancies. First, semi-suppressed fuzzy C-means and restricted region growing algorithms are used to extract buildings. Second, a binary image is generated from the minimum bounding rectangle that covers overlapping regions. Then, connected components labeling algorithm is applied to process the binary image to extract individual buildings. After that, building matching is performed based on MHD. Third, a coarse-to-fine approach is used to segment building roof planes. Then, plane matching is conducted under the constraints of MHD and normal vectors similarity. The last step is the calculation of the parameters based on Euclidean distance minimization between matched planes. Two different types of datasets, one of which was acquired by a dual-channel LiDAR system Trimble AX80, were selected to verify the proposed method. Experimental results show that the corresponding planar features that meet adjustment requirements can be successfully detected without any manual operations or auxiliary data or transformation of raw data, while the discrepancies between strips can be effectively eliminated. Although adjustment results of the proposed method slightly outperform the comparison alternative, the proposed method also has the advantage of processing the adjustment in a more automatic manner than the comparison method.
In this paper, a novel framework for the automatic extraction of road footprints from airborne LiDAR point clouds in urban areas is proposed. The extraction process consisted of three phases: The first phase is to extract road points by using the deep learning model PointNet++, where the features of the input data include not only those selected from raw LiDAR points, such as 3D coordinate values, intensity, etc., but also the digital number (DN) of co-registered images and generated geometric features to describe a strip-like road. Then, the road points from PointNet++ were post-processed based on graph-cut and constrained triangulation irregular networks, where both the commission and omission errors were greatly reduced. Finally, collinearity and width similarity were proposed to estimate the connection probability of road segments, thereby improving the connectivity and completeness of the road network represented by centerlines. Experiments conducted on the Vaihingen data show that the proposed framework outperformed others in terms of completeness and correctness; in addition, some narrower residential streets with 2 m width, which have normally been neglected by previous studies, were extracted. The completeness and the correctness of the extracted road points were 84.7% and 79.7%, respectively, while the completeness and the correctness of the extracted centerlines were 97.0% and 86.3%, respectively.
Airborne Light Detection and Ranging (LiDAR) system and digital camera are usually integrated on a flight platform to obtain multi-source data. However, the photogrammetric system calibration is often independent of the LiDAR system and performed by the aerial triangulation method, which needs a test field with ground control points. In this paper, we present a method for the direct georeferencing of images collected by a digital camera integrated in an airborne LiDAR system by automatic boresight misalignments calibration with the auxiliary of point cloud. The method firstly uses an image matching to generate a tie point set. Space intersection is then performed to obtain the corresponding object coordinate values of the tie points, while the elevation calculated from the space intersection is replaced by the value from the LiDAR data, resulting in a new object point called Virtual Control Point (VCP). Because boresight misalignments exist, a distance between the tie point and the image point of VCP can be found by collinear equations in that image from which the tie point is selected. An iteration process is performed to minimize the distance with boresight corrections in each epoch, and it stops when the distance is smaller than a predefined threshold or the total number of epochs is reached. Two datasets from real projects were used to validate the proposed method and the experimental results show the effectiveness of the method by being evaluated both quantitatively and visually.
Airborne light detection and ranging (LiDAR) technology has been widely utilized for collecting three-dimensional (3D) point cloud data on forest scenes, enabling the generation of high-accuracy digital elevation models (DEMs) for the efficient investigation and management of forest resources. Point cloud filtering serves as the crucial initial step in DEM generation, directly influencing the accuracy of the resulting DEM. However, forest filtering presents challenges in dealing with sparse point clouds and selecting appropriate initial ground points. The introduction of full-waveform LiDAR data offers a potential solution to the problem of sparse point clouds. Additionally, advancements in multi-source data integration and machine learning algorithms have created new avenues that can address the issue of initial ground point selection. To tackle these challenges, this paper proposes a novel filtering method for forest scenes utilizing full-waveform LiDAR data and hyperspectral image data. The proposed method consists of two main steps. Firstly, we employ the improved dynamic graph convolutional neural network (IDGCNN) to extract initial ground points. In this step, we utilize three types of low-correlation features: LiDAR features, waveform features, and spectral features. To enhance its accuracy and adaptability, a self-attention module was incorporated into the DGCNN algorithm. Comparative experiments were conducted to evaluate the effectiveness of the algorithm, demonstrating that the IDGCNN algorithm achieves the highest classification accuracy with an overall accuracy (OA) value of 99.38% and a kappa coefficient of 95.95%. The second-best performer was the RandLA-net algorithm, achieving an OA value of 98.73% and a kappa coefficient of 91.68%. The second step involves refining the initial ground points using the cloth simulation filter (CSF) algorithm. By employing the CSF algorithm, non-ground points present in the initial ground points are effectively filtered out. To validate the efficacy of the proposed filtering method, we generated a DEM with a resolution of 0.5 using the ground points extracted in the first step, the refined ground points obtained with the combination of the first and second steps, and the ground points obtained directly using the CSF algorithm. A comparative analysis with 23 reference control points revealed the effectiveness of our proposed method, as evidenced by the median error of 0.41 m, maximum error of 0.75 m, and average error of 0.33 m.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.