Building Footprint Extraction in Dense Area from LiDAR Data using Mask R-CNN

Mohamed, Sayed A.; Mahmoud, Amira S.; Moustafa, Marwa; Helmy, Ashraf K.; Nasr, Ayman H.

doi:10.14569/ijacsa.2022.0130643

Cited by 3 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparing our findings to LiDAR building extraction research [13,30], our study had 93.40% accuracy, 92.34% recall, and 92.72% F1. Point CNN retrieves features from point clouds without rasterization, which may explain this.…”

Section: Comparison Between Two Methodssupporting

confidence: 62%

See 1 more Smart Citation

A Performance Analysis of Point CNN and Mask R-CNN for Building Extraction from Multispectral LiDAR Data

Mandouh,

Ali,

Mohamed

et al. 2023

IJACSA

View full text Add to dashboard Cite

The extraction of buildings from multispectral Light Detection and Ranging (LiDAR) data holds significance in various domains such as urban planning, disaster response, and environmental monitoring. State-of-the-art deep learning models, including Point Convolutional Neural Network (Point CNN) and Mask Region-based Convolutional Neural Network (Mask R-CNN), have effectively addressed this particular task. Data and application characteristics affect model performance. This research compares multispectral LiDAR building extraction models, Point CNN and Mask R-CNN. Models are tested for accuracy, efficiency, and capacity to handle irregularly spaced point clouds using multispectral LiDAR data. Point CNN extracts buildings from multispectral LiDAR data more accurately and efficiently than Mask R-CNN. CNN-based point cloud feature extraction avoids preprocessing like voxelization, improving accuracy and processing speed over Mask R-CNN. CNNs can handle LiDAR point clouds with variable spacing. Mask R-CNN outperforms Point CNN in some cases. Mask R-CNN uses image-like data instead of point clouds, making it better at detecting and categorizing objects from different angles. The study emphasizes selecting the right deep learning model for building extraction from multispectral LiDAR data. Point CNN or Mask R-CNN for accurate building extraction depends on the application. For building extraction from multispectral LiDAR data, two approaches were compared utilizing precision, recall, and F1 score. The point-CNN model outperformed Mask R-CNN. The point-CNN model had 93.40% precision, 92.34% recall, and 92.72% F1 score. Mask R-CNN has moderate precision, recall, and F1.

show abstract

Section: Comparison Between Two Methodssupporting

confidence: 62%

“…Several studies have employed deep learning models to extract buildings from mono-wavelength LiDAR data in a raster format, as evidenced by the works of [3,[12][13][14][15]. In contrast, some researchers have studied the extraction of buildings from LiDAR data in the form of point clouds [11].…”

Section: Related Workmentioning

confidence: 99%

A Performance Analysis of Point CNN and Mask R-CNN for Building Extraction from Multispectral LiDAR Data

Mandouh,

Ali,

Mohamed

et al. 2023

IJACSA

View full text Add to dashboard Cite

show abstract

“…Buyukdemircioglu et al (2022) developed a DL-based approach using red-green-blue (RGB), true orthophotos and digital surface model data. Mohamed et al (2022) developed a Mask R-CNN (a region-based convolutional neural network, He et al, 2017) method for building footprint extraction in a dense urban area using LiDAR point clouds. Zeng et al (2013) pointed out that methods for building footprint extraction are not 100% successful, and it is almost impossible to reach that level, the reasons behind the deficiency are scene complexity, the complex architecture of the buildings, incomplete cue extraction, and sensor dependency.…”

Section: Introductionmentioning

confidence: 99%

Robust Techniques for Building Footprint Extraction in Aerial Laser Scanning 3d Point Clouds

Nurunnabi

Teferle²,

Balado³

et al. 2022

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. The building footprint is crucial for a volumetric 3D representation of a building that is applied in urban planning, 3D city modeling, cadastral and topographic map generation. Aerial laser scanning (ALS) has been recognized as the most suitable means of large-scale 3D point cloud data (PCD) acquisition. PCD can produce geometric detail of a scanned surface. However, it is almost impossible to get point clouds without noise and outliers. Besides, data incompleteness and occlusions are two common phenomena for PCD. Most of the existing methods for building footprint extraction employ classification, segmentation, voting techniques (e.g., Hough-Transform or RANSAC), or Principal Component Analysis (PCA) based methods. It is known that classical PCA is highly sensitive to outliers, even RANSAC which is known as a robust technique for shape detection is not free from outlier effects. This paper presents a novel algorithm that employs MCMD (maximum consistency within minimum distance), MSAC (a robust variant of RANSAC) and a robust regression to extract reliable building footprints in the presence of outliers, missing points and irregular data distributions. The algorithm is successfully demonstrated through two sets of ALS PCD.

show abstract

Automatic Building Extraction from Multispectral LiDAR Using Novel 3D Spatial Indices and Deep Learning Point CNN

Mandouh,

Ali,

Mohamed

et al. 2024

J Indian Soc Remote Sens

View full text Add to dashboard Cite

Building Footprint Extraction in Dense Area from LiDAR Data using Mask R-CNN

Cited by 3 publications

References 44 publications

A Performance Analysis of Point CNN and Mask R-CNN for Building Extraction from Multispectral LiDAR Data

A Performance Analysis of Point CNN and Mask R-CNN for Building Extraction from Multispectral LiDAR Data

Robust Techniques for Building Footprint Extraction in Aerial Laser Scanning 3d Point Clouds

Automatic Building Extraction from Multispectral LiDAR Using Novel 3D Spatial Indices and Deep Learning Point CNN

Contact Info

Product

Resources

About