Dyad Deep Learning-Based Geometry and Color Attribute Codecs for 3D Airborne LiDAR Point Clouds

2022 ◽  
pp. 383-412
Author(s):  
A. Christoper Tamilmathi ◽  
P. L. Chithra
Keyword(s):  
Deep Learning ◽  
Point Clouds ◽  
Airborne Lidar ◽  
Color Attribute

scholarly journals QUALITY IMPROVEMENT FOR AIRBORNE LIDAR DATA FILTERING BASED ON DEEP LEARNING METHOD

2020 ◽  
Vol XLIII-B2-2020 ◽  
pp. 355-360
Author(s):  
T. Yotsumata ◽  
M. Sakamoto ◽  
T. Satoh
Keyword(s):  
Deep Learning ◽  
Ground Surface ◽  
Point Clouds ◽  
Airborne Lidar ◽  
Baseline Method ◽  
Classification Result ◽  
Multiple Networks ◽  
The Individual ◽  
Airborne Lidar Data

Abstract. In this paper, we discuss how to improve the quality of classification results when deep learning is applied for the filtering of airborne LiDAR point cloud. We introduce the baseline method which utilizes convolutional neural network (CNN) based on voxelization, and then we propose three methods to improve the quality of classification result. The first method is data pre-processing that aims to exclude data in advance that is clearly not on the ground surface in order to efficiently extract the ground surface data. Data pre-processing can greatly reduce the number of target points and the subsequent processing can be performed efficiently. It also has the effect of preventing noise-like points floating in the air from being misclassified as the ground surface, as compared to the case without pre-processing. The second method is changing the network structure. In recent years, various networks have been proposed for classifying point clouds. In our study, the baseline is using very simple networks. In order to improve the classification result of the baseline method, the layer depth and the range size of convolution are changed, and we investigated about the improvements of the results. The current discussion can be used as a guidance when considering new networks. The third method is the integration of classification results from multiple networks. We integrated individual results from multiple networks with varying layer depths and convolution sizes, starting with the baseline, and investigated whether the results improved. We observed that even if the individual results were similar, the classification results can be improved by integrating the results.

scholarly journals GROUND POINT FILTERING FROM AIRBORNE LIDAR POINT CLOUDS USING DEEP LEARNING: A PRELIMINARY STUDY

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 1559-1565 ◽  
Author(s):  
E. Janssens-Coron ◽  
E. Guilbert
Keyword(s):  
Deep Learning ◽  
Point Clouds ◽  
Airborne Lidar ◽  
Lidar Data ◽  
Learning Approach ◽  
Preliminary Results ◽  
Ground Point ◽  
Preliminary Study ◽  
Airborne Lidar Data ◽  
Made In

<p><strong>Abstract.</strong> Airborne lidar data is commonly used to generate point clouds over large areas. These points can be classified into different categories such as ground, building, vegetation, etc. The first step for this is to separate ground points from non-ground points. Existing methods rely mainly on TIN densification but there performance varies with the type of terrain and relies on the user’s experience who adjusts parameters accordingly. An alternative may be on the use of a deep learning approach that would limit user’s intervention. Hence, in this paper, we assess a deep learning architecture, PointNet, that applies directly to point clouds. Our preliminary results show mitigating classification rates and further investigation is required to properly train the system and improve the robustness, showing issues with the choices we made in the preprocessing. Nonetheless, our analysis suggests that it is necessary to enrich the architecture of the network to integrate the notion of neighbourhood at different scales in order to increase the accuracy and the robustness of the treatment as well as its capacity to treat data from different geographical contexts.</p>

Deep Learning-Based Classification of Large-Scale Airborne LiDAR Point Cloud

2021 ◽  
pp. 1-15
Author(s):  
Mathieu Turgeon-Pelchat ◽  
Samuel Foucher ◽  
Yacine Bouroubi
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Large Scale ◽  
Airborne Lidar

scholarly journals Terrestrial Laser Scanning for Vegetation Analyses with a Special Focus on Savannas

2021 ◽  
Vol 13 (3) ◽  
pp. 507
Author(s):  
Tasiyiwa Priscilla Muumbe ◽  
Jussi Baade ◽  
Jenia Singh ◽  
Christiane Schmullius ◽  
Christian Thau
Keyword(s):  
Remote Sensing ◽  
Vegetation Structure ◽  
Laser Scanning ◽  
Spatial Scales ◽  
Terrestrial Laser Scanning ◽  
Point Clouds ◽  
Parameter Extraction ◽  
Airborne Lidar ◽  
Special Focus ◽  
Vegetation Parameter

Savannas are heterogeneous ecosystems, composed of varied spatial combinations and proportions of woody and herbaceous vegetation. Most field-based inventory and remote sensing methods fail to account for the lower stratum vegetation (i.e., shrubs and grasses), and are thus underrepresenting the carbon storage potential of savanna ecosystems. For detailed analyses at the local scale, Terrestrial Laser Scanning (TLS) has proven to be a promising remote sensing technology over the past decade. Accordingly, several review articles already exist on the use of TLS for characterizing 3D vegetation structure. However, a gap exists on the spatial concentrations of TLS studies according to biome for accurate vegetation structure estimation. A comprehensive review was conducted through a meta-analysis of 113 relevant research articles using 18 attributes. The review covered a range of aspects, including the global distribution of TLS studies, parameters retrieved from TLS point clouds and retrieval methods. The review also examined the relationship between the TLS retrieval method and the overall accuracy in parameter extraction. To date, TLS has mainly been used to characterize vegetation in temperate, boreal/taiga and tropical forests, with only little emphasis on savannas. TLS studies in the savanna focused on the extraction of very few vegetation parameters (e.g., DBH and height) and did not consider the shrub contribution to the overall Above Ground Biomass (AGB). Future work should therefore focus on developing new and adjusting existing algorithms for vegetation parameter extraction in the savanna biome, improving predictive AGB models through 3D reconstructions of savanna trees and shrubs as well as quantifying AGB change through the application of multi-temporal TLS. The integration of data from various sources and platforms e.g., TLS with airborne LiDAR is recommended for improved vegetation parameter extraction (including AGB) at larger spatial scales. The review highlights the huge potential of TLS for accurate savanna vegetation extraction by discussing TLS opportunities, challenges and potential future research in the savanna biome.

scholarly journals Cloth simulation-based construction of pit-free canopy height models from airborne LiDAR data

2020 ◽  
Vol 7 (1) ◽  
Author(s):  
Wuming Zhang ◽  
Shangshu Cai ◽  
Xinlian Liang ◽  
Jie Shao ◽  
Ronghai Hu ◽  
...  
Keyword(s):  
Tree Height ◽  
Point Clouds ◽  
Airborne Lidar ◽  
Canopy Height ◽  
Lidar Data ◽  
Cloth Simulation ◽  
Simulation Based ◽  
Maximum Tree Height ◽  
Airborne Lidar Data ◽  
Better Than

Abstract Background The universal occurrence of randomly distributed dark holes (i.e., data pits appearing within the tree crown) in LiDAR-derived canopy height models (CHMs) negatively affects the accuracy of extracted forest inventory parameters. Methods We develop an algorithm based on cloth simulation for constructing a pit-free CHM. Results The proposed algorithm effectively fills data pits of various sizes whilst preserving canopy details. Our pit-free CHMs derived from point clouds at different proportions of data pits are remarkably better than those constructed using other algorithms, as evidenced by the lowest average root mean square error (0.4981 m) between the reference CHMs and the constructed pit-free CHMs. Moreover, our pit-free CHMs show the best performance overall in terms of maximum tree height estimation (average bias = 0.9674 m). Conclusion The proposed algorithm can be adopted when working with different quality LiDAR data and shows high potential in forestry applications.

scholarly journals An Approach to Map Visibility in the Built Environment From Airborne LiDAR Point Clouds

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 44150-44161
Author(s):  
Guan-Ting Zhang ◽  
Edward Verbree ◽  
Xiao-Jun Wang
Keyword(s):  
Built Environment ◽  
Point Clouds ◽  
Airborne Lidar

scholarly journals Multi-Dimensional Underwater Point Cloud Detection Based on Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 884
Author(s):  
Chia-Ming Tsai ◽  
Yi-Horng Lai ◽  
Yung-Da Sun ◽  
Yu-Jen Chung ◽  
Jau-Woei Perng
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Three Dimensional ◽  
Point Clouds ◽  
Training Data ◽  
Network Architectures ◽  
Point Cloud Data ◽  
Data Types ◽  
Raw Data ◽  
Cloud Data

Numerous sensors can obtain images or point cloud data on land, however, the rapid attenuation of electromagnetic signals and the lack of light in water have been observed to restrict sensing functions. This study expands the utilization of two- and three-dimensional detection technologies in underwater applications to detect abandoned tires. A three-dimensional acoustic sensor, the BV5000, is used in this study to collect underwater point cloud data. Some pre-processing steps are proposed to remove noise and the seabed from raw data. Point clouds are then processed to obtain two data types: a 2D image and a 3D point cloud. Deep learning methods with different dimensions are used to train the models. In the two-dimensional method, the point cloud is transferred into a bird’s eye view image. The Faster R-CNN and YOLOv3 network architectures are used to detect tires. Meanwhile, in the three-dimensional method, the point cloud associated with a tire is cut out from the raw data and is used as training data. The PointNet and PointConv network architectures are then used for tire classification. The results show that both approaches provide good accuracy.

Sign in / Sign up

Export Citation Format

Share Document