scholarly journals Hyperspectral and LiDAR Data Fusion Classification Using Superpixel Segmentation-Based Local Pixel Neighborhood Preserving Embedding

2019 ◽  
Vol 11 (5) ◽  
pp. 550 ◽  
Author(s):  
Yunsong Li ◽  
Chiru Ge ◽  
Weiwei Sun ◽  
Jiangtao Peng ◽  
Qian Du ◽  
...  
Keyword(s):  
Experimental Data ◽  
Data Fusion ◽  
Experimental Results ◽  
New Method ◽  
Light Detection And Ranging ◽  
Actual Data ◽  
Lidar Data ◽  
Light Detection ◽  
Superpixel Segmentation ◽  
Open Standard

A new method of superpixel segmentation-based local pixel neighborhood preserving embedding (SSLPNPE) is proposed for the fusion of hyperspectral and light detection and ranging (LiDAR) data based on the extinction profiles (EPs), superpixel segmentation and local pixel neighborhood preserving embedding (LPNPE). A new workflow is proposed to calibrate the Goddard’s LiDAR, hyperspectral and thermal (G-LiHT) data, which allows our method to be applied to actual data. Specifically, EP features are extracted from both sources. Then, the derived features of each source are fused by the SSLPNPE. Using the labeled samples, the final label assignment is produced by a classifier. For the open standard experimental data and the actual data, experimental results prove that the proposed method is fast and effective in hyperspectral and LiDAR data fusion.

Filtering LiDAR Data Using Binary Quadric Trend Surface and Morphological Approaches

2012 ◽  
Vol 594-597 ◽  
pp. 2361-2366 ◽  
Author(s):  
Feng Li ◽  
Xi Min Cui ◽  
Ling Zhang ◽  
Shu Wei Shan ◽  
Kun Lun Song
Keyword(s):  
Point Clouds ◽  
Experimental Results ◽  
Light Detection And Ranging ◽  
Lidar Data ◽  
Data Sets ◽  
Type I ◽  
Morphological Filter ◽  
Light Detection ◽  
Trend Surface ◽  
Sample Data

Automatically identifying and removing above-ground laser points from terrain surface is proved to be a challenging task for complicated and discontinuous scenarios. Eight methods have been developed and contrasted with each other for filtering LiDAR (Light Detection and Ranging) data. Only one approach is difficult to acquire high precisions for various landscapes. This paper presents a method filtering point clouds in which firstly a binary quadric trend surface is used to remove most non-terrain points by a defined height threshold and subsequently a progressive morphological filter further is employed to detect ground measurements. The experimental results demonstrate that this method yields less type I and total errors compared with other eight approaches based on ISPRS sample data sets.

scholarly journals A Novel Method for Feature Extraction and Classification for an Aerial Image and LiDAR Data with Genetic Algorithm

2012 ◽  
pp. 264-270
Author(s):  
Manjunath B. E ◽  
D. G. Anand ◽  
Mahant. G. Kattimani
Keyword(s):  
Feature Extraction ◽  
Light Detection And Ranging ◽  
Aerial Image ◽  
Lidar Data ◽  
Light Detection ◽  
Aerial Photos ◽  
The Earth ◽  
Digital Elevation ◽  
Land Surveying ◽  
Novel Method

Airborne Light Detection and Ranging (LiDAR) provides accurate height information for objects on the earth, which makes LiDAR become more and more popular in terrain and land surveying. In particular, LiDAR data offer vital and significant features for land-cover classification which is an important task in many application domains. Aerial photos with LiDAR data were processed with genetic algorithms not only for feature extraction but also for orthographical image. DSM provided by LiDAR reduced the amount of GCPs needed for the regular processing, thus the reason both efficiency and accuracy are highly improved. LiDAR is an acronym for Light Detection and Ranging, which is typically defined as an integration of three technologies into a single system, which is capable of acquiring a data to produce accurate Digital Elevation Models.

scholarly journals Tunnel Vision

2016 ◽  
Vol 4 (2) ◽  
pp. 192-204 ◽  
Author(s):  
Thomas G. Garrison ◽  
Dustin Richmond ◽  
Perry Naughton ◽  
Eric Lo ◽  
Sabrina Trinh ◽  
...  
Keyword(s):  
3D Models ◽  
Present Form ◽  
Light Detection And Ranging ◽  
Lidar Data ◽  
Technical Expertise ◽  
Ancient Maya ◽  
Light Detection ◽  
Terrestrial Lidar ◽  
Tunnel Vision ◽  
El Zotz

AbstractArchaeological tunneling is a standard excavation strategy in Mesoamerica. The ancient Maya built new structures atop older ones that were no longer deemed usable, whether for logistical or ideological reasons. This means that as archaeologists excavate horizontal tunnels into ancient Maya structures, they are essentially moving back in time. As earlier constructions are encountered, these tunnels may deviate in many directions in order to document architectural remains. The resultant excavations often become intricate labyrinths, extending dozens of meters. Traditional forms of archaeological documentation, such as photographs, plan views, and profile drawings, are limited in their ability to convey the complexity of tunnel excavations. Terrestrial Lidar (light detection and ranging) instruments are able to generate precise 3D models of tunnel excavations. This article presents the results of a model created with a Faro™ Focus 3D 120 Scanner of tunneling excavations at the site of El Zotz, Guatemala. The lidar data document the excavations inside a large mortuary pyramid, including intricately decorated architecture from an Early Classic (A.D. 300–600) platform buried within the present form of the structure. Increased collaboration between archaeologists and scholars with technical expertise maximizes the effectiveness of 3D models, as does presenting digital results in tandem with traditional forms of documentation.

Predicting forest stand variables from LiDAR data in the Great Lakes – St. Lawrence forest of Ontario

2008 ◽  
Vol 84 (6) ◽  
pp. 827-839 ◽  
Author(s):  
M. Woods ◽  
K. Lim ◽  
P. Treitz
Keyword(s):  
Great Lakes ◽  
Laser Scanning ◽  
Basal Area ◽  
Common Species ◽  
Forest Stand ◽  
Light Detection And Ranging ◽  
Lidar Data ◽  
Average Height ◽  
Light Detection ◽  
Forest Modelling

Models were developed to predict forest stand variables for common species of the Great Lakes – St. Lawrence forest of central Ontario, Canada from light detection and ranging (LiDAR) data. Stands that had undergone various ranges of partial harvesting or initial spacing treatments from multiple geographic sites were considered. A broad forest stratification was adopted and consisted of: (i) natural hardwoods; (ii) natural conifers; and (iii) plantation conifers. Stand top height (R2 = 0.96, 0.98, and 0.98); average height (R2 = 0.86, 0.76, and 0.98); basal area (R2 = 0.80, 0.80, and 0.85); volume (R2 = 0.89, 0.81, and 0.91); quadratic mean diameter (R2 = 0.80, 0.68, and 0.83); and density (R2 = 0.74, 0.71, and 0.73) were predicted from low density (i.e., 0.5 point m-2) LiDAR data for these 3 strata, respectively. Key words: light detection and ranging, LiDAR, airborne laser scanning, forest modelling, remote sensing, forest stand variables, Great Lakes – St. Lawrence forest

A New Method for Testing Formability in Sheet Metal Forming at Biaxial Tensile State

2014 ◽  
Vol 626 ◽  
pp. 275-280 ◽  
Author(s):  
Rong Shean Lee ◽  
Ta Wei Chien
Keyword(s):  
Experimental Data ◽  
Sheet Metal ◽  
Sheet Metal Forming ◽  
Metal Forming ◽  
Experimental Results ◽  
New Method ◽  
Dome Height ◽  
Uniaxial Tensile ◽  
Biaxial Tensile ◽  
Theoretical Predictions

This paper presents a new method concerning testing formability in sheet metal forming, especially focuses on clarifying the divergence of the experiment and a variety of theoretical predictions on biaxial tensile state. Up to now, there are many different fracture criteria appeared. All researches have presented their experimental data which could justify the criterion they presented. However, the experimental results and predictions in the first quadrant of the forming limit diagram (FLD) often diverge. Today, limiting dome height test is commonly used for FLD experiment, but specimens are rubbed and bended during the test, both influencing the experimental results.In order to provide for convincible experimental data, this paper presents a new experimental method to establish the first quadrant of FLD. In this method, cruciform biaxial tensile specimen and biaxial tensile apparatus have been developed. The proposed specimen has the feature of thickness reduction and contour design to ensure the fracture location is in the central region, so that accurate biaxial tensile state can be obtained. Through this method, there is an opportunity to obtain the whole FLD using uniaxial tensile testing machine, which is a low-cost alternative in compared with limiting dome height test. Besides, the experimental results can be utilized to clarify the divergence between various theoretical predictions and experimental results in the first quadrant of the FLD.

A WORD POSITION-RELATED LDA MODEL

2011 ◽  
Vol 25 (06) ◽  
pp. 909-925 ◽  
Author(s):  
LIDONG ZHAI ◽  
ZHAOYUN DING ◽  
YAN JIA ◽  
BIN ZHOU
Keyword(s):  
Experimental Data ◽  
Probabilistic Model ◽  
Latent Dirichlet Allocation ◽  
Semantic Information ◽  
Experimental Results ◽  
New Method ◽  
Word Position ◽  
Average Improvement ◽  
Latent Topics ◽  
Dirichlet Allocation

LDA (Latent Dirichlet Allocation) proposed by Blei is a generative probabilistic model of a corpus, where documents are represented as random mixtures over latent topics, and each topic is characterized by a distribution over words, but not the attributes of word positions of every document in the corpus. In this paper, a Word Position-Related LDA Model is proposed taking into account the attributes of word positions of every document in the corpus, where each word is characterized by a distribution over word positions. At the same time, the precision of the topic-word's interpretability is improved by integrating the distribution of the word-position and the appropriate word degree, taking into account the different word degree in the different word positions. Finally, a new method, a size-aware word intrusion method is proposed to improve the ability of the topic-word's interpretability. Experimental results on the NIPS corpus show that the Word Position-Related LDA Model can improve the precision of the topic-word's interpretability. And the average improvement of the precision in the topic-word's interpretability is about 9.67%. Also, the size-aware word intrusion method can interpret the topic-word's semantic information more comprehensively and more effectively through comparing the different experimental data.

scholarly journals Mapeamento das áreas de armazenamento de água em depressão, usando dados LIDAR: Estudo de caso avenida Caxangá

2021 ◽  
Vol 14 (1) ◽  
pp. 058
Author(s):  
Camila Gardenea de Almeida Bandim ◽  
Josiclêda Domiciano Galvíncio
Keyword(s):  
Water Storage ◽  
Light Detection And Ranging ◽  
Lidar Data ◽  
Urban Drainage ◽  
Lidar System ◽  
Light Detection ◽  
Urban Flood ◽  
Digital Elevation ◽  
Elevation Model

O objetivo deste estudo consiste em avaliar as áreas inundáveis em Recife, com especial atenção à avenida Caxangá.  Iniciando uma análise sobre a drenagem convencional utilizando a tecnologia LIDAR (Light Detection And Ranging). Os dados empregados neste trabalho foram captados pelo sistema LIDAR e possuem 50 cm de resolução, sendo um total de 12 quadrículas xyz para a constituição do mosaico Modelo Digital de Elevação (MDE) da avenida Caxangá, com destaque para as quadrículas 81_50-05 e 81_60-05, partindo dessas foram geradas as direções e acúmulos de fluxo. Os resultados obtidos enfatizam a alta resolução através da nítida visualização de elementos naturais e artificiais, e ainda o nivelamento do terreno. Em seguida, observa-se o acúmulo de fluxo que exibe as diferentes direções e acúmulos do escoamento superficial, ainda se percebe a influência na drenagem urbana das construções antrópicas e da vegetação em locais pontuais da avenida Caxangá. Em conclusão os dados do sistema LIDAR responderam positivamente, tanto na captação na modelagem do terreno e topografia artificial, como também para as gerações de direções e acúmulo de fluxos apresentando maiores valores para áreas depressivas naturais e antropizadas. Sendo destaque neste estudo as áreas antropizadas por provocarem problemas de desastres naturais. Conclui-se que as áreas antropizadas exercem um importante papel na drenagem urbana.  Mapping water storage areas in depression, using LIDAR data: Caxangá Avenida case study A B S T R A C TThe objective of this study is to evaluate the floodable areas in Recife, with special attention to Avenida Caxangá. Starting an analysis on conventional drainage using LIDAR (Light Detection And Ranging) technology. The data used in this work were captured by the LIDAR system and have 50 cm of resolution, with a total of 12 xyz squares for the constitution of the Digital Elevation Model (MDE) mosaic on Avenida Caxangá, with emphasis on the squares 81_50-05 and 81_60 -05, from these directions and flow accumulations were generated. The results obtained emphasize the high resolution through the clear visualization of natural and artificial elements, as well as the leveling of the terrain. Then, there is the accumulation of flow that shows the different directions and accumulations of runoff, the influence on the urban drainage of anthropic buildings and vegetation in specific places on Avenida Caxangá is still perceived. In conclusion, the data from the LIDAR system responded positively, both in capturing terrain modeling and artificial topography, as well as for generations of directions and accumulation of flows, presenting higher values for natural and anthropized depressive areas. Being highlighted in this study the areas anthropized because they cause problems of natural disasters. It is concluded that anthropized areas play an important role in urban drainage.Keywords: Geoprocessing. Remote sensing. Urbanization. Urban flood. drainage

Sign in / Sign up

Export Citation Format

Share Document