scholarly journals SPECTRAL BAND SELECTION FOR URBAN MATERIAL CLASSIFICATION USING HYPERSPECTRAL LIBRARIES

2016 ◽  
Vol III-7 ◽  
pp. 33-40 ◽  
Author(s):  
A. Le Bris ◽  
N. Chehata ◽  
X. Briottet ◽  
N. Paparoditis
Keyword(s):  
Urban Areas ◽  
Large Scale ◽  
Near Infrared ◽  
Spectral Band ◽  
Band Selection ◽  
Svm Classifier ◽  
Stochastic Algorithm ◽  
Confidence Measure ◽  
Data Set ◽  
Material Classification

In urban areas, information concerning very high resolution land cover and especially material maps are necessary for several city modelling or monitoring applications. That is to say, knowledge concerning the roofing materials or the different kinds of ground areas is required. Airborne remote sensing techniques appear to be convenient for providing such information at a large scale. However, results obtained using most traditional processing methods based on usual red-green-blue-near infrared multispectral images remain limited for such applications. A possible way to improve classification results is to enhance the imagery spectral resolution using superspectral or hyperspectral sensors. In this study, it is intended to design a superspectral sensor dedicated to urban materials classification and this work particularly focused on the selection of the optimal spectral band subsets for such sensor. First, reflectance spectral signatures of urban materials were collected from 7 spectral libraires. Then, spectral optimization was performed using this data set. The band selection workflow included two steps, optimising first the number of spectral bands using an incremental method and then examining several possible optimised band subsets using a stochastic algorithm. The same wrapper relevance criterion relying on a confidence measure of Random Forests classifier was used at both steps. To cope with the limited number of available spectra for several classes, additional synthetic spectra were generated from the collection of reference spectra: intra-class variability was simulated by multiplying reference spectra by a random coefficient. At the end, selected band subsets were evaluated considering the classification quality reached using a rbf svm classifier. It was confirmed that a limited band subset was sufficient to classify common urban materials. The important contribution of bands from the Short Wave Infra-Red (SWIR) spectral domain (1000–2400 nm) to material classification was also shown.

scholarly journals SPECTRAL BAND SELECTION FOR URBAN MATERIAL CLASSIFICATION USING HYPERSPECTRAL LIBRARIES

2016 ◽  
Vol III-7 ◽  
pp. 33-40 ◽  
Author(s):  
A. Le Bris ◽  
N. Chehata ◽  
X. Briottet ◽  
N. Paparoditis
Keyword(s):  
Urban Areas ◽  
Large Scale ◽  
Near Infrared ◽  
Spectral Band ◽  
Band Selection ◽  
Svm Classifier ◽  
Stochastic Algorithm ◽  
Confidence Measure ◽  
Data Set ◽  
Material Classification

In urban areas, information concerning very high resolution land cover and especially material maps are necessary for several city modelling or monitoring applications. That is to say, knowledge concerning the roofing materials or the different kinds of ground areas is required. Airborne remote sensing techniques appear to be convenient for providing such information at a large scale. However, results obtained using most traditional processing methods based on usual red-green-blue-near infrared multispectral images remain limited for such applications. A possible way to improve classification results is to enhance the imagery spectral resolution using superspectral or hyperspectral sensors. In this study, it is intended to design a superspectral sensor dedicated to urban materials classification and this work particularly focused on the selection of the optimal spectral band subsets for such sensor. First, reflectance spectral signatures of urban materials were collected from 7 spectral libraires. Then, spectral optimization was performed using this data set. The band selection workflow included two steps, optimising first the number of spectral bands using an incremental method and then examining several possible optimised band subsets using a stochastic algorithm. The same wrapper relevance criterion relying on a confidence measure of Random Forests classifier was used at both steps. To cope with the limited number of available spectra for several classes, additional synthetic spectra were generated from the collection of reference spectra: intra-class variability was simulated by multiplying reference spectra by a random coefficient. At the end, selected band subsets were evaluated considering the classification quality reached using a rbf svm classifier. It was confirmed that a limited band subset was sufficient to classify common urban materials. The important contribution of bands from the Short Wave Infra-Red (SWIR) spectral domain (1000–2400 nm) to material classification was also shown.

Potential for Remote Sensing to Detect and Predict Herbicide Injury on Waterhyacinth (Eichhornia crassipes)

2010 ◽  
Vol 3 (4) ◽  
pp. 440-450 ◽  
Author(s):  
Wilfredo Robles ◽  
John D. Madsen ◽  
Ryan M. Wersal
Keyword(s):  
Large Scale ◽  
Rating Scale ◽  
Spectral Band ◽  
Simulated Data ◽  
Science Research ◽  
Mississippi State University ◽  
State University ◽  
Data Set ◽  
The Relationship ◽  
Reflectance Measurements

AbstractMany large-scale management programs directed toward the control of waterhyacinth rely on maintenance management with herbicides. Improving the implementation of these programs could be achieved through accurately detecting herbicide injury in order to evaluate efficacy. Mesocosm studies were conducted in the fall and summer of 2006 and 2007 at the R. R. Foil Plant Science Research Center, Mississippi State University, to detect and predict herbicide injury on waterhyacinth treated with four different rates of imazapyr and glyphosate. Herbicide rates corresponded to maximum recommended rates of 0.6 and 3.4 kg ae ha−1(0.5 and 3 lb ac−1) for imazapyr and glyphosate, respectively, and three rates lower than recommended maximum. Injury was visually estimated using a phytotoxicity rating scale, and reflectance measurements were collected using a handheld hyperspectral sensor. Reflectance measurements were then transformed into a Landsat 5 Thematic Mapper (TM) simulated data set to obtain pixel values for each spectral band. Statistical analyses were performed to determine if a correlation existed between bands 1, 2, 3, 4, 5, and 7 and phytotoxicity ratings. Simulated data from Landsat 5 TM indicated that band 4 was the most useful band to detect and predict herbicide injury of waterhyacinth by glyphosate and imazapyr. The relationship was negative because pixel values of band 4 decreased when herbicide injury increased. At 2 wk after treatment, the relationship between band 4 and phytotoxicity was best (r2of 0.75 and 0.90 for glyphosate and imazapyr, respectively), which served to predict herbicide injury in the following weeks.

scholarly journals The distance to M31 in the era of precision cosmology

2012 ◽  
Vol 8 (S289) ◽  
pp. 235-235
Author(s):  
David Valls-Gabaud
Keyword(s):  
Large Scale ◽  
Near Infrared ◽  
Hubble Space Telescope ◽  
Three Dimensional ◽  
Eclipsing Binaries ◽  
Wide Field ◽  
Acoustic Oscillations ◽  
Data Set ◽  
Red Giant ◽  
Precision Cosmology

AbstractWith the advent of precision cosmology, where distances out to redshifts z < 0.6 can be measured to 2% precision on the basis of baryon acoustic oscillations, it appears essential to establish an accurate calibration of the primary and secondary indicators of the cosmological distance ladder. Here we review recent attempts at anchoring M31 very accurately using three independent methods, and discuss in detail the systematics that affect each. Two double-lined eclipsing binaries yield a distance to M31 which is precise to 4%. New Bayesian methods have been applied to determine the tip of the red-giant branch, even in sparsely populated colour–magnitude diagrams, and provide unique insights in the context of a precise three-dimensional distribution of the satellites in the M31 system. Over 2500 Cepheids have been identified in large-scale multi-colour surveys of M31, the largest homogeneous data set thus far obtained for any galaxy. A subset of 68 with periods longer than 10 days have been observed with the Wide-Field Camera 3 on board the Hubble Space Telescope, yielding the tightest-ever near-infrared period–luminosity relation, with a mean distance error of 1%. Combined with other measurements, the distance to M31 is now measured with a precision of 3%. Forthcoming improvements, and their implications, are also discussed.

Dynamic multi-sensor platform for efficient 3D-digitalization of cities: part II

2021 ◽  
pp. 1-9
Author(s):  
Angel-Ivan Garcia-Moreno
Keyword(s):  
Urban Areas ◽  
Large Scale ◽  
Point Clouds ◽  
Urban Environments ◽  
Data Set ◽  
Urban Scenes ◽  
3D Data ◽  
Sensor Platform ◽  
Laser Scanners ◽  
Potential Applications

Abstract The digitization of geographic environments, such as cities and archaeological sites, is of priority interest to the scientific community due to its potential applications. But there are still several issues to address. There are various digitization strategies, which include terrestrial/ airborne platforms and composed of various sensors, among the most common, cameras and laser scanners. A comprehensive methodology is presented to reconstruct urban environments using a mobile land platform. All the implemented stages are described, which includes the acquisition, processing, and correlation of the data delivered by a Velodyne HDL-64E scanner, a spherical camera, GPS, and inertial systems. The process to merge several point clouds to build a large-scale map is described, as well as the generation of surfaces. Being able to render large urban areas using a low density of points but without losing the details of the structures within the urban scenes. The proposal is evaluated using several metrics, for example, Coverage and Root-Mean-Square-Error (RSME). The results are compared against 3 methodologies reported in the literature. Obtaining better results in the 2D/3D data fusion process and the generation of surfaces. The described method has a low RMSE (0.79) compared to the other methods and a runtime of approximately 40 seconds to process each data set (point cloud, panoramic image, and inertial data). In general, the proposed methodology shows a more homogeneous density distribution without losing the details, that is, it conserves the spatial distribution of the points, but with fewer data.

scholarly journals Carbon monoxide, methane and carbon dioxide columns retrieved from SCIAMACHY by WFM-DOAS: year 2003 initial data set

2005 ◽  
Vol 5 (12) ◽  
pp. 3313-3329 ◽  
Author(s):  
M. Buchwitz ◽  
R. de Beek ◽  
S. Noël ◽  
J. P. Burrows ◽  
H. Bovensmann ◽  
...  
Keyword(s):  
Carbon Dioxide ◽  
Carbon Monoxide ◽  
Large Scale ◽  
Near Infrared ◽  
Central Africa ◽  
Co2 Uptake ◽  
Data Set ◽  
Model Simulations ◽  
Mixing Ratios ◽  
Carbon Dioxide Co2

Abstract. The near-infrared nadir spectra measured by SCIAMACHY on-board ENVISAT contain information on the vertical columns of important atmospheric trace gases such as carbon monoxide (CO), methane (CH4), and carbon dioxide (CO2). The scientific algorithm WFM-DOAS has been used to retrieve this information. For CH4 and CO2 also column averaged mixing ratios (XCH4 and XCO2) have been determined by simultaneous measurements of the dry air mass. All available spectra of the year 2003 have been processed. We describe the algorithm versions used to generate the data (v0.4; for methane also v0.41) and show comparisons of monthly averaged data over land with global measurements (CO from MOPITT) and models (for CH4 and CO2). We show that elevated concentrations of CO resulting from biomass burning have been detected in reasonable agreement with MOPITT. The measured XCH4 is enhanced over India, south-east Asia, and central Africa in September/October 2003 in line with model simulations, where they result from surface sources of methane such as rice fields and wetlands. The CO2 measurements over the Northern Hemisphere show the lowest mixing ratios around July in qualitative agreement with model simulations indicating that the large scale pattern of CO2 uptake by the growing vegetation can be detected with SCIAMACHY. We also identified potential problems such as a too low inter-hemispheric gradient for CO, a time dependent bias of the methane columns on the order of a few percent, and a few percent too high CO2 over parts of the Sahara.

scholarly journals SEMCITY TOULOUSE: A BENCHMARK FOR BUILDING INSTANCE SEGMENTATION IN SATELLITE IMAGES

2020 ◽  
Vol V-5-2020 ◽  
pp. 109-116
Author(s):  
R. Roscher ◽  
M. Volpi ◽  
C. Mallet ◽  
L. Drees ◽  
J. D. Wegner
Keyword(s):  
Machine Learning ◽  
Urban Areas ◽  
Large Scale ◽  
Training Data ◽  
Adjacent Area ◽  
Learning Approaches ◽  
Test Bed ◽  
Learning Methods ◽  
Data Set ◽  
Instance Segmentation

Abstract. In order to reach the goal of reliably solving Earth monitoring tasks, automated and efficient machine learning methods are necessary for large-scale scene analysis and interpretation. A typical bottleneck of supervised learning approaches is the availability of accurate (manually) labeled training data, which is particularly important to train state-of-the-art (deep) learning methods. We present SemCity Toulouse, a publicly available, very high resolution, multi-spectral benchmark data set for training and evaluation of sophisticated machine learning models. The benchmark acts as test bed for single building instance segmentation which has been rarely considered before in densely built urban areas. Additional information is provided in the form of a multi-class semantic segmentation annotation covering the same area plus an adjacent area 3 times larger. The data set addresses interested researchers from various communities such as photogrammetry and remote sensing, but also computer vision and machine learning.

scholarly journals An Investigation of Spectral Band Selection for Hyperspectral LiDAR Technique

Electronics ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 148
Author(s):  
Hui Shao ◽  
Yuwei Chen ◽  
Wei Li ◽  
Changhui Jiang ◽  
Haohao Wu ◽  
...  
Keyword(s):  
Classification Accuracy ◽  
Spectral Band ◽  
Selection Method ◽  
Experimental Results ◽  
Laser Source ◽  
Band Selection ◽  
Support Vector ◽  
Svm Classifier ◽  
Feature Parameters ◽  
Spectral Bands

Hyperspectral LiDAR (HSL) has been widely discussed in recent years, which attracts increasing attention of the researchers in the field of electronic information technology. With the application of supercontinuum laser source, it is now possible to develop an HSL system, which can collect spectral and spatial information of targets simultaneously. Meanwhile, eye-safety and miniature HSL device with multiple spectral bands are given more priorities in on-site applications. In this paper, we tempt to investigate how to select spectral bands with a selection method. The proposed method consists of three steps: first, the variances among the classes based on hyperspectral feature parameters, termed inter-class variances, are calculated; second, the channels are sorted based on corresponding variances in descending order, and those with the two highest values are adopted as the initial input of classification; finally, the channels are selected successively from the rest of the sorted sequence until the classification accuracy reaches 100%. To test the performance of the proposed method, we collect 91/71-channel hyperspectral measurements of four different categories of materials with 5 nm spectral resolution using an acousto-optic tunable filter (AOTF) based HSL. Experimental results demonstrate that the proposed method could achieve higher classification accuracy than a random band selection method with different classifiers (naïve Bayes (NB) and support vector machine (SVM)) regardless of classification feature parameters (echo maximum and reflectance). To reach 100% accuracy, it demands 8–9 channels on average by echo maximum and 4–5 channels on average by reflectance based on NB classifier; these figures are 3–4 by echo maximum and 2–3 by reflectance with SVM classifier. The proposed method can complete classification task much faster than the random selection method. We further confirm the specific channels for the classification of different materials, and find that the optimal channels vary with different materials. The experimental results prove that the optimal band selection of HSL system for classification is reliable.

Do Smart Cities Invest in Smarter Policies? Learning From the Past, Planning for the Future

2016 ◽  
Vol 34 (6) ◽  
pp. 657-672 ◽  
Author(s):  
Andrea Caragliu ◽  
Chiara F. Del Bo
Keyword(s):  
Smart City ◽  
Urban Areas ◽  
Large Scale ◽  
Smart Cities ◽  
Empirical Relationship ◽  
Data Set ◽  
Empirical Results ◽  
Real Effects ◽  
Definition Of ◽  
The Relationship

Research on Smart Cities has come of age. Intense discussion on this topic has been ongoing for years, and the academic prominence of this concept has also engendered several policy initiatives inspired by this label at different administrative levels. However, to date, no large-scale evaluation of the relationship between urban smartness and smart urban policies has been attempted. This article aims at filling this gap. By building on a solid definition of Smart Cities, the article tests the empirical relationship between urban smartness and the intensity of Smart City policies. A novel data set on four different types of policies and smart urban characteristics is assembled for 314 European Union cities. Empirical results suggest that Smart City policies are more likely to be designed and implemented in cities that are already endowed with smart characteristics. Our findings also point to a higher probability that Smart City policies are implemented in denser and wealthier urban areas. These empirical results call for further research on the real effects of actual implemented Smart City policies, with the aim to verify the potential of this policy concept as an overall urban development model encompassing the main drivers of endogenous urban growth.

Machine Learning Verdict of EEG Signals in Brain Computer Interface

2018 ◽  
pp. 429-441
Author(s):  
M. Jeyanthi ◽  
C. Velayutham
Keyword(s):  
Nearest Neighbor ◽  
Technology Development ◽  
Vital Role ◽  
Svm Classifier ◽  
K Nearest Neighbor ◽  
Data Mining Technique ◽  
Data Set ◽  
Eeg Data ◽  
Irrelevant Attributes

In Science and Technology Development BCI plays a vital role in the field of Research. Classification is a data mining technique used to predict group membership for data instances. Analyses of BCI data are challenging because feature extraction and classification of these data are more difficult as compared with those applied to raw data. In this paper, We extracted features using statistical Haralick features from the raw EEG data . Then the features are Normalized, Binning is used to improve the accuracy of the predictive models by reducing noise and eliminate some irrelevant attributes and then the classification is performed using different classification techniques such as Naïve Bayes, k-nearest neighbor classifier, SVM classifier using BCI dataset. Finally we propose the SVM classification algorithm for the BCI data set.

Sign in / Sign up

Export Citation Format

Share Document