Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358950
Wenping Song, Yang Bai, Xiang Li, Shiqiang Tian, X. Qi
Launched on January 15, 2020, the Hongqi-1-H9 wide-range satellite, with a resolution of better than 1 meter and a swath width of 136 km, is the largest sub-meter level satellite in the world and the first ton-level commercial remote sensing satellite in China, which can acquire sub-meter image data of about 1,000km2 per second and realize the acquisition of full-coverage image information of more than 1000,000 km2. Based on the characteristics of the Hongqi-1-H9 satellite, this paper gives an experimental analysis and the experimental results reveal the high geometric positioning performance. In the study area, the Hongqi-1-H9 exhibits a good geometric positioning performance, with the positioning accuracy of 3.2448m in latitude direction, 1.6639m in longitude direction and 1.7466m in elevation direction when using 5 GPS points. Therefore, the Hongqi-1-H9 satellite can achieve high-precision positioning performance for the experimental area, and will be more widely used in many fields.
{"title":"Experimental Analysis of the Hongqi-1 H9 Satellite Imagery for Geometric Positioning","authors":"Wenping Song, Yang Bai, Xiang Li, Shiqiang Tian, X. Qi","doi":"10.1109/InGARSS48198.2020.9358950","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358950","url":null,"abstract":"Launched on January 15, 2020, the Hongqi-1-H9 wide-range satellite, with a resolution of better than 1 meter and a swath width of 136 km, is the largest sub-meter level satellite in the world and the first ton-level commercial remote sensing satellite in China, which can acquire sub-meter image data of about 1,000km2 per second and realize the acquisition of full-coverage image information of more than 1000,000 km2. Based on the characteristics of the Hongqi-1-H9 satellite, this paper gives an experimental analysis and the experimental results reveal the high geometric positioning performance. In the study area, the Hongqi-1-H9 exhibits a good geometric positioning performance, with the positioning accuracy of 3.2448m in latitude direction, 1.6639m in longitude direction and 1.7466m in elevation direction when using 5 GPS points. Therefore, the Hongqi-1-H9 satellite can achieve high-precision positioning performance for the experimental area, and will be more widely used in many fields.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"38 1","pages":"78-81"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74319355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358924
Swadhina Koley, J. C
The water footprint of a crop is defined as the total volume of water consumed for the production of the crop in the growing season. The total water footprint comprises of the three components, i.e. the rainwater (green water footprint), irrigated water (blue water footprint) and the polluted water (grey water footprint) usage for the production. This study discusses the potential of the remote sensing techniques for the assessment of the green and blue water footprint of rice crop with the help of high temporal resolution and real-time data, in the tropical region of Ranchi, Jharkhand. In this paper, the evapotranspiration (ET) and rainfall (RF) have been identified as the key parameters for the assessment of the water usage. The study uses MODIS Evapotranspiration data and CHIRPS rainfall data, along with CLIMWAT station data to estimate the green and blue component of the water usage.
{"title":"Estimation of the Green and Blue Water Footprint of Kharif Rice Using Remote Sensing Techniques: a Case Study of Ranchi","authors":"Swadhina Koley, J. C","doi":"10.1109/InGARSS48198.2020.9358924","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358924","url":null,"abstract":"The water footprint of a crop is defined as the total volume of water consumed for the production of the crop in the growing season. The total water footprint comprises of the three components, i.e. the rainwater (green water footprint), irrigated water (blue water footprint) and the polluted water (grey water footprint) usage for the production. This study discusses the potential of the remote sensing techniques for the assessment of the green and blue water footprint of rice crop with the help of high temporal resolution and real-time data, in the tropical region of Ranchi, Jharkhand. In this paper, the evapotranspiration (ET) and rainfall (RF) have been identified as the key parameters for the assessment of the water usage. The study uses MODIS Evapotranspiration data and CHIRPS rainfall data, along with CLIMWAT station data to estimate the green and blue component of the water usage.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"29 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83072974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358962
Paul Caesar M. Flores, F. Siringan
Understanding shoreline change due to engineering modifications and how it compares with the long-term trends is vital for future development plans. In this study, we focused on the Jaro Floodway, which was constructed in 2012 to mitigate the yearly floods experienced by Iloilo City. Shoreline positions were extracted from geometrically corrected historical maps (1947, 1955, and 1988) and Landsat images (1998, 2004, 2006, 2008, 2010, 2014, 2016, and 2018) for change analysis. Between 1947-1988, the coastline prograded by ~1 km due to channel avulsion most likely induced by fishpond construction at the river mouth. Between 1988-1998, erosion occurred likely due to the compounding effects of loss of mangrove cover and an increase in the number of typhoon events during the period. The majority of the coastline became relatively stable from 2004-2006. Progradation occurred at the mouth of Jaro River from 2006-2010. By the end of 2018, shoreline prograded by as much as 1.4 km. Rapid progradation is attributed to both large sediment input and the low accommodation space in the area of new discharge. The estimated volume of sediment deposited annually from 2010 is 4.11 x 105 m3, while the annual sediment input during the progradation phase between 1947-1988 is estimated at 2.70 x 104 m3. The shortened floodwater route likely contributed to the one order magnitude increase in sediment input but an increase of sediment yield in the upper stretches of Jaro River likely had a greater contribution.
{"title":"Shoreline Change in Response to the Construction of a Flood Canal in Jaro, Iloilo City, Philippines","authors":"Paul Caesar M. Flores, F. Siringan","doi":"10.1109/InGARSS48198.2020.9358962","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358962","url":null,"abstract":"Understanding shoreline change due to engineering modifications and how it compares with the long-term trends is vital for future development plans. In this study, we focused on the Jaro Floodway, which was constructed in 2012 to mitigate the yearly floods experienced by Iloilo City. Shoreline positions were extracted from geometrically corrected historical maps (1947, 1955, and 1988) and Landsat images (1998, 2004, 2006, 2008, 2010, 2014, 2016, and 2018) for change analysis. Between 1947-1988, the coastline prograded by ~1 km due to channel avulsion most likely induced by fishpond construction at the river mouth. Between 1988-1998, erosion occurred likely due to the compounding effects of loss of mangrove cover and an increase in the number of typhoon events during the period. The majority of the coastline became relatively stable from 2004-2006. Progradation occurred at the mouth of Jaro River from 2006-2010. By the end of 2018, shoreline prograded by as much as 1.4 km. Rapid progradation is attributed to both large sediment input and the low accommodation space in the area of new discharge. The estimated volume of sediment deposited annually from 2010 is 4.11 x 105 m3, while the annual sediment input during the progradation phase between 1947-1988 is estimated at 2.70 x 104 m3. The shortened floodwater route likely contributed to the one order magnitude increase in sediment input but an increase of sediment yield in the upper stretches of Jaro River likely had a greater contribution.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"30 1","pages":"134-137"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82479236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358947
Dinesh Sathyanarayanan, D. Anudeep, C. A. Keshav Das, Sanat Bhanadarkar, U. D, R. Hebbar, K. Raj
In general, a visual interpretation technique is adopted for mapping of Land Use / Land Cover (LULC) using temporal satellite data. Although highly accurate, the process is tedious, time consuming and requires a significant amount of domain knowledge. This limitation introduces a scope for partial automation to reduce manual effort involved in interpretation, while maintaining baseline accuracy. The research explores a novel multi-class training approach using a Deep Learning (DL) model to generate major LULC classes. Five spectral bands, namely Blue, Green, Red, Near-Infrared (NIR) and Short wave Infrared (SWIR) from the Sentinel-2A satellite, covering Mandya, Karnataka, India was used to train the model. An existing LULC map of the region was used as an input for automatically generating labeled training samples and a modified SegNet was implemented for classification. Four major LULC classes of interest - water bodies, forest lands, croplands, built-up were classified with an average F1 score of 0.84. The trained model applied to other regions has shown encouraging results which makes this an effective method to explore the generation of LULC maps.
{"title":"A Multiclass Deep Learning Approach for LULC Classification of Multispectral Satellite Images","authors":"Dinesh Sathyanarayanan, D. Anudeep, C. A. Keshav Das, Sanat Bhanadarkar, U. D, R. Hebbar, K. Raj","doi":"10.1109/InGARSS48198.2020.9358947","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358947","url":null,"abstract":"In general, a visual interpretation technique is adopted for mapping of Land Use / Land Cover (LULC) using temporal satellite data. Although highly accurate, the process is tedious, time consuming and requires a significant amount of domain knowledge. This limitation introduces a scope for partial automation to reduce manual effort involved in interpretation, while maintaining baseline accuracy. The research explores a novel multi-class training approach using a Deep Learning (DL) model to generate major LULC classes. Five spectral bands, namely Blue, Green, Red, Near-Infrared (NIR) and Short wave Infrared (SWIR) from the Sentinel-2A satellite, covering Mandya, Karnataka, India was used to train the model. An existing LULC map of the region was used as an input for automatically generating labeled training samples and a modified SegNet was implemented for classification. Four major LULC classes of interest - water bodies, forest lands, croplands, built-up were classified with an average F1 score of 0.84. The trained model applied to other regions has shown encouraging results which makes this an effective method to explore the generation of LULC maps.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"77 1","pages":"102-105"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91242796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358953
Swastik Bhattacharya, D. Desai
The World Health Organization (WHO) declared the outbreak of the COVID-19 virus as a pandemic on 11 March 2020. As a preventive measure to arrest its spread, the Government of India implemented one of the largest lockdowns in human history on 25 March 2020. This led to closure of a large number of industries and restriction on people movement. Such a measure reduced the concentration of major pollutants in the atmosphere. Present study quantified the impact of change in particulate air pollutants in terms of aerosol optical depth (AOD) on incident light energy over the Indian Sub-continent using satellite imaging observations at 10:30 AM and a radiation transfer algorithm. Change in incident photosynthetically active radiation (IPAR) was used to denote change in level of light energy before and after the commencement of the lockdown. A net increase in IPAR up to 25% was estimated due to lockdown.
{"title":"Change Detection of Incident Light Over Indian Sub-Continent During Covid-19 Lockdown Using Satellite Imaging Data","authors":"Swastik Bhattacharya, D. Desai","doi":"10.1109/InGARSS48198.2020.9358953","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358953","url":null,"abstract":"The World Health Organization (WHO) declared the outbreak of the COVID-19 virus as a pandemic on 11 March 2020. As a preventive measure to arrest its spread, the Government of India implemented one of the largest lockdowns in human history on 25 March 2020. This led to closure of a large number of industries and restriction on people movement. Such a measure reduced the concentration of major pollutants in the atmosphere. Present study quantified the impact of change in particulate air pollutants in terms of aerosol optical depth (AOD) on incident light energy over the Indian Sub-continent using satellite imaging observations at 10:30 AM and a radiation transfer algorithm. Change in incident photosynthetically active radiation (IPAR) was used to denote change in level of light energy before and after the commencement of the lockdown. A net increase in IPAR up to 25% was estimated due to lockdown.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"149 1","pages":"162-165"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82048911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358932
Yash Dahima, Tejas Turakhia, A. Chhabra, Rajesh C. Iyer
This study has been carried out to understand the effect of aerosols on the urban climate of Gandhinagar. As a part of it, we have carried out measurements of Aerosol Optical Depth at selected locations of Gandhinagar for winter, summer and post-monsoon seasons of 2017 and 2018, respectively. An analysis of short-wave Aerosol Direct Radiative Forcing (ADRF) is done using these measurements as inputs to the SBDART model. The hourly averaged ADRF of the atmosphere 73.6 Wm−2 in 2017 and 69.6 Wm−2 in 2018, indicates that a high amount of energy was trapped within the atmosphere by aerosols which results in the heating of the atmosphere. This model estimation indicates that atmospheric radiative forcing occurs in all the seasons, but much more strongly during the summer season. A large difference between SURF and TOA forcing in the summer season indicates large absorption of the radiant energy (~95.5 Wm−2) within the atmosphere. Correlation between AOD and aerosol radiative forcing has also been calculated as an attempt is made to estimate the dependency of ADRF on a very import optical property of aerosols.
{"title":"Estimation of Aerosol Radiative Forcing Over an Urban Environment Using Radiative Transfer Model","authors":"Yash Dahima, Tejas Turakhia, A. Chhabra, Rajesh C. Iyer","doi":"10.1109/InGARSS48198.2020.9358932","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358932","url":null,"abstract":"This study has been carried out to understand the effect of aerosols on the urban climate of Gandhinagar. As a part of it, we have carried out measurements of Aerosol Optical Depth at selected locations of Gandhinagar for winter, summer and post-monsoon seasons of 2017 and 2018, respectively. An analysis of short-wave Aerosol Direct Radiative Forcing (ADRF) is done using these measurements as inputs to the SBDART model. The hourly averaged ADRF of the atmosphere 73.6 Wm−2 in 2017 and 69.6 Wm−2 in 2018, indicates that a high amount of energy was trapped within the atmosphere by aerosols which results in the heating of the atmosphere. This model estimation indicates that atmospheric radiative forcing occurs in all the seasons, but much more strongly during the summer season. A large difference between SURF and TOA forcing in the summer season indicates large absorption of the radiant energy (~95.5 Wm−2) within the atmosphere. Correlation between AOD and aerosol radiative forcing has also been calculated as an attempt is made to estimate the dependency of ADRF on a very import optical property of aerosols.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"22 1","pages":"185-188"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91531705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358966
Varsha Kshirsagar-Deshpande, T. Patel, Ali Abbas, Khushbhu Bhatt, R. Bhalerao, Jiten Shah
In the proposed method, an innovative image processing technique for vehicle tracking at a roundabout is described. Background subtraction is applied to get the objects (vehicles) in the foreground. The objects are thus obtained and tracked using morphological operations and object properties. In the video stream, tracking is established by tracing the center of the target object. In present case,four different directions of incoming traffic are considered and four vehicle classes are defined. Implementation of above mentioned method achieved promising result of accuracy greater than 90 % for moderate traffic conditions where occlusion is not an issue.
{"title":"Vehicle Tracking Using Morphological Properties for Traffic Modelling","authors":"Varsha Kshirsagar-Deshpande, T. Patel, Ali Abbas, Khushbhu Bhatt, R. Bhalerao, Jiten Shah","doi":"10.1109/InGARSS48198.2020.9358966","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358966","url":null,"abstract":"In the proposed method, an innovative image processing technique for vehicle tracking at a roundabout is described. Background subtraction is applied to get the objects (vehicles) in the foreground. The objects are thus obtained and tracked using morphological operations and object properties. In the video stream, tracking is established by tracing the center of the target object. In present case,four different directions of incoming traffic are considered and four vehicle classes are defined. Implementation of above mentioned method achieved promising result of accuracy greater than 90 % for moderate traffic conditions where occlusion is not an issue.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"10 1","pages":"98-101"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87826256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358921
Usha Patel, Hardik Dave, Vibha Patel
Hyperspectral Image generally contains hundreds of spectral bands and thus provides a huge amount of information for a particular scene. Despite this, the classification task for hyperspectral image is considered difficult due to less number of labeled samples available. In recent years, deep learning algorithms have grown as the most significant and highly effective for classification tasks. But these algorithms require a huge amount of labeled data which is not suitable for hyperspectral images as getting labeled data is costly. To mitigate this problem, we can employ semi-supervised learning techniques that can address the issue of less labeled samples for training. In this paper, we have used label propagation technique to improve the performance of the CNN model using semi-supervised learning. By considering this semi-supervised learning strategy, we can obtain comparative performance on hyperspectral data using very less number of labeled samples.
{"title":"Hyperspectral image classification using semi-supervised learning with label propagation","authors":"Usha Patel, Hardik Dave, Vibha Patel","doi":"10.1109/InGARSS48198.2020.9358921","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358921","url":null,"abstract":"Hyperspectral Image generally contains hundreds of spectral bands and thus provides a huge amount of information for a particular scene. Despite this, the classification task for hyperspectral image is considered difficult due to less number of labeled samples available. In recent years, deep learning algorithms have grown as the most significant and highly effective for classification tasks. But these algorithms require a huge amount of labeled data which is not suitable for hyperspectral images as getting labeled data is costly. To mitigate this problem, we can employ semi-supervised learning techniques that can address the issue of less labeled samples for training. In this paper, we have used label propagation technique to improve the performance of the CNN model using semi-supervised learning. By considering this semi-supervised learning strategy, we can obtain comparative performance on hyperspectral data using very less number of labeled samples.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"171 1","pages":"205-208"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77490594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358942
Dwijendra Pandey, Kailash Chandra Tiwari
The remote sensing imageries are helpful in monitoring the urban environment, specifically the growth analysis of urban impervious surfaces as they can provide quick and accurate information about these surfaces over the large geographical areas. The recently developed high spatial and spectral resolution hyperspectral sensors are capable of extracting impervious surfaces with very high accuracy. Therefore, this study utilizes AVIRIS-NG hyperspectral data of Jodhpur, Rajasthan region of India for the analysis. Further, on the basis of existing literature, RGB and NIR bands are selected for generation of three Impervious Surface Index (ISI). The results of the analysis suggest that, Green-NIR combination provides best extraction result with an Overall Accuracy (OA) of 95.20 %, while result of Blue-NIR with OA 90.28 % appears to be better than Red-NIR, which is having OA as 85.29 %. These results have also been verified using histogram plot of various urban land cover classes.
{"title":"Index Based Extraction of Impervious Surfaces Using RGB and NIR Band Combinations in AVIRIS-NG Hyperspectral Imagery","authors":"Dwijendra Pandey, Kailash Chandra Tiwari","doi":"10.1109/InGARSS48198.2020.9358942","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358942","url":null,"abstract":"The remote sensing imageries are helpful in monitoring the urban environment, specifically the growth analysis of urban impervious surfaces as they can provide quick and accurate information about these surfaces over the large geographical areas. The recently developed high spatial and spectral resolution hyperspectral sensors are capable of extracting impervious surfaces with very high accuracy. Therefore, this study utilizes AVIRIS-NG hyperspectral data of Jodhpur, Rajasthan region of India for the analysis. Further, on the basis of existing literature, RGB and NIR bands are selected for generation of three Impervious Surface Index (ISI). The results of the analysis suggest that, Green-NIR combination provides best extraction result with an Overall Accuracy (OA) of 95.20 %, while result of Blue-NIR with OA 90.28 % appears to be better than Red-NIR, which is having OA as 85.29 %. These results have also been verified using histogram plot of various urban land cover classes.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"6 1","pages":"201-204"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90328623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：