This paper explores the optimal methods for processing CBERS-02B images and using them to classify the land uses of karst mountain areas with 3S technologies, especially the RS digital image processing technology. Through multiple experiments and analysis, the difficulty of CBERS-02B images in distinguishing water from mountain shades, construction land from dry land and paddy field are satisfactorily removed. And the combination of band 421, based on OIF method, is proved optimal for classifying the land uses of karst areas. After comparing and evaluating the effect of HIS, PCA and HPC based image fusion methods, the HIS transformation based image fusion method is found best for CBERS-02B HR and CCD data fusion in the case of karst highland mountains. Based on the experiments, this paper proves that CBERS images are capable of large scale land use classification for karst areas, a competent substitute of TM images for karst mountain area land use survey.
{"title":"The investigation of special information distilling method of land use in karst area based on CBERS-02B and analysis on application: a case study of Duyun, Guizhou","authors":"Juan Hu, M. Luo, Yulun An","doi":"10.1117/12.910422","DOIUrl":"https://doi.org/10.1117/12.910422","url":null,"abstract":"This paper explores the optimal methods for processing CBERS-02B images and using them to classify the land uses of karst mountain areas with 3S technologies, especially the RS digital image processing technology. Through multiple experiments and analysis, the difficulty of CBERS-02B images in distinguishing water from mountain shades, construction land from dry land and paddy field are satisfactorily removed. And the combination of band 421, based on OIF method, is proved optimal for classifying the land uses of karst areas. After comparing and evaluating the effect of HIS, PCA and HPC based image fusion methods, the HIS transformation based image fusion method is found best for CBERS-02B HR and CCD data fusion in the case of karst highland mountains. Based on the experiments, this paper proves that CBERS images are capable of large scale land use classification for karst areas, a competent substitute of TM images for karst mountain area land use survey.","PeriodicalId":340728,"journal":{"name":"China Symposium on Remote Sensing","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122147248","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}
The vegetation, as the main component of the ecosystems, is the main receptor of acid rain pollution. Because of the discrepancy of the vegetation characteristics and environment, the responses of the different types of vegetation to acid rain in different regions are different. In this paper, we chose 9 eco-regions in southern China as study area, based on the acid rain and NOAA/NDVI data from 1992 to 2006, and revealed the impact of acid rain on the vegetation by using spatial interpolation, cluster analysis and curve fitting. The result shows that the most tropical and subtropical moist broadleaf forests were positively correlated with the acidity of precipitation and the growth was inhibited obviously. On the contrary, the growth of temperate coniferous forests was promoted by acid rain to some extent. In generally, the vegetation in the condition of the weak acid rain grew better, especially the Qin Ling Mountains deciduous forests and the Changjiang Plain evergreen forests. For South China-Vietnam subtropical evergreen forest, Yunnan Plateau subtropical evergreen forests and Qionglai-Minshan conifer forests, the significant difference of NDVI between the different gradients of acid rain lasted almost the whole year, while that of the other eco-regions only appeared most obviously in Winter.
{"title":"Analysis of acid rain effects on vegetation in eco-regions in China based on AVHRR/NDVI","authors":"Jiaxin Jin, Hong Jiang, Xiuying Zhang, Xiaobin Xu","doi":"10.1117/12.910415","DOIUrl":"https://doi.org/10.1117/12.910415","url":null,"abstract":"The vegetation, as the main component of the ecosystems, is the main receptor of acid rain pollution. Because of the discrepancy of the vegetation characteristics and environment, the responses of the different types of vegetation to acid rain in different regions are different. In this paper, we chose 9 eco-regions in southern China as study area, based on the acid rain and NOAA/NDVI data from 1992 to 2006, and revealed the impact of acid rain on the vegetation by using spatial interpolation, cluster analysis and curve fitting. The result shows that the most tropical and subtropical moist broadleaf forests were positively correlated with the acidity of precipitation and the growth was inhibited obviously. On the contrary, the growth of temperate coniferous forests was promoted by acid rain to some extent. In generally, the vegetation in the condition of the weak acid rain grew better, especially the Qin Ling Mountains deciduous forests and the Changjiang Plain evergreen forests. For South China-Vietnam subtropical evergreen forest, Yunnan Plateau subtropical evergreen forests and Qionglai-Minshan conifer forests, the significant difference of NDVI between the different gradients of acid rain lasted almost the whole year, while that of the other eco-regions only appeared most obviously in Winter.","PeriodicalId":340728,"journal":{"name":"China Symposium on Remote Sensing","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131592812","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}
The Northeast China is the largest distribution region of forests in China, thus its changes in forest undoubtedly have great impact on the global carbon cycle. However, no comprehensive analyses of the changes in forest of this region over the past 25 years have been conducted. In this paper, vegetation in Northeast China was first classified with an expert classification method based on different vegetation types with different NDVI time profiles, then the 25-year changes in forest attribution (i.e., area, growing stock and biomass) was examined based on models constructed, and the comprehensive analysis by using the forest identity was also made. The results showed that forest area, growing stock volume and biomass decreased 1.5 Mha (1 Mha = 106 ha), 187 Mm3(1 Mm3 = 106 m3) and 222.75 Mt (1 Mt = 106 ton), respectively, with the relative annual change rates of -0.18%, -0.32% and -0.34% over the past 25 years. The comprehensive analysis showed that the forest carbon storage in Northeast China was estimated 1.21 Pg C (1 Pg = 1015 g) in the period of 2004-2006, and forests of this region released 3.64 Tg C per year (1 Tg = 1012 g), which means that it demonstrated as a carbon source over the past 25 years. However, such changes in forest attribution showed a significant regional variation; for example, the attributes declined in Heilongjiang and Jilin, while increased in Liaoning Province. The declines in forest growing stock volume are mainly due to the decrease in area, which may be further caused by the coupling effects of frequent forest fires and deforestation.
{"title":"Changes of forest in northeast China over the past 25 years: an analysis based on remote sensing technique","authors":"Lei Shi","doi":"10.1117/12.910414","DOIUrl":"https://doi.org/10.1117/12.910414","url":null,"abstract":"The Northeast China is the largest distribution region of forests in China, thus its changes in forest undoubtedly have great impact on the global carbon cycle. However, no comprehensive analyses of the changes in forest of this region over the past 25 years have been conducted. In this paper, vegetation in Northeast China was first classified with an expert classification method based on different vegetation types with different NDVI time profiles, then the 25-year changes in forest attribution (i.e., area, growing stock and biomass) was examined based on models constructed, and the comprehensive analysis by using the forest identity was also made. The results showed that forest area, growing stock volume and biomass decreased 1.5 Mha (1 Mha = 106 ha), 187 Mm3(1 Mm3 = 106 m3) and 222.75 Mt (1 Mt = 106 ton), respectively, with the relative annual change rates of -0.18%, -0.32% and -0.34% over the past 25 years. The comprehensive analysis showed that the forest carbon storage in Northeast China was estimated 1.21 Pg C (1 Pg = 1015 g) in the period of 2004-2006, and forests of this region released 3.64 Tg C per year (1 Tg = 1012 g), which means that it demonstrated as a carbon source over the past 25 years. However, such changes in forest attribution showed a significant regional variation; for example, the attributes declined in Heilongjiang and Jilin, while increased in Liaoning Province. The declines in forest growing stock volume are mainly due to the decrease in area, which may be further caused by the coupling effects of frequent forest fires and deforestation.","PeriodicalId":340728,"journal":{"name":"China Symposium on Remote Sensing","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133696420","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}
Lingwei Shi, Heguang Liu, Ke Xu, Shuangbao Yang, Xiyu Xu
Radar altimeter is playing an important and irreplaceable role in ocean remote sensing. The Delay/Doppler Radar Altimeter (DDA) is a new type of radar altimeter and has high spatial resolution, low power consumption and small size. It can be applied in open oceans, coastal zone and polar ice. In a fully developed linear ocean, the ocean model is generated by sea wave spectrum model which consists of swell and wind spectrum. The sea surface is of random character and can be described by random variables such as the ocean surface elevation probability density function (OSE PDF) and the ocean surface wave height probability density function (OSWH PDF). In this paper different echoes with the different OSWH PDFs and sea states are simulated. With spatial and temporal characteristics, the K-distribution echo is closer to the ideal echo model. The results from this paper are helpful to the algorithmic method and performance of the DDA. They also have directive to the DDA echo simulator.
{"title":"Delay/Doppler radar altimeter simulation echoes from different sea states","authors":"Lingwei Shi, Heguang Liu, Ke Xu, Shuangbao Yang, Xiyu Xu","doi":"10.1117/12.910395","DOIUrl":"https://doi.org/10.1117/12.910395","url":null,"abstract":"Radar altimeter is playing an important and irreplaceable role in ocean remote sensing. The Delay/Doppler Radar Altimeter (DDA) is a new type of radar altimeter and has high spatial resolution, low power consumption and small size. It can be applied in open oceans, coastal zone and polar ice. In a fully developed linear ocean, the ocean model is generated by sea wave spectrum model which consists of swell and wind spectrum. The sea surface is of random character and can be described by random variables such as the ocean surface elevation probability density function (OSE PDF) and the ocean surface wave height probability density function (OSWH PDF). In this paper different echoes with the different OSWH PDFs and sea states are simulated. With spatial and temporal characteristics, the K-distribution echo is closer to the ideal echo model. The results from this paper are helpful to the algorithmic method and performance of the DDA. They also have directive to the DDA echo simulator.","PeriodicalId":340728,"journal":{"name":"China Symposium on Remote Sensing","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114711678","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}
Using the inherent features of high resolution data, such as the shape and the texture, this paper proposed an object and rule based fuzzy classification method. First, multi-scale segmentations were used to obtain homogeneous objects at different scales. According to fuzzy classification ideas, these segmented objects were further classified by using the corresponding spectral, shape, texture, topology and other object-related characteristics. This method not only overcomes the limitations of pixel based classifications, but also takes advantage of the inherent features of high resolution data. To fully compare and analyze the proposed classification method, an IKONOS image of urban areas was selected as test data. According to four main classification steps, this data was classified as houses, roads, vegetation, and bare land. The classification results showed that the proposed method enhances the accuracy of classification and is of great advantages compared with the traditional pixel based classification methods.
{"title":"Object and rule based approach for classification of high spatial resolution data over urban areas","authors":"L. Ni","doi":"10.1117/12.910410","DOIUrl":"https://doi.org/10.1117/12.910410","url":null,"abstract":"Using the inherent features of high resolution data, such as the shape and the texture, this paper proposed an object and rule based fuzzy classification method. First, multi-scale segmentations were used to obtain homogeneous objects at different scales. According to fuzzy classification ideas, these segmented objects were further classified by using the corresponding spectral, shape, texture, topology and other object-related characteristics. This method not only overcomes the limitations of pixel based classifications, but also takes advantage of the inherent features of high resolution data. To fully compare and analyze the proposed classification method, an IKONOS image of urban areas was selected as test data. According to four main classification steps, this data was classified as houses, roads, vegetation, and bare land. The classification results showed that the proposed method enhances the accuracy of classification and is of great advantages compared with the traditional pixel based classification methods.","PeriodicalId":340728,"journal":{"name":"China Symposium on Remote Sensing","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132594154","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}
H. Du, H. Gong, Zunfeng Jiang, J. Jia, Zhongsheng Quan
This paper is concerned with the construction of spatial data acquisition and application, and the communication and service platforms. The techniques for managing multi-source spatial data used in disaster rescues are discussed, including data- and meta-database construction and system development. An application example is also given. The results of this study were proven to be effective. The data processing period was significantly reduced and the validity of decision-making was similarly improved.
{"title":"Technology and application of emergency spatial data management","authors":"H. Du, H. Gong, Zunfeng Jiang, J. Jia, Zhongsheng Quan","doi":"10.1117/12.910418","DOIUrl":"https://doi.org/10.1117/12.910418","url":null,"abstract":"This paper is concerned with the construction of spatial data acquisition and application, and the communication and service platforms. The techniques for managing multi-source spatial data used in disaster rescues are discussed, including data- and meta-database construction and system development. An application example is also given. The results of this study were proven to be effective. The data processing period was significantly reduced and the validity of decision-making was similarly improved.","PeriodicalId":340728,"journal":{"name":"China Symposium on Remote Sensing","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129749493","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}
Land cover is a crucial product required to be calibrated, validated and used in various land surface models that provide the boundary conditions for the simulation of climate, carbon cycle and ecosystem change. This paper presented a method to map land cover from multitemporal landsat images using Dempster-Shafer theory of evidence. The method firstly resolved in Gaussian probability density function calculate the basic probability assignment of each single satellite image, then multitemporal landsat images were combined using Dempster's Rule of combination. Finally, a decision rule based on ancillary information is used to make classification decisions. This method had 87.91% overall accuracy for the land cover types compared with the result of the Aerial hyperspectral image classification. The results of this study showed that Dempster-Shafer theory of evidence is an effective tool to map land cover using multitemporal landsat image.
{"title":"Mapping land cover of the Yellow River source using multi-temporal Landsat images","authors":"Yong Hu, Liangyun Liu, Lingling Liu, Quanjun Jiao, Jianhua Jia","doi":"10.1117/12.910403","DOIUrl":"https://doi.org/10.1117/12.910403","url":null,"abstract":"Land cover is a crucial product required to be calibrated, validated and used in various land surface models that provide the boundary conditions for the simulation of climate, carbon cycle and ecosystem change. This paper presented a method to map land cover from multitemporal landsat images using Dempster-Shafer theory of evidence. The method firstly resolved in Gaussian probability density function calculate the basic probability assignment of each single satellite image, then multitemporal landsat images were combined using Dempster's Rule of combination. Finally, a decision rule based on ancillary information is used to make classification decisions. This method had 87.91% overall accuracy for the land cover types compared with the result of the Aerial hyperspectral image classification. The results of this study showed that Dempster-Shafer theory of evidence is an effective tool to map land cover using multitemporal landsat image.","PeriodicalId":340728,"journal":{"name":"China Symposium on Remote Sensing","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126359168","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}
Lin Guo, Zhiyuan Pei, Songling Zhang, Qingfa Wang, H. Mcnairn, J. Shang, X. Jiao
Most of China's rice production is located in the southern provinces of the country where frequent cloudy conditions hinder the successful acquisition of optical imagery. Small field sizes and complex planting patterns pose additional challenges to crop mapping using remote sensing approaches. High resolution radar data are most suitable for operational monitoring of crops in this region of China. In this study, the suitability of high-resolution TerraSAR-X StripMap data (6 m resolution) for identification of rice was investigated for a site in Xuwen, Guangdong Province, China. An integrated decision tree and object-oriented classification approach was used. The results showed that higher rice identification accuracies can be obtained using multi-temporal TerraSAR-X data at the tillering, jointing and flowering periods. Both the VV and VH polarizations provided accurate rice identification.
{"title":"Rice identification using TerraSAR-X data","authors":"Lin Guo, Zhiyuan Pei, Songling Zhang, Qingfa Wang, H. Mcnairn, J. Shang, X. Jiao","doi":"10.1117/12.910396","DOIUrl":"https://doi.org/10.1117/12.910396","url":null,"abstract":"Most of China's rice production is located in the southern provinces of the country where frequent cloudy conditions hinder the successful acquisition of optical imagery. Small field sizes and complex planting patterns pose additional challenges to crop mapping using remote sensing approaches. High resolution radar data are most suitable for operational monitoring of crops in this region of China. In this study, the suitability of high-resolution TerraSAR-X StripMap data (6 m resolution) for identification of rice was investigated for a site in Xuwen, Guangdong Province, China. An integrated decision tree and object-oriented classification approach was used. The results showed that higher rice identification accuracies can be obtained using multi-temporal TerraSAR-X data at the tillering, jointing and flowering periods. Both the VV and VH polarizations provided accurate rice identification.","PeriodicalId":340728,"journal":{"name":"China Symposium on Remote Sensing","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123945370","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}
Fangfang Zhou, Bin Zhou, Weiping Zhu, Wenjie Dou, Zaiying Ling
Water optical properties are important factors that affect phytoplankton biomass, carbon formation and carbon output of the upper body. Water spectral absorption properties are among the most important inherent optical properties. This paper was a preliminary analysis on spectral absorption properties of water suspended particle, de-pigmented particle, pigment particle and chromophoric dissolved organic matter (CDOM) in main channel of Hangzhou Xixi Wetland National Park phase I. The results indicate that the absorption spectrum of suspended particle is similar to the de-pigmented particle, while the absorption spectrum of pigment particle is almost submerged in the de-pigmented particle; The absorption spectrum of de-pigmented particle and CDOM follows the exponential decay law, the former slope Sd average value of the exponential function in the range of 400-700nm is 9.56±0.86μm-1, the latter slope Sgaverage value of the exponential function in the range of 400-500nm is 14.28±1.23μm-1. The absorption peak of chlorophyll a of pigment particle near 440nm is virtually not existent and also very weak at 675nm. According to the absorption contribution rate of each component to the total absorption, de-pigmented particle is the greater contributor than pigment particle and CDOM in this field campaign. In addition, according to water mass classification based on the contribution rate of absorption coefficient at 440nm, vast majority of the water body in study area could be classified into the most optical complex water mass type.
{"title":"Optical absorption properties of water components in Xixi wetland of Hangzhou","authors":"Fangfang Zhou, Bin Zhou, Weiping Zhu, Wenjie Dou, Zaiying Ling","doi":"10.1117/12.910432","DOIUrl":"https://doi.org/10.1117/12.910432","url":null,"abstract":"Water optical properties are important factors that affect phytoplankton biomass, carbon formation and carbon output of the upper body. Water spectral absorption properties are among the most important inherent optical properties. This paper was a preliminary analysis on spectral absorption properties of water suspended particle, de-pigmented particle, pigment particle and chromophoric dissolved organic matter (CDOM) in main channel of Hangzhou Xixi Wetland National Park phase I. The results indicate that the absorption spectrum of suspended particle is similar to the de-pigmented particle, while the absorption spectrum of pigment particle is almost submerged in the de-pigmented particle; The absorption spectrum of de-pigmented particle and CDOM follows the exponential decay law, the former slope Sd average value of the exponential function in the range of 400-700nm is 9.56±0.86μm-1, the latter slope Sgaverage value of the exponential function in the range of 400-500nm is 14.28±1.23μm-1. The absorption peak of chlorophyll a of pigment particle near 440nm is virtually not existent and also very weak at 675nm. According to the absorption contribution rate of each component to the total absorption, de-pigmented particle is the greater contributor than pigment particle and CDOM in this field campaign. In addition, according to water mass classification based on the contribution rate of absorption coefficient at 440nm, vast majority of the water body in study area could be classified into the most optical complex water mass type.","PeriodicalId":340728,"journal":{"name":"China Symposium on Remote Sensing","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124139735","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}
In remote sensing imagery, ground objects belonging to the same land cover category always have similar optimal segmentation scales. The paper proposed a method using the land cover categories as a prior knowledge to guide the synthesis of multi-scale image segmentation results. This method took into account the variety of scale characteristics of different ground objects as well as the similarity of scale of objects belonging to the same land cover category. Firstly, the image was coarsely divided into multiple regions, and each of them belonged to a land cover category. Then for each category, we selected the optimal segmentation scale by the supervised accuracy assessment of segmentation results. Finally, the optimal scales of segmentation results were synthesized to get the final segmentation result. To validate this method, the Quickbird image was segmented and classified. Experimental results showed that this method could generate accurate segmentation results for the latter classification.
{"title":"Synthesis of multi-scale segmentation results based on land cover categories","authors":"Lina Yi, Zhaocong Wu, Guifeng Zhang, Yiming Zhang","doi":"10.1117/12.910406","DOIUrl":"https://doi.org/10.1117/12.910406","url":null,"abstract":"In remote sensing imagery, ground objects belonging to the same land cover category always have similar optimal segmentation scales. The paper proposed a method using the land cover categories as a prior knowledge to guide the synthesis of multi-scale image segmentation results. This method took into account the variety of scale characteristics of different ground objects as well as the similarity of scale of objects belonging to the same land cover category. Firstly, the image was coarsely divided into multiple regions, and each of them belonged to a land cover category. Then for each category, we selected the optimal segmentation scale by the supervised accuracy assessment of segmentation results. Finally, the optimal scales of segmentation results were synthesized to get the final segmentation result. To validate this method, the Quickbird image was segmented and classified. Experimental results showed that this method could generate accurate segmentation results for the latter classification.","PeriodicalId":340728,"journal":{"name":"China Symposium on Remote Sensing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115543762","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：