Pub Date : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820233
Zhanya Xu, Shuling Meng, Shaobo Zhong, L. Di, C. Yang, E. Yu
Crop classification is an important part of national agricultural management, and accurate crop classification is conducive to crop growth monitoring and yield assessment. However, due to the different growing years and regions, even the same crop has different growth processes and different phenological characteristics. Therefore, improving the spatial and temporal adaptability of the classification model is an important research content for large-scale crop classification. In this paper, several adjacent agricultural production areas are studied. Based on the stable time-series remote sensing image dataset, the adaptive changes of several machine learning classification methods with higher classification accuracy in spatial and temporal are studied. The paper selected Sentinel 1 satellite data with good anti-cloud interference and a short return visit cycle for experiments. Firstly, the training of each classification model in the same area is completed, and then the spatial adaptability of the model is studied in different adjacent ranges. Finally, the adaptability of different classification models to the change of the growth cycle of the same type of crop is also compared. The paper finds that the models such as CNN+LSTM and BinConvLSTM perform better in temporal and spatial.
{"title":"Study on Temporal and Spatial Adaptability of Crop Classification Models","authors":"Zhanya Xu, Shuling Meng, Shaobo Zhong, L. Di, C. Yang, E. Yu","doi":"10.1109/Agro-Geoinformatics.2019.8820233","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820233","url":null,"abstract":"Crop classification is an important part of national agricultural management, and accurate crop classification is conducive to crop growth monitoring and yield assessment. However, due to the different growing years and regions, even the same crop has different growth processes and different phenological characteristics. Therefore, improving the spatial and temporal adaptability of the classification model is an important research content for large-scale crop classification. In this paper, several adjacent agricultural production areas are studied. Based on the stable time-series remote sensing image dataset, the adaptive changes of several machine learning classification methods with higher classification accuracy in spatial and temporal are studied. The paper selected Sentinel 1 satellite data with good anti-cloud interference and a short return visit cycle for experiments. Firstly, the training of each classification model in the same area is completed, and then the spatial adaptability of the model is studied in different adjacent ranges. Finally, the adaptability of different classification models to the change of the growth cycle of the same type of crop is also compared. The paper finds that the models such as CNN+LSTM and BinConvLSTM perform better in temporal and spatial.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130141571","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}
Wheat powdery mildew (Blumeria graminis Dc.speer) is one of the most devastating crop diseases in the globe. Thinking of economic effective and environmental protection value, early detection of the severity of wheat powdery mildew can provide important information and technical support for disease prevention. In this study, the wheat leaves infected powdery mildew were chosen as observation objects, the obtained hyperspectral imagery data was pre-processed by reflectance calculation and noise elimination. After the disease-infected samples with different severities were divided into three-levels, four-levels, and five-levels, the effects of samples classification on identification of the disease were explored. Subsequently, the Relief-F algorithm was used to screen the sensitive bands of the disease in the early and mid-late growth stages, to observe the wavelengths change of disease identification in different developmental periods. The results showed that the sensitive bands of disease detection respectively locate at 700 nm and 680 nm for the early and mid-late growth stages, and the position of sensitive wavelength moves toward the short-wave direction as the disease worsens. On the basis, Calculating the powdery mildew disease index (PMDI) and nine kinds of common vegetation indexes, to compare their effects on disease identification, the study found that when the samples were divided into four levels, the determination coefficientR2 of PMDI is the highest. For the early and mid-late infection stages, theR2 are respectively 0.763 and 0.766. Furthermore, the corresponding SVM models were established in the different developmental periods, the classification accuracy is 90.63% at the early growth stage, while that one is the 84.62% at mid-late developmental period. The above results show that PMDI calculated by the sensitive band screening has good effective on identifying the severity of the disease, especially there is a good potential at the early growth stage.
{"title":"Research on Diagnosis Characteristics of Wheat Powdery Mildew Under Different Severity Grading Standards","authors":"Dongyan Zhang, Xun Yin, Fenfang Lin, Linsheng Huang, Jinling Zhao, Yu Liu, Wei Ma, Qi Hong","doi":"10.1109/Agro-Geoinformatics.2019.8820416","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820416","url":null,"abstract":"Wheat powdery mildew (Blumeria graminis Dc.speer) is one of the most devastating crop diseases in the globe. Thinking of economic effective and environmental protection value, early detection of the severity of wheat powdery mildew can provide important information and technical support for disease prevention. In this study, the wheat leaves infected powdery mildew were chosen as observation objects, the obtained hyperspectral imagery data was pre-processed by reflectance calculation and noise elimination. After the disease-infected samples with different severities were divided into three-levels, four-levels, and five-levels, the effects of samples classification on identification of the disease were explored. Subsequently, the Relief-F algorithm was used to screen the sensitive bands of the disease in the early and mid-late growth stages, to observe the wavelengths change of disease identification in different developmental periods. The results showed that the sensitive bands of disease detection respectively locate at 700 nm and 680 nm for the early and mid-late growth stages, and the position of sensitive wavelength moves toward the short-wave direction as the disease worsens. On the basis, Calculating the powdery mildew disease index (PMDI) and nine kinds of common vegetation indexes, to compare their effects on disease identification, the study found that when the samples were divided into four levels, the determination coefficientR2 of PMDI is the highest. For the early and mid-late infection stages, theR2 are respectively 0.763 and 0.766. Furthermore, the corresponding SVM models were established in the different developmental periods, the classification accuracy is 90.63% at the early growth stage, while that one is the 84.62% at mid-late developmental period. The above results show that PMDI calculated by the sensitive band screening has good effective on identifying the severity of the disease, especially there is a good potential at the early growth stage.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132059251","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 : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820593
B. Ren, Huizhen Zhou, Hua Shen, Zeyu Wang, F. Guan, Hong Yu
Cotton is an important economic crop and plays an important role in the national economy. Therefore, timely and accurate access to crop planting area and spatial distribution information is very important for government departments to make economic decisions and adjust cotton planting structure. At the same time, crop census and cotton growth monitoring There are also important applications in terms of production estimates and disaster assessment. This study is based on Google Earth Engine remote sensing big data cloud computing platform and Sentinel-2 data, taking Zaoqiang County of Hengshui City, Hebei Province as an example, using nearly 50 scenes of Sentinel-2 data, combined with interest area index calculation, S-G filtering method, etc. The time series phenotypic analysis method was constructed to analyze the phenological characteristics of the main crop cotton and the interfering crop corn in Zaoqiang County. Based on the phenological analysis results, the key time phase data of cotton extraction was screened, and the objectoriented information extraction method was combined with spectral features and texture features. The cotton distribution information of Zaoqiang County was extracted, and the accuracy of the results was analyzed with the field sample data. The overall accuracy was 92%, which satisfied the cotton monitoring application demand of Zaoqiang County.
{"title":"Research on Cotton Information Extraction Based on Sentinel-2 Time Series Analysis","authors":"B. Ren, Huizhen Zhou, Hua Shen, Zeyu Wang, F. Guan, Hong Yu","doi":"10.1109/Agro-Geoinformatics.2019.8820593","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820593","url":null,"abstract":"Cotton is an important economic crop and plays an important role in the national economy. Therefore, timely and accurate access to crop planting area and spatial distribution information is very important for government departments to make economic decisions and adjust cotton planting structure. At the same time, crop census and cotton growth monitoring There are also important applications in terms of production estimates and disaster assessment. This study is based on Google Earth Engine remote sensing big data cloud computing platform and Sentinel-2 data, taking Zaoqiang County of Hengshui City, Hebei Province as an example, using nearly 50 scenes of Sentinel-2 data, combined with interest area index calculation, S-G filtering method, etc. The time series phenotypic analysis method was constructed to analyze the phenological characteristics of the main crop cotton and the interfering crop corn in Zaoqiang County. Based on the phenological analysis results, the key time phase data of cotton extraction was screened, and the objectoriented information extraction method was combined with spectral features and texture features. The cotton distribution information of Zaoqiang County was extracted, and the accuracy of the results was analyzed with the field sample data. The overall accuracy was 92%, which satisfied the cotton monitoring application demand of Zaoqiang County.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114920012","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}
Coastal aquaculture surveys play an important role in the marine economic development, coastal resources utilization and marine environmental protection. With the development of satellite remote sensing technology, investigation and analysis of coastal aquaculture with high resolution satellite images has been a hot topic. Based on the analysis of spectral and geospatial features of coastal cage aquaculture areas, this study proposes an object-based classification method with GF-2 image. First, the NDWI threshold was used to achieve land-sea separation. Secondly, rules designed according to the spectral feature for cage aquaculture detection in high turbidity water bodies were established considering that same spectrum with different objects and other phenomena may easily affect the extraction accuracy due to the turbidity of the water in the study area. Results show that the object-based method can quickly and accurately monitor the distribution of different types of aquaculture areas, and the overall detection accuracy can reach over 93%, which is much better than the pixel based method of Maximum Likelihood Method. This objet-based method then was used to calculate the nutrients loading of the cage aquaculture areas, which can provide effective information support and auxiliary decision analysis for management departments to scientifically plan and environmental manage coastal aquaculture areas.
{"title":"Remote Sensing Monitoring and Environmental Pollution Load Assessment of Coastal Aquaculture Area Based on GF-2","authors":"Tinggang Wang, Xiaoyu Zhang, Yixuan Xiong, Guorong Huang, Jiaxing Chen","doi":"10.1109/Agro-Geoinformatics.2019.8820243","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820243","url":null,"abstract":"Coastal aquaculture surveys play an important role in the marine economic development, coastal resources utilization and marine environmental protection. With the development of satellite remote sensing technology, investigation and analysis of coastal aquaculture with high resolution satellite images has been a hot topic. Based on the analysis of spectral and geospatial features of coastal cage aquaculture areas, this study proposes an object-based classification method with GF-2 image. First, the NDWI threshold was used to achieve land-sea separation. Secondly, rules designed according to the spectral feature for cage aquaculture detection in high turbidity water bodies were established considering that same spectrum with different objects and other phenomena may easily affect the extraction accuracy due to the turbidity of the water in the study area. Results show that the object-based method can quickly and accurately monitor the distribution of different types of aquaculture areas, and the overall detection accuracy can reach over 93%, which is much better than the pixel based method of Maximum Likelihood Method. This objet-based method then was used to calculate the nutrients loading of the cage aquaculture areas, which can provide effective information support and auxiliary decision analysis for management departments to scientifically plan and environmental manage coastal aquaculture areas.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130323129","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 : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820560
A. Moomen, I. Yussif
The quest to achieve industrialisation and economic diversification has brought a new form of thinking current among African leadership, which has implications for geo-space and rural livelihood. Governments are leasing large tracts of rural lands for mineral resource extraction. However, little attention has been given to developing baseline conditions that would facilitate a possible peaceful co-existence between large-scale mining and agriculture which is a basic rural livelihood activity. Hence, this study appraises land use/cover conditions of the Northwest mining region of Ghana to identify the availability of space for farming and large-scale mining exploration activities at the village level. The study uses a combination of Landsat satellite imagery for the years 2000 and 2014, and Participatory Geographic Information Systems to classify the landscape into four major land use/cover types, namely: water, waterlog, vegetation and occupied lands. Occupied lands include farmlands, settlements and bare grounds. It is found that between 2000 and 2014, much of the area is characterised by waterlog features and flood potentials juxtaposed to an increasing large-scale exploration and mining activities interest in local space. Overall, the net gain of space by occupied lands is about 47% of total land cover in the area. Much of this gain is in the Nadowli-Kaleo and Jirapa areas of the study region where exploration leases are wide-spreading. It is also observed that there is an expansion of barelands and settlements in the villages around the exploration and mine sites. This phenomenon is a signal of potential land use conflict between mining and farming in villages nearby and must be addressed before mine commissioning.
对实现工业化和经济多样化的追求为非洲领导人带来了一种新的思维形式，这对地理空间和农村生计产生了影响。政府正在租赁大片农村土地开采矿产资源。但是，很少注意发展基线条件，以促进大规模采矿和农业之间可能的和平共存，而农业是农村的基本生计活动。因此，本研究评估了加纳西北矿区的土地利用/覆盖条件，以确定村庄一级农业和大规模采矿勘探活动的可用空间。该研究结合了2000年和2014年的Landsat卫星图像，以及参与式地理信息系统(Participatory Geographic Information Systems)，将景观分为四种主要的土地利用/覆盖类型，即:水、涝渍、植被和被占用土地。被占领的土地包括农田、定居点和裸地。研究发现，在2000年至2014年期间，该地区的大部分地区都具有内涝特征和洪水潜力，同时当地空间的大规模勘探和采矿活动也在增加。总体而言，被占用土地的净空间增益约占该地区总土地覆盖面积的47%。大部分的增长发生在研究区域的Nadowli-Kaleo和Jirapa地区，这些地区的勘探租约分布广泛。人们还注意到，在勘探和矿区周围的村庄里，荒地和定居点正在扩大。这一现象是附近村庄采矿和农业之间可能发生土地使用冲突的信号，必须在矿山投产之前加以解决。
{"title":"Evaluation of Farmland availability and Large- Scale Mining Sector Activities at Village Scale","authors":"A. Moomen, I. Yussif","doi":"10.1109/Agro-Geoinformatics.2019.8820560","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820560","url":null,"abstract":"The quest to achieve industrialisation and economic diversification has brought a new form of thinking current among African leadership, which has implications for geo-space and rural livelihood. Governments are leasing large tracts of rural lands for mineral resource extraction. However, little attention has been given to developing baseline conditions that would facilitate a possible peaceful co-existence between large-scale mining and agriculture which is a basic rural livelihood activity. Hence, this study appraises land use/cover conditions of the Northwest mining region of Ghana to identify the availability of space for farming and large-scale mining exploration activities at the village level. The study uses a combination of Landsat satellite imagery for the years 2000 and 2014, and Participatory Geographic Information Systems to classify the landscape into four major land use/cover types, namely: water, waterlog, vegetation and occupied lands. Occupied lands include farmlands, settlements and bare grounds. It is found that between 2000 and 2014, much of the area is characterised by waterlog features and flood potentials juxtaposed to an increasing large-scale exploration and mining activities interest in local space. Overall, the net gain of space by occupied lands is about 47% of total land cover in the area. Much of this gain is in the Nadowli-Kaleo and Jirapa areas of the study region where exploration leases are wide-spreading. It is also observed that there is an expansion of barelands and settlements in the villages around the exploration and mine sites. This phenomenon is a signal of potential land use conflict between mining and farming in villages nearby and must be addressed before mine commissioning.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128577296","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 : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820529
Dongyan Zhang, Daoyong Wang, Shizhou Du, Linsheng Huang, Haitao Zhao, Dong Liang, Chunyan Gu, Xue Yang
Wheat (Triticum aestivum L.) is one of the three major cereals worldwide. The FusaHum graminearum Sehw., special fugus always damages the wheat ear, and produces vomitoxin,is difficult to control and prevent, and seriously threatens the health of humans, animals and China's food security. Currently, rapidly, accurately and non-destructively diagnostic devices or systems for this disease have not been disclosed. In this study, the infected ears with different severities were picked up in key growth stages. The diseased area of wheat ear was extracted using hypergreen characteristic, and a total of 30 features of infected ears were chosen including color (Lab, HSI, HSV, YCbCr color space), texture (LBP and LLE dimension reduction), and shape (squareness, shape complexity, and eccentricity). Then using the competitive adaptive re-weighted sampling (CARS) and rough set algorithm (RS) to screen the characteristics of the diseased ear, the four characteristics with the largest contribution were determined to establish the CARS-SVM and CARS-RS-SVM models respectively. The study found that the recognition rate of CARS-SVM model is 85.4%, while CARS-RS-SVM model is 92.7%. Thus the CARS-RS-SVM was thought of as the optimal model by two indicators of identification accuracy. On the basis, a wheat scab diagnosis system based on Android mobile phone was constructed. It consists of three parts - Clients, Service-Terminal and Database. The Client was designed by Android Studio and its functions mainly include image acquisition, image storage, GPS positioning, image uploading and diagnostic results display. The Service-Terminal was completed by the mixed programming of Myeclipse and Matlab software, and Tomcat was used as the Server. It mainly implements the functions of image receiving, image preprocessing, feature extraction and selection, and classifier modeling. The MySQL was used to establish two databases: the “Disease Characteristics Database” and the “Disease Diagnosis Knowledge Base”. Finally, through samples testing and validating, the Android-based mobile terminal can real-time collect the image of Fusarium head blight and upload the server. After the target image was processed and compared by the “Disease Characteristics Database”, the appropriate diagnostic knowledge was selected from the “Disease Diagnosis Knowledge Base” and feedbacked to the client. In summary, the results of this study showed that it was helpful for the rapid and non-destructive investigation of infected FHB in the field, and it would provide a reference for the study of other crop diseases, facilitate the application and development of new technologies such as artificial intelligence and big data in agriculture.
{"title":"A Rapidly Diagnosis and Application System of Fusarium Head Blight Based on Smartphone","authors":"Dongyan Zhang, Daoyong Wang, Shizhou Du, Linsheng Huang, Haitao Zhao, Dong Liang, Chunyan Gu, Xue Yang","doi":"10.1109/Agro-Geoinformatics.2019.8820529","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820529","url":null,"abstract":"Wheat (Triticum aestivum L.) is one of the three major cereals worldwide. The FusaHum graminearum Sehw., special fugus always damages the wheat ear, and produces vomitoxin,is difficult to control and prevent, and seriously threatens the health of humans, animals and China's food security. Currently, rapidly, accurately and non-destructively diagnostic devices or systems for this disease have not been disclosed. In this study, the infected ears with different severities were picked up in key growth stages. The diseased area of wheat ear was extracted using hypergreen characteristic, and a total of 30 features of infected ears were chosen including color (Lab, HSI, HSV, YCbCr color space), texture (LBP and LLE dimension reduction), and shape (squareness, shape complexity, and eccentricity). Then using the competitive adaptive re-weighted sampling (CARS) and rough set algorithm (RS) to screen the characteristics of the diseased ear, the four characteristics with the largest contribution were determined to establish the CARS-SVM and CARS-RS-SVM models respectively. The study found that the recognition rate of CARS-SVM model is 85.4%, while CARS-RS-SVM model is 92.7%. Thus the CARS-RS-SVM was thought of as the optimal model by two indicators of identification accuracy. On the basis, a wheat scab diagnosis system based on Android mobile phone was constructed. It consists of three parts - Clients, Service-Terminal and Database. The Client was designed by Android Studio and its functions mainly include image acquisition, image storage, GPS positioning, image uploading and diagnostic results display. The Service-Terminal was completed by the mixed programming of Myeclipse and Matlab software, and Tomcat was used as the Server. It mainly implements the functions of image receiving, image preprocessing, feature extraction and selection, and classifier modeling. The MySQL was used to establish two databases: the “Disease Characteristics Database” and the “Disease Diagnosis Knowledge Base”. Finally, through samples testing and validating, the Android-based mobile terminal can real-time collect the image of Fusarium head blight and upload the server. After the target image was processed and compared by the “Disease Characteristics Database”, the appropriate diagnostic knowledge was selected from the “Disease Diagnosis Knowledge Base” and feedbacked to the client. In summary, the results of this study showed that it was helpful for the rapid and non-destructive investigation of infected FHB in the field, and it would provide a reference for the study of other crop diseases, facilitate the application and development of new technologies such as artificial intelligence and big data in agriculture.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116903324","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 : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820680
Yunzhi Chen, Jinhan Lin, Yankui Yang, Xiaoqin Wang
Tea is the most popular drink in China. The spatial distribution information of tea plantation is useful for local government management. Lantian Country, with an area of 99.77km2, located in the midwest of Anxi County, which is famous for Oolong Tea, was chosen as study area, and image from Chinese high resolution satellite Gaofen-2 acquired on Jan 22, 2015 was used to study the method of tea plantations extraction. In order to construct best features for classification, optimum index factor (OIF) were firstly calculated on different original spectral bands combinations and the one with max OIF was chosen. Secondly, spectral enhancement was carried on multi-spectral bands.Difference between two vegetation indexes, namely, normalized difference vegetation index and modified normalized difference vegetation index was calculated and named as DNDVI. In DNDVI image, the brightness difference between tea plantation and background was improved and shadowed area in either index image was reduced. Thirdly, gray level co-occurrence matrix (GLCM), Gabor filter, local binary patterns (LBP) extraction, and method combined LBP and Gabor was carried on pan image to construct texture features. Among eight common features based GLCM, contrast, dissimilarity, entropy, variance, tea plantation area was darker. In homogeneity and angular second moment, this phenomena is just the opposite. In mean and correlation, there was no obvious difference between target tea plantation and background. So the gray level co-occurrence texture (GLCT) subtract sum of second two features from sum of the first four feature was used as final GLCM feature, and window size for GLCM set to be 15 was preferred. Multi-scale and multidirectional Gabor texture with max frequency set to be 1HZ was derived. For LBP, the operator LBP16, 2 with rotation invariance was tested to be the best. Finally, five schemes combine these spectral and textural features as inputs of classifier were evaluated in term of classification accuracy. Six categories including tea plantation, forest, roads, water, build-up, bare soil, shadows were classified by support vector machine. The result showed that overall accuracy range from 75.55% to 89.11%, Kappa coefficient range from 0.613 to 0.843, for plantation, user accuracy range from 84.95% to 100%, producer accuracy range from 53.29% to 91.53%. Gaofen-2 show its capacity to map the tea plantation area accurately. Schemes utilized spectral and textural features together perform much better than that utilized spectral only. The scheme combination of band1, band 3, ban4, DNDVI, LBP_Gabor outperformed other Scheme, with the highest overall accuracy and Kappa coefficient. The textures feature of high resolution image helps to improve the accuracy, and the way to construct suitable texture feature and merge different texture feature deserved study more. The proposed method to extract tea plantation is applicable at administrative level of country.
{"title":"Extraction of tea plantation with high resolution Gaofen-2 image","authors":"Yunzhi Chen, Jinhan Lin, Yankui Yang, Xiaoqin Wang","doi":"10.1109/Agro-Geoinformatics.2019.8820680","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820680","url":null,"abstract":"Tea is the most popular drink in China. The spatial distribution information of tea plantation is useful for local government management. Lantian Country, with an area of 99.77km2, located in the midwest of Anxi County, which is famous for Oolong Tea, was chosen as study area, and image from Chinese high resolution satellite Gaofen-2 acquired on Jan 22, 2015 was used to study the method of tea plantations extraction. In order to construct best features for classification, optimum index factor (OIF) were firstly calculated on different original spectral bands combinations and the one with max OIF was chosen. Secondly, spectral enhancement was carried on multi-spectral bands.Difference between two vegetation indexes, namely, normalized difference vegetation index and modified normalized difference vegetation index was calculated and named as DNDVI. In DNDVI image, the brightness difference between tea plantation and background was improved and shadowed area in either index image was reduced. Thirdly, gray level co-occurrence matrix (GLCM), Gabor filter, local binary patterns (LBP) extraction, and method combined LBP and Gabor was carried on pan image to construct texture features. Among eight common features based GLCM, contrast, dissimilarity, entropy, variance, tea plantation area was darker. In homogeneity and angular second moment, this phenomena is just the opposite. In mean and correlation, there was no obvious difference between target tea plantation and background. So the gray level co-occurrence texture (GLCT) subtract sum of second two features from sum of the first four feature was used as final GLCM feature, and window size for GLCM set to be 15 was preferred. Multi-scale and multidirectional Gabor texture with max frequency set to be 1HZ was derived. For LBP, the operator LBP16, 2 with rotation invariance was tested to be the best. Finally, five schemes combine these spectral and textural features as inputs of classifier were evaluated in term of classification accuracy. Six categories including tea plantation, forest, roads, water, build-up, bare soil, shadows were classified by support vector machine. The result showed that overall accuracy range from 75.55% to 89.11%, Kappa coefficient range from 0.613 to 0.843, for plantation, user accuracy range from 84.95% to 100%, producer accuracy range from 53.29% to 91.53%. Gaofen-2 show its capacity to map the tea plantation area accurately. Schemes utilized spectral and textural features together perform much better than that utilized spectral only. The scheme combination of band1, band 3, ban4, DNDVI, LBP_Gabor outperformed other Scheme, with the highest overall accuracy and Kappa coefficient. The textures feature of high resolution image helps to improve the accuracy, and the way to construct suitable texture feature and merge different texture feature deserved study more. The proposed method to extract tea plantation is applicable at administrative level of country.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128084583","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 : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820227
Di Jiang, Xiaoyu Zhang, Haoji Hu, Wen Xu
Understanding suspended sediment concentration (SSC) distribution is of great significance to the comprehensive management of offshore engineering, structure safety and landsea interaction material flux. Combing satellite remote sensing, which has the advantage on quickly and dynamically obtaining the spatial distribution of sea surface SSC with high spatial resolution and large scale spatial coverage, with the acoustic-based method, which is able to obtain high temporal and spatial resolution data along the vertical water column profile, has been proved as promising in obtaining three-dimensional SSC distribution in the target area. In this paper, based on the sea surface SSC map inversed from GF-1 satellite data, we intend to design optimal sampling route for acoustic-based in-situ measurement to maximize the environmental information with the least experiment cost. An optimal shipping path planning algorithm is proposed, in which the Kriging variance is utilized as a reward function to find the most informative sampling points, and the optimal sampling path is then planned to bring the ship as close as possible to those sampling points concerning the cost constraint. Meanwhile, we also use Voronoi polygon to accelerate the operation. The effectiveness of the algorithm is verified by the in-situ measurement near Zhoushan island. A 3D SSC map is then produced with satellite inversed surface SSC and subsurface SSC along the depth profile measured by acoustic based in-situ measurements in the planned optimal sampling routine. We also test the algorithm in a wider sea area with more complicated hydrodynamic environment based on the satellite SSC and proved to be suitable for supplementation of large-scale measurement network.
{"title":"3D Suspended Sediment Concentration Mapping through GF-1 Satellite Image and Kriging-based Optimal Shipping Path Planning for Acoustic Subsurface Measurements","authors":"Di Jiang, Xiaoyu Zhang, Haoji Hu, Wen Xu","doi":"10.1109/Agro-Geoinformatics.2019.8820227","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820227","url":null,"abstract":"Understanding suspended sediment concentration (SSC) distribution is of great significance to the comprehensive management of offshore engineering, structure safety and landsea interaction material flux. Combing satellite remote sensing, which has the advantage on quickly and dynamically obtaining the spatial distribution of sea surface SSC with high spatial resolution and large scale spatial coverage, with the acoustic-based method, which is able to obtain high temporal and spatial resolution data along the vertical water column profile, has been proved as promising in obtaining three-dimensional SSC distribution in the target area. In this paper, based on the sea surface SSC map inversed from GF-1 satellite data, we intend to design optimal sampling route for acoustic-based in-situ measurement to maximize the environmental information with the least experiment cost. An optimal shipping path planning algorithm is proposed, in which the Kriging variance is utilized as a reward function to find the most informative sampling points, and the optimal sampling path is then planned to bring the ship as close as possible to those sampling points concerning the cost constraint. Meanwhile, we also use Voronoi polygon to accelerate the operation. The effectiveness of the algorithm is verified by the in-situ measurement near Zhoushan island. A 3D SSC map is then produced with satellite inversed surface SSC and subsurface SSC along the depth profile measured by acoustic based in-situ measurements in the planned optimal sampling routine. We also test the algorithm in a wider sea area with more complicated hydrodynamic environment based on the satellite SSC and proved to be suitable for supplementation of large-scale measurement network.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124026457","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 : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820566
Asli Uzun, B. Ustaoğlu
Turkey ranks the 5th in the world in terms of total olive fields, and the 4th in terms of olive production. Although this ranking varies over the years because of the periodicity feature of the olive, Turkey is an important olive producer country in Mediterranean. The olive tree (Olea europaea L.) is a member of the maquis community that is involved in the natural vegetation of the Mediterranean climate. It is accepted as a bioindicator that characterizes this zone because of its good adaptation to the Mediterranean climate. According to the report of the World Meteorological Organization (WMO), the year 2016 was determined as the year with the highest global average temperatures (1880-2018). It is considered that the variability in climatic conditions and the increasing frequency of extreme weather events (extreme precipitaion, floods, extreme temperatures, heat waves, hail, etc.) that have been occurring frequently in recent years are associated with the changes in the large-scale pressure and wind circulation and atmospheric oscillations (with direct and indirect effects, e.g. NAO-North Atlantic Oscillation, AO-Arctic Oscillation and ENSO-El Nino Southern Oscillation, etc.). In this study, the effects of Southern Oscillation (El Nino/ La Nina) and North Atlantic Oscillation (NAO) on the olive yield in Turkey will be examined. The objective of this study is to a.) determining the statistical relationship between climatic conditions and atmospheric index values during the phenological periods of olives, b) determining the effects of oscillations on yield by examining the years of strong atmospheric oscillation indexes and yield values on the line graph. To do this, the phenological periods of the olive were determined. Daily average temperature data of 48 years covering the years 1970-2017 for Adana, Osmaniye, Kahramanmaraş, Antalya, Mersin and Iskenderun meteorological stations, and daily average total rainfall data were used as the climatic data. Nino 3, Nino 3.4, Nino 4 and ONI indexes representing the El Nino activities and effective during the 1970-2017 period and the NAOI index representing the North Atlantic Oscillation were used. The relationship between the monthly average temperatures which were effective in the phenological period of olive and the atmospheric index values was statistically analyzed according to Pearson correlation coefficient method. As a result of the analyses, statistically significant relationships varying between 40-64% were found between average temperatures during the flowering and first initiation of fruit period among the phenological periods of the olive and Nino 3.4 and Nino 3 indexes. Statistically significant relationships varying between 38-60% were found between total rainfall and Nino indexes. In addition, no statistically significant relationship was found between North Atlantic Oscillation Index (NAOI) and climatic conditions. In order to determine the effect of the oscillations on yield by determinin
{"title":"Impacts of El Nino Southern Oscillation (ENSO) and North Atlantic Oscillation (NAO) on the Olive Yield in the Mediterranean Region, Turkey","authors":"Asli Uzun, B. Ustaoğlu","doi":"10.1109/Agro-Geoinformatics.2019.8820566","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820566","url":null,"abstract":"Turkey ranks the 5th in the world in terms of total olive fields, and the 4th in terms of olive production. Although this ranking varies over the years because of the periodicity feature of the olive, Turkey is an important olive producer country in Mediterranean. The olive tree (Olea europaea L.) is a member of the maquis community that is involved in the natural vegetation of the Mediterranean climate. It is accepted as a bioindicator that characterizes this zone because of its good adaptation to the Mediterranean climate. According to the report of the World Meteorological Organization (WMO), the year 2016 was determined as the year with the highest global average temperatures (1880-2018). It is considered that the variability in climatic conditions and the increasing frequency of extreme weather events (extreme precipitaion, floods, extreme temperatures, heat waves, hail, etc.) that have been occurring frequently in recent years are associated with the changes in the large-scale pressure and wind circulation and atmospheric oscillations (with direct and indirect effects, e.g. NAO-North Atlantic Oscillation, AO-Arctic Oscillation and ENSO-El Nino Southern Oscillation, etc.). In this study, the effects of Southern Oscillation (El Nino/ La Nina) and North Atlantic Oscillation (NAO) on the olive yield in Turkey will be examined. The objective of this study is to a.) determining the statistical relationship between climatic conditions and atmospheric index values during the phenological periods of olives, b) determining the effects of oscillations on yield by examining the years of strong atmospheric oscillation indexes and yield values on the line graph. To do this, the phenological periods of the olive were determined. Daily average temperature data of 48 years covering the years 1970-2017 for Adana, Osmaniye, Kahramanmaraş, Antalya, Mersin and Iskenderun meteorological stations, and daily average total rainfall data were used as the climatic data. Nino 3, Nino 3.4, Nino 4 and ONI indexes representing the El Nino activities and effective during the 1970-2017 period and the NAOI index representing the North Atlantic Oscillation were used. The relationship between the monthly average temperatures which were effective in the phenological period of olive and the atmospheric index values was statistically analyzed according to Pearson correlation coefficient method. As a result of the analyses, statistically significant relationships varying between 40-64% were found between average temperatures during the flowering and first initiation of fruit period among the phenological periods of the olive and Nino 3.4 and Nino 3 indexes. Statistically significant relationships varying between 38-60% were found between total rainfall and Nino indexes. In addition, no statistically significant relationship was found between North Atlantic Oscillation Index (NAOI) and climatic conditions. In order to determine the effect of the oscillations on yield by determinin","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115330351","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 : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820545
Bilgi Görkem Yazgaç, M. Kirci
Fractional calculus is a generalization of integration and derivation to noninteger order with a fundamental operator. Due to the extra free parameter of noninteger order $alpha$, fractional order based methods provide additional degree of freedom in optimization performance. Expectedly fractional-order based methods have find their applications in image processing field. In this work color analysis applied pomegranate and orange pictures. After color analysis edge detection is used to segment fruits in the picture. For segmentation a fractional order calculus based Sobel operator is used. The performance of the system is evaluated with respect to the noninteger order $alpha$.
{"title":"Fractional order calculus based fruit detection","authors":"Bilgi Görkem Yazgaç, M. Kirci","doi":"10.1109/Agro-Geoinformatics.2019.8820545","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820545","url":null,"abstract":"Fractional calculus is a generalization of integration and derivation to noninteger order with a fundamental operator. Due to the extra free parameter of noninteger order $alpha$, fractional order based methods provide additional degree of freedom in optimization performance. Expectedly fractional-order based methods have find their applications in image processing field. In this work color analysis applied pomegranate and orange pictures. After color analysis edge detection is used to segment fruits in the picture. For segmentation a fractional order calculus based Sobel operator is used. The performance of the system is evaluated with respect to the noninteger order $alpha$.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130641057","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：