检索结果-内蒙古大学图书馆

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Li, Zhiqing Li, Erzhu Su, Zhigang Xu, Tianyu Jiangsu Normal Univ Sch Geog Geomat & Planning Xuzhou 221116 Jiangsu Peoples R China Zhengyuan Geomat Grp Co Ltd Shandong Branch Jinan 250101 Shandong Peoples R China

ISBN: (数字)9781665427920

ISBN: (纸本)9781665427920

Land cover and land use (LULC) classification of very fine spatial resolution remote sensing images is a challenging task. Though the object-based convolutional neural network (OCNN) has proven to be an effective method for LULC classification, it still has some shortcomings. For example, it is difficult to achieve a well-segmented result with few parameter adjustments. Besides, the traditional convolutional neural network (CNN) is hard to make full use of the spectral information in the remote sensing images. To this end, we propose an improved LULC classification method. Specifically, an adaptive segmentation algorithm is used to automatically adjust segmentation parameters to achieve the best-segmented results. Due to the different areas and shapes in segmented units, a unique sample extraction method is proposed to better extract representative samples. For better classification, a new CNN model is also constructed to fully use spectral information. The proposed method has been validated on two real remote sensing images and achieved excellent classification performance.

关键词： object-based image analysis sample extraction land cover classification

来源：评论

学校读者我要写书评

暂无评论

Combining OBIA approach and Machine Learning algorithm to extract photovoltaic panels from Sentinel-2 images automatically 24

Combining OBIA approach and Machine Learning algorithm to ex...

引用

Conference on Remote Sensing for Agriculture, Ecosystems, and Hydrology XXIV Part of SPIE Remote Sensing Conferene

作者： Ladisa, Claudio Capolupo, Alessandra Ripa, Maria Nicolina Tarantino, Eufemia Politecn Bari Dept Civil Environm Land Construct & Chem DICATEC Via Orabona 4 I-70125 Bari Italy Univ Tuscia Dept Agr & Forest Sci DAFNE Via S Camillo de Lellis Snc I-01100 Viterbo Italy

ISBN: (纸本)9781510655287;9781510655270

The Energy Union Framework Strategy is pushing the entire world to move from fossil fuels to renewable energy to tackle climate changes and mitigate their effects. Among the clean energy alternatives, the sun is recognized as the most abundant and inexhaustible source and the energy production can be carried out through photovoltaic panels. Nevertheless, such a solar park requires the use of large land areas, stolen, in such a way, from food production, which demand has strongly increased in the last few years due to the growing world population. Thus, agrophotovoltaic systems, also known as agrivoltaic structures, are under way to meet the above-mentioned needs synergistically. This has led to the necessity of monitoring solar panels amount and allocation. Their detection is challenging since, albeit their spectral signature is totally different from that one emitted from other land covers, their occurrence received little attention in the field of remote sensing. Thus, in this study, a proper rule-based model for distinguishing photovoltaic panels developed on eCognition environment was proposed. Such a model is based on the combination of object-based image analysis and machine learning algorithm. Indeed, after optimizing segmentation parameters and analyzing morphological features of the panels, the Random Forest classification algorithm was implemented. Lastly, classification accuracy was evaluated. The experimentation was conducted on the study area of Viterbo (Lazio Region, Italy) by adopting open medium-resolution satellite data (Sentinel 2). This research showed promising results in classifying targets for almost all months of the time series, except for the months of October and November where there is a lowering of the accuracy value due to the variability of spectral signatures.

关键词： object-based image analysis Sentinel 2 medium-resolution satellite images photovoltaic panels

来源：评论

学校读者我要写书评

暂无评论

Machine learning and multi-sensor data fusion for mapping lithology: A case study of Kowli-kosh area, SW Iran

引用

ADVANCES IN SPACE RESEARCH 2021年第10期68卷 3992-4015页

作者： Shayeganpour, Samira Tangestani, Majid H. Gorsevski, Pece V. Shiraz Univ Fac Sci Dept Earth Sci Shiraz Iran Bowling Green State Univ Dept Geog Bowling Green OH 43403 USA

Lithological maps derived from traditional pixel-based image analysis are widely established in remote sensing. Recent development of new segmentation-based approaches such as object-based image analysis (OBIA) has led to significant improvements of accuracy in land cover classifications. However, additional enhancements have been reported by coupling OBIA with machine learning (ML) techniques. ML which automates computer algorithms and model building, enables learning, reasoning, and decision making through analysis and interpretation of data patterns and structures. This study is an attempt for evaluating and comparing the performances of four ML classifiers, including support vector machine (SVM), normal Bayes (NB), k-nearest neighbor (k-NN), and random forest (RF). This approach was tested with medium resolution imagery using an object-based classification procedure in a metamorphic complex, SW Iran. The multi-band input datasets were assembled form individual and multi-sensor layers from ASTER, Landsat 8 OLI, Sentinel-1 and Sentinel-2A. Results revealed that combined data sets obtain more reasonable classes for lithology, and combination of ASTER + simulated panchromatic of Sentinel-2A data shows the most efficient results. We also showed that, in general, RF and SVM algorithms were the most advantageous classifiers when using an object-based image analysis approach. When integrating the data sets aiming improvement of spatial resolution, the maximum accuracies of RF, SVM, k-NN and NB algorithms increased from 90% to 98%, 81% to 97%, 52 to 75%, and 40% to 64%, respectively. We also revealed that the integration of Sentinel-1 and Sentinel-2A data was promising and allowed for additional extraction of rock relief. (C) 2021 COSPAR. Published by Elsevier B.V. All rights reserved.

关键词： Lithology Machine learning Classification object-based image analysis Sentinel ASTER

来源：评论

学校读者我要写书评

暂无评论

Quantifying the Long-Term Expansion and Dieback of Spartina Alterniflora Using Google Earth Engine and object-based Hierarchical Random Forest Classification

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2021年 14卷 9781-9793页

作者： Yan, Dandan Li, Jingtai Yao, Xiuying Luan, Zhaoqing Nanjing Forestry Univ Coll Biol & Environm Coinnovat Ctr Sustainable Forestry Southern China Nanjing 210037 Peoples R China

The overwhelming spread of Spartina alterniflora (S. alterniflora) (smooth cordgrass) over recent decades has put many native plant communities and coastal environments at risk. Therefore, long-term monitoring of S. alterniflora dynamics is necessary to better understand and manage the invasion of the species. However, it is difficult to map Spartina saltmarshes in China on an annual or multiyear epoch basis. To address this issue, we developed a classification approach integrating Google Earth Engine (GEE) and object-based hierarchical random forest (RF) classification, and we applied this approach to quantify the expansion and dieback of S. alterniflora at Dafeng Milu National Nature Reserve, Jiangsu, China during 1993-2020. Results showed that the area of S. alterniflora expanded from 24.48 ha in 1993 to 1564.96 ha in 2010. However, after ecological hydrological engineering and an increase in Elaphures davidianus (Pere David's deer) numbers in 2011, the S. alterniflora area decreased significantly to 944.28 ha in 2020. During 2011-2020, the S. alterniflora area decreased substantially at a rate of 67 ha per year and by 86% in one area studied in Dafeng Milu National Nature Reserve. In 2020, the 944.28 ha of S. alterniflora in the reserve was mainly distributed in mudflats by the sea. Overall, these results show that it is feasible to identify S. alterniflora using the GEE platform and object-based hierarchical RF classification;moreover, this approach could improve understanding and management of this invasion species.

关键词： Earth Remote sensing Artificial satellites Radio frequency Wetlands Forestry Sea measurements Dafeng milu national nature reserve Google Earth Engine landsat object-based image analysis random forest (RF) spartina alterniflora

来源：评论

学校读者我要写书评

暂无评论

Improving hyperspectral image segmentation by applying inverse noise weighting and outlier removal for optimal scale selection

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2021年 171卷 348-366页

作者： Dao, Phuong D. Mantripragada, Kiran He, Yuhong Qureshi, Faisal Z. Univ Toronto Dept Geog Geomat & Environm 3359 Mississauga Rd Mississauga ON L5L 1C6 Canada Univ Toronto Sch Environm 33 Willcocks St Toronto ON M5S 3E8 Canada Ontario Tech Univ Fac Sci 2000 Simcoe St North Oshawa ON L1G OC5 Canada

Optimal scale selection for image segmentation is an essential component of the object-based image analysis (OBIA) and interpretation. An optimal segmentation scale is a scale at which image objects, overall, best represent real-world ground objects and features across the entire image. At this scale, the intra-object variance is ideally lowest and the inter-object spatial autocorrelation is ideally highest, and a change in the scale could cause an abrupt change in these measures. Unsupervised parameter optimization methods typically use global measures of spatial and spectral properties calculated from all image objects in all bands as the target criteria to determine the optimal segmentation scale. However, no studies consider the effect of noise in image spectral bands on the segmentation assessment and scale selection. Furthermore, these global measures could be affected by outliers or extreme values from a small number of objects. These issues may lead to incorrect assessment and selection of optimal scales and cause the uncertainties in subsequent segmentation and classification results. These issues become more pronounced when segmenting hyperspectral data with large spectral variability across the spectrum. In this study, we propose an enhanced method that 1) incorporates the band's inverse noise weighting in the segmentation and 2) detects and removes outliers before determining segmentation scale parameters. The proposed method is evaluated on three well-established segmentation approaches k-means, mean-shift, and watershed. The generated segments are validated by comparing them with reference polygons using normalized over-segmentation (OS), under-segmentation (US), and the Euclidean Distance (ED) indices. The results demonstrate that this proposed scale selection method produces more accurate and reliable segmentation results. The approach can be applied to other segmentation selection criteria and are useful for automatic multi-parameter tuning and opti

关键词： Inverse noise weighting Outlier detection Optimal scale selection image segmentation object-based image analysis Hyperspectral image classification

来源：评论

学校读者我要写书评

暂无评论

Discrepancy measures for selecting optimal combination of parameter values in object-based image analysis

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2012年第1期68卷 144-156页

作者： Liu, Yong Bian, Ling Meng, Yuhong Wang, Huanping Zhang, Shifu Yang, Yining Shao, Xiaomin Wang, Bo Lanzhou Univ Coll Earth & Environm Sci Lanzhou 730000 Peoples R China SUNY Buffalo Dept Geog Amherst NY 14261 USA

Most object-based image analysis use parameters to control the size, shape, and homogeneity of segments. Because each parameter may take a range of possible values, different combinations of value between parameters may produce different segmentation results. Assessment of segmentation quality, such as the discrepancy between reference polygons and corresponding image segments, can be used to identify the optimal combination of parameter values. In this research, we (1) evaluate four existing indices that describe the discrepancy between reference polygons and corresponding segments, (2) propose three new indices to evaluate both geometric and arithmetic discrepancies, and (3) compare the effectiveness of the existing and proposed indices in identifying optimal combinations of parameter values for image segmentation through a case study. A Landsat 5 Thematic Mapper (TM) image and an ALOS image of arid Northwestern China were used in the case study. The four existing indices include Quality Rate (QR), Over-segmentation Rate (OR), Under-segmentation Rate (UR), and Euclidean Distance 1 (ED1). The three proposed discrepancy indices include Potential Segmentation Error (PSE), Number-of-Segments Ratio (NSR), and Euclidean Distance 2 (ED2). These indices measure overlap, over-segmentation, and under-segmentation between reference polygons and corresponding image segments. Results show that the three proposed indices PSE, NSR, and ED2 are more effective than the four existing indices QR, OR, UR, and ED1 in their ability to identify optimal combinations of parameter values. ED2 that represents both geometric (PSE) and arithmetic (NSR) discrepancies is most effective. (C) 2012 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS) Published by Elsevier B.V. All rights reserved.

关键词： object-based image analysis image segmentation Discrepancy measures Optimal parameter value combinations Under-segmentation Over-segmentation

来源：评论

学校读者我要写书评

暂无评论

Discriminating crops/weeds in an upland rice field from UAV images with the SLIC-RF algorithm

引用

PLANT PRODUCTION SCIENCE 2021年第2期24卷 198-215页

作者： Kawamura, Kensuke Asai, Hidetoshi Yasuda, Taisuke Soisouvanh, Pheunphit Phongchanmixay, Sengthong Japan Int Res Ctr Agr Sci JIRCAS Tsukuba Ibaraki Japan Yamanashi Prefectural Govt Mt Fuji Res Inst Fujiyoshida Yamanashi Japan Natl Agr & Forestry Res Inst NAFRI Rice Res Ctr Viangchan Laos

In this study, we propose a method for discriminating crops/weeds in upland rice fields using a commercial unmanned aerial vehicles (UAVs) and red-green-blue (RGB) cameras with the simple linear iterative clustering (SLIC) algorithm and random forest (RF) classifier. In the SLIC-RF algorithm, we evaluated different combinations of input features: three color spaces (RGB, hue-saturation-brightness [HSV], CIE-L*a*b), canopy height model (CHM), spatial texture (Texture) and four vegetation indices (VIs) (excess green [ExG], excess red [ExR], green-red vegetation index [GRVI] and color index of vegetation extraction [CIVE]). Among the color spaces, the HSV-based SLIC-RF model showed the best performance with the highest out-of-bag (OOB) accuracy (0.904). The classification accuracy was improved by the combination of HSV with CHM, Texture, ExG, or CIVE. The highest OOB accuracy (0.915) was obtained from the HSV+Texture combination. The greatest errors from the confusion matrix occurred in the classification between crops and weeds, while soil could be classified with a very high accuracy. These results suggest that with the SLIC-RF algorithm developed in this study, rice and weeds can be discriminated by consumer-grade UAV images with acceptable accuracy to meet the needs of site-specific weed management (SSWM) even in the early growth stages of small rice plants..

关键词： Laos machine learning object-based image analysis weed management

来源：评论

学校读者我要写书评

暂无评论

object-based crop classification in Hetao plain using random forest

引用

EARTH SCIENCE INFORMATICS 2021年第1期14卷 119-131页

作者： Su, Tengfei Zhang, Shengwei Inner Mongolia Agr Univ Coll Water Conservancy & Civil Engn 306 Zhaowuda Rd Hohhot Peoples R China Inner Mongolia Autonomous Reg Key Lab Big Data Re 306 Zhaowuda Rd Hohhot Peoples R China

Crop classification based on object-based image analysis (OBIA) is increasingly reported. However, it is still challenging to produce high-quality crop type maps by using recent techniques. This article introduces a new object-based crop classification algorithm which contains 4 steps. First, a random forest (RF) classifier is trained by using the initial training set, which tends to have a relatively small size. Second, importance scores for each feature variable are derived by using the RF model. Third, by treating the importance scores as weighting factors, a weighted Euclidean distance criterion is designed and used for sample creation to enlarge training set. Fourth, RF is re-trained by using the enlarged training set, and then it is employed for final classification. To validate the proposed strategy, a Worldview-2 image covering a part of Hetao plain is experimented. Results indicate that the new method yields the best overall accuracy, which equals 90.52%.

关键词： object-based image analysis Crop classification Random forest

来源：评论

学校读者我要写书评

暂无评论

Detection of Oil Pollution Using SAR and Optical Remote Sensing imagery: A Case Study of the Persian Gulf

引用

JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING 2021年第10期49卷 2377-2385页

作者： Mohammadi, Mina Sharifi, Alireza Hosseingholizadeh, Mohammad Tariq, Aqil Shahid Rajaee Teacher Training Univ Fac Civil Engn Dept Surveying Engn Tehran Iran Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430079 Peoples R China

The coastal regions in the Persian Gulf are renowned for having the largest oil reserves. Pipelines, as a means of oil transportation, are one of the most common options for transporting petroleum products in these regions. Hence, the risk of oil spill pollution has become a vital challenge for local authorities, which has gradually increased since the last decade. Therefore, it is essential to use a method for timely detection of oil spills to prevent environmental damage. In this study, Sentinel-1 SAR data and Sentinel-2 image have been used for timely detection of oil slicks in the Persian Gulf. The area of oil pollution that extracted from Sentinel-2 (optical data), Sentinel-1 (SAR data), and field data is 114.7, 98.5, and 124.7 square kilometres, respectively. The results indicated that the object-based image analysis (OBIA) method using optical data had better results than using SAR data. In addition, the results indicated that the OBIA could be used as a method to produce ground truth map. Therefore, this research demonstrates the applicability of remote sensing data to recognize oil spill pollution on the surface of the water with the applicability of Sentinel-1 and Sentinel-2 data.

关键词： Oil spill detection object-based image analysis Sentinel-1 Sentinel-2 Remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Combination of OBIA and Random Forest based on Visible UAV Remote Sensing for Accurately Extracted Information about Weeds in Areas with Different Weed Densities in Farmland

引用

REMOTE SENSING 2023年第19期15卷 4696页

作者： Feng, Chao Zhang, Wenjiang Deng, Hui Dong, Lei Zhang, Houxi Tang, Ling Zheng, Yu Zhao, Zihan Chengdu Univ Technol Coll Earth Sci Chengdu 610059 Peoples R China Tibet Autonomous Reg Geol Min Explorat & Dev Bur 2 Geol Team Lhasa 850007 Peoples R China Fujian Agr & Forestry Univ Coll Forestry Fuzhou 350002 Peoples R China

Weeds have a significant impact on the growth of rice. Accurate information about weed infestations can provide farmers with important information to facilitate the precise use of chemicals. In this study, we utilized visible light images captured by UAVs to extract information about weeds in areas of two densities on farmland. First, the UAV images were segmented using an optimal segmentation scale, and the spectral, texture, index, and geometric features of each segmented object were extracted. Cross-validation and recursive feature elimination techniques were combined to reduce the dimensionality of all features to obtain a better feature set. Finally, we analyzed the extraction effect of different feature dimensions based on the random forest (RF) algorithm to determine the best feature dimensions, and then we further analyzed the classification result of machine learning algorithms, such as random forest, support vector machine (SVM), decision tree (DT), and K-nearest neighbors (KNN) and compared them based on the best feature dimensions. Using the extraction results of the best classifier, we created a zoning map of the weed infestations in the study area. The results indicated that the best feature subset achieved the highest accuracy, with respective overall accuracies of 95.38% and 91.33% for areas with dense and sparse weed densities, respectively, and F1-scores of 94.20% and 90.57. Random forest provided the best extraction results for each machine learning algorithm in the two experimental areas. When compared to the other algorithms, it improved the overall accuracy by 1.74-12.14% and 7.51-11.56% for areas with dense and sparse weed densities, respectively. The F1-score improved by 1.89-17.40% and 7.85-10.80%. Therefore, the combination of object-based image analysis (OBIA) and random forest based on UAV remote sensing accurately extracted information about weeds in areas with different weed densities for farmland, providing effective information suppor

关键词： UAV remote sensing weeds random forest object-based image analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：