Factors Affecting Spatial Variation of Classification Uncertainty in an Image Object-based Vegetation Mapping

2008 ◽  
Vol 74 (8) ◽  
pp. 1007-1018 ◽  
Author(s):  
Qian Yu ◽  
Peng Gong ◽  
Yong Q. Tian ◽  
Ruiliang Pu ◽  
Jun Yang
Keyword(s):  
Spatial Variation ◽  
Vegetation Mapping ◽  
Factors Affecting ◽  
Classification Uncertainty ◽  
Object Based ◽  
Image Object

scholarly journals Integration of Convolutional Neural Networks and Object-Based Post-Classification Refinement for Land Use and Land Cover Mapping with Optical and SAR Data

2019 ◽  
Vol 11 (6) ◽  
pp. 690 ◽  
Author(s):  
Shengjie Liu ◽  
Zhixin Qi ◽  
Xia Li ◽  
Anthony Yeh
Keyword(s):  
Neural Networks ◽  
Land Use ◽  
Land Cover ◽  
Convolutional Neural Networks ◽  
Spatial Resolution ◽  
Spatial Information ◽  
Object Based ◽  
Sar Data ◽  
The University ◽  
Image Object

Object-based image analysis (OBIA) has been widely used for land use and land cover (LULC) mapping using optical and synthetic aperture radar (SAR) images because it can utilize spatial information, reduce the effect of salt and pepper, and delineate LULC boundaries. With recent advances in machine learning, convolutional neural networks (CNNs) have become state-of-the-art algorithms. However, CNNs cannot be easily integrated with OBIA because the processing unit of CNNs is a rectangular image, whereas that of OBIA is an irregular image object. To obtain object-based thematic maps, this study developed a new method that integrates object-based post-classification refinement (OBPR) and CNNs for LULC mapping using Sentinel optical and SAR data. After producing the classification map by CNN, each image object was labeled with the most frequent land cover category of its pixels. The proposed method was tested on the optical-SAR Sentinel Guangzhou dataset with 10 m spatial resolution, the optical-SAR Zhuhai-Macau local climate zones (LCZ) dataset with 100 m spatial resolution, and a hyperspectral benchmark the University of Pavia with 1.3 m spatial resolution. It outperformed OBIA support vector machine (SVM) and random forest (RF). SVM and RF could benefit more from the combined use of optical and SAR data compared with CNN, whereas spatial information learned by CNN was very effective for classification. With the ability to extract spatial features and maintain object boundaries, the proposed method considerably improved the classification accuracy of urban ground targets. It achieved overall accuracy (OA) of 95.33% for the Sentinel Guangzhou dataset, OA of 77.64% for the Zhuhai-Macau LCZ dataset, and OA of 95.70% for the University of Pavia dataset with only 10 labeled samples per class.

scholarly journals A new method of vegetation mapping by object-based classification using high resolution satellite data

2006 ◽  
Vol 45 (1) ◽  
pp. 43-49 ◽  
Author(s):  
Noritoshi KAMAGATA ◽  
Keitarou HARA ◽  
Masaru MORI ◽  
Yukio AKAMATSU ◽  
Yunqing LI ◽  
...  
Keyword(s):  
High Resolution ◽  
Satellite Data ◽  
Vegetation Mapping ◽  
New Method ◽  
Object Based

scholarly journals THE USE OF SPECTRAL AND TEXTURAL FEATURES IN CROP TYPE MAPPING USING SENTINEL-2A IMAGES: A CASE STUDY, ÇUKUROVA REGION, TURKEY

2021 ◽  
Vol XLIII-B3-2021 ◽  
pp. 117-122
Author(s):  
A. Tuzcu Kokal ◽  
A. F. Sunar ◽  
A. Dervisoglu ◽  
S. Berberoglu
Keyword(s):  
Satellite Image ◽  
Support Vector ◽  
Textural Features ◽  
Factors Affecting ◽  
Object Based ◽  
Crop Types ◽  
Sentinel 2A ◽  
Occurrence Matrix ◽  
Agriculture Management ◽  
Sentinel 2

Abstract. Turkey has favorable agricultural conditions (i.e. fertile soils, climate and rainfall) and can grow almost any type of crop in many regions, making it one of the leading sectors of the economy. For sustainable agriculture management, all factors affecting the agricultural products should be analyzed on a spatial-temporal basis. Therefore, nowadays space technologies such as remote sensing are important tools in providing an accurate mapping of the agricultural fields with timely monitoring and higher repetition frequency and accuracy. In this study, object based classification method was applied to 2017 Sentinel 2 Level 2A satellite image in order to map crop types in the Adana, Çukurova region in Turkey. Support Vector Machine (SVM) was used as a classifier. Texture information were incorporated to spectral wavebands of Sentinel-2 image, to increase the classification accuracy. In this context, all of the textural features of Gray-Level Co-occurrence Matrix (GLCM) were tested and Entropy, Standard deviation, and Mean textural features were found to be the most suitable among them. Multi-spectral and textural features were used as an input separately and/or in combination to evaluate the potential of texture in differentiating crop types and the accuracy of output thematic maps. As a result, with the addition of textural features, it was observed that the Overall Accuracy and Kappa coefficient increased by 7% and 8%, respectively.

scholarly journals Factors Affecting Spatial Variation of Annual Apparent Q10 of Soil Respiration in Two Warm Temperate Forests

PLoS ONE ◽  
2013 ◽  
Vol 8 (5) ◽  
pp. e64167 ◽  
Author(s):  
Junwei Luan ◽  
Shirong Liu ◽  
Jingxin Wang ◽  
Xueling Zhu
Keyword(s):  
Soil Respiration ◽  
Spatial Variation ◽  
Temperate Forests ◽  
Factors Affecting ◽  
Warm Temperate

scholarly journals Object-Based Window Strategy in Thermal Sharpening

2019 ◽  
Vol 11 (6) ◽  
pp. 634 ◽  
Author(s):  
Haiping Xia ◽  
Yunhao Chen ◽  
Jinling Quan ◽  
Jing Li
Keyword(s):  
High Resolution ◽  
Land Surface ◽  
Urban Areas ◽  
Simulated Data ◽  
Window Size ◽  
Landsat 8 ◽  
Factors Affecting ◽  
Object Based ◽  
Land Surface Temperatures ◽  
The Mean

The trade-off between spatial and temporal resolutions has led to the disaggregation of remotely sensed land surface temperatures (LSTs) for better applications. The window used for regression is one of the primary factors affecting the disaggregation accuracy. Global window strategies (GWSs) and local window strategies (LWSs) have been widely used and discussed, while object-based window strategies (OWSs) have rarely been considered. Therefore, this study presents an OWS based on a segmentation algorithm and provides a basis for selecting an optimal window size balancing both accuracy and efficiency. The OWS is tested with Landsat 8 data and simulated data via the “aggregation-then-disaggregation” strategy, and compared with the GWS and LWS. Results tested with the Landsat 8 data indicate that the proposed OWS can accurately and efficiently generate high-resolution LSTs. In comparison to the GWS, the OWS improves the mean accuracy by 0.19 K at different downscaling ratios, in particular by 0.30 K over urban areas; compared with the LWS, the OWS performs better in most cases but performs slightly worse due to the increasing downscaling ratio in some cases. Results tested with the simulated data indicate that the OWS is always superior to both GWS and LWS regardless of the downscaling ratios, and the OWS improves the mean accuracy by 0.44 K and 0.19 K in comparison to the GWS and LWS, respectively. These findings suggest the potential ability of the OWS to generate super-high-resolution LSTs over heterogeneous regions when the pixels within the object-based windows derived via segmentation algorithms are more homogenous.

Sign in / Sign up

Export Citation Format

Share Document