scholarly journals Classification of the Complex Agricultural Planting Structure with a Semi-Supervised Extreme Learning Machine Framework

2020 ◽  
Vol 12 (22) ◽  
pp. 3708 ◽  
Author(s):  
Ziyi Feng ◽  
Guanhua Huang ◽  
Daocai Chi
Keyword(s):  
Remote Sensing ◽  
Support Vector Machine ◽  
Computational Efficiency ◽  
Large Scale ◽  
Statistical Data ◽  
Support Vector ◽  
Small Scale ◽  
Remote Sensing Images ◽  
Learning Machine

Many approaches have been developed to analyze remote sensing images. However, for the classification of large-scale problems, most algorithms showed low computational efficiency and low accuracy. In this paper, the newly developed semi-supervised extreme learning machine (SS-ELM) framework with k-means clustering algorithm for image segmentation and co-training algorithm to enlarge the sample sets was used to classify the agricultural planting structure at large-scale areas. Data sets collected from a small-scale area within the Hetao Irrigation District (HID) at the upper reaches of the Yellow River basin were used to evaluate the SS-ELM framework. The results of the SS-ELM algorithm were compared with those of the random forest (RF), ELM, support vector machine (SVM) and semi-supervised support vector machine (S-SVM) algorithms. Then the SS-ELM algorithm was applied to analyze the complex planting structure of HID in 1986–2010 by comparing the remote sensing estimated results with the statistical data. In the small-scale case, the SS-ELM algorithm performed better than the RF, ELM, SVM, and S-SVM algorithms. For the SS-ELM algorithm, the average overall accuracy (OA) was in a range of 83.00–92.17%. On the contrary, for the other four algorithms, their average OA values ranged from 56.97% to 92.84%. Whereas, in the classification of planting structure in HID, the SS-ELM algorithm had an excellent performance in classification accuracy and computational efficiency for three major planting crops including maize, wheat, and sunflowers. The estimated areas by using the SS-ELM algorithm based on the remote sensing images were consistent with the statistical data, and their difference was within a range of 3–25%. This implied that the SS-ELM framework could be served as an effective method for the classification of complex planting structures with relatively fast training, good generalization, universal approximation capability, and reasonable learning accuracy.

Penentuan Luas Area Sawah Kabupaten Sleman Pada Citra Landsat 8 Operational Land Imager (OLI)

Respati ◽  
2018 ◽  
Vol 13 (3) ◽  
Author(s):  
Sulidar Fitri ◽  
Novi Nurjanah
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Support Vector Machine ◽  
Rice Field ◽  
Image Data ◽  
Rice Fields ◽  
Support Vector ◽  
Landsat 8 ◽  
Landsat 8 Oli ◽  
Learning Machine

INTISARITeknologi penginderaan jauh sangat baik dijadikan data pembuatan peta penggunaan lahan, karena kebutuhan pemetaan semakin tinggi terutama untuk mendeteksi perubahan penggunaan lahan terutama untuk penentuan luas area khususnya sawah di kabupaten Sleman. Untuk mendapatkan informasi luasan area sawah dari interpretasi citra landsat-8 OLI (Operational Land Imager) diperlukan metode khusus, terutama untuk pengolahan data citra penginderaan jauh secara digital. Salah satu metode pengolahan citra penginderaan jauh adalah metode Support Vector Machine (SVM). Metode SVM merupakan metode learning machine (Pembelajaran mesin) yang dapat mengklasifikasikan pola serta mengenali pola dari inputan atau contoh data yang diberikan dan juga termasuk ke dalam supervised learning. Hasil area sawah yang didapati dari citra Landsat 8 OLI dengan pengolahan metode SVM didapati berada di 18 kecamatan dala Kabupaten Sleman. Luasan tertinggi ada di kecamatan Ngaglik dengan 19,78 KM2 dan terendah di kecamatan Turi seluas 2,14 KM2. Nilai keseluruhan akurasi yang didapat untuk kelas lahan sawah dan area non sawah adalah adalah 53%.Kata kunci— Landsat-8 OLI, SVM, Data Citra, Geospasial, Luas Area Sawah ABSTRACTRemote sensing technology is very well used as a data for making land use maps, because mapping needs are increasingly high especially for detecting land use changes, especially for determining the area, especially rice fields in Sleman district. To get information about the area of the rice fields from the interpretation of Landsat-8 OLI (Operational Land Imager), special methods are needed, especially for processing remote sensing image data digitally. One method of processing remote sensing images is the Support Vector Machine (SVM) method. The SVM method is a learning machine method that can classify patterns and recognize patterns from input or sample data provided and also includes supervised learning. The results of the rice field that were found from the Landsat 8 OLI image by processing the SVM method were found in 18 sub-districts in Sleman Regency. The highest area is in Ngaglik sub-district with 19.78 KM2 and the lowest in Turi sub-district is 2.14 KM2. The overall value of the accuracy obtained for the class of rice field and non-rice field is 53%.Kata kunci—  Landsat-8 OLI, SVM, Image Data, Geospatial, Area of Rice Fields

scholarly journals Attention-Based Pyramid Network for Segmentation and Classification of High-Resolution and Hyperspectral Remote Sensing Images

2020 ◽  
Vol 12 (21) ◽  
pp. 3501
Author(s):  
Qingsong Xu ◽  
Xin Yuan ◽  
Chaojun Ouyang ◽  
Yue Zeng
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Image Classification ◽  
Large Scale ◽  
Feature Fusion ◽  
Spectral Information ◽  
Spatial Problem ◽  
Remote Sensing Images ◽  
Heavy Weight

Unlike conventional natural (RGB) images, the inherent large scale and complex structures of remote sensing images pose major challenges such as spatial object distribution diversity and spectral information extraction when existing models are directly applied for image classification. In this study, we develop an attention-based pyramid network for segmentation and classification of remote sensing datasets. Attention mechanisms are used to develop the following modules: (i) a novel and robust attention-based multi-scale fusion method effectively fuses useful spatial or spectral information at different and same scales; (ii) a region pyramid attention mechanism using region-based attention addresses the target geometric size diversity in large-scale remote sensing images; and (iii) cross-scale attention in our adaptive atrous spatial pyramid pooling network adapts to varied contents in a feature-embedded space. Different forms of feature fusion pyramid frameworks are established by combining these attention-based modules. First, a novel segmentation framework, called the heavy-weight spatial feature fusion pyramid network (FFPNet), is proposed to address the spatial problem of high-resolution remote sensing images. Second, an end-to-end spatial-spectral FFPNet is presented for classifying hyperspectral images. Experiments conducted on ISPRS Vaihingen and ISPRS Potsdam high-resolution datasets demonstrate the competitive segmentation accuracy achieved by the proposed heavy-weight spatial FFPNet. Furthermore, experiments on the Indian Pines and the University of Pavia hyperspectral datasets indicate that the proposed spatial-spectral FFPNet outperforms the current state-of-the-art methods in hyperspectral image classification.

Sign in / Sign up

Export Citation Format

Share Document