Using Support Vector Machine to Monitor Behavior of an Object Based WSN System

2019 ◽  
pp. 174-185
Author(s):  
Nga Ly-Tu ◽  
Qui Vo-Phu ◽  
Thuong Le-Tien
Keyword(s):  
Support Vector Machine ◽  
Support Vector ◽  
Object Based

Pixel and object-based classification approaches for mapping forest fuel types in Tenerife Island from ASTER data

2013 ◽  
Vol 22 (3) ◽  
pp. 306 ◽  
Author(s):  
Alfonso Alonso-Benito ◽  
Lara A. Arroyo ◽  
Manuel Arbelo ◽  
Pedro Hernández-Leal ◽  
Alejandro González-Calvo
Keyword(s):  
Support Vector Machine ◽  
Image Analysis ◽  
National Forest Inventory ◽  
Support Vector ◽  
Fire Behaviour ◽  
Object Based Image Analysis ◽  
Object Based ◽  
Forest Fuel ◽  
Tenerife Island ◽  
Representative Area

Four classification algorithms have been assessed and compared with mapped forest fuel types from Terra-ASTER sensor images in a representative area of Tenerife Island (Canary Islands, Spain). A BEHAVE fuel-type map from 2002, together with field data also obtained in 2002 during the Third Spanish National Forest Inventory, was used as reference data. The BEHAVE fuel types of the reference dataset were first converted into the Fire Behaviour Fuel Types described by Scott and Burgan, taking into account the vegetation of the study area. Then, three pixel-based algorithms (Maximum Likelihood, Neural Network and Support Vector Machine) and an Object-Based Image Analysis were applied to classify the Scott and Burgan fire behaviour fuel types from an ASTER image from 3 March 2003. The performance of the algorithms tested was assessed and compared in terms of quantity disagreement and allocation disagreement. Within the pixel-based classifications, the best results were obtained from the Support Vector Machine algorithm, which showed an overall accuracy of 83%; 14% of disagreement was due to allocation and 3% to quantity disagreement. The Object-Based Image Analysis approach produced the most accurate maps, with an overall accuracy of 95%; 4% disagreement was due to allocation and 1% to quantity disagreement. The object-based classification achieved thus an overall accuracy of 12% above the best results obtained for the pixel-based algorithms tested. The incorporation of context information to the object-based classification allowed better identification of fuel types with similar spectral behaviour.

scholarly journals A Novel Class-Specific Object-Based Method for Urban Change Detection Using High-Resolution Remote Sensing Imagery

2021 ◽  
Vol 87 (4) ◽  
pp. 249-262
Author(s):  
Ting Bai ◽  
Kaimin Sun ◽  
Wenzhuo Li ◽  
Deren Li ◽  
Yepei Chen ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
High Resolution ◽  
Land Cover ◽  
Change Detection ◽  
Urban Areas ◽  
Support Vector ◽  
Change Type ◽  
Optimal Classifier ◽  
Object Based ◽  
Specific Object

A single-scale object-based change-detection classifier can distinguish only global changes in land cover, not the more granular and local changes in urban areas. To overcome this issue, a novel class-specific object-based change-detection method is proposed. This method includes three steps: class-specific scale selection, class-specific classifier selection, and land cover change detection. The first step combines multi-resolution segmentation and a random forest to select the optimal scale for each change type in land cover. The second step links multi-scale hierarchical sampling with a classifier such as random forest, support vector machine, gradient-boosting decision tree, or Adaboost; the algorithm automatically selects the optimal classifier for each change type in land cover. The final step employs the optimal classifier to detect binary changes and from-to changes for each change type in land cover. To validate the proposed method, we applied it to two high-resolution data sets in urban areas and compared the change-detection results of our proposed method with that of principal component analysis k-means, object-based change vector analysis, and support vector machine. The experimental results show that our proposed method is more accurate than the other methods. The proposed method can address the high levels of complexity found in urban areas, although it requires historical land cover maps as auxiliary data.

scholarly journals PERBANDINGAN METODE KLASIFIKASI PENUTUP LAHAN BERBASIS PIKSEL DAN BERBASIS OBYEK MENGGUNAKAN DATA PiSAR-L2

2016 ◽  
Vol 13 (1) ◽  
Author(s):  
R. Johannes Manalu ◽  
Ahmad Sutanto ◽  
Bambang Trisakti
Keyword(s):  
Support Vector Machine ◽  
Maximum Likelihood ◽  
Synthetic Aperture Radar ◽  
Spatial Resolution ◽  
Synthetic Aperture ◽  
Support Vector ◽  
Object Based ◽  
Mixed Pixels ◽  
Salt And Pepper ◽  
Neighbor Classifier

PiSAR-L2 program is an experimental program for PALSAR-2 sensor installed on ALOS-2. Research collaboration had been conducted between the Japan Aerospace Exploration Agency (JAXA) and Ministry for Research and Technology of Indonesia in 2012 to assess the ability of PiSAR-L2 data for some applications. This paper explores the utilization of PiSAR-L2 data for land cover classification in forest area using pixel-based and object-based methods, then carried out comparison between the two methods. PiSAR-L2 data full polarization with 2.1 level for Riau province was used. Field data conducted by JAXA team and landcover map from WWF were used as references to collect input and evaluation sample. Pre-processing was done by doing backscatter conversion and filtering, then classification was conducted and it`s accuracy was tested. Two methods were used, 1) Maximum Likelihood Enhance Neighbor classifier for pixel-based and 2) Support Vector Machine for object based classification. The effect of spatial resolution on classification result was also analyzed. The results show that pixel-based produced mixed pixels "salt and pepper", the classification accuracies were 62% for 2.5 m and 83% for 10 m spatial resolution. While the object-based has some advantages: high homogeneity (absence of mixed pixels), clear and sharp boundary among classes, and high accuracy (97% for 10 m spatial resolution), although it was still found errors in some classes. Abstrak Program Polarimetric Interferometric Airborne Synthetic Aperture Radar of L-band version 2 (PiSAR-L2) adalah program eksperimen sensor Phased-Array Synthetic Aperture RADAR-2 (PALSAR-2) yang dipasang pada satelit Advanced Land Observing Satellite-2 (ALOS-2). Kerjasama riset telah dilakukan antara JAXA dan Kementerian Riset dan Teknologi pada 2012 untuk mengkaji kemampuan data PiSAR L-2 yang direkam menggunakan pesawat untuk beberapa aplikasi. Kegiatan ini menggunakan data PiSAR L-2 untuk klasifikasi penutup lahan di wilayah hutan dengan metode klasifikasi berbasis piksel dan berbasis obyek, kemudian membandingkan kedua metode tersebut. Data yang digunakan adalah data PiSAR L-2 polarisasi penuh dengan level 2.1 untuk wilayah Provinsi Riau. Data lapangan diperoleh dari survei lapangan tim JAXA dan peta penutup lahan dari World Wildlife Fund  dijadikan sebagai referensi untuk sampel masukan dan pengujian. Pengolahan awal melakukan konversi backscatter dan filtering, kemudian melakukan klasifikasi dan uji akurasi. Dua metode klasifikasi yang digunakan, 1) Metode Maximum Likelihood Enhance Neighbor classifier untuk klasifikasi berbasis piksel dan 2) Metode Support Vector Machine untuk klasifikasi berbasis obyek. Pada kegiatan ini dilakukan analisis pengaruh resolusi spasial terhadap hasil klasifikasi. Hasil memperlihatkan bahwa metode berbasis piksel mempunyai piksel bercampur “salt and pepper”, akurasi klasifikasi adalah 62% untuk spasial resolusi 2.5 m dan 83% untuk spasial resolusi 10 m. Sedangkan klasifikasi berbasis obyek mempunyai kelebihan dengan homogenitas obyek yang tinggi (tidak adanya piksel bercampur), batas antara kelas yang jelas dan tegas, serta akurasi yang tinggi (97% untuk resolusi spasial 10 m), walau masih ada kesalahan pada beberapa kelas penutup lahan.

scholarly journals KLASIFIKASI MANGROVE BERBASIS OBJEK DAN PIKSEL MENGGUNAKAN CITRA SENTINEL-2B DI SUNGAI LIONG, BENGKALIS, PROVINSI RIAU

2018 ◽  
Vol 10 (3) ◽  
pp. 601-615
Author(s):  
. Rosmasita ◽  
Vincentius P. Siregar ◽  
Syamsul B. Agus
Keyword(s):  
Support Vector Machine ◽  
Land Cover ◽  
Unmanned Aerial Vehicle ◽  
Spatial Data ◽  
Data Availability ◽  
Support Vector ◽  
Object Based ◽  
Svm Algorithm ◽  
Aerial Vehicle ◽  
Increase In Accuracy

ABSTRAK Penelitian pemetaan mangrove di Sungai Liong, Bengkalis Provinsi Riau sangat terbatas, sehingga ketersediaan data spasial di wilayah ini masih sangat terbatas. Pemanfaatan citra satelit dapat dijadikan alternatif dalam menyediakan data spasial secara efektif dan efesien. Penelitian ini bertujuan untuk memetakan mangrove sampai tingkat komunitas menggunakan citra sentinel 2B dengan metode klasifikasi berbasis objek/OBIA dan membandingkannya dengan teknik klasifikasi berbasis piksel. Algoritma yang digunakan pada penelitian ini adalah support vector machine (SVM). Pengembangan skema klasifikasi mangrove pada penelitian ini di bagi menjadi 2 level, yaitu kelas penutup lahan di sekitar mangrove dan kelas komunitas mangrove. Data yang digunakan untuk klasifikasi kelas penutup lahan adalah data foto udara yang diperoleh dengan menggunakan pesawat tanpa awak (unmanned aerial vehicle/UAV) dan untuk klasifikasi komunitas menggunakan data transek tahun 2013. Akurasi keseluruhan  (OA) yang diperoleh untuk klafikasi penutup lahan mangrove dengan kedua teknik klasifikasi berbasis objek dan piksel berturut-turut adalah 78,7% dan 70,9%. Sedangkan akurasi keseluruhan (OA) untuk klasifikasi komunitas mangrove berbasis objek dan piksel berutru-turut yaitu 76,6% dan 75,0%. Sekitar 7,8% peningkatan akurasi pemetaan penutup lahan dan sekitar 1,6% peningkatan akurasi pemetaan komunitas mangrove yang diperoleh dengan metode klasifikasi berbasis objek. ABSTRACTResearch on mangrove mapping at the Liong River Bengkalis Riau Province was very limited, therefore the spatial data availability of mangrove in Liong River is also very limited. The use of satellite remote sensing to map mangrove has become widespread as it can provide accurate, effecient, and repeatable assessments. The purposed of this study was to map mangrove at the community level using sentinel 2B imagery based on object-based classification method (OBIA) and it compared pixel-based classification at Liong River, Bengkalis, Riau Provinc. This study was used support vector machine (SVM) algorithm. The scheme classification use is that land cover and mangrove community. The classification data of land cover was collected using unmanned aerial vehicle (UAV) and community mangrove was using transect data of 2013. The result of land cover classification and community mangrove indicated that object-based classification technique was better than pixel-based classification. The highest an overall accuracy of land cover is 78.7% versus 70.9%, whereas mangrove community is 76.6 versus 75.0%. Approximately 7.8% increase in accuracy can be achieved by object-based method of classification for land cover and 1.6% for mangrove community.

Sign in / Sign up

Export Citation Format

Share Document