scholarly journals TOPIC MODELLING FOR OBJECT-BASED CLASSIFICATION OF VHR SATELLITE IMAGES BASED ON MULTISCALE SEGMENTATIONS

2016 ◽  
Vol XLI-B7 ◽  
pp. 359-363 ◽  
Author(s):  
Li Shen ◽  
Linmei Wu ◽  
Zhipeng Li
Keyword(s):  
Satellite Images ◽  
Topic Modelling ◽  
Classification Methods ◽  
Object Class ◽  
Class Label ◽  
Similarity Comparison ◽  
Object Based ◽  
Multiscale Segmentation ◽  
Better Than

Multiscale segmentation is a key prerequisite step for object-based classification methods. However, it is often not possible to determine a sole optimal scale for the image to be classified because in many cases different geo-objects and even an identical geo-object may appear at different scales in one image. In this paper, an object-based classification method based on mutliscale segmentation results in the framework of topic modelling is proposed to classify VHR satellite images in an entirely unsupervised fashion. In the stage of topic modelling, grayscale histogram distributions for each geo-object class and each segment are learned in an unsupervised manner from multiscale segments. In the stage of classification, each segment is allocated a geo-object class label by the similarity comparison between the grayscale histogram distributions of each segment and each geo-object class. Experimental results show that the proposed method can perform better than the traditional methods based on topic modelling.

scholarly journals TOPIC MODELLING FOR OBJECT-BASED CLASSIFICATION OF VHR SATELLITE IMAGES BASED ON MULTISCALE SEGMENTATIONS

2016 ◽  
Vol XLI-B7 ◽  
pp. 359-363 ◽  
Author(s):  
Li Shen ◽  
Linmei Wu ◽  
Zhipeng Li
Keyword(s):  
Satellite Images ◽  
Topic Modelling ◽  
Classification Methods ◽  
Object Class ◽  
Class Label ◽  
Similarity Comparison ◽  
Object Based ◽  
Multiscale Segmentation ◽  
Better Than

Multiscale segmentation is a key prerequisite step for object-based classification methods. However, it is often not possible to determine a sole optimal scale for the image to be classified because in many cases different geo-objects and even an identical geo-object may appear at different scales in one image. In this paper, an object-based classification method based on mutliscale segmentation results in the framework of topic modelling is proposed to classify VHR satellite images in an entirely unsupervised fashion. In the stage of topic modelling, grayscale histogram distributions for each geo-object class and each segment are learned in an unsupervised manner from multiscale segments. In the stage of classification, each segment is allocated a geo-object class label by the similarity comparison between the grayscale histogram distributions of each segment and each geo-object class. Experimental results show that the proposed method can perform better than the traditional methods based on topic modelling.

scholarly journals COMPARISON OF OBJECT BASED MACHINE LEARNING CLASSIFICATIONS OF PLANETSCOPE AND WORLDVIEW-3 SATELLITE IMAGES FOR LAND USE / COVER

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 1887-1892 ◽  
Author(s):  
A. Tuzcu ◽  
G. Taskin ◽  
N. Musaoğlu
Keyword(s):  
Land Use ◽  
Satellite Images ◽  
Saline Soil ◽  
Accuracy Assessment ◽  
Support Vector ◽  
Classification Methods ◽  
Rule Based ◽  
Object Based ◽  
Water Vegetation

<p><strong>Abstract.</strong> The purpose of the study was to compare performance of the classification methods, that are Rule Based (RB) classifier and Support Vector Machine (SVM), of Planetscope and Worldview-3 satellite images in order to produce land use / cover thematic maps. Six classes, which are deep water, shallow water, vegetation, agricultural area, soil and saline soil, were considered. After performing the classification process, accuracy assessment was employed based on the error matrices. The results showed that, both of the classification methods and satellite data were adequate to classify the area. Besides, classification accuracy was improved when Worldview-3 satellite and SVM method were used. The classification accuracies of RB classification of Planetscope and Worldview-3 were %87 and %94 respectively and the classification accuracies of SVM classification of Planetscope and Worldview-3 were %93 and %96 respectively.</p>

scholarly journals Analysis of the Influence of Vegetation Index Choice on the Classification of Satellite Images for Monitoring Forest Pathology

2020 ◽  
pp. paper49-1-paper49-12
Author(s):  
Evgeniy Trubakov ◽  
Olga Trubakova
Keyword(s):  
Satellite Images ◽  
Vegetation Index ◽  
Vegetation Indices ◽  
Multispectral Images ◽  
Classification Methods ◽  
Planted Forests ◽  
The Earth ◽  
Evaluation Algorithm ◽  
And Control

Rational use of natural resources and control over their recovery, as well as over destruction due to natural and technogenic causes, is currently one of the most urgent problems of the humanity. Forests are no exception. Multispectral images from Earth’s satellites are most often used for monitoring changes in forest planting. This is due to the fact that merging images taken in certain spectra makes it possible to recognize vegetation containing chlorophyll quite well. It also allows to detect changes in the level of chlorophyll, which shows the differences between healthy and damaged plants. Large areas of planted forests create the need to process huge amounts of data, which is difficult to do manually. One of the most important stages of image processing is the classification of objects in these images. This paper deals with various classification methods used to solve the problem of classifying images of remote sensing of the Earth. As a result, it was decided to evaluate the accuracy of classification methods on various vegetation indices. In the course of the study, the evaluation algorithm was determined, as well as one of the options for analyzing the results obtained. Conclusions were made about the work of classification methods on different vegetation indices.

Kajian Metode Klasifikasi Citra Landsat-8 untuk Pemetaan Habitat Bentik di Kepulauan Padaido, Papua

2017 ◽  
Vol 2 (1) ◽  
pp. 1 ◽  
Author(s):  
Muhammad Hafizt ◽  
Marindah Yulia Iswari ◽  
Bayu Prayudha
Keyword(s):  
Coral Reefs ◽  
Satellite Remote Sensing ◽  
Satellite Images ◽  
Habitat Mapping ◽  
Benthic Habitat ◽  
Landsat 8 ◽  
Classification Methods ◽  
Landsat 8 Oli ◽  
Remote Sensing Technique ◽  
Object Based

<strong>Assessment of Landsat-8 Classification Method for Benthic Habitat Mapping in Padaido Islands, Papua.</strong> Indonesia is the biggest archipelagic country in the world with an area of coral reefs of 39,583 km.This area has to be managed effectively and efficiently utilizing satellite remote sensing technique capable of mapping of benthic habitat coverage, such as coral reefs, seagrasses, macroalgae, and bare substrates. The technique is supported by the availability of Landsat-8 OLI satellite images that have been recording the regions of Indonesia continuously every 16 days. This research was carried out in June 2015 in parts of Padaido Islands, Papua. This area was selected due to high coral reef damages. This study utilized Landsat-8 OLI to compare two classification methods, namely pixel based and object based methods using ‘maximum 2 likelihood’ (ML) and ‘example based feature extraction’ classifications, respectively, after water column correction (Lyzenga method).  The results showed that both methods produced benthic habitat maps with 7 class covers. The pixel-based classification resulted in a better overall accuracy (47.57%) in the mapping of benthic habitats than object-based classification approach (36.17%). Thus, the ML classification is applicable for benthic habitat mapping in Padaido Islands. However, the consistency of this method must be analyzed in many diffrent locations of Indonesian waters.

A Rule-Based Approach to Sentiment Classification of Chinese Microblogging Texts

2013 ◽  
Vol 765-767 ◽  
pp. 1441-1445
Author(s):  
Jia Jun Cheng ◽  
Xin Zhang ◽  
Peng Yi Fan ◽  
Pei Li ◽  
Hui Wang
Keyword(s):  
Sentiment Classification ◽  
Classification Methods ◽  
Rule Based ◽  
Rule Based Approach ◽  
Basic Semantic ◽  
Better Than

Chinese microblogging texts are always short and casual, which bring some troubles to the traditional sentiment classification methods based on learning. To overcome this problem, we use a rule-based approach to classify the sentiment of Chinese microblogging texts. According to the characteristics of Chinese microblogging texts, we construct a thesaurus of subjective words for it, summarize the basic semantic rules expressing emotion and propose a rule-based approach to sentiment classification of Chinese microblogging texts. Finally, we compare our approach with a SVM-based approach. Our rule-based approach achieves an accuracy of 0.865, which is better than that of SVM-based approach.

Sign in / Sign up

Export Citation Format

Share Document