ARTMAP Neural Networks for Multispectral Image Classification

2000 ◽  
Vol 4 (4) ◽  
pp. 240-245
Author(s):  
Norbert Kopco ◽  
◽  
Peter Sincak ◽  
Stanislav Kaleta ◽  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Classification Accuracy ◽  
Satellite Images ◽  
Feature Space ◽  
Fuzzy Artmap ◽  
Cluster Type ◽  
The Difference ◽  
Analysis Of Performance

This paper presents an analysis of performance of several types of the ARTMAP neural network. The performance of the networks is analyzed in the task of classification of satellite images obtained by remote sensing. The analysis is concentrated on the dependence of classification accuracy on the difference in cluster type preferably identified by each of the classifiers. Three types of ARTMAP classifier are compared: fuzzy ARTMAP, Gaussian ARTMAP, and Extended Gaussian ARTMAP The main difference among these classifiers is in the way they determine/represent individual clusters in feature space. Best results are obtained for Extended Gaussian ARTMAP, a modification of the Gaussian ARTMAP neural network that preferably identifies Gaussian-distributed clusters.

Classification of EgyptSat-1 Images Using Deep Learning Methods

2020 ◽  
Vol 10 (1) ◽  
pp. 37-46 ◽  
Author(s):  
Hatem Keshk ◽  
Xu-Cheng Yin
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
High Performance ◽  
Satellite Images ◽  
Satellite Image ◽  
Aerial Photographs ◽  
Average Accuracy

Background: Deep Learning (DL) neural network methods have become a hotspot subject of research in the remote sensing field. Classification of aerial satellite images depends on spectral content, which is a challenging topic in remote sensing. Objective: With the aim to accomplish a high performance and accuracy of Egyptsat-1 satellite image classification, the use of the Convolutional Neural Network (CNN) is raised in this paper because CNN is considered a leading deep learning method. CNN is developed to classify aerial photographs into land cover classes such as urban, vegetation, desert, water bodies, soil, roads, etc. In our work, a comparison between MAXIMUM Likelihood (ML) which represents the traditional supervised classification methods and CNN method is conducted. Conclusion: This research finds that CNN outperforms ML by 9%. The convolutional neural network has better classification result, which reached 92.25% as its average accuracy. Also, the experiments showed that the convolutional neural network is the most satisfactory and effective classification method applied to classify Egyptsat-1 satellite images.

scholarly journals Tile-Based Semisupervised Classification of Large-Scale VHR Remote Sensing Images

2018 ◽  
Vol 2018 ◽  
pp. 1-14 ◽  
Author(s):  
Haikel Alhichri ◽  
Essam Othman ◽  
Mansour Zuair ◽  
Nassim Ammour ◽  
Yakoub Bazi
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Classification Accuracy ◽  
Large Scale ◽  
Graph Laplacian ◽  
Semisupervised Learning ◽  
Random Walker ◽  
Spatial Graph ◽  
Training Samples

This paper deals with the problem of the classification of large-scale very high-resolution (VHR) remote sensing (RS) images in a semisupervised scenario, where we have a limited training set (less than ten training samples per class). Typical pixel-based classification methods are unfeasible for large-scale VHR images. Thus, as a practical and efficient solution, we propose to subdivide the large image into a grid of tiles and then classify the tiles instead of classifying pixels. Our proposed method uses the power of a pretrained convolutional neural network (CNN) to first extract descriptive features from each tile. Next, a neural network classifier (composed of 2 fully connected layers) is trained in a semisupervised fashion and used to classify all remaining tiles in the image. This basically presents a coarse classification of the image, which is sufficient for many RS application. The second contribution deals with the employment of the semisupervised learning to improve the classification accuracy. We present a novel semisupervised approach which exploits both the spectral and spatial relationships embedded in the remaining unlabelled tiles. In particular, we embed a spectral graph Laplacian in the hidden layer of the neural network. In addition, we apply regularization of the output labels using a spatial graph Laplacian and the random Walker algorithm. Experimental results obtained by testing the method on two large-scale images acquired by the IKONOS2 sensor reveal promising capabilities of this method in terms of classification accuracy even with less than ten training samples per class.

NEURO-WAVELET CLASSIFIER FOR MULTISPECTRAL REMOTE SENSING IMAGES

2007 ◽  
Vol 05 (04) ◽  
pp. 589-611 ◽  
Author(s):  
B. UMA SHANKAR ◽  
SAROJ K. MEHER ◽  
ASHISH GHOSH
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Satellite Images ◽  
Satellite Image ◽  
Spectral Feature ◽  
Spectral Features ◽  
Remote Sensing Images ◽  
Feature Based ◽  
Multispectral Remote Sensing

A neuro-wavelet supervised classifier is proposed for land cover classification of multispectral remote sensing images. Features extracted from the original pixels information using wavelet transform (WT) are fed as input to a feed forward multi-layer neural network (MLP). The WT basically provides the spatial and spectral features of a pixel along with its neighbors and these features are used for improved classification. For testing the performance of the proposed method, we have used two IRS-1A satellite images and one SPOT satellite image. Results are compared with those of the original spectral feature based classifiers and found to be consistently better. Simulation study revealed that Biorthogonal 3.3 (Bior3.3) wavelet in combination with MLP performed better compared to all other wavelets. Results are evaluated visually and quantitatively with two measurements, β index of homogeneity and Davies–Bouldin (DB) index for compactness and separability of classes. We suggested a modified β index in accessing the percentage of accuracy (PAβ) of the classified images also.

scholarly journals Automatic Classification of Pararubber Trees in Thailand from LANDSAT-8 Images Using Neural Network Method

2021 ◽  
Author(s):  
C. Supunyachotsakul ◽  
N. Suksangpanya
Keyword(s):  
Neural Network ◽  
Classification Accuracy ◽  
Satellite Images ◽  
Ground Truth ◽  
Classification Model ◽  
Landsat 8 ◽  
Neural Network Method ◽  
Network Method ◽  
Convolutional Encoder

Classifying features from satellite images has been a time-consuming manual process which requires lots of manpower. This work exploits deep convolutional encoder-decoder neural network to develop an algorithm that can automatically classify the extents of the Pararubber tree-growing areas from the LANDSAT-8 images. The ground truth of the areas of the Pararubber tree was manually prepared and was separated into training datasets and the validation datasets. The classification model from this approach obtained using the training datasets was verified with the classification accuracy of70.90%, precision of 67.66%, recall of 80.80%, and F1 score of 73.59%.

scholarly journals Critical Land Detection using Remote Sensing Device and Geographic Information (Case Study of Critical Land Basic of Catchments Area, Alang, Wonogiri)

2017 ◽  
Vol 19 (1) ◽  
pp. 1
Author(s):  
Beny Harjadi
Keyword(s):  
Remote Sensing ◽  
Field Survey ◽  
Critical Level ◽  
Satellite Image ◽  
Geographic Information ◽  
Level Data ◽  
The Difference

Work criteria and indicator of Catchments Area need to be determined because the success and the failure of cultivating Catchments Area can be monitored and evaluated through the determined criteria. Criteria Indicators in utilizing land, one of them is determined based on the erosion index and the ability of utilizing land, for analyzing the land critical level. However, the determination of identification and classification of land critical level has not been determined; as a result the measurement of how wide the real critical land is always changed all the year. In this study, it will be tried a formula to determine the land critical/eve/ with various criteria such as: Class KPL (Ability of Utilizing Land) and the difference of the erosion tolerance value with the great of the erosion compared with land critical level analysis using remote sensing devices. The aim of studying land critical level detection using remote sensing tool and Geographic Information System (SIG) are:1. The backwards and the advantages of critical and analysis method2. Remote Sensing Method for critical and classification3. Critical/and surveyed method in the field (SIG) Collecting and analyzing data can be found from the field survey and interpretation of satellite image visually and using computer. The collected data are analyzed as:a. Comparing the efficiency level and affectivity of collecting biophysical data through field survey, sky photo interpretation, and satellite image analysis.b. Comparing the efficiency level and affectivity of land critical level data that are found from the result of KPL with the result of the measurement of the erosion difference and erosion tolerance.

scholarly journals A Novel Method for Sea-Land Clutter Separation Using Regularized Randomized and Kernel Ridge Neural Networks

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6491
Author(s):  
Le Zhang ◽  
Jeyan Thiyagalingam ◽  
Anke Xue ◽  
Shuwen Xu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Classification Accuracy ◽  
Signal Amplitude ◽  
Statistical Characteristics ◽  
Support Vector ◽  
Amplitude Change ◽  
Novel Method

Classification of clutter, especially in the context of shore based radars, plays a crucial role in several applications. However, the task of distinguishing and classifying the sea clutter from land clutter has been historically performed using clutter models and/or coastal maps. In this paper, we propose two machine learning, particularly neural network, based approaches for sea-land clutter separation, namely the regularized randomized neural network (RRNN) and the kernel ridge regression neural network (KRR). We use a number of features, such as energy variation, discrete signal amplitude change frequency, autocorrelation performance, and other statistical characteristics of the respective clutter distributions, to improve the performance of the classification. Our evaluation based on a unique mixed dataset, which is comprised of partially synthetic clutter data for land and real clutter data from sea, offers improved classification accuracy. More specifically, the RRNN and KRR methods offer 98.50% and 98.75% accuracy, outperforming the conventional support vector machine and extreme learning based solutions.

Sign in / Sign up

Export Citation Format

Share Document