COMPARISON OF AUTOMATIC AND SEMI-AUTOMATIC METHODS FOR CLASSIFICATION OF SIDE SCAN SONAR IMAGERY

ABSTRACT. The main scope of this paper is the analysis of seafloor classification using acoustic remote sensing data. These data were acquired in a hydroacoustic survey of bathymetry and sonography using an interferometric swath bathymetry system. The study area is a sector of the internal northeast Brazilian shelf adjacent to the Ponta Negra beach - Natal (RN). The objective of the work is to identify and draw the different textural patterns, which characterize the seafloor of the study area. In addition, two approaches for textural classification of sonograms were compared and evaluated, which were: Automatic Gray Level Co-occurrence Matrix (GLCM) classification available in SonarWiz software; and the semi-automatic Maximum Likelihood, available in ArcGIS software. The comparison tested the capacity for identifying and drawing the textural patterns distribution. The automated classification identified 4 patterns while on the semi-automated 5 patterns were identified. It was made the correlation between the textural patterns found in each classification, besides the correlation between textural patterns and the levels of intensity of reflectance presents on the sonogram.Keywords: sonography, textural classification, textural patterns, hydroacoustic. RESUMO. Este trabalho foi realizado a partir da análise de dados geofísicos adquiridos em levantamento hidroacústico de batimetria e sonografia utilizando um sonar interferométrico EdgeTech 4600. A área de estudo é uma porção da plataforma interna do nordeste brasileiro adjacente Natal (RN). O objetivo deste trabalho é identificar e delimitar os diferentes padrões texturais que caracterizam o substrato marinho da área de estudo. Adicionalmente, são avaliadas e comparadas duas abordagens distintas de classificação textural de sonogramas, sendo elas: a classificação automática GLCM disponível no software SonarWiz, e a classificação semi-automática máxima verossimilhança (Maximum Likelihood) disponível no software ArcGIS. A comparação foi realizada com base na capacidade de identificação e delimitação da distribuição dos padrões texturais. A utilização da classificação automática identificou 4 padrões, enquanto que, na classificação semi-automática 6 padrões foram identificados. Foi feita a correlação entre os padrões texturais encontrados em cada classificação, além da correlação entre os padrões texturais e os níveis de intensidade de reflectância presente no sonograma.Palavras-chave: sonografia, classificação textural, padrões de textura, hidroacústica.

Download Full-text

Toward automated classification of monolayer versus few-layer nanomaterials using texture analysis and neural networks

Scientific Reports ◽

10.1038/s41598-020-77705-8 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Shrouq H. Aleithan ◽

Doaa Mahmoud-Ghoneim

Keyword(s):

Neural Networks ◽

Texture Analysis ◽

Higher Order ◽

Image Texture ◽

Proper Class ◽

Automated Classification ◽

Linear Discriminant ◽

Ann Classifier ◽

Occurrence Matrix

AbstractThe need for a fast and robust method to characterize nanostructure thickness is growing due to the tremendous number of experiments and their associated applications. By automatically analyzing the microscopic image texture of MoS2 and WS2, it was possible to distinguish monolayer from few-layer nanostructures with high accuracy for both materials. Three methods of texture analysis (TA) were used: grey level histogram (GLH), grey levels co-occurrence matrix (GLCOM), and run-length matrix (RLM), which correspond to first, second, and higher-order statistical methods, respectively. The best discriminating features were automatically selected using the Fisher coefficient, for each method, and used as a base for classification. Two classifiers were used: artificial neural networks (ANN), and linear discriminant analysis (LDA). RLM with ANN was found to give high classification accuracy, which was 89% and 95% for MoS2 and WS2, respectively. The result of this work suggests that RLM, as a higher-order TA method, associated with an ANN classifier has a better ability to quantify and characterize the microscopic structure of nanolayers, and, therefore, categorize thickness to the proper class.

Download Full-text

On the accuracy of glacier outlines derived from remote-sensing data

Annals of Glaciology ◽

10.3189/2013aog63a296 ◽

2013 ◽

Vol 54 (63) ◽

pp. 171-182 ◽

Cited By ~ 278

Author(s):

F. Paul ◽

N.E. Barrand ◽

S. Baumann ◽

E. Berthier ◽

T. Bolch ◽

...

Keyword(s):

Remote Sensing ◽

Reference Value ◽

Remote Sensing Data ◽

Automated Classification ◽

Automated Mapping ◽

Sensing Data ◽

Medium Resolution ◽

Debris Cover ◽

Manual Correction

AbstractDeriving glacier outlines from satellite data has become increasingly popular in the past decade. In particular when glacier outlines are used as a base for change assessment, it is important to know how accurate they are. Calculating the accuracy correctly is challenging, as appropriate reference data (e.g. from higher-resolution sensors) are seldom available. Moreover, after the required manual correction of the raw outlines (e.g. for debris cover), such a comparison would only reveal the accuracy of the analyst rather than of the algorithm applied. Here we compare outlines for clean and debris-covered glaciers, as derived from single and multiple digitizing by different or the same analysts on very high- (1 m) and medium-resolution (30 m) remote-sensing data, against each other and to glacier outlines derived from automated classification of Landsat Thematic Mapper data. Results show a high variability in the interpretation of debris-covered glacier parts, largely independent of the spatial resolution (area differences were up to 30%), and an overall good agreement for clean ice with sufficient contrast to the surrounding terrain (differences ∼5%). The differences of the automatically derived outlines from a reference value are as small as the standard deviation of the manual digitizations from several analysts. Based on these results, we conclude that automated mapping of clean ice is preferable to manual digitization and recommend using the latter method only for required corrections of incorrectly mapped glacier parts (e.g. debris cover, shadow).

Download Full-text

High-Silica Lava Morphology at Ocean Spreading Ridges: Machine-Learning Seafloor Classification at Alarcon Rise

Geosciences ◽

10.3390/geosciences9060245 ◽

2019 ◽

Vol 9 (6) ◽

pp. 245 ◽

Cited By ~ 1

Author(s):

Christina H. Maschmeyer ◽

Scott M. White ◽

Brian M. Dreyer ◽

David A. Clague

Keyword(s):

Fuzzy Inference ◽

Full Range ◽

Automated Classification ◽

Submarine Lava ◽

Seafloor Classification ◽

High Silica ◽

Lava Morphology ◽

Ocean Ridge ◽

The Relationship

The oceanic crust consists mostly of basalt, but more evolved compositions may be far more common than previously thought. To aid in distinguishing rhyolite from basaltic lava and help guide sampling and understand spatial distribution, we constructed a classifier using neural networks and fuzzy inference to recognize rhyolite from its lava morphology in sonar data. The Alarcon Rise is ideal to study the relationship between lava flow morphology and composition, because it exhibits a full range of lava compositions in a well-mapped ocean ridge segment. This study shows that the most dramatic geomorphic threshold in submarine lava separates rhyolitic lava from lower-silica compositions. Extremely viscous rhyolite erupts as jagged lobes and lava branches in submarine environments. An automated classification of sonar data is a useful first-order tool to differentiate submarine rhyolite flows from widespread basalts, yielding insights into eruption, emplacement, and architecture of the ocean crust.

Download Full-text

Selection of an algorithm for automatic classification of satellite images for the study of agricultural crops on the territory of Vietnam

IOP Conference Series Earth and Environmental Science ◽

10.1088/1755-1315/937/3/032082 ◽

2021 ◽

Vol 937 (3) ◽

pp. 032082

Author(s):

B N Olzoev ◽

H Z Huang ◽

L A Plastinin ◽

V E Gagin ◽

O V Danchenko

Keyword(s):

Maximum Likelihood ◽

Satellite Images ◽

Remote Sensing Data ◽

Classification Algorithms ◽

Agricultural Activity ◽

Landsat 8 ◽

Agricultural Crop ◽

Agricultural Crops ◽

Selection Of

Abstract The paper is devoted to the choice of an algorithm for automatic controlled classification of multi-zone satellite images of Landsat 8 OLI for the purposes of agricultural crop research based on the analysis of various mathematical classification algorithms and comparison of the practical results of these algorithms when using the ENVI 5.4 software package. In the period from June to August 2020, a field survey was conducted by coordinating and ground-based object recognition for the purpose of compiling decryption standards based on images. The paper analyzes four frequently used popular algorithms for automatic controlled classification – maximum likelihood, minimum distance, Mahalanobis distance, parallelepiped. As a result, it is concluded that when classifying objects with very close brightness values, the maximum likelihood algorithm gives optimal and objective results. This conclusion was confirmed by the cameral method by evaluating the reliability of the classification results. The result of the study can be used for mapping agricultural crops and solving other problems of agricultural activity in Vietnam. The methodology presented in the paper can be applied when choosing controlled classification algorithms for other groups of plant complexes and objects based on remote sensing data from space.

Download Full-text

Corn Classification System based on Computer Vision

Symmetry ◽

10.3390/sym11040591 ◽

2019 ◽

Vol 11 (4) ◽

pp. 591 ◽

Cited By ~ 8

Author(s):

Xiaoming Li ◽

Baisheng Dai ◽

Hongmin Sun ◽

Weina Li

Keyword(s):

Machine Learning ◽

Computer Vision ◽

Maximum Likelihood ◽

Classification System ◽

Automated Classification ◽

Shape Features ◽

Segmentation Method ◽

Likelihood Estimator ◽

Color Features

Automated classification of corn is important for corn sorting in intelligent agriculture. This paper presents a reliable corn classification method based on techniques of computer vision and machine learning. To discriminate different damaged types of corns, a line profile segmentation method is firstly used to segment and separate a group of touching corns. Then, twelve color features and five shape features are extracted for each individual corn object. Finally, a maximum likelihood estimator is trained to classify normal and damaged corns. To evaluate the performance of the proposed method, a private dataset consisting of images of normal corn and six kinds of damage corns, including heat-damaged, germ-damaged, cob-rot-damaged, blue eye mold-damaged, insect-damaged, and surface mold-damaged, were collected in this work. The proposed method achieved an accuracy of 96.67% for the classification between normal corns and the first four common damaged corns, and an accuracy of 74.76% was achieved for the classification between normal corns and six kinds of damaged corns. The experimental results demonstrated the effectiveness of the proposed corn classification system.

Download Full-text