• Korean Journal of Remote Sensing
• /
• v.37 no.6_3
• /
• pp.2011-2025
• /
• 2021

In high-resolution satellite image classification, when the color values of pixels belonging to one class are different, such as buildings with various colors, it is difficult to determine the color information representing the class. In this paper, to solve the problem of determining the representative color information of a class, we propose a method to divide the color channel of HSV (Hue Saturation Value) and perform object-based classification. To this end, after transforming the input image of the RGB color space into the components of the HSV color space, the Hue component is divided into subchannels at regular intervals. The minimum distance-based image classification is performed for each hue subchannel, and the classification result is combined with the image segmentation result. As a result of applying the proposed method to KOMPSAT-3A imagery, the overall accuracy was 84.97% and the kappa coefficient was 77.56%, and the classification accuracy was improved by more than 10% compared to a commercial software.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.144-150
• /
• 2017

Recently, deep learning is used for intelligent processing and accuracy improvement of data. It is formed calculation model composed of multi data processing layer that train the data representation through an abstraction of the various levels. A category of deep learning, convolution neural network is utilized in various research fields, which are human pose estimation, face recognition, image classification, speech recognition. When using the deep layer and lots of class, CNN that show a good performance on image classification obtain higher classification rate but occur the overfitting problem, when using a few data. So, we design the training network based on convolution neural network and trained our image data set for object classification in few class problem. The experiment show the higher classification rate of 7.06% in average than the previous networks designed to classify the object in 1000 class problem.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.4-6
• /
• 2003

A holistic representation, such as sparse ceding or independent component analysis (ICA), was successfully applied to explain early auditory processing and sound classification. In contrast, Part-based representation is an alternative way of understanding object recognition in brain. In this paper. we employ the non-negative matrix factorization (NMF)［1］which learns parts-based representation for sound classification. Feature extraction methods from spectrogram using NMF are explained. Experimental results show that NMF-based features improve the performance of sound classification over ICA-based features.

• The Journal of the Korea Contents Association
• /
• v.16 no.7
• /
• pp.31-41
• /
• 2016

Atmospheric correction as a preprocessing work should be performed to conduct accurately landcover/landuse classification using hyperspectral imagery. Atmospheric correction on airborne hyperspectral images was conducted and then the effect of atmospheric correction by comparing spectral reflectance characteristics before and after atmospheric correction for a few landuse classes was analyzed. In addition, land cover classification was first conducted respectively by the maximum likelihood method and the spectral angle mapper method after atmospheric correction and then the results were compared. Applying the spectral angle mapper method, the sea water area were able to be classified with the minimum of noise at the threshold angle of 4 arc degree. It is considered that object-based classification method, which take into account of scale, spectral information, shape, texture and so forth comprehensively, is more advantageous than pixel-based classification methods in conducting landcover classification of the coastal area with hyperspectral images in which even the same object represents various spectral characteristics.

• Journal of Korea Multimedia Society
• /
• v.25 no.6
• /
• pp.769-782
• /
• 2022

A study on agricultural automation became more important. In Korea, sweet persimmon farmers spend a lot of time and effort on classifying profitable persimmons. In this paper, we propose and implement an efficient grading algorithm for persimmons before shipment. We gathered more than 1,750 images of persimmons, and the images were graded and labeled for classifications purpose. Our main algorithm is based on EfficientDet object detection model but we implemented more exquisite method for better classification performance. In order to improve the precision of classification, we adopted a machine learning algorithm, which was proposed by PyCaret machine learning workflow generation library. Finally we acquired an improved classification model with the accuracy score of 81%.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.1
• /
• pp.77-85
• /
• 2006

In this paper, we propose a hierarchical classifier of object images using neural networks for content-based image classification. The images for classification are object images that can be divided into foreground and background. In the preprocessing step, we extract the object region and shape-based texture features extracted from wavelet transformed images. We group the image classes into clusters which have similar texture features using Principal Component Analysis(PCA) and K-means. The hierarchical classifier has five layes which combine the clusters. The hierarchical classifier consists of 59 neural network classifiers learned with the back propagation algorithm. Among the various texture features, the diagonal moment was the most effective. A test with 1000 training data and 1000 test data composed of 10 images from each of 100 classes shows classification rates of 81.5% and 75.1% correct, respectively.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1271-1281
• /
• 2017

It is essential to collect and analyze target information around the vehicle for autonomous driving of the vehicle. Based on the analysis, environmental information such as location and direction should be analyzed in real time to control the vehicle. In particular, obstruction or cutting of objects in the image must be handled to provide accurate information about the vehicle environment and to facilitate safe operation. In this paper, we propose a method to simultaneously generate 2D and 3D bounding box proposals using LiDAR Edge generated by filtering LiDAR sensor information. We classify the classes of each proposal by connecting them with Region-based Fully-Covolutional Networks (R-FCN), which is an object classifier based on Deep Learning, which uses two-dimensional images as inputs. Each 3D box is rearranged by using the class label and the subcategory information of each class to finally complete the 3D bounding box corresponding to the object. Because 3D bounding boxes are created in 3D space, object information such as space coordinates and object size can be obtained at once, and 2D bounding boxes associated with 3D boxes do not have problems such as occlusion.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.28 no.6
• /
• pp.627-636
• /
• 2010

Image segmentation technique is becoming increasingly important in the field of remote sensing image analysis in areas such as object oriented image classification to extract object regions of interest within images. This paper presents a new method for image segmentation to consider spectral and spatial information of high resolution satellite image. Firstly, the initial seeds were automatically selected using local variation of multi-spectral edge information. After automatic selection of significant seeds, a segmentation was achieved by applying MSRG which determines the priority of region growing using information drawn from similarity between the extracted each seed and its neighboring points. In order to evaluate the performance of the proposed method, the results obtained using the proposed method were compared with the results obtained using conventional region growing and watershed method. The quantitative comparison was done using the unsupervised objective evaluation method and the object-based classification result. Experimental results demonstrated that the proposed method has good potential for application in the object-based analysis of high resolution satellite images.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.4
• /
• pp.578-585
• /
• 2018

In this paper, we propose a classification and theft detection system for human and livestock for various moving objects in a barn. To do this, first, we extract the moving objects using the GMM method. Second, the noise generated when extracting the moving object is removed, and the moving object is recognized through the labeling method. And we propose a method to classify human and livestock using model formation and color for the unique form of the detected moving object. In addition, we propose a method of tracking and overlapping the classified moving objects using Kalman filter. Through this overlap determination method, an event notifying a dangerous situation is generated and a theft determination system is constructed. Finally, we demonstrate the feasibility and applicability of the proposed system through several experiments.

• Korean Journal of Remote Sensing
• /
• v.36 no.2_2
• /
• pp.277-292
• /
• 2020

The purpose of this study is to propose the possibility of precise surface sedimentary facies classification and a more accurate classification method by generating the large-scale map of surface sedimentary facies based on UAV data and object-based image analysis (OBIA) for Hwang-do tidal flat in Cheonsu bay. The very high resolution UAV data extracted factors that affect the classification of surface sedimentary facies, such as RGB ortho imagery, Digital elevation model (DEM), and tidal channel density, and analyzed the principal components of surface sedimentary facies through statistical analysis methods. Based on principal components, input data to be used for classification of surface sedimentary facies were divided into three cases such as (1) visible band spectrum, (2) topographical elevation and tidal channel density, (3) visible band spectrum and topographical elevation, tidal channel density. The object-based image analysis classification method was applied to map the classification of surface sedimentary facies according to conditions of input data. The surface sedimentary facies could be classified into a total of six sedimentary facies following the folk classification criteria. In addition, the use of visible band spectrum, topographical elevation, and tidal channel density enabled the most effective classification of surface sedimentary facies with a total accuracy of 63.04% and the Kappa coefficient of 0.54.