• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.1
• /
• pp.23-33
• /
• 2020

Recently, high-resolution images can be easily acquired using UAV (Unmanned Aerial Vehicle), so that it is possible to produce small area observation and spatial information at low cost. In particular, research on the generation of cover maps in crop production areas is being actively conducted for monitoring the agricultural environment. As a result of comparing classification performance by applying RF(Random Forest), SVM(Support Vector Machine) and CNN(Convolutional Neural Network), deep learning classification method has many advantages in image classification. In particular, land cover classification using satellite images has the advantage of accuracy and time of classification using satellite image data set and pre-trained parameters. However, UAV images have different characteristics such as satellite images and spatial resolution, which makes it difficult to apply them. In order to solve this problem, we conducted a study on the application of deep learning algorithms that can be used for analyzing agricultural lands where UAV data sets and small-scale composite cover exist in Korea. In this study, we applied DeepLab V3 +, FC-DenseNet (Fully Convolutional DenseNets) and FRRN-B (Full-Resolution Residual Networks), the semantic image classification of the state-of-art algorithm, to UAV data set. As a result, DeepLab V3 + and FC-DenseNet have an overall accuracy of 97% and a Kappa coefficient of 0.92, which is higher than the conventional classification. The applicability of the cover classification using UAV images of small areas is shown.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.2
• /
• pp.94-101
• /
• 2012

This paper proposes an improved image steganalysis scheme to raise the detection rate of stego images out of cover images. To improve the detection rate of stego image in the steganalysis, tiny variation caused by data hiding should be amplified. For this, we extract feature vectors of cover image and stego image by two steps. First, we separate image into upper 4 bit subimage and lower 4 bit subimage. As a result, stego noise is expanded more than two times. We decompose separated subimages into twelve subbands by applying 3-level Haar wavelet transform and calculate co-occurrence probabilities of two different subbands in the same scale. Since co-occurrence probability of the two wavelet subbands is affected by data hiding, it can be used as a feature to differentiate cover images and stego images. The extracted feature vectors are used as the input to the multilayer perceptron(MLP) classifier to distinguish between cover and stego images. We test the performance of the proposed scheme over various embedding rates by the LSB, S-tool, COX's SS, and F5 embedding method. The proposed scheme outperforms the previous schemes in detection rate to existence of hidden message as well as exactness of discrimination.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2003.11a
• /
• pp.175-179
• /
• 2003

We propose a new watermarking scheme that can be used to embed multiple bits and also resilient to JPEG compression and geometrical transforms such as scaling, rotation, and cropping based on holographic watermark that allows multiple watermark recovery without original content(cover image).

• International Journal of Contents
• /
• v.8 no.4
• /
• pp.95-102
• /
• 2012

In this paper, we present a technique to extract the title areas from book cover images. A typical book cover image may contain text, pictures, diagrams as well as complex and irregular background. In addition, the high variability of character features such as thickness, font, position, background and tilt of the text also makes the text extraction task more complicated. Therefore, we propose a two steps efficient method that uses Histogram of Oriented Gradients and color information to find the title areas. Firstly, text localization is carried out to find the title candidates. Finally, refinement process is performed to find the sufficient components of title areas. To obtain the best result, we also use other constraints about the size, ratio between the length and width of the title. We achieve encouraging results of extracted title regions from book cover images which prove the advantages and efficiency of the proposed method.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1470-1472
• /
• 2003

Hyperion, as hyperspectral data, is carried on NASA’s EO-1 satellite, can be used in more subtle discrimination on forest cover, with 224 band in 360 ?2580 nm (10nm interval). In this study, Hyperion image is used to investigate the effects of topography on the classification of forest cover, and to assess whether the topographic correction improves the discrimination of species units for practical forest mapping. A publicly available Digital Elevation Model (DEM), at a scale of 1:25,000, is used to model the radiance variation on forest, considering MSR(Mean Spectral Ratio) on antithesis aspects. Hyperion, as hyperspectral data, is corrected on a pixel-by-pixel basis to normalize the scene to a uniform solar illumination and viewing geometry. As a result, the approach on topographic effect normalization in hyperspectral data can effectively reduce the variation in detected radiance due to changes in forest illumination, progress the classification of forest cover.

• Journal of Forest and Environmental Science
• /
• v.37 no.1
• /
• pp.44-51
• /
• 2021

Rapid urbanization and population growth have caused substantial land use land cover (LULC) change in the Kathmandu valley. The lack of temporal and geographical data regarding LULC in the middle mountain region like Kathmandu has been challenging to assess the changes that have occurred. The purpose of this study is to investigate the changes in LULC in Chandragiri Municipality between 1996 and 2017 using geographical information system (GIS) and remote sensing. Using Landsat imageries of 1996 and 2017, this study analyzed the LULC change over 21 years. The images were classified using the Maximum Likelihood classification method and post classified using the change detection technique in GIS. The result shows that severe land cover changes have occurred in the Forest (11.63%), Built-up areas (3.68%), Agriculture (-11.26%), Shrubland (-0.15%), and Bareland (-3.91%) in the region from 1996 to 2017. This paper highlights the use of GIS and remote sensing in understanding the changes in LULC in the south-west part of Kathmandu valley.

• Journal of the Korean Geographical Society
• /
• v.45 no.2
• /
• pp.275-292
• /
• 2010

This study investigated the land-cover changes in the tidal flat of the Taean peninsula due to man-made environmental changes between 1972 and 2008, through time-series analysis based on a modified post-classification comparison method and multi-temporal satellite images. The analysis revealed that the land-cover of the tidal flat has changed from tidal flat to wetland and from wetland to paddy field between 1972 and 2008. Also, the pattern of detailed land-cover changes is as follows: tidal flat to wetland; lake and saltpan to bare land and paddy field. The accurate classification of each image is needed for the application of the post-classification comparison method. The overall accuracy of the classified images was found to be 95.33% on average, and the Kappa value was 0.941 on average.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.2 no.1
• /
• pp.32-44
• /
• 1999

Texture features can be incorporated in classification procedure to resolve class confusions. However, there have been few application-oriented studies made to evaluate the relative powers of texture analysis methods in a particular environment. This study evaluates the increases in the land-cover classification accuracy of the SPOT HRV multispectral data of Pusan Metropolitan area from texture processing. Twenty-four texture measures were derived from the SPOT HRV band 3 image. Each of these features were used in combination with the three spectral images in the classification of 10 land-cover classes. Supervised training and a Gaussian maximum likelihood classifier were used in the classification. It was found that while entropy produces the best empirical results in terms of the overall classification, other texture features can also largely improve the classification accuracies obtained by the use of the spectral images only. With the inclusion of texture, the classification for each category improves. Specially, urban built-up areas had much increase in accuracy. The results indicate that texture size 5 by 5 and 7 by 7 may be suitable at land cover classification of Pusan Metropolitan area.

• Spatial Information Research
• /
• v.15 no.1
• /
• pp.67-80
• /
• 2007

The land cover map represent the state of earth surfaces. It can be used as basic data to explore present conditions of earth surfaces and develop future plans for local areas. To produce the land cover map with efficiency, gathering geographic information from satellite images is important. Exporting, building, and managing processes on the land cover information are needed as well. In this study we aim to review the producing process of the level-2 land cover map in detail and enhance it. h present status of the producing process of the land cover map in Korea is reviewed, problems of the process are explored, and measures for improving it are proposed. The criteria for fixing boundaries and providing attributes for the land cover map are proposed. This proposed criteria may solve problems in a present producing process. The improving measures proposed in this study should be continuously revised in future studies.

• Korean Journal of Remote Sensing
• /
• v.26 no.2
• /
• pp.87-98
• /
• 2010

For generating accurate land cover map over the whole Korean Peninsula, post-mosaic classification method is desirable in large area where multiple image data sets are used. We try to derive an optimal mosaic method of multi-temporal Landsat ETM+ scenes for the land cover classification over the Korea Peninsula. Total 65 Landsat ETM+ scenes were acquired, which were taken in 2000 and 2001. To reduce radiometric difference between adjacent Landsat ETM+ scenes, we apply three relative radiometric correction methods (histogram matching, 1st-regression method referenced center image, and 1st-regression method at each Landsat ETM+ path). After the relative correction, we generated three mosaic images for three seasons of leaf-off, transplanting, leaf-on season. For comparison, three mosaic images were compared by the mean absolute difference and computer classification accuracy. The results show that the mosaic image using 1st-regression method at each path show the best correction results and highest classification accuracy. Additionally, the mosaic image acquired during leaf-on season show the higher radiance variance between adjacent images than other season.