• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.3
• /
• pp.636-642
• /
• 2017

In this paper, We proposed a novel hand-gesture recognition algorithm using concentric-circle expanding and tracing. The proposed algorithm determines region of interest of hand image through preprocessing the original image acquired by web-camera and extracts the feature of hand gesture such as the number of stretched fingers, finger tips and finger bases, angle between the fingers which can be used as intuitive method for of human computer interaction. The proposed algorithm also reduces computational complexity compared with raster scan method through referencing only pixels of concentric-circles. The experimental result shows that the 9 hand gestures can be recognized with an average accuracy of 90.7% and an average algorithm execution time is 78ms. The algorithm is confirmed as a feasible way to a useful input method for virtual reality, augmented reality, mixed reality and perceptual interfaces of human computer interaction.

• Journal of Broadcast Engineering
• /
• v.18 no.6
• /
• pp.795-807
• /
• 2013

In recent years, 2D-to-3D conversion techniques have gained much attraction. Most of conventional methods focused on natural images such as movie, animation and so forth. However, it is difficult to apply these techniques to window images mixed with text, image, logo, and icon. Also, different depth values of text pixels will cause distortion and a proper 3D image can not be delivered in some situations. To solve this problem, we propose a method to classify a given image into either a window or a natural image. For the window image, only rectangular image regions (RIR) are detected and converted in 3D. Other text and background are displayed in 2D. The proposed method was performed on more than 10,000 test images. In the experimental results, the detection ratio of window image reaches 97% and RIR detection ratio is 87%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.10C
• /
• pp.961-967
• /
• 2009

In this paper, the lossless compression method is proposed for an 8-bit bitplane of the input image. The lower bitplanes are not well compressed because of irregularity of pixels. To overcome these drawbacks, this paper propose a mixed coding method that using the block-based lossless compression and the bit-based losselss compression, introducing the H. 264 and the JBIG. First, to take advantage of the characteristics of the bitplanes, 8-bitplane against the top 4 bits and lower 4 bits were separated. Next, the JBIG compression method was used in separated top 4-bitplane because of a lot of correlation between bits. And a separated lower 4-bitplane was applied the improved method that using the H. 264 lossless prediction. A pre-processing method applied to the lower 4-bitplane then irregular distribution of pixel values are converted to regular. Using the proposed method to test for various test images were performed. Experimental results from a printer using 8-bit image compared to JBIG average 19%, lower 4bit image compression performance with an average of 11% could be obtained.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.53 no.2
• /
• pp.1-8
• /
• 2011

In this study, In order to evaluate reliable of MODIS GPP, the MODIS GPP and Flux tower measured GPP were compared to evaluate the use of method on 8 days composite MODIS GPP. The 2008 Flux data ($CO_2$ Flux and air temperature) measured in Seolmacheon watershed ($8.48\;km^2$) were used. The Flux tower GPP was estimated as the sum of $CO_2$ Flux and $R_{ec}$ (ecosystem respiration) by Lloyd and Taylor method (1994). The summer Monsoon period from June to August mostly contributed the underestimation of MODIS GPP by cloud contamination on MODIS pixels. The 2008 MODIS GPP and Flux tower GPP of the watershed were $1133.2\;g/m^2/year$ and $1464.3\;g/m^2/year$ respectively and the determination coefficient ($R^2$) after correction of cloud-originated errors was 0.74 (0.63 before correction). Even though effect of Cloud-Originated Errors was eliminated, Solar radiation and Temperature are affected at GPP. Measurement of correct GPP is difficult. But, If errors of MODIS GPP analyze on Cloud Moonsoon Climate in korea and eliminated effect of Cloud-Originated Errors, MODIS GPP will be considered GPP increasing of 9 %. There, Our results indicate that MODIS GPP show reliable and useful data except for summer period in Moonsoon Climate.

• Korean Journal of Remote Sensing
• /
• v.25 no.2
• /
• pp.193-203
• /
• 2009

Snow cover is one of the important parameters since it determines surface energy balance and its variation. To classify snow and cloud from satellite data is very important process when inferring land surface information. Generally, misclassified cloud and snow pixel can lead directly to error factor for retrieval of surface products from satellite data. Therefore, in this study, we perform algorithm for detecting snow cover area with remote sensing data. We just utilize visible reflectance, and infrared channels rather than using NDSI (Normalized Difference Snow Index) which is one of optimized methods to detect snow cover. Because COMS MI (Meteorological Imager) channels doesn't include near infra-red, which is used to produce NDSI. Detecting snow cover with visible channel is well performed over clear sky area, but it is difficult to discriminate snow cover from mixed cloudy pixels. To improve those detecting abilities, brightness temperature difference (BTD) between 11 and 3.7 is used for snow detection. BTD method shows improved results than using only visible channel.

• The Korean Journal of Ecology
• /
• v.28 no.4
• /
• pp.215-222
• /
• 2005

MODIS (Moderate Resolution Image Spectrometer) is a core satellite sensor boarded on Terra and Aqua satellite of NASA Earth Observing System since 1999 and 2001, respectively. MODIS LAI, FPAR, and GPP provide useful means to monitor plant phonology and material cycles in terrestrial ecosystems. In this study, LAI, FPAR, and GPP in Korea were evaluated and errors associated with cloud contamination on MODIS pixels were eliminated for years $2001\sim2003$. Three-year means of cloud-corrected annual GPP were 1836, 1369, and 1460g C $m^{-2}y^{-1}$ for evergreen needleleaf forest, deciduous broadleaf forest, and mixed forest, respectively. The cloud-originated errors were 8.5%, 13.1%, and 8.4% for FPAR, LAI, and GPP, respectively. Summertime errors from June to September explained by 78% of the annual accumulative errors in GPP. This study indicates that cloud-originated errors should be mitigated for practical use of MODIS vegetation products to monitor seasonal and annual changes in plant phonology and vegetation production in Korea.

• Journal of the Korean earth science society
• /
• v.33 no.2
• /
• pp.113-125
• /
• 2012

The estimations of the surface rain intensity and rain-related physical variables derived from two independent Tropical Rainfall Measuring Mission (TRMM) satellite sensors, TRMM Microwave Imager (TMI) and Precipitation Radar (PR), were compared over four different oceans. The precipitating clouds developed most frequently in the warmest sea surface temperature (SST) region of the west Pacific, which is 1.5 times more frequent than in the east Pacific and the tropical Atlantic oceans. However, the east Pacific exhibited the most intense rain intensity for the convective and mixed rain types while the tropical Atlantic showed the most intense rain intensity for all TMI rainy pixels. It was found that the deviation of TMI-derived rain rate yielded a big difference in region-to-region and rain type-to-type if the PR rain intensity value is assumed to be closer to the truth. Furthermore, the deviation by rain types showed opposite signs between convective and non-convective rain types. It was found that the region-to-region deviation differences reached more than 200% even though the selected tropical oceans have relatively similar geophysical environments. Therefore, the validation for the microwave rain estimation needs to be performed according to both rain types and climate regimes, and it also requires more sophisticated TMI algorithm which reflects the locality of rainfall characteristics.

• Korean Journal of Remote Sensing
• /
• v.30 no.4
• /
• pp.493-503
• /
• 2014

A hierarchical classification scheme, which can reduce the spectral ambiguity and also reflect crop cultivation patterns from past land-cover maps, is presented for the purpose of the early production of crop classification maps in large-scale crop areas. Specifically, the effects of mixed pixels are minimized not only by applying a hierarchical classification approach based on different spectral characteristics from crop growth cycles, but also by considering temporal contextual information derived from past crop cultivation patterns. The applicability of the presented classification scheme was evaluated by a case study of Iowa State in USA with time-series MODIS 250 m Normalized Difference Vegetation Index(NDVI) data sets and past Cropland Data Layers(CDLs). Corn and soybean, which are major crop types in the study area and also display spectral similarity, could be properly classified by applying different classification stages and accounting for past crop cultivation patterns. The classification result by the presented scheme showed increases of minimum 7.68%p and maximum 20.96%p in overall accuracy, compared with one based on purely spectral information. In addition, the combination of temporal contextual information during classification was less affected by the number of NDVI data sets and the best overall accuracy of 86.63% was achieved. Thus, it is expected that this classification scheme can be effectively used for the early production of large-area crop classification maps in major feed-grain importing countries.

• The Journal of the Korea Contents Association
• /
• v.13 no.12
• /
• pp.38-47
• /
• 2013

An image coding based on MRC model, a kind of multi-layer image model, first segments a screen image into foreground, mask, and background layers, and then compresses each layer using a codec that is suitable to the layer. The mask layer defines the position of foreground regions such as textual and graphical contents. The colour signal of the foreground (background) region is saved in the foreground (background) layer. The mask layer which contains the segmentation result of foreground and background regions is of importance since its accuracy directly affects the overall coding performance of the codec. This paper proposes a new layer segmentation algorithm for the MRC based image coding. The proposed method extracts text pixels from the background using morphological top hat filtering. The application of white or black top hat transformation to local blocks is controlled by the information of relative brightness of text compared to the background. In the proposed method, the boundary information of text that is extracted from the edge map of the block is used for the robust decision on the relative brightness of text. Simulation results show that the proposed method is superior to the conventional methods.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1181-1189
• /
• 2022

Clouds are composed of tiny water droplets, ice crystals, or mixtures suspended in the atmosphere and cover about two-thirds of the Earth's surface. Cloud detection in satellite images is a very difficult task to separate clouds and non-cloud areas because of similar reflectance characteristics to some other ground objects or the ground surface. In contrast to thick clouds, which have distinct characteristics, thin transparent clouds have weak contrast between clouds and background in satellite images and appear mixed with the ground surface. In order to overcome the limitations of transparent clouds in cloud detection, this study conducted cloud detection focusing on transparent clouds using machine learning techniques (Random Forest [RF], Convolutional Neural Networks [CNN]). As reference data, Cloud Mask and Cirrus Mask were used in MOD35 data provided by MOderate Resolution Imaging Spectroradiometer (MODIS), and the pixel ratio of training data was configured to be about 1:1:1 for clouds, transparent clouds, and clear sky for model training considering transparent cloud pixels. As a result of the qualitative comparison of the study, bothRF and CNN successfully detected various types of clouds, including transparent clouds, and in the case of RF+CNN, which mixed the results of the RF model and the CNN model, the cloud detection was well performed, and was confirmed that the limitations of the model were improved. As a quantitative result of the study, the overall accuracy (OA) value of RF was 92%, CNN showed 94.11%, and RF+CNN showed 94.29% accuracy.