• The Journal of the Acoustical Society of Korea
• /
• v.21 no.1
• /
• pp.19-26
• /
• 2002

This paper defines the visual basic speech units, visemes and investigates various visual features of a lip for the effective Korean lipreading. First, we analyzed the visual characteristics of the Korean vowels from the database of the lip image sequences obtained from the multi-speakers, thereby giving a definition of seven Korean vowel visemes. Various spatio-temporal features of a lip are extracted from the feature points located on both inner and outer lip contours of image sequences and their classification performances are evaluated by using a hidden Markov model based classifier for effective lipreading. The experimental results for recognizing the Korean visemes have demonstrated that the feature victor containing the information of inner and outer lip contours can be effectively applied to lipreading and also the direction and magnitude of the movement of a lip feature point over time is quite useful for Korean lipreading.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.6 no.3
• /
• pp.139-150
• /
• 2003

There was a close relationship between spatio-temporal distribution of Cochlodinium polykrikoides red tide and meso-scale variation of oceanographic environment around the Korean waters. Oceanographic conditions of Narodo island, where red tide usually first occurred during summer seasons were formation of the thermohaline frontal zone from 1995 to 2001. Huge C. polykrikoides red tides were observed in every uneven year during the past 7 years (1995~2001) and quasi-biennial oscillation also occurred in the oceanographic variations of sea surface temperature and salinity in the northern part of the East China Sea during the same years. The distribution area and moving pattern of C. polykrikoides red tides were definitely depended on the temporal and spatial variation of upwelling cold water originated form the southeastern coast of the Korean peninsula in summer season.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.7
• /
• pp.488-498
• /
• 2007

This paper presents a novel approach for representing the spatio-temporal topology of the camera network with overlapping and non-overlapping fields of view (FOVs) in Ubiquitous Smart Space (USS). The topology is determined by tracking moving objects and establishing object correspondence across multiple cameras. To track people successfully in multiple camera views, we used the Merge-Split (MS) approach for object occlusion in a single camera and the grid-based approach for extracting the accurate object feature. In addition, we considered the appearance of people and the transition time between entry and exit zones for tracking objects across blind regions of multiple cameras with non-overlapping FOVs. The main contribution of this paper is to estimate transition times between various entry and exit zones, and to graphically represent the camera topology as an undirected weighted graph using the transition probabilities.

• Korean Journal of Remote Sensing
• /
• v.34 no.3
• /
• pp.553-564
• /
• 2018

Water use efficiency (WUE) is the amount of carbon uptake per unit of water use, which is a key measure of the functions of terrestrial ecosystems, as it is related to both the hydrologic and carbon cycles. Furthermore, it can vary with many factors, such as climate conditions and land cover characteristics, in different regions. In this study, we aim to understand the spatial and temporal variations in WUE on the Korean Peninsula as well as the associated response to drought. The Moderate Resolution Imaging Spectroradiometer (MODIS)-derived gross primary productivity (GPP) and evapotranspiration (ET) datasets and climate data were used to derive a drought index. Based on the monthly WUE, we found that WUE decreased during the monsoon summer in all regions and for all vegetation types. Furthermore, the annual WUE was negatively correlated with the drought index, with increasing correlation coefficients from the northern region to the southern region of the Korean Peninsula.

• The Journal of the Korea Contents Association
• /
• v.12 no.4
• /
• pp.31-39
• /
• 2012

DVC(Distributed Video Coding) techniques have been attracting a lot of research works since these enable us to implement the light-weight video encoder and to provide good coding efficiency by introducing the feedback channel. However, the feedback channel causes the decoder to increase the decoding complexity and requires very high decoding latency because of numerous iterative decoding processes. So, in order to reduce the decoding delay and then to implement in a real-time environment, this paper proposes several parity bit estimation methods which are based on the temporal correlation, spatial correlation and spatio-temporal correlations between LDPCA frames on each bit plane in the consecutive video frames in pixel-domain Wyner-Ziv video coding scheme and then the performances of these methods are compared in fast DVC scheme. Through computer simulations, it is shown that the adaptive spatio-temporal correlation-based estimation method and the temporal correlation-based estimation method outperform others for the video frames with the highly active contents and the low active contents, respectively. By using these results, the proposed estimation schemes will be able to be effectively used in a variety of different applications.

• The Journal of the Korea Contents Association
• /
• v.7 no.2
• /
• pp.40-50
• /
• 2007

In this paper, we propose an efficient method for detecting and tracking multiple moving objects based on morphological region merging from real-time video sequences. The proposed approach consists of adaptive threshold extraction, morphological region merging and detecting and tracking of objects. Firstly, input frame is separated into moving regions and static regions using the difference of images between two consecutive frames. Secondly, objects are segmented with a reference background image and adaptive threshold values, then, the segmentation result is refined by morphological region merge algorithm. Lastly, each object segmented in a previous step is assigned a consistent identification over time, based on its spatio-temporal information. The experimental results show that a proposed method is efficient and useful in terms of real-time multiple objects detecting and tracking.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.15 no.1
• /
• pp.172-183
• /
• 2012

In 2011, floods were at the worst stage of devastation in Chao Phraya river basin of Thailand. The purpose of this study is to trace the flood inundation area around Chao Phraya river basin by using Terra MODIS image because it has the ability of spatiotemporal dynamics. The MODIS indices, which included the enhanced vegetation index(EVI), land surface water index(LSWI), and the difference in the values of EVI and LSWI(DVEL), were extracted from MODIS product MOD09 8-day composite datasets with a spatial resolution of 500m from Jul. 29, 2011 to Jan. 09, 2012. We found that combined application of EVI, LSWI, and DVEL was suitable for monitoring flood inundation. For the extracted flood inundation area and water-related area. The result can be used to acquire the flood inundation data scattered and demonstrate the potential for the use of MODIS data for temporal and spatial detection of flood effects.

• Broadcasting and Media Magazine
• /
• v.3 no.2
• /
• pp.44-58
• /
• 1998

최근의 멀티미디어 기술은 정보의 디지털화와 온라인화에 따라 가전, 컴퓨터, 통신 및 방송 기술이 융화되어 가는 추세에 있으며, 대화형의 하이브리드 멀티미디어 기술을 그 특징으로 하고있다. 하이브리드 멀티미디어는 컴퓨터 그래픽 및 미디(MIDI) 기술로 인위적으로 생성한 2D/3D그래픽 및 음향을 실제의 자연적인 영상과 소리에 추가하여 합성하므로 생성된다. MPEG-4는 이렇게 인위적으로 합성되거나 자연적인 영상 혹은 음향 정보의 디지털 하이브리드 멀티미디어 부호화를 목적으로 하며, 활성화된 혼합 미디어의 내용기반 처리, 상호, 동작 및 사용자의 쉬운 접근 등을 가능하게 한다. SNHC(Synthetic-Natural Hybrid Coding)는 기존의 수동적인 미디어의 전달뿐 아니라 실시간 처리가 가능한 인터랙티브 응용 분야까지 다루고 있으며, 통합된 시공간 부호화 기법을 사용하여 시각, 청각, 2차원, 3차원 컴퓨터 그래픽스 등 다양한 형태의 표준 AV(Aural/Visual) 객체를 처리한다. 표준화는 주로mesh-segmented 비디오 부호화, 구조물 부호화, 객체간의 동기화, AV 객체 스트림의 멀티플렉싱, 혼합 미디어 형태의 시-공간 통합화 등에서 이루어지게 되는데, 이는 궁극적으로 네트워크로 연결되는 가상 환경(Virtual Environment)에서 다수의 사용자가 서로 상호작용 할 수 있는 틀을 제공하는데 있다. 이러한 틀이 제공되면, 대화형 하이브리드 멀티미디어라는 새로운 형태의 정보를 사용함으로써 기존의 미디어로는 경험하지 못하는 다양한 응용과 서비스를 경험할 수 있을 것이다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.49-52
• /
• 2006

본 논문에서는 은닉 마르코프 모델을 바탕으로 하는 발걸음을 이용한 개인 식별 시스템을 제안한다. 개인의 발걸음은 연속적인 자세나 움직임의 집합으로 나타낼 수 있는데, 구조적으로 연속적인 움직임의 변화는 확률적인 특성을 가지고 있기 때문에 은닉 마르코프 모델을 이용하여 적절하게 모델링 할 수 있다. 개인의 발걸음은 N개의 이산적인 자세 간의 전이로 이루어졌다고 가정하였으며, 이를 계산하기 위해 MMSI라는 발걸음 특징 모델을 제안하였다. MMSI는 발걸음 인식에 중요한 역할을 하는 시공간적인 정보를 가지고 있는 그레이-스케일 영상이다. 실험 결과는 MMSI를 이용하여 은닉 마르코프 모델을 바탕으로 한 발걸음 인식 결과를 보여준다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.489-490
• /
• 2015

객체의 인식을 위한 컴퓨터 비전 알고리즘은 안개와 비와 같은 기상이 좋지 않은 상황에서는 인식 성능이 떨어지고 있다. 이로 인하여 최근 악천후 환경에서 촬영된 영상으로부터 날씨 현상을 제거하는 기법들이 연구되고 있다. 빗줄기는 시공간적 무작위성으로 인하여 검출 및 제거가 어려운 현상이다. 또한 기존의 빗줄기 검출 및 제거 기법들은 대부분 고정된 카메라로부터 촬영된 영상을 대상으로 처리함으로써 자동차와 같은 움직임이 있는 촬영환경에서는 부적합하다. 최근에는 카메라나 객체의 움직임에 대응할 수 있는 빗줄기 검출 및 제거 알고리즘이 개발되고 있으나, 방대한 연산량이 필요하기 때문에 실시간이 불가능하다. 본 논문에서는 최근 연구되고 있는 카메라 움직임이 있는 환경에서 빗줄기 검출 및 제거 알고리즘을 DSP 환경에서 구현하고 내부 메모리 최적화와 EMDA 이용, 소프트웨어 파이프라인 등을 통해 최적화를 수행하여 실시간성을 보인다.