• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2754-2768
• /
• 2013

Video fingerprints generated from global features are usually vulnerable against general geometric transformations. In this paper, a novel video fingerprinting algorithm is proposed, in which a new spatio-temporal gradient is designed to represent the spatial and temporal information for each frame, and a new partition scheme, based on concentric circle and rings, is developed to resist the attacks efficiently. The centroids of spatio-temporal gradient orientations (CSTGO) within the circle and rings are then calculated to generate a robust fingerprint. Our experiments with different attacks have demonstrated that the proposed approach outperforms the state-of-the-art methods in terms of robustness and discrimination.

• 인터넷정보학회논문지
• /
• 제16권3호
• /
• pp.21-32
• /
• 2015

동작인식 연구에서 비디오를 표현하는 시공간 부분 특징이 모델 없는 상향식 방식의 주요 주제가 되면서 동작 특징을 검출하고 표현하는 방법이 여러 연구를 통해 다양하게 제안되고 있다. 그 중에서 BoF(bag of features)방식은 가장 일관성 있는 인식 결과를 보여주고 있다. 비디오의 동작을 BoF로 나타내기 위해서는 어떻게 동작의 역동적 정보를 표현할 것인가가 가장 중요한 부분이다. 그래서 기존 연구에서는 비디오를 시공간 볼륨으로 간주하고 3D 동작 특징점 주변의 볼륨 패치를 복잡하게 설명하는 것이 가장 일반적인 방법이다. 본 연구에서는 기존 3D 기반 방식을 간략화하여 비디오의 동작을 BoF로 표현할 때 비디오에서 2D 특징점을 직접 수집하는 방식을 제안한다. 제안 방식의 기본 아이디어는 일반적 공간프레임의 2D xy 평면뿐만 아니라 시공간 프레임으로 불리는 시간축 평면에서 동작 특징점을 추출하여 표현하는 것으로 특징점이 비디오에서 역동적 동작 정보를 포착하기 때문에 동작 표현 특징 설명자를 3D로 확장할 필요 없이 2D 설명자만으로 간단하게 동작인식이 가능하다. SIFT, SURF 특징 표현 설명자로 표현하는 시공간 BoF 방식을 주요 동작인식 데이터에 적용하여 우수한 동작 인식율을 보였다. 3D기반의 HoG/HoF 설명자와 비교한 경우에도 제안 방식이 더 계산하기 쉽고 단순하게 이해할 수 있다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.384-387
• /
• 2003

Most of the real world phenomena change over time. The ability to represent and to reason geographic data becomes crucial. A large amount of non-standard applications are dealing with data characterized by spatial, temporal and/or uncertainty features. Non-standard data like spatial and temporal data have an inner complex structure requiring sophisticated data representation, and their operations necessitate sophisticated and efficient algorithms. Current GIS technology is inefficient to model and to handle complex geographic phenomena, which involve space, time and uncertainty dimensions. This paper concentrates on developing a fuzzy spatio-temporal data model based on fuzzy set theory and relational data models. Fuzzy spatio-temporal operators are also provided to support dynamic query.

• International Journal of Contents
• /
• 제17권3호
• /
• pp.1-14
• /
• 2021

Since the outbreak of the coronavirus disease 2019 (COVID-19) pandemic, a lot of efforts have been made in the field of data science to help combat against this disease. Among them, forecasting the number of cases of infection is a crucial problem to predict the development of the pandemic. Many deep learning-based models can be applied to solve this type of time series problem. In this research, we would like to take a step forward to incorporate spatial data (geography) with time series data to forecast the cases of region-level infection simultaneously. Specifically, we model a single spatio-temporal graph, in which nodes represent the geographic regions, spatial edges represent the distance between each pair of regions, and temporal edges indicate the node features through time. We evaluate this approach in COVID-19 in a Korean dataset, and we show a decrease of approximately 10% in both RMSE and MAE, and a significant boost to the training speed compared to the baseline models. Moreover, the training efficiency allows this approach to be extended for a large-scale spatio-temporal dataset.

• 한국음향학회지
• /
• 제21권1호
• /
• pp.19-26
• /
• 2002

본 논문에서는 한국어 입술독해를 위한 기반 연구로서 음성학에 기반하여 음성의 시각적 기본 단위인 viseme을 정의하고 입술의 움직임을 적절히 표현할 수 있는 특징들을 추출하여 그 성능을 분석하였다. 먼저, 다수의 화자로부터 한국어 모음에 해당하는 입술의 동영상 데이터베이스를 획득하고 각모음별 시각적 특성을 분석하여 7개의 한국어 모음 viseme을 정의하였으며 입술 윤곽선상의 특징점과 시공간적 특징 벡터들을 추출하여 은닉 마르코프 모델에 적용함으로써 효과적인 입술독해를 위한 각 특징 벡터별 성능을 비교하였다. 7개의 한국어 각 viseme에 대한 인식 실험 결과에서 입술의 안팎 윤곽선의 정보가 모두 반영된 특징 벡터가 입술독해에 효과적으로 적용될 수 있으며 윤곽선 상의 특징점들의 시간적 움직임 크기와 방향이 입술독해를 위하여 매우 중요한 요소임을 확인할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4026-4040
• /
• 2019

In this paper, we present an approach for detecting slide transitions in lecture videos by introducing the spatio-temporal residual networks. Given a lecture video which records the digital slides, the speaker, and the audience by multiple cameras, our goal is to find keyframes where slide content changes. Since temporal dependency among video frames is important for detecting slide changes, 3D Convolutional Networks has been regarded as an efficient approach to learn the spatio-temporal features in videos. However, 3D ConvNet will cost much training time and need lots of memory. Hence, we utilize ResNet to ease the training of network, which is easy to optimize. Consequently, we present a novel ConvNet architecture based on 3D ConvNet and ResNet for slide transition detection in lecture videos. Experimental results show that the proposed novel ConvNet architecture achieves the better accuracy than other slide progression detection approaches.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2008년도 학술대회 1부
• /
• pp.298-303
• /
• 2008

사용자의 과거 이동 경로 자료는 사용자의 현재 이동 위치를 예측하고 이외 관련된 서비스를 제공하는데 유용하게 사용될 수 있다. 본 논문에서는 사용자의 과거 이동 경로의 분석을 통하여 이동 중인 사용자의 시공간 위치예측 기술을 제안한다. 환경으로부터 발생한 사용자의 이동 경로를 수집하고 수집된 데이터에서 이동 경로 요약(Path Summarization)과 이동 경로 선택(Path Selection) 방법을 제안한다. 이동 경로 요약 방법은 환경으로부터 수집한 사용자의 이동 경로를 군집 분류하고, 이동 경로 선택 방법은 이동 중에 발생한 경로의 거리, 시간, 방향의 요소와 동적 정합법을 사용하여 유사성(Similarity)을 측정하며 유사성이 가장 높은 경로를 선택한다. 선택된 경로는 시간에 따른 공간 정보 빚 위치에 따른 시간 예측 서비스를 위하여 사용가능 하며, 실험을 통하여 유사성이 높은 이동 경로를 선택하는 모습을 확인하였다.

• Journal of Information Science Theory and Practice
• /
• 제10권spc호
• /
• pp.135-142
• /
• 2022

Recently, with the development of data processing technology and the increase of computational power, methods to solving social problems using Artificial Intelligence (AI) are in the spotlight, and AI technologies are replacing and supplementing existing traditional methods in various fields. Meanwhile in Korea, heavy rain is one of the representative factors of natural disasters that cause enormous economic damage and casualties every year. Accurate prediction of heavy rainfall over the Korean peninsula is very difficult due to its geographical features, located between the Eurasian continent and the Pacific Ocean at mid-latitude, and the influence of the summer monsoon. In order to deal with such problems, the Korea Meteorological Administration operates various state-of-the-art observation equipment and a newly developed global atmospheric model system. Nevertheless, for precipitation nowcasting, the use of a separate system based on the extrapolation method is required due to the intrinsic characteristics associated with the operation of numerical weather prediction models. The predictability of existing precipitation nowcasting is reliable in the early stage of forecasting but decreases sharply as forecast lead time increases. At this point, AI technologies to deal with spatio-temporal features of data are expected to greatly contribute to overcoming the limitations of existing precipitation nowcasting systems. Thus, in this project the dataset required to develop, train, and verify deep learning-based precipitation nowcasting models has been constructed in a regularized form. The dataset not only provides various variables obtained from multiple sources, but also coincides with each other in spatio-temporal specifications.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2824-2838
• /
• 2013

There has been a lot of attention paid recently to analyze dynamic human gestures that vary over time. Most attention to dynamic gestures concerns with spatio-temporal features, as compared to analyzing each frame of gestures separately. For accurate dynamic gesture recognition, motion feature extraction algorithms need to find representative features that uniquely identify time-varying gestures. This paper proposes a new feature-extraction algorithm using temporal self-similarity based on a hierarchical human model. Because a conventional temporal self-similarity method computes a whole movement among the continuous frames, the conventional temporal self-similarity method cannot recognize different gestures with the same amount of movement. The proposed model-based temporal self-similarity method groups body parts of a hierarchical model into several sets and calculates movements for each set. While recognition results can depend on how the sets are made, the best way to find optimal sets is to separate frequently used body parts from less-used body parts. Then, we apply a multiclass support vector machine whose optimization algorithm is based on structural support vector machines. In this paper, the effectiveness of the proposed feature extraction algorithm is demonstrated in an application for taebo gesture recognition. We show that the model-based temporal self-similarity method can overcome the shortcomings of the conventional temporal self-similarity method and the recognition results of the model-based method are superior to that of the conventional method.

• Journal of Electrical Engineering and Technology
• /
• 제13권2호
• /
• pp.961-968
• /
• 2018

Recently, researches on automatic recognition of human activities have been actively carried out with the emergence of various intelligent systems. Since a large amount of visual data can be secured through Closed Circuit Television, it is required to recognize human behavior in a dynamic situation rather than a static situation. In this paper, we propose new intelligent human activity recognition model using the trajectory information extracted from the video sequence. The proposed model consists of three steps: segmentation and partitioning of trajectory step, feature extraction step, and behavioral learning step. First, the entire trajectory is fuzzy partitioned according to the motion characteristics, and then temporal features and spatial features are extracted. Using the extracted features, four pedestrian behaviors were modeled by decision tree learning algorithm and performance evaluation was performed. The experiments in this paper were conducted using Caviar data sets. Experimental results show that trajectory provides good activity recognition accuracy by extracting instantaneous property and distinctive regional property.