• Journal of KIISE:Databases
• /
• v.35 no.4
• /
• pp.345-355
• /
• 2008

SIFT is popularly used in computer vision application such as object recognition, motion tracking, and 3D reconstruction among various shape descriptors. However, it is not easy to apply SIFT into the image similarity search as it is since it uses many high dimensional keypoint vectors. In this paper, we present a SIFT based image similarity search method using an edge image pyramid and an interesting region detection. The proposed method extracts keypoints, which is invariant to contrast, scale, and rotation of image, by using the edge image pyramid and removes many unnecessary keypoints from the image by using the hough transform. The proposed hough transform can detect objects of ellipse type so that it can be used to find interesting regions. Experimental results demonstrate that the retrieval performance of the proposed method is about 20% better than that of traditional SIFT in average recall.

• Journal of KIISE:Software and Applications
• /
• v.27 no.5
• /
• pp.510-520
• /
• 2000

For content-based video indexing and retrieval, it is necessary to segment video data into video shots and then select key frames or representative frames for each shot. However, it is very difficult to select key frames automatically because the task of selecting meaningful frames is quite subjective. In this paper, we propose a new approach in selecting key frames based on visual contents such as region information and their temporal variations in the shot. First of all, we classify video shots into panning shots, zooming shots, tilting shots or no camera motion shots by detecting camera motion information in video shots. Then, in each category, we apply appropriate fuzzy rules to select key frames based on meaningful content in frame. Finally, we control the number of key frames in the selection process by adjusting the degree of detail in representing video shots.

• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.53-62
• /
• 2004

The processing of emotional information is very important in Human-Computer Interaction (HCI). In particular, it is very important in video information processing to deal with a user's affection. To handle emotional information, it is necessary to represent meaningful features and detect them efficiently. Even though it is not an easy task to detect emotional events from low level features such as colour and motion, it is possible to detect them if we use statistical analysis like Linear Discriminant Analysis (LDA). In this paper, we propose a representation scheme for emotion-related features and a defection method. We experiment with extracted features from video to detect emotional events and obtain desirable results.

• Journal of Korea Multimedia Society
• /
• v.10 no.5
• /
• pp.559-568
• /
• 2007

Anchor-person scene detection is of significance for video shot semantic parsing and indexing clues extraction in content-based news video indexing and retrieval system. This paper proposes an efficient algorithm extracting anchor ranges that exist in sports news video for unit structuring of sports news. To detect anchor person scenes, first, anchor person candidate scene is decided by DCT coefficients and motion vector information in the MPEG4 compressed video. Then, from the candidate anchor scenes, image processing method is utilized to classify the news video into anchor-person scenes and non-anchor(sports) scenes. The proposed scheme achieves a mean precision and recall of 98% in the anchor-person scenes detection experiment.

• Journal of Internet Computing and Services
• /
• v.10 no.4
• /
• pp.1-11
• /
• 2009

Recently there has arisen concern in both the database community and the graphics society about data retrieval from large motion databases because the high dimensionality of motion data implies high costs. In this circumstance, finding an effective distance measure and an efficient query processing method for such data is a challenging problem. This paper presents an elaborate motion query processing system, SMoFinder (Similar Motion Finder), which incorporates a novel kinematic distance measure and an efficient indexing strategy via adaptive frame segmentation. To this end, we regard human motions as multi-linkage kinematics and propose the weighted Minkowski distance metric. For efficient indexing, we devise a new adaptive segmentation method that chooses representative frames among similar frames and stores chosen frames instead of all frames. For efficient search, we propose a new search method that processes k-nearest neighbors queries over only representative frames. Our experimental results show that the size of motion databases is reduced greatly (${\times}1/25$) but the search capability of SMoFinder is equal to or superior to that of other systems.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.11C
• /
• pp.1541-1550
• /
• 2004

In this paper, we propose an advanced hardware architecture for fast multi-resolution motion estimation of the video coding standard MPEG-1,2 and MPEG-4 AVC. We describe the algorithm and derive hardware architecture emphasizing the importance of area for low cost and fast operation by using the shared memory, the special ram architecture, the motion vector for 4 pixel x 4 pixel, the spiral search and so on. The proposed architecture has been verified by ARM-interfaced emulation board using Excalibur Altera FPGA and also by ASIC synthesis using Samsung 0.18 m CMOS cell library. The ASIC synthesis result shows that the proposed hardware can operate at 140 MHz, processing more than 1,100 QCIF video frames or 70 4CIF video frames per second. The hardware is going to be used as a core module when implementing a complete MPEG-4 AVC video encoder ASIC for real-time multimedia application.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.1
• /
• pp.97-104
• /
• 2012

Natural User Interface(NUI) technologies introduce new trends in using devices such as computer and any other electronic devices. In this paper, an augmented reality on a mobile device is implemented by using face detection, recognition and motion tracking. The face detection is obtained by using Viola-Jones algorithm from the images of the front camera. The Eigenface algorithm is employed for face recognition and face motion tracking. The augmented reality is implemented by overlapping the rear camera image and GPS, accelerator sensors' data with the 3D graphic object which is correspond with the recognized face. The algorithms and methods are limited by the mobile device specification such as processing ability and main memory capacity.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.46 no.5
• /
• pp.868-889
• /
• 2022

Fashion companies are using a big data approach as a key strategic analysis to predict and forecast sales. This study investigated the effectiveness of the past sales, web search volume, information amount, brand promotion, and the advertising endorser on the sales forecasting model. The study conducted the autoregressive distributed lag (ARDL) time series model using the internal and external social big data of a national fashion brand. Results indicated that the brand's past sales, search volume, promotion, and amount of advertising endorser information amount significantly affected the sales forecast, whereas the brand's advertising endorser search volume and information amount did not significantly influence the sales forecast. Moreover, the brand's promotion had the highest correlation with sales forecasting. This study adds to information-searching behavior theory by measuring consumers' brand involvement. Last, this study provides digital marketers with implications for developing profitable marketing strategies on the basis of consumers' interest in the brand and advertising endorser.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.15-18
• /
• 2001

동영상에서 움직이는 객체 검출은 동영상의 내용을 표현하고 유사한 동영상을 검색하는 데 있어 중요한 특징간을 추출하는 방법으로 사용된다. 그러나 복잡하게 카메라가 움직이는 동영상에서 움직이는 객체 검출은 아직까지 어려운 과제이다. 본 논문에서는 복잡한 카메라의 움직임이 있는 환경에서 움직이는 객체를 강인하게 검출하는 방법을 제안한다. 움직이는 객체 검출 방법은 입력 영상을 색상간의 클러스터링을 이용하여 각 영역으로 구분하는 Mean Shift 알고리즘과 인접한 프레임에서 구분된 영역을 대응시켜 영역의 모션 벡터를 구하는 영역 매칭, 유사한 궤적을 가지는 영역들의 클러스터링을 이용하여 객체를 검출하는 궤적 클러스터링 알고리즘을 사용한다. 제안한 영역 기반 알고리즘은 기존의 픽셀이나 블록 기반의 방법보다 움직이는 객체를 정확하게 검출하였다. 실험 결과 복잡하게 움직이는 카메라의 환경 속에서 움직이는 객체를 강인하게 검출하였다.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.690-695
• /
• 2009

본 논문은 영화, 방송, 애니메이션 등의 다양한 동영상 콘텐츠에 수화 애니메이션을 합성하여 동영상 콘텐츠를 청각 및 언어장애인들에게 이해시키기 위한 수화 통역 VR 콘텐츠 시스템을 제안하고자 한다. 제안된 시스템은 수화 사전에 있는 수화들을 3D 애니메이션으로 DB화하기 위해, 모션 캡처 시스템과 데이터 글러브를 사용하여 실제 사람처럼 자연스러운 애니메이션을 생성하였다. 최종적으로 동영상 콘텐츠의 자막이나 대본의 구문분석을 한 후, 이를 수화용 단어자막을 통해 수화 애니메이션을 DB에서 검색한 후, 실시간적으로 기존 동영상 콘텐츠와 동기합성을 하여 수화 통역 콘텐츠를 제공하는 VR 콘텐츠 시스템을 구현하였고 이 시스템을 동화용 애니메이션에 적용하였다.