• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.133-136
• /
• 2001

오디오 비디오 데이터의 활용이 증가함에 따라 멀티미디어 데이터의 내용에 대해 표현하려는 연구와 함께 멀티미디어 데이터의 내용이나 메타데이터를 저장하고, 검색하고, 조작하는 연구의 필요성이 증가하였다. 멀티미디어 데이터의 표현은 사용자가 원하는 내용만을 쉽게 검색하고, 접근한 수 있도록 표현되고 저장되어야 한다. 그러나 기존의 멀티미디어 검색 시스템들은 특정 객체에 중점을 두고 색상, 위치, 모양 등의 정보를 가지고 유사 객체를 찾는 방식을 취하고 있으므로 특정 사건이나 구체적인 인물 정보나 에피소드의 정보를 검색하고자 한 때는 키워드에 의한 검색을 해야하므로 불필요한 정보가 다량으로 검색되며 여러 번의 검색이 이루어져야 하는 단점이 있다. 또한 일반 사용자들은 주로 특정 장면에서 특정 객체의 특징이나 행동, 장소, 사건 등의 정보에 대해 관심을 갖고, 이에 따른 질의를 하는 경향이 있다. 따라서 본 논문에서는 "장면"이라는 계층 구조에 중점을 두고 멀티미디어 데이터의 내용 정보와 구조 정보를 표현 및 저장을 하며, 사용자는 특정 사건이나 객체들의 특징 정보를 가지고 장면이나 전체 구조를 검색찬 수 있는 시스템을 설계하고 구현한다. 멀티미디어 데이터의 표현 및 저장 검색의 모든 과정은 데이터의 재사용성과 접근 용이성을 위해 XML을 기반으로 하여 처리된다. 이렇게 XML로 표현된 데이터는 사용자들에게 구조 정보나 내용 정보에 있어서 다양한 검색 결과를 제공할 수 있는 장점이 있다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.1
• /
• pp.38-43
• /
• 2001

This Paper suggests a new feature for shot detection, using the proposed robust feature from the DC image constructed by DCT DC coefficients in the MPEG video stream, and proposes the characterizing value that reflects the characteristic of kind of video (movie, drama, news, music video etc.). The key frames are pulled out from many frames by using the local minima and maxima of differential of the value. After original frame(not do image) are reconstructed for key frame, indexing process is performed through computing parameters. Key frames that are similar to user's query image are retrieved through computing parameters. It is proved that the proposed methods are better than conventional method from experiments. The retrieval accuracy rate is so high in experiments.

• The KIPS Transactions:PartD
• /
• v.10D no.2
• /
• pp.283-292
• /
• 2003

One-dimensional time-series data have been studied in various database applications such as data mining and data warehousing. However, in the current complex business environment, multidimensional data sequences (MDS') become increasingly important in addition to one-dimensional time-series data. For example, a video stream can be modeled as an MDS in the multidimensional space with respect to color and texture attributes. In this paper, we propose the effective similarity measures on which the similar pattern retrieval is based. An MDS is partitioned into segments, each of which is represented by various geometric and semantic features. The similarity measures are defined on the basis of these segments. Using the measures, irrelevant segments are pruned from a database with respect to a given query. Both data sequences and query sequences are partitioned into segments, and the query processing is based upon the comparison of the features between data and query segments, instead of scanning all data elements of entire sequences.

• Journal of KIISE:Databases
• /
• v.29 no.3
• /
• pp.168-179
• /
• 2002

In this paper, we investigate video representation techniques that are the foundational work for the subsequent video processing such as video storage and retrieval. A video data set if a collection of video clips, each of which is a sequence of video frames and is represented by a multidimensional data sequence (MDS). An MDS is partitioned into video segments considering temporal relationship among frames, and then similar segments of the clip are grouped into video clusters. Thus, the video clip is represented by a small number of video clusters. The video segmentation and clustering algorithm, VDCluster, proposed in this paper guarantee clustering quality to south an extent that satisfies predefined conditions. The experiments show that our algorithm performs very effectively with respect to various video data sets.

• The KIPS Transactions:PartD
• /
• v.11D no.2
• /
• pp.247-258
• /
• 2004

Recently, there have been researches on storage and retrieval technique of moving objects, which are highly concerned by user in database application area such as video databases, spatio-temporal databases, and mobile databases. In this paper, we propose a new signature-based indexing scheme which supports similar sub-trajectory retrieval at well as good retrieval performance on moving objects trajectories. Our signature-based indexing scheme is classified into concatenated signature-based indexing scheme for similar sub-trajectory retrieval, entitled CISR scheme and superimposed signature-based indexing scheme for similar sub-trajectory retrieval, entitled SISR scheme according to generation method of trajectory signature based on trajectory data of moving object. Our indexing scheme can improve retrieval performance by reducing a large number of disk access on data file because it first scans all signatures and does filtering before accessing the data file. In addition, we can encourage retrieval efficiency by appling k-warping algorithm to measure the similarity between query trajectory and data trajectory. Final]y, we evaluate the performance on sequential scan method(SeqScan), CISR scheme, and SISR scheme in terms of data insertion time, retrieval time, and storage overhead. We show from our experimental results that both CISR scheme and SISR scheme are better than sequential scan in terms of retrieval performance and SISR scheme is especially superior to the CISR scheme.

• Journal of KIISE:Software and Applications
• /
• v.37 no.2
• /
• pp.137-147
• /
• 2010

A blog is a website, usually maintained by an individual, with regular entries of commentary, descriptions of events, or other material such as graphics or video. Entries are commonly displayed in reverse chronological order. Blog search engines, like web search engines, seek information for searchers on blogs. Blog search engines sometimes output unsatisfactory results, mainly due to spam blogs or splogs. Splogs are blogs hosting spam posts, plagiarized or auto-generated contents for the sole purpose of hosting advertizements or raising the search rankings of target sites. This thesis focuses on splog detection. This thesis proposes a new splog detection method, which is based on blog post structure similarity and posting count per day. Experiments based on methods proposed a day show excellent result on splog detection tasks with over 90% accuracy.

• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.47-60
• /
• 2012

Video data comes in the form of the unstructured and the complex structure. As the importance of efficient management and retrieval for video data increases, studies on the video parsing based on the visual features contained in the video contents are researched to reconstruct video data as the meaningful structure. The early studies on video parsing are focused on splitting video data into shots, but detecting the shot boundary defined with the physical boundary does not cosider the semantic association of video data. Recently, studies on structuralizing video shots having the semantic association to the video scene defined with the semantic boundary by utilizing clustering methods are actively progressed. Previous studies on detecting the video scene try to detect video scenes by utilizing clustering algorithms based on the similarity measure between video shots mainly depended on color features. However, the correct identification of a video shot or scene and the detection of the gradual transitions such as dissolve, fade and wipe are difficult because color features of video data contain a noise and are abruptly changed due to the intervention of an unexpected object. In this paper, to solve these problems, we propose the Scene Detector by using Color histogram, corner Edge and Object color histogram (SDCEO) that clusters similar shots organizing same event based on visual features including the color histogram, the corner edge and the object color histogram to detect video scenes. The SDCEO is worthy of notice in a sense that it uses the edge feature with the color feature, and as a result, it effectively detects the gradual transitions as well as the abrupt transitions. The SDCEO consists of the Shot Bound Identifier and the Video Scene Detector. The Shot Bound Identifier is comprised of the Color Histogram Analysis step and the Corner Edge Analysis step. In the Color Histogram Analysis step, SDCEO uses the color histogram feature to organizing shot boundaries. The color histogram, recording the percentage of each quantized color among all pixels in a frame, are chosen for their good performance, as also reported in other work of content-based image and video analysis. To organize shot boundaries, SDCEO joins associated sequential frames into shot boundaries by measuring the similarity of the color histogram between frames. In the Corner Edge Analysis step, SDCEO identifies the final shot boundaries by using the corner edge feature. SDCEO detect associated shot boundaries comparing the corner edge feature between the last frame of previous shot boundary and the first frame of next shot boundary. In the Key-frame Extraction step, SDCEO compares each frame with all frames and measures the similarity by using histogram euclidean distance, and then select the frame the most similar with all frames contained in same shot boundary as the key-frame. Video Scene Detector clusters associated shots organizing same event by utilizing the hierarchical agglomerative clustering method based on the visual features including the color histogram and the object color histogram. After detecting video scenes, SDCEO organizes final video scene by repetitive clustering until the simiarity distance between shot boundaries less than the threshold h. In this paper, we construct the prototype of SDCEO and experiments are carried out with the baseline data that are manually constructed, and the experimental results that the precision of shot boundary detection is 93.3% and the precision of video scene detection is 83.3% are satisfactory.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.331-334
• /
• 2005

움직임 추정은 비디오신호의 압축에 중요한 역할을 한다. 본 논문은 효율적으로 움직임 벡터를 찾기 위하여 움직임 벡터의 시간적, 공간적 유사성을 이용하였다. 벡터를 검색하기 이전에 움직임 벡터의 검색 범위를 크게 9개의 영역으로 나눈 후, 이전 프레임에서 동일한 위치, 현재 프레임의 현재 매크로블록의 상위, 상우와 좌측의 매크로블록에서의 움직임 벡터까지 총 4개의 움직임 벡터를 이용하여 9개의 영역 중 한 영역을 제 1 후보, 그를 둘러싼 영역을 제 2 후보라 정하고 극소점들(Local Minima)을 피하였다. 모의실험을 통한 결과 NDS(New Diamond Search) 알고리즘에 비하여 매크로블록 당 평균 탐색 포인트 수가 5.79 포인트 감소하고, MSE는 최대 104.23 감소한 것을 확인할 수 있었다.

• 전자공학회논문지 IE
• /
• v.43 no.2
• /
• pp.49-53
• /
• 2006

A fast motion-estimation algorithm based on regulated partial block distortions is proposed. The proposed algorithm can obtain very accurate motion vectors with a small computational load. Simulation results show that the proposed scheme provides very close performance to the full search while it is about 6 to 28 times faster than the full search.

• Journal of Broadcast Engineering
• /
• v.5 no.1
• /
• pp.102-112
• /
• 2000

The previous video structuring techniques are mainly limited to shot or shot group level. However, the shot level structure couldn't provide semantics within a video. So, researches on high level structuring are going on for getting over the drawbacks of shot level structure, recently. To overcome the drawbacks of shot level structure, we propose video scene segmentation technique based on color and motion features. For considering various color distribution, each shot is divided into sub-shots based on color feature. A key frame is extracted from each sub-shot. The motion feature in a shot is extracted from MPEG-1 video's motion vector. Moreover adaptive weights based on motion's property in search range are applied to color and motion features. The experiment results of proposed technique show the excellence in view of the over-segmentation and the reflection of semantics, comparing with those of previous techniques. The proposed technique decomposes video into meaningful hierarchical structure and provides video browsing or retrieval based on scene.