• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.07a
• /
• pp.252-253
• /
• 2015

군중의 이상행동을 검출하는 것은 군중 모니터링, 보안 및 CRM 시스템의 관점에서 중요한 요소 중의 하나이다. 기존의 방법은 대다수가 옵티컬플로우를 기반으로한 검출방법으로 객체가 움직이지 않는 경우에는 객체로 인식할 수 없는 문제점이 생긴다. 또한, 많은 데이터량을 처리하기 때문에 실시간성이 보장되지 않는다는 단점이 있다. 이를 극복하기 위해서, 본 논문에서는 특징점 맵 보정과 분포분석을 통한 군중의 밀집과 대피하는 현상을 검출하는 방법을 제안한다. 먼저, 군중에서 옵티컬플로우 기반으로 움직이는 FAST 특징점을 추출하고 추출된 특징점의 분포에따라 특징점맵을 복원한다. 복원된 특징점 맵과 특징점의 분포에 기반하여 군중의 이상정도를 결정하게 된다. PETS2009 데이터베이스를 사용하여 결과를 측정하였다.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.9-22
• /
• 2024

Mobility data is important to understand social phenomena and problem. Previous studies have utilized Origin-Destination (OD) visualization methods to represent human's mobility. However, the effectiveness of visualization tools as a method for understanding social phenomena remains unexplored. Therefore, in this study, we developed a visualization tool called SeoulOD-Vis to facilitate understanding social issues. It included three different modules: map visualization, condition selection, and detailed information presentation. We recruited 28 participants to evaluate the SeoulOD-Vis and compared it with a publicly available visualization tool. The results suggested that the SeoulOD-Vis had higher usability and problem-solving performances. Interview results suggested that it attributed to its 'condition selection' and 'detailed information presentation' modules. Our results will contribute to develop visualization tools to solve social problems using mobility data.

• Journal of Korea Multimedia Society
• /
• v.13 no.1
• /
• pp.76-82
• /
• 2010

Reversible watermarking hides some information in a digital image in such a way that an authorized party could decode the hidden information and also restore the image to its original state. In this paper, a high capacity reversible watermarking method using histogram shifting is proposed. In order to increase embedding capacity, the proposed method divides the image into $2{\times}2$ blocks and uses a paring(horizontal, vertical, diagonal) inside each block, then finds a maximum embedding bin which has the most frequent difference values among the parings. Also, the proposed method removes the overflow and underflow by using location map which including the maximum embedding bin and increases the embedding capacity by embedding iteratively. The experimental results show that the proposed method provides a high embedding capacity and good visual quality compared with the conventional reversible watermarking methods.

• Journal of Internet Computing and Services
• /
• v.20 no.1
• /
• pp.87-96
• /
• 2019

In this paper, we propose a MapReduce-supported clustering technique for collecting and classifying distributed workflow enactment event logs as a preprocessing tool. Especially, we would call the distributed workflow enactment event logs as Workflow BIG-Logs, because they are satisfied with as well as well-fitted to the 5V properties of BIG-Data like Volume, Velocity, Variety, Veracity and Value. The clustering technique we develop in this paper is intentionally devised for the preprocessing phase of a specific workflow process mining and analysis algorithm based upon the workflow BIG-Logs. In other words, It uses the Map-Reduce framework as a Workflow BIG-Logs processing platform, it supports the IEEE XES standard data format, and it is eventually dedicated for the preprocessing phase of the ${\rho}$-Algorithm that is a typical workflow process mining algorithm based on the structured information control nets. More precisely, The Workflow BIG-Logs can be classified into two types: of activity-based clustering patterns and performer-based clustering patterns, and we try to implement an activity-based clustering pattern algorithm based upon the Map-Reduce framework. Finally, we try to verify the proposed clustering technique by carrying out an experimental study on the workflow enactment event log dataset released by the BPI Challenges.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.154-156
• /
• 2022

본 논문은 카메라 어레이기반 실사 다시점 입체영상을 획득·생성하기 위한 워크플로우를 제시하고 이를 검증하기 위한 실험 결과를 소개한다. 구체적으로, 액션 캠 기반 수렴형 리그 구조, 획득 동기화, 카메라 캘리브레이션, 깊이 맵 추출을 포함하는 일련의 과정 및 이에 대한 검증으로 실내외 2종의 콘텐츠의 획득 실험 결과를 기술한다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.2
• /
• pp.32-40
• /
• 2011

Reversible data hiding, which can recover the original image without any distortion after the extraction of the hidden data, has drawn considerable attention in recent years. However, underflow and overflow problems have occurred occasionally in the embedded image. To overcome these problems, we propose a new reversible data hiding algorithm which embeds a compressed location map used to identify these underflow and overflow points. In addition, the proposed algorithm allows for multilevel data hiding to increase the hiding capacity. The simulation results demonstrate that the proposed algorithm generates good performances in the PSNR, the embedding capacity, and the size of side information.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.10
• /
• pp.1443-1449
• /
• 2013

Automatic detection of vehicles in front is an integral component of many advanced driver-assistance system, such as collision mitigation, automatic cruise control, and automatic head-lamp dimming. Regardless day and night, tail-lights play an important role in vehicle detecting and status recognizing of driving in front. However, some drivers do not know the status of the tail-lights of vehicles. Thus, it is required for drivers to inform status of tail-lights automatically. In this paper, a recognition method of status of tail-lights based on video processing and recognition technology is proposed. Background estimation, optical flow and Euclidean distance is used to detect vehicles entering tollgate. Then saliency map is used to detect tail-lights and recognize their status in the Lab color coordinates. As results of experiments of using tollgate videos, it is shown that the proposed method can be used to inform status of tail-lights.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.219-221
• /
• 2012

본 논문은 무손실 데이터 은닉 기법중 주변 화소의 통계적 특성을 이용하여 어떠한 추가적인 맵 정보 없이 키 파라미터로써 원본 영상과 삽입한 데이터를 정확히 분리해 내는 기법이다. 오버/언더 플로우에 더 강한 데이터 은닉을 위해, 데이터 삽입에 대한 변수로 작용할 수 있는 주변 화소값들의 범위 뿐만 아니라 주변 화소값들의 표준 편차와 평균값을 모두 키 파라미터의 인자로 사용하여 화소값이 낮은, 즉 영상의 밝기가 어두운 부분에 더 많은 데이터를 삽입할 수 있는 기법을 제안하였고, 실험을 통하여 기존 기법 대비 평균 2배 이상의 삽입 용량이 증진된 것을 확인하였다.

• Annual Conference of KIPS
• /
• 2003.11c
• /
• pp.1725-1728
• /
• 2003

인터넷의 보급 확산과 정보통신기술 및 웹 기술의 발달로 쇼핑몰 사이트가 등장하게 되었다. 현재 쇼핑몰 사이트는 그 종류가 다양해지고, 규모가 대형화되고 있으며, 매출규모 또한 증가하고 있는 추세이다. 이러한 많은 쇼핑몰 사이트들은 매출경쟁에서 자사의 수익창출을 위해 끈임없이 노력하고 있고 특히, 고객이 편리하게 쇼핑을 할 수 있도록 원활한 페이지 이동을 지원하고 있다. 고객의 쇼핑과정에 영향을 미치는 페이지 이동을 기존의 웹사이트 설계기법인 플로우차트, 스토리보드, 사이트 맵으로 표현하기에는 미흡한 점이 있다. 따라서 본 논문에서는 개념적이고 직관적인 설계가 가능한 EMFG(Extended Mark Flow Graph)[6]를 이용하여 쇼핑몰 사이트에서 웹 페이지간의 이동흐름을 나타내는 링크구조를 표현하고 분석 한다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.25 no.8
• /
• pp.1294-1301
• /
• 2001

In order to reduce the time and cost for assembly, automobile speaker grills have been injection molded with door trims or map pockets in one piece recently. However, several defects such as short shots or air traps can easily occur due to the decreased fluidity of the melting polymer according to the excessive heat transfer to the mold. Therefore, it is necessary to optimize the resin feed system and predict possible defects by CAE analysis. However it is not possible to obtain exact analysis results for the speaker grill by using general shell elements since the heat transfer in the thickness direction which is the dominant factor of the filling stage can not be considered. Therefore, there have been several efforts to simulate the injection molding nature of the speaker grill by using shell elements with an effective thickness which is smaller than the actual thickness of the part. Two empirical values have been recommended for the effective thickness in real practice. One is 50∼70% of the thickness of the speaker grill and another is the gap distance between the adjacent holes. In this paper, CAE analyses of a map pocket with a speaker grill were conducted using shell elements with both of these recommended effective thicknesses, and the predicted flow fronts were compared with the findings from injection molding experiments. The commercial code MOLDFLOW was used for injection molding analysis and an 850 ton injection molding machine was used for experiments.