• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.60-75
• /
• 2024

The demand of users, who want to focus on the core functionality of their applications without having to manage complex virtual environments in the cloud environment, has created a new computing model called serverless computing. Within the serverless paradigm, resource provisioning and server administration tasks are delegated to cloud services, facilitating application development exclusively focused on program logic. Serverless computing has upgraded the utilization of cloud computing by reducing the burden on cloud service users, and it is expected to become the basic model of cloud computing in the future. A serverless platform is responsible for managing the cloud virtual environment on behalf of users, and it is also responsible for executing serverless functions that compose applications in the cloud environment. Considering the characteristics of serverless computing in which users are billed in proportion to the resources used, the efficiency of the serverless platform is a very important factor for both users and service providers. This paper aims to identify various factors that affect the performance of serverless computing and analyze the latest research trends related to it. Drawing upon the analysis, the future directions for serverless computing that address key challenges and opportunities in serverless computing are proposed.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.10
• /
• pp.323-332
• /
• 2022

As various services using AI technology are being developed, much attention is being paid to AI service production. Recently, AI technology is acknowledged as one of ICT services, a lot of research is being conducted for general-purpose AI service production. In this paper, I describe the research results in terms of systems for AI service production, focusing on the distribution and production of machine learning models, which are the final steps of general machine learning development procedures. Three different Ubuntu systems were built, and experiments were conducted on the system, using data from 2017 validation COCO dataset in combination of different AI models (RFCN, SSD-Mobilenet) and different communication methods (gRPC, REST) to request and perform AI services through Tensorflow serving. Through various experiments, it was found that the type of AI model has a greater influence on AI service inference time than AI machine communication method, and in the case of object detection AI service, the number and complexity of objects in the image are more affected than the file size of the image to be detected. In addition, it was confirmed that if the AI service is performed remotely rather than locally, even if it is a machine with good performance, it takes more time to infer the AI service than if it is performed locally. Through the results of this study, it is expected that system design suitable for service goals, AI model development, and efficient AI service production will be possible.

• Journal of Korea Multimedia Society
• /
• v.15 no.7
• /
• pp.837-846
• /
• 2012

This paper presents a watermarking scheme based on the perspective distance for the secure mash-up service. The proposed scheme embeds the watermark of the location information of satellite image and the user information using edge color histogram, which is dissimilar to general digital image. Therefore, this scheme can trace the illegal distributor and can protect private information of user through the watermarking scheme that is adaptive to satellite image. Experimental results verified that our scheme has the invisibility and also the robustness against geometric attacks of rotation and translation.

• Journal of the Korea Convergence Society
• /
• v.10 no.4
• /
• pp.33-38
• /
• 2019

Recently, to support location-based services, there have been many researches which consider the spatial network. For this, there are many experimental data for data processing on the road network. However, the data to process the trajectory of moving objects are not suitable. Therefore, we propose index structure to process the trajectory data on the road network and the trajectory data generation algorithm. In addition, to prove efficiency of our index structure and algorithm, we show that edge-based trajectory data are generated through the proposed algorithm using the map data of San Francisco Bay.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.11
• /
• pp.2474-2479
• /
• 2011

As society has developed rapidly toward a highly advanced digital information age, a multimedia communication service for acquisition, transmission and storage of image data as well as voice has being commercialized. However, image data is always corrupted by various noises during image processing, so researches for removing noises have been continued until now. In this paper, in order to remove impulse noise we proposed modified adaptive switching median filter that consists of two stages: noise detection and noise removal. Proposed algorithm only processes noise pixels and these noise pixels are replaced by filter output, so proposed algorithm performs well not only removes noise but also preserves edge information. Also we compare existing methods using PSNR(peak signal to noise ratio) as the standard of judgement of improvement effect and choose conventional algorithms to compare with our proposed method.

• Journal of Advanced Technology Convergence
• /
• v.1 no.2
• /
• pp.01-09
• /
• 2022

Recently, safety issues in companies and public institutions are no longer a task that can be postponed, and when a major safety accident occurs, not only direct financial loss, but also indirect loss of social trust in the company and public institution is greatly increased. In particular, in the case of a fatal accident, the damage is even more serious. Accordingly, as companies and public institutions expand their investments in industrial safety education and prevention, open AI learning model creation technology that enables safety management services without being affected by user behavior in industrial sites where high-risk situations exist, edge terminals System development using inter-AI collaboration technology, cloud-edge terminal linkage technology, multi-modal risk situation determination technology, and AI model learning support technology is underway. In particular, with the development and spread of artificial intelligence technology, research to apply the technology to safety issues is becoming active. Therefore, in this paper, an open cloud platform design method that can support AI model learning for high-risk site safety management is presented.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1996.06a
• /
• pp.187-190
• /
• 1996

본 논문은 고속의 프랙탈 영상압축 기법으로 알려져 있는 Bath 프랙탈 영상 압축 기법의 성능을 여러 가지 측면에서 분석한다. Bath 프랙탈 영상 압축 기법은 영상의 빠른 복호화가 가능하므로 미래의 다양한 형태로 요구되는 정보서비스, VOD(Video On Demand), CD-ROM 등과 같이 저장되어 있는 영상 정보의 빠른 복원이 요구되는 곳에 적합한 부호화 기술이므로 그 성능에 대한 분석이 중요하다. 본 논문에서는 Bath 프랙탈 압축 기법의 양자화 방법에 따른 성능 분석, 프랙탈 계수 값의 분포에 따른 성능 평가, 사용된 어핀 맵핑식에 따른 성능 비교, 영상내의 에지 빈도수에 따른 성능 변화, 쿼드트리 구조의 작은 블록들에 대한 BFT의 성능 평가 등을 고찰한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2010.07a
• /
• pp.117-119
• /
• 2010

본 논문에서는 옴니버스 형태의 동영상을 각 프로그램 별로 자동 분할하는 방법에 대해 제안하고자 한다. 국내 TV 프로그램의 경우 대부분의 개그 프로그램에서는 코너 별로 상단 또는 하단의 일정 위치에 코너명을 캡션으로 삽입하여 옴니버스 형태의 영상을 서비스한다. 이러한 코너명을 태깅아이콘으로 하여 지속되는 구간을 검출하여 시작시점과 종료시점을 검출함으로써 동영상을 의미적으로 분할 할 수 있다. 하지만 태깅아이콘의 경우 매우 높은 투명도를 갖는 경우가 많으므로 본 연구에서는 에지와 시간적인 지속성을 이용하여 에피소드를 분할하는 방법을 제안하고, 옴니버스 형태의 다양한 개그 프로그램에 대해 실험하여 제안한 방법의 우수성을 보인다.

• Proceedings of the KSRS Conference
• /
• 2009.03a
• /
• pp.296-300
• /
• 2009

가상현실이나 인터넷 웹지도 서비스와 같이 3차원의 실세계를 시스템 상에 그대로 재현(reconstruction)하기 위해서는 정교하고 세밀한 3차원 도시모델이 필수적이다. 이러한 3차원 도시모델의 자동생성은 원격탐사 및 사진측량 분야에서 많은 연구가 수행되고 있다. 이러한 연구들은 다양한 센서 데이터와 기 구축되어 있는 GIS자료를 이용하여 건물, 도로, 지형 등의 도시모델을 자동으로 생성하고자 한다. 그러나 대부분의 연구에서 추출한 각 기본요소(primitives)-평면패치(planar patches), 에지(edges), 모서리(corners)에 대한 국부적인 정제(refinement)는 수행하였으나, 생성한 건물 모델에 대한 광역적인 조정을 통한 정규화에 대한 연구는 미비한 상태이다. 본 연구에서는 다양한 데이터로부터 생성된 B-rep (boundary representation) 형태의 건물 모델에 대하여 기하학적인 제약요소(constraints)를 이용한 정규화(regularization) 방법론을 제시하고자 한다. 제안하는 방법은 건물의 Domain Knowledge에 기반하여 도출한 건물을 구성하는 기본요소(primitives)간의 인접성, 직교성, 평행성, 교차성 등의 다양한 제약조건을 이용하여 광역적으로 조정한다. 시뮬레이션 데이터에 적용한 결과의 분석을 통해 제안된 정규화 방법을 통해 오차가 포함된 건물모델이 보다 정형화된 형태로 조정되었음을 확인하였다.

• Annual Conference of KIPS
• /
• 2020.11a
• /
• pp.589-592
• /
• 2020

본 논문은 스마트 해상 물류에 필요한 최신 Edge Computing과 인공지능을 구성한 자율 접안 시뮬레이터의 개발이다. 먼저, 스마트 해상 물류에서 선박의 접안에 관한 요구 사항을 분석하고, 다음으로 그 분석된 결과를 사용하여 서비스, 시스템, 핵심부품을 설계하고 제작한다. 결국, 본 논문은 스마트 해상물류에 필요한 자율접안 시뮬레이터를 개발한다. 향후, 본 논문은 실제 스마트 해상 물류에 필요한 Edge Computing과 인공지능의 기계 학습 알고리즘을 개발할 계획이다.