• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2016년도 추계학술발표대회
• /
• pp.804-807
• /
• 2016

빅데이터 분야에 대한 다양한 연구가 활발하게 진행됨에 따라 표준화에 대한 요구가 증가하고 있다. 이러한 요구를 충족하기 위해 최근 ISO/IEC JTC 1 산하 표준화 위원회를 중심으로 빅데이터 표준화에 대한 연구가 활발하게 진행되고 있다. 그러나 아직까지 구체적인 기술 측면에서의 표준화는 미비한 상황이다. 이 논문에서는 기존 표준화 연구 내용을 간략하게 조망하고 빅데이터 센싱 객체 관리 측면에서의 표준화 방안에 대하여 논의한다. 이 논문은 향후 빅데이터 분야, 특히 빅데이터를 생성하는 센싱 객체의 규범적인 관리를 위한 표준 개발에 기여할 것으로 기대된다.

• 전기학회논문지P
• /
• 제67권1호
• /
• pp.42-46
• /
• 2018

In this paper, we propose fast object detection method of the cars by applying YOLOv2(You Only Look Once version 2) and UAVs (Unmanned Aerial Vehicles) while on the highway. We operated Darknet, OpenCV, CUDA and Deep Learning Server(SDX-4185) for our simulation environment. YOLOv2 is recently developed fast object detection algorithm that can detect various scale objects as fast speed. YOLOv2 convolution network algorithm allows to calculate probability by one pass evaluation and predicts location of each cars, because object detection process has simple single network. In our result, we could find cars on the highway area as fast speed and we could apply to the real time.

• 반도체디스플레이기술학회지
• /
• 제6권2호
• /
• pp.59-63
• /
• 2007

Radio Frequency Identification (RFID) is a common term for technologies using micro chips that are able to communicate over short-range radio and that can be used for identifying physical objects. RFID technology already has several application areas and more are being envisioned all the time. While it has the potential of becoming a really ubiquitous part of the information society over time, there are many security and privacy concerns related to RFID that need to be solved. This paper proposes a method which could protect private information and ensure RFID's identification effectively storing face feature information on RFID tag. This method improved linear discriminant analysis has reduced the dimension of feature information which has large size of data. Therefore, face feature information can be stored in small memory field of RFID tag. The proposed algorithm in comparison with other previous methods shows better stability and elevated detection rate and also can be applied to the entrance control management system, digital identification card and others.

• 한국IT서비스학회:학술대회논문집
• /
• 한국IT서비스학회 2009년도 추계학술대회
• /
• pp.544-548
• /
• 2009

The underlying success of logistics depends on the flow of data and information for effective management. Over the last 30 years, we have seen the power of microprocessors double about every 18months. This continuing trend means that computers will become considerably smaller, cheaper, and more abundant; indeed, they are becoming ubiquitous and are even finding their way into everyday objects, resulting in the creation of smart things. In the long term, ubiquitous technologies will take on great economic significance. Industrial products will become smart because of their integrated information processing capacity, or take on an electronic identity that can be queried remotely, or be equipped with sensors for detecting their environment, enabling the development of innovative products and totally new services. The global marketplace runs on logistics, security, speed, agility and flexibility..In this paper we report that pairing these traditional logistics functions with RFID technology can be a huge value-driver for companies. This winning combination yields increased logistics management effectiveness and more efficient visibility into the supply chain management.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2005년도 추계학술대회 및 정기총회
• /
• pp.19-24
• /
• 2005

Radio Frequency Identification (RFID) is a technology used to identify the physical objects and get information about the object on which the tag attaches from network. It is expected that RFID will lead IT market from human-oriented to object-oriented. Therefore, RFID technology and services will become wide-spread. But the system of RFID naming service is quite similar to the existing DNS facilities. So it has many weak points against to DDos attack. Furthermore if the MDS server Is under attack, there might be trouble of total RFID networks.In this paper, we propose a new detecting model to find attack traffic at local routers by using Management Information Base (MIB) which is optimized for RFID MDS server.

• 한국통신학회논문지
• /
• 제22권4호
• /
• pp.793-803
• /
• 1997

Open networking architecture is required to support new multimedia services as integrated functions of network management and service architecture. In this paper, we propose the methodology of building block modeling using object grouping concepts and the sharing scheme of different distributed processing environments based on open networking architecture. The building block has the functions of object management, security object instance registry and object mapping in object group. It is necessary for the connection management information to be shared on the interworking between two domains. We implemented and validated connection management functions using computational object modeling and building block modeling in different distributed processing environments.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.60-61
• /
• 2019

Drones are opening new horizon as a major Internet-of-Things (IoT) player which is a network of objects. Drone needs to charge itself during providing services from the charging stations. If there are lots of drones and one charging station, then it is a critical situation to decide which drone should get charged first and make order of priorities for drones to get charged sequentially. In this paper, we propose an efficient scheduling algorithm for drone power charging (ESADPC), in which charging station would have a scheduler to decide which drone can get charged earlier among many other drones. Simulation results have showed that our algorithm reduces the deadline miss ration and turnaround time.

• International Journal of Advanced Culture Technology
• /
• 제7권3호
• /
• pp.134-142
• /
• 2019

As the 4th industry has been widely distributed, there is a need for a process of real-time image recognition in various fields such as identification of company employees, security maintenance, and development of military weapons. Therefore, in this paper, we will propose an algorithm that effectively recognizes a test object by comparing it with the DB model. The proposed object recognition system first expresses the outline of the test object as a set of vertices with the distances of predefined length or more. Then, the degree of matching of the structures of the two objects is calculated by examining the distances to the outline of the DB model from the vertices constituting the test object. Because the proposed recognition algorithm uses the outline of the object, the recognition process is easy to understand, simple to implement, and a satisfactory recognition result is obtained.

• 스마트미디어저널
• /
• 제7권4호
• /
• pp.61-69
• /
• 2018

Multi-tracking of general objects and specific faces is an important topic in the field of computer vision applicable to many branches of industry such as biometrics, security, etc. The rapid development of deep neural networks has resulted in a dramatic improvement in face recognition and object detection problems, which helps improve the multiple-face tracking techniques exploiting the tracking-by-detection method. Our proposed method uses face detection trained with a head dataset to resolve the face deformation problem in the tracking process. Further, we use robust face features extracted from the deep face recognition network to match the tracklets with tracking faces using Hungarian matching method. We achieved promising results regarding the usage of deep face features and head detection in a face tracking benchmark.

• 한국멀티미디어학회논문지
• /
• 제24권2호
• /
• pp.186-198
• /
• 2021

Security control using surveillance cameras is established when people observe all surveillance videos directly. However, this task is labor-intensive and it is difficult to detect all abnormal situations. In this paper, we propose a deep neural network model, called AT-Net, that automatically detects abnormal situations in the surveillance video, and introduces an automatic video surveillance system developed based on this network model. In particular, AT-Net alleviates the ambiguity of existing abnormal situation detection methods by mapping features representing relationships between people and objects in surveillance video to the new tensor structure based on sparse coding. Through experiments on actual surveillance videos, AT-Net achieved an F1-score of about 89%, and improved abnormal situation detection performance by more than 25% compared to existing methods.