• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.1
• /
• pp.78-87
• /
• 1989

In this paper, a spatio-temporal gradient (STG) method with generalized least square estimation (GLSE) is proposed for the detection of an object motion in an image sequence corrupted by white Gaussian noise. The proposed method is applied to an automatic target tracker using a high speed 16-bit microprocessor in order to track one moving target in real time. Experimental results show that the proposed method has much better performance over the conventional one with least square estimation (LSE).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.6
• /
• pp.1182-1187
• /
• 2004

Robust, real-time, fully automatic tracking of facial features is required for many computer vision and graphics applications. In this paper, we describe a fully automatic system that tracks eyes and eyebrows in real time. The pupils are tracked using the red eye effect by an infrared sensitive camera equipped with infrared LEDs. Templates are used to parameterize the facial features. For each new frame, the pupil coordinates are used to extract cropped images of eyes and eyebrows. The template parameters are recovered by PCA analysis on these extracted images using a PCA basis, which was constructed during the training phase with some example images. The system runs at 30 fps and requires no manual initialization or calibration. The system is shown to work well on sequences with considerable head motions and occlusions.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.292-293
• /
• 2018

최근 증강현실 산업 분야가 많은 각광을 받고, 시장이 성장함에 따라 보다 쉽게 증강현실을 구현 할 수 있도록 많은 SDK(Software Development Kit)들이 발표되었다. 기존에 발표 된 SDK들이 대부분 강체 추적만을 제공한다. 이는 현재 추적 알고리즘의 기반이 되는 이론이 강체에 한정되어 있기 때문이다. 그러나 제안하는 프레임워크는 강체 추적뿐만 아니라 비강체 추적 또한 가능하다. 이를 위하여, 제안하는 프레임워크는 증강현실의 핵심 기술인 추적 엔진과 보다 넓은 확장성을 가지도록 추적하고자 하는 물체를 사전에 분석하고 실시간으로 모델 변형 정보를 추정하는 시뮬레이션 엔진으로 구성된다. 추적 엔진은 기본적으로 물체의 표면에 존재하는 특징점 정보를 이용하여 추적을 진행 하되, 비강체 추적을 위하여 시뮬레이션 엔진의 도움을 받는 형태로 구성된다. 시뮬레이션 엔진에서는 물체의 역학 파라미터를 추정하여 이를 추적을 진행 할 때, 추적 엔진의 물체 표면 특징점 정보를 이용하여 물체의 변형 정보를 추정한다. 또한 제안하는 프레임워크는 성능 상의 장점 외에도 오픈소스로 공개되기에 국내 증강현실 시장 성장에 발판이 될 것으로 기대된다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.6
• /
• pp.137-142
• /
• 2020

As research on security systems using IoT (Internet of Things) devices increases, the need for research to track the location of specific objects is increasing. The goal is to detect the movement of objects in real-time and to predict the radius of movement in short time. Many studies have been done to clearly recognize and detect moving objects. However, it does not require the sharing of information between cameras that recognize objects. In this paper, using the device information of the camera and the video information taken from the camera, the movement radius of the object is predicted and information is shared about the camera within the radius to provide the movement path of the object.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.4
• /
• pp.43-49
• /
• 2021

A small infrared image homing system is a tracking system that has an infrared image sensor that identifies a target through the day and night infrared image processing of the target on the ground and searches for and detects the target with respect to the main target. This paper describes the development of a board equipped with a high-speed CPU and FPGA (Field Programmable Gate Array) to identify target through real-time image processing by acquiring target information through infrared image. We propose a CPU-FPGA combining architecture for CPU and FPGA selection and video signal processing, and also describe a controller design using FPGA to control infrared sensor.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.6
• /
• pp.1166-1174
• /
• 2015

There were the attempts to prevent the spread of harmful materials of the agri-food through the record tracking of the products with the bar code, the partial information tracking of the agri-food storage and the delivery vehicle, or the control of the temperature by intuition. However, there were many problems in the attempts because of the insufficient information, the information distortion and the independent information network of each distribution company. As a result, it is difficult to prevent the spread over the life-cycle of the agri-food using the attempts. To solve the problems, we propose the mechanism mainly to do context awareness, predict, and track the harmful materials of agri-food using big data processing.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2005.11a
• /
• pp.147-153
• /
• 2005

폐기물의 처리과정을 발생부터 최종 처리까지 처리경로를 확인하여 적정하고 투명한 처리를 도모하기 위해 폐기물의 배출에서부터 최종처리까지의 과정을 실시간 확인할 수 있는 Web 기반의 폐기물 적법처리 입증정보시스템을 구축하였다. 그러나 위치적으로 고정적인 폐기물 배출자 및 처리자와는 달리 양자간에 움직이며 폐기물을 실질적으로 이동하는 폐기물 운반차량의 관리에 대한 한계가 제기되고 있다. 이러한 폐기물 운반차량의 부실관리는 운반차량의 불법적인 투기 및 부실운반 사례로 이어져, 폐기물의 방치로 인한 환경오염을 초래하게 된다. 이러한 문제점을 해결하고자 국내의 실정에 맞는 GPS를 이용한 위치추적시스템을 구축하여 폐기물운반차량관리를 할 수 있는 시스템구축의 필요성이 제기되고 있다. 본 연구에서는 국내 도로데이터 구축현황, 시스템 구축방법 등 국내 실정에 맞는 폐기물 운반차량 위치추적시스템 구축에 대한 방법에 대한 연구를 수행하였다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.435-440
• /
• 2003

본 논문에서는 실시간 출입통제시스템에 적용이 가긍한 복잡한 배경에서의 다중 얼굴 영역 검출과 추적을 통한 얼굴 인식 알고리즘을 제안하였다. 제안된 알고리즘에서는 배경영상과 입력된 연속적인 프레임간의 차영상을 적용함으로써 물체의 움직임을 감지한 후. IISI컬러 좌표모델을 이용하여 얼굴의 1차 후보 영역을 검출하고, 잡음제거를 위해 모폴로지 연산을 수행하였다 또한 Line Projection을 이용한 객체 분할법(Object Segmentation)으로 객체를 분할함으로써 다중 얼굴 영역을 추출하였다. 또한 추출된 얼굴영역에서 눈 영역 검출을 통해 각각의 얼굴 영역들을 검증하였으며 검증된 얼굴들의 최외각 4개의 좌표를 이용하여 얼굴 추적율을 높였다. 마지막으로 얼굴 인식은 추출된 얼굴 영역으로부터 주성분 분석(PCA ： Principle Component Analysis)방법을 이용함으로써 97～98％의 높은 인식율을 보였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.6
• /
• pp.1148-1152
• /
• 2012

In this paper, we propose an intelligent surveillance system using fuzzy contrast and HOG method. This surveillance system is mainly for the intruder detection. In order to enhance the brightness difference, we apply fuzzy contrast and also apply subtraction method to before/after the surveillance. Then the system identifies the intrusion when the difference of histogram between before/after surveillance is sufficiently large. If the incident happens, the camera stops automatically and the analysis of the screen is performed with fuzzy binarization and Blob method. The intruder is detected and tracked in real time by HOG method and linear SVM. The proposed system is implemented and tested in real world environment and showed acceptable performance in both detection rate and tracking success rate.

• The Journal of the Korea Contents Association
• /
• v.19 no.12
• /
• pp.313-320
• /
• 2019

One of the causes of many damage cases that occur today by hacking attack is social engineering attack. The attacker is usually a malicious traitor or an ignorant insider. As a solution, we are strengthening security training for all employees in the organization. Nevertheless, there are frequent situations in which computers are shared. In this case, the person in charge of the computer has difficulty in tracking and responding when a specific representative accessed and what a specific representative did. In this paper, we propose the method that the person in charge of the computer tracks in real time through the smartphone when a representative access the computer, when a representative access offline using hacked or shared authentication. Also, we propose a method to prevent the leakage of important information by encrypting and backing up important files of the PC through the smartphone in case of abnormal access.