• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.399-402
• /
• 2003

This paper deals with the making avatar like a caricature from human face image which is made by web camera. Generally, the Image made by web camera is not low quality but also, there are always various lights and backgrounds. So, It is impossible to recognize a human face's contour by some methods which only find some feature points of a image. Therefore, In this paper, we propose a new method for overcoming defeat of that methods. First, we got the area of human face roughly by color information. And then, we could find the exact human face's contour by using B-spline Snake.

• Journal of Information Technology Applications and Management
• /
• v.10 no.3
• /
• pp.45-54
• /
• 2003

Security system with web camera remarkably has been developed at an Internet era. Using transmitted images from remote camera, the system can recognize current situation and take a proper action through web. Existing motion detection methods use simply difference image, background image techniques or block matching algorithm which establish initial block by set search area and find similar block. But these methods are difficult to detect exact motion because of useless noise. In this paper, the proposed method is updating changed background image as much as $N{\times}M$pixel mask as time goes on after get a difference between imput image and first background image. And checking image pixel can efficiently detect motion by computing fixed distance pixel instead of operate all pixel.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.449-452
• /
• 2005

For home networking system with a function of air quality monitoring, a wireless sensor module with several air quality monitoring sensors was developed for indoor environment monitoring system in home networking. The module has various enlargements for various kinds of sensors such as humidity sensor, temperature sensor, CO2 sensor, flying dust sensor, and etc. The developed wireless module is very convenient to be installed on the wall of a room or office, and the sensors in the module can be easily replaced due to well designed module structure and RF connection method. To reduce the system cost, only one RF transmission block was used for sensors' signal transmission to 8051 microcontroller board in time sharing method. In this home networking system, various indoor environmental parameters could be monitored in real time from RF wireless sensor module. Indoor vision was transferred to client PC or PDA from surveillance camera installed indoor or desired site. Web server using Oracle DB was used for saving the visions by web-camera and various data from wireless sensor module.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.637-640
• /
• 2011

기존의 보안시스템은 설비가 비싸고 녹화를 끊임없이 계속함에 따라 저장 용량이 커야하는 문제점이 있고 영상을 단순히 저장하는 외에 다른 부가적 기능이 없다. 본 연구에서는 고성능, 고가의 장비가 아닌 단순한 PC 카메라 와 일반컴퓨터를 이용한 화상 보안 시스템을 제안 한다. 이 시스템은 단순한 녹화 외에 다양한 부가기능을 포함하고 있으며 프로그램이 설치된 컴퓨터를 떠난 외부에서도 감지한 침입을 통보 받을 수 있다. Main Application의 역할은 감시, 재생, 통계, 필터로 분류된다. 카메라에서 실시간으로 보내오는 영상을 메인 프로그램에서 보여주고 일시 정지, 필터 바로 가기 등을 통하여 필터와 연계된다. 이미 저장된 영상은 재생기능을 통하여 재생하며 이제까지 저장된 영상들은 모두 데이터베이스에 통계 화 되어 저장된다. 또한 실시간으로 보여 지는 영상들을 일정한 간격으로 웹 서버로 보내진다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11b
• /
• pp.1443-1446
• /
• 2002

This paper proposes to integrate WAP(Wireless Application Protocol) with Bluetooth to implement a home automation system. One of the most important benefits of the proposed approach is the elimination of the problem of limited distance of Bluetooth as less than 10 meter. With WAP providing a data link between the Internet and a mobile phone and embedded WEB camera through Bluetooth, we can control various home appliances whenever and wherever we want. The hardware and software design issues for implementing such system are discussed and a pilot home automation system is implemented.

• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.295-301
• /
• 2021

Digital media technology is gradually developing with the development of convergence quaternary industrial technology and mobile devices. The combination of deep learning and augmented reality can provide more convenient and lively services through the interaction of 3D virtual images with the real world. We combine deep learning-based pose prediction with augmented reality technology. We predict the eight vertices of the bounding box of the object in the image. Using the predicted eight vertices(x,y), eight vertices(x,y,z) of 3D mesh, and the intrinsic parameter of the smartphone camera, we compute the external parameters of the camera through the PnP algorithm. We calculate the distance to the object and the degree of rotation of the object using the external parameter and apply to AR content. Our method provides services in a web environment, making it highly accessible to users and easy to maintain the system. As we provide augmented reality services using consumers' smartphone cameras, we can apply them to various business fields.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.69-71
• /
• 2022

Today, the AI market is very large due to the development of AI. Among them, the most advanced AI is image detection. Thus, there are many object detection models using YOLOv5.However, most object detection in AI is focused on detecting objects that are stereotyped.In order to recognize such unstructured data, the object may be recognized by learning and filtering the object. Therefore, in this paper, a fire monitoring system using YOLOv5 was designed to detect and analyze unstructured data fires and suggest ways to improve the fire object detection model.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• v.10 no.2
• /
• pp.396-399
• /
• 2005

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.12
• /
• pp.1036-1040
• /
• 2002

To process data of digital linescan camera, the frame grabber is essential to handle the data in low-level and in high speed more than 30 MHz stably. Traditional approaches to the development of hardware in vision system for the special purpose are mai y based on PC system, and are expensive and gigantic. Therefore, there are many difficulties in applying those in the field. So we investigate, in this paper, the implementation of FPGA for real-time processing of digital linescan camera. The system is not based on PC, but electronic device such as micropncessor. So it is expected that the use of FPGAs for low-level processing represents a fast, stable and inexpensive system. The experiments are carried out on the web guiding system in order to show the efficiency of the new image processor.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2414-2417
• /
• 2005

Compact Camera Module(CCM) is widely used in PDA, Celluar phone and PC web camera. With the greatly increasing use for mobile applications, there has been a considerable demands for high speed production of CCM. The major burden of production of CCM is assembly of lens module onto CCD or CMOS packaged circuit board. After module is assembled, the CCM is inspected. In this paper, we developed the image capture board for CCM and the imaging processing algorithm to inspect the defects in captured image of assembled CCMs. The performances of the developed inspection system and its algorithm are tested on samples of 10000 CCMs. Experimental results reveal that the proposed system can focus the lens of CCM within 5s and we can recognize various types of defect of CCM modules with good accuracy and high speed.