• Proceedings of the Korean Information Science Society Conference
• /
• 2010.11a
• /
• pp.127-128
• /
• 2010

본 논문에서는 CCTV 감시 영상에서 취득한 얼굴 이미지를 이용하여, 범죄자 감시목록에 등록된 범죄 용의자를 탐지 식별하는 시스템을 설계 및 구현하였다. 특히 본 논문에서 제안한 SVDD와 SRC를 혼합한 계층적 구조의 범죄 용의자 식별 모듈은 다음과 같은 특성을 갖는다: 1) 먼저 SVDD를 이용하여 범죄 용의자만을 빠르게 인식함으로써, 일반인에 대한 불필요한 범죄자 식별 연산을 수행하지 않는다; 2) 다양한 식별 성능을 저해하는 환경에서도 이미 강인한 성능이 검증된 SRC를 범죄 용의자 식별과정에 적용함으로써 안정적이고 정확한 식별 시스템을 보장한다; 3) 동일 생체 특정의 반복적 사용을 통한 다수결 투표전략을 취함으로써 시스템의 신뢰도를 보장한다; 4) 점증적 갱신의 학습 능력으로 인하여 범죄 용의자 감시목록 데이터베이스의 변화에도 능동적으로 적응한다 실제 KUFD(Korea University Face Database)를 자체 제작하고 캠퍼스 내에서 CCTV 환경의 얼굴 인식 기반 범죄 용의자 탐지 및 식별 시스템 환경을 모의 구축하여 실험적으로 제안된 시스템의 성능을 검증한다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.4
• /
• pp.3-10
• /
• 2015

The various studies and applications for UAVS(Unmaned Aerial Vehicle System) have been recently increased as a new technology to create 3D spatial information rapidly and accurately. UAV(Unmanned Aerial Vehicle) is economical when comparing with conventional technique, such as satellite and aerial survey, and can quickly obtain high resolution data under 5cm. This paper examined the utilizing possibility to creating 3D spatial information and analysis the compatibility the UAV data obtained by non-metric digital camera with conventional numerical photogrammetric system. The DEM and normal orthophoto is created by exclusive S/W and DPW(Digital Photogrammetry Workstation) then analysis the accuracy of created data. As a result, the accuracy of the created DEM and normal orthophoto, which is obtained by UAV then processed by DPW, is not satisfied;so it is estimated that the compatibility the UAV data with conventional numerical photogrammetric system is low.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.363-366
• /
• 2001

The present process of grading leather quality by the rare eyes is not reliable. Because inconsistency of grading due to eyes strain for long time can cause incorrect result of grading. Therefore it is necessary to automate the process of grading quality of leather based on objective standard for it. In this paper, leather automatic classification system consists of the process obtaining the information of leather and the process grading the quality of leather from the information. Leather is graded by its information such as texture density, types and distribution of defects. This paper proposes the algorithm which sorts out leather information like texture density and defects from the gray-level images obtained by digital camera. The density information is sorted out by the distribution value of Fourier spectrum which comes out after original image is converted to the image in frequency domain. And the defect information is obtained by the statistics of pixels which is relevant to Window using searching Window after sort out boundary lines from preprocessed images. The information for entire leather is used as standard of grading leather quality, and the proposed algorithm is practically applied to machine vision system.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.151-161
• /
• 2024

In this paper, we develop 'the Danger Map' of a workplace to identify risk and harmful factors by analyzing images of each process within the manufacturing plant site using artificial intelligence (AI). We proposed a system that automatically derives 'the risk and safety levels' based on the frequency and intensity derived from this Danger Map in accordance with actual field conditions and applies them to similar manufacturing industries. In particular, in the traditional evaluation method of manually evaluating the risk of a workplace using Excel, the risk level for each risk and harmful factor acquired from the video is automatically calculated and evaluated to ensure safety through the system and calculate the safety level, so that the company can take appropriate actions accordingly. and measures were prepared. To automate safety calculation and evaluation, 'Heinrich's law' was used as a model, and a 5X4 point evaluation scale was calculated for risky behavior patterns. To demonstrate this system, we applied it to a casting factory and were able to save 2 people the time and labor required to calculate safety each month.

• Korean Journal of Remote Sensing
• /
• v.19 no.6
• /
• pp.447-456
• /
• 2003

This study investigated the method for obtaining 3-dimensional terrain information on inaccessable areas by evaluating geometric accuracy of the EOC pass image and scene image acquired from the KOMPSAT-1 satellite. For this purpose, the following four experiments were conducted to evaluate the accuracy of the KOMPSAT-1 EOC satellite data. 1) Calculation of ground coordinates by using ancillary data and image coordinates on Level 1R that were processed by the pre-processing system of KOMPSAT-1. 2) Calculation of 3-dimensional ground coordinates from the ground coordinates of stereo images calculated by using ancillary data, based on space intersections. 3) Execution of bundle adjustment by using GCP (Ground Control Point) extracted in a part of the stereo pass image (KOMPSAT-1 EOC, 1 scene size); and then, evaluation of the ground coordinates from the calculated exterior orientation. 4) Evaluation of accuracy by applying the exterior orientation calculated from 3) To the whole pass image.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.1
• /
• pp.44-49
• /
• 2022

Abstract Recently, with the development of IoT technology and communication media, various video equipment is being used in industrial fields. Image data acquired from cameras and sensors are easily affected by noise during transmission and reception, and noise removal is essential as it greatly affects system reliability. In this paper, we propose a weight filter algorithm based on the pixel value distribution pattern to preserve details in the process of restoring images damaged in AWGN. The proposed algorithm calculates weights according to the pixel value distribution pattern of the image and restores the image by applying a filtering mask. In order to analyze the noise removal performance of the proposed algorithm, it was simulated using enlarged image and PSNR compared to the existing method. The proposed algorithm preserves important characteristics of the image and shows the performance of efficiently removing noise compared to the existing method.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.4
• /
• pp.409-415
• /
• 2011

A gimbal system in observation reconnaissance aircraft was fabricated by assembling many parts and bearings. This system consists of a camera module and a stabilization gimbal that supports the camera module. During the flight for recording images, the gimbal system experiences various accelerations with wide frequencies. Although base excitation of stabilization gimbal results in vibration of the camera module, the camera module must be able to capture the correct and clear image even while vibrating. Hence, it is important to know the natural frequencies and vibration modes of the gimbal system with the camera module. Considering bearings as spring elements, the vibration characteristic of the gimbal system was analyzed by finite element method. In addition, harmonic response analysis was performed to determine the correct transmissibility of acceleration for the camera module in the frequency range of 0-500 Hz.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.962-970
• /
• 2021

The cause of the majority of vehicle accidents is a safety issue due to the driver's inattention, such as drowsy driving. A forward collision warning system (FCWS) can significantly reduce the number and severity of accidents by detecting the risk of collision with vehicles in front and providing an advanced warning signal to the driver. This paper describes a low power embedded system based FCWS for safety. The algorithm computes time to collision (TTC) through detection, tracking, distance calculation for the vehicle ahead and current vehicle speed information with a single camera. Additionally, in order to operate in real time even in a low-performance embedded system, an optimization technique in the program with high and low levels will be introduced. The system has been tested through the driving video of the vehicle in the embedded system. As a result of using the optimization technique, the execution time was about 170 times faster than that when using the previous non-optimized process.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.815-818
• /
• 2016

Forward collision warning systems(FCWS) and lane departure warning systems(LDWS) need regions of interest for detecting lanes and objects as road regions. In general, the lane departure warning system using a vehicle front camera is tracking a lane curve using RANSAC or the like in the form of a straight line obtained image are compared with the center of the vehicle. This algorithm has weaknesses that requires a wide range of the lane being vulnerable to the curve. This paper presents an algorithm that checks whether the current lane departure by car from the Top-view space. The algorithm also can check whether the vehicle in the lane departure of the narrow range, and shows the result that is almost not affected by noise.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.314-317
• /
• 2020

환자의 생체신호 측정 및 관찰, 영상 위생 등을 포함하는 직접간호는 간호사들의 총 간호활동 시간 중 내과는 48%, 외과는 40% 로 간호사들의 업무 부담이 되고 있다. 또한 의료기관에서 사용되는 의료기기들은 여러 회사에서 구매하여 사용되기 때문에 각 회사마다 상이한 프로토콜을 가지고 있어 하나의 시스템으로 생체신호를 모으기가 쉽지 않다. 따라서 여러 장비에서 생체신호를 실시간으로 취득하여 통합 관리할 수 있는 시스템 개발을 통해 간호사의 직접간호 업무량을 줄여 간호사의 근무환경 개선뿐만 아니라 중증환자의 경우 환자 생체신호에 대한 실시간 원격감시가 가능하고 환자에게서 발생된 모든 생체신호가 데이터베이스 시스템으로 기록관리 됨으로 인해 환자의 생체 신호에 대한 이력 추적관리가 가능함으로써, 양질의 의료 서비스가 가능한 환자케어시스템을 개발하고자 한다.