• Journal of Korea Multimedia Society
• /
• v.16 no.8
• /
• pp.927-933
• /
• 2013

Face detection algorithm of OpenCV recognizes the faces by Haar matching between input image and Haar features which are learned through a set of training images consisting of many front faces. Therefore the face detection method by Haar matching yields a high face detection rate for the front faces but not in the case of the pan and deformed faces. On the assumption that distributional characteristics of color histogram is similar even if deformed or side faces, a face detection method using the histogram pattern matching is proposed in this paper. In the case of the missed detection and false detection caused by Haar matching, the proposed face detection algorithm applies the histogram pattern matching with the correct detected face area of the previous frame so that the face region with the most similar histogram distribution is determined. The experiment for evaluating the face detection performance reveals that the face detection rate was enhanced about 8% than the conventional method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.1
• /
• pp.169-177
• /
• 2014

It is essential to support the image and video analysis technology such as motion detection since the DVR and NVR storage were adopted in the real time visual surveillance system. Especially the network camera would be popular as a video input device. The traditional CCTV that supports analog video data get be replaced by the network camera. In this paper, we present the design and implementation of video surveillance system that provides the real time motion detection by the video storage server. The mobile application also has been implemented in order to provides the retrieval functionality of image analysis results. We develop the video analysis server with open source library OpenCV and implement the daemon process for video input processing and real-time image analysis in our video surveillance system.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.319-320
• /
• 2019

본 논문에서는 opencv를 이용한 이메일 송신기능을 가진 감시 카메라을 제안한다. 라즈베리파이와 라즈베리파이 전용 카메라를 이용하여 구현하였다. opencv를 이용해 얼굴 검출이 가능하게 하였다. 그리고 motion 라이브러리를 사용하여 인터넷으로 스트리밍이 가능하도록 하였다. SMTP 라이브러리를 이용하여 이메일을 보낼 수 있다.

• Journal of the Korean Electrochemical Society
• /
• v.6 no.2
• /
• pp.113-118
• /
• 2003

Processible polyaniline (PAM) dispersions consisting of polyaniline micro-particles, cyclohexanone, and a polymeric surfactant were prepared in a micro-milling machine with various mixing conditions. The electrochemical properties of the dispersion film coated on Pt electrode were investigated by cyclic voltammetry (CV). The electrochemistry of the PAM dispersion coatings was basically similar to a pure PAM coating based on the results of CV. The results of polarization measurements and open circuit potential measurements carried out in $3\;wt.\%$ NaCI solution showed increase in corrosion potential when the PANI dispersion coatings applied on steel surface. Variation of open circuit potential $(OCP,\;V_{OC})$ of the dispersion coating/steel electrodes was observed, which differed with milling conditions. The results demonstrated practical use of the conducting polymer dispersion as a coating material for corrosion prevention of steel.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.46 no.11
• /
• pp.911-920
• /
• 2018

In this study, we performed a study to track the angle between the guided weapon and the target by using the strap-down image seeker, and constructed a test bed that can simulate it visually. This paper describes a method to maintain high-performance feature distribution in the implementation of sparse feature tracking algorithm such as Lucas Kanade's optical flow algorithm for target tracking using image information. We have extended the feature tracking problem to the concept of feature management. To realize this, we constructed visual environment using Unity3D engine and developed image processing simulation using OpenCV. For the co-simulation, dynamic system modeling was performed with Matlab Simulink, the visual environment using Unity3D was constructed, and computer vision work using OpenCV was performed.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.4
• /
• pp.679-686
• /
• 2022

In this paper, we implemented an algae removal device that recognizes and removes algae existing in water using Raspberry Pi camera and DO (Dissolved Oxygen) sensor. The Raspberry Pi board recognizes the color of green algae by converting the RGB values obtained from the camera into HSV. Through this, the location of the algae is identified and when the amount of dissolved oxygen's decrease at the location is more than the reference value using the DO sensor, the algae removal device is driven to spray the algae removal solution. Raspberry Pi's camera uses OpenCV, and the motor movement is controlled according to the output value of the DO sensor and the result of the camera's green algae recognition. Algae recognition and spraying of algae removal solution were implemented through Arduino and Raspberry Pi, and the feasibility of the proposed portable algae removal device was verified through experiments.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.1101-1104
• /
• 2021

최근 COVID-19(코로나 바이러스 감염증) 확산에 따라 다양한 분야에서 힘든 상황이 이어지고 있다. 중앙 재난 안전 대책본부에 따르면 지난 2월 한 달간 코로나 안전신고는 약 2만 5천 건의 방역수칙 위반 신고가 들어온 것으로 집계됐다. 이에 따라 음식점 및 매장은 QR코드. 수기 작성을 통한 동선 체크, 온도 검사 등 코로나 확산을 방지하기 위한 방법을 시행하고 있지만 이는 단지 코로나 확산 방지를 위한 대책 일뿐 소상공인의 매장 운영이나 안정적인 영업 유지 등 직접적인 영향을 줄 수 없다. 이에 본 논문은 OpenCV를 활용한 고객 출입 관리 시스템을 제안한다. 본 시스템은 OpenCV 영상처리기술을 활용하여 매장을 방문하는 고객의 나이, 성별을 수집하여 주요 고객층 분석, 출입 현황 및 이용 시간을 파악한다. 본 시스템은 코로나 확진자 동선 파악을 위한 역학조사와 소상공인의 효율적인 매장 운영 시간을 분석하여 '코로나 확산 방지', '소상공인 매출 증가'의 기대 효과를 얻을 수 있다. 향후, 제안하는 기법의 실질적인 검증을 위해 실제 매장 환경에서의 테스트가 필요하다.

• The Journal of Bigdata
• /
• v.9 no.1
• /
• pp.89-100
• /
• 2024

In the field of computer vision, models such as You Look Only Once (YOLO) and ResNet are widely used due to their real-time performance and high accuracy. However, to apply these models in real-world environments, factors such as runtime compatibility, memory usage, computing resources, and real-time conditions must be considered. This study compares the characteristics of three deep model runtimes: ONNX Runtime, TensorRT, and OpenCV DNN, and analyzes their performance on two models. The aim of this paper is to provide criteria for runtime selection for practical applications. The experiments compare runtimes based on the evaluation metrics of time, memory usage, and accuracy for vehicle license plate recognition and classification tasks. The experimental results show that ONNX Runtime excels in complex object detection performance, OpenCV DNN is suitable for environments with limited memory, and TensorRT offers superior execution speed for complex models.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.2
• /
• pp.1083-1088
• /
• 2014

Recently, due to advances in both imaging technology and ICT, various types of image processing services became available and the application services of these two technologies are diversifying. Recognition of vehicle license plates is used in places where vehicle information is needed such as in parking management. However, existing systems have economic disadvantages like issuing parking tickets and attaching unnecessary equipment. In order to solve these problems, we designed and implemented automatic parking management system through recognition of vehicle license plates by using emguCV that is based on OpenCV. Additionally, we designed improved UI to handle the entire parking management situation which include information such as details of each parking vehicle, parking time and remaining parking spaces without screen movement. This improved UI is implemented with the use of WPF which is the latest technology in user program development. The emguCV used in this paper showed the most optimized performance in Intel based environment. With it, we obtained the result of within 0.5 seconds of recognition processing time and over 90% of recognition rate. Through improved UI, the manager could both simply and intuitively manage the entire system.

• Journal of the Korea Convergence Society
• /
• v.7 no.1
• /
• pp.37-42
• /
• 2016

Recent advances have been made in technology of sensor devices. Accordingly, the size of devices has been miniaturized, to which diverse functions can be applied. On top of that, the devices use image processing technology to observe circumstances of users' living spaces and detect risk situations saved in database. In case of detecting risk situations, M2M environment is constructed so that the information can be delivered to other communication devices to immediately raise an alarm. This paper aims to introduce solutions that construct M2M environment by using color detection algorithm of OpenCV and Raspberry Pi, raise an alarm to users in case of fire, and provide information on follow-up measures for it.