• Journal of IKEEE
• /
• v.14 no.4
• /
• pp.291-296
• /
• 2010

This paper handles, pitching and rolling posture change detection using the visual image changes due to the road slope conditions. When the moving vehicle is slanted to a direction, the objects in the visual images of the vehicle are moving to up or down and right or left. This is similar to the human's balancing behavior depending on the visual image change detection as well as the vestibular organs and semicircular canal in the ear. The proposes method shows the visual image through the camera can be used for the image information itself and for the posture change detection through the experiments.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.4
• /
• pp.749-754
• /
• 2021

In order to solve problems such as a decrease in the agricultural population and an aging population, research on agricultural robots is being actively conducted for the purpose of automating various agricultural tasks. The harvesting process is the most labor-intensive process among farm work and this process consumes about 2-3 times more compared to other processes. Since the transport of agricultural crops requires the most labor costs and there is a risk of injury during the operation, automating the transport operation through an agricultural robot can improve safety and significantly improve productivity. Therefore, this paper proposes an agricultural robot that is optimized for farm worksites and capable of autonomous driving.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.133-135
• /
• 2022

With the development of IoT and AI technologies and media, various digital devices are being used, and unmanned and automation is progressing rapidly. In particular, high-level image processing technology is required in fields such as smart factories, autonomous driving technology, and intelligent CCTV. However, noise present in the image affects processes such as edge detection and object recognition, and causes deterioration of system accuracy and reliability. In this paper, we propose a filtering algorithm using fuzzy weights to reconstruct images damaged by complex noise. The proposed algorithm obtains a reference value using noise judgment and calculates the final output by applying a fuzzy weight. Simulation was conducted to verify the performance of the proposed algorithm, and the result image was compared with the existing filter algorithm and evaluated.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.25-27
• /
• 2021

With the recent development of deep learning technology, computer vision-based AI technologies have been studied to analyze the abnormal behavior of objects in image information acquired through CCTV cameras. There are many cases where surveillance cameras are installed in dangerous areas or security areas for crime prevention and surveillance. For this reason, companies are conducting studies to determine major situations such as intrusion, roaming, falls, and assault in the surveillance camera environment. In this paper, we propose a real-time abnormal behavior analysis algorithm using object detection and tracking method.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.199-200
• /
• 2021

최근 어린이 보호구역 내에서의 운전자의 부주의로 사망 혹은 상해 사고를 일으킨 가해자를 가중 처벌하는 내용의 '민식이법'이 발의됨에 따라 많은 운전자들이 보호구역을 주행할 때 많은 부담감을 느끼며, 이에 대한 운전자의 부담감과 사고 피해를 최소화할 수 있는 시스템이 필요하다. 본 논문에서는 OpenCV 영상인식기술과 OCR 문자인식기술인 Tesseract를 이용해 노약자 보호구역 표지판을 인식하여 법정 제한속도를 준수하며 갑작스러운 장애물 등장 시 급정거하여 사고피해를 최소화하고, 또한, 사용자에게 알람 메시지를 전송하는 시스템을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.1245-1248
• /
• 2021

최근 세계적으로 코로나바이러스가 유행 중인 가운데, 우리나라는 인구 밀집도가 높은 곳이 많아 연쇄 감염이 일어나기 쉽고 특히 식당이나 카페 같은 장소는 불가피한 음식 섭취, 환기되지 않는 실내 공간 등의 이유로 바이러스에 취약하다. 사람들은 코로나 감염 가능성이 큰 사람이 밀집된 장소를 피하고, 비교적 사람이 적은 곳을 선호한다. 하지만 방문하고자 하는 매장에 사람이 얼마나 있는지 확인하는 과정은 번거롭다. 또한, 인기 있는 매장의 경우 코로나바이러스와 무관하게 이용객이 많아 방문 시에 대기해야 하는 불편함이 있다. 이러한 불편함을 해결하기 위해 본 논문에서는 안드로이드 기반 스마트폰 앱을 이용하여 방문하고자 하는 매장에 인원수를 실시간으로 확인할 수 있는 실시간 객체 인식 알고리즘, 앱의 구현 내용을 소개하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.465-466
• /
• 2022

본 논문에서는 딥러닝 영상인식 기술을 활용한 객체검출 모델인 YOLOv4를 활용하여 차량의 모델과 번호판인식 시스템을 제안한다. 본 논문에서 제안하는 시스템은 실시간 영상처리기술인 YOLOv4를 사용하여 차량모델 인식과 번호판 영역 검출을 하고, CNN(Convolutional Neural Network)알고리즘을 이용하여 번호판의 글자와 숫자를 인식한다. 이러한 방법을 이용한다면 카메라 1대로 차량의 모델 인식과 번호판 인식이 가능하다. 차량모델 인식과 번호판 영역 검출에는 실제 데이터를 사용하였으며, 차량 번호판 문자 인식의 경우 실제 데이터와 가상 데이터를 사용하였다. 차량 모델 인식 정확도는 92.3%, 번호판 검출 98.9%, 번호판 문자 인식 94.2%를 기록하였다.

• Journal of Advanced Navigation Technology
• /
• v.25 no.6
• /
• pp.466-475
• /
• 2021

Airport-related laws restrict the installation of lights that obstruct the identification of airport lights or cause glare to pilots and controllers around the airport. However, with regard to the glare that lights give to the pilot or controller, it is only judged whether there is a limit based on a qualitative judgment, and a quantitative review has not been made. Therefore, in this study, visual disturbances that may occur to pilots and controllers due to large lighting facilities around airports during nighttime flight operation were quantitatively calculated and confirmed through disability glare, object recognition, and identification obstruction. And based on this study, it was suggested to supplement the related system to prevent the visual impairment of pilots and controllers caused by lighting facilities.

• Korean Journal of Construction Engineering and Management
• /
• v.19 no.2
• /
• pp.15-24
• /
• 2018

Despite the recognition of the need for productivity information and its importance, the feedback of productivity information is not well-established in the construction industry. Effective use of productivity information is required to improve the reliability of construction planning. However, in many cases, on-site productivity information is hardly management effectively, but rather it relies on the experience and/or intuition of project participants. Based on the literature review and expert interviews, the authors recognized that one of the possible solutions is to develop a systematic approach in dealing with productivity information of the construction job-sites. It is required that the new system should not be burdensome to users, purpose-oriented information management, easy-to follow information structure, real-time information feedback, and productivity-related factor recognition. Based on the preliminary investigations, this study proposed a framework for a novel system that facilitate the effective management of construction productivity information. This system has utilized Sketchup software which has good user accessibility by minimizing additional data input and related workload. The proposed system has been designed to input, process, and output the pertinent information through a four-stage process: preparation, input, processing, and output. The inputted construction information is classified into Task Breakdown Structure (TBS) and Material Breakdown Structure (MBS), which are constructed by referring to the contents of the standard specification of building construction, and converted into productivity information. In addition, the converted information is also graphically visualized on the screen, allowing the users to use the productivity information from the job-site. The productivity information management system proposed in this study has been pilot-tested in terms of practical applicability and information availability in the real construction project. Very positive results have been obtained from the usability and the applicability of the system and benefits are expected from the validity test of the system. If the proposed system is used in the planning stage in the construction, the productivity information and the continuous information is accumulated, the expected effectiveness of this study would be conceivably further enhanced.

• Journal of Sensor Science and Technology
• /
• v.11 no.5
• /
• pp.255-262
• /
• 2002

Human retina is able to detect the edge of an object effectively. We designed a CMOS vision chip by modeling cells of the retina as hardwares involved in edge detection. There are several fluctuation factors which affect characteristics of MOSFETs during CMOS fabrication process and this effect appears as output offset of the vision chip which is composed of pixel arrays and readout circuits. The vision chip detecting edge information from input image is used for input stage of other systems. Therefore, the output offset of a vision chip determine the efficiency of the entire performance of a system. In order to eliminate the offset at the output stage, we designed a vision chip by using CDS(Correlated Double Sampling) technique. Using standard CMOS process, it is possible to integrate with other circuits. Having reliable output characteristics, this chip can be used at the input stage for many applications, like targe tracking system, fingerprint recognition system, human-friendly robot system and etc.