http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
주문형 케이크 제작 자동화를 위한 영상 기반 식품 모양 인식 및 측위
오장섭,이재성,Oh, Jang-Sub,Lee, Jaesung 한국정보통신학회 2020 한국정보통신학회논문지 Vol.24 No.10
본 논문에서는 주문형 케이크의 자동화 제작을 위해 필요한 일련의 영상 기반 식품 모양 인식 및 정밀 측위 방법을 제안한다. 초소형 카메라 모듈을 푸드 아트 프린터 내부의 비스듬한 위치에 장착 후 원근 변환을 적용하여 탑 뷰(top veiw) 이미지로 전환 후 에지 검출, 직선 및 원형 허프 변환 등을 수행하도록 하여 식품의 모양을 인식하고 무게 중심 좌표를 검출하도록 하였다. 본 알고리즘을 케이크 및 떡 모형에 적용하여 테스트를 수행하였으며 그 결과 180~250 lux 범위의 조명 환경에서 98.75% 의 높은 객체 인식률을 얻을 수 있었으며 50~120 lux 범위에서 0.87% 이내의 중심점 측위 오차율을 얻을 수 있었다. 이는 수요처의 요구 사항을 충분히 만족하는 수치이며 실시간 처리 성능도 프레임당 0.5초 이내로 나타나 상용화 가능성을 충분히 갖춘 것으로 판단된다. This paper proposes a vision-based food recognition method for automated production of custom cakes. A small camera module mounted on a food art printer recognizes objects' shape and estimates their center points through image processing. Through the perspective transformation, the top-view image is obtained from the original image taken at an oblique position. The line and circular hough transformations are applied to recognize square and circular shapes respectively. In addition, the center of gravity of each figure are accurately detected in units of pixels. The test results show that the shape recognition rate is more than 98.75% under 180 ~ 250 lux of light and the positioning error rate is less than 0.87% under 50 ~ 120 lux. These values sufficiently meet the needs of the corresponding market. In addition, the processing delay is also less than 0.5 seconds per frame, so the proposed algorithm is suitable for commercial purpose.
동적 장면에서의 차간 거리 보정을 위한 광학 흐름 기반 차량 자세 추정
오장섭,김형래,이동현,김종광,이성우,김학일 제어·로봇·시스템학회 2022 제어·로봇·시스템학회 논문지 Vol.28 No.11
Stable inter-vehicle distance estimations are required in dynamic scenes as they are essential for advanced driver-assistance systems (ADAS) and high-level autonomous driving. However, instantaneous changes in the pose of a vehicle in the dynamic scene may cause errors in the estimation of the inter-vehicle distance, which can lead to traffic accidents and also affect obstacle avoidance performance. In this study, the optical flow motion vector is histogrammed to extract a representative value, and the correlation between the representative value and inertial measurement unit (IMU) data is confirmed to verify the accuracy in vehicle pose estimation based on the optical flow motion vector. Then, an algorithm is proposed for improving the vehicle distance estimation accuracy in real-time ground compensation. Experiments have been conducted using an autonomous vehicle on the road with speed bumps, and the data from the IMU sensor installed in the vehicle and LiDAR detection results are used as the ground-truth data. The pose estimation with the proposed method shows an average error of 0.0029 rad, and the distance correction error can be reduced from 2.73 m (14.8%) to 0.86 m (4.6%), demonstrating the possibility of accurate real-time inter-vehicle distance correction. .
오장섭(Jangsub Oh),홍순원(Sunwon Hong),김학일(Hakil Kim) 대한기계학회 2022 대한기계학회 춘추학술대회 Vol.2022 No.3
본 논문에서는 저가형 라이다의 데이터 패킷을 UDP 소켓 통신을 통해 수신하고, 해당 패킷의 거리 데이터를 3차원 좌표로 변환하여 로봇운영체제(Robot Operating System, ROS)의 PointCloud2 메시지 형식으로 출력하는 드라이버를 제안하였다. 주요 목표는 해당 업체의 다른 라이다 제품에 대한 드라이버 호환성 확보와 해외 업체의 드라이버에 근접하는 성능을 보이는 것이다. 개발한 드라이버의 성능은 2 채널 기준 0.0153%의 변환 오차율과 14.3hz의 수신 속도, 1.8ms의 데이터 변환 속도를 보이며 해외 업체의 라이다와 거리 오차율을 기준으로 강우 환경에서의 성능 비교 평가를 실시하였다. This paper proposes a driver that receives data packets of low-cost LiDAR through UDP Socket communication, coverts distance data of the packets into three-dimensional coordinates, and outputs them in the form of PointCloud2 messages of the Robot Operating System(ROS). The main goal is to secure driver compatibility with other LiDAR products of the company and to show close performance to drivers of overseas companies. The developed driver has a conversion error rate of 0.015%, reception rate of 14.3hz, and data conversion rate of 1.8ms based on 2 channels. A comparative evaluation of the distance error rate and performance in a rainfall environment of LiDAR, an overseas company, was conducted.
오장섭(Jang-Sub Oh),이재성(Jaesung Lee) 대한전자공학회 2020 대한전자공학회 학술대회 Vol.2020 No.8
This paper proposes shape recognition and precise positioning method for multi-food printing. A small camera module mounted on a food printer recognizes the shape of the object through image processing and measure its center point. The top-view image is obtained through the perspective transformation from the image taken in real time. The circular and line hough transformations are used to recognize circular or square shapes respectively. In addition, the center of gravity coordinates of each figure are accurately detected in units of pixels. The test results shows a object recognition rate of 87.50%~98.75% and a positioning error rate of less than 1.27% under a lighting environment of 50~120 lux. These values sufficiently meet the requirements of the consumer.
이재구,오장섭,정성훈,송복식,문동찬,김선태 한국전기전자재료학회 1996 電氣電子材料學會誌 Vol.9 No.9
Undoped p-type and Te doped n-type GaSb crystals were grown by the vertical Bridgman method. The lattice constant of the GaSb crystals was 6.096.+-.000373.angs.. The carrier concentration, the resistivity, and the carrier mobility measured by the van der Pauw method were p.iden.8*10$^{16}$ c $m^{-3}$ , .rho..iden.0.20 .ohm.-cm, .mu.$_{p}$ .iden.400c $m^{2}$ $V^{-1}$ se $c^{-1}$ for p-type, n.iden.1*10$^{17}$ c $m^{-3}$ , .rho..iden.0.15 .ohm.-cm, .mu.$_{n}$ .iden.500c $m^{2}$ $V^{-1}$ se $c^{-1}$ for n-type at 300K. In case of treatment with metal ion of R $u^{+3}$, P $t^{+4}$, the carrier concentration, resistivity and carrier mobility of the GaSb crystals were p.iden.2*10$^{17}$ c $m^{-3}$ , .rho..iden.0.08.ohm.-cm, .mu.$_{p}$ .iden.420c $m^{2}$ $V^{-1}$ se $c^{-1}$ for p-type, n.iden.2.5*10$^{17}$ c $m^{-3}$ , .rho..iden.0.07.ohm.-cm, .mu.$_{n}$ .iden.520c $m^{2}$ $V^{-1}$ se $c^{-1}$ for n-type respectively. GaSb crystals had a tendency to lower resistivity and higher mobility, for surface treatment with metal ion effectively diminished surface recombination centers.s.
이은상,오장섭 한국세라믹학회 1984 한국세라믹학회지 Vol.21 No.2
The Effect of Dditives $ZrO_2$ and $TiO_2$ on the enstatite body the composition of which was MgO.$SiO_2$ has been closely investigated on the physical properties and microstructure. $ZrO_2$ and $TiO_2$ as additives were added by weight 5, 10, 15, 20, 25% and 1, 2, 2.5, 5, 10, 20% respectively to the mixture (MgO : SiO2=1:1) and fired at the temperature ranging from 130$0^{\circ}C$ to 145$0^{\circ}C$ and 1275$^{\circ}C$ to 1375$^{\circ}C$. Increasing the add ition or $ZrO_2$ to 20% the physical property became better. In case of $TiO_2$ the sample containing 20% $TiO_2$ had a best effect on the enstastite body. The optimum firing range proved to 14$25^{\circ}C$ for $ZrO_2$ and 1325~135$0^{\circ}C$ for $TiO_2$. The effect of $ZrO_2$ and $TiO_2$ addition on the thermal expansion was observed not ot be remarkable.
카메라-IMU 센서 융합 기반 자세 추정을 통한 전방 객체 거리 정밀 보정
이동현,김종광,오장섭,이성우,류춘우,김학일 제어·로봇·시스템학회 2022 제어·로봇·시스템학회 논문지 Vol.28 No.12
This paper presents a novel method to correct with only the camera and IMU sensors an estimated distance error due to a rapid change in a vehicle’s posture while driving, as it is very important to estimate the distance of a front car in autonomous driving. To estimate the change in vehicle’s posture, the proposed method adopts a visual odometry method using the optical flow and the camera-IMU fusion. The error in the estimated distance caused by an instantaneous change in the vehicle's posture is reduced by compensating the ground surface according to the pitch angle acquired by the estimated vehicle’s posture. In real-road experiments with a real vehicle, the proposed method demonstrates its practical usability by reducing the average ranging error from 35% to 3%. .