• Title/Summary/Keyword: 무인계산대

Search Result 17, Processing Time 0.031 seconds

Implementation of An Unmanned Counter based on YOLO Deep Learning Object Recognition (YOLO 기반 딥러닝 객체 인식 무인계산대 개발에 관한 연구)

  • Park, Tae-Baek
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2022.11a
    • /
    • pp.776-778
    • /
    • 2022
  • 우리는 일상 속에서 다양한 결제시스템을 접할 수 있다. 그중 무인계산 시스템은 소비자가 구매부터 결제까지 스스로 하는 방식이다. 발전된 기술이 편리함을 제공하지만, 일부 소비자들은 오히려 사용에 어려움을 겪고 사람이 계산을 해주는 기존의 시스템을 선호하는 경우가 많다. 본 논문에서는 소형 IOT 기기와 딥러닝 객체 인식 시스템을 기반으로 한 무인계산대를 설계하고 개발하였다. 계산대의 모습을 구현하기 위해 아두이노 컨베이어 벨트를 이용하고 라즈베리 파이와 파이 카메라를 이용하여 객체 인식 환경을 구현하였다. 파이 카메라를 통해 영상을 인식하고 해당 영상을 실시간으로 전송하여 PC에서 YOLO를 통해 객체를 탐지한다. 이후 탐지된 객체는 소비자가 확인할 수 있도록 디스플레이에 시각화한다. 본 논문에서 제안한 딥러닝 객체 인식 무인계산 시스템은 공산품이 주를 이루는 무인 상점에 활용할 수 있다.

A study on the User Experience at Unmanned Checkout Counter Using Big Data Analysis (빅데이터 분석을 통한 무인계산대 사용자 경험에 관한 연구)

  • Kim, Ae-sook;Jung, Sun-mi;Ryu, Gi-hwan;Kim, Hee-young
    • The Journal of the Convergence on Culture Technology
    • /
    • v.8 no.2
    • /
    • pp.343-348
    • /
    • 2022
  • This study aims to analyze the user experience of unmanned checkout counters perceived by consumers using SNS big data. For this study, blogs, news, intellectuals, cafes, intellectuals (tips), and web documents were analyzed on Naver and Daum, and 'unmanned checkpoints' were used as keywords for data search. The data analysis period was selected as two years from January 1, 2020 to December 31, 2021. For data collection and analysis, frequency and matrix data were extracted through Textom, and network analysis and visualization analysis were conducted using the NetDraw function of the UCINET 6 program. As a result, the perception of the checkout counter was clustered into accessibility, usability, continuous use intention, and others according to the definition of consumers' experience factors. From a supplier's point of view, if unmanned checkpoints spread indiscriminately to solve the problem of raising the minimum wage and shortening working hours, a bigger employment problem will arise from a social point of view. In addition, institutionalization is needed to supply easy and convenient unmanned checkout counters for the elderly and younger generations, children, and foreigners who are not familiar with unmanned calculation.

For Reasonable Smart Cart (합리적 소비를 위한 스마트 카트)

  • Choi, Kwon Woo;Noh, Ji-Hun;Son, Hyun-Uk;Kim, Min-Su
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2021.11a
    • /
    • pp.1124-1127
    • /
    • 2021
  • 대형마트 혹은 일반 마트에서 물건을 구매할 때 지금까지 얼마치의 물건을 담았는지 소비자들은 알기 어렵다. 그리고 여러 사람들이 많은 물건을 한 번에 구매하기 때문에 계산대에서 길게 늘어진 줄을 보고 최대한 사람이 적은 곳을 찾은 경험은 다들 있을 것이다. 그러한 점에서 최근 조금씩 늘어나는 무인 계산대에서 아이디어를 얻어 쇼핑을 할 때 끌고 다니는 카트에서 계산과정을 처리해 계산시간을 줄이고자 했다. 그러하여 카트에서 물건을 인식할 수 있어야 하며 인식한 물건의 가격 및 정보 등을 저장하고 있어야한다. 그래서 카트에 바코드를 인식할 수 있는 리더기와 가격정보를 보여 주는 스크린을 설치하였으며 계산대에 가서 저장했던 정보를 한 번에 처리기위해 QR 코드를 사용하였다. 스크린에 QR 코드를 띄우고 계산대에서 QR 코드를 찍으면 가격정보를 알 수 있고 그 자리에서 계산까지 가능하며 원하는 소비자는 본인의 휴대폰에 설치된 가계부에서도 QR 코드를 찍어서 구매한 물건들의 가격과 자세한 구매목록을 쉽게 저장할 수 있다. 기존 가계부에서는 구매목록을 하나하나 적어야 하기 때문에 귀찮을 수 있지만 이러한 방법을 통하면 기존방식보다 훨씬 편리할 것이라 생각했다.

Collision-free Flight Planning for Cooperation of Multiple Unmanned Aerial Vehicles (다중 무인 항공기의 협동 작업을 위한 무 충돌 비행 계획)

  • Park, Jae-Byung
    • Journal of the Institute of Electronics Engineers of Korea SC
    • /
    • v.49 no.2
    • /
    • pp.63-70
    • /
    • 2012
  • The collision-free flight planning method based on the extended collision map is proposed for cooperation of multiple unmanned aerial vehicles (UAVs) in a common 3-dimensional workspace. First, a UAV is modeled as a sphere, taking its 3-D motions such as rolling into consideration. We assume that after entering the common workspace, the UAVs move along their straight paths until they depart from the workspace, and that the priorities of the UAVs are determined in advance. According to the assumptions, the collision detection problem between two spheres in $R^3$ can be reduced into the collision detection problem between a circle and a line in $R^2$. For convenience' sake and safety, the collision regions are approximated by collision boxes. Using the collision boxes, the entrance times of the UAVs are scheduled for collision avoidance among the UAVs. By this way, all UAVs can move in the common workspace without collisions with one another. For verifying the effectiveness of the proposed flight planning method, the simulation with 12 UAVs is carried out.

Development of Intelligent Auto-Parking Algorithm (지능형 자동주차 알고리즘 개발)

  • Cho, Kyoung-Hwan;Chung, Jin-Wok;Ahn, Dong-Jun
    • Proceedings of the KAIS Fall Conference
    • /
    • 2011.05a
    • /
    • pp.29-34
    • /
    • 2011
  • 비접촉 거리측정 장치인 레이저스캐너를 이용하여 무인차량의 평행주차 및 직각주차 알고리즘 개발을 목적으로 하였다. 이 알고리즘을 검증하기 위하여 GPS와 차량에 6대의 레이저스캐너를 장착하여 이용하였고, 레이저스캐너를 이용한 위치 계산의 오차를 줄이기 위해 타이어 미끄러짐을 최소로 할 수 있도록 5km/h로 차량의 이동 속도를 제한하였다.

  • PDF

A study on improving LSAST ambiguity resolution for CDGPS (CDGPS를 위한 LSAST 미지정수 추정기법 개선에 관한 연구)

  • Lee, Gi-Hun
    • Journal of the Korean Society for Aeronautical & Space Sciences
    • /
    • v.34 no.5
    • /
    • pp.74-80
    • /
    • 2006
  • GPS, which has been opened to the public since the 1980's, uses the C/A code time of arrival to estimate the position, and measures the carrier doppler frequency to estimate the velocity. In development from the 1990's, DGPS has improved position accuracy by eliminating common errors and CDGPS has achieved cm-level position accuracy using carrier phase. In this paper, a modified LSAST ambiguity resolution method for CDGPS is proposed to improve reliability and computational efficiency. Also the test results of cm level relative positioning of a moving vehicle using single frequency GPS receivers are compared to INS position. This research result can be widely used for the development of high precision INS, unmanned autonomous driving, survey and mapping, etc.

Development of Auto-Parking Algorithm for Driving in Urban (무인차량의 자동주차 알고리즘 개발)

  • Cho, Kyoung-Hwan;Chung, Jin-Wok
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.12 no.5
    • /
    • pp.2360-2366
    • /
    • 2011
  • The Unmanned Ground Vehicle is comprised of four systems of obstacle detection: The navigation system, vehicle controlling system, obstacle detecting and an integration system that use the various sensors. The research introduced utilizes 6 lasers to recognize obstacles. The system operates an avoidance system within the unmanned ground vehicle, using six lasers. The Unmanned Ground Vehicle's parallel parking and right angle parking is in development using algorithms. This algorithms' certification is intended to be installed in the encoder, in the GPS. By using the Laser Scannerfor the position's calculation, errors are both reduced and minimized, so the tire's slip minimized to the point where the vehicle had a limit of about 5Km/h.

Autonomous Formation Flight Tests of Multiple UAVs (다수 무인항공기의 자동 편대비행 시험)

  • Song, Yong-Kyu;Heo, Chang-Hwan;Lee, Sang-Jun;Kim, Jung-Han
    • Journal of the Korean Society for Aeronautical & Space Sciences
    • /
    • v.38 no.3
    • /
    • pp.264-273
    • /
    • 2010
  • In this work, autonomous formation flight tests of multiple UAVs are experimentally studied. After a guidance and control system for a UAV is designed and tested, PID formation controller for follower UAV is tested using longitudinal and lateral distance feedback. It is shown that more stable and efficient formation guidance system is obtained by using position and attitude of the leader aircraft, which is exploited to calculate virtual waypoint for follower. In order to improve transient response during turn, part of roll command of the leader is added to the guidance command. Finally, autonomous formation flight test results of 3 UAVs are shown by using the best guidance algorithm suggested.

Routing of ALVs under Uncertainty in Automated Container Terminals (컨테이너 터미널의 불확실한 환경 하에서의 ALV 주행 계획 수립방안)

  • Kim, Jeongmin;Lee, Donggyun;Ryu, Kwang Ryel
    • Journal of Navigation and Port Research
    • /
    • v.38 no.5
    • /
    • pp.493-501
    • /
    • 2014
  • An automated lifting vehicle(ALV) used in an automated container terminal is a type of unmanned vehicle that can self-lift a container as well as self-transport it to a destination. To operate a fleet of ALVs efficiently, one needs to be able to determine a minimum-time route to a given destination whenever an ALV is to start its transport job. To find a route free from any collision or deadlock, the occupation time of the ALV on each segment of the route should be carefully scheduled to avoid any such hazard. However, it is not easy because not only the travel times of ALVs are uncertain due to traffic condition but also the operation times of cranes en route are not predicted precisely. In this paper, we propose a routing method based on an ant colony optimization algorithm that takes into account these uncertainties. The result of simulation experiment shows that the proposed method can effectively find good routes under uncertainty.

Agricultural Climatology of Cheju Island II. Potential Evapotranspiration Based on Near-Real Time Data Measured by Automated Weather Stations (제주도의 농업기후 분석 II. 무인관측강에 의한 기상실황자료 수집 및 증발산위 계산)

  • 윤진일
    • KOREAN JOURNAL OF CROP SCIENCE
    • /
    • v.35 no.6
    • /
    • pp.504-511
    • /
    • 1990
  • Weather data acquisition and potential evapotranspiration (PET) calculation procedure were investigated to support the agricultural development efforts in the mid-altitude mountainous region of Cheju Island. Automated weather stations (AWS) were installed at two points representing the east and the west of the study area. A personal computer was employed to collect the near-real time weather data from AWS through the public telephone line. Hourly data were available for solar radiation, air and soil temperature, relative humidity, wind speed and direction, and precipitation. Based on the data for the month of June 1989, daily climatic features were comparatively analyzed for the two areas and the Penman equation was used to calculate PET. Air temperature was higher by 1 to 2 degree C in the east due mainly to the higher solar radiation and partly to the Fohn effect caused by the daytime southwesterly blowing over Mt. Halla. Diurnal march of soil temperature lagged by 4 hours behind that of air temperature and the diurnal range for 10cm subsurface soil was 3 degree C. Wind was consistently stronger and a marked sea-land breeze circulation was detected in the west. Calculated PET values were higher in the east by 6% than in the west. Overall values from the east and the west of the mid-altitude mountainous region were higher by 30% than those of the coastal region, which were estimated from the Class A Pan evaporation measured by the Korea Meteorological Service Offices.

  • PDF