• Journal of Biosystems Engineering
• /
• 제23권5호
• /
• pp.481-490
• /
• 1998

A computer vision system to measure low flow rate of solid particles was developed and tested to examine its performance with various sized 7 kinds of seeds, perilla, mung bean, paddy, small red bean, black soybean, Cuba bean and small potato tuber. The test was performed for two types of particle flow, continuous and discontinuous. For the continuous flow tested with perilla, mung bean and paddy, the tests resulted correlation coefficients for the flow rates measured by the computer vision and direct method about 0.98. Average errors of the computer vision measurement were in a range of 6∼9%. For the discontinuous flow tested with small red bean, black soybean, Cuba bean and small potato tuber, the tests resulted correlation coefficients for the flow rates measured by the computer vision and direct method 0.98∼0.99. Average errors of the computer vision measurement were in a range of 5∼10%. Performance of the computer vision system was compared with that of the conventional optical sensor to count particles in discontinuous flow. The comparison was done with black soybean, Cuba bean and small potato tuber, and resulted that the computer vision has much better performance than the optical sensor in a sense of precision of the measurement.

• 한국정보기술응용학회:학술대회논문집
• /
• 한국정보기술응용학회 2005년도 6th 2005 International Conference on Computers, Communications and System
• /
• pp.285-288
• /
• 2005

We propose a novel programmable miniature vision module based on a custom designed analog VLSI (aVLSI) chip. The vision module consists of the optical flow vision sensor embedded with commercial off-the-shelves digital hardware; in our case is the Intel XScale PXA270 processor enforced with a programmable gate array device. The aVLSI sensor provides gray-scale imager data as well as smooth optical flow estimates, thus each pixel gives a triplet of information that can be continuously read out as three independent images. The particular computational architecture of the custom designed sensor, which is fully parallel and also analog, allows for efficient real-time estimations of the smooth optical flow. The Intel XScale PXA270 controls the sensor read-out and furthermore allows, together with the programmable gate array, for additional higher level processing of the intensity image and optical flow data. It also provides the necessary standard interface such that the module can be easily programmed and integrated into different vision systems, or even form a complete stand-alone vision system itself. The low power consumption, small size and flexible interface of the proposed vision module suggests that it could be particularly well suited as a vision system in an autonomous robotics platform and especially well suited for educational projects in the robotic sciences.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.56-59
• /
• 1997

Vision system is mainly consist of three parts of perception, action. One of these parts, perception system detects visual target in surrounding environment. Block-based motion estimation with compensation is one of the popular approaches without accuracy. The hierarchical method the optical flow with gradient is used to improve optical flow time delay.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.881-884
• /
• 2000

Foveated vision has the big advantage of exhibiting a wide field of view, along with a high resolution fovea. However, in the case of using optical flow, foveated vision kas one demerit. The demerit is a concentrate of optical flow. For foveated vision, an object moves almost only around the center of the field. In this paper, we suggest how to segment motion of some objects, and how to discriminate a hand and another object. In the future, the method we suggested may be useful for recognizing human actions by foveated vision.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권2호
• /
• pp.133-139
• /
• 2013

This paper proposes a vision-based indoor localization method for autonomous vehicles. A single upward-facing digital camera was mounted on an autonomous vehicle and used as a vision sensor to identify artificial landmarks and any natural corner features. An interest point detector was used to find the natural features. Using an optical flow detection algorithm, information related to the direction and vehicle translation was defined. This information was used to track the vehicle movements. Random noise related to uneven light disrupted the calculation of the vehicle translation. Thus, to estimate the vehicle translation, a Kalman filter was used to calculate the vehicle position. These algorithms were tested on a vehicle in a real environment. The image processing method could recognize the landmarks precisely, while the Kalman filter algorithm could estimate the vehicle's position accurately. The experimental results confirmed that the proposed approaches can be implemented in practical situations.

• 한국항공우주학회지
• /
• 제37권3호
• /
• pp.267-274
• /
• 2009

최근 무인 항공기(Unmanned Aerial Vehicle, UAV)는 다양한 임무수행이 가능한 무인 시스템이라는 점에서 크게 주목받고 있다. 특히 정찰, 추적 등의 임무는 영상을 이용하여 임무 수행이 이루어진다. 소형 무인 항공기의 경우 중량과 비용을 고려하여 단안 영상을 이용하는 임무 수행 연구가 활발하게 이루어지고 있다. 그러나 실제 지표면과 목표물이 고도 차이를 가지고 있어, 영상의 상대깊이를 고려하지 않은 3차원 거리는 임무 수행 시 오차 요인으로 작용 할 수 있다. 본 연구에서는 상대 깊이 추정을 위한 평균이동 알고리즘, 광류, 부분 공간법에 관하여 차례로 제시한다. 평균이동 알고리즘은 영상 내 목표물 추적과 관심영역을 결정하며 광류는 영상의 자기를 이용한 영상 이동 정보를 포함한다. 마지막으로 부분 공간법은 영상안의 움직임을 추정하며 각 영역의 상대깊이를 결정한다.

• 설비공학논문집
• /
• 제15권4호
• /
• pp.268-273
• /
• 2003

In the present study, the characteristics of upward bubble flow were experimentally investigated in a liquid bath. An electro-conductivity probe was used to measure local volume fraction and bubble frequency. Since the gas is concentrated at the near nozzle, the flow parameters are high near the nozzle. In general their axial and radial values tended to decrease with increasing distance. For visualization of flow characteristics, a Particle Image Velocimetry (P.I..V) and a thermo-vision camera were used in the present study. The experimental results show that heat transfer from bubble surface to water is largely completed within z=10mm from the nozzle, and then the temperature of bubble surface reaches that of water rapidly. Due to the centrifugal force, the flow was more developed near the wall than at bubble-water plume. Vortex flow in the bottom region was relatively weaker than that in the upper region.

• International Journal of Air-Conditioning and Refrigeration
• /
• 제13권1호
• /
• pp.44-50
• /
• 2005

In the present study, the characteristics of upward bubble flow were experimentally investigated in a liquid bath. An electro-conductivity probe was used to measure local volume fraction and bubble frequency. Since the gas was concentrated at the near the nozzle, the flow parameters were high near the nozzle. In general their axial and radial values tended to decrease with increasing distance. For visualization of flow characteristics, a Particle Image Velocimetry (PIV) and a thermo-vision camera were used in the present study. The experimental results showed that heat transfer from bubble surface to water was largely completed within z = 10 mm from the nozzle, and then the temperature of bubble surface reached that of water rapidly. Due to the centrifugal force, the flow was more developed near the wall than at bubble-water plume. Vortex flow in the bottom region was relatively weaker than that in the upper region.

• 한국통신학회논문지
• /
• 제11권1호
• /
• pp.1-15
• /
• 1986

Optic flow는 이동물체표면의 3차원 속도를 영상판(image plane)에 투영시킨 2차원 속도이다. 본 논문은 이 동물체의 연속영상으로부터 optic flow 를 구하는 기술들을 조사분석하고 정해진 optic flow로부터 물체의 인식 및 3차원 속도를 결정하는 기술들을 논하였다. 연속영상으로부터 구해진 optic flow는 영상압축기술인 영상간 부호(inter-frame image coding)에 해당되며 컴퓨터비젼 시스템(computer vision system)에서 이동물체 인식에 사용된다.

• 한국ITS학회 논문지
• /
• 제21권2호
• /
• pp.17-32
• /
• 2022

본 연구에서는 개별 차량의 차두 시간(time headway) 정보를 활용하여 고속도로 환경에서의 단일 링크에 대한 교통류 모형(flow-density diagram)을 추정하는 방법에 대해 탐구한다. 차두 시간 기반 교통류 모형(empirical flow-density diagram) 연구를 위해 차량용 비전 센서가 탑재된 실험 차량에서 9개월동안 수집된 데이터의 전처리 및 GIS 기반 맵 매칭을 수행한다. 기존의 교통류 모델식을 활용한 차두 시간 기반 교통류 모형(empirical flow-density diagram)의 검증을 위해, 차량 검지기 기반의 VDS(Vehicle Detection System) 데이터(loop detection traffic data) 기반 교통류 모형과 결과 비교 및 분석을 수행한다. 차두 시간 기반 교통류 모형의 추정 오차 원인을 분석하기 위해 각 교통류 모형의 차두 시간 및 차두 거리의 확률분포와 단위시간 교통량과 차량 밀도의 표준편차를 활용하였다. 분석 결과 링크 내 제한된 샘플 차량 대수 및 수집 데이터에 대한 주행환경 편향성이 추정 오차의 주된 요인이며. 이에 따른 추정 오차 개선을 위한 방법에 대해 제안한다.