• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 춘계학술대회 논문집
• /
• pp.169-172
• /
• 2002

A vision sensor measure range data using laser light source. This sensor generally use patterned laser which shaped single line. But this vision sensor cannot satisfy new trend which feeds foster and more precise processing. The sensor's sampling rate increases as reduced image processing time. However, the sampling rate can not over 30fps, because a camera has mechanical sampling limit. If we use multi line laser pattern, we will measure multi range data in one image. In the case of using same sampling rate camera, number of 2D range data profile in one second is directly proportional to laser line's number. For example, the vision sensor using 5 laser lines can sample 150 profiles per second in best condition.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.584-587
• /
• 2002

A vision sensor measure range data using laser light source. This sensor generally use patterned laser which shaped single line. But this vision sensor cannot satisfy new trend which needs laster and more precise processing. The sensor's sampling rate increases as reduced image processing time. However, the sampling rate can not over 30fps, because a camera has mechanical sampling limit. If we use multi line laser pattern, we will measure multi range data in one image. In the case of using same sampling rate camera, number of 2D range data profile in one second is directly proportional to laser line's number. For example, the vision sensor using 5 laser lines can sample 150 profiles per second in best condition.

• 한국멀티미디어학회논문지
• /
• 제17권9호
• /
• pp.1041-1051
• /
• 2014

In this paper, we propose a new image alignment technique based on CUDA SURF in order to solve the initial image alignment problem that frequently occurs in machine vision applications. Machine vision systems using multi-spectral images have recently become more common for solving various decision problems that cannot be performed by the human vision system. These machine vision systems mostly use markers for the initial image alignment. However, there are some applications where the markers cannot be used and the alignment techniques have to be changed whenever their markers are changed. In order to solve these problems, we propose a new image alignment method for multi-spectral machine vision applications based on SURF extracting image features without depending on markers. In this paper, we propose an image alignment method that obtains a sufficient number of feature points from multi-spectral images using SURF and removes outlier iteratively based on a least squares method. We further propose an effective preliminary scheme for removing mismatched feature point pairs that may affect the overall performance of the alignment. In addition, we reduce the execution time by implementing the proposed method using CUDA based on GPGPU in order to guarantee real-time operation. Simulation results show that the proposed method is able to align images effectively in applications where markers cannot be used.

• 한국인터넷방송통신학회논문지
• /
• 제12권6호
• /
• pp.141-146
• /
• 2012

본 논문에서는 영상 기반 자동 착륙 시스템 개발과 이 시스템을 사용하는 멀티로터 플랫폼 개발에 대해서 소개 한다. 멀티로터 플랫폼은 뉴턴 오일러 개념을 근간으로 하는 강체 운동 모델링을 하였고, LQR 제어 기법을 통한 제어기 튜닝 및 시뮬레이션을 하였다. 영상기반 자동 착륙 시스템은 멀터로터 시스템에 탑재된 단일 카메라를 사용하여 추가적인 임무장비 없이 증강 현실 알고리즘을 사용하여 마커를 탐지하고 정밀한 착륙을 유도하도록 GCS와 연동 코드를 구현 하였다.

• Journal of Welding and Joining
• /
• 제25권2호
• /
• pp.49-54
• /
• 2007

Since the wall thickness can be up to 6" or greater, welds must be made in many layers, each layer containing several passes. However, the welding time for the conventional welding processes such as SAW(Submerged Arc Welding) and FCAW(Flux Cored Arc Welding) can be required many hours. The aim of this paper is to develop a high speed welding system with multi-torch and laser vision sensor for increasing the production speed on the line and to remove the need for the operator so that the system can run automatically for the complete multi-torch multi-layer weld. It was shown that the developed laser vision sensor and analysis of arc blow for multi-torch were effective for multi-pass seam tracking and stable arc. A new automated multi-torch welding systems for thick wall applications has been proved in several production lines.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.555-555
• /
• 2000

This study is concentrated on the development of hight speed multi-object image processing algorithm, and based on these a1gorithm, vision control scheme is developed for the robot's position control in real time. Recently, the use of vision system is rapidly increasing in robot's position centre. To apply vision system in robot's position control, it is necessary to transform the physical coordinate of object into the image information acquired by CCD camera, which is called image processing. Thus, to control the robot's point position in real time, we have to know the center point of object in image plane. Particularly, in case of rigid body, the center points of multi-object must be calculated in a image plane at the same time. To solve these problems, the algorithm of multi-object for rigid body control is developed.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.227-241
• /
• 2021

Object detection techniques based on deep learning such as YOLO have high detection performance and precision in a single channel video stream. In order to expand to multiple channel object detection in real-time, however, high-performance hardware is required. In this paper, we propose a novel back-end server framework, a real-time AI vision platform (RAVIP), which can extend the object detection function from single channel to simultaneous multi-channels, which can work well even in low-end server hardware. RAVIP assembles appropriate component modules from the RODEM (real-time object detection module) Base to create per-channel instances for each channel, enabling efficient parallelization of object detection instances on limited hardware resources through continuous monitoring with respect to resource utilization. Through practical experiments, RAVIP shows that it is possible to optimize CPU, GPU, and memory utilization while performing object detection service in a multi-channel situation. In addition, it has been proven that RAVIP can provide object detection services with 25 FPS for all 16 channels at the same time.

• 대한교통학회지
• /
• 제8권2호
• /
• pp.7-25
• /
• 1990

In road traffic, road circumstances, vehicle, and driver are closely related each other. When road facilities are established in road planning, only road structure has been considered. However, relatively little work has been done regarding the relation between road circumstances and human with respect to a driver. This dissertation focuses on analysis of driver's visual characteristics to improve road circumstances. In this study, driver's visual characteristics are measured with eye-mark recorder and analyzed statistically. This study includes that visual characteristics, visual range, visual time, distribution of fixation duration, and visual moving angle with respect to road circumstances are established qualitatively and quantitatively by driving testing vehicle on streets, roads and high-ways. The main features of this study are : The driver's visual ranges are different over 10% depending on lane in multi-lanes. The visual range on two-lanes is more than twice as big as that on multi-lanes at 85% of whole vision. The right and left visual ranges by as big as that on multi-lanes at 85% of whole vision. The right and left visual ranges by as big as that on multi-lanes at 85% of whole vision. The right and left visual ranges by as big as that on multi-lanes at 85% of whole vision. The right and left visual ranges by speed are $34^{\circ}$ for 30-50km/hr, $28^{\circ}$ for 50-70km/hr, $22^{\circ}$ for 70-90km/hr and 16^{\circ} for over 90km/hr at 95% of visual rate. Accordingly, increasing speed results in narrow visual range.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2002년도 춘계학술발표대회 개요집
• /
• pp.49-52
• /
• 2002

A vision sensor measure range data using laser light source, This sensor generally use patterned laser which shaped single line. But this vision sensor cannot satisfy new trend which needs faster and more precise processing. The sensor's sampling rate increases as reduced image processing time. However, the sampling rate can not over 30fps, because a camera has mechanical sampling limit. If we use multi line laser pattern, we will measure multi range data in one image. In the case of using same sampling rate camera, number of 2D range data profile in one second is directly proportional to laser line's number. For example, the vision sensor using 5 laser lines can sample 150 profiles per second in best condition.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.339-342
• /
• 2002

The feature points in the uncalibrated stereo vision should represent all the characteristics of an image in multiple resolution, have high precision, and have the robustness against mismatching. This paper proposed an algorithm which detects the corner points in multi-resolution for stereo computer vision. The algorithm has sub-pixel precision, rejects the mismatched points, and corrects the lens distortion. We show the performance of the algorithm by estimating the homography with it.