http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Propose Real-time Human motion analysis method by Extracting characteristic point from silhouette
Jeisung Lee,Minkyu Cheon,Mignon Park 대한전자공학회 2010 ICEIC:International Conference on Electronics, Inf Vol.1 No.1
Human motion recognition in the environment that many people are there has recently gained growing interest from computer vision researchers. Visual interpretation of gestures is very useful for accomplishing the human-robot interaction (HRI) and for building surveillance system. This paper proposes a method for analyzing human motion in the video stream. Moving object is detected in the video and silhouette of the target object is extracted from the background. Five characteristic points is extracted from the silhouette. Those points are cues for the body motion. Continuous sequence of the points can be used to recognize human motion. Unlike the prior other models, this does not need a lot of pixels on object. Furthermore, it is computationally inexpensive. So, it is suitable to simultaneously recognize many people motion in the real world video applications such as outdoor video surveillance.
Development of Efficient Emergency Stop Algorithm for Manipulator
Chang-Soon Kang,Jeisung Lee,Minkyu Cheon,Mignon Park 대한전자공학회 2010 ICEIC:International Conference on Electronics, Inf Vol.1 No.1
This paper proposes an efficient emergency stop algorithm for manipulator using distance measuring sensors. A large manipulator can inflict a severe injury on humans by links of the manipulator. In order to prevent collision, emergency stop algorithm which can predict a collision with obstacles is necessary. We propose an emergency stop algorithm which considers moving direction of the manipulator and classifies the parts of manipulator and other obstacles for efficient operation of manipulator.
Vision Sensor-Based Driving Algorithm for Indoor Automatic Guided Vehicles
Quan Nguyen Van,Hyuk-Min Eum,Jeisung Lee,Chang-Ho Hyun 한국지능시스템학회 2013 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.13 No.2
In this paper, we describe a vision sensor-based driving algorithm for indoor automatic guided vehicles (AGVs) that facilitates a path tracking task using two mono cameras for navigation. One camera is mounted on vehicle to observe the environment and to detect markers in front of the vehicle. The other camera is attached so the view is perpendicular to the floor, which compensates for the distance between the wheels and markers. The angle and distance from the center of the two wheels to the center of marker are also obtained using these two cameras. We propose five movement patterns for AGVs to guarantee smooth performance during path tracking: starting, moving straight, pre-turning, left/right turning, and stopping. This driving algorithm based on two vision sensors gives greater flexibility to AGVs, including easy layout change, autonomy, and even economy. The algorithm was validated in an experiment using a two-wheeled mobile robot.