http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A High Speed Vision Algorithms for Axial Motion Sensor
Mousset, Stephane .,Miche, Pierre .,Bensrhair, Abdelaziz .,Lee, Sang Goog 한국센서학회 1998 센서학회지 Vol.7 No.6
In this paper, we present a robust and fast method that enables real-time computing of axial motion component of different points of a scene from a stereo images sequence. The aim of our method is to establish axial motion maps by computing a range of disparity maps. We propose a solution in two steps. In the first step we estimate motion with a low evel computing for an image point by a detection estimation-structure. In the second step, we use t,te neighbourhood information of the image point with morphology operation. The motion maps are established with a constant computation time without spatio-temporal matching.
Real time stereo vision system for axial motion detection
BENSRHAIR, A,MOUSSET, S.,MICHÉ,Lee, Sang-Goog 경북대학교 센서기술연구소 1998 센서技術學術大會論文集 Vol.9 No.1
In this paper, we present a new real time axial motion system which is based on a new stereo vision system. The first step of the stereo process uses a mono-dimensional operator called declivity, then a dynamic programming method is used to match declivities and finally a 3-D map is achieved. Then, a detection estimation-structure is used to compute motion with a low level computing for an image point. Finally, we use the neighbourhood information of the image point with morphology operation in order to compute motion maps. These maps are established with a constant computation time without spatio-temporal matching. Experimental results obtained on real images are presented.