Responsive image

 首頁 |   Language  : English


永續教育學院 > 職安消防進修學士學位學程 > 期刊論文 >

題名:Study of Moving Obstacle Detection at Railway Crossing by Machine Vision
作者:Yong-Ren Pu, Li-Wei Chen, Su-Hsing Lee
期刊名稱:Information Technology Journal
發表頁數:pp. 2611-2618
摘要:This study is designed to develop an advanced safety system which is able to detect the existence of moving obstacles at a railway crossing. In a miniature railway crossing scaled 1:22.5, we installed a grayscale CCD camera and developed the graphical user interface to process the images of the crossing. To achieve the goal, the software was programmed to perform several image processing techniques such as image subtraction, binarization, morphological transformation and segmentation to track down the moving obstacles. Furthermore, portions of the monitored image around the rails were labeled as the alert and alarm zones where the obstacles would trigger sirens of this system. Under various illuminant conditions in the indoor environment, the experiments on the developed system detecting the model cars with different colors demonstrated that the level of illuminance was a significant factor on the average alert accuracy rate, but the color of cars was not. Above all, the average alert accuracy rate reached 97.8%. Due to the promising results to recognize the obstacles that might pose threats, this system is worth further development on site to provide effective protection for the railway crossings.
英文關鍵字:CCD, Railway crossing, Obstacle detection, Machine vision
Vol:Vol. 13
NO:No. 16