文章基本信息

标题：A HYBRID FUZZY MORPHOLOGY AND CONNECTED COMPONENTS LABELING METHODS FOR VEHICLE DETECTION AND COUNTING SYSTEM
本地全文：下载
作者：Chastine Fatichah ; Joko Lianto Buliali ; Ahmad Saikhu 等
期刊名称：International Journal on Smart Sensing and Intelligent Systems
印刷版ISSN：1178-5608
出版年度：2016
卷号：9
期号：2
页码：765-779
出版社：Massey University
摘要：A hybrid fuzzy morphology and connected components labeling method is proposed for detectingand counting the number of vehicles in an image taken from a traffic monitoring camera. A fuzzymorphology approach in image segmentation method is used in the system to achieve faster computationtime compared to the supervised learning. The connected components labeling method is combined with afuzzy morphology method to determine the region and number of objects in an image. The processingphases in the proposed system are image preprocessing, image segmentation, and vehicle detection andcounting the number of vehicles. Images are captured from the traffic monitoring cameras installed inhighways. Results from testing phase using thirty images with varying brightness, contrast, and qualitytaken from different cameras during daylight showed that the accuracy of the system in counting thenumber of vehicles is 78.21%.
关键词：connected component labeling; fuzzy morphology; image segmentation; vehicle detection