Automatic Urban Road Segmentation

Abstract

自動都市馬路區塊擷取於電腦視覺影像處理的應用上是非常重要的，舉例而言，交通流量偵測、交通監控、以及事件偵測等都需要這項技術為基礎。自動都市馬路區塊擷取可以提供影像中有效的路面區域，避免物件偵測程式浪費不需要的運算於非路面區域，並且可以減少錯誤偵測的發生。本論文中所提出自動都市馬路區塊擷取方法使用了模糊與陰影集（fuzzy-shadowed sets）的方法來自動判斷路面的區域。本論文所提出的方法包括以下四個主要步驟：背景自動產生、前景物的偵測、背景黏貼法、路面定位。由實驗的結果中顯示，本論文所提出的方法在許多實際路面影像處理應用上都有良好的結果。

Automatic road segmentation is important for many vision-based traffic applications, such as traffic surveillance, traffic flow measurement, and incident detection. Road segmentation provides useful information for precluding from further consideration the objects and activities appearing outside road areas. The proposed method, using fuzzy-shadowed set operations, consists of four major steps: background image generation, foreground object extraction, background pasting, and road localization. The experimental results reveal that the proposed method can effectively detect road areas under different environmental conditions.