適用於智慧型運輸系統之昏睡偵測

Abstract

在避免意外的技術領域中，預防駕駛者昏睡的發展技術，是智慧型運輸系統所面對最主要的挑戰。我們必須精確的偵測出駕駛者是否昏睡，以防止低警覺駕駛的發生。本文是利用影像處理技術，處理與分析數位攝影機所拍攝的駕駛者臉部影像，根據駕駛者眼睛睜開的情況，我們判斷出駕駛者的昏睡程度及其警覺性是否下降。本文利用對駕駛者眼睛睜閉狀況的兩種證據跡象，即一段時間內之眼睛閉合比例及眨眼頻率，對駕駛者是否昏睡做出判定之標準。本文利用模糊積分(fuzzy integral)的概念，發展出上述兩種證據跡象資訊整合的技術，以增加偵測的可靠度。本偵測系統提出非接觸式之駕駛者是否昏睡的判定技術，以期及早偵測昏睡而對駕駛提出警訊，確保安全駕駛。

The development of technologies for preventing drowsiness at the wheel is a major challenge in the field of accident avoidance systems. Preventing drowsiness during driving requires a method for accurately detecting a decline in driver alertness. In this thesis, we have developed a system that uses image processing technology to analyze images of the driver’s face taken with a digital video recorder. Diminished alertness is detected on the basis of the degree to which the driver’s eyes are open or closed. Our proposed system is capable of integrating two different evidence sources, PERCLOS and blink rate, into a knowledgeable decision, to determine a driver is drowsy or not. The evidence fusion technique, based on the notion of fuzzy integral is presented. The detection system provides a noncontact technique for determining various levels of driver alertness and facilitates an early detection and providing the warning of a decline in alertness to achieve a save driving.