具備多工排程功能之無線嵌入式腦機介面系統及其在即時汽車駕駛員疲勞狀態偵測與提醒之應用

Abstract

近年來，有許多高速公路車禍發生的原因是由於駕駛者精神狀態不佳所造成；而在精神狀態不佳或是疲勞時，腦電位會產生一些特徵訊號，因此可以利用這些生理特徵訊號進行其精神狀態之估測。以往的生理訊號監控系統大多只做到訊號記錄部分，再藉由電腦進行後續離線處理，而缺乏即時分析的功能，因此，本論文提出一套具備即時分析能力的腦機介面系統以改善以往生理訊號監控系統的缺點，並實際應用於汽車駕駛員疲勞狀態偵測與提醒。我們以雙核心處理器，搭配無線傳輸模組、生理訊號放大器，來實現一套即時無線腦機介面系統，包含三大發展主軸，分別為「無線傳輸與腦電位訊號量測」、「嵌入式多工排程」及應用於「即時汽車駕駛員疲勞狀態偵測與提醒」並即時運作於嵌入式系統上。首先，我們開發一套嵌入式多工排程系統與雙核心處理系統來增加系統於接收資料以及訊號處理的即時處理效能，並利用可切換式無線訊號傳輸系統來克服系統接線以及傳輸距離的問題。接著提出一即時的駕駛員疲勞狀態偵測的演算法，最 後整合提醒訊號回饋以喚醒精神狀態不佳的駕駛員。實際線上測試顯示，本論文所提出的系統在即時處理效能以及疲勞狀態偵測的準確度上，都有非常好的效果。

Recently, many traffic accidents on the highway are caused by the drivers’ drowsiness. If the driver is drowsy, there are some features in EEG signals. We can use these features to estimate the driver’s drowsiness. But the past bio-signal monitor system usually can only record the signals and is unable of real-time signal processing. We propose the Brain Computer Interface (BCI) system in this thesis, which can process bio-signal real-time, and we apply it to detect the driver’s drowsiness and warn the driver when the driver’s drowsiness occurs. The goal of this thesis is to build up a real-time wireless Brain Computer Interface, which include wireless transmission and bio-signal measurement, an embedded multi-task scheduling system, and its application on real-time driver’s drowsiness detection and warning. We propose the embedded multi-task scheduling system and the dual-core processing system to improve the ability of real-time processing, including receiving data and processing data, and use a selectable wireless transmission system to overcome the problems of routing and transmission distance. Finally, we propose a real-time driver’s drowsiness detection algorithm and integrate the warning signal to warn the drowsiness driver. The practical online test shows that the system we propose is effective with the ability of real-time processing and drowsiness detection.