| 摘要: | 隨著經濟快速成長，人民所得提高，生活品質提昇，人口增加，機動車輛數量亦隨之快速成長。車輛增多，再加上開車時的各種環境、道路、及人為等因素，而使得交通事故之件數及其所造成之死傷人數也相對增加。因此若能有一些協助駕駛人偵測道路狀況、行車狀況、及駕駛狀況等機制，提供各種道路相關資訊給駕駛人，並提醒駕駛人，對社會大眾而言，勢必多了一層安全保障。本研究的目的即是結合電腦視覺、影像處理、與圖形識別等技術，考慮各國環境之需求，發展與世界同步之視覺偵測技術，給予駕駛者提醒、警示、及預防等機制，降低駕駛者工作負荷，減低人為失誤，進而預防交通事故發生，提升行車安全性。從 2001 年起，我們就一直在從事先進安全車輛之視覺偵測技術的研究。藉由多樣性的電腦視覺偵測技術，偵測駕駛環境及個人狀況，提供警示功能，以提高行車安全。本研究即建立在過去的基礎及成果上，繼續針對各種可能的交通安全性及駕駛方便性，發展更新的或更穩定的電腦視覺輔助道路安全駕駛技術；讓技術得以實現出來，創造利潤，造福人群。本計畫之電腦視覺系統涵蓋了四個研究主題：(1) 前後車防撞偵測、(2) 側邊盲點偵測、(3) 停車輔助、及 (4) 駕駛昏睡狀態偵測。 (1) 前後車防撞偵測的研究項目有：LDW/FCW 在平面道路之實現與改進、LDW/FCW 的嵌入式系統化、使用粒子濾波 (particle filter) 做前後車偵測與追蹤、?眼立體視覺偵測技術發展、900 奈米紅外線雷射掃描雷達偵測技術發展、影像與雷達資料融合。 (2) 側邊盲點偵測的研究項目有：盲點位置的物體偵測及距離估計、24 GHz 微波雷達或40 KHz 超音波雷達單點偵測技術發展、影像與雷達資料融合、側邊立體視覺測距、車上PTZ 相機之車牌定位與辨識。 (3) 停車輔助的研究項目有：車體環場鳥瞰監視系統、車輛前進後退之軌跡分析、結合環場鳥瞰監視與軌跡分析的停車輔助。 (4) 駕駛昏睡狀態偵測的研究項目有：臉部/眼睛偵測與分析、昏睡與注意力分析、結合眼睛閉合及偏離車道資訊的昏睡判定。四個研究主題將同時執行。每個研究主題中的工作項目都將依序在三年中完成。雖然研究項目很多，但目前實驗室有5 位博士生及 6 位碩士生正在從事上述題目的研究；所以請審查委員多多支持多位學生的相關研究。上述相關於安全偵測的研究重點在於準確性與穩定性。視覺安全偵測很容易受到天候及環境因素的影響；所以技術研發的關鍵在於方法是否不受天候狀況 (晴、陰、雨、霧、暗) 的影響；是否在各式道路環境 (高速、快速、平面道路、巷弄、鄉間小道) 都可維持良好的偵測效果。考慮各種天候及環境因素對於視覺偵測的影響是我們技術發展上的特色之一。計畫主持人已有二十多年電腦視覺的研究經歷，且已有六年多電腦視覺技術應用在車輛安全駕駛上的經驗，並且獨自獲得電腦視覺輔助道路安全駕駛之2004年美國及2006年中華民國發明專利，其部份成果具備高度實用性，已被中科院、永彰機電、及華夏科技選用於發展前車防撞警示 (forward collision warning, FCW) 及偏離車道警示 (lane departure warning, LDW) 系統中；因此我們有能力完成本計畫的執行。 In these few decades, the vehicle number is rapidly increasing because people’s incomes are increasing. In addition to the vehicle number, more factors of road situation, driving environment, and human attention result in a large amount of traffic accidents and casualties. If there is a mechanism to help the driver to detect the road situation and driving environment, and then to provide some useful information to the driver in these situations, the danger is therefore avoided. In this research project, we are just combining the techniques of computer vision, image processing, and pattern recognition, and matching the domestic environment to develop state-of-the-art techniques of vision detection to reduce the load of drivers, to reduce the traffic accidents, and then improve the driving safety. From 2001, we have studied the vision detection techniques for the advanced safety vehicle. Based on the versatile computer vision techniques, we proposed methods to detect the situations of driving environment and personal conditions and provide warning to improve the safety of driving. Based on our previous basis and the results, this research project aims various driving conditions to develop new-function and more practical techniques to aid driving. There are four studying topics of computer vision in this research project: (1) forward and rear collision detection and warning, (2) detection in side and blind spots, (3) parking assistance, and (4) driver drowsiness detection and warning. (1) forward and rear collision detection and warning system consists of the research topics: LDW/FCW implemented in the general roads, LDW/FCW implemented with an embedded system, preceding and read vehicle detection and tracking using particle filters, binocular stereo vision detection technique, 900 nm infrared laser radar detection technique, image and radar data fusion. (2) detection in blind spots and lateral view consists of the research topics: target detection and distance estimation in blind spot and lateral location, 24 GHz microwave or 40 KHz ultrasonic single-point detection technique, image and single-point radar data fusion, stereo vision detection in the lateral view, PTZ camera for license plate detection and recognition. (3) parking assistance system consists of the research topics: surround-view surveillance system, trajectory analysis of parking vehicle, parking assistance system by combining surround-view surveillance and trajectory analysis. (4) driver drowsiness detection and warning system consists of the research topics: face and eye detection and analysis, drowsiness and vigilance analysis, drowsiness analysis and discrimination by combining PERCLOS and lane departure information. These four topics will be executed simultaneously. The studying items in each research topic will be sequentially completed in the following three years. The proposed system seemingly include too many items; but there are 5 ph.D students and 6 master students studying the related topics; thus the number studying items is not problem; please all reviewers support our studying with more students. The key problems of the safety detection techniques are accuracy and stability. The methods concerning the safety vehicles are easily influenced by climate conditions and environment factors; thus the key points of useful methods are whether the proposed methods are not influenced by various climate conditions (sunny, cloudy, rainy, foggy, and night days) ? whether the proposed methods may keep well performance in variant road conditions (freeway, highway, general road, and country roads). Considering the influence factors of climate conditions and environment situations to the vision detection techniques is one characteristic of our development of the computer vision techniques for advanced safety vehicles. The principal investigator of this project is an original researcher on computer vision, he has studied computer vision techniques more than twenty years; moreover, he has the application experience of computer vision aided road vehicle driving for safety more than six years. In the advanced safety vehicle, he has also gotten the US patents and Taiwan patents in 2004 and 2006, respectively. Partial techniques of the system are practiced and have been employed by the Chung-shan Institute of Science & Technology, Taiwan Calsonic Co., and AsiaTek Co. to develop their forward collision warning (FCW) and lane departure warning (LDW) systems; thus we have ability to complete the execution of the research project. 研究期間：9908 ~ 10007 |
