請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/62344
標題: | 智慧型手機平台上基於闖紅燈預測之車輛碰撞預防系統 RedEye: Preventing Collisions Caused by Red-Light Running Scooters with Smartphones |
作者: | Kuang-Shih Huang 黃光世 |
指導教授: | 蔡欣穆(Hsin-Mu Tsai) |
關鍵字: | 機器學習,智慧型手機,闖紅燈預測,車輛行為, Machine Learning,Smartphone,Red-light runner,vehicular behavior, |
出版年 : | 2013 |
學位: | 碩士 |
摘要: | 本論文提出一個以智慧型手機作為平台、基於闖紅燈辨識的機車防撞系統。當偵測到闖紅燈行為即將發生時,一方面會對機車騎士本身發出警告,另一方面同時警告其他方向車輛闖紅燈行為即將發生。藉以降低因闖紅燈造成的交通事故。針對此問題,我們不使用利用雷達或攝影機等設備的基礎建設解決方案。主要原因為,除了實施成本高,此類方法也只能夠避免有裝設此裝置的路口所發生的交通事故。我們提出一個建立在智慧型手機的機車解決方案。智慧型手機提供了一個相當有效的平台,較高的市場佔有率,足夠的運算能力,具備各種通用的感應器,足以反映駕駛行為,並發送或接收來自其他車輛的信息的通信能力。
在此系統中,我們採用支持向量機(SVM)為基礎,設計了一套針對闖紅燈行為分類及預測的機器學習演算法。驗證結果顯示,此演算法可以提供超過70%的識別率。相比之下,使用成本高上許多的基礎設施,如使用激光測距儀(LADAR)的機制,則約可達到80%的辨識率。本論文提出的方法雖然在辨識準確度上略差,但智慧型手機平台的眾多優勢仍提供一個更實際可行的解決方案。 In this thesis, we present a scooter collision avoidance system which can identify red-light runners (RLR) at intersections. When the RLR behavior is detected, the system would advise the RLR to slow down immediately and warn nearby vehicles on the intersecting road in real time. In particular, we do not consider infrastructure-based solutions such as those utilizing a radar or a camera. This is because that, in addition to high implementation costs, collisions can only be avoided at intersections where such infrastructure configurations are deployed. Instead, we advance an on-scooter solution using smartphones carried by scooter riders. Smartphones provide a useful platform that has a high penetration rate, more than sufficient computational power, inertial sensors to reflect the driving behavior, and the communication capability to transmit or receive information from other vehicles. In our system, we utilize support vector machine (SVM) and design a set of RLR classifiers for learning and predicting RLR behaviors. The evaluation results show that our system is able to achieve over 70% recognition rates when distinguishing between RLR and None-RLR (NRLR) cases, compared to approximately 80% accuracies of the infrastructure-based (and higher-cost) solution using a laser range finder (LADAR). |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/62344 |
全文授權: | 有償授權 |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-102-1.pdf 目前未授權公開取用 | 4.77 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。