車輛先進駕駛輔助系統之簡易自適應巡航控制與紅綠燈號誌辨識實作

在各品牌汽車系統中，近年來為發展智慧車輛以及無人自駕車，先進駕駛輔助系統(Advanced Driver Assistance Systems；ADAS)乃達到真正無人自動駕駛之過程中所需要的技術之一。本論文利用個人電腦為上位控制器，試圖透過已訓練好之深度學習模型，透過影像偵測技術，找到紅綠燈及車輛在影像中的位置資訊，以完成無人駕駛時之自動辨識與偵測。依據前車距離遠近做為控制目標，以串列傳輸的方式利用PD控制器控制改裝電動車的油門、方向與剎車，而達到簡易自適應巡航控制。論文中以電腦視覺與影像處理開源函式庫(Open Source Computer Vision Library；OpenCV)進行影像處理與分析，完成紅綠燈之號誌辨識。結果顯示以單一鏡頭完成辨識道路紅綠燈號誌及自適應巡航控制的可行性，以及在未來開發應用上的可拓展性。

關鍵字

巡航控制系統；號誌辨識；先進駕駛輔助系統

並列摘要

In various brands of automotive systems, in recent years, in order to develop smart vehicles and self-driving cars, Advanced Driver Assistance Systems (ADAS) is one of the technologies required in the process of truly Self-Driving . This thesis uses a personal computer as a host controller to try to find the location information of traffic lights and vehicles in the image through the well-trained deep learning model to complete the automatic identification and detection of Self-Driving.According to the distance of the front vehicle as the control target, the PD controller is used to control the throttle, direction and brake of the modified electric vehicle in a serial transmission mode to achieve simple adaptive cruise control.In this paper, the Open Source Computer Vision Library (OpenCV) is used for image processing and analysis to complete the identification of traffic lights. The results show the feasibility of identifying road traffic lights and adaptive cruise control with a single lens, and the scalability of future development and application.

並列關鍵字

cruise control system ； identification ； ADAS

參考文獻

[1] 岩子庭，2016，以影像為基礎之日間前車偵測與車距估算，元智大學電機工程學系碩士論文。

Google Scholar

[2] 莫又寧，2017，以混合式特徵偵測前方車尾並使用卷積神經網路辨識車型，元智大學電機工程學系碩士論文。

Google Scholar

[3] 林奇叡，2008，先進安全車輛的前方與盲點視覺偵測，中央大學資訊工程學系碩士論文。

Google Scholar

[4] 鄭弼倫，2011，高速公路前車陰影結合車輪之偵測，中正大學電機工程學系學位論文。

Google Scholar

[5] Zehang Sun ,G. Bebis ,R. Miller “Monocular precrash vehicle detection: features and classifiers.” IEEE Transactions on Image Processing, Vol.15, Issue: 7, July 2006 2019-2034

Google Scholar

主題瀏覽