應用於智慧型手機之夜間行車輔助系統研究

A Study of Automobile Driver’s Assisting System at Night-Time using Smart Phones

江杰穎(Jie-Ying Jiang)

指導教授 ： 張元翔

中原大學/工學院/資訊工程研究所/碩士(2012年)

https://doi.org/10.6840/cycu201200672

摘要

由於智慧型手機技術的最新進展，在日常生活各方面均有應用軟體被開發以協助使用者。在這許多應用中，行車輔助系統的技術無論是在學術界和產業界，都引起許多研究人員的關注，部分是因為智慧型手機所帶來的便利性。本研究旨在開發『應用於智慧型手機之夜間行車輔助系統』，其目的是協助高速公路駕駛人，並在必要時警示駕駛人。本系統是以視覺方式為基礎，包括：(1) 車道偵測；(2) 車輛偵測；(3) 警示系統。研究方法主要是克服夜間車道和車輛偵測之挑戰性問題。在正常駕駛的情況下，本系統設計是用來標記車道及車輛區域，以作為駕駛人的參考資訊。此外，本系統可以提供兩個特定的警示訊息，即『車道偏離』和『與前車距離太近』。使用一組視訊資料庫，本研究呈現初步結果並進行評估，在實際駕駛場景中，系統可提供正向的成果。總結而言，本系統具有潛力成為行車輔助工具，以確保行車安全。

關鍵字

車道偵測 ； 車輛偵測 ； 智慧型手機

並列摘要

Because of recent advance of smart phone technology, application software has been developed to assist users in various aspects for daily life. Among these many applications, techniques for automobile driver’s assisting systems have drawn attention to many researchers both in academy and in industry, partly because of convenience of smart phones for daily use. This study is aimed to develop an “Automobile driver’s assisting system at night-time using smart phones” with the objective to assist drivers during highway driving and warn drivers when necessary. Our system is vision-based and includes: (1) Lane Detection, (2) Vehicle Detection, and (3) Warning System. The methods are focused to overcome challenge of detecting traffic lanes and vehicles at night-time. During normal driving situation, our system is designed to mark the lane and vehicle regions for driver’s reference. In addition, our system can yield two particular warning messages, namely “Lane Departure” and “Front Car Too Close”. Our preliminary results are demonstrated and evaluated using a video database, which provide promising results in real driving scenarios. In summary, this system can be potentially used as a tool to assure the driving safety.

並列關鍵字

automobile driver’s assisting system ； vehicle detection ； smart phones ； lane detection

參考文獻

[2] M. Bertozzi and A. Broggi, “GOLD: A Parallel Real-Time Stereo Vision System for Generic Obstacle and Lane Detection,” IEEE Trans. on Image Processing, vol. 7, no. 1, pp. 62-81, Jan. 1998.

[3] K. Kluge and S. Lakshmanan, “A Deformable-Template Approach to Lane Detection,” Proc. IEEE Intelligent Vehicles ’95 Symp., pp. 54-59, Sep. 1995

[6] N. Otsu, “A Threshold Selection Method from Gray-Level Histogram,” IEEE Trans. Systems, Man and Cybernetics, vol.SMC-9, no. 1, pp. 62-66, 1979.

[8] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 3rd Edition, Prentice Hall, New York, 2007.

[1] Smartphones to Account for Majority of Cellphone Shipments by 2015,http://www.isuppli.com/Mobile-and-Wireless-Communications/News/Pages/Smartphones-to-Account-for-Majority-of-Cellphone-Shipments-by2015.aspx