整合夜間車燈與車道偵測與事件記錄功能之嵌入式駕駛輔助系統

Integrating the Night Lights and Lane Detection and Recording Event Functions into the Embedded Driver Assistance Systems

林敬竣(Ching-Chun Lin)

指導教授 ： 陳彥霖

國立臺北科技大學/電資學院/資訊工程系研究所/碩士(2011年)

https://doi.org/10.6841/NTUT.2011.00451

摘要

本論文之目的在於發展一套以電腦視覺技術為基礎的嵌入式夜間駕駛安全輔助與監控系統，藉由架設於汽車擋風玻璃後之視訊擷取裝置，即時獲取前方路況以及車輛影像，並且以一系列電腦視覺技術加以分析處理，以提供對於夜間行車輔助所需的車輛偵測、辨識、前方路況分析與判斷、事件偵測與即時行車影像記錄等各項技術模組，並整合實現於一套異質雙核心(ARM+DSP)之嵌入式系統平台上。在實作上，首先會整合車輛偵測系統與車道偵測系統，然後會依照DSP的特性為這兩個系統進行一定程度的優化。接著加入行車事件偵測與分類模組、行車影像壓縮與記錄模組，最後整合並實現於一套嵌入式系統平台上，實現一套應用電腦視覺技術的嵌入式夜間駕駛輔助與監控系統。

關鍵字

電腦視覺技術 ； 異質雙核心 ； 嵌入式系統

並列摘要

The study presents an embedded night driver assistance and monitor system based on computer vision technology. A CCD camera is set up in the windshield of the vehicle to get the real-time traffic situation and return it to the embedded system. When the embedded system receives the image from the CCD camera, it exploits a series of computer vision technology to analyze the video for the vehicle detection, the traffic situation analysis, and the real-time driving video recording. The computer vision technology is integrated and implemented on the heterogeneous dual-core embedded platform. For optimizing the algorithm, the vehicle detection and the land detection module are integrated on the embedded platform by DSP properties. The embedded platform also includes the driving event judgment, video compression, and the record module. Finally, all the modules are integrated in an embedded system to implement a embedded night driver assistance and monitor system.

並列關鍵字

computer vision technology ； heterogeneous dual-core ； embedded system

參考文獻

[1] D. Pomerleau, “RALPH: Rapidly adapting lateral position handling,” in Proc. IEEE Intelligent Vehicle Symp., pp. 506–511, 1995.

[2] D. Langer and T. Jochem, “Fusing Radar and Vision for Detecting, Classifying and Avoiding Roadway Obstacles,” in Proc. IEEE Intelligent Vehicle Symp., pp. 333 - 338, 1996.

[3] M. Bertozzi, A. Broggi, and A. Fascioli, “Vision-based intelligent vehicles: State of the art and perspectives,” Robot. Automat. Syst., vol. 32, pp. 1–16, 2000.

[6] C. J. Taylor, J. Malik, and J. Weber , "A Real-Time Approach to Stereopsis and Lane-Finding", in Proc. 1996 IEEE Intelligent Vehicles Symposium, pp. 207–213, 1996.

[7] P. McLauchlan, and J. Malik , "Vision for longitudinal vehicle control", in Proc. 1997 IEEE Intelligent Transportation Systems, pp. 918-923, 1997.