基於行車紀錄器之路不平偵測與辨識系統

Abstract

由於汽車的數量大增，行車安全議題在近幾年備受重視，加速了駕駛安全輔助系統的發展，駕駛安全輔助系統也常利用一些周邊裝置作為輔助，例如智慧型手機、GPS導航、行車紀錄器…等。在用路安全方面，路不平的議題在近幾年備受關注，不僅容易造成汽車的受損，也會影響行車的安全，尤其在夜間或是視線不清的情況下。近幾年台灣政府投入數百億預算給路平專案，但路面修復依賴用路人的回報，成效仍然不彰，各地仍時常傳出因路不平造成的交通事故。因此，路不平自動偵測系統實為刻不容緩之研究主題。 本論文提出了基於行車紀錄器之路不平偵測與辨識系統。一開始，我們偵測車輛有沒有行經路不平的區域，如果有，我們就去分析路不平附近畫面，看是什麼原因造成路不平。接著，路不平的成因與GPS位置便會回報至中央次伺服器，因此，當其他車輛接近路不平區域時，便會收到警告訊息。除此之外，此資訊也可以提供給相關單位做路面修補的參考。

Advanced vehicle safety is a recently emerging issue, appealed from the rapidly explosive population of cars. Increasing driver assistance systems have been designed for warning drivers of what should be noticed by analyzing surrounding environments with sensors and/or cameras. As one of the hazard road conditions, road bumps not only damage vehicles but also cause serious danger, especially at night or under poor lighting conditions. In this thesis we propose a vision-based road bump detection system using a front-mounted car camcorder, which tends to be widespread deployed. First, we estimate the vehicle motion through input video and infer the existence of road bumps. Once a bump is detected, objects at the vicinities of the detected bumps are then recognized. Consequently, the information of this bump is then extracted. The location obtained from GPS and information is reported to a central server, so that other vehicles can receive warnings when approaching the detected bumpy regions. Encouraging experimental results show that the proposed system can detect road bumps efficiently and effectively. It can be expected that traffic security will be significantly promoted through the mutually beneficial mechanism that a driver who is willing to report the bumps he/she encounters can receive warnings issued from others as well.