Vehicle Detection Algorithm for Applications Pertaining to License Plate Recognition

The technology of license plate recognition (LPR) is widely applied to parking lot management systems, intelligent transportation systems, and electronic toll collections. The goal of LPR is to identify license plates quickly and accurately. Therefore, many researchers have proposed methods for achieving this goal. This paper proposes an algorithm that uses information regarding the location of the vehicle to trigger the camera to capture an image of the vehicle. This not only achieves the goal of detecting an image in real time, but also obtains the best image with the license plate as a triggering image. The proposed algorithm does not require additional hardware, and facilitates the precise retrieval of an image that both contains a vehicle and represents the best image from a series of images for recognizing the characters on license plates. This significantly reduces the cost of hardware and is much easier and cheaper to maintain than the traditional detection methods. Experimental results show that the detection success rate of the proposed algorithm reached 92% during the daytime and nighttime. Despite diverse weather conditions, moreover, the detection success rate of the proposed algorithm reached 91%. An extensive vehicle-detection test demonstrates that the proposed algorithm is reliable and accurate.

關鍵字

license plate recognition ； image trigger ； moving vehicle

並列摘要

車牌辨識系統廣泛應用於停車場管理系統、智能運輸系統及電子收費系統。因此，許多學者提出不同的方法想要達到此目的。一般而言，目前並沒有針對擷取車輛車牌的的最佳位置影像，提供給車牌辨識系統做進一步辨識的研究，本文即針對此問題提出一個利用攝影機擷取車輛車牌的最佳位置的演算法。本系統不僅滿足即時偵測的目標，且可在連續影像中獲得一張具有最佳車輛車牌的觸發影像，並且無需額外架設特別的硬體裝置，本演算法提出精確擷取具有最佳車輛車牌的觸發影像，並提供給車牌辨識系統進行車牌辨識。與傳統的偵測方法相比，可大量省下硬體的成本及維護費用。實驗結果顯示，本演算法在白天及夜間的觸發成功率可達92%以上；在不同天候下的觸發成功率可達91%以上。藉由一週的長時間測試，實驗結果顯示本演算法是穩定且傑出的演算法。

並列關鍵字

車牌辨識；觸發影像；移動車輛

主題瀏覽