【摘要】：車輛跟蹤廣泛用于軍事及交通系統(tǒng)。車輛跟蹤的關(guān)鍵在于能實(shí)時(shí)準(zhǔn)確地跟蹤。在有部分遮擋,車輛突然改變軌跡,光照變化的影響下,都能保證跟蹤的準(zhǔn)確性。本文主要討論基于車牌識(shí)別的車輛跟蹤和有部分遮擋的車輛跟蹤。在跟蹤車輛時(shí),車牌具有唯一性,能快速確定車輛的身份。若被跟蹤車輛的車牌被遮擋,此時(shí)跟蹤車牌的方法失效。用特征點(diǎn)匹配方法跟蹤目標(biāo)車輛。為了滿足實(shí)時(shí)跟蹤的需要,提出改進(jìn)的ORB(Oriented FAST and Rotated BRIEF)算法跟蹤目標(biāo)車輛,實(shí)驗(yàn)表明在有部分遮擋時(shí)能實(shí)時(shí)準(zhǔn)確地跟蹤目標(biāo)車輛�；谲嚺谱R(shí)別的車輛跟蹤首先識(shí)別目標(biāo)車輛的車牌。對(duì)采集的圖像去噪,然后灰度化,再對(duì)其邊緣檢測(cè)。形態(tài)學(xué)結(jié)合邊緣檢測(cè)初步確定連通域,再根據(jù)車牌的固有特征精確定位車牌區(qū)域。定位到車牌后,對(duì)其二值化,然后用垂直投影法結(jié)合車牌的先驗(yàn)知識(shí)對(duì)其分割,將車牌分割成單個(gè)字符。對(duì)得到的字符用基于輪廓的模板匹配法將其識(shí)別出來(lái)。用卡爾曼濾波跟蹤車牌從而跟蹤目標(biāo)車輛。在跟蹤車牌的過程中,車牌面積較小,容易被其它車輛遮擋。此時(shí),車輛龐大的外形特征可以幫助我們跟蹤車輛,然而跟蹤車輛時(shí),目標(biāo)車輛也易被其它車輛遮擋。為了解決部分遮擋情況下車輛實(shí)時(shí)跟蹤不丟失的問題,提出了基于特征點(diǎn)匹配的改進(jìn)的ORB算法。其具有平移,旋轉(zhuǎn),縮放不變性。改進(jìn)的ORB算法在FAST檢測(cè)特征點(diǎn)后用拉普拉斯極值去除虛假角點(diǎn),相比ORB算法提高了匹配的正確率,也提高了檢測(cè)速度。其中改進(jìn)的FAST檢測(cè)特征點(diǎn)速度快,BRIEF(Binary Robust Independent Elementary Features)描述子縮短了建立描述符的時(shí)間,且減少了存儲(chǔ)空間。由此提高了特征點(diǎn)匹配的速度,滿足實(shí)時(shí)跟蹤的需要。實(shí)驗(yàn)表明,在有光照變化和噪聲干擾的情況下,改進(jìn)的ORB算法依然能夠快速準(zhǔn)確地跟蹤有部分遮擋的車輛。
[Abstract]:Vehicle tracking is widely used in military and transportation systems. The key of vehicle tracking is to track the vehicle accurately and in real time. Under the influence of partial occlusion, sudden change of vehicle trajectory and light change, the tracking accuracy can be guaranteed. This paper mainly discusses vehicle tracking based on license plate recognition and vehicle tracking with partial occlusion. When tracking the vehicle, the license plate is unique and can quickly determine the identity of the vehicle. If the license plate of the tracked vehicle is blocked, the method of tracking the vehicle license plate is invalid. The feature point matching method is used to track the target vehicle. In order to meet the need of real-time tracking, an improved ORB (Oriented FAST and Rotated BRIEF) algorithm is proposed to track the target vehicles. The experimental results show that the target vehicles can be tracked in real time and accurately when there is partial occlusion. Vehicle tracking based on license plate recognition first recognizes the vehicle license plate of the target vehicle. The image is de-noised, then grayscale, and then the edge is detected. The connected region is preliminarily determined by morphology combined with edge detection, and then the license plate area is accurately located according to the inherent characteristics of the license plate. After locating the license plate, the license plate is binary, then the license plate is segmented into a single character by the vertical projection method combined with the prior knowledge of the license plate. The resulting characters are recognized by contour-based template matching. The target vehicle is tracked by Kalman filter. In the process of tracking the license plate, the license plate area is small, easy to be blocked by other vehicles. At this point, the huge shape of the vehicle can help us track the vehicle, but when tracking the vehicle, the target vehicle is easily blocked by other vehicles. An improved ORB algorithm based on feature point matching is proposed to solve the problem of vehicle real-time tracking without losing in partial occlusion. It has translation, rotation, zoom invariance. The improved ORB algorithm uses Laplace extremum to remove false corner points after FAST detection. Compared with ORB algorithm, it improves the accuracy of matching and the speed of detection. The improved FAST detection feature point fast, BRIEF (Binary Robust Independent Elementary Features) descriptor shortens the time of establishing descriptor and reduces the storage space. Therefore, the speed of feature point matching is improved and the need of real-time tracking is satisfied. The experimental results show that the improved ORB algorithm can track partially occluded vehicles quickly and accurately in the presence of illumination changes and noise interference.
【學(xué)位授予單位】：遼寧科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：U495

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張曉媚;陳偉海;劉敬猛;趙志文;;基于柔性曲桿的車輛跟蹤算法設(shè)計(jì)與實(shí)現(xiàn)[J];北京航空航天大學(xué)學(xué)報(bào);2011年07期

2 郭鋒;王秉政;楊晨暉;;復(fù)雜背景下車輛跟蹤的改進(jìn)算法及逆行檢測(cè)[J];圖學(xué)學(xué)報(bào);2013年04期

3 劉青;張曉暉;陳建新;侯云;;基于先驗(yàn)知識(shí)的高速公路逃費(fèi)車輛跟蹤算法研究[J];公路工程;2013年04期

4 楊敏;裴明濤;王永杰;董震;武玉偉;;一種基于運(yùn)動(dòng)目標(biāo)檢測(cè)的視覺車輛跟蹤方法[J];北京理工大學(xué)學(xué)報(bào);2014年04期

5 黃福獻(xiàn);車輛跟蹤管理系統(tǒng)簡(jiǎn)介[J];汽車運(yùn)用;2001年06期

6 曹智英;;基于學(xué)習(xí)機(jī)制的時(shí)空車輛跟蹤與索引框架[J];現(xiàn)代計(jì)算機(jī);2007年05期

7 朱華林;;基于高清視頻檢測(cè)和高清圖片識(shí)別的車輛跟蹤系統(tǒng)設(shè)計(jì)[J];交通世界(運(yùn)輸.車輛);2011年07期

8 曾智洪;高速公路中的行車道檢測(cè)和車輛跟蹤(英文)[J];自動(dòng)化學(xué)報(bào);2003年03期

9 周志宇,汪亞明,曹麗;基于模糊聚類和α-β-γ濾波的車輛跟蹤[J];浙江工業(yè)大學(xué)學(xué)報(bào);2004年01期

10 陳繼紅;;基于3G技術(shù)的車輛跟蹤服務(wù)系統(tǒng)的研究[J];物探裝備;2008年03期

相關(guān)會(huì)議論文 前3條

1 楊華;鄒月嫻;劉志剛;時(shí)廣軼;關(guān)佩;王一言;;基于視頻的復(fù)雜交通場(chǎng)景車輛跟蹤技術(shù)研究[A];第六屆全國(guó)信息獲取與處理學(xué)術(shù)會(huì)議論文集（1）[C];2008年

2 孫燎原;石川;張楊;;基于GoogleMaps的車輛跟蹤態(tài)勢(shì)顯示系統(tǒng)研究與實(shí)現(xiàn)[A];第十六屆全國(guó)青年通信學(xué)術(shù)會(huì)議論文集（上）[C];2011年

3 張暉;董育寧;夏洋;;一種基于改進(jìn)的GVF-Snake模型的車輛跟蹤算法[A];第十三屆全國(guó)圖象圖形學(xué)學(xué)術(shù)會(huì)議論文集[C];2006年

相關(guān)重要報(bào)紙文章 前4條

1 神州通信有限公司GIS部 廖志杰;構(gòu)建中國(guó)空間信息服務(wù)網(wǎng)絡(luò)平臺(tái)系統(tǒng)(六)[N];通信產(chǎn)業(yè)報(bào);2004年

2 中國(guó)全球定位系統(tǒng)技術(shù)應(yīng)用協(xié)會(huì)GPS信息咨詢服務(wù)部 曹沖;GPS上車[N];計(jì)算機(jī)世界;2002年

3 本報(bào)記者 楊濱;打牢百年精品客專的基石[N];人民鐵道;2010年

4 龐偉燕;用科技編織安全網(wǎng)[N];中國(guó)郵政報(bào);2011年

相關(guān)博士學(xué)位論文 前3條

1 吳剛;基于粒子濾波與增量學(xué)習(xí)的車輛跟蹤方法研究[D];南京理工大學(xué);2014年

2 徐旭;復(fù)雜環(huán)境下的車輛目標(biāo)跟蹤技術(shù)研究[D];吉林大學(xué);2013年

3 王軍偉;ITS中運(yùn)動(dòng)車輛自動(dòng)跟蹤方法的研究[D];中國(guó)農(nóng)業(yè)大學(xué);2003年

，

本文編號(hào)：2309013