【摘要】：車輛是城市道路交通最重要的組成部分,因此開展車輛視頻檢測器的研究對城市智能交通系統(tǒng)的發(fā)展具有重要的意義。隨著智能交通系統(tǒng)對產(chǎn)品小型化、低功耗、低成本且穩(wěn)定可靠的需求日益強(qiáng)烈,開展嵌入式車輛視頻檢測器的研究更具有了重要的現(xiàn)實(shí)意義和應(yīng)用價(jià)值。本論文基于TI公司的數(shù)字信號處理器(DSP)TMS320DM642平臺,對嵌入式車輛視頻檢測算法進(jìn)行了研究,設(shè)計(jì)與實(shí)現(xiàn)了嵌入式的視頻車輛檢測器。論文的主要內(nèi)容和研究成果包括： 1.嵌入式算法設(shè)計(jì)：本文在虛擬線圈算法框架下,引入速度、方差和均值等計(jì)算簡單的統(tǒng)計(jì)量,提出了基于虛擬線圈統(tǒng)計(jì)量的快速視頻車輛檢測算法。該算法首先基于塊匹配原理計(jì)算虛擬線圈速度統(tǒng)計(jì)量,然后采用高階統(tǒng)計(jì)量分塊法來進(jìn)行背景建模并得到前景圖像的均值和方差統(tǒng)計(jì)量,最后通過統(tǒng)計(jì)量的邏輯運(yùn)算來判斷車輛到達(dá)、經(jīng)過、離開、駐停等狀態(tài)。該算法在滿足實(shí)時(shí)性要求的前提下,對于光照、陰影等外界條件的干擾有較強(qiáng)的魯棒性,適合在嵌入式平臺上運(yùn)行。實(shí)驗(yàn)結(jié)果表明,該算法在PC機(jī)上可以達(dá)到50幀/秒的檢測速度,同時(shí)在理想條件下白天的檢測率可以達(dá)到98%以上,夜間的檢測率達(dá)到93%,在白天車輛密集且有陰影時(shí)檢測率達(dá)到94%,滿足實(shí)際使用需求。 2.程序?qū)崿F(xiàn)與優(yōu)化：本文以基于虛擬線圈統(tǒng)計(jì)量的車輛檢測算法為軟件核心,在DM642平臺上實(shí)現(xiàn)了嵌入式視頻車輛檢測器。通過使用內(nèi)聯(lián)函數(shù)、展開循環(huán)、重排軟件流水、利用乒乓機(jī)制傳輸數(shù)據(jù)等多種手段對程序進(jìn)行了優(yōu)化。實(shí)際道路的測試結(jié)果表明,本文研制的嵌入式車輛檢測器能夠達(dá)到20幀/秒的檢測速度,達(dá)到了實(shí)時(shí)檢測,同時(shí)車輛檢測率白天可以達(dá)到96%,夜晚達(dá)到90%,誤檢率白天不高于2%,漏檢率白天為4%,誤檢率夜晚不高于4%,漏檢率夜晚為10%。 測試結(jié)果表明,本文研制的基于DM642的視頻車輛檢測器能夠?qū)囕v進(jìn)行實(shí)時(shí)的檢測,同時(shí)也保證了檢測的準(zhǔn)確性,在檢測速度和檢測率兩者之間的平衡性上表現(xiàn)出色,為以后嵌入式視頻車輛檢測器的研制與應(yīng)用奠定了一定的基礎(chǔ)。
[Abstract]:Vehicle is the most important part of urban road traffic, so the research of vehicle video detector is of great significance to the development of urban intelligent transportation system. With the increasing demand of intelligent transportation system for miniaturization, low power consumption, low cost, stability and reliability, the research of embedded vehicle video detector has important practical significance and application value. In this paper, based on the digital signal processor (DSP) TMS320DM642 platform of TI Company, the embedded vehicle video detection algorithm is studied, and the embedded video vehicle detector is designed and implemented. The main contents and research results of the paper include: 1. Embedded algorithm design: in the framework of virtual coil algorithm, this paper introduces simple statistics such as speed, variance and mean, and proposes a fast video vehicle detection algorithm based on virtual coil statistics. Firstly, the virtual coil velocity statistics are calculated based on the block matching principle, and then the background modeling is carried out by using the high-order statistics block method, and the mean and variance statistics of the foreground image are obtained. Finally, the logical operation of statistics is used to judge the state of vehicle arrival, passing, leaving, stopping and so on. On the premise of meeting the real-time requirements, the algorithm has strong robustness to the interference of light, shadow and other external conditions, and is suitable for running on embedded platforms. The experimental results show that the detection speed of the algorithm can reach 50 frames per second on PC, and the detection rate can reach 98% in daytime and 93% in night under ideal conditions. When the vehicles are dense and shaded during the day, the detection rate reaches 94%, which meets the actual demand. 2. Program implementation and optimization: this paper takes the vehicle detection algorithm based on virtual coil statistics as the software core, and implements the embedded video vehicle detector on DM642 platform. The program is optimized by using inline function, expanding loop, rearranging software pipeline, using ping-pong mechanism to transmit data and so on. The test results of the actual road show that the embedded vehicle detector developed in this paper can achieve the detection speed of 20 frames per second and achieve real-time detection. At the same time, the vehicle detection rate can reach 96% during the day and 90% at night. The false detection rate is not more than 2% during the day, the missed detection rate is 4% during the day, the false detection rate is not more than 4% at night, and the missed detection rate is 10% at night. The test results show that the video vehicle detector based on DM642 can detect the vehicle in real time, at the same time, it also ensures the accuracy of the detection, and performs well in the balance between the detection speed and the detection rate. It lays a certain foundation for the development and application of embedded video vehicle detector in the future.
【學(xué)位授予單位】：北方工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2013
【分類號】：U495;TP368.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張玲,陳麗敏,何偉,郭磊民;基于視頻的改進(jìn)幀差法在車流量檢測中的應(yīng)用[J];重慶大學(xué)學(xué)報(bào)(自然科學(xué)版);2004年05期

2 宋勝利;曾巒;;DSP/BIOS在數(shù)字圖像處理中的應(yīng)用[J];國外電子測量技術(shù);2005年12期

3 艾紅;孫碩;;紅外測量在車流量監(jiān)測中的應(yīng)用[J];紅外技術(shù);2008年04期

4 盛翊智,謝寒生,李炳基,黃瓊;基于快速匹配算法的虛擬線圈設(shè)計(jì)[J];華中科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2004年03期

5 王亮,胡衛(wèi)明,譚鐵牛;人運(yùn)動(dòng)的視覺分析綜述[J];計(jì)算機(jī)學(xué)報(bào);2002年03期

6 劉海峰,郭寶龍,馮宗哲;用于塊匹配運(yùn)動(dòng)估值的正方形-菱形搜索算法[J];計(jì)算機(jī)學(xué)報(bào);2002年07期

7 王圣男,郁梅,蔣剛毅;智能交通系統(tǒng)中基于視頻圖像處理的車輛檢測與跟蹤方法綜述[J];計(jì)算機(jī)應(yīng)用研究;2005年09期

8 馬楓;張慶英;;基于以太網(wǎng)的超聲波車流量自動(dòng)檢測系統(tǒng)設(shè)計(jì)[J];武漢理工大學(xué)學(xué)報(bào)(交通科學(xué)與工程版);2007年01期

9 何偉;陳彬;張玲;;DSP/BIOS在基于DM642的視頻圖像處理中的應(yīng)用[J];信息與電子工程;2006年01期

10 魏武,張起森,王明俊,黃中祥;基于計(jì)算機(jī)視覺和圖像處理的交通參數(shù)檢測[J];信息與控制;2001年03期

相關(guān)碩士學(xué)位論文 前8條

1 丁莉雅;基于視頻圖像處理的交通信息采集系統(tǒng)[D];浙江大學(xué);2003年

2 萬文靜;基于光流的圖像目標(biāo)跟蹤方法研究[D];西北工業(yè)大學(xué);2006年

3 王衛(wèi)岳;基于TMS320DM642的車牌識別系統(tǒng)[D];浙江大學(xué);2007年

4 朱克忠;基于光流法對移動(dòng)目標(biāo)的視頻檢測與應(yīng)用研究[D];合肥工業(yè)大學(xué);2007年

5 高鵬;基于嵌入式的監(jiān)測監(jiān)控系統(tǒng)硬件開發(fā)與實(shí)現(xiàn)[D];北京郵電大學(xué);2007年

6 李天長;基于DM642的嵌入式實(shí)時(shí)圖像處理的研究[D];重慶大學(xué);2008年

7 錢毅;基于3G標(biāo)準(zhǔn)的嵌入式網(wǎng)絡(luò)視頻監(jiān)控系統(tǒng)設(shè)計(jì)與實(shí)現(xiàn)[D];廈門大學(xué);2008年

8 趙克棟;視頻監(jiān)控系統(tǒng)設(shè)計(jì)與工程應(yīng)用[D];北京郵電大學(xué);2009年

，

本文編號：2481928