【摘要】：隨著社會(huì)的發(fā)展,視頻監(jiān)控系統(tǒng)已走進(jìn)了千家萬(wàn)戶中,智能化是監(jiān)控系統(tǒng)主要的發(fā)展趨勢(shì),而在監(jiān)控系統(tǒng)中實(shí)現(xiàn)對(duì)運(yùn)動(dòng)目標(biāo)的跟蹤是智能化的重要體現(xiàn)。本文將智能視頻監(jiān)控作為研究重點(diǎn),首先設(shè)計(jì)了目標(biāo)跟蹤算法的實(shí)現(xiàn)平臺(tái)——基于多核DSP的特色視頻監(jiān)控系統(tǒng),之后研究了運(yùn)動(dòng)目標(biāo)跟蹤算法,最后把算法在多核DSP監(jiān)控平臺(tái)上進(jìn)行了實(shí)現(xiàn)。本文的研究重點(diǎn)如下:(1)本文以TMS320DM8168(簡(jiǎn)稱DM8168)多核處理器為核心設(shè)計(jì)了特色視頻監(jiān)控系統(tǒng),實(shí)現(xiàn)了視頻的采集、處理、顯示和網(wǎng)絡(luò)輸出等功能。系統(tǒng)的特色之處在于根據(jù)實(shí)際需求設(shè)計(jì)了視頻流框架,對(duì)視頻做了TILER變換、添加OSD標(biāo)志、馬賽克拼接等處理,并為了實(shí)現(xiàn)視頻的網(wǎng)絡(luò)輸出功能,設(shè)計(jì)了流媒體服務(wù)器程序。在設(shè)計(jì)時(shí)通過(guò)添加AVS功能提升了系統(tǒng)的穩(wěn)定性,通過(guò)設(shè)計(jì)PCIe驅(qū)動(dòng)增強(qiáng)了系統(tǒng)的擴(kuò)展性。(2)在本文中特征提取算法是目標(biāo)跟蹤算法的重要組成部分,本文通過(guò)對(duì)比多種特征提取算法,選擇使用性能與效率兼顧的SURF算法提取目標(biāo)的特征,并使用多種匹配算法相結(jié)合的方式對(duì)目標(biāo)的SURF特征進(jìn)行匹配。在對(duì)目標(biāo)跟蹤算法整體測(cè)試時(shí)設(shè)計(jì)了合理的仿真流程,對(duì)目標(biāo)跟蹤中的目標(biāo)形態(tài)變化、目標(biāo)被遮擋、目標(biāo)影子影響等常見(jiàn)問(wèn)題,提出了解決方法,并對(duì)仿真結(jié)果進(jìn)行了分析。(3)根據(jù)DM8168多核監(jiān)控平臺(tái)的特點(diǎn),設(shè)計(jì)了多個(gè)核共同參與的目標(biāo)跟蹤算法實(shí)現(xiàn)流程,并根據(jù)流程對(duì)算法進(jìn)行了實(shí)現(xiàn)。由于算法實(shí)現(xiàn)后對(duì)實(shí)時(shí)性要求很高,所以根據(jù)DSP的特點(diǎn)對(duì)算法進(jìn)行了深入的優(yōu)化,使其速度得到了提升。通過(guò)對(duì)目標(biāo)跟蹤算法的測(cè)試驗(yàn)證了實(shí)現(xiàn)效果。(4)為了更好的保證算法的性能和速度,把目標(biāo)跟蹤算法中耗時(shí)最長(zhǎng)的SURF算法在TMS320C6678(簡(jiǎn)稱C6678)平臺(tái)上進(jìn)行了實(shí)現(xiàn)。在實(shí)現(xiàn)時(shí)采取劃分圖片的方式實(shí)現(xiàn)對(duì)整個(gè)任務(wù)的劃分,使得每個(gè)核處理一個(gè)子任務(wù)。通過(guò)對(duì)處理結(jié)果的分析,證明了這種劃分方法的正確性,同時(shí)算法的速度也得到了大幅度提升。通過(guò)對(duì)SURF算法在C6678平臺(tái)上實(shí)現(xiàn)方式的探索為后續(xù)目標(biāo)跟蹤算法在DM8168+C6678整個(gè)大平臺(tái)上的實(shí)現(xiàn)奠定了基礎(chǔ)。
[Abstract]:With the development of society, video surveillance system has entered into thousands of households, intelligent monitoring system is the main trend of development, and in the monitoring system to achieve the tracking of moving targets is an important embodiment of intelligent. In this paper, intelligent video surveillance is taken as the research focus. Firstly, the realization platform of target tracking algorithm is designed, which is based on multi-core DSP video surveillance system, and then the moving target tracking algorithm is studied. Finally, the algorithm is implemented on the multi-core DSP monitoring platform. The research focus of this paper is as follows: (1) this paper designs a special video monitoring system based on TMS320DM8168 (DM8168) multi-core processor, which realizes the functions of video acquisition, processing, display and network output. The characteristic of the system is that the video stream frame is designed according to the actual demand, the video is transformed by TILER, OSD logo is added, mosaic and so on. In order to realize the network output function of the video, the streaming media server program is designed. In the design, the stability of the system is improved by adding AVS function, and the expansibility of the system is enhanced by designing PCIe driver. (2) in this paper, feature extraction algorithm is an important part of target tracking algorithm. In this paper, by comparing various feature extraction algorithms, we select the SURF algorithm, which takes both performance and efficiency into account, to extract the feature of the target, and use a combination of multiple matching algorithms to match the SURF feature of the target. The reasonable simulation flow is designed in the whole test of the target tracking algorithm. Some common problems, such as the change of the target shape, the occlusion of the target, the influence of the shadow of the target, and so on, are proposed. The simulation results are analyzed. (3) according to the characteristics of DM8168 multi-core monitoring platform, the realization flow of target tracking algorithm with multiple cores is designed, and the algorithm is implemented according to the flow chart. Because of the high requirement of real-time performance, the algorithm is optimized deeply according to the characteristics of DSP, and the speed of the algorithm is improved. The result is verified by testing the target tracking algorithm. (4) in order to better guarantee the performance and speed of the algorithm, the SURF algorithm, which takes the longest time in the target tracking algorithm, is implemented on the platform of TMS320C6678 (C6678). In the implementation, the whole task is partitioned by the way of dividing pictures, so that each kernel processes one sub-task. Through the analysis of the processing results, the correctness of the method is proved, and the speed of the algorithm is greatly improved. By exploring the implementation of SURF algorithm on C6678 platform, this paper lays a foundation for the realization of the following target tracking algorithm on the whole platform of DM8168 C6678.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41;TN948.6

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 黃凱奇;陳曉棠;康運(yùn)鋒;譚鐵牛;;智能視頻監(jiān)控技術(shù)綜述[J];計(jì)算機(jī)學(xué)報(bào);2015年06期

2 仇大偉;劉靜;;復(fù)雜場(chǎng)景下基于特征點(diǎn)匹配的目標(biāo)跟蹤算法[J];山東科學(xué);2014年04期

3 倪郁東;王晨;;基于窗口的Surf目標(biāo)跟蹤[J];安徽大學(xué)學(xué)報(bào)(自然科學(xué)版);2014年04期

4 張坤;許廷發(fā);王平;馮亮;;高精度實(shí)時(shí)全幀頻SURF電子穩(wěn)像方法[J];光學(xué)精密工程;2011年08期

5 陳書(shū)明;萬(wàn)江華;魯建壯;劉仲;孫海燕;孫永節(jié);劉衡竹;劉祥遠(yuǎn);李振濤;徐毅;陳小文;;YHFT-QDSP:High-Performance Heterogeneous Multi-Core DSP[J];Journal of Computer Science & Technology;2010年02期

6 信師國(guó);劉慶磊;劉全賓;;網(wǎng)絡(luò)視頻監(jiān)控系統(tǒng)現(xiàn)狀和發(fā)展趨勢(shì)[J];信息技術(shù)與信息化;2010年01期

7 王亞琴;董彥榮;薄靜儀;;流媒體傳輸協(xié)議及應(yīng)用[J];辦公自動(dòng)化;2009年24期

相關(guān)博士學(xué)位論文 前6條

1 謝凌曦;基于局部特征的圖像表示模型理論與實(shí)踐[D];清華大學(xué);2015年

2 侯躍恩;基于稀疏表示的視覺(jué)目標(biāo)跟蹤算法研究[D];華南理工大學(xué);2014年

3 劉晴;基于區(qū)域特征的目標(biāo)跟蹤算法研究[D];北京理工大學(xué);2014年

4 牛長(zhǎng)鋒;復(fù)雜背景下視頻運(yùn)動(dòng)目標(biāo)跟蹤的研究[D];北京理工大學(xué);2010年

5 郭龍?jiān)?計(jì)算機(jī)視覺(jué)立體匹配相關(guān)理論與算法研究[D];南京理工大學(xué);2009年

6 夏永泉;計(jì)算機(jī)視覺(jué)中雙目匹配相關(guān)技術(shù)研究[D];南京理工大學(xué);2007年

相關(guān)碩士學(xué)位論文 前6條

1 王禹程;基于局部特征的運(yùn)動(dòng)目標(biāo)跟蹤算法的研究與實(shí)現(xiàn)[D];電子科技大學(xué);2016年

2 王朋;基于DM8168的網(wǎng)絡(luò)智能監(jiān)控系統(tǒng)的研究與實(shí)現(xiàn)[D];電子科技大學(xué);2015年

3 陳誠(chéng);基于雙目視覺(jué)的運(yùn)動(dòng)目標(biāo)跟蹤算法研究與應(yīng)用[D];哈爾濱工業(yè)大學(xué);2014年

4 鄒依峰;智能視頻監(jiān)控中的行人檢測(cè)與跟蹤方法研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2011年

5 卜珂;基于SURF的圖像配準(zhǔn)與拼接技術(shù)研究[D];大連理工大學(xué);2009年

6 王典;基于混合高斯的背景建模與陰影抑制算法研究[D];西北工業(yè)大學(xué);2006年

，

本文編號(hào)：2401763