本文選題：視頻濃縮 + 目標(biāo)檢測(cè)��； 參考：《山東大學(xué)》2017年碩士論文

【摘要】：隨著信息化的迅猛發(fā)展以及人們對(duì)社會(huì)公共安全的日益關(guān)注,以攝像機(jī)為主要媒介的視頻監(jiān)控手段以其豐富、直觀(guān)而具體的信息表達(dá)形式越來(lái)越得到廣泛認(rèn)可,獲取的視頻監(jiān)控?cái)?shù)據(jù)為人們?cè)诎踩婪逗蜎Q策支持方面都起到了舉足輕重的作用。伴隨著數(shù)量急劇增加的監(jiān)控相機(jī)而來(lái)的是海量的視頻數(shù)據(jù),這些數(shù)據(jù)的處理需要耗費(fèi)大量的人力財(cái)力物力,如何從這些數(shù)據(jù)中快速獲取有價(jià)值的信息己成為行業(yè)的迫切需求。視頻濃縮技術(shù)作為解決上述問(wèn)題的有效方法,是對(duì)監(jiān)控獲取的原始視頻的高度濃縮,去除大量冗余信息的同時(shí)保留視頻中的關(guān)鍵信息,已成為監(jiān)控領(lǐng)域的熱點(diǎn)問(wèn)題�；趯�(duì)當(dāng)前視頻濃縮技術(shù)總體框架的研究,本文對(duì)運(yùn)動(dòng)目標(biāo)檢測(cè)、目標(biāo)跟蹤及軌跡提取、軌跡組合優(yōu)化及圖像融合這幾個(gè)關(guān)鍵技術(shù)進(jìn)行具體分析及優(yōu)化。本文采用改進(jìn)的視覺(jué)背景提取算法實(shí)現(xiàn)了運(yùn)動(dòng)目標(biāo)的檢測(cè),完整檢測(cè)出運(yùn)動(dòng)目標(biāo),抑制了傳統(tǒng)算法中的"鬼影"問(wèn)題;為了提高跟蹤性能,解決目標(biāo)丟失及濃縮視頻中出現(xiàn)的頻閃效應(yīng),本文提出一種基于目標(biāo)跟蹤的自適應(yīng)評(píng)價(jià)機(jī)制,并對(duì)評(píng)價(jià)機(jī)制做出定性及定量分析,設(shè)計(jì)跟蹤系統(tǒng)進(jìn)行驗(yàn)證,進(jìn)而提出基于跟蹤評(píng)價(jià)機(jī)制的魯棒跟蹤算法。之后,提取和存儲(chǔ)運(yùn)動(dòng)目標(biāo)的完整軌跡,并建立軌跡間能量函數(shù),將求取最優(yōu)軌跡組合的問(wèn)題轉(zhuǎn)化為求能量函數(shù)最小值的問(wèn)題,更新能量函數(shù)因子并使用模擬退火算法求取代價(jià)函數(shù)的最優(yōu)解。最后根據(jù)最優(yōu)軌跡組合提取出運(yùn)動(dòng)目標(biāo),將目標(biāo)區(qū)域與背景圖像融合得到濃縮視頻。為了提高融合效果,消除縫合邊界不自然的現(xiàn)象,提出閾值判斷的方法,生成瀏覽舒適度較高的濃縮視頻。通過(guò)對(duì)視頻濃縮算法中各個(gè)模塊進(jìn)行測(cè)試,本文研發(fā)的基于自適應(yīng)跟蹤評(píng)價(jià)機(jī)制的視頻濃縮技術(shù)能很好的去除原始視頻中的冗余信息,大大縮短視頻長(zhǎng)度,節(jié)省存儲(chǔ)空間,很好的保留原始視頻中運(yùn)動(dòng)物體的活動(dòng)信息,且不改變目標(biāo)的空間一致性,真實(shí)度高,能實(shí)現(xiàn)用戶(hù)快速瀏覽的需求。因此,本文提出的監(jiān)控視頻濃縮方法有良好的工程應(yīng)用價(jià)值。
[Abstract]:With the rapid development of information technology and people's increasing attention to social public safety, video surveillance means with video camera as the main medium is more and more widely recognized for its rich, intuitive and concrete forms of information expression. The obtained video surveillance data play an important role in security prevention and decision support. With the rapid increase in the number of surveillance cameras is a huge amount of video data, these data processing needs a lot of human, financial and material resources, how to quickly obtain valuable information from these data has become an urgent need of the industry. As an effective method to solve the above problems, video concentration technology has become a hot issue in the field of monitoring, which is highly concentrated on the original video obtained by monitoring, removing a large amount of redundant information while retaining the key information in the video. Based on the research of the general frame of video concentration technology, this paper analyzes and optimizes the key technologies of moving target detection, target tracking and trajectory extraction, trajectory combination optimization and image fusion. In this paper, the improved visual background extraction algorithm is used to detect moving targets, which can completely detect the moving targets and suppress the "ghost" problem in the traditional algorithms. To solve the stroboscopic effect in target loss and concentrated video, an adaptive evaluation mechanism based on target tracking is proposed in this paper. The evaluation mechanism is qualitatively and quantitatively analyzed, and the tracking system is designed to verify it. Then a robust tracking algorithm based on tracking evaluation mechanism is proposed. After that, the complete trajectory of moving object is extracted and stored, and the energy function between trajectories is established. The problem of finding the optimal trajectory combination is transformed into the problem of finding the minimum value of the energy function. The energy function factor is updated and the optimal solution of the cost function is obtained by simulated annealing algorithm. Finally, the moving target is extracted according to the optimal trajectory combination, and then the target region is fused with the background image to obtain the condensed video. In order to improve the fusion effect and eliminate the phenomenon of unnatural stitching boundary, a threshold judgment method is proposed to generate concentrated video with high browsing comfort. By testing each module of video concentration algorithm, the video concentration technology based on adaptive tracking and evaluation mechanism developed in this paper can remove redundant information from original video, greatly shorten the length of video and save storage space. It can keep the moving information of moving objects in the original video without changing the spatial consistency of the target. It has a high degree of reality and can realize the requirement of users to browse quickly. Therefore, the video concentration method proposed in this paper has good engineering application value.
【學(xué)位授予單位】：山東大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李杰;熊琨;楊東曉;;基于邊緣光流法向分量的運(yùn)動(dòng)區(qū)域劃分[J];北京理工大學(xué)學(xué)報(bào);2011年04期

2 姚彬;史萍;葛菲;謝志揚(yáng);;監(jiān)控視頻的摘要提取方法研究[J];電視技術(shù);2010年04期

3 楊戈;劉宏;;視覺(jué)跟蹤算法綜述[J];智能系統(tǒng)學(xué)報(bào);2010年02期

4 黃鑫娟;周潔敏;劉伯揚(yáng);;自適應(yīng)混合高斯背景模型的運(yùn)動(dòng)目標(biāo)檢測(cè)方法[J];計(jì)算機(jī)應(yīng)用;2010年01期

5 張娟;毛曉波;陳鐵軍;;運(yùn)動(dòng)目標(biāo)跟蹤算法研究綜述[J];計(jì)算機(jī)應(yīng)用研究;2009年12期

6 吳倩;史萍;;視頻摘要技術(shù)淺析[J];中國(guó)傳媒大學(xué)學(xué)報(bào)(自然科學(xué)版);2008年02期

7 欒悉道;謝毓湘;應(yīng)龍;吳玲達(dá);肖鵬;;基于EDU模型的新聞視頻摘要技術(shù)研究[J];系統(tǒng)仿真學(xué)報(bào);2007年16期

8 鐘小品;薛建儒;鄭南寧;平林江;;基于融合策略自適應(yīng)的多線(xiàn)索跟蹤方法[J];電子與信息學(xué)報(bào);2007年05期

9 劉桂清,李建成,肖鵬,王辰;基于“實(shí)體-描述-效用”模型的視頻摘要技術(shù)[J];計(jì)算機(jī)工程與科學(xué);2005年10期

10 歐陽(yáng)建權(quán),李錦濤,張勇東;視頻摘要技術(shù)綜述[J];計(jì)算機(jī)工程;2005年10期

，

本文編號(hào)：1861351