本文選題：非重疊視域 + 多攝像機(jī)目標(biāo)跟蹤　； 參考：《西安科技大學(xué)》2017年碩士論文

【摘要】：隨著安防技術(shù)的迅速發(fā)展,生活場所中攝像機(jī)數(shù)目不斷增加,監(jiān)控覆蓋區(qū)域也逐漸擴(kuò)大。如何在大范圍攝像機(jī)監(jiān)控視域內(nèi)實(shí)現(xiàn)運(yùn)動目標(biāo)連續(xù)跟蹤的難題應(yīng)運(yùn)而生。不同于單攝像機(jī)的是多攝像機(jī)視域中光照、目標(biāo)姿勢和攝像機(jī)屬性等因素更具復(fù)雜性,尤其在非重疊視域下目標(biāo)的運(yùn)動在時空上都是離散的,為多攝像機(jī)目標(biāo)跟蹤帶來了巨大挑戰(zhàn)。本文對非重疊視域多攝像機(jī)目標(biāo)跟蹤方法展開深入研究。1)要想實(shí)現(xiàn)大范圍多攝像機(jī)視域內(nèi)的目標(biāo)連續(xù)跟蹤,首先需要進(jìn)行單攝像機(jī)下的目標(biāo)檢測與跟蹤。為了更加完整的獲取目標(biāo)區(qū)域,設(shè)計了一種基于小波變換的混合高斯背景建模檢測方法。利用小波變換去除噪聲使目標(biāo)信息更加清晰,然后建立混合高斯背景模型提取目標(biāo)。實(shí)驗(yàn)表明該方法相比于其他常用的檢測方法具有更高的準(zhǔn)確性。在跟蹤階段,為了改善TLD算法實(shí)時性差、對光線突變敏感等問題,提出基于Kalman濾波的TLD目標(biāo)跟蹤方法。用Kalman濾波器代替TLD中的光流法成為新的跟蹤器,在跟蹤過程中利用TLD中檢測器的結(jié)果更新跟蹤器。最后綜合跟蹤器和檢測器實(shí)現(xiàn)目標(biāo)定位。實(shí)驗(yàn)表明本方法相對于TLD算法來說具有更高的實(shí)時性和準(zhǔn)確性。2)為了減少攝像機(jī)視域之間不重疊而造成的時空差異,設(shè)計了一種基于高斯和互相關(guān)函數(shù)的拓?fù)涔烙嫹椒▉慝@取攝像機(jī)之間的時空關(guān)系。該方法利用單攝像機(jī)目標(biāo)檢測與跟蹤方法來確定拓?fù)浣Y(jié)點(diǎn)。根據(jù)多個時間窗口內(nèi)的平均互相關(guān)函數(shù)估計結(jié)點(diǎn)之間的連接關(guān)系,降低噪聲干擾。最后利用高斯分布描述每條連接上的轉(zhuǎn)移時間概率分布,使拓?fù)潢P(guān)系更加穩(wěn)定。實(shí)驗(yàn)表明本方法在不需要事先獲取攝像機(jī)間連接關(guān)系的情況下,能準(zhǔn)確估計出攝像機(jī)網(wǎng)絡(luò)的拓?fù)潢P(guān)系。3)首先為了消除攝像間光線的差異,提出基于累積顏色屬性轉(zhuǎn)換模型的目標(biāo)匹配方法。利用多張圖像學(xué)習(xí)累積顏色屬性轉(zhuǎn)換模型,將不同攝像機(jī)視域內(nèi)的圖像進(jìn)行顏色轉(zhuǎn)換,縮小了不同視域內(nèi)同一目標(biāo)的表觀差異。實(shí)驗(yàn)表明該方法顯著提高了目標(biāo)的識別率。其次,為了度量不同攝像機(jī)下目標(biāo)的相似性,采用基于SIFT特征的目標(biāo)匹配方法,先提取SIFT描述子建立表觀模型,然后給出基于序列的目標(biāo)匹配策略計算匹配度,使匹配結(jié)果更加可靠。實(shí)驗(yàn)證明該方法能夠準(zhǔn)確的在攝像機(jī)間進(jìn)行目標(biāo)匹配。4)為了實(shí)現(xiàn)最終的非重疊視域下的目標(biāo)連續(xù)跟蹤,提出一種基于拓?fù)潢P(guān)系和表觀模型相融合的目標(biāo)關(guān)聯(lián)方法。將拓?fù)潢P(guān)系、表觀模型和匹配策略融合到目標(biāo)關(guān)聯(lián)方法的框架中。首先根據(jù)拓?fù)潢P(guān)系確定候選目標(biāo)集,利用累積顏色屬性轉(zhuǎn)換模型處理不同視域下光線突變的問題,然后建立表觀模型,利用基于序列的匹配策略度量目標(biāo)的相似性,將不同視域內(nèi)的運(yùn)動軌跡進(jìn)行關(guān)聯(lián)。該方法減少了目標(biāo)關(guān)聯(lián)的計算量,并提升了準(zhǔn)確性。
[Abstract]:With the rapid development of security technology, the number of cameras in the living place is increasing, and the surveillance coverage area is also gradually expanding. How to realize the continuous tracking of moving targets in the field of wide range camera surveillance arises at the historic moment. Different from the single camera, the illumination in the multi-camera field is more complicated, especially the motion of the target is discrete in time and space, especially in the non-overlapping field of view. It poses a great challenge for multi-camera target tracking. In this paper, the method of multi-camera tracking in non-overlapping field of view is studied deeply. 1) in order to realize the continuous tracking of targets in the field of view of large range and multi-camera, it is necessary to detect and track the target under single camera first. In order to obtain the target region more completely, a hybrid Gao Si background modeling and detection method based on wavelet transform is designed. Wavelet transform is used to remove noise so that the target information is clearer, and then the mixed Gao Si background model is established to extract the target. Experiments show that this method is more accurate than other commonly used detection methods. In the tracking phase, in order to improve the real-time performance of the TLD algorithm and to be sensitive to the sudden change of light, a TLD target tracking method based on Kalman filter is proposed. The Kalman filter is used to replace the optical flow method in TLD as a new tracker. In the tracking process, the result of the detector in TLD is used to update the tracker. Finally, the target location is realized by synthesizing tracker and detector. Experiments show that this method has higher real-time and accuracy than TLD algorithm. A topology estimation method based on Gao Si and cross-correlation function is designed to obtain the temporal and spatial relationship between cameras. The method uses single camera target detection and tracking method to determine topological nodes. The connection relationship between nodes is estimated according to the average cross-correlation function in multiple time windows, and the noise interference is reduced. Finally, the transition time probability distribution on each connection is described by Gao Si distribution, which makes the topological relation more stable. The experimental results show that the proposed method can accurately estimate the topological relationship of camera network without obtaining the connection relationship between cameras in advance.) first of all, the difference of light between cameras can be eliminated. An object matching method based on cumulative color attribute transformation model is proposed. Based on the cumulative color attribute transformation model of multiple images, the color conversion of different cameras in the field of view is carried out, which reduces the apparent difference of the same object in the different field of view. Experiments show that this method can improve the target recognition rate significantly. Secondly, in order to measure the similarity of targets under different cameras, the target matching method based on sift feature is adopted. Firstly, the sift descriptor is extracted to establish the apparent model, and then the target matching strategy based on sequence is given to calculate the matching degree. Make the matching result more reliable. Experiments show that this method can accurately match the target between cameras. In order to realize the target continuous tracking in the final non-overlapping visual field, a target association method based on the combination of topological relation and apparent model is proposed. The topological relation, the apparent model and the matching strategy are fused into the framework of the target association method. First, the candidate target set is determined according to the topological relation, and the problem of light mutation in different horizons is dealt with by using the cumulative color attribute transformation model. Then, the apparent model is established, and the similarity of the target is measured by the matching strategy based on sequence. The motion trajectories in different horizons are correlated. This method reduces the computation of target association and improves the accuracy.
【學(xué)位授予單位】：西安科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TN948.41;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 尹紅娟;欒帥;;三幀差分運(yùn)動目標(biāo)檢測算法分析與驗(yàn)證[J];計算機(jī)與數(shù)字工程;2017年01期

2 尹宏鵬;陳波;柴毅;劉兆棟;;基于視覺的目標(biāo)檢測與跟蹤綜述[J];自動化學(xué)報;2016年10期

3 肖軍;朱世鵬;黃杭;謝亞男;;基于光流法的運(yùn)動目標(biāo)檢測與跟蹤算法[J];東北大學(xué)學(xué)報(自然科學(xué)版);2016年06期

4 於正強(qiáng);潘峗;宦若虹;;一種結(jié)合幀差法和混合高斯的運(yùn)動檢測算法[J];計算機(jī)應(yīng)用與軟件;2015年04期

5 張誠;馬華東;傅慧源;;基于時空關(guān)聯(lián)圖模型的視頻監(jiān)控目標(biāo)跟蹤[J];北京航空航天大學(xué)學(xué)報;2015年04期

6 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];計算機(jī)學(xué)報;2015年06期

7 姚倩;安世全;姚路;;三幀差法和Mean-shift結(jié)合的行人檢測與跟蹤研究[J];計算機(jī)工程與設(shè)計;2014年01期

8 黎萬義;王鵬;喬紅;;引入視覺注意機(jī)制的目標(biāo)跟蹤方法綜述[J];自動化學(xué)報;2014年04期

9 董文會;常發(fā)亮;李天平;;融合顏色直方圖及SIFT特征的自適應(yīng)分塊目標(biāo)跟蹤方法[J];電子與信息學(xué)報;2013年04期

10 張繼;王洪元;;一種基于增量半監(jiān)督判別分析的跟蹤方法[J];南京大學(xué)學(xué)報(自然科學(xué)版);2012年04期

相關(guān)博士學(xué)位論文 前1條

1 董文會;多攝像機(jī)監(jiān)控網(wǎng)絡(luò)中的目標(biāo)連續(xù)跟蹤方法研究[D];山東大學(xué);2015年

相關(guān)碩士學(xué)位論文 前10條

1 任榮;非重疊域多攝像機(jī)目標(biāo)檢測與跟蹤算法研究[D];中國礦業(yè)大學(xué);2016年

2 肖沙;基于幀間差和背景差的視頻運(yùn)動目標(biāo)檢測方法研究[D];海南大學(xué);2015年

3 潘邈;多攝像機(jī)下運(yùn)動目標(biāo)跟蹤關(guān)聯(lián)的關(guān)鍵技術(shù)研究[D];電子科技大學(xué);2015年

4 劉潔;基于光流法的運(yùn)動目標(biāo)檢測和跟蹤算法研究[D];中國礦業(yè)大學(xué);2015年

5 陸磊;無重疊視域多攝像機(jī)目標(biāo)跟蹤若干問題研究[D];合肥工業(yè)大學(xué);2015年

6 陳海濤;智能視頻的目標(biāo)檢測與目標(biāo)跟蹤算法研究[D];電子科技大學(xué);2015年

7 汪蘭;基于稀疏表示和壓縮感知的目標(biāo)檢測與跟蹤研究[D];廈門大學(xué);2014年

8 周天鳳;無重疊視域多攝像機(jī)目標(biāo)關(guān)聯(lián)研究[D];合肥工業(yè)大學(xué);2014年

9 王斌;無重疊視域多攝像機(jī)目標(biāo)跟蹤研究[D];合肥工業(yè)大學(xué);2013年

10 舒翔;基于隨機(jī)森林的目標(biāo)跟蹤算法研究[D];合肥工業(yè)大學(xué);2013年

，

本文編號：2118369