本文選題：智能交通監(jiān)控 + 軌跡多特征　； 參考：《哈爾濱工程大學》2014年碩士論文

【摘要】：隨著智能交通監(jiān)控技術的不斷發(fā)展,基于運動目標軌跡的行為分析和識別已成為研究熱點,其中聚類分析和異常檢測是研究的重點內容。通過對運動目標的軌跡進行聚類,可以自動的獲取監(jiān)控場景的典型軌跡運動模式并了解場景結構;而異常檢測的目標是能實時的自動的檢測出監(jiān)控場景中的異常行為,并及時的報警異常,是實現(xiàn)智能化監(jiān)控的關鍵步驟。本文對智能交通監(jiān)控領域中的軌跡聚類分析和異常檢測這兩個關鍵技術中存在的問題進行了深入的研究,充分利用了軌跡的不同特征信息,提出了切實可行的改進方法,主要工作體現(xiàn)在以下幾個方面:在聚類分析方面,針對傳統(tǒng)聚類方法只利用軌跡的單一特征信息進行聚類,聚類準確率低的問題,提出了基于軌跡多特征的分層聚類算法。該方法分別采用Bhattacharyya距離和基于線段插值的改進Hausdorff距離衡量軌跡間運動方向和空間位置的相似度,通過由粗到細的分層聚類來提取軌跡運動模式。為了提高聚類的效率,在每層的凝聚層次聚類中引入Laplacian映射以降低計算復雜度并同時自動確定每層的聚類數目。在異常檢測方面,首先對異常行為進行了全新的描述。根據異常軌跡偏離正常模式的程度和性質的不同,定義了三種常見的異常類型,分別為起點異常、全局異常和局部異常,有效解決了傳統(tǒng)的異常描述方法通用性不強、異常類型定義模糊等問題。然后針對傳統(tǒng)的異常檢測方法只考慮了軌跡的空間位置異常而忽略方向異常,或只能粗略檢測差異較大的軌跡異常而忽略軌跡局部子段異常等問題,提出了基于軌跡多特征的在線異常檢測方法。該方法先通過GMM模型學習監(jiān)控場景的軌跡起點位置分布模式,建立軌跡起點分布模型;再以移動窗作為基本比較單元,學習聚類后的每個正常軌跡參考類的空間位置模式和運動方向模式,建立基于位置距離和方向距離的分類器。最后在異常檢測階段,結合本文定義的異常類型,通過提出的在線多特征異常檢測算法從起點分布、空間位置和運動方向三個層次來衡量待測軌跡和正常軌跡模式之間的差異,判斷軌跡是否異常;并通過滑動移動窗口的方式,實現(xiàn)了對動態(tài)遞增軌跡數據的在線檢測。最后,將本文提出的聚類算法和異常檢測方法應用于真實交通場景的車輛軌跡數據中。實驗結果表明,本文的方法能快速準確的提取交通場景的車輛運動模式并能自動檢測出各種常見的交通異常行為,而且兩種方法分別在聚類準確率和異常識別率上更優(yōu)于傳統(tǒng)方法。
[Abstract]:With the continuous development of intelligent traffic monitoring technology, behavior analysis and recognition based on moving target trajectory has become a hot research topic, among which clustering analysis and anomaly detection are the focus of the research. By clustering the trajectory of moving objects, we can automatically obtain the typical trajectory motion pattern and understand the scene structure; and the object of anomaly detection is to detect the abnormal behavior in the monitoring scene in real time and automatically. And timely alarm abnormal, is a key step to achieve intelligent monitoring. In this paper, the problems of trajectory clustering analysis and anomaly detection in intelligent traffic monitoring field are deeply studied, the different characteristic information of trajectory is fully utilized, and a feasible improvement method is put forward. The main work is as follows: in the aspect of clustering analysis, aiming at the problem that the traditional clustering method only uses the single feature information of the trajectory to cluster, and the accuracy of clustering is low, a hierarchical clustering algorithm based on multiple locus features is proposed. In this method, Bhattacharyya distance and improved Hausdorff distance based on line segment interpolation are used to measure the similarity between trajectory direction and space position, and the trajectory motion pattern is extracted by hierarchical clustering from coarse to fine. In order to improve the efficiency of clustering, Laplacian mapping is introduced into the cluster of condensed layers in each layer to reduce the computational complexity and determine the number of clusters in each layer automatically at the same time. In the aspect of anomaly detection, the abnormal behavior is described completely new. According to the degree and nature of abnormal trajectory deviating from normal mode, three common types of anomaly are defined, which are starting point anomaly, global anomaly and local anomaly. The definition of exception type is vague and so on. Then the traditional anomaly detection method only considers the space position anomaly of the trajectory and neglects the direction anomaly, or only roughly detects the track anomaly with great difference and neglects the local subsegment anomaly of the trajectory, and so on. An online anomaly detection method based on multiple locus features is proposed. In this method, first of all, the GMM model is used to study the distribution pattern of the locus starting point of the scene, and then the moving window is used as the basic comparison unit. A classifier based on position distance and direction distance is established by studying the spatial position pattern and moving direction pattern of each normal trajectory reference class after clustering. Finally, in the phase of anomaly detection, combined with the anomaly types defined in this paper, the online multi-feature anomaly detection algorithm is proposed to measure the difference between the trajectory to be tested and the normal trajectory pattern from three levels: starting point distribution, space position and movement direction. To judge whether the trajectory is abnormal or not, and to realize the on-line detection of dynamic incremental trajectory data by sliding moving window. Finally, the proposed clustering algorithm and anomaly detection method are applied to the vehicle trajectory data of real traffic scene. The experimental results show that the proposed method can quickly and accurately extract the vehicle motion patterns of traffic scenes and detect all kinds of common abnormal traffic behaviors automatically. Moreover, the two methods are better than the traditional methods in clustering accuracy and anomaly recognition rate respectively.
【學位授予單位】：哈爾濱工程大學
【學位級別】：碩士
【學位授予年份】：2014
【分類號】：U495;TP311.13

【參考文獻】

相關期刊論文 前10條

1 吳定海;張培林;任國全;陳非;;基于支持向量的單類分類方法綜述[J];計算機工程;2011年05期

2 袁和金;吳靜芳;賈建軍;;一種基于HMM聚類的視頻目標軌跡分析方法[J];華北電力大學學報(自然科學版);2010年06期

3 陳斌;陳松燦;潘志松;李斌;;異常檢測綜述[J];山東大學學報(工學版);2009年06期

4 郝久月;李超;高磊;熊璋;;智能監(jiān)控場景中運動目標軌跡聚類算法[J];北京航空航天大學學報;2009年09期

5 蔡曉妍;戴冠中;楊黎斌;;譜聚類算法綜述[J];計算機科學;2008年07期

6 潘奇明;程詠梅;;基于隱馬爾可夫模型的運動目標軌跡識別[J];計算機應用研究;2008年07期

7 孫吉貴;劉杰;趙連宇;;聚類算法研究[J];軟件學報;2008年01期

8 潘奇明;程詠梅;楊濤;潘泉;趙春暉;;真實場景運動目標軌跡有效性判斷與自動聚類算法研究[J];計算機應用研究;2007年04期

9 高琰;谷士文;唐t;蔡自興;;機器學習中譜聚類方法的研究[J];計算機科學;2007年02期

10 侯志強;韓崇昭;;視覺跟蹤技術綜述[J];自動化學報;2006年04期

相關博士學位論文 前1條

1 張一;智能視頻監(jiān)控中的目標識別與異常行為建模與分析[D];上海交通大學;2010年

相關碩士學位論文 前8條

1 余忠慶;基于視頻的車輛軌跡聚類分析及異常檢測[D];北京交通大學;2012年

2 湯欣妍;移動對象路徑聚類和異常路徑檢測算法研究[D];華南理工大學;2011年

3 劉榮輝;基于主動學習的半監(jiān)督譜聚類算法研究[D];重慶大學;2011年

4 曹妍妍;交通視頻中車輛異常行為檢測及應用研究[D];蘇州大學;2011年

5 吳萌;交通監(jiān)控視頻中的異常事件檢測[D];北京郵電大學;2010年

6 卜德云;自適應譜聚類算法的研究與應用[D];南京航空航天大學;2010年

7 王曉龍;基于目標運動軌跡及空間分布的行為分析研究[D];中南大學;2009年

8 段明秀;層次聚類算法的研究及應用[D];中南大學;2009年

，

本文編號：1917878