本文選題：前景檢測(cè)　切入點(diǎn)：多目標(biāo)跟蹤　出處：《西南交通大學(xué)》2014年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著意外事故、犯罪和恐怖活動(dòng)的增加,公共安全顯得越來越重要。面對(duì)這些突發(fā)事件,智能視頻監(jiān)控系統(tǒng)能夠及時(shí)的給出預(yù)警信號(hào)或報(bào)警。與傳統(tǒng)的人工監(jiān)控?cái)z像頭相比,智能監(jiān)控系統(tǒng)能夠節(jié)省大量的人力、物力和財(cái)力,并且能夠更加高效的對(duì)這些合法的視頻監(jiān)控?cái)?shù)據(jù)實(shí)現(xiàn)自動(dòng)或者半自動(dòng)的解釋和分析處理。在智能監(jiān)控系統(tǒng)的研究中,視頻前景檢測(cè)、多目標(biāo)跟蹤和異常行為識(shí)別研究作為比較新的研究方向,已經(jīng)成為計(jì)算機(jī)視覺和模式識(shí)別領(lǐng)域的研究熱點(diǎn),它們的研究對(duì)于提高智能監(jiān)控系統(tǒng)的性能具有非常重要的意義。 本文通過對(duì)視頻前景檢測(cè)、多目標(biāo)跟蹤和異常行為識(shí)別領(lǐng)域的算法分析,對(duì)智能監(jiān)控系統(tǒng)的開發(fā)進(jìn)行了深入的研究。主要完成以下幾個(gè)方面的工作： 1.歸納總結(jié)了前景檢測(cè)領(lǐng)域常用的運(yùn)動(dòng)目標(biāo)檢測(cè)方法,并對(duì)常用的運(yùn)動(dòng)前景檢測(cè)方法進(jìn)行介紹,提出一個(gè)改進(jìn)的基于混合高斯模型的運(yùn)動(dòng)目標(biāo)檢測(cè)方法,大大提高了以往基于混合高斯模型的前景檢測(cè)的魯棒性和準(zhǔn)確性,其抗干擾能力顯著增強(qiáng)。 2.在跟蹤階段,針對(duì)單固定攝像頭,提出一個(gè)稀疏的多目標(biāo)跟蹤系統(tǒng)框架。該框架重點(diǎn)是將單目標(biāo)跟蹤很好的TLD算法和關(guān)聯(lián)矩陣結(jié)合起來,有效解決多目標(biāo)跟蹤過程的合并遮擋問題。在目標(biāo)合并處理階段,對(duì)合并的目標(biāo)加窗且引入雙三次插值算法對(duì)初始化的目標(biāo)和所加窗口進(jìn)行同比例超分辨縮放。該操作能很好地解決大目標(biāo)的計(jì)算復(fù)雜度高和小目標(biāo)的不能正常初始化問題。對(duì)于關(guān)聯(lián)矩陣的一些特殊情況進(jìn)行特殊處理。最后在濾波階段,該框架用分?jǐn)?shù)階卡爾曼算法代替卡爾曼算法進(jìn)行濾波,不僅能夠降低機(jī)動(dòng)目標(biāo)的觀測(cè)噪聲,還能在間隔跟丟時(shí)準(zhǔn)確地預(yù)測(cè)目標(biāo)的位置。 3.在基于軌跡的異常檢測(cè)階段,本文提出一個(gè)基于時(shí)間分割的多特征表示的軌跡異常檢測(cè)方法。首先提出一種新的軌跡特征表示方法,該方法由六個(gè)特征空間組成：1)軌跡的方向和長(zhǎng)度,2)軌跡的平均位置,3)初始位置、軌跡分割片段的時(shí)間長(zhǎng)度、分割片段的方向,4)分割片段序列的平均速度序列,5)分割片段序列的平均加速度序列,6)整條軌跡的最大加速度。接著利用監(jiān)督型的支持向量機(jī)分類算法來對(duì)軌跡特征集進(jìn)行訓(xùn)練、檢測(cè)。該方法提高了軌跡異常行為的異常檢測(cè)率和識(shí)別準(zhǔn)確度,降低了虛警率。同時(shí),由于不需要對(duì)訓(xùn)練和測(cè)試樣本進(jìn)行縮放處理從而大大提高了該方法的實(shí)用價(jià)值。
[Abstract]:With the increase of accidents, crime and terrorist activities, public safety becomes more and more important. In the face of these emergencies, intelligent video surveillance system can give early warning signal or alarm in time. Intelligent monitoring system can save a lot of manpower, material resources and financial resources, and can more efficiently interpret and analyze these legitimate video surveillance data automatically or semi-automatically. As a new research direction, video foreground detection, multi-target tracking and abnormal behavior recognition have become the research focus in the field of computer vision and pattern recognition. Their research is very important for improving the performance of intelligent monitoring system. Through the algorithm analysis of video foreground detection, multi-target tracking and abnormal behavior recognition, the development of intelligent monitoring system is deeply studied in this paper. 1. The common moving target detection methods in the field of foreground detection are summarized, and the commonly used motion foreground detection methods are introduced, and an improved moving target detection method based on mixed Gao Si model is proposed. The robustness and accuracy of foreground detection based on mixed Gao Si model are greatly improved, and its anti-jamming ability is greatly enhanced. 2. In the tracking phase, a sparse multi-target tracking system framework is proposed for a single fixed camera, which focuses on combining the TLD algorithm with the correlation matrix. Effectively solve the merge occlusion problem in the multi-target tracking process. The combined target is windowed and the bi-cubic interpolation algorithm is introduced to scale the initialized object and the added window in the same proportion. This operation can solve the problem of high computational complexity of large target and abnormal initial value of small target. To deal with some special cases of incidence matrix. Finally, in the filtering stage, The frame uses fractional order Kalman algorithm instead of Kalman algorithm to filter, which can not only reduce the observation noise of maneuvering target, but also predict the position of target accurately at interval and loss time. 3. In the phase of locus based anomaly detection, this paper presents a method of trajectory anomaly detection based on multi-feature representation based on time division. Firstly, a new trajectory feature representation method is proposed. The method consists of six feature spaces, the direction and length of the trajectory, the average position of the trajectory, the initial position and the time length of the segment. The direction of the segment is 4) the average velocity sequence of the segment sequence is 5) the average acceleration sequence of the segment sequence is 6) the maximum acceleration of the whole trajectory is obtained. Then the supervised support vector machine classification algorithm is used to train the trajectory feature set. The method improves the detection rate and recognition accuracy of trajectory anomaly behavior and reduces the false alarm rate. At the same time, the practical value of the method is greatly improved because it does not need to scale the training and test samples.
【學(xué)位授予單位】：西南交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TN948.6

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 翟海濤;;多假設(shè)跟蹤算法研究及其應(yīng)用[J];信息化研究;2010年08期

2 侯志強(qiáng);韓崇昭;;視覺跟蹤技術(shù)綜述[J];自動(dòng)化學(xué)報(bào);2006年04期

，

本文編號(hào)：1650082