本文選題：人群場景 + 異常檢測��； 參考：《天津大學》2016年碩士論文

【摘要】：監(jiān)控設(shè)備的普及催生了大量的監(jiān)控數(shù)據(jù),使得對監(jiān)控視頻中的異常進行人工檢測變得非常困難。為了減輕人力資源和經(jīng)濟負擔,同時提高異常檢測的準確率,人們不斷尋求對視頻當中的異常進行自動檢測的方法。人群密集的場景更是事故的多發(fā)場景,因此,如何對人群異常場景進行自動檢測尤為重要。本文提出了一種基于隱馬爾科夫模型(HMM)的方法來進行人群中的異常檢測和分類。本文將人群中的異常檢測定義為密集人群中出現(xiàn)異常的目標:機動車、自行車、滑板;另外還有人群的群體異常行為:人群突然的逃散。本文的目的就是要將這些異常目標和群體異常檢測出來,并將異常目標分類。隱馬爾科夫模型(HMM)可以利用變量的時空上下文關(guān)系為變量建立模型,本文選用隱馬爾科夫模型(HMM)進行監(jiān)控視頻中的人群異常檢測也正是基于隱馬爾科夫模型(HMM)的這種特點。在異常檢測階段,首先利用光流紋理描述運動物體的剛性特征,利用這一特征獲得異常的預檢測結(jié)果,在此基礎(chǔ)上利用隱馬爾科夫模型(HMM)建立時間上下文的異常檢測模型,然后利用Viterbi算法解碼獲得最優(yōu)隱狀態(tài)序列,這個隱狀態(tài)序列就是異常檢測的結(jié)果。在獲得異常檢測結(jié)果的同時獲得異常目標的所在位置。在異常分類階段,將異常目標的Radon特征與SVM分類器結(jié)合,得到異常目標預分類的結(jié)果,并利用異常目標的時間上下文關(guān)系建立基于隱馬爾科夫模型(HMM)分類模型,解碼獲得異常分類的結(jié)果。為了驗證本文算法的有效性,我們在UCSD PED2和UMN數(shù)據(jù)庫中進行實驗。實驗分為兩個階段,首先對人群中的異常目標和群體異常行為進行檢測,然后將檢測出的正確異常目標進行分類。最終實驗結(jié)果表明,本文算法可以準確的對異常進行檢測、定位,并對異常進行有效分類。
[Abstract]:The popularity of monitoring equipment has given birth to a large amount of monitoring data, which makes it very difficult to detect anomalies in surveillance video manually. In order to reduce the burden of human resources and economy, and improve the accuracy of anomaly detection, people are constantly looking for automatic detection of anomalies in video. Crowd-intensive scene is the frequent scene of accidents, so it is very important to detect the abnormal scene automatically. In this paper, a method based on Hidden Markov Model (hmm) is proposed to detect and classify abnormal population. In this paper, the abnormal detection in the crowd is defined as the abnormal target in the dense crowd: motor vehicle, bicycle, skateboard, and the abnormal behavior of the crowd: the sudden dispersal of the crowd. The purpose of this paper is to detect and classify these abnormal targets and population anomalies. The Hidden Markov Model (HMMM) can be used to establish the model by using the temporal and spatial context of the variable. In this paper, the Hidden Markov Model (HMMM) is used to detect the abnormal crowd in the surveillance video, which is based on the Hidden Markov Model (HMMM). In the phase of anomaly detection, the rigid feature of moving object is described by optical flow texture, and the pre-detection result of anomaly is obtained by using this feature. Based on this, an anomaly detection model of time context is established by using Hidden Markov Model (HMMM). Then Viterbi algorithm is used to decode the optimal hidden state sequence, which is the result of anomaly detection. The location of the abnormal target is obtained at the same time the result of anomaly detection is obtained. In the phase of anomaly classification, the Radon features of abnormal objects are combined with the SVM classifier to obtain the results of pre-classification of abnormal objects, and the hmm) classification model based on Hidden Markov Model (hmm) is established by using the temporal context of abnormal objects. Decode the result of abnormal classification. In order to verify the validity of this algorithm, we have carried out experiments in UCSD PED2 and UMN databases. The experiment is divided into two stages. First, the abnormal target and the abnormal behavior of the population are detected, and then the correct abnormal targets are classified. Finally, the experimental results show that the algorithm can accurately detect, locate and classify the anomalies.
【學位授予單位】：天津大學
【學位級別】：碩士
【學位授予年份】：2016
【分類號】：TP391.41;TN948.6

【參考文獻】

相關(guān)期刊論文 前1條

1 高晶;吳育峰;吳昆;孫繼銀;;基于角點檢測的圖像匹配算法[J];儀器儀表學報;2013年08期

相關(guān)博士學位論文 前1條

1 路子峗;光流場計算及其若干優(yōu)化技術(shù)研究[D];合肥工業(yè)大學;2012年

相關(guān)碩士學位論文 前5條

1 王夢偉;基于局部運動聚類的人群異常行為檢測[D];燕山大學;2014年

2 馬橋;基于光流直方圖和稀疏表示的群體異常檢測[D];廣西師范大學;2014年

3 古緒新;基于人群速度與人群分布的異常人群行為檢測[D];哈爾濱工業(yè)大學;2013年

4 余啟明;基于背景減法和幀差法的運動目標檢測算法研究[D];江西理工大學;2013年

5 張科銘;人群行為分析算法研究與實現(xiàn)[D];上海交通大學;2012年

，

本文編號：1815482