發(fā)布時間：2018-05-07 18:20

  本文選題：計算機視覺 + 群體行為分析�。� 參考：《哈爾濱工業(yè)大學(xué)》2017年博士論文

【摘要】：隨著人口的快速增長、人群活動更加多樣以及社會化進程的迅速發(fā)展,群體場景變得更加普遍,于是建模、分析和理解視頻中群體行為數(shù)據(jù)的需求日益增強。相比于以往的視頻內(nèi)容分析的工作,群體視頻中人群數(shù)量增大,場景更為復(fù)雜等因素使得對視頻中的群體行為的分析問題面臨著巨大的挑戰(zhàn)。與此同時,群體行為中蘊含著很多跨學(xué)科領(lǐng)域問題的重要線索,理解群體行為的形成機理早已成為社會學(xué)和自然科學(xué)重要的研究課題之一。群體行為分析的研究可以為很多關(guān)鍵工程應(yīng)用提供支持和相應(yīng)的解決方案,如智能視頻監(jiān)控,人群異常監(jiān)測,公共設(shè)施規(guī)劃等。這使得對群體行為的高層語義理解和分析變得越來越迫切。對于視頻中的群體場景人群行為的分析,簡稱群體行為分析,主要目的是以普通的監(jiān)控視頻為基礎(chǔ)進行群體場景語義內(nèi)容的理解和分析。在對研究現(xiàn)狀分析的基礎(chǔ)上發(fā)現(xiàn)現(xiàn)有方法的發(fā)展主要受到兩方面挑戰(zhàn)的制約,主要是群體認(rèn)知機理匱乏和結(jié)構(gòu)化語義缺失。本文以結(jié)構(gòu)化認(rèn)知信息在群體行為分析中的作用為出發(fā)點,以結(jié)構(gòu)化認(rèn)知信息在表達、協(xié)同、挖掘的三個階段的表現(xiàn)形式為主線,對高效的群體行為計算框架和算法模型展開研究:基于結(jié)構(gòu)化交互屬性,期望獲得描述群體行為交互作用的表達模型;利用結(jié)構(gòu)化語義信息進行群組建模,探索群組的共生結(jié)構(gòu)和形成結(jié)構(gòu)的一致性以及多屬性融合的群組協(xié)同模型;面向群體行為高層語義知識,挖掘群體情感和建模注意選擇機制。研究群體行為在視頻內(nèi)容智能分析領(lǐng)域的具體應(yīng)用,試圖挖掘真實場景視頻數(shù)據(jù)中出現(xiàn)的動態(tài)群體模式和行為。具體來說,本文的研究內(nèi)容和主要貢獻可以概括如下:首先,針對群體行為認(rèn)知機理的缺乏,即“所提取的底層運動特征與高層群體語義之間需要認(rèn)知機理來填補語義鴻溝”的問題,本文提出了一種基于結(jié)構(gòu)化交互屬性的群體認(rèn)知表達模型,以刻畫群體行為的交互作用來增強現(xiàn)有的群體表達的判別力和豐富性�，F(xiàn)有的群體行為表達模型缺乏對社會性交互作用的深層建模,需訴諸于屬性或概念特征,構(gòu)建從底層運動描述到中層對象交互的特定語義表示。通過借鑒社會化群體行為認(rèn)知機理,本文系統(tǒng)地提出了結(jié)構(gòu)化交互屬性的組織和表示方法,將量化后的屬性作為群體表達,并從結(jié)構(gòu)化屬性自身特點出發(fā)提出了在線融合策略。在UMN、UCSD、UCF-Web多個數(shù)據(jù)集上進行了群體行為異常檢測任務(wù)的比較實驗。結(jié)果證明了基于結(jié)構(gòu)化交互屬性的群體表達模型的有效性。其次,本文就結(jié)構(gòu)化語義信息在群組表達中的缺失,即“如何利用群組的結(jié)構(gòu)及關(guān)聯(lián)特性和多屬性信息”的問題進行了拓展研究,通過協(xié)同建模來提高結(jié)構(gòu)化的語義表示。本文提出了基于結(jié)構(gòu)一致性圖挖掘的群組檢測方法,其中包含基于共生結(jié)構(gòu)一致性的軌跡圖詞包模型來進行群體事件的刻畫,以及基于形成結(jié)構(gòu)一致性的密集子圖模型進行群組結(jié)構(gòu)的描述。在UMN、PETS等數(shù)據(jù)集上的實驗結(jié)果表明,所提方法可以在群體事件識別和群組檢測中有效地提高性能。更進一步,可以通過多種屬性來全面地描述群組輪廓,包括同質(zhì)、異質(zhì)、拓?fù)鋵傩缘取１疚奶接懭绾螌⑷航M的多屬性信息進行融合,進而提出基于深度屬性嵌入圖學(xué)習(xí)的群體描述方法,來進行群體視頻檢索。所提方法整合多種屬性到圖排序的框架中,同時進行排序分?jǐn)?shù)、屬性權(quán)重和深度轉(zhuǎn)換矩陣的優(yōu)化。在CUHK-Crowd數(shù)據(jù)集上進行了群體視頻檢索實驗,實驗結(jié)果表明了所提方法的優(yōu)異性能。最后,本文以結(jié)構(gòu)化認(rèn)知表示為基礎(chǔ),提出了面向群體行為高層語義知識挖掘的包括群體情感和注意選擇機制的建模方法。針對群體情感,本文探討結(jié)構(gòu)化軌跡特征和情感空間的映射關(guān)系,進而提出基于結(jié)構(gòu)化軌跡學(xué)習(xí)的群體情感建模方法。通過結(jié)構(gòu)化的軌跡學(xué)習(xí)提取連貫的軌跡特征,進一步加權(quán)回歸學(xué)習(xí)將特征映射到情感空間來構(gòu)建群體情感曲線表示。實驗結(jié)果表明,所提方法可以有效地進行群體情感的分類匹配等任務(wù)。另外,從群體場景的顯著度建模出發(fā),本文探討群體場景中的注意選擇機理,并提出了基于級聯(lián)深度網(wǎng)絡(luò)的群體顯著度預(yù)測方法。實驗結(jié)果表明,所提方法同時考慮到群體和顯著度的感知特性,同主流方法相比更為有效。通過以上研究,本文對面向視頻內(nèi)容分析的群體行為表達和計算模型進行了深入的探索,為群體行為分析研究中所面臨的關(guān)鍵問題提供了切實的解決方案。結(jié)果表明:結(jié)構(gòu)化的認(rèn)知因素在群體行為表達和應(yīng)用中起到重要作用。通過引入結(jié)構(gòu)化交互屬性,可以提取出更豐富和易于理解的特征增強對象級的描述,從而提升異常檢測任務(wù)的準(zhǔn)確率;特定的群組結(jié)構(gòu)化語義中具有共生和形成結(jié)構(gòu)一致性,綜合考慮利用一致性以及協(xié)同多屬性優(yōu)化可以顯著提升群組模式分析的性能;結(jié)合群體行為認(rèn)知機理,可以進一步對群體行為的情感和注意機制等高層語義進行合理解釋和建模,同時能夠有效地解決群體事件識別、情感分類、顯著度預(yù)測等實際的應(yīng)用問題。
[Abstract]:With the rapid growth of the population, the more diverse activities of the population and the rapid development of the process of socialization, the group scene has become more common, so the demand for modeling, analysis and understanding of the group behavior data in video is increasing. Compared with the previous video content analysis, the number of people in group video is increasing and the scene is more complex. Factors make a great challenge to the analysis of group behavior in video. At the same time, group behavior contains many important interdisciplinary clues. Understanding the formation mechanism of group behavior has already become one of the most important research topics in sociology and natural science. The key engineering applications provide support and corresponding solutions, such as intelligent video surveillance, crowd anomaly monitoring, public facility planning, etc.. This makes the high-level semantic understanding and analysis of group behavior becoming more and more urgent. Understanding and analyzing the semantic content of group scene based on monitoring video. Based on the analysis of the present situation, it is found that the development of the existing methods is mainly restricted by two challenges, mainly the lack of group cognitive mechanism and the lack of structured semantics. This paper is based on the role of structured cognitive information in group behavior analysis. On the basis of structured cognitive information in the three stages of expression, collaboration and mining, the main line is to study the efficient computing framework and algorithm model of group behavior: Based on structured interaction properties, we expect to obtain an expression model describing the interaction of group behavior, and use structured semantic information to model groups and explore groups. The conformance of the symbiotic structure and the formation structure of the group and the group cooperative model of multi attribute fusion, the high level semantic knowledge of group behavior, the mining of group emotion and the attention selection mechanism of modeling, and the application of group behavior in the field of video content intelligence analysis, trying to dig out the dynamic groups in the video data of real scene. In particular, the research content and main contributions of this paper can be summarized as follows: firstly, in view of the lack of cognitive mechanism of group behavior, that is, "the underlying movement features and the high-level group semantics need cognitive mechanism to fill the gap of complement meaning", this paper proposes a structured interactive attribute. The model of group cognitive expression to characterize the interaction of group behavior to enhance the discriminatory power and richness of the existing group expression. The existing model of group behavior expression lacks the deep modeling of social intercourse interaction. It needs to resort to attribute or conceptual features, and constructs a specific semantic representation from the bottom transport description to the middle object interaction. By drawing on the cognitive mechanism of social group behavior, this paper systematically proposes the organization and representation of structured interactive attributes, expresses the quantized attributes as groups, and proposes an online fusion strategy from the characteristics of structured attributes itself. The task of group behavior anomaly detection is carried out on multiple data sets of UMN, UCSD and UCF-Web. The results demonstrate the effectiveness of the group expression model based on structured interaction properties. Secondly, this paper extends the research on the lack of structured semantic information in the group expression, that is, "how to use the structure of groups and association characteristics and multi attribute information", and through collaborative modeling to improve the structure of the language. In this paper, a group detection method based on the structure consistency graph mining is proposed, which includes the trajectory graph packet model based on the conformance of symbiotic structure to depict the group events, and the description of the group structure based on the dense subgraph model based on the conformance of the structure. The experimental result table on the data set of UMN, PETS and so on The proposed method can effectively improve performance in group event recognition and group detection. Further, the group profiles can be described comprehensively through a variety of attributes, including homogeneity, heterogeneity and topological properties. This paper discusses how to integrate the multi attribute information of groups, and then proposes a group based on the depth attribute embedding graph to learn the group. Description method to carry out group video retrieval. The proposed method integrates multiple attributes to graph sorting framework, and performs sorting score, attribute weight and depth conversion matrix optimization. A group video retrieval experiment on CUHK-Crowd data sets is carried out. The experimental results show the excellent performance of the proposed method. Finally, this paper is structured. On the basis of cognitive representation, a modeling method including group emotion and attention selection mechanism for group behavior high-level semantic knowledge mining is proposed. Based on group emotion, this paper discusses the mapping relationship between structural trajectory characteristics and emotional space, and then proposes a group affective modeling method based on structured trajectory learning. Trajectory learning extracts coherent trajectory features, and further weighted regression learning maps features to emotional space to construct a group emotional curve. The experimental results show that the proposed method can effectively carry out the task of classification and matching of group emotions. In addition, from the modeling of the group scene, this paper discusses the group scene. The method of group saliency prediction based on cascade depth network is proposed. The experimental results show that the proposed method takes into account the perception characteristics of group and saliency, which is more effective than the mainstream method. Deep exploration provides a practical solution for the key problems in group behavior analysis. The results show that structured cognitive factors play an important role in the expression and application of group behavior. By introducing structured interaction properties, a more rich and understandable feature enhancement object level can be extracted. In order to improve the accuracy of the exception detection task, the specific group structure semantics have symbiotic and structural consistency. Considering the use of consistency and cooperative multi attribute optimization, the performance of the group pattern analysis can be improved significantly, and the cognitive mechanism of group behavior can be used to further the emotion and attention mechanism of group behavior. Such high-level semantics can be reasonably interpreted and modeled, and at the same time, it can effectively solve the practical application problems such as group event recognition, sentiment classification, saliency prediction and so on.

【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2017
【分類號】：TP391.41
，

本文編號：1857972