請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/41378
標題: | 電腦視覺技術於行人偵測之研究 Computer Vision Techniques for Effective Pedestrian Detection |
作者: | Yu-Ting Chen 陳昱廷 |
指導教授: | 洪一平(Yi-Ping Hung) |
關鍵字: | 階層式背景模型,差值統計圖,人員偵測,整體行人偵測,階層式前饋分類器,meta階層,AdaBoost,部件行人偵測,多重實例學習,多類多重實例boosting,特徵共用,視覺監控, Hierarchical background modeling,contrast histogram,human detection,holistic pedestrian detection,cascaded feed-forward classifiers,meta-stages,AdaBoost,part-based pedestrian detection,multi-instance learning,multi-class multi-instance boosting,feature sharing,visual surveillance, |
出版年 : | 2009 |
學位: | 博士 |
摘要: | 視訊安全監控相關研究中,前景偵測與行人偵測是基礎且重要的課題。在本論文裡,我們針對背景模型學習、整體行人偵測和部件行人偵測等題目進行研究與探討。在背景模型學習方面,大多數方法都是以像素為基礎,其優點是可提供精細的前景偵測結果,但對動態背景則無法有好的描述。近年來,有一些研究使用以區塊為基礎的方法來處理動態背景的問題,但無法提供精細的前景偵測結果。有鑑於此,我們提出了一個階層式架構來整合以像素與以區塊為基礎的方法,此架構除可克服動態背景的影響,亦可提供兩階段多尺度的前景偵測結果。在整體行人偵測的研究上,我們使用異質性特徵來描述行人影像,並提出了階層式連鎖前饋分類器來學習整體行人偵測器。在我們的架構中,藉由使用Meta階層,不同階層間的資訊可以被使用,因此,偵測正確率與效率可進一步提昇。當人被遮蔽時,整體行人偵測器可能無法將人成功偵測出來。針對此一問題,我們提出了一個多類多重實例boosting來學習部件偵測器。藉由使用多重實例學習方法,訓練影像對位的問題可以被解決;且藉由特徵共用的特性,我們的方法可以學習出一個有效率的部件偵測器。此外,我們也提出一個機率模型方法來整合部件偵測結果。藉由廣泛的實驗,我們證明此方法能有效地進行人的偵測。最後,我們整合了本論文提出之背景模型技術與行人偵測技術來進行視訊安全監控。 Three important research topics in visual surveillance are studied, including background modeling, holistic pedestrian detection, and part-based pedestrian detection. Most previous background modeling approaches are pixel-based, while some approaches began to study block-based representations which are more robust to non-stationary backgrounds. We propose a method that integrates block- and pixel-based approaches into a single framework. Quantitative results show that the proposed method has better classification results than existing single-level approaches. In addition, we develop a method that can detect holistic pedestrians in images. In our approach, heterogeneous features are employed for weak-learner selection, and a novel cascaded structure that exploits both the stage-wise classification information and the inter-stage cross-reference information is proposed. Experiment results show that our approach can detect pedestrians with both efficiency and accuracy. We also propose a multi-class multi-instance boosting method for effective part-based pedestrian detection in images. Training examples are represented as a set of non-aligned instances, and the alignment problem caused by human appearance variation can be handled. Our method has the feature-sharing ability in a cascaded structure for efficient detection. Experiment results demonstrate the superior performance of the proposed method. We also combine background modeling and pedestrian detection techniques for visual surveillance application. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/41378 |
全文授權: | 有償授權 |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-98-1.pdf 目前未授權公開取用 | 12.71 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。