(18.207.240.230) 您好!臺灣時間:2020/07/09 11:07
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
本論文永久網址: 
line
研究生:曾宥臻
研究生(外文):You-Jhen Zeng
論文名稱:影像中賦予信任等級的群眾切割
論文名稱(外文):Crowd Segmentation with Confidence Level Computation
指導教授:鄭旭詠
指導教授(外文):HSU-YUNG CHENG
學位類別:碩士
校院名稱:國立中央大學
系所名稱:資訊工程研究所
學門:工程學門
學類:電資工程學類
論文出版年:2011
畢業學年度:99
語文別:英文
論文頁數:55
中文關鍵詞:改進式類Haar-like特徵運算式的有向性梯度直方圖曲波有向性梯度直方圖行人偵測群眾切割
外文關鍵詞:MHOOGHOOGCurveletHOGcrowd segmentationpedestrian detection
相關次數:
  • 被引用被引用:1
  • 點閱點閱:96
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
隨著科技日益增進,和社會及個人安全的考量,基於影像資訊發展的監控系統成為現今非常重要的研究標的;其中,基於視覺影像的群眾切割,更是廣泛地應用在不同應用系統當中,不論是多人追踨、無人駕駛智慧車、行人偵測、人數統計或是行為分析,都需要準確地的標記出群眾中各個個體的位置,才能進一步作其偵測與分析。 群眾切割是一個極富挑戰性的題目,由於人的肢體動作變化性大,人體的正面和側面輪廓有所不同,每個人的衣著打扮各有不同,再加上一群人走在一起常有彼此遮蔽的問題,更是造成特徵擷取的困難。故我們在本研究中提出一套適用在複雜情境的群眾切割系統,且賦予切割的目標一個信任等級,可被其他應用系統當作參考,例如多人追蹤,有助於提升其偵測和分析結果。
本研究的第一部分,特徵擷取方面利用有向性梯度直方圖HOG (Histogram of Oriented Gradients, HOG) 配合Curvelet (曲波),配合分類器向量支撐機 (Support Vector Machine, SVM) 對群眾中的個體進行偵測,和單純使用HOG特徵的結果比較,可顯著地提升群眾切割的準確率。第二部分,為了避免人與人之間的遮蔽問題,我們提出一個新的特徵---改進式類Haar-like特徵運算式的有向性梯度直方圖 (Modified Haar of Oriented Gradients, MHOOG),分別為MHOOG-U和MHOOG-L,以較少的維度資訊,對人體上半身和下半身做準確的偵測,並賦予其信任等級,我們可藉由多張frame之間的信任等級,提供進階研究作較精確的參考。實驗部分呈現本研究所提出的方法可以達成可信度高的群眾切割,在賦予信任等級的偵測實驗中,等級1的每張frame平均的false alarm偵測人數約為0.0227~0.0401,等級4的每張frame平均miss的偵測人數約為0.125~0.4417。本研究確實提供擁有高可靠性參考資訊的群眾切割。
Crowd Segmentation plays an important role in security surveillance systems. We propose a confidence level computation mechanism and three effective feature extraction methods which facilitate crowd segmentation. With confidence level information of multiple frames, segment individuals in crowds can be performed more accurately. Besides, our system can be exploited in subsequent applications such as tracking or human activity analysis.
Firstly, we design a new feature descriptor based on HOG (Histogram of Oriented Gradients) and curvelet. Then, we exploit the descriptor and support vector machine (SVM) to detect the full body of the pedestrian. Secondly, we construct an upper body detector and a lower body detector using new features MHOOG-U (Modified Haar of Oriented Gradients for Upper Body) and MHOOG-L (Modified Haar of Oriented Gradients for Lower Body). To locate the upper body and lower body of the individuals in the crowd, MHOOG-U and MHOOG-L are not only reliable and require much fewer dimension information compared with HOG features. Afterwards, we evaluate the segmentation results according to the detection responses of these three parts. According to the experimental results, with quite few the false alarm number per frame about 0.0227~0.0401 in confidence level 1 and low miss number per frame around 0.125~0.4417 in level 4, we confirmedly provide the valuable information from our confidence level computation mechanism. With multiple frames‟ information provided from our system, reliable detection information is evaluated and crowd segmentation can be achieved more accurately.
摘 要 i
ABSTRACT ii
CONTENTS iii
LIST OF FIGURES iv
LIST OF TABLES . vi
CHAPTER 1 INTRODUCTION 1
1.1 Motivation 1
1.2 Related Works 2
1.3 System Overview 5
1.4 Thesis Organization 6
CHAPTER 2 REVIEW OF RELEVANT TECHNIQUES 7
2.1 Histograms of oriented gradients (HOG) 7
2.2 Curvelet Features 9
2.3 Edge of Orientation (EOH) and Haar of Oriented Gradients (HOOG) 14
2.4 Support Vector Machine (SVM) 17
CHAPTER 3 CROWD SEGMENTATION . 20
3.1 Multi-scale Sliding Detection Windows 20
3.2 Full Body Feature Extraction 21
3.3 Upper Body Feature Extraction 23
3.4 Lower Body Feature Extraction 27
3.5 Confidence Level Computation and Clustering 28
CHAPTER 4 EXPERIMENTAL RESULTS 31
4.1 The Evaluation of the Proposed Feature Extraction Method 31
4.1.1 The Evaluation of the Full Body Feature Extraction Method 31
4.1.2 The Evaluation of Upper Body and Lower Body Feature Extraction Method 33
4.2 System Environment and Dataset 37
4.3 Detection Results and Confidence Level Computation 39
4.4 Performance Analysis 42
CHAPTER 5 CONCLUSIONS .44
REFERENCES 45
[1] P. Tu, T. Sebastian, G. Doretto, N. Krahnstoever, J. Rittscher and T. Yu, “ Unified Crowd Segmentation”, ECCV (4)’08, pp. 691–704 , 2008.
[2] J. Rittscher, P. Tu, and N. Krahnstoever, “Simultaneous Estimation of Segmentation and Shape”, Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 487-493, 2005.
[3] T. Zhao, R. Nevatia, “Bayesian human segmentation in crowded situations”, Proc. IEEE Conf, CVPR (2)’03, pp. 459-466, 2003.
[4] T. Zhao and R. Nevatia, “Stochastic human segmentation from a static camera”, Proc. IEEE workshop on Motion and Video Computing, pp. 9–14, 2002.
[5] I. Haritaoglu, D. Harwood, and L. Davis. Hydra, “Multiple people detection and tracking using silhouettes”, Proc. IEEE workshop on Visual Surveillance, pp. 6–13, 1999.
[6] L. Dong, V. Parameswaran, V. Ramesh, and I. Zoghlami, “Fast Crowd Segmentation Using Shape Indexing”, International Conference on Computer Vision, pp. 1-8, 2007.
[7] B. Leibe, E. Seemann, and B. Schiele, “Pedestrian Detection in Crowded Scenes”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 878-885, 2005.
[8] D. Gavrila, “A Bayesian, Exemplar-Based Approach to Hierarchical Shape Matching”, IEEE Trans. Pattern Anal. Mach. Intell., pp.1408-1421, 2007.
[9] D. M. Gavrila and S. Munder, “Multi-cue pedestrian detection and tracking from a moving vehicle”, International Journal of Computer Vision, pp. 41-59, 2007.
[10] P. viola ad M. Jones, and D. Snow, “Rapid object detection using a boosted
cascade of simple features”, IEEE Conference on Computer Vision and Pattern Recognition, pp.511-518, 2001.
[11] P. viola ad M. J. Jones, and D. Snow, “Detecting pedestrians using patterns of motion and appearance”, IEEE International Conference on Computer vision, pp.734-741, 2003.
[12] B. Wu and R. Nevatia, “Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors”, ICCV’ 05, pp.90-97, 2005.
46
[13] B. Wu and R. Nevatia, “Tracking of Multiple, Partially Occluded Humans based on Static Body Part Detection”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 951-958, 2006.
[14] K. Mikolajczyk, C. Schmid, and A. Zisserman, “Human detection based on aprobabilistic assembly of robust part detectors”, ECCV (1)''04, pp. 69–82, 2004.
[15] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection”, CVPR (1)''05, pp. 886-893, 2005.
[16] Q. Zhu, S. Avidan, M. Yeh, and K.T. Cheng, “Fast Human Detection Using a Cascade of Histograms of Oriented Gradients”, Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1491-1498, 2006.
[17] H. Grabner, P. M. Roth, and H. Bischof, “Is pedestrian detection really a hard task”, IEEE International Workshop on PETS, pp.1-8, Oct. 2007.
[18] N. He, J. Cao, and L. Song, “Scale space histogram of oriented gradients for human detection”, International Symposium on Information Science and Engineering, pp. 167-170, 2008.
[19] S. Paisitkriangkrai , C. Shen, and J. Zhang, “Performance evaluation of local features in human classification and detection”, IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 236-246, 2008.
[20] P. Dollár, Z. Tu, P. Perona, and S. Belongie, “Integral channel features”, In BMVC, 2009.
[21] K. Levi and Y. Weiss, “Learning object detection from a small number of examples”, In Proc. CVPR(2)''04, pp. 53–60, 2004.
[22] W. Zhang, J. Sun, and X. Tang, “Cat head detection - how to effectively exploit shape and texture features”, in ECCV (4), pp. 802–816, 2008.
[23] C.J.C, Burges, “A tutorial on support vector machines for pattern recognition”, Data Mining and Knowledge Discovery, vol. 2, no. 2, pp. 121-167, 1998.
[24] N. Cristianini and J. Shawe-Taylor, “An Introduction to Support Vector Machines and Other Kernel-based Learning Methods”, Cambridge University Press, Cambridge, UK, 2000.
[25] D. L. Donoho and M. R. Duncan, “Digital curvelet transform: Strategy, implementation and experiments”, Proc. SPIE, vol. 4056, pp. 12–29, 2000.
[26] J. Starck, E.J. Candès, and D.L. Donoho, “The curvelet transform for image denoising” , IEEE Transactions on Image Processing, pp.670-684, 2002.
[27] E. Candès and D. Donoho, “New tight frames of curvelets and optimal representations of objects with piecewise singularities”, Commun. Pure Appl. Math., vol.57, no. 2, pp. 219–266, 2004.
47
[28] E. Candès, L. Demanet, D. Donoho, and L. Ying, “Fast discrete curvelet transforms,” Multiscale Model. Simul., vol. 5, no. 3, pp. 861–899, 2006.
[29] S. Munder and D. M. Gavrila, “An Experimental Study on Pedestrian Classification”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 11, pp.1863-1868, 2006.
[30] H.Y. Cheng, S.H. Hsu, C.C. Yu and Y.J. Zeng, “Pedestrian Detection Using Combined Features of HOG and Curvelets”, 2010 International Security Technology and Management Conference, Taipei, Taiwan, Sep. 2010.
[31] EC Funded CAVIAR Project, IST 2001 37540, found at: http://homepages.inf.ed.ac.uk/rbf/CAVIAR/
[32] I.J. Sumana, “Content Based Image Retrieval Using Curvelet Transform”, Monash University, Australia, 2008.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊
 
系統版面圖檔 系統版面圖檔