請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/9746
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 傅立成 | |
dc.contributor.author | Cheng-Hsiung Chuang | en |
dc.contributor.author | 莊振勛 | zh_TW |
dc.date.accessioned | 2021-05-20T20:38:58Z | - |
dc.date.available | 2008-07-30 | |
dc.date.available | 2021-05-20T20:38:58Z | - |
dc.date.copyright | 2008-07-30 | |
dc.date.issued | 2007 | |
dc.date.submitted | 2008-07-25 | |
dc.identifier.citation | [1] P. Viola, M. J. Jones, and D. Snow, 'Detecting Pedestrians Using Patterns of Motion and Appearance,' International Journal of Computer Vision, 2005.
[2] J. J. Little and J. E. Boyd, 'Recognizing People by Their Gait: The Shape of Motion,' Journal of Computer Vision Research, p. pp. 1—32, 1998. [3] B. Heisele and C. Woehler, 'Motion-based recognition of pedestrians,' in International Conference on Pattern Recognition, 1998, pp. 1325-1330 vol.2. [4] L. Wang, T. Tan, H. Ning, and W. Hu, 'Silhouette analysis-based gait recognition for human identification,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, pp. 1505-1518, 2003. [5] D. Cunado, M. S. Nixon, and J. N. Carter, 'Automatic Extraction and Description of Human Gait Models for Recognition Purposes,' Computer Vision and Image Understanding, vol. 90, p. 1—41, 2003. [6] C. Curio, J. Edelbrunner, T. Kalinke, C. Tzomakas, and W. von Seelen, 'Walking pedestrian recognition,' IEEE Transactions on Intelligent Transportation Systems, vol. 01, pp. 155-163, 2000. [7] S. A. Niyogi and E. H. Adelson, 'Analyzing and recognizing walking figures in XYT,' in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1994, pp. 469-474. [8] D. M. Gavrila, 'The Visual Analysis of Human Movement: A Survey,' Computer Vision and Image Understanding, vol. 73, pp. 82-89, 1999. [9] R. Yang, Z. Qinfen, I. Weiss, L. S. Davis, W. Abd-Almageed, and Z. Liang, 'Pedestrian classification from moving platforms using cyclic motion pattern,' in International Conference on Image Processing, 2005, pp. II-854-7. [10] Yang Ran, Isaac Weiss, Q. Zheng, and L. S. Davis, 'Pedestrian Detection via Periodic Motion Analysis,' International Journal of Computer Vision, 2007. [11] A. Broggi, M. Bertozzi, A. Fascioli, and M. Sechi, 'Shape-based pedestrian detection,' in Proceedings of the IEEE Intelligent Vehicles Symposium, 2000, pp. 215-220. [12] J. B. Hayfron, M. S. Nixon, and J. N. Carter, 'Human Identification by Spatio-Temporal Symmetry,' in IEEE International Conference on Pattern Recognition, 2002, pp. 11-15. [13] Ying Wu and T. Yu, 'A field model for human detection and tracking,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, pp. 753-765, 2006. [14] D. M. Gavrila, 'Pedestrian Detection from a Moving Vehicle,' in Proceedings of the European Conference on Computer Vision (ECCV), 2000. [15] D. M. Gavrila and S. Munder, 'Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle,' International Journal of Computer Vision, 2007. [16] C.-Y. Liu and L.-C. Fu, 'Computer Vision Based Object Detection and Recognition for Vehicle Driving,' in IEEE International Conference on Robotics and Automation, 2001. [17] A. Mohan, C. Papageorgiou, and T. Poggio, 'Example-based object detection in images by components,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, pp. 349-361, 2001. [18] D. Ramanan, D. A. Forsyth, and A. Zisserman, 'Tracking People by Learning Their Appearance,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, pp. 65-81, 2007. [19] B. Leibe, E. Seemann, and B. Schiele, 'Pedestrian detection in crowded scenes,' in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, pp. 878-885 vol. 1. [20] M. Oren, C. Papageorgiou, P. Sinha, E. Osuna, and T. Poggio, 'Pedestrian detection using wavelet templates,' in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1997, pp. 193-199. [21] B. Wu and R. Nevatia, 'Simultaneous Object Detection and Segmentation by Boosting Local Shape Feature based Classifier,' in IEEE Conference on Computer Vision and Pattern Recognition, 2007, pp. 1-8. [22] P. Sabzmeydani and G. Mori, 'Detecting Pedestrians by Learning Shapelet Features,' in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007. [23] N. Dalal and B. Triggs, 'Histograms of oriented gradients for human detection,' in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, pp. 886-893 vol. 1. [24] Qiang Zhu, Shai Avidan, Mei-Chen Yeh, and K.-T. Cheng, 'Fast Human Detection Using a Cascade of Histograms of Oriented Gradients,' in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006. [25] C.-C. R. Wang and J.-J. J. Lien, 'AdaBoost Learning for Human Detection Based on Histograms of Oriented Gradients,' in Proceedings of the Asian Conference on Computer Vision, 2007. [26] 'Mobileye: Improvement of Vehicle Safety with Vehicle Tracking & Car Tracking,' http://www.mobileye-vision.com/, Retrived May 5, 2008. [27] P. Viola and M. Jones, 'Rapid Object Detection using a Boosted Cascade of Simple Features,' in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001. [28] V. N. Vapnik, The nature of statistical learning theory: Springer-Verlag New York, Inc., 1995. [29] Y. Freund and R. E. Schapire, 'A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting,' Journal of Computer and System Sciences, vol. 55, pp. 119-139, 1997. [30] D. G. Lowe, 'Distinctive Image Features from Scale-Invariant Keypoints ' International Journal of Computer Vision, vol. 60, Number 2, pp. 91-110, 2004. [31] C.-C. Chang and C.-J. Lin, 'LIBSVM : a library for support vector machines.,' Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm, 2001. [32] B. Scholkopf and A. Smola, Learning with Kernels Support Vector Machines, Regularization, Optimization and Beyond. MIT Press, Cambridge, MA, 2002. [33] D. Hoiem, A. A. Efros, and M. Hebert, 'Putting Objects in Perspective,' in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, pp. 2137-2144. [34] OpenCV, 'Intel Open Source Computer Vision Library,' http://www.intel.com/technology/computing/opencv/, 2000 - 2006. [35] W. Pratt, Digital Image Processing, 3rd ed. New York: John Wiley & Sons, 2001. [36] 'MIT: CBCL Pedestrian Database,' http://cbcl.mit.edu/software-datasets/PedestrianData.html, Retrived June 17, 2008. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/9746 | - |
dc.description.abstract | 本篇論文提出利用增強性方向梯度直方圖(Augmented Histograms of Oriented Gradients (AHOG))於移動式平台上進行多人偵測,在本篇研究中,我們利用人體的幾何特徵來加強方向梯度直方圖(Histograms of Oriented Gradients (HOG))描述人型外觀的能力,其中我們把直立人型中存在的對稱性,每個身體部位的相對距離,以及人型在梯度特徵中的密度分佈加入HOG特徵中,來提升HOG特徵的描述能力,包含了上述人型特徵的HOG在此篇研究稱為AHOG,接著利用串接式AdaBoost演算法建立ㄧ個人型串接式分類器,用來對輸入影像中的可能區域進行偵測,由此人型分類器所決定之區域,則被考慮為人型可能區域,除此之外,利用串接式分類器的架構,可以減少偵測人型的時間;最後人型可能區域會再經由人型輪廓驗證,來確信此區域確實有人型存在,並且減少因為由複雜背景所引發的錯誤訊息,藉此降低錯誤偵測的發生。在此研究實驗中,於多種不同的實驗環境中,都可以提供可靠的人型偵測準確率。 | zh_TW |
dc.description.abstract | In this thesis we introduce an Augmented Histograms of Oriented Gradients (AHOG) feature for human detection from a non-static camera. This research tries to increase the discriminating power of original Histograms of Oriented Gradients (HOG) feature by adding human shape properties, such as contour distances, symmetry, gradient density, and shape approximation. The relations among AHOG features are characterized by the contour distances to the centroid of human. By observing on the biological structure of a human shape, we impose the symmetry property on every HOG feature and compute the similarity between feature itself and its symmetric pair so as to weigh HOG features. After that, the capability of describing human features is greatly improved when being compared with that of traditional one, especially when the moving humans are under consideration. Besides, we also augment the gradient density into AHOG to mitigate the influences caused by repetitive backgrounds. Moreover, we reject the false detections via an elliptical verifier learned when one tries to approximate a human shape. In the experiments, our proposed human detection method demonstrates highly reliable accuracy and provides the comparable performance to the state-of-the-art human detector on different databases. | en |
dc.description.provenance | Made available in DSpace on 2021-05-20T20:38:58Z (GMT). No. of bitstreams: 1 ntu-96-R95922141-1.pdf: 3340683 bytes, checksum: df18e5311edd42ae2baf9e9893a7f8b4 (MD5) Previous issue date: 2007 | en |
dc.description.tableofcontents | 口試委員會審定書 #
致謝 i 中文摘要 ii ABSTRACT iii CONTENTS iv LIST OF FIGURES vii LIST OF TABLES ix Chapter 1 Introduction 1 1.1 Motivation 2 1.2 Challenges of Human Detection 3 1.3 Related Work 8 1.4 Objective 11 1.5 Organization 11 Chapter 2 Preliminaries 13 2.1 Problem Definition 13 2.2 Support Vector Machine (SVM) 14 2.2.1 Objective of SVM 15 2.2.2 Preliminary Knowledge of SVM 16 2.3 AdaBoost Algorithm 18 2.3.1 Objective of AdaBoost Algorithm 19 2.3.2 Preliminary Knowledge of AdaBoost Algorithm 19 2.3.3 Preliminary Knowledge of Cascaded AdaBoost Algorithm 21 2.4 Approach Overview 25 2.5 Summary of Contributions 25 Chapter 3 Human Candidate Detection 27 3.1 Augmented Histograms of Oriented Gradients 27 3.1.1 Feature Type 28 3.1.2 Gradient Computation 31 3.1.3 Symmetry 33 3.1.4 Gradient Density 36 3.1.5 Contour Distance 37 3.1.6 Dominant Orientation Rotation 39 3.1.7 Orientation Histogram Construction 41 3.2 Training 42 3.3 Detection 43 3.3.1 Human Potential Location 43 3.3.2 Classification 44 Chapter 4 Human Candidate Verification 46 4.1 Ellipse Approximation 47 4.1.1 Connected Components 47 4.1.2 Moments 48 4.2 Training & Verification 50 Chapter 5 Experiment 52 5.1 Environment Description 52 5.2 Database 52 5.3 Training 53 5.3.1 Discussion of Training Process 55 5.4 Experiment Results 57 5.4.1 Performance of MIT Database 57 5.4.2 Performance of Our Database 58 Chapter 6 Conclusion 63 References 64 | |
dc.language.iso | en | |
dc.title | 利用單眼視覺之增強性方向梯度直方圖於多人偵測 | zh_TW |
dc.title | Monocular Multi-Human Detection Using Augmented Histograms of Oriented Gradients | en |
dc.type | Thesis | |
dc.date.schoolyear | 96-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 洪一平,蕭培墉,陳祝嵩,黃世勳 | |
dc.subject.keyword | 人型偵測,方向性梯度直方圖,行人偵測, | zh_TW |
dc.subject.keyword | human detection,histograms of oriented gradients,AdaBoost, | en |
dc.relation.page | 64 | |
dc.rights.note | 同意授權(全球公開) | |
dc.date.accepted | 2008-07-28 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
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-96-1.pdf | 3.26 MB | Adobe PDF | 檢視/開啟 |
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。