請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/63720
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 傅立成(Li-Chen Fu) | |
dc.contributor.author | Yi-Shu Lee | en |
dc.contributor.author | 李依書 | zh_TW |
dc.date.accessioned | 2021-06-16T17:17:12Z | - |
dc.date.available | 2017-08-20 | |
dc.date.copyright | 2012-08-20 | |
dc.date.issued | 2012 | |
dc.date.submitted | 2012-08-17 | |
dc.identifier.citation | [1] N. Dalal and B. Triggs, 'Histograms of Oriented Gradients for Human Detection,' in IEEE Conference on Computer Vision and Patter Recognition, p. 886~893, 2005.
[2] Q. Zhu, M.-C. Yeh, K.-T. Cheng, and S. Avidan, 'Fast Human Detection Using a Cascade of Histograms of Oriented Gradients,' in IEEE Conference on Computer Vision and Pattern Recognition, pp. 1491-1498, 2006. [3] J. Li, W. Gong, J. Yang, and W. Li, 'Intensity-Distance Projection Space Based Human Tracking in Far-Infrared Image Sequences,' in WRI World Congress on Computer Science and Information Engineering, pp. 371-375, 2009. [4] M. Bertozzi, A. Broggi, M. Felisa, S. Ghidoni, P. Grisleri, G. Vezzoni, C. H. Gómez, and M. D. Rose, 'Multi Stereo-Based Pedestrian Detection by Daylight and Far-Infrared Cameras,' in Augmented Vision Perception in Infrared, pp. 371-401, 2009. [5] R. O'Malley, M. Glavin, and E. Jones, 'A Review of Automotive Infrared Pedestrian Detection Techniques,' Signals and Systems Conference, pp. 168-173, 2008. [6] F. Xu, X. Liu, and F. K., 'Pedestrian Detection and Tracking with Night Vision,' IEEE Transactions on Intelligent Transportation Systems, vol. 6, pp. 63-71, 2005. [7] D. Olmeda, A. de la Escalera, and J. M. Armingol, 'Contrast Invariant Features for Human Detection in Far Infrared Images,' in Intelligent Vehicles Symposium (IV), 2012 IEEE, pp. 117-122, 2012. [8] M. Bertozzi, A. Broggi, S. Ghidoni, and M. M. Meinecke, 'A Night Vision Module for the Detection of Distant Pedestrians,' in IEEE Intelligent Vehicles Symposium, pp. 25-30, 2007. [9] M. Bertozzi, A. Broggi, A. Fascioli, T. Graf, and M. M. Meinecke, 'Pedestrian Detection for Driver Assistance using Multiresolution Infrared Vision,' IEEE Transactions on Vehicular Technology, vol. 53, pp. 1666-1678, 2004. [10] B. M., B. A., G. P., G. T., and M. M., 'Pedestrian Detection in Infrared Images,' in IEEE Intelligent Vehicles Symposium, pp. 662-667, 2003. [11] A. Broggi, A. Fascioli, M. Carletti, T. Graf, and M. Meinecke, 'A Multi-resolution Approach for Infrared Vision-based Pedestrian Detection,' in IEEE Intelligent Vehicles Symposium, pp. 7-12, 2004. [12] Y. Chen and C. Han, 'Night-time Pedestrian Detection by Visual-infrared Video Fusion,' in Intelligent Control and Automation, pp. 5079-5084, 2008. [13] R. Arndt, R. Schweiger, W. Ritter, D. Paulus, and O. Lohlein, 'Detection and Tracking of Multiple Pedestrians in Automotive Applications,' in IEEE Intelligent Vehicles Symposium, pp. 13-18, 2007. [14] M. Soga, S. Hiratsuka, H. Fukamachi, and Y. Ninomiya, 'Pedestrian Detection for a Near Infrared Imaging System,' in IEEE Conference on Intelligent Transportation Systems, pp. 1167-1172, 2008. [15] J. Ge, Y. Luo, and G. Tei, 'Real-Time Pedestrian Detection and Tracking at Nighttime for Driver-Assistance Systems,' IEEE Transactions on Intelligent Transportation Systems, vol. 10, pp. 283-298, 2009. [16] T. Kancharla, P. Kharade, S. Gindi, K. Kutty, and V. G. Vaidya, 'Edge Based Segmentation for Pedestrian Detection using NIR Camera,' in Image Information Processing (ICIIP), 2011 International Conference on, pp. 1-6, 2011. [17] M. Krystian, S. Cordelia, and Z. Andrew, 'Human Detection based on a Probabilistic Assembly of Robust Part Detectors,' in European Conference on Computer Vision, pp. 69-81, 2004. [18] 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. [19] Y.-T. Chen, C.-S. Chen, Y.-P. Hung, and K.-Y. Chang, 'Multi-Class Multi-Instance Boosting for Part-Based Human Detection,' in IEEE International Conference on Computer Vision Workshops, pp. 1177-1184, 2009. [20] P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan, 'Object Detection with Discriminatively Trained Part-Based Models,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, pp. 1627-1645, 2010. [21] L. Zhe and L. S. Davis, 'Shape-Based Human Detection and Segmentation via Hierarchical Part-Template Matching,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, pp. 604-618, 2010. [22] L. Bourdev, S. Maji, T. Brox, and J. Malik, 'Detecting People Using Mutually Consistent Poselet Activations,' in European Conference on Computer Vision, pp. 168-181, 2010. [23] L. Bourdev and J. Malik, 'Poselets: Body Part Detectors Trained using 3D Human Pose Annotations,' in IEEE International Conference on Computer Vision, pp. 1365-1372, 2009. [24] D. Geronimo, A. M. Lopez, A. D. Sappa, and T. Graf, 'Survey of Pedestrian Detection for Advanced Driver Assistance Systems,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, pp. 1239-1258, 2010. [25] V. N. Vapnik, The nature of statistical learning theory: Springer-Verlag New York, Inc., 1995. [26] R. Dechter, Constraint Processing: Morgan Kaufmann, 2003. [27] I. B. Vapnyarskii, Lagrange multipliers: Springer, 2001. [28] S. P. Boyd and L. Vandenberghe. (2004). Convex Optimization. [29] J. Nocedal and S. J. Wright, Numerical Optimization (2nd ed.): Springer, 2006. [30] Y.-C. Lin, Y.-M. Chan, L.-C. Chuang, L.-C. Fu, S.-S. Huang, P.-Y. Hsiao, and M.-F. Luo, 'Near-Infrared Based Nighttime Pedestrian Detection by Combining Multiple Features,' in IEEE Conference on Intelligent Transportation Systems, pp. 1549-1554, 2011. [31] J. C. Gower and G. B. Dijksterhuis, Procrustes Problems: Oxford University Press, 2004. [32] I. Borg and P. J. F. Groenen, Modern Multidimensional Scaling Theory and Applications: Springer, 2005. [33] G. Borgefors, 'Hierarchical Chamfer Matching: A Parametric Edge Matching Algorithm,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 10, pp. 849-865, 1988. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/63720 | - |
dc.description.abstract | 在智慧型運輸系統領域中,行人偵測是一個重要的議題。由於行人並非光源體,在夜間黑暗的環境下,駕駛者更不容易注意到行人,使得夜間行人偵測對於幫助偵測行人以協助駕駛的視覺系統是十分關鍵的。因此,本論文提出一個在移動式車輛上使用之基於近紅外線光源的夜間行人偵測方法,在近紅外線影像中會顯示輻射近紅外線以及反射經由近紅外線投射燈投出的紅外線的區域。但在某些情況下,行人身上衣物的材質會吸收大部分投射在身上的紅外線,造成這個行人部分區域無法在紅外線影像中顯示。為了解決這類的議題,我們提出了一種部分式的行人偵測方法,根據在人身上標記的關鍵點將行人分成許多部份。由於計算負荷量太高,有效部分的選擇成為當務之急。本研究中首先收集了大量的夜間影片,然後分析偵測率/處理時間和不同數量/類型的部分之間的關係。此外,系統將會學習任兩個部分間的空間關係。藉由這些空間資訊,即使遇偵測的行人部分被遮蔽或者正反左右偵測錯誤,還是可以強化對偵測到的行人部分的信心。在偵測步驟之後我們試著去精鍊其結果,進而提出一種基於塊的分割方法,採用穩健的局部門檻值的方法和兩種過濾器,來驗證行人的偵測框。由實驗可證明,此系統有著令人滿意的結果。 | zh_TW |
dc.description.abstract | Pedestrian detection is an important issue in the intelligent transportation system field. Since the pedestrian is not an apparent object at nighttime, it is more critical for the vision system to help detecting the pedestrian for assisting driving. Accordingly, this thesis proposes a nighttime pedestrian detection method for a moving vehicle equipped with a camera and the near-infrared lighting. The objects in the nighttime environment will reflect the infrared projected by our emitted spotlight. In some cases, however, the clothes on the pedestrian will absorb most of the infrared and make the pedestrian partially invisible in that part. To deal with this, a part-based pedestrian detection method which divides pedestrian into many parts according to the key points marked on them is used. Due to high computation load, selection of effective parts becomes imperative. In this research work, we first collect a large number of nighttime videos and then analyze the relations between the detection rate/ processing time and different numbers/types of parts. Besides, we will learn the spatial relationship between every pair of two parts. By using this spatial information, we can enhance the confidence of the detected parts even if some parts are occluded or are same types but with different opposite body part. While trying to refine pedestrians after detection, we propose a block-based segmentation method which uses robust local thresholding approach and two filters to verify the bounding boxes. The proposed system is verified by experiments and appealing results have been demonstrated. | en |
dc.description.provenance | Made available in DSpace on 2021-06-16T17:17:12Z (GMT). No. of bitstreams: 1 ntu-101-R99922131-1.pdf: 3050886 bytes, checksum: 96562c70c6334c7c3b148a4b5e074ba4 (MD5) Previous issue date: 2012 | en |
dc.description.tableofcontents | 口試委員會審定書 #
誌謝 i 中文摘要 iii ABSTRACT iv CONTENTS v LIST OF FIGURES viii LIST OF TABLES xii Chapter 1 Introduction 1 1.1 Motivation 2 1.2 Challenges 3 1.3 Related Work 6 1.4 Contributions 11 1.5 Thesis Organization 12 Chapter 2 Preliminaries 13 2.1 Problem Definition 13 2.2 Histogram of Oriented Gradients (HOG) Feature 15 2.3 Support Vector Machine (SVM) 17 2.3.1 Objective of SVM 17 2.3.2 Overview of SVM 18 2.4 System Overview 21 Chapter 3 Near-Infrared Part based Classifier Construction 23 3.1 Near-Infrared Part Generation 24 3.1.1 Training Dataset with Concise Keypoints Annotation 24 3.1.2 Strong and Rich Informative Part Candidate Generation 27 3.2 Part Classifier Construction and Selection 29 3.2.1 Classifier Construction and Improving 30 3.2.2 Part Classifier Sorting, Grouping and Selection 30 3.3 Exploiting Relationship among Parts and Clustering Parts 36 3.3.1 Position Relation Model Construction 37 3.3.2 Grouping Parts by Their Spatial Relation 40 Chapter 4 Near-Infrared based Nighttime Pedestrian Detection 43 4.1 Preprocessing 44 4.2 Part Matching and Grouping 47 4.3 Bounding Box Refinement 49 4.3.1 Road Area Filter 50 4.3.2 Block Based Segmentation 52 4.3.3 Final Detection Bounding Box 54 Chapter 5 Experimental Results 57 5.1 Environment Description 57 5.2 Video Database 58 5.3 Part Performance Analysis 61 5.4 Detection Result and Performance Evaluation 63 5.4.1 Evaluation Method 63 5.4.2 Detection Result 64 Chapter 6 Conclusion 68 NOMENCLATU 69 References 71 | |
dc.language.iso | en | |
dc.title | 使用分組式部分模型之基於近紅外線夜間行人偵測 | zh_TW |
dc.title | Near-Infrared Based Nighttime Pedestrian Detection Using Grouped Part Models | en |
dc.type | Thesis | |
dc.date.schoolyear | 100-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 蕭培墉(Pei-Yung Hsiao) | |
dc.contributor.oralexamcommittee | 傅楸善(Chiou-Shann Fuh),方瓊瑤(Chiung-Yao Fang),黃世勳(Shih-Shinh Huang) | |
dc.subject.keyword | 行人偵測,夜間,近紅外線,幾何資訊,空間關係,基於片段,方向梯度直方圖, | zh_TW |
dc.subject.keyword | pedestrian detection,nighttime,near-infrared,geometric information,spatial relationship,part-based,HOG, | en |
dc.relation.page | 74 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2012-08-18 | |
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-101-1.pdf 目前未授權公開取用 | 2.98 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。