請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/62606完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 傅楸善(Chiou-Shann Fuh) | |
| dc.contributor.author | Yi Hsiao | en |
| dc.contributor.author | 蕭翊 | zh_TW |
| dc.date.accessioned | 2021-06-16T16:05:28Z | - |
| dc.date.available | 2014-07-11 | |
| dc.date.copyright | 2013-07-11 | |
| dc.date.issued | 2013 | |
| dc.date.submitted | 2013-06-20 | |
| dc.identifier.citation | [1] J. Begard, N. Allezard, and P. Sayd, “Real-Time Human Detection in Urban Scenes: Local Descriptors and Classifiers Selection with AdaBoost-like Algorithms,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Anchorage, AK, pp. 1–8, 2008.
[2] Z. Lin, G. Hua, L. S. Davis, and C. Park, “Multi-Scale Shared Features for Cascade Object Detection,” in Proceedings of IEEE International Conference on Image Processing, Orlando, FL, pp. 1865–1868, 2012. [3] D. Mitzel, P. Sudowe, and B. Leibe, “Real-Time Multi-Person Tracking with Time-Constrained Detection,” in Proceedings of the British Machine Vision Conference, Dundee, Scotland, UK, pp. 104.1–104.11, 2011. [4] Papago, Inc, “Papago P3,” http://www.papago.com.tw/products/Product P3.aspx, 2012. [5] K. C. Peng, “Pedestrian Detection and Range Estimation Based on CENTRIST Descriptor and Implementation,” Master Thesis, Department of Computer Science and Information Engineering, National Taiwan University, 2011. [6] M. Souded and F. Bremond, “Optimized Cascade of Classifiers for People Detection Using Covariance Features,” in Proceedings of International Conference on Computer Vision Theory and Applications, Barcelona, Espagne, pp. 1–7, 2013. [7] P. Viola and M. Jones, “Robust Real-Time Object Detection,” International Journal of Computer Vision, vol. 57, no. 2, pp. 137–154, 2002. [8] Volvo, “World Unique Pedestrian Detection in Action,” http://youtu.be/9fVWB1I9a08, 2010. [9] Wikipedia, “Poisson Process,” http://en.wikipedia.org/wiki/Poisson process, 2010. [10] J. Wu and J. M. Rehg, “Real-Time Human Detection Using Contour Cues,” in Proceedings of IEEE International Conference on Robotics and Automation, Shanghai, China, pp. 0–7, 2011. [11] R. Xu, J. Jiao, B. Zhang, and Q. Ye, “Pedestrian Detection in Images via Cascaded L1-Norm Minimization Learning Method,” Pattern Recognition, vol. 45, no. 7, pp.2573–2583, 2012. [12] R. Zabih and J. Wood, “Non-Parametric Local Transforms for Computing Visual Correspondence,” in Proceedings of European Conference on Computer Vision, Stockholm, Sweden, pp. 151–158, 1994. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/62606 | - |
| dc.description.abstract | A method of pedestrian detection based on CENTRIST descriptor and stochastic process is proposed in this thesis. In related work such as C4 and Peng’s method, they use only single image as input, regardless driving is a continuous process. In our work, we will use sequential data and use stochastic process to help determine the possibility of pedestrian appearance. We use the training set cut from our own database built by driving recorder Papago P3 to train SVM models to be our basic object detector. Our experimental results show that our method outperforms C4 and Peng’s method in execution time and comparable accuracy by applying stochastic determination. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-16T16:05:28Z (GMT). No. of bitstreams: 1 ntu-102-R00944030-1.pdf: 4430615 bytes, checksum: 5cc3a7be6cda951797a9ecced737e0a3 (MD5) Previous issue date: 2013 | en |
| dc.description.tableofcontents | Acknowledgments iii
Abstract iv List of Tables vi List of Figures viii Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Objectives and Contributions 2 1.3 Thesis Organization 2 Chapter 2 Background and Related Work 3 2.1 Background 3 2.1.1 Census Transform Histogram 3 2.1.2 C4 Human Detection Method 7 2.1.3 Peng’s Method 8 2.1.4 Poisson Process 11 2.2 RelatedWork 15 Chapter 3 System Model and Methodology 18 3.1 System Overview 18 3.2 Stochastic Determination 20 3.3 Post-processing 22 3.3.1 Non-Maximal Suppression (NMS) 24 3.3.2 Repetition around Real Human Figure 26 3.3.3 SVM Bias Adjustment 26 3.4 ROI Tracking 30 Chapter 4 Experimental Results 32 Chapter 5 Conclusion and FutureWork 51 References 52 | |
| dc.language.iso | en | |
| dc.subject | 行人偵測 | zh_TW |
| dc.subject | 隨機過程 | zh_TW |
| dc.subject | CENTRIST特徵 | zh_TW |
| dc.subject | stochastic process | en |
| dc.subject | Pedestrian detection | en |
| dc.subject | CENTRIST descriptor | en |
| dc.title | 基於CENTRIST特徵和隨機過程實現行人偵測 | zh_TW |
| dc.title | Pedestrian Detection Based on CENTRIST Descriptor and Stochastic Process and Implementation | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 101-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 蔣迪豪(Ti-Hao Chiang),張振龍(Bert Chang) | |
| dc.subject.keyword | 行人偵測,CENTRIST特徵,隨機過程, | zh_TW |
| dc.subject.keyword | Pedestrian detection,CENTRIST descriptor,stochastic process, | en |
| dc.relation.page | 53 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2013-06-21 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
| 顯示於系所單位： | 資訊網路與多媒體研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-102-1.pdf 未授權公開取用 | 4.33 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。