請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/67133
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 貝蘇章(Soo-Chang Pei) | |
dc.contributor.author | Fang-Yi Chao | en |
dc.contributor.author | 趙芳儀 | zh_TW |
dc.date.accessioned | 2021-06-17T01:20:53Z | - |
dc.date.available | 2017-08-31 | |
dc.date.copyright | 2017-08-31 | |
dc.date.issued | 2016 | |
dc.date.submitted | 2017-08-10 | |
dc.identifier.citation | [1] Ojala, T., Pietikainen, M., Harwood, D.: ‘A comparative study of texture measures with classification based on featured distributions’, Pattern Recognition, 1996, 29, (1), pp. 51–59
[2] Suruliandi A and Ramar K “Local Texture Patterns- A Univariate Texture Model for classification of images”, Advanced computing and communications, 2008 ADCOM International Conference10.1109/ADCOM 2008 Pages 32-39. [3] A. Suruliandi, K. Meena, and R. Reena Rose, “Local binary pattern and its derivatives for face recognition,” ICV, vol. 6, no. 5, pp. 480 –488, sept. 2012. [4] P.Brodatz, Texture – A Photographic Album for Artists and Designers, Reinhold, New York (1968). [5] Ahonen, T., Pietikainen, M.: ‘Face description with local binary pattern: applications to face recognition’, IEEE Trans. Pattern Anal. Mach. Intell.2006, 28, (12), pp. 2037–2041 [6] http://www.Jaffe Face Database [7] C. R. Wren, A. Azarbayejani, T. Darrell, and A. P. Pentland, “Pfinder: Real-time tracking of the human body,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 19, no. 7, pp. 780–785, Jul. 1997. [8] C. Stauffer and W. E. L. Grimson, “Adaptive background mixture models for real-time tracking,” in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2. Jun. 1999. [9] M. Harville, “A framework for high-level feedback to adaptive, per-pixel, mixture-of-Gaussian background models,” in Computer Vision. Berlin, Germany: Springer-Verlag, 2002, pp. 543–560. [10] M. Heikkila and M. Pietikainen, “A texture-based method for modeling the background and detecting moving objects,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, no. 4, pp. 657–662, Apr. 2006. [11] H. Han, J. Zhu, S. Liao, Z. Lei, and S.Z. Li, “Moving object detection revisited: Speed and robustness,” Circuits and Systems for Video Technology, vol. PP, no. 99, pp. 1–1, 2014. [12] S. Liao, G. Zhao, V. Kellokumpu, M. Pietikainen, and S. Z. Li, “Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2010, pp. 1301–1306. [13] L. Li, W. Huang, I. Y. H. Gu, and Q. Tian, “Foreground object detection from videos containing complex background,” in Proc. 11th ACM Int. Conf. Multimedia, 2003, pp. 2–10. [14] K. Toyama, J. Krumm, B. Brumitt, B. Meyers, “Wallflower: Principles and Practice of Background Maintenance”, Proc. 7th IEEE Int. Conf. Computer Vision, 1, 255-261, 1999. [15] Basilio, Jorge Alberto Marcial, ”Explicit Image Detection using YCbCr Space Color Model as Skin Detection,” Mexico City : Escuela Superior de Ingeniería Mecánica y Eléctrica Unidad Culhuacan. [16] D. Chai, and K.N. Ngan, 'Face segmentation using skin-color map in videophone applications'. IEEE Trans. on Circuits and Systems for Video Technology, 9(4): 551-564, June 1999. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/67133 | - |
dc.description.abstract | 局部區域三元化圖型特徵(Local Ternary Pattern)是一種優良的材質描述子,衍伸自局部區域二元化圖型特徵(Local Binary Pattern),最初於材質分類上有非常良好的應用,其優點如光線變化下的穩定性、旋轉不變性,以及運算方便性使它在往後廣泛應用於移動物體偵測、人臉辨識等。藉由結合這些應用,我們提出一個人臉偵測與辨識的保全系統,可以在監視器畫面中擷取到移動的物體並偵測、辨識其人臉。
此篇論文利用尺度不變局部區域三元化圖型特徵(SILTP)做為材質描述子,因為它在燈光變化以及雜訊干擾的情況下,表現更優於原本的局部區域三元化圖型特徵,使得此保全系統可以在動態背景(如樹影搖曳、窗簾擺動、水花四濺)中正確地擷取移動物體。再利用皮膚偵測尋找可能是人臉的區塊進行人臉辨識。由於移動物體偵測及人臉辨識都使用相同的材質描述子,可增加此保全系統的效率。我們實地拍攝測試影片做實驗並分析討論此系統的優缺點。 | zh_TW |
dc.description.abstract | We propose a method to distinguish moving people in surveillance video by moving object detection, skin detection to extract face area then do face recognition. Local Ternary Pattern (LTP), which is a derivative of Local Binary Pattern, is proven to be a strong yet simple texture descriptor because of its good properties on illumination robustness, rotation invariance and simplicity computation. It can be used in a wide variety of applications such as texture classification, moving object detection and face recognition. By integrating these applications which can be completed by the same texture extraction method, we can make a security system efficient and able to distinguish people in surveillance video.
A derivative of LTP, Scale Invariant Local Ternary Pattern (SILTP) are introduced and used in moving object detection and face recognition. The properties of SILTP make it suitable in illumination variation conditions and dynamic background. By integrating SILTP and other image processing techniques in moving object detection, skin detection and face recognition, a simple security system which can distinguish moving people in surveillance videos are designed. Experiments are conducted with self-shooting fixed focal length video. The performance, advantages and disadvantages are also discussed. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T01:20:53Z (GMT). No. of bitstreams: 1 ntu-105-R03942045-1.pdf: 14004010 bytes, checksum: a7520addce5564af4847001dea971047 (MD5) Previous issue date: 2016 | en |
dc.description.tableofcontents | Contents
口試委員會審定書 # 誌謝 i 摘要 ii ABSTRACT iii CONTENTS iv LIST OF FIGURES vi LIST OF TABLES ix Chapter 1 Introduction 1 1.1 Local Binary Pattern and its derivatives Local Ternary Pattern 2 1.1.1 Local Binary Pattern (LBP) 2 1.1.2 Local Ternary Pattern (LTP) 4 1.2 Texture Classification using LTP 10 1.3 LTP on Face Recognition 13 Chapter 2 Moving object detection using LTP in videos 19 2.1 Overall Algorithm 21 2.1.1 Background Modeling 21 2.1.2 Foreground Detection. 30 2.1.3 Parameter Choice. 32 2.2 Improved algorithm 34 2.2.1 Improved Color Information. 34 2.2.2 Morphology. 39 2.2.3 Performance Comparison. 40 Chapter 3 Skin Detection 44 3.1 Algorithm 45 3.1.1 Pixel-Based Methods 45 3.1.2 Morphology 49 3.2 Application in Surveillance Video 50 Chapter 4 Face Recognition using LTP in videos 52 4.1 Algorithm 52 4.2 Application in Surveillance Video 53 Chapter 5 Conclusions and Future Work 61 REFERENCE 62 | |
dc.language.iso | en | |
dc.title | 局部區域三元化圖型特徵用於移動物件追蹤與辨認 | zh_TW |
dc.title | Moving Object Detection and Recognition using Local Ternary Pattern in Surveillance Video | en |
dc.type | Thesis | |
dc.date.schoolyear | 105-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 林康平(Kang-Ping Lin),吳家麟(Ja-Ling Wu),鍾國亮(Kuo-Liang Chung) | |
dc.subject.keyword | 局部區域三元化圖型特徵,局部區域二值模式,移動物件偵測,動態背景模型,人臉辨識,保全系統, | zh_TW |
dc.subject.keyword | Local Ternary Pattern,Local Binary Pattern,Moving Object Detection,Dynamic Background Modeling,Face Recognition,Surveillance System, | en |
dc.relation.page | 63 | |
dc.identifier.doi | 10.6342/NTU201702825 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2017-08-11 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電信工程學研究所 | zh_TW |
顯示於系所單位: | 電信工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-105-1.pdf 目前未授權公開取用 | 13.68 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。