臺灣博碩士論文加值系統

如何從靜態的影像中偵測出人臉如何從影像中偵測出人臉的位置長久以來

一直是許多人所研究的問題，而動態的影片中來追蹤人臉更是更近一步的研究課

題。人臉偵測追常見的應用在於支援人臉辨識與人臉追蹤。目前人臉辨識多以單

張影像之辨識為主，很少有利用3D立體影像 進行人臉追蹤之研究。然而在人

臉追蹤的研究上，目前大部分的文獻都還只是靜態資料庫上的測試，都還無法有

效地拿來作即時性的應用，其中最大的困難就是不同的網路頻寬。

本論文提出基於可調式影像編碼下的人臉追蹤研究，在我們的系統架構下，整個

系統可以區分成兩個部分：第一個部分是針對可調式影像編碼和解碼的方法，第

二部份是對人臉追蹤的方法。我們希望以可調式影像編碼的方法來減少人臉追蹤

時的資料量，在資料量減少的情形下，不影響辨識的結果以及影像的正確性，因

為資料的減少便能大量縮減人臉辨識追蹤的時間，提高即時影像中人臉追蹤的能

力。為了減少處理資料量，我們使用移動向量(MV)來追蹤。

How is it measure people face to detect in static image, how be a lot of problem

that people study since detect the position that measures the faces of people for a long

time in the image and come to track in the dynamic film the faces of people are

research lesson of nearly one step even more question. To distinguish for main fact

pieces of image, few utilize 3D three-dimensional image carry on people research that

face track. But on the research that tracks in the faces of people, present most

documents are still only the test on static database, also unable to is it make instant

application of to bring effectively, most heavy difficulty different network frequently

wide among them.The paper is based on scalable video coding algorithm to do face

tracking on scalable video, first part we introduce the algorithm of scalable video,

second part is for face tracking method. We hope to reduce the data amount of

processing face tracking, we use motion vector (MV) to make it.

一、 緒論……………………………………………………………………………..1

1.1 研究動機 1

1.2 目前研究現況 1

1.3 章節介紹 1

二、 可調式視訊編碼Scalable video coding………………………………………..3

2.1 可調式視訊編碼流程 3

2.2 時間域小波分解 3

2.2.1 沿著移動軌跡的時間域小波分解..……………………………………… 4

2.2.2 移動線程(Motion Threading)..……………………………………………4

2.2.3 時間輕量化濾波器(Temporal lifting-based filter)..…………………….. .5

2.2.4 輕量化線程(Lifting-based motion-threading)….….……………………...5

2.2.5 多層移動線程(Multi-layer Motion Threading)..………………………….7

2.2.6 關聯式移動評估……………………………..……………………………9

2.2.7 最佳失真率評估準則 …………………………………………………..10

2.3 空間域小波分解(Spatial wavelet decomposition)………………………11

2.4 Entropy Coding…………………………………………………………..12

三、可調性視訊之人臉追蹤………………………………………………………..13

3.1 人臉追蹤系統架構………………………………………………………13

3.1.1 追蹤步驟.………………………………………………………………. .13

3.1.2 可調性視訊人臉追蹤系………………………………………………....13

3.2 人臉追蹤(Face Tracking)………………………………………………..14

3.2.1 初始人臉位置……………………………………………………………14

3.2.2 時間小波解碼追蹤分析…………………………………………………15

3.2.3 空間小波解碼追蹤分析…………………………………………………16

3.2.4 人臉追蹤流程……………………………………………………………17

3.3 人臉追蹤實例說明………………………………………………………18

四、實驗結果與討論………………………………………………………………..20

4.1 實驗架構參數設定 20

4.2 時間調變實驗 21

4.3 空間調變實驗 22

4.4 實驗結果分析 22

五、結論與未來之研究……………………………………………………………..23

1. WenxianYang,Feng Wu,Yan Lu,Jianfei Cai,King Ngi Ngan,Shipeng Li,Scalable Multiview Video Coding Using Wavelet,2005.
2. Xiangyang Ji, Jizheng Xu, Debin Zhao, Feng Wu, "Architectures of incorporating MPEG-4 AVC into three-dimensional wavelet video coding," Picture Coding Symposium, San Francisco, CA, USA, Dec 2004.
3. J.-Z. Xu, S. Li and Y.-Q. Zhang, “Three-dimensional shape-adaptive discrete wavelet transforms for efficient object-based video coding,” to be appeared in Proceedings of SPIE VCIP’2000, Perth, Australia, July, 2000.
4. Lin Luo, Feng Wu, Shipeng Li, Zhenquan Zhuang, and Ya-Qin Zhang, A two-pass optimal motion-threading technique for 3D wavelet video coding, IEEE Intl. Symposium on Circuits and Systems (ISCAS 2002), pp.819-822, Scottsdale, AZ.
5. Lin Luo, Feng Wu, Shipeng Li, and Zhenquan Zhuang, Advanced lifting-based Motion-Threading (MTh) techniques for 3D wavelet video coding, invited paper, to appear in SPIE/IEEE Visual Communications and Image Processing (VCIP2003), Lugano, Switzerland.
6. Lin Luo, Feng Wu, Shipeng Li, and Zhenquan Zhuang, Layer-correlated motion estimation and motion vector coding for the 3D-wavelet video coding, IEEE International Conference on Image Processing (ICIP2003), Barcelona, Spain.
7. Lin Luo, Feng Wu, Shipeng Li, Zixiang Xiong, Zhenquan Zhuang, “Advanced motion threading for 3D wavelet video coding”, Signal Processing: Image Communication, special issue on subband/wavelet video coding, 2004.
8. Wanzeng Kong , Shan`an Zhu ”,A New Method of Single Color Face Detection Based on Skin Model and Gaussian Distribution 2006.
9. Kumar, C. N. Ravi Bindu, A.,An Efficient Skin Illumination Compensation Model for Efficient Face Detection,2006.
10. J. Yang and A. Waibel, “A real-time tracker,” in proc. Of the 3rd IEEE Workshop on Applications of Computer Vision, Dec. 1996,pp.142-147.
11. U. Neumann, I Coben, S You, D. Fidaleo, and K Seo, “Real-time face detection from one camera,” in IMSC and computer science, USC.
12. G. L. Foresti, C. Micheloni, L. Snidaro, and C. Marchiol, “Face detection for visual surveillance,” in Proc. of the 12th IEEE International Conference on Image Analysis and Processing, Sept. 2003, pp. 115-120.
13. R. L. Hsu, M. A. Mottaleb, and A. K. Jain, “Face detection in color images,” IEEE Trans. Pattern Anal. Machine Intell., vol. 24, pp. 696–706, 2002.
14.C. Gareia and M.Delakis, “Convolution face finder: a neural architecture for fast and robust face detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 11, pp. 1408-1423, 2004.
15.M. H. Yang, D. J. Krieguan, and N. Abuja, “Detecting faces in images: a survey,” IEEE Transaction on Pattern Analysis and Machine Intelligence, vol, 24, no. 1, pp. 34-58, Jan 2002.