臺灣博碩士論文加值系統

前景偵測能有效從背景中分辨前景物件包含移動或靜態是動態影像分析與監控是重要的。
而人臉是屬於立體非鋼性物體，會因不同的動作姿勢、視角與光線角度，造成特徵萃取的改變，進而造成人臉偵測非常困難與複雜，而GMM可以有效的偵測這些局部的變形物件，此技術可用於居家安全系統，例如行車安全監控，GMM特徵及偵測物件的過程中，因有太多雜訊的運算，以致造成無法即時的偵測到物件，所以在行車安全輔助系統會造成隱憂。本論文主要目的為提出一個嶄新的方法，來增加HRV的偵測效能，偵測物件過程中，HRV使用大量的運算，將在進行運算前，先使用背景減法及更深入的YCbCr膚色區間來過濾不必要計算的區域，縮小範圍而來達到加速目的，而過濾的方式需要準確，否則會刪到重要的影像資料。

Foreground detection methods can be applied to efficiently distinguish foreground objects including moving or static objects from background which is very important in the application of video analysis, especially video surveillance.
It is difficult to do feature extraction from targets with different postures of non-rigid objects and varying viewpoints in a simple formula. Face detection is one of the most effective algorithm to detect face, and it can be used in HRV camera system such as home security system. Despite its high accuracy, it is hard to achieve real-time detection because massive noise and calculation is required. It could be a critical issue for the HRV system which needs real-time detection. This thesis provides a method to improve the performance of HRV. Our method uses background subtraction and further improve YCbCr region color constraints to reduce the unnecessary computation and achieve acceleration and then retain the accuracy of Heartrate detection.
The proposed image processing technology can be implemented in HRV system of Heartrate recorder to improve the home and outdoors safety dramatically. We also expect it to be applied to embedded system

摘 要 I
ABSTRACT II
ACKNOWLEDGMENTS III
TABLE OF CONTENTS IV
LIST OF FIGURES VI
LIST OF TABLES VII
CHAPTER 1 INTRODUCTION 1
1.1 MOTIVATION 1
1.2 RELATED WORK 2
1.3 PURPOSE AND METHODS 9
1.4 FRAMEWORK 11
CHAPTER 2 RESEARCH FRAMEWORK 12
CHAPTER 3 BACKGROUND KNOWLEDGE 13
3.1 ONLINE MOG-LRMF 13
3.2 YCBCR COLOR MODEL 14
3.3 PRINCIPAL COMPONENT ANALYSIS 15
3.4 BACKGROUND SUBTRACTION 16
3.5 HEART RATE VARIABILITY 17
3.6 GMM (GAUSSIAN MIXTURE MODEL) 20
CHAPTER 4 HRV AMELIORATION METHODS 25
4.1 GMM FEATURE FILTER 27
4.2 YCBCR CHANNEL TRACKER 27
CHAPTER 5 EXPERIMENTAL RESULTS AND DATA 30
5.1 EXPERIMENTAL CONDITIONS 30
5.2 TESTING DATA 31
5.3 EXPERIMENTAL RESULTS 33
5.4 EXPERIMENTAL DATA 35
CHAPTER 6 CONCLUSION 39
REFERENCES 41

[1] Y Xu, J Dong, B Zhang,, and D Xu, “Background modeling methods in video analysis: A review and comparative evaluation,” CAAI Transactions on Intelligence Technology, 2016 – Elsevier
[2] H Yong, D Meng, W Zuo and L Zhang, " Robust online matrix factorization for dynamic background subtraction," IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017 - ieeexplore.ieee.org.
[3] Y Xie, S Gu, Y Liu, W Zuo, W Zhang, and L Zhang, " Weighted nSchatte p-Norm Minimization for Image Denoising and Background Subtraction," IEEE Transactions on Image Processing, 2016 - ieeexplore.ieee.org.
[4] SY Chiu, CC Chiu and S Xu, " A Background Subtraction Algorithm in Complex Environments Based on Category Entropy Analysis," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 8, pp. 1532-1545, 2014.
[5] M Chen, X Wei, Q Yang, Q Li, G Wang and MH Yang, “Spatiotemporal GMM for background subtraction with superpixel hierarchy”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017 - ieeexplore.ieee.org.
[6] L Yu, T Yang, and AB Chan, “Density-Preserving Hierarchical EM Algorithm: Simplifying Gaussian Mixture Models for Approximate Inference”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018 - ieeexplore.ieee.org
[7] MR Mahmoodi, " High performance novel skin segmentation algorithm for images with complex background." arXiv preprint arXiv:1701.05588, 2017 - arxiv.org.
[8] Z Zhao, Y Shkolnisky, and A Singer, “algorithm that performs principal component analysis (PCA) efficiently and accurately”, IEEE Transactions on Computational Imaging, 2016 - ieeexplore.ieee.org
[9] T Elgamal, M Yabandeh, A Aboulnaga, W Mustafa, and M Hefeeda, "spca: Scalable principal component analysis for big data on distributed platforms." Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, 2015 - dl.acm.org.
[10] F Saxen, and A Al-Hamadi, " Color-based skin segmentation: An evaluation of the state of the art," 2014 IEEE International Conference on Image Processing (ICIP), 2014 - ieeexplore.ieee.org.
[11] S. Kolkur, D. Kalbande, P. Shimpi, C. Bapat, and J. Jatakia, “Human skin detection using RGB, HSV and YCbCr color models”, arxiv preprint arxiv journal, 2017 - arxiv.org
[12] KB Shaik, P Ganesan, V Kalist, BS Sathish, and JMM Jenitha. Gool, “Comparative study of skin color detection and segmentation in HSV and YCbCr color space”, Procedia Computer Science Volume 57, 2015, Pages 41-48, 2015 – Elsevier
[13] F Shaffer, and JP Ginsberg, “An overview of heart rate variability metrics and norms”, Frontiers in public health, 2017frontiersin.org
[14] X Li, J Chen, G Zhao, and M Pietikainen, " Remote Heart Rate Measurement From Face Videos Under Realistic Situations," Proc. of IEEE Int. Conf. on Computer.
[15] A Lam, and Y Kuno, “Robust heart rate measurement from video using select random patches”, Proceedings of the IEEE International Conference …, 2015 - cv-foundation.org
[16] JZ Pong, S Fook-Chong, ZX Koh, MI Samsudin, T Tagami, and CJ Chiew, " Combining Heart Rate Variability with Disease Severity Score Variables for Mortality Risk Stratification in Septic Patients Presenting at the Emergency Department," International Journal of Environmental Research and Public Health, Volume 16 (2019), 2019 - mdpi.com.
[17] HM Stauss, " Heart rate variability: just a surrogate for mean heart rate?," 2014 - Am Heart Assoc.
[18] G Ernst, “Heart-Rate variability—More than Heart Beats?”, Frontiers in public health, 2017 - frontiersin.org
[19] BW Johnston, R Barrett-Jolley, A Krige, and ID Welters, “Heart rate variability: Measurement and emerging use in critical care medicine”, Journal of the Intensive Care Society - journals.sagepub.com
[20] Y Wu, J Lim, and MH Yang, " Object tracking benchmark," IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015 - ieeexplore.ieee.org.
[21] Q Wang, L Zhang, L Bertinetto, W Hu, and PHS Torr, " Fast online object tracking and segmentation: A unifying approach," Proceedings of the IEEE, 2019 - openaccess.thecvf.com.