臺灣博碩士論文加值系統

本論文提出一個在視覺上新穎的即時偵測跌倒系統，我們這個系統能夠支援於各種攝影機視角的擺設，突破單一環境的限制。該系統的演算法藉由人體形狀與自然線索兩大特徵去區分跌倒與非跌倒的事件，並且有很高的準確率。對於人體形狀的分析上，我們提出一個利用影子來估測人體高度的方法，同時也結合HOG特徵以及行為能力特徵來加強整個系統的偵測能力。最後利用支援向量機(SVM)來做特徵的訓練以及串接式的分類來辨別跌倒行為。系統執行的結果是有效的應用在鳥瞰視角與一般視角，而我們的實驗結果也證明該系統可達到很高的偵測率及很低的計算量。

We present a novel real-time video-based human fall detection system in this thesis. Because the system is based on a combination of shadow-based features and various human postures, it can distinguish between fall-down and fall-like incidents with a high degree of accuracy. To support effective operation in different viewpoints, we propose a new feature called virtual height that can estimate the body height without 3D model reconstruction. As a result, the model is low computational complexity. Our experiment results demonstrate that the proposed system can achieve a high detection rate and a low false alarm rate.

目錄
中文摘要
英文摘要
誌謝
圖目錄
表目錄
第一章 緒論………………………………………………………………………….. 1
1.1 目標……………………………………………………………………………2
1.2 貢獻……………………………………………………………………………2
1.3 系統架構………………………………………………………………………3
1.4 論文架構………………………………………………………………………3
第二章 相關工作……………………………………………………………………...4
2.1 跌倒偵測相關研究……………………………………………………………4
第三章 背景模型與影子偵測……………………………………………………….. 7
3.1 排除前景像素…………………………………………………………………8
3.2 建立背景模型與影子偵測……………………………………………………9
第四章 強健式之新穎的跌倒偵測演算法………………………………………….12
4.1 演算法架構…………………………………………………………………..12
4.2 影像前處理…………………………………………………………………..14
4.2.1連通物件演算法…………………………………………………………..14
4.2.2雜訊的移除………………………………………………………………..16
4.2.3物件追蹤…………………………………………………………………..17
4.3 跌倒行為的特徵研究………………………………………………………..18
4.3.1 虛擬高度………………………………………………………………….18
4.3.2 方向性梯度直方圖統計………………………………………………….22
4.3.3 行為能力………………………………………………………………….23
4.4 串接式分類器………………………………………………………………..25
第五章 實驗結果…………………………………………………………………….27
5.1 實驗數據與比較……………………………………………………………..27
5.1.1 一般視角拍攝於戶外環境……………………………………………….29
5.1.2鳥瞰視角拍攝於廣場……………………………………………………..30
5.1.3 一般視角拍攝於實驗室………………………………………………….31
5.1.4 ETHZ影片集合…………………………………………………………...33
5.1.5 Shoaib影片集合…………………………………………………………..35
5.2 比較跌倒偵測應用於不同環境與執行時間………………………………..36
5.3 於不同照度下虛擬高度與姿勢的關係……………………………………..38
5.3.1一般環境在照度為300拉克斯下………………………………………..39
5.3.2極亮環境在照度為2500拉克斯下……………………………………….40
5.3.3極暗環境在照度為50拉克斯下………………………………………….41
第六章 結論………………………………………………………………………....42
參考文獻……………………………………………………………………………..43

[1] J. Tiao, M. Turjo, M. Wong, M. Wang and Y. Tan, “Fall Incidents
Detection for Intelligent Video Surveillance,” In Proc. of the 15th International Conference On Communications and Signal Processing,
pp.1590 – 1594, 2005
[2] V. Vishwakarma, C. Mandal, and S. Sural, ”Automatic Detection of Human Fall in Video, "In Proc. of International Conference on Pattern Recognition and Machine Intelligent , Lecture Notes in Computer
Science, pp.612 – 613, 2007
[3] T. Zhang, J. Wang , and L. Xu , ”Using Wearable Sensor and NMF
Algorithm to Realize Ambulatory Fall Detection," In Proc. of International Conference on Advances in Natural Computation, Lecture
Notes in Computer Science, Vol. 4222 , pp.488 – 491, 2006
[4] B. T oreyin, Y. Dedeoglu, and A. C, etin, “HMM-based Falling Person
Detection Using Both Audio and Video," In Proc. of IEEE International workshop on human-computer interaction 2005.
[5] J. W. Hsieh, Y. T. Hsu, H. Y. Liao and C. C. Chen, Chih-Chiang Chen, ”Video-based Human Movement Analysis and Its Application to Surveillance Systems," IEEE Transactions on Multimedia, Vol.10, No.
3, pp. 372 – 392, 2008
[6] 江龍興，”運用輪廓分析對人行為模式辨識之研究” 國立台灣科技
大學電子工程研究所，碩士論文，2010。
[7] D. Anderson, R. H. Luke, J.M. Keller,M. Skubic, M. Rantz, and M. Aud,
“Linguistic summarization of video for fall detection using voxel person
and fuzzy logic,” Comput. Vision Image Understanding, vol. 113, pp. 80 – 89, 2008.
[8] C. Meunier, J. St-Arnaud, A. Rousseau, J. Rougier, ”Fall Detection from Human Shape and Motion History Using Video Surveillance," In Proc. of the 21st International Conference on Advanced Information Networking and Applications Workshops, pp. 875 – 880, 2007.
[9] T. Horprasert, D. Harwood, and L. Davis, “A Statistical Approach for Real-Time Robust Background Subtraction and Shadow Detection.” In Proc. of IEEE International Conference on Computer Vision,
Frame-Rate Workshop, pp 1 – 19, 1999.
43
[10] A. Prati, I. Mikic, M. Trivedi, and R. Cucchiara, “Detecting moving shadows: algorithms and evaluation," IEEE Transactions on Pattern Analysis and Maching Intelligence 25, pp. 918 – 923, July 2003.
[11] N. Dalal and B. Triggs, “Histograms of oriented gradients for human
detection”, IEEE Computer Society Conference on Computer Vision and
Pattern Recognition, Vol. 1, pp. 886 – 893, 2005.
[12] A. F. Bobick and J. W. Davis, ”The Recognition of Human Movement Using Temporal Template," IEEE Transactions on Pattern Analysis and
Machine Intelligence, Vol. 23, No. 3, pp. 257 – 267, 2001.
[13] G. Bradski and A. Kaehler, Learning OpenCV: Computer Vision with OpenCV Library, O’Reilly Media, Inc., Sebastopol, CA, USA. 2008.
[14] An available dataset http://www.tnt.uni-hannover.de/~shoaib/fall.html
[15] EZTH dataset http://www.vision.ee.ethz.ch/~fnater/unsupHBA/index.html
[16] Pratt Willam, Digital Image Processing, 4th ed., John Wiley and Sons, Ltd., New York, USA, 2007.