透過您的圖書館登入
IP:3.136.18.247
  • 學位論文

利用流形學習與隱藏式馬可夫模型做步態分析用以鑑別身分

Gait Analysis for Human Identification through Manifold Learning and HMM

指導教授 : 黃仲陵

摘要


視覺監控系統可以被應用在許多場合,如機場、銀行、學校等,運用電腦視覺的技術,可以幫助使用者分析一些行為。視覺監控系統的目的是希望能夠分析,分類且進一步達到辨識觀測物體功能,尤其是在911攻擊後,有許多研究是有關於視覺監控系統。遠距離的身分鑑別系統在近年來也吸引人們許多注意。步態辨識是利用每個人的獨特走路方式來進行身鑑別。與其它人體生物特徵相比,萃取人的步伐不需要太精密的攝影設備,而且人的步伐提供我們可以在較遠的距離下進行身份辨識,這點是其他生物特徵無法提供的,而且也不需要使用者的互動,讓辨識的過程更簡單與方便。本篇論文提出了一個利用步伐剪影來實現路徑及身份的多重辨識用系統,首先目標物的路徑方向會先被偵測出,之後再對目標物進行身份辨識。我們會利用機率模型將前景與背景做分割,產生出乾淨的剪影。由於步伐動作是一種非線性的行為,所以我們也會利用一些例子說明非線性降維方法處理後的效果比線性佳。步伐剪影被非線性的轉換到維度較低空間並利用高斯機率對低維度空間分類,而在時間上步伐剪影的變化也會對印在低維度空間上高斯機率的轉移,因此我們可以利用隱藏式馬可夫模型來幫助我們進行訓練與身份辨識,實驗結果顯示所提出的系統架構可以有效率的鑑別身份。

並列摘要


With the increasing demands of visual surveillance systems, human identification at a distance has recently gained more interest. Gait recognition is a process of identifying individuals by the way they walk, which is often used as a unobstrusive biometric offering the possibility to identify people at a distance without any interaction or co-operation with the subject. This thesis has presents a novel effectively method for both automatic viewpoint and person identification using only the silhouette sequence of gait. The gait silhouettes are nonlinearly transformed into low dimensional embedding and the dynamics in time-series images are modeled by HMM in the corresponding embedding space. The experimental results will demonstrate that the proposed algorithm is an encouraging progress for the research of human identification.

並列關鍵字

MANIFOLD ISOMAP HMM GP-LVM

參考文獻


1) T. Horprasert, D. Harwood, and L. S. Davis, “A robust background subtraction and shadow detection”, 4th Asian Conf. on Computer Vision, Taipei, Taiwan, pp. 983-988, 2000.
2) Elgammal, A., Duraiswami, R., Harwood, D., and Davis, L.S. “Background and Foreground Modeling Using Nonparametric Kernel Density Estimation for Visual Surveillance”, Proc. of the IEEE, vol. 90, 2002.
3) Liang Wang, Huazhong Ning, Tieniu Tan and Weiming Hu, “Fusion of static and dynamic body biometrics for gait recognition”, Proc. of the NinthIEEE Int. Conf. On Computer Vision, pp.1449-1454, 2003.
6) P. J. Phillips, S. Sarkar, I. Robledo, P. Grother, and K. W. Bowyer, . “The gait identification challenge problem: Data sets and baseline algorithm”,. in International Conference on Pattern Recognition, August 2002.
8) C. BenAbdelkader, R. Culter, H. Nanda, and L. Davis, “EigenGait: Motion-Based Recognition of People Using Image Self-Similarity,” Proc. Int’l Conf. Audio- and Video-Based Biometric Person Authentication, pp. 284-294, 2001.

延伸閱讀