近年來，在電腦視覺方面，人體參數的偵測一直是一門很熱門的學問。但是受限於經費和技術，一直都不是有很大方面的突破，最主要限制這方面研究的問題是在於人體模型的複雜度和人體動作的多變性，目前大部分的系統都必需在人體上面增加額外的探測器或者是感測器，這樣一來就大大的增加了使用上面的不方便和動輒百萬元以上的使用經費，所以在這種狀況下，我們試著去建立一套系統完全建立在視覺方面，並且只要做一些影像方面的處理，就可以很輕易的擷取畫面中人物的動作參數。如此一來，也符合了方便性和節省成本這兩項要素。
在本篇論文當中，首先我們會建立一個3D的人體模型，裡面會用位置和角度這兩樣參數去表示它，此外再加上結構上面和運動學上面的一些限制，這樣我們的人體模型就可以很充分的去表現在側邊走路的姿態。接下來我們採用了一個傳統上很廣泛利用的Particle filter來追蹤人體的參數，為了節省運算時間和增加精確度，我們將人體分成6個部份，再分別使用六個分群的particle去擷取裡面的參數,之後再結合了一些經由資料庫所提供的一些資訊，就可以很精確的去預估我們所想要的參數。每當參數預估出來以後,我們再利用NBP這個理論來做收歛的動作，NBP的理論基本上是一個很複雜的網絡關係，每當要推估出一個點的答案，我們要蒐集所有和這個點相連的點所提供的資訊來做評估，而所提供的資訊也是經由人類走路的影片所提供的，所以可以解決在影片當中被擋住的身體部分參數的推估，經由兩個理論的結合，就可以很輕易的算中人走路影片的角度和位置，然後再經由我們所建立的人體模型去展現，目前系統的誤差角度大概在11~12度左右。

This paper proposes a motion capturing system for human walking in the side view. First we build a 3D human model with structural and kinematical constraints. The model is build by OpenGL and viewed as the candidate model. To track the human motion parameters, we use the separated particle filter for tracking six parts of human body. This method can obviously reduce the high-dimensional parameters.

Second we use the Particle Filter (PF) and Nonparametric Belief Propagation (NBP) for human tracking. PF will estimate some initial pose, and then NBP will compute the results after several iterations. Then the results will be viewed as the initial value for the next stage of particle filter. Finally, we can compute the motion parameter of each frame. Then error angle of our system is less than 11 degrees.

[1] Sungmin Kim, Chang-Beom Park,Seong-Whan Lee. “Tracking 3D Human Body using Particle Filter in Moving Monocular Camera”. International Conference on Pattern Recognition 2006.
[2] Mun Wai Lee, Isaac Cohen, Soon Ki Jung. “Particle Filter with Analytical Inference for Human Body Tracking”. Proceeding of the Workshop on Motion and Video Computing (Motion’02).
[3] Leonid Sigal, Sidharth Bhatia, Stefan Roth. “Tracking Loose-limbed People”. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2004.
[4] Erik B.Sudderth, Alexander T.Ihler. “Nonparametric Belief Propagation”. IEEE Conference on Computer Vision and Pattern Recognition 2003.
[5] Tony X.Han, Huazhong Ning, Thomas S.Huang. “Efficient Nonparametric Belief Propagation with Application to Articulated Body Tracking”. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2006.
[6] Jamal Saboune, Francois Charpillet. ”Using Interval Particle Filtering for Marker less 3D Human Motion Capture”. IEEE International Conference on Tools with Artificial Intelligence 2005.
[7] Mun Wai Lee, Ramakant Nevatia. “Dynamic Human Pose Estimation Using Markov Chain Monte Carlo Approach”. IEEE Workshop on Motion and Video Computing 2005.
[8] Tatsuya Osawa, Xiaojun Wu, Kaoru Wakabayashi, Takayuki Yasuno, “Human Tracking by Particle Filtering Using Full 3D Model of Both Target and Environment”. IEEE 2006.
[9] Guoying Zhao, Guoyi Liu , Hua Li ,Matti Pietikainen. “3D Gait Recognition Using Mutiple Cameras”. International Conference on Automatic Face and Gesture Recognition 2006.
[10] Joachim Schmidt, Jannik Fritsch, Bogdan Kwolek. “Kernel Particle Filter for Real-Time 3D Body Tracking in Monocular Color Images”. International Conference on Automatic Face and Gesture Recognition 2006.
[11] Haiping Lu, K.N.Plataniotis, A.N.Venetsanopoulos. “A Layered Deformable Model for Gait Analysis”. International Conference on Automatic Face and Gesture Recognition 2006.
[12] Oliver Bernier. “Real-Time 3D Articulated Pose Tracking using Particle Filters Interacting through Belief Propagation”. International Conference on Pattern Recognition 2006.
[13] M.Isard. “PAMPAS: Real-Valued Graphical Models for Computer Vision”. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2003.
[14] Xiangyang Lan, Daniel P.Huttenlocher. “Beyond Trees: Common-Factor Models for 2D Human Pose Recovery”. IEEE International Conference on Computer Vision 2005.
[15] Leonid Sigal, Michael Isard, Benjamin H.Sigelman, Michael J.Black. “Attractive People:Assembling Loose-Limbed Models using Non-parametric Belief Propagation”.
[16]Leonid Sigal, Michael J.Black. “Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation”. Computer Vision and Pattern Recognition 2006.