在本論文中，我們提出一個在頻域下即時分析人體姿勢的方法，並以一個主成分分析(PCA) 的方法做為我們的模型，來產生一個特徵空間。一般人體的姿勢在二維投影空間中都有其固定的形狀和輪廓。而我們希望在固定的姿勢中，儘管有些微的變化，我們還是能識別出其姿勢的意義－站立、坐下、彎腰、舉手、躺臥，及走路，接著再利用重心區分出更細的動作像是舉右手和舉左手、向右彎和向左彎，或彎腰和坐在地上等等經過旋轉後相似的形狀。在整個系統中，亦包含了一個背景更新的方法及濾除雜訊的前處理，如此可得到更為完整的前景。
整個系統的一開始是一背景相減法及前景的前處理，背景相減法是將影像減去背景得到一較為粗糙的前景，再將這粗糙的前景用去陰影、開洞、補洞，及尋找相連區塊等方法找出一個更為完整的前景。接著找出其輪廓並給予一個起始點對輪廓做排序，而經由排序過的輪廓可用傅利葉頻譜轉換來分析，再對PCA模型所訓練出來的資料做比對，找出其相似性最大的一組資料，最後辨識出其所對應最接近的姿勢。我們所使用的PCA模型是要將不同體型的人，針對同一個姿勢，訓練出一個特徵空間，然後以此特徵空間中的資料做為我們辨識的依據。整個系統在硬體所提供的條件下，對連續擷取的畫面，以一秒約十五張的速度完成姿勢辨識，以達到一個接近即時的系統。

In this thesis, we introduce a real time people tracking detection and posture analysis under frequency domain and use a principal component analysis (PCA) model to generate an eigenspace. In general, the shape and silhouette of 2-D projection of human postures is changeless and it is a cue for us to determine what the person is doing. The postures we want to classify are stand, sit, bend, raise-hand, lying and walking. For these postures, we want to recognize each of them in spite of tiny variance of contour. In the whole system, in order to obtain a more clear and complete foreground silhouette, a method of background of maintenance and preprocessing of filtering noise is included.
In the beginning of our system, there is a method of background subtraction and preprocessing, which include labeling of connected components, shape remover, morphology opening and closing. Then trace the contour pixels with a start point and sort them in order. With the ordered contour pixels, we can apply Fourier Descriptor (F.D.) on them to analysis the frequency component of our defined posture. And then estimate the similarity between F.D. of current image and the pre-stored data by our PCA models. With finding the maximum similarity, we can classify what the posture now is belonging to. The PCA model is used to generate an eigenspace by training each of the same posture of different people. And then we can recognize each posture according to these trained data.

Under the condition and ability the hardware could provide, our system will analyze each frame of video input within about 1/15 second and achieve a near-real-time system.

1) G. Johansson, “Visual motion perception,” Sci. Am. 232(6), 1975, 76-88.
2) T. B. Moeslund and E. Granum, “A Survey of computer vision-based human motion capture,” Computer Vision and Image Understanding, vol. 81, pp.231-268, 2001.
3) K. Tamagawa, T. Yamada, T. Ogi, and M. Hirose, “Developing a 2.5-D Video Avatar,” IEEE Signal Processing Magazine, pp.35-42, 2001.
4) K. Rohr, “Human Movement analysis based on explicit motion models,” chap.8, pp.171-198, Kluwer Academic Press, Boston, 1997.
5) C. R. Wren, A. Azarbayejani, T. Darwell and A. Penland, “Real-time tracking of human body,” IEEE Trans. PAMI, v0l. 19, no.7, pp.780-785, 1997.
6) I. Haritaoglu, D. Harwood, and L. S. Davis, “W4: Real-time surveillance of people and their activities,” IEEE Trans. on PAMI, vol.22, no.8, pp. 809-830, Aug 2000.
7) I. Haritaoglu, D. Harwood, and L. S. Davis, “A fast background scene modeling and maintenance for outdoor surveillance,” ICPR, Barcelona, Spain, Sept. 2000.
8) 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.
9) Y. Li, S. Ma, and H. Lu, “A Multiscale Morphological Method for Human Posture Recognition,” Int. Conf. on Auto. Face and Gesture Recog., Nara, Japan, April 14-16, 1998.
10) A. G. Bharatkumar, K. E. Daigle, M. G. Pandy, Q. Cai, and J. K. Aggarwal, “Lower limb kinematics of human walking with the medial axis transformation,” IEEE Workshop on Motion of Non-Rigid and Articulated Objects, Austin, TX, 1994, pp. 70-76.
11) M. K. Leung and Y. H. Yang, “First sight: A human body outline labeling system,” IEEE Trans. PAMI 17(4), 1995, 359-377.
12) J. O’Rourke and N. I. Badler, “Model-based image analysis of human motion using constraint propagation,” IEEE Trans. PAMI, 2:522-536, 1980.
13) D. Marr and H. K. Nishihara, “Representation and recognition of the spatial organization of three-dimensional shapes,” R. Soc. London, 1978, Vol. B, pp. 269-294.
14) K. Sato, T. Maeda, H. Kato, and S. Inokuchi, “CAD-based object tracking with distributed monocular camera for security monitoring,” Proc. 2nd CAD-Based Vision Workshop, Champion, PA, February 1994, pp. 291-297.
15) C. Bregler, “Learning and recognition human dynamics in video sequrence,” Proc. IEEE Conf. on CVPR, pp.568-574, 1997.
16) I. C. Chang and C. L. Huang, “The model-based human body motion analysis system,” Image and Vision Computing, vol.18, pp.1067-1083, 2000.
17) M. Brand and V. Kettnaker, “Discovery and Segmentation of activities in video,” IEEE trans. on PAMI, vol.22, no.2, pp.844-851, Aug. 2000.
18) Q. Cai and J. K. Aggarwal, “Tracking human motion using multiple cameras,” Proc. of Intl. Conf. on Pattern Recogintion,” ICPR, Vienna, Austria, August 1996, pp. 68-72,.
19) Q. Cai and J. K. Aggarwal, “Automatic tracking of human motion in indoor scene across multiple synchronized video streams,” ICCV, Bombay, India, January 1998.
20) D. M. Gavrila and L. S. Davis, “3-D model-based tracking of humans in action: a multi-view approach,” Proceeding of CVPR, June 1996.
21) A. Nkazawa, H. Kato, and S. Inokuchi, “Human tracking using Distributed Vision System,” ICPR Brisbane, Australia, Aug. 1998.
22) N. Krahnstover, M. Yeasin, and R. Sharma, “Toward a unified framework for tracking and analysis of human motion,”IEEE Workshop on Detection and Recognition Events in Video, 2001.
23) S. Iwaswa, J. Ohya, K. Takahashi, T.Sakaguchi, K. Ebihara, and S. Morishima, “Human Body Posture from Trinocular Camera Images,” Int. Conf. on Automatic Face and Gesture Recognition, Grenoble, France, March 2000.
24) R. Cutler and L. Davis, “Robust real-time periodic motion detection, analysis, and application,” IEEE trans. on PAMI, vol.22, no.8, pp. 781-796, Aug 2000.
25) Y. Ricquebourg and P. Bouthemy, “Real-time tracking of moving persons by exploiting sptio-temporal image slices,” IEEE trans. on PAMI, vol.22, no.8, pp. 797-808, Aug 2000.
26) A. Utsumi, H. Yang, and J. Ohya, “Adaptive Human motion tracking using non-synchronous multiple viewpoint observation,” Proc. of ICPR, Barcelona, Spain, Sept. 2000.
27) Y. Song, L. Goncalves, E. D.i Bernrdo, and P. Perona, “Monocular perception ob biological motion detection and labeling,” IEEE CVPR, vol.2, pp.805-812, 1999.
28) T. F. Cootes, C. J. Taylor, D.H. Cooper, and J. Graham, “Active Shape Models – Their Training and Application,”Computer Vision and Image Understanding, vol.1 pp.38-95, 1995.
29) C. T. Zahn and R. Z. Roskies, "Fourier Descriptor for Plane CLosed Curves," IEEE Trans. on Computer,vo. C-21, No.3, pp.269-281, 1972.