標題: 根據法則於人類正常與異常動作辨識Rule Based Human Normal and Abnormal Activity Recognition 作者: 陳冠廷Kuan-Ting Chen張志永Jyh-Yeong Chang電控工程研究所 關鍵字: 根據法則於人類正常與異常動作辨識;Rule Based Human Normal and Abnormal Activity Recognition 公開日期: 2007 摘要: 人類動作辨識在自動監視系統、人機界面、居家安全照護系統和智慧型居家環境等方面的應用中佔有主要的地位。人類動作辨識系統如僅利用單一張影像的姿式來辨別該動作，應是不足的；但是，在時間序列上，姿式狀態轉換的關係是用來辨別人類動作的重要資訊。 在此篇論文中，我們結合時序姿態比對與模糊法則的方法來完成人類動作的識別。首先，每一張影像的前景人物利用一個基於前後影像比值而建立之統計背景模型抽取出來，並將抽取出來影像轉換成二值化的影像格式。抽取出來的影像經過特徵空間和標準空間轉換後，最後人類動作辨識在標準空間中完成。經由樣板比對的方法可將三張影像序列，此三張影像序列乃從動作視訊5:1減低抽樣獲得，轉換成轉變成一組時序姿態序列。接著，利用模糊法則的推論方法，將這組時序姿態序列分類為某一個動作類別。模糊法則，不僅能夠結合時間序列上的資訊，並且可以容忍不同人做相同動作上的差異。在訓練已知動作時，我們統計每種已知動作的平均值和標準差，藉由這些數值運算，可作為判別已知和未知動作的依據，最後把未知動作擷取出來，再經由非教導式分類演算法 (Unsupervised Clustering Algorithm) 選出新動作的主要姿態，藉由上述的方法，我們可以提高整體動作，即包含正常與未知動作，的辨識率。Human activity recognition plays an essential role in applications such as automatic surveillance systems, human-machine interface, home care system and smart home applications. It is in-sufficient that a human activity recognition system uses only the posture of an image frame to classify an activity. On the other hand, transitional relationships of postures embedded in the temporal sequence are important information for human activity recognition. In the thesis, we combine temple posture matching and fuzzy rule reasoning to recognize an action. Firstly, a foreground subject is extracted and converted to a binary image by a statistical background model based on frame ratio. The binary image is then transformed to a new space by eigenspace and canonical space transformation, and recognition is done in canonical space. A three image frame sequence, 5:1 down sampling from the video, is converted to a posture sequence by template matching. The posture sequence is classified to an action by fuzzy rules inference. Fuzzy rule approach can not only combine temporal sequence information for recognition but also be tolerant to the variation of action done by different people. During the training of image sequences, we can compute the mean and standard deviation of each pre-defined activity. These numbers can be employed to determine whether an input image belongs to one of the pre-defined actions or an unknown action. Lastly, we will also use Unsupervised Clustering Algorithm to generate some key postures for unknown activities. Our action recognition system not only can recognize an pre-defined action but also can signal an unknown action, which enhance the capability and recognition accuracy of activity recognition. URI: http://140.113.39.130/cdrfb3/record/nctu/#GT009512611http://hdl.handle.net/11536/38320 Appears in Collections: Thesis

Files in This Item: