使用星狀骨架作人類動作自動辨識

Abstract

這篇論文提出一建構在隱藏式馬可夫模型的動作辨識方法，此方法使用星狀骨架來對人類的姿勢做出代表性的描述。星狀骨架是一種藉由連結物件中心到物件輪廓突出點的快速骨架技巧。為了使用星狀骨架作為動作辨識的特徵，我們明確地定義星狀骨架如何作為辨識的特徵。因為頭和四肢經常是人形狀的突出點，所以辨識的特徵被定義為星狀的五維向量。 此辨識方法將人的動作視為沿著時間的一連串星狀骨架，因此，表示人類動作的時間序列影像被轉換成特徵向量序列。接著，特徵向量序列必須轉換成符號序列使得隱藏式馬可夫模型可以為動作建立模型。我們設計一本包含每一類動作星狀骨架的姿勢編碼書並且為特徵向量定義距離來量測特徵向量間的相似度。姿勢序列中的每個特徵向量會和編碼書中的特徵向量做比對，並會被編碼成編碼書中與自己最為相似的特徵向量所代表的符號。因此時間序列的姿勢影像被轉換成符號序列。 我們以隱藏式馬可夫模型為每種被辨識的動作建立模型。在訓練模型的階段，每個動作模型的參數皆最佳化以適當地描述訓練的符號序列。在動作辨識的階段，與測試符號序列最相配的動作模型即為所辨識出的動作。 我們建立一個可以自動地辨識出十種不同動作的系統，這個系統分成兩種情況對人類動作影片作測試。第一種情況是我們對一百個包含單一動作的影片作分類，此系統達到了百分之九十八的辨識率。另一種是比較實際的情況，由一個人做出一連串不同的動作，系統即時的辨識出目前的動作。實驗的結果顯現出大有可為的效果。

This paper presents a HMM-based methodology for action recognition using star skeleton as a representative descriptor of human posture. Star skeleton is a fast skeletonization technique by connecting from centroid of target object to contour extremes. To use star skeleton as feature for action recognition, we clearly define the feature as a five-dimensional vector in star fashion because the head and four limbs are usually local extremes of human shape. In our proposed method, an action is composed of a series of star skeletons over time. Therefore, time-sequential images expressing human action are transformed into a feature vector sequence. Then the feature vector sequence must be transformed into symbol sequence so that HMM can model the action. We design a posture codebook, which contains representative star skeletons of each action type and define a star distance to measure the similarity between feature vectors. Each feature vector of the sequence is matched against the codebook and is assigned to the symbol that is most similar. Consequently, the time-sequential images are converted to a symbol posture sequence. We use HMMs to model each action types to be recognized. In the training phase, the model parameters of the HMM of each category are optimized so as to best describe the training symbol sequences. For human action recognition, the model which best matches the observed symbol sequence is selected as the recognized category. We implement a system to automatically recognize ten different types of actions, and the system has been tested on real human action videos in two cases. One case is the classification of 100 video clips, each containing a single action type. A 98% recognition rate is obtained. The other case is a more realistic situation in which human takes a series of actions combined. An action-series recognition is achieved by referring a period of posture history using a sliding window scheme. The experimental results show promising performance.