İnsan hareketlerinin tanınması için anahtar kare tabanlı bir poz temsili

This thesis utilizes a key-pose based representation to recognize human actions in videos. Webelieve that the pose of the human figure is a powerful source for describing the nature of theongoing action in a frame. Each action can be represented by a unique set of frames thatinclude all the possible spatial configurations of the human body parts throughout the time theaction is performed. Such set of frames for each action referred as "key poses" uniquelydistinguishes that action from the rest. For extracting "key poses", we define a similarity valuebetween the poses in a pair of frames by using the lines forming the human figure along witha shape matching method. By the help of a clustering algorithm, we group the similar framesof each action into a number of clusters and use the medoids as "key poses" for that action.Moreover, in order to utilize the motion information present in the action, we include simpleline displacement vectors for each frame in the "key poses" selection process. Experiments onWeizmann and KTH datasets show the effectiveness of our key-pose based approach inrepresenting and recognizing human actions.