الفهرس | Only 14 pages are availabe for public view |
Abstract Human action recognition is a very active research topic in computer vision and pattern recognition. Recently, it has shown a great potential for human action recognition using the 3D depth data captured by the promising RGB-D cameras, and particularly, the Microsoft Kinect which has made highresolution real-time depth cheaply available. Several features and descriptors have been proposed for depth based action recognition, and they have given high results when recognizing the actions, but one dilemma always exists; the labeled data given, which are manually set by humans. They are not enough to build the system; especially that the use of human action recognition is mainly for surveillance of people activities. In this thesis, the paucity of labeled data is addressed, by the popular semi supervision machine learning technique ”eo-training”, which makes full use of unlabeled samples of two different independent views. The features are derived from the skeleton joints and the depth maps provided by Kinect cameras. 3Djoints positions are extracted from the skeletal view, and HON4D are extracted from the depth maps; both together are combined to derive a strong classifier. The experiments are conducted on two popular datasets used in human action recognition: MSR 3D-Action and MSR DailyActivity. Both experiments give higher accuracy of classification than state of art. |