Ruoyu Yang

Learn More
In recent years, researches on virtual fitting are mostly based on the data of garment pieces through Computer Aided Design. However, three-dimensional garment models are more intuitive, integrated and easy to access and manage. Therefore, we propose and design a method to automatically align virtual humans with three-dimensional garment models. Firstly, we(More)
We propose a method for training deep convolutional neu-ral networks (CNNs) to recognize the human actions captured by depth cameras. The depth maps and 3D positions of skeleton joints tracked by depth camera like Kinect sensors open up new possibilities of dealing with recognition task. Current methods mostly build classifiers based on complex features(More)
—In view of the high rate of false alarm problems on the distributed optical fiber sensing technique applied in enclosure, a sensor is proposed based on double Mach-Zehnder interferometer and a method is needed urgently to identify intrusion accurately. This involves eliminating non-intrusion events caused by operating environments from intrusion events. To(More)