No abstract

No abstract

No abstract

No abstract

No abstract

To avoid the staircase artifacts, an adaptive image denoising model is proposed by the weighted combination of Tikhonov regularization and total variation regularization. In our model, Tikhonov regularization and total variation regularization can be adaptively selected based on the gradient information of the image. When the pixels belong to the smooth regions, Tikhonov regularization is adopted, which can eliminate the staircase artifacts. When the pixels locate at the edges, total variation regularization is selected, which can preserve the edges. We employ the split Bregman method to solve our model. Experimental results demonstrate that our model can obtain better performance than those of other models.

Human action recognition has become one of the most active research topics in natural human interaction and artificial intelligence, and has attracted much attention. Human movement ranges from simple to complex, from low-level to advanced, with an increasing degree of complexity and data noise. In other words, there is a complicated hierarchy in movement actions. Hierarchy theory can efficiently describe these complicated hierarchical relationships of human actions. Accordingly, a hierarchical framework for humanaction recognition is designed in this paper. Different features are selected according to the level of action, and specific classifiers are selected for different features. In particular, a two-level hierarchical recognition framework is constructed and tested on Kinect skeleton data. At the first level, we use support vector machine for a coarse-grained classification, while at the second level we use a combination of support vector machine and a hidden Markov model for a fine-grained classification. Tenfold cross-validations are used in our performance evaluation on public and self-built datasets, achieving average recognition rates of 95.69% and 97.64%, respectively. These outstanding results imply that the hierarchical step-wise precise classification can well reflect the inherent process of human action.

No abstract