Presentations

We present techniques for activity recognition integration human skeleton and appearance. Joint positions and angles are applied in skeleton tracking,and at the same time multiple features are used for appearance-based activity recognition. Moreover,the experiment shows how to understand human activities in our daily scenes.

This paper describes a new accurate interpolation method of a low-resolution depth image using a high-resolution color image for the structural analysis of 3d data. Our method adopts the strategy to detect and omit regions where it is difficult to estimate depth value accurately. In order to achieve this, Color geodesic neighborhood is used as the local smooth surface, and depth data is interpolated with checking smoothness of connections between them. Pixels where they can not be smoothly connected are omitted automatically as indeterminable pixels in this process. Experiments with images of the Middlebury stereo datasets demonstrate that in the quantitative sense our method can interpolate depth images more accurately than other interpolation methods.