Online action recognition is an important task for human-centered intelligent services. However, it remains a highly challenging problem due to the high varieties and uncertainties of spatial and temporal How to cite this article: Liu G, Zhang Q, Cao Y, Tian G, Ji Z. Online human action recognition with spatial and temporal skeleton features using a distributed camera network.

Abstract:In order to help the visually impaired to perceive images with tactile mode, a tactile perception system is designed, which used image acquisition module to analog shape, color and luminance information of the object seen by human eyes in the surrounding environment, and analyzed and processed the information through the data processing module. Through the different control signals, the data processing module controlled tactile producing device and current producing module to produce the current of different region, frequency and intensity to stimulate the body skin of user in certain parts, thus transferring the included shape, color and luminance information of image information to user. The system can help the visually impaired to perceive the image information.