Vision-based System
Surveillance of a crowd of pedestrians in public places like squares and subway stations is a challenging issue to public security. The crisis might lurk in the motion of crowd. To deal with the above-mentioned problem, we establish a modeling approach called “crowd modeling” and have built up a series of surveillance systems for testing. |
We present a low–cost surveillance system to model and analyze human actions based on leaning by demonstration. By teaching the system the difference between normal and abnormal human motions, the computational model built inside the trained machines can automatically identify whether the newly observed behaviors require security interference. |
We have developed a human-following wheeled mobile robot, which has the human tracking function, based on a sensory system to get the position of the target person in real-time. This mobile robot platform can be used for many applications. One potential application is the transportation of baggage in airports. |
We are developing techniques to model and analyze human real-time actions based on learning by demonstration. |
We are developing a novel concept of real-time wearable translating glasses, named intelligent glasses, which can realize real-time multilingual translation. It is useful to a tourist who does not know the local language. |
