Elliptical Head Tracking Using Intensity Gradients and Color Histograms
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Hi-index | 0.00 |
In order to control a remote robot over the internet, the operator needs to be able to exchange information with it in real-time. However, the camera image generally used for providing feedback information is too large to send in real-time over the internet. Furthermore, it takes a long time for the operator to send complex robot commands repetitively. These time delays in exchanging feedback and command information between the remote robot and its operator make it difficult to control internet robots efficiently. This paper proposes an information exchange technique for controlling a remote robot over the internet, in which the desired information is extracted from the image in order to reduce the time required to send the feedback information, and a task-level command is used to reduce the time required to send the robot commands. As a result, the proposed technique can help an operator to control a remote robot in real-time over the internet.