초록 ▼

An active public user interface in a computerized kiosk senses humans visually using movement and color to detect changes in the environment indicating the presence of people. Interaction spaces are defined and the system records an initial model of its environment which is updated over time to refl

An active public user interface in a computerized kiosk senses humans visually using movement and color to detect changes in the environment indicating the presence of people. Interaction spaces are defined and the system records an initial model of its environment which is updated over time to reflect the addition or subtraction of inanimate objects and to compensate for lighting changes. The system develops models of the moving objects and is thereby able to track people as they move about the interaction spaces. A stereo camera system further enhances the system's ability to sense location and movement. The kiosk presents audio and visual feedback in response to what it "sees."

대표청구항 ▼

[ What is claimed is:] [1.]1. A computerized interface for interacting with people, comprising:a camera providing video input representing a region of an arbitrary physical environment as a sequence of images organized with respect to distance from the interface;means responsive to the video input f

[ What is claimed is:] [1.]1. A computerized interface for interacting with people, comprising:a camera providing video input representing a region of an arbitrary physical environment as a sequence of images organized with respect to distance from the interface;means responsive to the video input for detecting changing distance between the interface and a person in the region from the sequence of images to determine intention of the person and hence identify the person as a target for interaction; andaudio visual means for rendering audio and video communication directed to the detected person in a manner such that the detected person engages in human-like informational conversant communication with the interface, content of the rendered audio and video communication changing as a function of change in detected distance between the interface and person.