Abstract: Embodiments of the present invention describe a collaborative framework for mining of surveillance videos to detect abnormal events, which introduces a two-stage training process to alleviate the high false alarm problem. In the first stage, unsupervised clustering is performed on the segments of the video streams and a set of abnormal events are combined with user feedback to generate a clean training set. In the second stage, the clean training set is used to train a more precise model for the analysis of normal events and the motion detection results from multiple cameras can be cross validated and combined. This description is not intended to be a complete description of, or limit the scope of, the invention. Other features, aspects, and objects of the invention can be obtained from a review of the specification, the figures, and the claims.

Abstract: A system for visualizing information in multi-display environments (“MDEs”) using spatial and perspective-aware visualization techniques. In one implementation, the position of each display in a three-dimensional MDE is determined relative to the other displays. Graphical decoration objects and link paths are then used to help visualize relatedness and continuity between graphical data objects and graphical node-link objects on different displays. Three-dimensional decoration objects and link paths are also constructed to visualize interrelationships between data objects on displays that are not on the same plane. The visualization techniques can also be integrated with mobile displays using location sensing technology to dynamically adjust the decoration objects. Additionally, user tracking systems will dynamically adjust the decoration objects based on user perspective. The visualization techniques are applicable to physical, virtual or mixed physical-virtual environments.

Abstract: Embodiments of the present invention enable an image based controller to control and manipulate objects with simple point-and-capture operations via images captured by a camera enhanced mobile device. Powered by this technology, a user is able to complete many complicated control tasks via guided control of objects without utilizing laser pointers, IR transmitters, mini-projectors, or bar code tagging and/or customized wall paper are not needed for the environment control. This description is not intended to be a complete description of, or limit the scope of, the invention. Other features, aspects, and objects of the invention can be obtained from a review of the specification, the figures, and the claims.

Abstract: A method and apparatus for providing multi-resolution video to multiple users under hybrid human and automatic control. Initial environment and close-up images are captured using a first camera and a PTZ camera. The initial images are then stored in memory. Current environment and close-up images are captured and the an estimated difference between the initial and current images and the true image is determined. The estimated differences are weighted and compared and the stored images are updated. A close-up image is then provided to each user of the system. The close-up camera is then directed to a portion of the environment image having high distortion, and current environment and close-up images are captured again.

Abstract: A system is provided for locating a target, such as a person, relative to a projection screen, the system including two infrared light sources for casting separate shadows of the target on a translucent screen, such as those commonly used for back-projection displays. A sensitive video camera with an infrared filter over the lens that blocks all visible light is located behind the screen. This video camera captures a crisp silhouette for each of the shadows of the target. Image processing techniques detect the person's location as well as typical gestures, such as indicating or pointing to an area of the screen. This allows natural interaction with the display, for example, controlling a pointer or cursor on the screen by pointing at the desired area.

Abstract: A method and apparatus for providing multi-resolution video to multiple users under hybrid human and automatic control. Initial environment and close-up images are captured using a first camera and a PTZ camera. The initial images are then stored in memory. Current environment and close-up images are captured and the an estimated difference between the initial and current images and the true image is determined. The estimated differences are weighted and compared and the stored images are updated. A close-up image is then provided to each user of the system. The close-up camera is then directed to a portion of the environment image having high distortion, and current environment and close-up images are captured again.

Abstract: A system is provided for locating a target, such as a person, relative to a projection screen, the system including two infrared light sources for casting separate shadows of the target on a translucent screen, such as those commonly used for back-projection displays. A sensitive video camera with an infrared filter over the lens that blocks all visible light is located behind the screen. This video camera captures a crisp silhouette for each of the shadows of the target. Image processing techniques detect the person's location as well as typical gestures, such as indicating or pointing to an area of the screen. This allows natural interaction with the display, for example, controlling a pointer or cursor on the screen by pointing at the desired area.