Abstract: Described is a training system for training a vision-based object detector. The system is configured to run an object detector on an image of a cleared scene to detect objects in the cleared scene. The object detector includes a support vector machine (SVM) or similar classifier with a feature model to generate an SVM score for object features and a spatial bias threshold to generate augmented object scores. The system designated detected objects in the cleared scene as false detections and, based on that, updates at least one of the feature model and spatial bias threshold to designate the false detections as background. The updated feature model or updated spatial bias threshold are then stored for use in object detection.

Abstract: The present invention relates to a system for detecting an object of interest in a scene. The system operates by receiving an image frame of a scene and extracting features from the image frame, the features being descriptors. The descriptors are quantized to generate PHOW features. A sliding window protocol is implemented to slide a window over the image and analyze the PHOW features that fall inside the window. Finally, the system determines if the PHOW features represent the object of interest and, if so, then designates the window as a location in the image with a detected object of interest.

Abstract: Described is a method and system for embedding unsupervised learning into three critical processing stages of the spatio-temporal visual stream. The system first receives input video comprising input video pixels representing at least one action and at least one object having a location. Microactions are generated from the input image using a set of motion sensitive filters. A relationship between the input video pixels and the microactions is then learned, and a set of spatio-temporal concepts is learned from the microactions. The system then learns to acquire new knowledge from the spatio-temporal concepts using mental imagery processes. Finally, a visual output is presented to a user based on the learned set of spatio-temporal concepts and the new knowledge to aid the user in visually comprehending the at least one action in the input video.

Abstract: The present invention relates to a system, method, and computer program product for immersive navigation in a virtual environment (VE) suitable for allowing a user to change a view orientation in the VE independently of physical orientation of a user input, such as orientation of the user's head.

Abstract: A real-time, group interactive, augmented-reality system for monitoring an area, suitable for enhancing the enjoyment of entertainment events, is presented. The system comprises a sensor data acquisition system for receiving sensor data, in real-time, from a plurality of data acquisition sensors disposed about an area to be monitored, and a plurality of display centers communicatively coupled with the data acquisition system for receiving sensor data therefrom. A display center includes an user input, a data acquisition sensor selector, an interaction interface for communicating in real-time with users of other display centers, an interface for connecting a display device, and a local display device augmenting system, which are configured to allow a user to interactively augment in real-time his/her local display of events with user-inputted doodles, user requested information and statistics, and user selected viewing angles.

Abstract: The present invention relates to a system, method and computer program product for navigating within a virtual environment (VE). More specifically, the present invention relates to navigating large distances in a VE, without becoming disoriented and without becoming cybersick due to exposure to excessive amounts of optical flow. In one embodiment, the present invention combines jumping and flying to allow for quick navigation of large distances, while preserving a sense of orientation and limiting optical flow.

Abstract: The present invention relates to a system, method and computer program product for enabling user interaction with objects in a virtual environment independently of apparent virtual viewpoint altitude, by non-linearly scaling the virtual actuator. In doing so, the system receives a virtual-viewpoint position and a virtual actuator position from a virtual environment processing subsystem, and a real-viewpoint position and a real-actuator position from a real-world environment tracking subsystem. An xy-scale factor is then calculated based on the virtual-viewpoint position. A non-linear mapping is thereafter calculated between a real dataset and a virtual dataset based on the xy-scale-factor. The real dataset comprises the real-actuator position and the real-viewpoint position in the real-world environment, and the virtual dataset comprises the virtual-actuator position and the virtual-viewpoint position in the virtual environment.

Abstract: The present invention provides active fiducials for use with augmented reality client systems. A computer system, a method, and a computer program product are presented, which provide location-registered patterns for providing information regarding objects in an area. The computer system comprises a memory for storing information regarding at least one object, the information including the location of an object. A processor is connected with the memory to retrieve a portion of the information, including the location of the object, from the memory for transmission to the client system via a wireless communication module which is connected with the processor and is configured to detect a compatible client system within communication range of the wireless communication module, and if a compatible client system is detected, to transmit a portion of the information regarding the object, including the location of the object, from the computer system to the client system.

Abstract: The present invention provides active fiducials for use with augmented reality client systems. A computer system, a method, and a computer program product are presented, which provide location-registered patterns for providing information regarding objects in an area. The computer system comprises a memory for storing information regarding at least one object, the information including the location of an object. A processor is connected with the memory to retrieve a portion of the information, including the location of the object, from the memory for transmission to the client system via a wireless communication module which is connected with the processor and is configured to detect a compatible client system within communication range of the wireless communication module, and if a compatible client system is detected, to transmit a portion of the information regarding the object, including the location of the object, from the computer system to the client system.

Abstract: The present invention allows a broadcaster 300a to encode a plurality of data, a portion of which may be from databases 302a, including spatial content and tracking data into a signal, the signal is sent to an overlay construction module 304a. Augmentation layers 306a, provided by users 308a are conveyed to the overlay construction module 304, where the signals are separably merged with the broadcast signal to create an augmented signal, which is transmitted, optionally via satellite 310a, to users 308a. The users 308a receive the augmented signal and display only the layers of interest to them. Thus each user may select a unique overlay combination, and experience individualized programming that more closely comports with that user's tastes.