Hrl Laboratories, LLC

Raytheon Company

Raytheon Systems Limited

Xlabs Holdings, LLC

Howard Neely, Iii

Michael J Daily

Jason Fox

Ronald Tadao Azuma

Mike Daily

Shinko Yuanhsien Cheng

Terrell Nathan Mundhenk

A Arturo Flores

Mathias Kolsch

Jason Jerald

Swarup S Medasani

Suhas E Chelian

Rashmi N Sundareswara

Jon Leonard

Peter Allmond Tinker

Matthew William Shomphe

Gerald B Isdale

Jerry Isdale

Matt Shomphe

Jason Jarald

Robert S Belvin

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.

Training system for infield training of a vision-based object detector

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.

System for detecting an object of interest in a scene

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.

Method and system for embedding visual intelligence

An automatic approach is described for the semantic analysis and conversion of video annotation metadata (e.g., Video Event Markup Language or 'VEML' metadata) to propositional graphs suitable for analysis by an analogical reasoning system (ARS). Also as described herein, a system architecture implements this conversion while maintaining semantic consistency from annotation through results reporting. Further, the techniques herein leverage the same ontology to populate options for an annotation tool, provide the rules for the metadata-to-propositional graph mapping, and provide the basis for comparison in an analogical reasoning algorithm.

Converting video metadata to propositional graphs for use in an analogical reasoning system

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. Specifically, the present invention combines three distinct virtual reality navigation metaphors (trackball navigation, grab navigation, and immersive navigation) into a hybrid navigation approach generating a final virtual-viewpoint that correlates to the characteristics of an intermediate virtual-viewpoint defined by radius, pitch, and heading of a virtual reference sphere (as in trackball navigation), while the final virtual-viewpoint also adjusts the location and gaze direction of the intermediate virtual-viewpoint based on pitch, heading, and roll of the user's head (as in immersive navigation), thus allowing the user to view a point of interest in the VE while simultaneously facing comfortably forward in the physical world.

Method and system for hybrid trackball and immersive navigation in a virtual environment

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. The system allows users to interactively share the locally augmented-reality display with users of other display centers.

Method and apparatus for real-time group interactive augmented-reality area monitoring, suitable for enhancing the enjoyment of entertainment events

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.

System and method for navigating operating in a virtual environment

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.

System and method for operating in a virtual environment

A beacon-augmented pose estimation system includes positionable beacons that can determine their own 3-D geospatial coordinates and transmit those coordinates back to the pose object. An imaging sensor images the field-of-view of the pose object to provide 2-D image coordinates for any of the beacons in the FOV. A pose object controller processes the sets of 3-D geospatial coordinates and 2-D image coordinates to refine a pose estimate of the pose object. The positionable beacons may include both static beacons that are pre-positioned and mobile beacons that are command-guided to position themselves in the pose object's likely or actual FOV.

Beacon-augmented pose estimation

A distributed multimodal collaboration system includes at least one server coupled to a network, a plurality of data sources coupled to the network and a plurality of clients executing on a corresponding plurality of client workstations coupled to the network. The system further includes a tuple-space having a plurality of descriptors. The tuple-space is accessible by the plurality of data sources, and the plurality of clients, and a descriptor distribution and invalidation protocol is operative to distribute and invalidate descriptors accessible by the plurality of clients and the plurality of data sources, and the system includes a transaction processor for committing a plurality of transactions associated with the descriptor distribution and invalidation protocol.

System and method for distributed multimodal collaboration using a tuple-space

An apparatus and method is disclosed for enabling accurate registration of virtual information upon real objects in selected environments from the perspective of a moveable observation platform having a position and an orientation within an observation space positioned within the environment, the position and orientation defining the registration of the virtual information within the observation space within the environment, which may comprise: a plurality of at least three tracking fiducials selectively each respectively located in fixed predetermined locations in the observation space; the observation platform including a position sensor apparatus adapted to sense an estimated position of the observation platform in the observation space and a heading sensor apparatus adapted to sense an estimated heading of the observation platform within the observation space; the observation platform further including a wide view fiducial detection apparatus mounted on the observation platform and adapted to detect the relative direction from the observation platform to each of the plurality of tracking fiducials, a heading error detection apparatus adapted to detect the difference between the estimated heading and the present heading based upon the observed relative directions to the respective tracking fiducials, and forming a corrected heading from the estimated heading and the detected heading error.

Growing community of inventors

Santa Monica, CA, United States of America

Howard Neely, Iii