Rensselaer Polytechnic Institute

Ut-battelle, Inc.

Boston University

Richard J Radke

Robert F Karlicek

Anil Cheriyadat

Jonas Braasch

Pankil M Butala

Li Jia

Gyanendra Sharma

Jonathan Mathews

Devavrat Jivani

A time-of-flight (TOF) array including a plurality of cameras is positioned with a coplanar Higher Order Ambisonics (HOA) array including a plurality of microphones above a target area such as a room or space for analyzing speaker activity in that area. The HOA microphone array iteratively samples sound energy level frames captured by the microphones to identify a sound vector associated with the global maximum energy level in the sound energy level frame. This sound vector is fused with the data from the TOF camera array that identified the positions of sound sources in the target area to associate produced sound corresponding with the sound vector with a physical active sound source in the target area. A beamformer can then be used to save audio corresponding to the sound vector and discard audio not associated with the sound vector to produce a sound recording associated with the active sound source.

Multi-sensor systems and methods for providing immersive virtual environments

Disclosed herein is an illumination system including an array of LED light sources for emitting light encoded with a modulation pattern, an array of sensors and a space characterization unit. The array of sensors receives emitted light scattered by an object. Each sensor determines a distance between the corresponding light source and the object using the modulation pattern. The space characterization unit uses the distance from each sensor to generate an elevation map indicating a presence of the object.

Sensory lighting system and method for characterizing an illumination space

Coherent motion regions extend in time as well as space, enforcing consistency in detected objects over long time periods and making the algorithm robust to noisy or short point tracks. As a result of enforcing the constraint that selected coherent motion regions contain disjoint sets of tracks defined in a three-dimensional space including a time dimension. An algorithm operates directly on raw, unconditioned low-level feature point tracks, and minimizes a global measure of the coherent motion regions. At least one discrete moving object is identified in a time series of video images based on the trajectory similarity factors, which is a measure of a maximum distance between a pair of feature point tracks.

Detecting multiple moving objects in crowded environments with coherent motion regions

Growing community of inventors

Slingerlands, NY, United States of America

Richard J Radke