Sarnoff Corporation

Sri International

David Sarnoff Research Center, Inc.

Other

Dolby Laboratories Licensing Corporation

Transpacific Information, LLC

Jeffrey Lubin

Harpreet Singh Sawhney

Michael Henry Brill

James Russell Bergen

Keith James Hanna

Rakesh Kumar

Manika Puri

Michael Anthony Isnardi

Ajay Divakaran

Jeffrey Adam Bloom

Albert P Pica

Gajinder Singh

Aalbert De Vries

Christos Alkivladis Polyzois

Bhaskar S Ramamurthy

Hui Ting Cheng

Christos Alkiviadis Polyzois

Girish Acharya

Michael Tinker

Jayakrishnan Kumar Eledath

Clay Douglas Spence

Zhiwei Zhu

Gooitzen Siemen Van Der Wal

David Watters

Saad Masood Khan

Behjat Siddiquie

John Brian Burns

Gary A Gendel

Heidi Aarlien Peterson

Aaron J Heller

Tom Pschar

Thomas Catanese

Roger L Crane

Walter B Paul

Olga Finard

Bradley J Clymer

Aravind Sundaresan

Douglas Bercow

An identification system includes a radar sensor configured to generate a time-domain or frequency-domain signal representative of electromagnetic waves reflected from one or more objects within a three-dimensional space over a period of time and a computation engine executing on one or more processors. The computation engine is configured to process the time-domain or frequency-domain signal to generate range and velocity data indicating motion by a living subject within the three-dimensional space. The computation engine is further configured to identify, based at least on the range and velocity data indicating the motion by the living subject, the living subject and output an indication of an identity of the living subject.

Identification system for subject or activity identification using range and velocity data

A biometric access control system for controlling access to an environment based on an authorization status of a living subject is disclosed. In one example, a data source generates image data of a tissue region of the subject. A liveness measurement unit processes the image data to detect changes over at least one of time or spatial volume in one or more structural features of the tissue region and generates, based on the detected changes, a spoofing attack detection status indicating that the image data is from living biological tissue or that a spoofing attack is detected. A biometric identification unit processes at least a portion of the same image data generated by the data source to generate biometric information indicative of an identity of the subject. Responsive to the spoofing attack detection status and the biometric information, an authorization unit outputs an authorization status for the subject.

Robust biometric access control based on dynamic structural changes in tissue

Techniques for verifying identity of a human subject to an identification document are described. In some examples, a computing device may be connected to least two cameras oriented such that a first field of view is a substantially opposite direction from a second field of view. The device may receive images from the first camera that include a human subject. Second images from the second camera may include images of an ID document with a photograph of the human subject. The device may process the first images along with the respective, corresponding second images to determine respective 3D locations for at least one of cameras at the respective times the images were captured. Based on the sequence of 3D locations, along with the first images and the second images, the device may determine whether the human subject is a valid human subject.

3D dynamic structure estimation using synchronized images

A multi-modal interaction modeling system can model a number of different aspects of a human interaction across one or more temporal interaction sequences. Some versions of the system can generate assessments of the nature or quality of the interaction or portions thereof, which can be used to, among other things, provide assistance to one or more of the participants in the interaction.

Multi-modal modeling of temporal interaction sequences

A computer implemented method for matching video data to a database containing a plurality of video fingerprints of the type described above, comprising the steps of calculating at least one fingerprint representing at least one query frame from the video data; indexing into the database using the at least one calculated fingerprint to find a set of candidate fingerprints; applying a score to each of the candidate fingerprints; selecting a subset of candidate fingerprints as proposed frames by rank ordering the candidate fingerprints; and attempting to match at least one fingerprint of at least one proposed frame.

Content-based matching of videos using local spatio-temporal fingerprints

A computer implemented method computer implemented method for deriving a fingerprint from video data is disclosed, comprising the steps of receiving a plurality of frames from the video data; selecting at least one key frame from the plurality of frames, the at least one key frame being selected from two consecutive frames of the plurality of frames that exhibiting a maximal cumulative difference in at least one spatial feature of the two consecutive frames; detecting at least one 3D spatio-temporal feature within the at least one key frame; and encoding a spatio-temporal fingerprint based on mean luminance of the at least one 3D spatio-temporal feature. The least one spatial feature can be intensity. The at least one 3D spatio-temporal feature can be at least one Maximally Stable Volume (MSV). Also disclosed is a method for matching video data to a database containing a plurality of video fingerprints of the type described above, comprising the steps of calculating at least one fingerprint representing at least one query frame from the video data; indexing into the database using the at least one calculated fingerprint to find a set of candidate fingerprints; applying a score to each of the candidate fingerprints; selecting a subset of candidate fingerprints as proposed frames by rank ordering the candidate fingerprints; and attempting to match at least one fingerprint of at least one proposed frame based on a comparison of gradient-based descriptors associated with the at least one query frame and the at least one proposed frame.

A method and system for analyzing at least one food item on a food plate is disclosed. A plurality of images of the food plate is received by an image capturing device. A description of the at least one food item on the food plate is received by a recognition device. The description is at least one of a voice description and a text description. At least one processor extracts a list of food items from the description; classifies and segments the at least one food item from the list using color and texture features derived from the plurality of images; and estimates the volume of the classified and segmented at least one food item. The processor is also configured to estimate the caloric content of the at least one food item.

Food recognition using visual analysis and speech recognition

A method and projection system for distorting a recording of a plurality of projected frames is disclosed, comprising a high frame rate display configured to impose a modulation on the projected frames at a frequency that is above the critical fusion frequency of the human visual system, wherein the modulation is of one of shutter width relative to shutter spacing, brightness, frame period, and pseudo-rastering. The high frame rate display may be a tonal display. The projection system may further include hardware for producing low frame rate imagery; an input buffer operatively coupled to said hardware for receiving one of a serial bit stream or blocks of data so as to store at least a predetermined portion of a frame; and a sub-frame generator operatively coupled to said input buffer and to said high frame rate tonal display for applying mathematical modulation techniques to said at least a predetermined portion of a frame.

Camcorder jamming techniques using high frame rate displays

Visually imperceptible distortion, from watermarking or compression, desired for embedding into frames of a video sequence is computed. Within each spatiotemporal region of the frames, points are counted, which have feature information amplitude that at least equals the desired distortion. In each region, a fraction of the points with magnitudes at least equal to desired distortion is determined, in relation to the total number of points and compared to a threshold. Regions with fractions at least equal to the threshold are identified. Visual aspects of features in the identified regions are analyzed for salience related to drawing visual attention. The salience is compared to a threshold. Identified regions that do not exceed the salience threshold may be selected as candidates for hiding the watermark. Spatial and temporal contrast values may relate to the salience, as well as luminance values computed therewith.

Digital watermarking with spatiotemporal masking

A method and apparatus for using a reference in a watermarking application is disclosed. Watermarked content and a reduced resolution reference are registered such that registration parameters are calculated. The watermarked content is processed using the registration parameters. A watermark is recovered using the processed watermarked content and the reduced resolution reference.

Method and apparatus for providing reduced reference techniques for low frequency watermarking

A method and apparatus for inserting a watermark onto an illuminated image sequence. A light modulator modulates a light source. A controller controls the light modulator such that a low frequency watermark is inserted onto the illuminated image sequence.

Method and apparatus for analog insertion of low frequency watermarks

A method and apparatus for inserting a low frequency watermark into a compressed data stream carrying compressed content is disclosed. A portion of the compressed data stream is decoded to generate decoded content. The decoded content is analyzed to generate watermark insertion information. The compressed content is embedded with a low frequency watermark using the watermark insertion information.

Method and apparatus for compressed-domain watermarking

For each small image region (in space and time), a measure of perceptual transparence of each of a set of possible watermark carrier modulations is used to choose a subset of such modulations, from which a secure random number generator selects, for each image region, a single carrier, modulations of which carry the watermark data.

Secure robust high-fidelity watermarking

A method and apparatus for providing an improved workflow for digital watermarking during a production process. The invention provides a content tracking authority facility that forms a centralized location for storing and distributing watermarks and locations within a payload to place the watermarks. All post-production facilities that are involved in processing a particular payload (e.g., any content that can be watermarked, including video content) connect to the content tracking authority facility to receive watermarks for the content they are processing as well as locations within the content to use to place the watermark.

Method and apparatus for providing improved workflow for digital watermarking

A method and apparatus for assessing the visibility of differences between two input signal sequences, e.g., image sequences is disclosed. The apparatus comprises a perceptual metric generator having an input signal processing section, a luminance processing section, a chrominance processing section and a perceptual metric generating section. The luminance processing section simultaneously processes at least two image fields, so as to provide spatio-temporal channels whose calibration is independent of pure-spatial and pure-temporal channels.

Growing community of inventors

Princeton, NJ, United States of America

Jeffrey Lubin