Nvidia Corporation

Texas Instruments Corporation

Shalini Gupta

Kihwan Kim

Kari Pulli

Pavlo Molchanov

Jan Kautz

Elif Albuz

Iuri Frosio

Nagilla Dikpal Reddy

Mateusz Jerzy Baranowski

Gregory P Meyer

Hamid Rahim Sheikh

William M Johnson

Aziz Umit Batur

Niranjan Avadhanam

John W Glotzbach

Jeffrey L Nye

Goran Devic

Rajesh Narasimha

David Harold Bartley

Murali S Chinnakonda

Ajay Jayaraj

Toshio Nagata

Stephen Busch

Thrinadh Kottana

Varun Allagadapa

Robert Jp Nychka

Ganesh Sundararajan

An apparatus and method for gesture detection and recognition. The apparatus includes a processing element, a radar sensor, a depth sensor, and an optical sensor. The radar sensor, the depth sensor, and the optical sensor are coupled to the processing element, and the radar sensor, the depth sensor, and the optical sensor are configured for short range gesture detection and recognition. The processing element is further configured to detect and recognize a hand gesture based on data acquired with the radar sensor, the depth sensor, and the optical sensor.

Multi-sensor based user interface

An apparatus and method for radar based gesture detection. The apparatus includes a processing element and a transmitter configured to transmit radar signals. The transmitter is coupled to the processing element. The apparatus further includes a plurality of receivers configured to receive radar signal reflections, where the plurality of receivers is coupled to the processing element. The transmitter and plurality of receivers are configured for short range radar and the processing element is configured to detect a hand gesture based on the radar signal reflections received by the plurality of receivers.

Radar based user interface

One embodiment of the present invention sets forth a technique for estimating a head pose of a user. The technique includes acquiring depth data associated with a head of the user and initializing each particle included in a set of particles with a different candidate head pose. The technique further includes performing one or more optimization passes that include performing at least one iterative closest point (ICP) iteration for each particle and performing at least one particle swarm optimization (PSO) iteration. Each ICP iteration includes rendering the three-dimensional reference model based on the candidate head pose associated with the particle and comparing the three-dimensional reference model to the depth data. Each PSO iteration comprises updating a global best head pose associated with the set of particles and modifying at least one candidate head pose. The technique further includes modifying a shape of the three-dimensional reference model based on depth data.

Model-based three-dimensional head pose estimation

In one embodiment of the present invention, a graphics processing unit (GPU) is configured to detect an object in an image using a random forest classifier that includes multiple, identically structured decision trees. Notably, the application of each of the decision trees is independent of the application of the other decision trees. In operation, the GPU partitions the image into subsets of pixels, and associates an execution thread with each of the pixels in the subset of pixels. The GPU then causes each of the execution threads to apply the random forest classifier to the associated pixel, thereby determining a likelihood that the pixel corresponds to the object. Advantageously, such a distributed approach to object detection more fully leverages the parallel architecture of the parallel processing unit (PPU) than conventional approaches. In particular, the PPU performs object detection more efficiently using the random forest classifier than using a cascaded classifier.

Performing object detection operations via a graphics processing unit

A method of noise filter parameter adaptation, the method comprising receiving a current video frame comprising a plurality of pixels. A table lookup is performed, using current statistical values associated with the current video frame. Noise filter parameters are adapted, based on current lighting conditions as determined from the performed table lookup. The current lighting conditions correspond to the current statistical values. The current video frame is noise filtered as defined by the adapted noise filter parameters.

Low complexity adaptive filtering for mobile captures

In one embodiment of the present invention, a graphics processing unit (GPU) is configured to detect an object in an image using a random forest classifier that includes multiple, identically structured decision trees. Notably, the application of each of the decision trees is independent of the application of the other decision trees. In operation, the GPU partitions the image into subsets of pixels, and associates an execution thread with each of the pixels in the subset of pixels. The GPU then causes each of the execution threads to apply the random forest classifier to the associated pixel, thereby determining a likelihood that the pixel corresponds to the object. Advantageously, such a distributed approach to object detection more fully leverages the parallel architecture of the PPU than conventional approaches. In particular, the PPU performs object detection more efficiently using the random forest classifier than using a cascaded classifier.

Performing object detection operations via random forest classifier

Traditionally, providing parallel processing within a multi-core system has been very difficult. Here, however, a system is provided where serial source code is automatically converted into parallel source code, and a processing cluster is reconfigured 'on the fly' to accommodate the parallelized code based on an allocation of memory and compute resources. Thus, the processing cluster and its corresponding system programming tool provide a system that can perform parallel processing from a serial program that is transparent to a user. Generally, a control node connected to the address and data leads of a host processor uses messages to control the processing of data in a processing cluster. The cluster includes nodes of parallel processors, shared function memory, a global load/store, and hardware accelerators all connected to the control node by message busses. A crossbar data interconnect routes data to the cluster circuits separate from the message busses.

Integrated circuit with control node circuitry and processing circuitry

A MacBeth color checker chart automatic detection system includes an imaging unit that provides an image and a processing unit that applies an edge detection operation to the image and performs a flood-fill operation on the image to provide a flood-filled image. Additionally, the MacBeth color checker chart automatic detection system includes a testing unit that tests the flood-filled image to provide a modified flood-fill image, wherein a set of heuristic tests are employed to automatically determine quantity and location of MacBeth color checker charts. Generally, the set of heuristic tests are employed to automatically reject regions that are unlikely to belong to a MacBeth color checker chart and to cluster the remaining regions that are likely to belong to a Macbeth color checker chart. A MacBeth color checker chart automatic detection method is also provided.

Robust automatic determination and location of MacBeth color checker charts

Dynamic adjustment of noise filter strengths for use with dynamic range enhancement of images is performed to produce better quality images by adapting dynamically to the image noise profile. Global and local brightness and contrast enhancement (GLBCE) is performed on a digital image to form an enhanced image. The GLBCE applies local gain values to the digital image based on local intensity values. A GLBCE gain versus intensity curve is determined for the enhanced image. A set of noise filter thresholds is adjusted in response to the GLBCE gain versus intensity curve to form a set of dynamically adjusted noise filter thresholds. The enhanced image is noise filtered using the set of dynamically adjusted noise filter thresholds to form a noise filtered enhanced image.

Dynamic adjustment of noise filter strengths for use with dynamic range enhancement of images

Growing community of inventors

San Francisco, CA, United States of America

Shalini Gupta