Carnegie Mellon University

Disney Enterprises, Inc.

Dartmouth College

Yang Zhang

Christopher Harrison

Tunc Ozan Aydin

Gierad Laput

Alanson P Sample

Michael O Maloney

Xia Zhou

Bo Robert Xiao

Chouchang Yang

Xing-Dong Yang

Blake G Sloan

Jun Gong

Jeroen Schulte

Yuvraj Agarwal

Sudershan Boovaraghavan

Chen Chen

Abhijit Hota

The exemplary embodiments relate to converting Standard Dynamic Range (SDR) content to High Dynamic Range (HDR) content using a machine learning system. In some embodiments, the neural network is trained to convert an input SDR image into an HDR image using the encoded representation of a training SDR image and a training HDR image. In other embodiments, the neural network is trained to convert an input SDR image into an HDR image using a predefined set of color grading actions and the training images.

Deep SDR-HDR conversion

The disclosure describes a wearable, low-cost and low-power Electrical Impedance Tomography system for gesture recognition. The system measures cross-sectional bio-impedance using electrodes on wearers' skin. Using all-pairs measurements, the interior impedance distribution is recovered, which is then fed to a hand gesture classifier. This system also solves the problem of poor accuracy of gesture recognition often observed with other gesture recognition approaches.

System for wearable, low-cost electrical impedance tomography for non-invasive gesture recognition

A touch sensing system is configured to determine a state of a paper material indicative of a touch input on the paper material. The actions include receiving one or more values of features representing physical properties of a paper material. The system generates, by a pair of electrodes in a conductive material that is electrically connected with the paper material, an electric field in the conductive material. The paper material is configured to shunt current from the conductive material when the paper material is touched. The system measures the electric field in the conductive material in the conductive material. The system generates an approximation of the electric field in the conductive material. The system determines with a classifier a state of the paper material indicative of a touch input on the paper material.

Touch-sensing system including a touch-sensitive paper

The exemplary embodiments relate to converting standard dynamic range (SDR) content to high dynamic range (HDR) content. An SDR image may be decomposed into a base layer of the SDR image that includes low frequency information from the SDR image and a detail layer of the SDR image that includes high frequency information from the SDR image. A base layer of an HDR image may be generated using the base layer of the SDR image and a detail layer of the HDR image may be generated using the detail layer of the SDR image. An HDR image is then generated using the base layer of the HDR image and the detail layer of the HDR image.

Detail reconstruction for SDR-HDR conversion

A system and method for detecting when a user contacts one arm to an opposing arm. The system comprises an emitter worn by the user on one arm and a receiver located on an opposing arm, on the user's head, or on a different part of the user's body. Contact, or touch, is indicated by comparing the value of an electrical signal flowing along a path establish, in part, through the user's skin to a threshold. When touch is initiated, multiple electrical paths are created, including one that generates airborne signal emanating from the user's body.

System and method for robust touch detection for on-skin augmented reality/virtual reality interfaces

A method for a touch sensing system includes generating, by a first pair of electrodes at a first location in a conductive material, an electric field in the conductive material; generating measurement data by measuring, by one or more second pairs of electrodes, the electric field in the conductive material at one or more second locations in the conductive material, with each of the one or more second locations differing from the first location; generating, based on the measurement data, an approximation of the electric field in the conductive material; and classifying, based on the approximation, one or more regions of the interface into a given state.

Touch-sensing system

An infrared (IR)-based gesture sensing and detection system that includes at least one IR sensor for sensing micro gestures of one or more heat-radiating bodies made within a gesture-sensing region located proximate to the IR sensor. Each unique micro gesture may be used as a control gesture for controlling one or more controllable devices. Non-limiting examples of controllable devices include smart wearable device, handheld computing devices, and smart appliances, among many others. In some embodiments, each IR sensor is a passive IR sensor based on a pyroelectric material, and the IR-based gesture sensing and detection system is configured to consume minimal power to operate.

Infrared-based gesture sensing and detection systems, and apparatuses, software, and methods relating to same

A sensing system includes a sensor assembly that is communicably connected to a computer system, such as a server or a cloud computing system. The sensor assembly includes a plurality of sensors that sense a variety of different physical phenomena. The sensor assembly featurizes the raw sensor data and transmits the featurized data to the computer system. Through machine learning, the computer system then trains a classifier to serve as a virtual sensor for an event that is correlated to the data from one or more sensor streams within the featurized sensor data. The virtual sensor can then subscribe to the relevant sensor feeds from the sensor assembly and monitor for subsequent occurrences of the event. Higher order virtual sensors can receive the outputs from lower order virtual sensors to infer nonbinary details about the environment in which the sensor assemblies are located.

Virtual sensor system

Human environments are typified by walls&#x2014;homes, offices, schools, museums, hospitals and pretty much every indoor context one can imagine has walls. In many cases, they make up a majority of readily accessible indoor surface area, and yet they are static&#x2014;their primary function is to be a wall, separating spaces and hiding infrastructure. We present the Wall++ system, a low-cost sensing approach that allows walls to become a smart infrastructure. Instead of merely separating spaces, walls can now enhance rooms with sensing and interactivity. Our wall treatment and sensing hardware can track users' touch and gestures, as well as estimate body pose if they are close. By capturing airborne electromagnetic noise, we can also detect what appliances are active and where they are located. Through a series of evaluations, we demonstrate the Wall++ system can enable robust room-scale interactive and context-aware applications.

Growing community of inventors

Pittsburgh, PA, United States of America

Yang Zhang