Samsung Electronics Co., Ltd.

Texas Instruments Corporation

National Semiconductor Corporation

Tcl Research America Inc.

Lin Sun

Wei Ma

Curtis D Aumiller

Yunhong Li

Cathy Kim

Marc Estruch Tena

Jun Yeon Cho

Dean N Reading

Imran Mohammed

Catherine S Kim

Fulya Yilmaz

Hanna Fuhrmann

Haohong Wang

Farshid Moussavi

Schuyler Cullen

Qi Chen

Chenxu Luo

Dariush Dabiri

In one embodiment, a method includes maintaining a video communication between client devices with each being associated with a respective video stream, which is associated with a respective match scale measured based on a height of frames of the video stream and a depth of subjects within the frames, determining a respective scaling factor and cropping for each video stream, wherein the respective scaling factor is calculated based on the match scale associated with the corresponding video stream and a target match scale determined from the match scales associated with all video streams, and wherein the respective cropping is determined based on a uniformity of positions of the subjects within the frames across all video streams, generating a merged video stream from each video stream based on the respective scaling factor and cropping, and sending instructions for presenting the merged video stream to one or more of the client devices.

Systems and methods for multi-user video communication with engagement detection and adjustable fidelity

In one embodiment, a method includes maintaining a video communication between two or more client devices with each client device comprising cameras and being associated with a respective video stream in the video communication, determining scene data within a field of view in a real-world environment captured by one or more of the cameras of a first client device of the two or more client devices, determining a privacy filter to apply to a first video stream associated with the first client device based on the scene data, and providing instructions to apply the privacy filter to the first video stream in the video communication.

Systems and methods for implementing privacy filters with variable obfuscation for video communications

Systems and methods for predicting a location of a target vehicle are disclosed. A processor receives trajectory information for the target vehicle and determines a trajectory feature based on the trajectory information. The processor further determines a lane feature of a lane within a threshold vicinity of the target vehicle, and determines a probability associated with the lane based on the trajectory feature and the lane feature. The lane that the vehicle may enter is identified based on the probability. The processor may also generate interactive features of interactions between the target vehicle and other vehicles. The processor predicts a location of the target vehicle in an upcoming time period based on the lane feature and the trajectory feature. In some embodiments, the interactive features are also used for the prediction.

Systems and methods for trajectory prediction

A system and method for three-dimensional (3D) object classification are disclosed. A computing system receives point cloud data from an input source. The point cloud data may include first and second points in 3D space. The first point may represent a feature of an object. The computing system invokes a neural network for classifying the first point with a first label, and regresses a bounding box based on classifying the first point with the first label. Regressing the bounding box includes predicting at least a location of the bounding box. The computing system may control an autonomous vehicle based on regressing the bounding box.

System and method for three-dimensional object detection

An object trajectory prediction system of a vehicle includes: one or more sensors to generate sensory data corresponding to one or more objects within a range of the vehicle; one or more processors; and memory connected to the one or more processors and having instructions that, when executed by the one or more processors, cause the one or more processors to: identify a first person of interest (POI) from the sensory data; estimate a 3-dimensional (3D) pose of the first POI from the sensory data; calculate a trajectory of the first POI according to at least the 3D pose of the first POI; and determine a navigational path of the vehicle according to the trajectory of the first POI.

System and method for object trajectory prediction in an autonomous scenario

A method of generating video in three-dimensional animation environment is provided. The method includes: obtaining and translating directorial hints for making a 3D animated movie based on user input; determining camera configurations in a 3D environment according to the directorial hints; establishing a camera search space that includes multiple candidate cameras to be used at different timestamps to shoot one or more scenes of the movie based on the camera configurations; performing editing optimization based on the camera search space and the directorial hints, to obtain an edited video. The editing optimization is formalized into a process of finding a path with minimum cost in a graph model, each path describing a candidate camera sequence for producing the movie, and at least some of the directorial hints are translated into cost functions of the graph model. The edited video is output as the produced 3D animated movie.

Director hint based auto-cinematography

A low power sound recognition sensor is configured to receive an analog signal that may contain a signature sound. Sound parameter information is extracted from the analog signal and compared to a sound parameter reference stored locally with the sound recognition sensor to detect when the signature sound is received in the analog signal. A trigger signal is generated when a signature sound is detected. A portion of the extracted sound parameter information is sent to a remote training location for adaptive training when a signature sound detection error occurs. An updated sound parameter reference from the remote training location is received in response to the adaptive training.

Cloud based adaptive learning for distributed sensors

A system and method for processing close talking differential microphone array (CTDMA) signals in which incoming microphone signals are transformed from time domain signals to frequency domain signals having separable magnitude and phase information. Processing of the frequency domain signals is performed using the magnitude information, following which phase information is reintroduced using phase information of one of the original frequency domain signals. As a result, high pass filtering effects of conventional differential signal processing of CTDMA signals are substantially avoided.

Growing community of inventors

San Jose, CA, United States of America

Lin Sun