Qualcomm Incorporated

Ming-chang Tsai

Chienchung Chang

John G. Mcdonough

Prashant Kantak

Randeep Singh

Charles E. Sakamaki

Ning Bi

Suhail Jalil

Andrew P Dejaco

Yingyong Qi

Ming-Chang Tsai

Anthony Patrick Mauro, Ii

King-Chung Lai

Naren Malayath

Paul Eric Jacobs

Khaled Helmi El-Maleh

Harinath Garudadri

Narendranath Malayath

John G McDonough

Charles E Sakamaki

Karthick Chinnaswami

George Gaozhi Pan

Prashant A Kantak

Robert Opalsky

John G Mcdonough

Gilbert Christopher Sih

Jason Borthwick Kenagy

Scott David Beith

Xin Zhong

Way-Shing Lee

Feng Guo

David Puig Oses

Xuerui Zhang

Bolan Jiang

William Yee-Ming Huang

Byron Yoshio Yafuso

Hanchi David Huang

James A Hutchison

Steven C Den Beste

Toa Shen

Andrew DeJaco

Chuck Han

Hari Garudadri

An apparatus includes a first sensor configured to generate first sensor data. The first sensor data is related to an occupant of a vehicle. The apparatus further includes a depth sensor and a processor. The depth sensor is configured to generate data corresponding to a volume associated with at least a portion of the occupant. The processor is configured to receive the first sensor data and to activate the depth sensor based on the first sensor data.

System and method of depth sensor activation

The techniques of this disclosure are directed to the feedback-based stereoscopic display of three-dimensional images, such as may be used for video telephony (VT) and human-machine interface (HMI) application. According to one example, a region of interest (ROI) of stereoscopically captured images may be automatically determined based on determining disparity for at least one pixel of the captured images are described herein. According to another example, a zero disparity plane (ZDP) for the presentation of a 3D representation of stereoscopically captured images may be determined based on an identified ROI. According to this example, the ROI may be automatically identified, or identified based on receipt of user input identifying the ROI.

Zero disparity plane for feedback-based three-dimensional video

A device is described that includes an encoder/decoder (CODEC) in which functionality is partitioned between a video front end (VFE) and a video back end (VBE). The VFE encapsulates functionality and image processing operations to support a variety of applications, and presents a flexible inter-processor by which an external master device can easily control these operations. The video back end (VBE) operates as an encoder and/or a decoder to generate encoded and/or decoded video sequences. The VFE and VBE may execute within an operating environment provided by a slave device.

Modular architecture having reusable front end for processing digital video data

A mobile user interface suitable for mobile computing devices uses device position/orientation in real space to select a portion of content that is displayed. Content (e.g., documents, files or a desktop) is presumed fixed in virtual space with the mobile user interface displaying a portion of the content as if viewed through a camera or magnifying glass. Data from motion, distance or position sensors are used to determine the relative position/orientation of the device with respect to the content to select the portion for display. Content elements can be selected by centering the display on the desired portion, obviating the need for cursors and pointing devices (e.g., mouse or touchscreen). Magnification can be manipulated by moving the device away from or towards the user. 3-D content viewing may be enabled by sensing the device orientation and displaying content that is above or below the display in 3-D virtual space.

User interface for mobile devices

In an image/video encoding and decoding system employing an artifact evaluator a method and/or apparatus to process video blocks comprising a decoder operable to synthesize an un-filtered reconstructed video block or frame and an artifact filter operable to receive the un-filtered reconstructed video block or frame, which generates a filtered reconstructed video block or frame. A memory buffer operable to store either the filtered reconstructed video block or frame or the un-filtered reconstructed video block or frame, and an artifact evaluator operable to update the memory buffer after evaluating and determining which of the filtered video block or frame, or the un-filtered video block or frame yields better image/video quality.

Enhanced image/video quality through artifact evaluation

This disclosure describes video encoding techniques capable of reducing the number of processing cycles and memory transfers necessary to encode a video sequence. In this manner, the disclosed video encoding techniques may increase video encoding speed and reduce power consumption. In general, the video encoding techniques make use of a candidate memory that stores video blocks in columns corresponding to a search space for a motion estimation routine. A memory control unit addresses the candidate memory to retrieve multiple pixels in parallel for simultaneous comparison to pixels in a video block to be encoded, e.g., using Sum of Absolute Difference (SAD) or Sum of Squared Difference (SSD) techniques. A difference processor performs the parallel calculations. In addition, for subsequent video blocks to be encoded, the candidate memory can be incrementally updated by loading a new column of video blocks, rather than reloading the entire search space.

Video encoding and decoding techniques

Video encoding techniques are described. In one example, a video encoding technique includes identifying a pixel location associated with a video block in a search space based on motion vectors associated with a set of video blocks within a video frame to be encoded, wherein the video blocks in the set are spatially located at defined locations relative to a current video block of the video frame to be encoded. A motion estimation routine can then be initialized for the current video block at the identified pixel location. By identifying a pixel location associated with a video block in a search space based on motion vectors associated with a set of video blocks within a video frame, the phenomenon of spatial redundancy can be more readily exploited to accelerate and improve the encoding process.

Motion estimation techniques for video encoding

Video encoding techniques are described that involve determining a number of processing cycles used during encoding of a video frame, and encoding the video frame without using motion estimation techniques when a number of processing cycles used during encoding exceeds a threshold. For example, the threshold may define a number of processing cycles available for encoding of the given video frame, and the determined number of processing cycles may be a counted number of cycles used during the encoding process of the given video frame. If the number of processing cycles used during encoding exceeds the threshold, motion estimation techniques can be discontinued in favor of less computationally intensive encoding techniques such as texture encoding.

Computationally constrained video encoding

This disclosure is directed to encoding techniques that can be used to improve encoding of digital video data. The techniques can be implemented by an encoder of a digital video device in order to reduce the number of computations and possibly reduce power consumption during video encoding. More specifically, video encoding techniques are described which utilize one or more programmable thresholds in order to terminate the execution of various computations when the computations would be unlikely to improve the encoding. By terminating computations prematurely, the amount of processing required for video encoding can be reduced, and power can be conserved.

Video encoding techniques

An improved system for an interactive voice recognition system () includes a voice prompt generator () for generating voice prompt in a first frequency band (). A speech detector () detects presence of speech energy in a second frequency band (). The first and second frequency bands () are essentially conjugate frequency bands. A voice data generator () generates voice data based on an output of the voice prompt generator () and audible speech of a voice response generator (). A control signal () controls the voice prompt generator () based on whether the speech detector () detects presence of speech energy in the second frequency band (). A back end () of the interactive voice recognition system () is configured to operate on an extracted front end voice feature based on whether the speech detector () detects presence of speech energy in the second frequency band ().

Interactive speech recognition apparatus and method with conditioned voice prompts

This disclosure is directed to encoding techniques that can be used to improve encoding of digital video data. The techniques can be implemented by an encoder of a digital video device in order to reduce the number of computations and possibly reduce power consumption during video encoding. More specifically, video encoding techniques are describe which utilize one or more programmable thresholds in order to terminate the execution of various computations when the computations would be unlikely to improve the encoding. By terminating computations prematurely, the amount of processing required for video encoding can be reduced, and power can be conserved.

A voice recognition system applies speaker-dependent modification functions to acoustic feature vectors prior to voice recognition pattern matching against a speaker-independent acoustic model. An adaptation engine matches a set of acoustic feature vectors X with an adaptation model to select a speaker-dependent feature vector modification function f( ), which is then applied to X to form a modified set of acoustic feature vectors f(X). Voice recognition is then performed by correlating the modified acoustic feature vectors f(X) with a speaker-independent acoustic model.

Distributed voice recognition system using acoustic feature vector modification

Generally stated a method and an accompanying apparatus provides for a voice recognition system () with programmable front end processing unit (). The front end processing unit () requests and receives different configuration files at different times for processing voice data in the voice recognition system (). The configuration files are communicated to the front end unit via a communication link () for configuring the front end processing unit (). A microprocessor may provide the front end configuration files on the communication link at different times.

Voice recognition system method and apparatus

Growing community of inventors

Rancho Santa Fe, CA, United States of America

Chienchung Chang