Ants Technology (hk) Limited

Broadcom Corporation

Frimory Technologies Ltd.

Alst Technical Excellence Center

Avago Technologies International Sales Pte. Limited

Ron Fridental

Ilya Blayvas

Ilia Vitsnudel

Pavel Nosko

Noam Sorek

Alex Rosen

Gal Perets

David Plowman

Lili Zhao

Ophir Gvirtzer

Benjamin Sewell

Naushir Patuck

Denis Simakov

Laurent Brisedoux

Assaf Arbelle

Masha Zeldin

Shengwei Da

Cresida Harding

Cressida Harding

Mica Arie Nachimson

Mica Arie-Nachimson

Oranit Dror

Ophir Gvirzer

A method for multiple sensor calibration and tracking, the method including identifying a non-permanent object in a first field of detection (FOD) of a sensor, wherein the sensor is one of a plurality of sensors positioned in various locations at a site, each sensor has a corresponding FOD; tracking the identified object by single-sensor tracking in the first FOD; predicting appearance of the object, and based on the predictions initiating single-sensor tracking in at least one other FOD where it is predicted that the object will appear; and outputting data captured from the tracked FODs.

Method and system for auto-calibration of multiple sensors for event tracking

A robotic system ('new robot') operative for performing at least one task in an environment, the system comprising: learn-from-predecessor functionality governed by a data exchange protocol, which controls short-range wireless knowledge transfer from a short-range wireless transmitter in a predecessor robot system ('old robot') to a short-range wireless receiver in said robotic system, said knowledge comprising at least one environment-specific datum previously stored by the predecessor robot.

Robot apparatus, methods and computer products

Disclosed are systems and devices for facilitating audiovisual communication. According to embodiments, there may be provided a communication device including or otherwise functionally associated with a video camera to acquire visual information from a scene and to convert the visual information into a video stream. A video processing circuit may (a) receive the video stream, (b) extract user related features from the video stream; and (c) detect and characterize one or more user actions. A controller to receive the video processing circuit output and responsive to an indication of one or more detected events within the video stream to trigger a communication session between said communication device and an addressee device, wherein different addressee devices may be associated with different detected actions.

Methods and systems for audiovisual communication

A system and method for accent invariant speech recognition comprising: maintaining a database scoring a set of language units in a given language, and for each of the language units, scoring audio samples of pronunciation variations of the language unit pronounced by a plurality of speakers; extracting and storing m the database a feature vector for locating each of the audio samples in a feature space; identifying pronunciation variation distances, which are distances between locations of audio samples of the same language unit in the feature space, and inter-unit distances, which are distances between locations of audio samples of different language units in the feature space; calculating a transformation applicable on the feature space to reduce the pronunciation variation distances relative to the inter-unit distances; and based on the calculated transformation, training a processor to classify as a same language unit pronunciation variations of the same language unit.

Accent invariant speech recognition

This application discloses to methods, circuits, devices, assemblies and systems for generating a searchable real-scene database including records indicating entities and physical events occurring within the real-scene. The said system may include a camera feed interface to receive a camera feed from each of one or more cameras observing the real-scene. It may also include image processing circuitry including a static scene analysis unit to: (a) extract features of entities appearing in a camera feed, (b) recognize entity types of entities appearing in the one or more camera feeds, (c) assign an entity designator to a specific entity appearing in the camera feeds, (d) generate an entity designator record for a uniquely identifiable entity, andgenerate an attribute record for a uniquely identifiable entity. The system may also include a scene dynamics analysis unit to: (a) detect entity movements, (b) detect entity speech, (c) characterize entity actions based on detected entity movement and/or entity speech, and (d) generate a record indicting an action taken by an entity.

Methods circuits devices systems and functionally associated machine executable code for generating a searchable real-scene database

A computerized method for providing no-configuration object recognition video analytics, the method comprising generating a database stored in computer memory and including labelled images of recognized objects imaged at an initial set of sites including at least one site; using the database as a training set to train a pattern recognition engine; uploading images of additional site/s including at least one additional site which is not a member in the initial set of sites; providing object recognition results for the additional site/s by using the pattern recognition engine on the images as uploaded; verifying the object recognition results; and using a processor for operating the pattern recognition engine on images generated at each the additional site/s including modifying the pattern recognition engine according to and when indicated by the verifying, thereby to provide no-configuration object recognition video analytics at the additional site/s.

Apparatus, methods and computer products for video analytics

The present invention includes computer vision based driver assistance devices, systems, methods and associated computer executable code (hereinafter collectively referred to as: 'ADAS'). According to some embodiments, an ADAS may include one or more fixed image/video sensors and one or more adjustable or otherwise movable image/video sensors, characterized by different dimensions of fields of view. According to some embodiments of the present invention, an ADAS may include improved image processing. According to some embodiments, an ADAS may also include one or more sensors adapted to monitor/sense an interior of the vehicle and/or the persons within. An ADAS may include one or more sensors adapted to detect parameters relating to the driver of the vehicle and processing circuitry adapted to assess mental conditions/alertness of the driver and directions of driver gaze. These may be used to modify ADAS operation/thresholds.

Computer vision based driver assistance devices, systems, methods and associated computer executable code

Disclosed is a system for automatically navigating a vehicle, which system comprises: a data storage containing one or more maps of one or more areas; electronic interfaces for: (i) receiving data relating to the one or more areas from external data sources; (ii) receiving parameters relating to motion of the vehicle from physical sensors; and (iii) receiving a location of the vehicle from a positioning device;a navigation processor comprising processing circuitry adapted to determine an initial optimal route for traversing the vehicle from a given point in the one or more areas to another point in the one or more areas by computationally resolving a constrained minimization problem.

Systems and methods for autonomous vehicle navigation

A method and devices for displaying images, the method comprising: receiving an image, the image comprising depth information; determining at least a first group of pixels and a second group of pixels, based on the depth information; and displaying the first group of pixels at a first focus position of the projection device, and the second group of pixels at a second focus position of the projection device.

Method and apparatus for displaying video data

A method and system for cooperative image acquisition and processing. A system comprising a group of network-connected cooperating cameras, where upon determining an imaging event a camera requests imaging from cooperating cameras. The best video describing the event is selected or generated from the acquired videos. The additional description of the video is created in the form of machine-readable metadata, and human-readable text description.

Distributed automatic image and video processing

Embodiments of imaging devices of the present disclosure automatically utilize simultaneous image captures in an image processing pipeline. In one embodiment, control processing circuitry initiates simultaneous capture of the first image by the first image sensor and the second image by the second image sensor; and image processing circuitry generates an enhanced monoscopic image comprising at least portions of the first image and the second image.

Dual image capture processing

A method and apparatus for enabling wide intensity range in digital imaging using a small amount of memory beyond the memory required for storing the relevant image. The methods and apparatus disclose exposing few-line segments within an image using two different exposure times before continuing with other segments of the image. In alternative configurations, sensors are sampled such that neighboring sensors having the same colors are sampled after being exposed for different durations.

Method and apparatus for expanded dynamic range imaging

A method and apparatus for capturing an image depicting an area or region of interest. The method and apparatus use a large sensor, and a sampling function, which can be non-uniform, so that sensor cells depicting the region or object of interest are sampled more densely than other sensor cells, thus providing more details for the object or region of interest than to other areas, while still showing other areas for orientation and navigation purposes. The method and apparatus can be used for tracking the object or area of interest if either the area or object of interest, or the capturing device moves, by constantly adapting the densely sampled area on the sensor. The method and apparatus can be used for controlling the capturing device from a remote location.

Method and apparatus for dynamic panoramic capturing

A method for electronic imaging, consisting of forming an image having a background color and a non-background color on a plurality of pixels in a color mosaic image sensor, and receiving from each of the plurality of pixels a respective initial signal responsive to the image. The method further includes determining the background color of the image responsive to the initial signals, determining the non-background color of the image responsive to the initial signals, and calculating an adjusted signal for each pixel of the plurality of pixels responsive to the initial signal of the pixel and to at least one of the background color and the non-background color.

Growing community of inventors

Shoham, Israel

Ron Fridental