Ambarella, Inc.

Lsi Logic Corporation

Ambarella International LP

Lsi Corporation

Didier LeGall

Elliot N Linzer

Leslie D Kohn

Aaron G Wells

Chi Hong John Ju

Shimon Pertsel

Kamil Metin Uz

Diego P De Garrido

Alexander Fink

Leslie Dean Kohn

Ruian Xu

Moshe Doron

An apparatus comprising a plurality of capture devices and a processor. The plurality of capture devices may each be configured to generate a video signal in response to captured images. The processor may be configured to (i) receive the video signals from at least two of the capture devices, (ii) perform a video stitching operation on the video signals, (iii) generate a stitched video based on the video stitching operation and (iv) calculate image stabilization data for the stitched video based on (A) the stitched video signal and (B) motion information. Video data from one of the video signals is used to perform image stabilization for another of the video signals based on the image stabilization data.

Image stabilization for a multi-sensor camera

An apparatus including an interface and a processor. The interface may be configured to receive pixel data. The processor may be configured to generate a plurality of video frames in response to the pixel data received from the interface, perform computer vision operations to detect objects in the video frames, extract features of the objects in response to characteristics of the objects determined using the computer vision operations, identify a person in the video frames based on the features, detect an event based on the person identified and generate a notification in response to detecting the event and a permission status. The permission status may suppress sending the notification when the permission status for the person identified corresponds to denying the notification and enable sending the notification when the permission status does not correspond to denying the notification.

Computer vision enabled smart snooze home security cameras

An apparatus comprising an interface and a processing circuit. The interface may be configured to receive (a) a video signal based on a targeted view in a vehicle and (b) one or more status signals from one or more sensors of the vehicle. The processing circuit may be configured to (A) analyze the video signal received from the interface and (B) detect a type of obstruction of a window of the vehicle visible in the video signal in response to (i) a classification of information in the video signal and (ii) one or more of the status signals. The processing circuit may (a) determine a confidence level for the type of obstruction, (b) activate one or more corrective measures when the confidence level is above a pre-defined threshold and (c) adjust the confidence level based on a response of the obstruction to the corrective measures.

Automatic maintenance of front and/or rear windshield visibility

An apparatus includes an interface and a circuit. The interface may be configured to receive a video signal comprising a plurality of interlaced fields and a plurality of progressive frames. The circuit may be configured to (i) generate a plurality of segments by parsing the video signal, (ii) encode the segments as both (a) a plurality of frame segments in a frame mode and (b) a plurality of field segments in a field mode and (iii) generate an encoded signal based on the frame segments and the field segments.

High efficiency video coding for video with interlaced and progressive content using lookahead

A method for encoding a video signal with both interlaced and progressive content using lookahead is disclosed. The method may include steps (A) to (C). Step (A) may calculate a cost of being interlaced within each of a plurality of windows in the video signal. The video signal generally has a plurality of interlaced fields and a plurality of progressive frames. Step (B) may determine a plurality of points in the video signal. Step (C) may encode the video signal with switching between a field mode and a frame mode at one or more of the points based on the costs. The encoding may be a high efficiency video coding.

An apparatus having a server is disclosed. The server may be configured to (i) receive via a network a first clip of video generated by a camera, (ii) receive via the network first information to edit the first clip, (iii) receive via the network one or more segments of a second clip of video generated by the camera as identified by the first information and (iv) create a third clip of video by editing the segments according to the first information. The second clip is generally a higher resolution version of the first clip. The third clip may have the higher resolution.

Video editing with connected high-resolution video camera and video cloud server

An apparatus comprising an interface and a processor. The interface may be configured to (i) receive a first clip of video generated by a camera through a network, (ii) receive edit information through the network, (iii) transfer parsing information to the camera and (iv) receive one or more segments of a second clip of video generated by the camera as identified by the parsing information through the network. The processor may be configured to (i) send/receive data to/from the interface, (ii) edit the first clip in response to the edit information, (iii) generate the parsing information based on the edit information and (iv) create a third clip of video by editing the segments according to the edit information. The second clip may be a higher resolution version of the first clip. The third clip may have the higher resolution.

Video editing processor for video cloud server

A method of pixel correction is disclosed. The method generally includes the steps of (A) generating a plurality of pixel values from a sensor in response to an optical signal, (B) generating a temperature signal representing a temperature of the sensor and (C) generating a plurality of corrected values by applying a per-pixel correction model to the pixel values, wherein the per-pixel correction model is responsive to the temperature.

Temperature-based fixed pattern noise and bad pixel calibration

A camera system and a method for zooming the camera system is disclosed. The method generally includes the steps of (A) generating an electronic image by sensing an optical image received by the camera, the sensing including electronic cropping to a window size to establish an initial resolution for the electronic image, (B) generating a final image by decimating the electronic image by a decimation factor to a final resolution smaller than the initial resolution and (C) changing a zoom factor for the final image by adjusting both of the decimation factor and the window size.

High resolution zoom: a novel digital zoom for digital video camera

An apparatus generally comprising an input circuit, a storage circuit and an output circuit is disclosed. The input circuit may be configured to generate a first intermediate signal from a plurality of input video signals. The storage circuit may be configured to (i) organize the first intermediate signal into a plurality of sequences each related to one of the input video signals and (ii) generate a second intermediate signal from the sequences. The output circuit may be configured to generate an output video signal by compressing the second intermediate signal.

Growing community of inventors

Los Altos, CA, United States of America

Didier LeGall