Ambarella International LP

Ambarella, Inc.

Pei-Chien Yu

Chih-Chun Lee

Tsung-Han Wu

Wei-Kang Che

Ching-Ming Wei

Pei-Chen Lin

An apparatus comprising an interface and a processor. The interface may be configured to receive pixel data. The processor may be configured to process the pixel data arranged as video frames, perform computer vision operations on the video frames to detect objects in the video frames, analyze characteristics of the objects detected, determine adaptive auto-exposure weightings in response to the characteristics of the objects detected, generate an auto-exposure weighting table based on the adaptive auto-exposure weightings and generate output video frames. Auto-exposure for the output video frames may be determined in response to the auto-exposure weighting table and the video frames. The auto-exposure weighting table may be generated for each of the video frames.

Object-based auto exposure using neural network models

An apparatus comprising an interface and a processor. The interface may be configured to receive pixel data from a capture device. The processor may be configured to process the pixel data arranged as video frames, generate similar images from the video frames, perform preprocessing on the video frames and the similar images, perform a similarity check between the video frames and the similar images and determine an image correctness in response to the similarity check. The preprocessing of the video frames and the similar images may use a same hardware pipeline. The video frames may be discarded if the image correctness is below a threshold value.

Video correctness checking

An apparatus includes a plurality of cameras and a circuit. The cameras may be mounted on a vehicle and configured to generate a plurality of initial video signals of a scene outside of the vehicle. A plurality of fields of view of adjoining ones of the cameras may spatially overlap each other. The circuit may be configured to (i) store calibration values of the cameras generated during a calibration process, (ii) modify at least one of the initial video signals by applying the calibration values and (iii) generate a final video signal suitable to display to a user of the vehicle by stitching together the initial video signals. The calibration values may be used by the circuit to generate approximately continuous brightness within the scene in the final video signal.

Growing community of inventors

Taipei, Taiwan

Pei-Chien Yu