公开(公告)号：US11481683B1

公开(公告)日：2022-10-25

申请号：US16888589

申请日：2020-05-29

Applicant: Amazon Technologies, Inc.

Inventor： Kunwar Yashraj Singh ,  Joaquin Zepeda Salvatierra ,  Erhan Bas ,  Vijay Mahadevan ,  Jonathan Wu ,  Rahul Bhotika

IPC: G06F15/18 ,  G06N20/00 ,  G06T3/00 ,  G06N5/04 ,  G06F17/16

Abstract: Techniques for creating machine learning models for direct homography regression for image rectification are described. In certain embodiments, a training service trains an algorithm on a source view of a training image and a homography matrix of the training image into a machine learning model that generates a normalized homography matrix for an input of the source view. The normalized homography matrix may then be utilized to generate a target view of an image input into the machine learning model. The target view of the image may be used in a document processing pipeline for document images captured using cameras.

公开(公告)号：US11341605B1

公开(公告)日：2022-05-24

申请号：US16588503

申请日：2019-09-30

Applicant: Amazon Technologies, Inc.

Inventor： Kunwar Yashraj Singh ,  Amit Adam ,  Shahar Tsiper ,  Gal Sabina Star ,  Roee Litman ,  Hadar Averbuch Elor ,  Vijay Mahadevan ,  Rahul Bhotika ,  Shai Mazor ,  Mohammed El Hamalawi

IPC: G06T3/00 ,  G06T1/20 ,  G06T3/60 ,  H04L67/02

Abstract: Techniques for document rectification via homography recovery using machine learning are described. An image rectification system can intelligently make use of multiple pipelines for rectifying document images based on the detected type of device that generated the images. The image rectification system can provide high-quality rectifications without requiring human cooperation, multiple views of the document in multiple images, and/or without being constrained to only be able to process images from one source context.

公开(公告)号：US10762644B1

公开(公告)日：2020-09-01

申请号：US16218973

申请日：2018-12-13

Applicant: Amazon Technologies, Inc.

Inventor： Vijay Mahadevan ,  Stefano Soatto

IPC: G06K9/00 ,  G06T7/246 ,  G06N3/04 ,  G06N3/08 ,  G06F17/18 ,  G06T11/20

Abstract: Techniques for multiple object tracking in video are described in which the outputs of neural networks are combined within a Bayesian framework. A motion model is applied to a probability distribution representing the estimated current state of a target object being tracked to predict the state of the target object in the next frame. A state of an object can include one or more features, such as the location of the object in the frame, a velocity and/or acceleration of the object across frames, a classification of the object, etc. The prediction of the state of the target object in the next frame is adjusted by a score based on the combined outputs of neural networks that process the next frame.