Image data segmentation and transmission

Patent metadata

Field	Value
Publication number	US-2022263921-A1
Application number	US-202217661970-A
Country	US
Kind code	A1
Filing date	May 4, 2022
Priority date	Nov 1, 2019
Publication date	Aug 18, 2022
Grant date	—

Abstract

A computing device is provided, including a logic subsystem with one or more processors, and memory storing instructions executable by the logic subsystem. These instructions are executed to obtain one or more source images, segment the one or more source images to generate a plurality of segments, determine a priority order for the plurality of segments, and transmit the plurality of segments to a remote computing device in the priority order. The plurality of segments are spatial components generated by spatial decomposition of the one or more source images and/or frequency components that are generated by frequency decomposition of the one or more source images. A remote computing device may receive these components in priority order, and perform certain algorithms on individual components without waiting for the entire image to upload.

First claim

1 . A method comprising:
performing spatial decomposition and/or frequency decomposition of one or more source images to thereby respectively generate a plurality of spatial components and/or frequency components; determining a priority order for the plurality of spatial components and/or frequency components, wherein the priority order is determined by:
adding noise to or performing quality degradation on one or more of the plurality of spatial components and/or frequency components,
obtaining a measurement of an effect of the noise or the quality degradation on objects in the one or more source images, and
determining the priority order based at least in part on the measurement; and
transmitting the plurality of spatial components and/or frequency components to a remote computing device in the priority order.

2 . The method of claim 1 , wherein
the components comprise the frequency components; and the frequency decomposition is a degradation of image quality.

3 . The method of claim 1 , wherein
the components comprise the frequency components; and the frequency decomposition is a decomposition of a frequency of visual characteristics of the one or more source images.

4 . The method of claim 1 , wherein
the components comprise the frequency components; and the one or more source images are encoded in a compression format that supports the frequency decomposition.

5 . The method of claim 4 , wherein
the compression format is one of JPEG XR, JPEG 2000, and AV1.

6 . The method of claim 1 , wherein
the components comprise the spatial components; and the spatial components are generated via at least one of human input or a machine learning algorithm trained on labeled visual features.

7 . The method of claim 1 , wherein
the components comprise the spatial components and the frequency components; and the frequency components are generated first, followed by the spatial components for each of the frequency components.

8 . The method of claim 1 , further comprising:
applying an application sensitivity algorithm to add the noise to, or perform the quality degradation on, each component.

9 . The method of claim 1 , wherein
the one or more source images are filtered to select a subset of the one or more of source images to perform spatial decomposition and/or frequency decomposition and transmit.

10 . The method of claim 9 , wherein
the subset of the one or more source images are images of a target object for analysis.

11 . A computing device, comprising:
a logic subsystem comprising one or more processors; and
memory storing instructions executable by the logic subsystem to:
perform spatial decomposition and/or frequency decomposition of one or more source images to thereby respectively generate a plurality of spatial components and/or frequency components;
determine a priority order for the plurality of spatial components and/or frequency components, wherein the priority order is determined by:
adding noise to or performing quality degradation on one or more of the plurality of spatial components and/or frequency components,
obtaining a measurement of an effect of the noise or the quality degradation on objects in the one or more source images, and
determining the priority order based at least in part on the measurement; and
transmitting the plurality of spatial components and/or frequency components to a remote computing device in the priority order.

12 . The computing device of claim 11 , wherein
the components comprise the frequency components; and the frequency decomposition is a degradation of image quality.

13 . The computing device of claim 11 , wherein
the components comprise the frequency components; and the frequency decomposition is a decomposition of a frequency of visual characteristics of the one or more source images.

14 . The computing device of claim 11 , wherein
the components comprise the frequency components; and the one or more source images are encoded in a compression format that supports the frequency decomposition.

15 . The computing device of claim 11 , wherein
the components comprise the spatial components; and the spatial components are generated via at least one of human input or a machine learning algorithm trained on labeled visual features.

16 . The computing device of claim 11 , wherein
the components comprise the spatial components and the frequency components; and the frequency components are generated first, followed by the spatial components for each of the frequency components.

17 . The computing device of claim 11 , wherein
an application sensitivity algorithm is applied to add the noise to or perform the quality degradation on each component.

18 . The computing device of claim 11 , wherein
the one or more source images are filtered to select a subset of the one or more source images to segment and transmit.

19 . The computing device of claim 18 , wherein
the subset of the one or more source images are images of a target object for analysis.

20 . A computing device, comprising:
a logic subsystem comprising one or more processors; and memory storing instructions executable by the logic subsystem to: perform spatial decomposition and/or frequency decomposition of one or more source images to thereby respectively generate a plurality of spatial components and/or frequency components; determine a priority order for the plurality of spatial components and/or frequency components, wherein the priority order is determined by:
adding noise to or performing quality degradation on one or more of the plurality of spatial components and/or frequency components,
obtaining a measurement of an effect of the noise or the quality degradation on objects in the one or more source images, and
determining the priority order based at least in part on the measurement; and
transmitting the plurality of spatial components and/or frequency components to a remote computing device in the priority order.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Badam Anirudh
• Chandra Ranveer
• Li Youjie
• Jha Sagar Ramanand

Classifications

• H04L67/5651 Primary

  Reducing the amount or size of exchanged application data · CPC title

• G06V20/13

  Satellite images · CPC title

• H04L67/06 Primary

  specially adapted for file transfer, e.g. file transfer protocol [FTP] · CPC title

• G06T2207/10024

  Color image · CPC title

• G06T7/30

  Determination of transform parameters for the alignment of images, i.e. image registration · CPC title