Priority Image Segmentation for Low-Latency Remote Transmission

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Transferring large amounts of image data from edge devices to cloud servers is bottlenecked by network constraints, especially in remote settings, leading to latency issues in applications requiring rapid data availability.

Innovation Solution

An edge device segments images into spatial and frequency components, determining a priority order for transmission based on importance, and transmitting these components to a remote computing device to optimize data transfer.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If image data is transmitted in full resolution without segmentation, then complete image quality is preserved, but transmission time and network bandwidth consumption increase significantly

Engineering Contradiction:
Improveimage qualityVSAvoidtransmission time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The image data is divided into multiple segments or blocks, allowing selective transmission of only those segments that contain important information. This segmentation enables the system to transmit partial image data quickly when full quality is not immediately required, reducing transmission time while preserving the option to send complete high-quality data when needed.

Inventive Principle:
Principle #1Segmentation

2Loss of information

If all image segments are transmitted with equal priority, then complete data is eventually received, but critical information is delayed when network bandwidth is constrained

Engineering Contradiction:
Improvedata completenessVSAvoidavailability time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

Different priority levels are assigned to different image segments based on their importance. Critical segments containing essential information are transmitted with higher priority, ensuring they reach the receiver first even when network bandwidth is limited. Less critical segments are transmitted afterward, maintaining data completeness while optimizing availability time for important information.

Inventive Principle:
Principle #3Local quality

3Speed

If network bandwidth is increased to reduce transmission latency, then transmission speed improves, but infrastructure cost and complexity increase

Engineering Contradiction:
Improvedata transfer speedVSAvoidnetwork infrastructure
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

Instead of transmitting the entire image dataset, only the necessary portion of image segments is transmitted first based on priority assessment. This partial transmission approach achieves acceptable performance for many applications without requiring increased network bandwidth, thereby avoiding the need for expensive infrastructure upgrades while still reducing effective transmission latency.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4052171B1Image data segmentation and transmission
Publication Date: 2025.11.26 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP4052171B1 patent drawingFigure 1
  • EP4052171B1 patent drawingFigure 2
  • EP4052171B1 patent drawingFigure 3A

AI summary

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.