AR Region Allocation for Latency Reduction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In augmented reality systems, the processing time for estimating attribute information of objects in real space can exceed the frame rate, especially when multiple recognizers are involved, leading to incomplete processing within the required time frame.

Innovation Solution

An information processing device and method that specifies regions in an image containing detected objects and allocates specific processing to these regions across multiple devices, such as a terminal device and a server device, to efficiently manage the processing load and reduce latency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If attribute information estimation accuracy is improved using advanced algorithms, then measurement precision is improved, but processing time increases and productivity deteriorates

Engineering Contradiction:

Improveattribute information estimation accuracyVSAvoidprocessing speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The image is divided into multiple regions, and different recognizers are assigned to different regions. This segmentation allows parallel processing of multiple regions simultaneously, improving overall processing speed while maintaining accurate attribute information estimation for each region using appropriate algorithms

Inventive Principle:

Principle #1Segmentation

2Measurement precision

If multiple recognizers are used to estimate attribute information for different regions, then measurement precision is improved, but device complexity increases and processing time exceeds frame rate

Engineering Contradiction:

Improveattribute information estimation accuracyVSAvoidnumber of recognizers

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system dynamically selects and allocates recognizers based on region attributes and processing requirements. The allocation unit assigns specific recognizers to specific regions dynamically, optimizing the balance between processing speed and accuracy for each region while managing device complexity

Inventive Principle:

Principle #15Dynamics

3Device complexity

If all processing is performed on a single terminal device, then device complexity is reduced, but processing time exceeds frame rate and productivity deteriorates

Engineering Contradiction:

Improvesystem configurationVSAvoidprocessing speed

Core Design Contradiction:

Device complexityVSProductivity

Solution Approach 1:

An allocation unit acts as an intermediary between the terminal device and server device, intelligently distributing processing tasks. The allocation unit determines which device should process each region based on current system state, enabling efficient load balancing and improving overall processing speed while maintaining manageable device complexity

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The processing workload is segmented and distributed across multiple devices (terminal device and server device). Different regions are assigned to different devices for parallel processing, significantly improving processing speed and enabling the system to meet frame rate requirements

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20250014303A1Information processing device, information processing method, and program

Publication Date: 2025.01.09 SONY GROUP CORP

AI summary

An information processing device includes: a region specifying unit that specifies a plurality of regions each including each of a plurality of objects detected from an image; and an allocation unit that allocates specific processing to be performed on each of the plurality of regions to a plurality of devices.