Activity Calculation via Regional Person Proportion Detection

Solution Overview

Problem

Existing methods for calculating the activity of individuals in a space, such as for air conditioning control, face difficulties in tracking individuals, especially in crowded areas or when sensor accuracy is low, making it challenging to detect and measure activity accurately.

Innovation Solution

An information processing apparatus and method that detects the proportion of individuals in predetermined regions within a space using camera images and calculates activity based on particle movement predictions, allowing for accurate activity measurement without individual tracking.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If individual tracking is performed to calculate activity, then activity measurement accuracy is improved, but detection difficulty increases in crowded areas or when sensor accuracy is low

Engineering Contradiction:

Improveactivity measurement accuracyVSAvoidindividual tracking difficulty

Core Design Contradiction:

Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The space is divided into multiple predetermined regions, and the proportion of persons is detected for each region independently. This segmentation allows activity calculation without tracking individual persons across the entire space, resolving the contradiction by making detection feasible in crowded areas while maintaining activity measurement capability through aggregated regional data.

Inventive Principle:

Principle #1Segmentation

2Measurement precision

If individual tracking is performed to calculate activity, then activity measurement accuracy is improved, but device complexity increases

Engineering Contradiction:

Improveactivity measurement accuracyVSAvoidtracking processing complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The space is divided into multiple predetermined regions, and the proportion of persons is detected for each region independently. This segmentation allows activity calculation without tracking individual persons across the entire space, resolving the contradiction by making detection feasible in crowded areas while maintaining activity measurement capability through aggregated regional data.

Inventive Principle:

Principle #1Segmentation

3Ease of manufacture

If sensor accuracy is low, then device cost is reduced, but individual detection reliability deteriorates

Engineering Contradiction:

Improvedevice costVSAvoidindividual detection reliability

Core Design Contradiction:

Ease of manufactureVSReliability

Solution Approach 1:

Multiple low-accuracy sensors detecting person proportions in different regions are merged to calculate overall activity. The combining of regional proportion data compensates for individual sensor inaccuracies, allowing the use of cheaper sensors while maintaining reliable activity measurement through aggregated information.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS11727727B2Information processing apparatus

Publication Date: 2023.08.15 NEC CORP

AI summary

An information processing apparatus according to the present invention includes: a detecting unit configured to detect a proportion of an existing person for each predetermined region; and a calculating unit configured to, on a basis of the proportion of the person in each predetermined region, calculate a value based on an amount of activity of the person.