Crowd Level Estimation via Dynamic Technique Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing crowd estimation techniques face challenges in achieving accurate results across various crowd conditions and locations, with methods like background subtraction and body part recognition experiencing inaccuracies due to occlusions and varying crowd densities.

Innovation Solution

A system and method for real-time crowd level estimation that dynamically selects and combines multiple crowd estimation techniques based on crowd density levels and locations, using a computer-readable medium to model spatial variations and determine the most suitable technique for accurate counting by comparing input images to pre-generated models of crowd levels.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If background subtraction techniques are used for crowd estimation, then the technique is simple to implement, but accuracy deteriorates when there is overlap of humans (occlusion)

Engineering Contradiction:

Improveease of implementationVSAvoidcrowd estimation accuracy

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The system dynamically adapts the crowd estimation technique based on detected crowd density levels. At low densities, simple background subtraction is used; at high densities with occlusions, the system switches to combined head pattern techniques. This dynamic adaptation resolves the contradiction by selecting the appropriate method based on operational conditions.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the estimation parameter approach based on crowd density. It transitions from pixel-level background subtraction at low densities to pattern-level combined head pattern matching at high densities. This parameter change allows the system to maintain accuracy across varying crowd conditions.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If body part recognition techniques are used for crowd estimation, then the technique can detect individual body parts, but accuracy deteriorates in cases of occlusions at high crowd densities

Engineering Contradiction:

Improvebody part detection accuracyVSAvoidperformance across crowd densities

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The system dynamically switches between body part recognition and combined head pattern techniques based on crowd density detection. When high density and occlusions are detected, it transitions to the more adaptable combined head pattern approach, maintaining versatility across different crowd conditions.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system introduces crowd density level detection as an intermediary that mediates between body part recognition and combined head pattern techniques. This intermediary assessment allows the system to select the appropriate technique based on current conditions, resolving the adaptability issue.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If combined head pattern techniques are used for crowd estimation, then accuracy is improved at high crowd densities, but accuracy deteriorates at sparse crowd levels or low crowd densities

Engineering Contradiction:

Improvecrowd estimation accuracy at high densityVSAvoidperformance across crowd densities

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The system dynamically adapts the estimation technique based on detected crowd density levels. At low densities, it uses background subtraction which performs well for sparse crowds; at high densities, it switches to combined head pattern techniques. This dynamic adaptation resolves the contradiction by selecting the appropriate method based on operational conditions.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

Inventive Principle:

Principle #35Parameter changes

4Ease of operation

If a single crowd estimation technique is used, then the system is simple to operate, but accuracy deteriorates across varying environmental and crowd conditions

Engineering Contradiction:

Improvesystem simplicityVSAvoidcrowd estimation accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system implements multi-functionality by incorporating multiple crowd estimation techniques (background subtraction, body part recognition, and combined head pattern techniques) within a single unified system. This allows the system to handle diverse environmental and crowd conditions while maintaining ease of operation through automatic technique selection.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11893798B2Method, system and computer readable medium of deriving crowd information

Publication Date: 2024.02.06 NEC CORP

AI summary

Methods and systems for crowd level estimation are provided. The system for crowd level estimation includes an input module and a crowd level estimation module. The input module receives an input image of a crowd and the crowd level estimation module estimates a crowd level of the crowd in the input image in response to a crowd density level.