Video Data Integration for Person Identification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing video monitoring systems struggle to effectively utilize and integrate various types of information, such as movement trajectories and facial data, from video images to provide comprehensive insights about individuals, often failing to associate these pieces of information accurately.

Innovation Solution

An information processing apparatus and method that acquires multiple types of base information from video data, including movement paths and facial features, and integrates them based on predetermined relations to generate comprehensive information about individuals, allowing for the association of different types of data as information about the same person.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If multiple types of base information (movement trajectory, facial information) are independently acquired from video images, then the quantity of information is increased, but the information remains separate and less useful for comprehensive monitoring

Engineering Contradiction:
Improvequantity of informationVSAvoidusefulness of information
Core Design Contradiction:
Quantity of substanceVSLoss of information

Solution Approach 1:

The patent applies the merging principle by integrating multiple types of base information (movement trajectory, facial information, and other monitoring data) that were previously acquired separately. The integration unit combines these disparate information types into unified integrated information, allowing comprehensive monitoring while maintaining the utility and relevance of the combined data through systematic association.

Inventive Principle:
Principle #5Merging (Combining)

2Device complexity

If various types of information are independently processed without integration, then the processing complexity is reduced, but the ability to obtain useful comprehensive information about individuals is diminished

Engineering Contradiction:
Improveprocessing complexityVSAvoidcomprehensive information about individuals
Core Design Contradiction:
Device complexityVSLoss of information

Solution Approach 1:

The patent applies segmentation by dividing the information processing system into distinct functional units: a base information acquisition unit that collects different types of data separately, and a base information integration unit that combines them. This segmentation maintains manageable processing complexity while enabling comprehensive information generation through the coordinated operation of specialized components.

Inventive Principle:
Principle #1Segmentation

3Loss of information

If comprehensive integration of all information types is performed, then the usefulness of monitoring information is improved, but the device complexity and processing requirements increase

Engineering Contradiction:
Improveusefulness of monitoring informationVSAvoidintegration system complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent applies universality by designing an integration unit that can handle multiple types of base information (movement trajectory, facial information, and other monitoring data) through a single unified process. This multi-functional approach improves monitoring usefulness while controlling complexity by using a general-purpose integration mechanism rather than separate specialized systems for each information type.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS11341774B2Information processing apparatus, data generation method, and non-transitory computer readable medium storing program
Publication Date: 2022.05.24 NEC CORP
  • US11341774B2 patent drawing
  • US11341774B2 patent drawing
  • US11341774B2 patent drawing

AI summary

An information processing apparatus, a data generation method, and a program capable of obtaining useful information about a person from video data are provided. An information processing apparatus (1) according to an example embodiment includes a base-information acquisition unit (2) that acquires a plurality of types of pieces of base information based on video data in which at least one person is shown, the pieces of base information being pieces of information used to monitor a person, and a base-information integration unit (3) that generates integrated information by integrating, among the plurality of pieces of base information, those that satisfy a predetermined relation as information of one and the same person.