Target Object Identification via Multi-Camera Imaging Time Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing surveillance systems face limitations in identifying target objects in wide or crowded areas, as they rely on camera ranges and require prior information about suspicious individuals, making it difficult to track individuals or objects consistently across multiple cameras.

Innovation Solution

A target object identifying device and method that matches monitoring targets across multiple cameras using imaging times to identify consistently present targets, regardless of camera range or crowd density, by analyzing video feeds and determining unusual long stays.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If one or more cameras are used to monitor a wide area, then the monitoring coverage is improved, but the number of cameras required increases significantly

Engineering Contradiction:

Improvemonitoring coverage areaVSAvoidnumber of cameras

Core Design Contradiction:

Area of stationary objectVSQuantity of substance

Solution Approach 1:

The patent merges the functions of multiple cameras into a unified monitoring system that processes video feeds from multiple sources simultaneously. The target object identifying device combines detection results from multiple cameras to identify objects that appear in one or more camera fields of view, effectively merging the monitoring capabilities of multiple cameras into a coordinated system that reduces the total number of cameras needed.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The monitoring system is designed with multi-functionality to handle various monitoring scenarios using a single integrated device. The target object identifying device can process video from multiple cameras, perform behavior analysis, track objects across different camera views, and identify target objects based on various criteria (time in frame, movement patterns, etc.), making the system universally applicable across different monitoring configurations without requiring separate specialized systems for each function.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Measurement precision

If multiple cameras with overlapping monitoring areas are used to track a specific person, then the tracking accuracy is improved, but the device complexity increases

Engineering Contradiction:

Improvetracking accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary processing layer (the target object identifying device) that receives video feeds from multiple cameras and performs centralized processing. This intermediary device matches detection results from different cameras, tracks objects across camera boundaries, and maintains continuous object identity throughout the monitoring area. By centralizing the complex matching and tracking logic in a single intermediary device rather than distributing it across multiple cameras, the system achieves high tracking accuracy while managing complexity centrally.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If face image recognition is used to identify specific persons, then the identification accuracy is improved, but the requirement for prior information about suspicious persons increases

Engineering Contradiction:

Improveidentification accuracyVSAvoidprior information requirement

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The patent performs preliminary actions by continuously monitoring and analyzing object behavior patterns before making final identification decisions. The system tracks objects throughout the monitoring area, records their movement patterns, time spent in specific zones, and behavioral characteristics. This preliminary behavior analysis creates a foundation of information about each object's activities, which can then be used to identify target objects based on unusual or suspicious behavior patterns without requiring prior knowledge of specific suspicious individuals' identities or appearances.

Inventive Principle:

Principle #10Preliminary action

4Area of stationary object

If the monitoring range is expanded to cover crowded areas, then the coverage area is improved, but the ability to track specific individuals in crowds deteriorates

Engineering Contradiction:

Improvemonitoring coverage areaVSAvoidtracking reliability in crowds

Core Design Contradiction:

Area of stationary objectVSReliability

Solution Approach 1:

The patent applies segmentation by dividing the monitoring area into multiple zones or regions that can be independently analyzed. The target object identifying device processes video feeds from different cameras covering different zones, and performs behavior analysis within each zone separately. This segmentation allows the system to manage complex crowd scenarios by breaking them down into smaller, more manageable analysis units, improving tracking reliability in crowded areas while maintaining broad coverage through the coordinated monitoring of multiple segmented zones.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11210527B2Target object identifying device, target object identifying method and target object identifying program

Publication Date: 2021.12.28 NEC CORP

AI summary

Monitoring target matching means 71 matches monitoring targets shown in video captured by one or more imaging devices, and identifies monitoring targets estimated to be the same monitoring target, as an identified monitoring target. Target object identifying means 72 identifies a desired target object from one or more identified monitoring targets captured, using imaging times of each of the one or more identified monitoring targets.