Camera Orchestration for Automated Face Identification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional solutions for individual identification in open spaces, such as train stations and airports, require a high number of cameras and involve high costs and processing overhead, as well as potential human errors and blind spots due to manual operation of PTZ cameras.

Innovation Solution

The implementation of a camera orchestration system using fixed high-resolution cameras and strategically positioned PTZ cameras, where the centralized video analytics component predicts trajectories and adjusts PTZ camera settings to capture faces effectively, reducing the need for multiple cameras and processing unnecessary frames, and eliminating human error.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a high number of cameras are deployed to increase face capture likelihood, then identification reliability is improved, but equipment cost and device complexity increase

Engineering Contradiction:

Improveidentification reliabilityVSAvoiddevice complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

A centralized video analytics component acts as an intermediary between fixed cameras and PTZ cameras. This component coordinates camera operations, intelligently selects targets for tracking, and manages face recognition processing, thereby reducing the number of cameras needed while maintaining identification reliability

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces manual PTZ camera operation with an automated video analytics system that uses algorithms to detect faces, track individuals, and control PTZ cameras. This substitution eliminates human error and reduces the need for multiple manually operated cameras

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If all video frames are analyzed for face recognition, then identification completeness is improved, but processing overhead and energy consumption increase

Engineering Contradiction:

Improveidentification completenessVSAvoidprocessing overhead

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

Instead of analyzing all video frames, the system applies face recognition processing selectively only to frames that contain detected faces. The video analytics component identifies relevant frames through preliminary detection, thereby reducing processing overhead while maintaining identification completeness

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system performs preliminary face detection and trajectory prediction on video frames before applying computationally intensive face recognition algorithms. This preliminary filtering ensures that processing resources are concentrated only on frames with potential targets, reducing overall processing overhead

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If PTZ cameras are used for manual monitoring, then identification precision can be improved, but human error and operational complexity increase

Engineering Contradiction:

Improveface capture qualityVSAvoidoperational ease

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The PTZ cameras are equipped with automated control capabilities that allow them to self-adjust pan, tilt, and zoom parameters based on instructions from the video analytics component. This self-service mechanism eliminates manual operation while maintaining face capture quality

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements a feedback loop where the video analytics component continuously monitors video feeds, evaluates face capture quality, and automatically adjusts PTZ camera parameters to optimize face recognition results. This closed-loop control ensures high measurement precision without manual intervention

Inventive Principle:

Principle #23Feedback

4Device complexity

If fixed cameras are used to cover large areas, then device complexity is reduced, but measurement precision and face capture quality deteriorate

Engineering Contradiction:

Improvecamera system complexityVSAvoidface recognition accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent merges the advantages of fixed cameras (wide coverage, low complexity) with PTZ cameras (high precision, adjustable focus) by coordinating their operations through a centralized video analytics component. This combination achieves both broad area coverage and high face recognition accuracy

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS11553129B2Camera orchestration technology to improve the automated identification of individuals

Publication Date: 2023.01.10 INTEL CORP

AI summary

Systems, apparatuses and methods may provide for technology that detects an unidentified individual at a first location along a trajectory in a scene based on a video feed of the scene, wherein the video feed is to be associated with a stationary camera, and selects a non-stationary camera from a plurality of non-stationary cameras based on the trajectory and one or more settings of the selected non-stationary camera. The technology may also automatically instruct the selected non-stationary camera to adjust at least one of the one or more settings, capture a face of the individual at a second location along the trajectory, and identify the unidentified individual based on the captured face of the unidentified individual.