Face Detection Display Correlating Viewer Data Across Cameras

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing digital signage systems lack the ability to effectively tailor advertising content to the current audience in real-time, making it difficult to maximize the persuasive impact of advertisements on consumers.

Innovation Solution

A display arrangement that includes cameras for face detection and recognition, allowing for the correlation of viewer data across different locations, enabling targeted promotional sequences based on detected audience demographics and behavior, thereby improving advertising effectiveness.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple cameras and face detection systems are deployed to track viewers across locations, then the ability to tailor advertising content to the current audience is improved, but the device complexity and cost increase

Engineering Contradiction:
Improveability to tailor advertising content to audienceVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The display arrangement is designed to perform multiple functions: it serves as both an advertising display device and a viewer detection/tracking system. The cameras capture images for both advertising display and audience analysis, while the processor handles both content delivery and face detection algorithms, eliminating the need for separate dedicated systems.

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

Solution Approach 2:

The system implements real-time feedback by detecting faces in captured images, determining viewer characteristics, and using this information to dynamically select and adjust advertising content. The processor continuously monitors viewer presence and characteristics, then modifies the displayed advertising material accordingly, creating a closed-loop adaptive system.

Inventive Principle:
Principle #23Feedback

2Loss of information

If real-time face detection and viewer tracking is implemented, then audience feedback for assessing advertising success is improved, but the processing requirements and energy consumption increase

Engineering Contradiction:
Improveaudience feedback informationVSAvoidprocessing energy
Core Design Contradiction:
Loss of informationVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary face detection and characteristic determination before selecting advertising content. By pre-analyzing viewer faces and storing their characteristics, the system avoids redundant processing when advertising material needs to be selected, reducing real-time computational energy requirements.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates copies of detected face images and stores viewer characteristic data for later reference. Instead of re-detecting and re-analyzing viewer characteristics for each advertising selection, the system uses stored copies of face data and pre-determined viewer characteristics, significantly reducing processing energy consumption.

Inventive Principle:
Principle #26Copying

3Measurement precision

If the system captures and analyzes face images from multiple cameras, then the precision of viewer identification and demographic analysis is improved, but the measurement and detection difficulty increases

Engineering Contradiction:
Improveviewer identification accuracyVSAvoidface detection complexity
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The system merges images from multiple cameras to create a comprehensive view of viewers. By combining data from different camera angles and positions, the system achieves more accurate face detection and viewer identification than any single camera could provide alone, while sharing the detection workload across multiple devices.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The face detection and analysis process is segmented into distinct stages: initial face detection in captured images, extraction of facial characteristics, determination of viewer demographics, and correlation with advertising effectiveness. This segmentation allows each component to be optimized independently and simplifies the overall complex detection task.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS7643658B2Display arrangement including face detection
Publication Date: 2010.01.05 SONY EUROPE BV
  • US7643658B2 patent drawing
  • US7643658B2 patent drawing
  • US7643658B2 patent drawing

AI summary

A display arrangement comprises an image display device having a first camera directed towards positions adopted by users viewing the display; one or more further cameras directed towards other respective locations; a face detector for detecting human faces in images captured by the cameras; and means for detecting those faces which appear in images captured by both the first camera and at least one of the further cameras.