EEG-Driven Image Triage System for Rapid Visual Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image triage systems, particularly those combining EEG technology and rapid serial visualization presentation, fail to provide location context information within broad area images, necessitating a method to efficiently identify and highlight regions of interest within large imagery collections for detailed scrutiny by analysts.
Innovation Solution
The system divides images into individual chips, displays each chip using rapid serial visualization, collects user data, assigns probabilities of target entity presence, and overlays these probabilities onto the original image, utilizing EEG data and classifiers to identify regions likely to contain target entities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If EEG technology and rapid serial visualization presentation are used to sort images, then the speed of image triage is improved, but location context information within broad area images is lost
Solution Approach 1:
The system divides a broad area image into multiple smaller image chips or tiles, which are then individually processed through RSVP presentation. This segmentation allows the system to maintain high processing speeds while preserving spatial information by mapping the processed chips back to their original locations in the broad area image, thus resolving the contradiction between speed and location context preservation.
2Measurement precision
If individual images are carefully analyzed by image analysts, then accurate target entity identification is achieved, but the workload and time required increase substantially
Solution Approach 1:
The system performs preliminary processing of broad area images by dividing them into chips, processing each chip through RSVP presentation, and assigning probabilities of target entity presence. This preliminary action creates a prioritized list of image chips that are most likely to contain target entities, allowing analysts to focus their careful examination only on these high-probability regions rather than analyzing every individual image or chip, thus reducing analysis time while maintaining identification accuracy.
3Quantity of substance
If large volumes of imagery are stored, then comprehensive coverage is achieved, but the cost of searching through the imagery increases substantially
Solution Approach 1:
The system applies RSVP presentation and probability assignment to only those image chips that are most likely to contain target entities, rather than processing every single chip in the large volume of imagery. This partial action approach, combined with the segmentation of broad area images into manageable chips, enables efficient searching of large imagery volumes by focusing computational resources on high-priority regions, thus maintaining comprehensive coverage while improving search efficiency.
Data Source
AI summary
A system and method of efficiently and effectively triaging an image that may include one or more target entities. The image is divided into a plurality of individual image chips, and each image chip is successively displayed to a user for a presentation time period. Data are collected from the user at least while each image chip is being displayed. For each image chip, a probability that the image chip at least includes a target entity is assigned, based at least in part on the collected data. The image is then displayed with the assigned probabilities overlaid thereon.