Gaze-Based Target Selection Using Intermediary Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional techniques for selecting targets based on a user's line of sight are unstable, making it difficult to accurately choose targets due to inaccuracies in line-of-sight detection and head-direction tracking.
Innovation Solution
An information processing apparatus that acquires line-of-sight information and object information, allowing for the selection of objects based on the positional relation between the user's gaze point and multiple objects, enabling flexible target selection by identifying the closest object or area to the user's gaze point.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If target selection is based on user line of sight, then hands-free operation is enabled, but selection accuracy deteriorates due to line of sight instability
Solution Approach 1:
The patent introduces an intermediary selection mechanism between line-of-sight detection and target selection. Instead of directly selecting the target under the gaze point, the system presents multiple candidate targets and uses additional input (such as head direction, voice command, or confirmation action) to resolve the final selection. This intermediary step filters out false selections caused by line-of-sight instability while maintaining hands-free operation capability.
2Adaptability or versatility
If line of sight detection is used for target selection, then user input flexibility is improved, but selection reliability deteriorates due to detection inaccuracies
Solution Approach 1:
The patent applies partial action by not relying solely on line-of-sight detection for complete target selection. Instead, it uses line of sight to narrow down candidate targets (partial selection) and then requires additional input modalities (head direction, voice, or confirmation) to finalize the selection. This partial use of line-of-sight information maintains user input flexibility while compensating for its reliability shortcomings through multi-modal verification.
Data Source
AI summary
An information processing apparatus according to the present disclosure includes: an acquisition unit that acquires a character string whose part of speech is to be estimated; and a generation unit that generates part-of-speech estimation information for estimating a part of speech of the character string based on a byte sequence obtained by converting the character string.


