In-Vehicle Pointing Recognition Using Speech-Based Object Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems struggle to efficiently identify a single target object when multiple candidates are present in the direction pointed by a vehicle occupant, leading to cumbersome decision-making that can compromise safe driving.
Innovation Solution
A data processing system that combines vehicle position detection, occupant state recognition, speech recognition, and object databases to narrow down target object candidates using both pointing direction and spoken features, enabling efficient identification through a dialogue interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional target object identification systems enumerate all candidate objects in the pointing direction, then complete candidate coverage is achieved, but the selection process becomes cumbersome and time-consuming
Solution Approach 1:
The system changes parameters by incorporating speech recognition to extract appearance features (color, shape, size) as additional filtering criteria beyond just pointing direction. This multi-parameter approach narrows down candidates from multiple objects in the pointing direction to a manageable subset that matches both directional and descriptive criteria
Solution Approach 2:
The candidate selection process is segmented into multiple stages: first filtering by pointing direction, then further filtering by speech-recognized appearance features. This segmentation transforms a single complex selection task into sequential filtering steps, reducing the cognitive load and time required for target identification
2Measurement precision
If the system requires multiple selection operations to identify the target object from multiple candidates, then accurate target identification is achieved, but driving safety is compromised due to increased operation complexity
Solution Approach 1:
The system replaces mechanical hand operations with voice-based selection. Instead of requiring the driver to manually navigate through multiple candidates using controls, the driver can select the target object by speaking its appearance features, substituting mechanical interaction with acoustic interaction that is more natural and less distracting
Solution Approach 2:
The system performs automatic filtering and candidate narrowing based on the driver's speech input about appearance features. The system serves itself by autonomously processing the speech recognition results to identify and present the most likely target candidates, reducing the driver's operational burden while maintaining identification accuracy
Data Source
AI summary
A data processing system efficiently identifies a target object pointed to by a vehicle occupant. The data processing system provides a position detection unit that detects the position of the vehicle; an occupant state recognition unit that recognizes motion of an occupant pointing to outside of the vehicle; a target object database that indicates position of target objects that may be pointed to by an occupant; an appearance feature database that indicates appearance features of the target object; a speech recognition unit that recognizes words indicative of appearance features from the speech of the occupant; an object recognition unit that extracts target object candidates pointed at by the occupant by searching the target object database and the appearance feature database using a direction pointed at by an occupant, and a word included in the speech recognized by the speech recognition unit; and an output unit that outputs target object candidates.