Vehicle Occupant Physique Estimation With Seat-Movement Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional techniques for estimating a vehicle occupant's physique inaccurately when the seat moves back and forth, as they fail to account for changes in image size and posture, leading to erroneous estimates.
Innovation Solution
A physique estimation device that includes a captured image acquiring unit, a skeleton point detecting unit, a correction amount calculating unit, and a physique estimation unit, which calculates a correction amount based on the ratio of horizontal distances to detect and correct skeleton coordinate points, thereby accurately estimating the occupant's physique despite seat movement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the seat is moved back and forth to adjust occupant position, then the occupant can be positioned comfortably or accessed by imaging devices, but the occupant's size in the captured image changes, leading to erroneous physique estimation
Solution Approach 1:
The system performs preliminary detection of seat position before physique estimation. The correction amount calculating unit uses the detected seat position to calculate a correction amount that compensates for the size change in the captured image, thereby preventing erroneous physique estimation before it occurs
Solution Approach 2:
The system changes the parameter used for physique estimation from raw image size to corrected image size. The correction amount calculating unit calculates a correction based on seat position, and the physique estimation unit uses this corrected size to accurately estimate physique despite seat movement
2Device complexity
If conventional physique estimation techniques are used without considering seat position, then the estimation process is simple, but the estimation accuracy deteriorates when the seat moves
Solution Approach 1:
The physique estimation process is segmented into distinct stages: seat position detection, correction amount calculation based on seat position, and physique estimation using corrected image size. This segmentation allows the system to maintain simplicity in each individual stage while achieving high overall accuracy through the coordinated sequence of operations
Solution Approach 2:
The correction amount acts as an intermediary between seat position detection and physique estimation. Instead of directly estimating physique from the captured image, the system introduces the correction amount as an intermediate step that compensates for seat position effects, thereby maintaining estimation accuracy without excessive complexity
Data Source
AI summary
Processing circuitry acquires a captured image in which an occupant of a vehicle is captured having an optical axis parallel to a moving direction of a seat movable back and forth, detects skeleton coordinate points of the occupant on the basis of the captured image, calculates, on the basis of the skeleton coordinate points, a correction amount on the basis of a ratio between a first distance that is a horizontal distance from a straight line passing through a center of and parallel to a longitudinal direction of the captured image to a correction amount calculating skeleton coordinate point and a second distance that is a horizontal distance from the straight line to a reference coordinate point on the captured image corresponding to the correction amount calculating skeleton coordinate point, and estimates a physique of the occupant on the basis of the skeleton coordinate points and the correction amount.