3D Occupant Detection Using Seat Row Maps for Irregular Seating
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing occupant detection systems struggle to accurately detect occupants when they are not seated at regular seating positions.
Innovation Solution
An occupant detection device that generates a seat row map using point cloud information and sets an upper end line to estimate the number and seating position of occupants based on the shape feature of this line, utilizing a sensor to transmit and receive electromagnetic waves and process the reflected waves to generate a three-dimensional-coordinate position of objects in the vehicle interior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If electromagnetic wave sensors and seating sensors are used to detect occupants, then the detection coverage is improved, but the detection accuracy deteriorates when occupants are not seated at regular seating positions
Solution Approach 1:
The patent transitions from two-dimensional sensor data (seating sensors detecting pressure distribution and electromagnetic wave sensors detecting reflective waves) to three-dimensional point cloud representation. By constructing a seat row map with height information from reflected wave intensity, the system creates a 3D spatial model that accurately represents occupant positions regardless of whether they are seated regularly or irregularly, thus resolving the contradiction between coverage and precision.
Solution Approach 2:
The system changes the detection parameter from simple presence/absence detection to height-based detection. By using the intensity of reflected electromagnetic waves to determine the height of objects in the detection region and constructing a seat row map with vertical dimension, the system can distinguish occupants from other objects even when occupants are not in regular seating positions, thereby improving detection accuracy while maintaining coverage.
2Device complexity
If traditional sensor-based detection methods are used, then the system complexity is reduced, but the ability to detect occupants at irregular positions deteriorates
Solution Approach 1:
The patent divides the detection space into multiple seat rows, and further segments each seat row into multiple detection regions along the width direction. By processing each segment independently and constructing separate seat row maps for each row, the system efficiently handles complex detection scenarios without requiring overly complex global processing, thus maintaining reasonable system complexity while improving detection adaptability to irregular positions.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables accurate detection of the number and seating position of occupants regardless of their seating position, reducing erroneous detections from non-head objects and improving overall detection accuracy.
Implementation Method 1
acquire, based on an intensity of a reflected wave generated when a transmission wave transmitted toward an interior of a moving body is reflected by an object present in the interior
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
An occupant detection device (1) includes: an acquisition unit (101) configured to acquire, based on an intensity of a reflected wave generated when a transmission wave transmitted toward an interior of a moving body is reflected by an object present in the interior, point cloud information indicating a three-dimensional-coordinate position of the object moving in the interior as a point cloud including a plurality of detection points; a generation unit (102) configured to generate, based on the point cloud information, a seat row map for each seat row including a plurality of seating regions, the seat row map indicating a distribution of the detection points in a plane region corresponding to an arrangement direction of the plurality of seating regions and a height direction of the moving body; a setting unit (103) configured to set, on the seat row map, an upper end line along an upper end portion of a plane point cloud including two or more of the detection points; and an estimation unit (104) configured to estimate the number of occupants for each seat row based on a shape feature of the upper end line.