Area information estimating device, area information estimating method, and air conditioning apparatus
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating a person's position in a sensing area from camera images face instability in distance estimation due to varying image quality, resolution, and physical characteristics, and require costly dual-camera setups, leading to complex processing.
Innovation Solution
A device that uses a camera to detect persons from images, excluding those with unsatisfactory coordinate-size relationships, calculates positions based on foot coordinates, and classifies standing and sitting positions to improve accuracy, employing a simple processing method that focuses on the relationship between image coordinates and size.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If depth distance is estimated based on the size of the person in the image, then the existence position can be calculated, but the distance estimation accuracy becomes unstable
Solution Approach 1:
The patent changes the parameter used for distance estimation from person size (which varies with body shape and posture) to the relationship between coordinate and size that must satisfy predetermined conditions. This parameter change stabilizes the estimation by filtering out unreliable data while maintaining the ability to calculate existence position.
2Measurement precision
If two cameras are used for triangulation to calculate existence position, then position accuracy improves, but device cost increases
Solution Approach 1:
The patent extracts only the necessary information (coordinate and size relationship satisfying predetermined conditions) from a single camera image to calculate existence position, eliminating the need for the second camera while maintaining position calculation capability through selective data usage.
3Measurement precision
If two cameras are used for triangulation, then position can be calculated, but processing becomes complicated
Solution Approach 1:
The patent extracts and uses only the coordinate and size relationship that satisfies predetermined conditions from a single image, simplifying the processing by eliminating the need to handle multiple camera images and their complex combinations while still achieving existence position calculation.
4Adaptability or versatility
If all detected persons are processed for position calculation, then detection coverage is maximized, but estimation accuracy degrades due to varying image quality and person characteristics
Solution Approach 1:
The patent applies different quality standards to different detection cases by requiring that coordinate-size relationships satisfy predetermined conditions. This local quality control ensures that only reliable detections contribute to accurate estimation while maintaining overall detection coverage.
Data Source
AI summary
An area information estimating device has a camera that photographs an image within a sensing area, a person detector that detects a person from the image from the camera, and a position calculator that calculates an existence position of the person in the sensing area based on a coordinate on the image in which the person is detected by the person detector. The person detector excludes the person in whom a relationship between the coordinate and a size on the image does not satisfy a predetermined condition from a detection target.