Monocular Room Shape Inference for Smarter Air Conditioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing air conditioning and lighting control systems face challenges in accurately determining room shape and layout, leading to suboptimal control, especially when the room has complex shapes or furniture, due to cumbersome user input requirements and high costs associated with advanced sensors like TOF and stereo cameras.
Innovation Solution
A room information inferring apparatus using a monocular camera to capture images, detect person positions, and generate presence maps to infer room shape, furniture placement, and people-containing regions, allowing for precise room information inference without user input, utilizing a normal monocular camera to reduce costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a TOF ranging sensor is used to accurately obtain the shape of the room, then measurement precision is improved, but device cost increases
Solution Approach 1:
The patent replaces expensive TOF ranging sensors with a standard monocular camera, which is a low-cost, widely available component. The system achieves room shape measurement by capturing images and detecting person positions through computer vision algorithms, eliminating the need for costly dedicated ranging hardware while maintaining functional capability.
Solution Approach 2:
The patent substitutes optical-mechanical ranging sensors (TOF) with an optical imaging system (monocular camera) combined with computational processing. Instead of using time-of-flight measurements, the system uses image capture and person detection algorithms to infer room geometry, replacing specialized sensing hardware with a more common imaging device and software processing.
2Measurement precision
If a stereo camera ranging sensor is used to obtain the shape of the room, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent uses a standard monocular camera instead of a complex stereo camera system. This single-camera approach reduces hardware complexity while achieving the same functional goal of room shape measurement through alternative computational methods based on person detection and tracking.
Solution Approach 2:
The patent extracts and utilizes only the essential imaging function from stereo camera systems, employing a single monocular camera. By removing the second camera and associated synchronization and processing complexity, the system achieves room shape measurement with simpler hardware while relying on sophisticated image analysis algorithms.
3Measurement precision
If user input is required to input room shape information, then measurement precision is improved, but ease of operation deteriorates
Solution Approach 1:
The system performs automatic room shape measurement without requiring user input. By deploying person detection and tracking algorithms, the system autonomously captures images, detects person positions, and infers room geometry, eliminating the need for users to manually input room shape information while achieving accurate measurements.
Solution Approach 2:
The system performs preliminary automatic measurement of room shape by detecting person positions and generating presence maps before air conditioning control is implemented. This preliminary automated characterization of the room environment eliminates the need for subsequent user input about room geometry, enabling immediate optimized control.
Data Source
Figure 1
Figure 2A~2B
Figure 3
AI summary
Information regarding a room, such as the shape of the room, is inferred simply and precisely. A room information inferring apparatus for inferring information regarding a room includes: an imaging unit that captures an image of a room that is to be subjected to inferring; a person detection unit that detects a person in an image captured by the imaging unit, and acquires the position of the person in the room; a presence map generation unit that generates a presence map indicating the distribution of detection points corresponding to persons detected in images captured at different times; and an inferring unit that infers information regarding the room based on the presence map. The person detection unit can detect the face, head, or upper body of the person in the image, and acquire the position of the person in the room based on the position and size of the face, head, or upper body in the image. The inferring unit can infer that a polygon circumscribed around the distribution of detection points in the presence map is the shape of the room.