Ceiling Map Building Using Scale Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ceiling map building methods require multiple cameras or known ceiling distances to create a uniform mosaic image, making them complex and impractical for large facilities with varying ceiling heights.
Innovation Solution
A method using a single camera to capture ceiling images, estimating image scales through object movement comparisons, and converting images to uniform scales for seamless combination into a ceiling map, employing transformation matrices and feature point matching for accurate scale estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If two cameras are used to capture stereo images for distance detection, then the distance to the ceiling can be determined and scale can be calculated, but the system complexity increases
Solution Approach 1:
The patent introduces an intermediary object (a known reference object placed on the ceiling) that mediates between the single camera and the ceiling distance measurement. By detecting this intermediary object with known dimensions, the system can calculate the ceiling distance through image processing without requiring a second camera, thus resolving the contradiction between measurement precision and device complexity
Solution Approach 2:
The patent uses a virtual copy or model of the reference object's known dimensions to calculate real-world distances from the 2D image data. By creating a mathematical model (copy) of the object's physical dimensions and comparing it with its projected size in the image, the system derives distance information without additional physical sensors, reducing system complexity while maintaining measurement accuracy
2Area of stationary object
If ceiling images are captured at various positions to form a mosaic image, then a complete ceiling map can be created, but the images have different scales making uniform combination difficult
Solution Approach 1:
The patent changes the scale parameter of each captured ceiling image based on the detected distance to the ceiling at that position. By applying scale transformation factors derived from the reference object detection, images captured at different distances are normalized to a uniform scale, enabling precise mosaic composition while maintaining large coverage area
Solution Approach 2:
The patent performs preliminary scale estimation and image resampling before the final mosaic composition. By pre-adjusting each image's scale based on initial distance measurements from the reference object, the system prepares uniformly scaled images in advance, making the subsequent mosaic assembly process simpler and more accurate
3Adaptability or versatility
If the height of the ceiling varies from position to position, then the captured images have different scales, but the system should still produce a uniform ceiling map
Solution Approach 1:
The patent dynamically changes the scale parameter of each image based on the locally detected ceiling height. By measuring the reference object's apparent size in each image and calculating the corresponding distance, the system adapts each image's scale factor to compensate for varying ceiling heights, producing a uniform final map despite architectural variations
Solution Approach 2:
The patent applies different scale transformation parameters to different local regions (individual images) based on their specific ceiling height conditions. Each image undergoes a customized scale adjustment tailored to its local environment, allowing the system to adapt to varying ceiling heights while maintaining overall map uniformity through localized parameter optimization
Data Source
AI summary
A ceiling map building method includes estimating a scale of each ceiling image based on information related to the ceiling image and information related to another ceiling image including a same object as included in the ceiling image, the scale being represented as a ratio of an amount of movement of the object between the two ceiling images to an amount of movement of the camera (6) between the positions thereof when the two ceiling images were respectively captured (ST16), and building a ceiling map (2) (ST2) by converting the ceiling images in accordance with the respective scales so as to have sizes suitable for the ceiling map and combining the converted ceiling images (ST84).