Spherical Image Floor Plan Generation via Coordinate Transformation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for creating floor plans from spherical images fail to accurately extract location data, as they do not provide information about physical spaces, as all points are represented on the internal surface of a sphere with equal distance from the central viewing point, making it difficult to identify specific locations within the image.
Innovation Solution
A method involving a processor that creates a spherical image format with a center corresponding to the camera position, identifies selected points by yaw and pitch angles, and intersects these points with a plane to generate Cartesian coordinates, allowing for the rendering of a floor plan representing the positions of these points on a surface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If spherical image format is used to provide immersive viewing, then viewing coverage is improved, but location information accuracy deteriorates
Solution Approach 1:
The patent transforms spherical coordinates (azimuth, elevation, radius) into Cartesian coordinates (x, y, z) and then projects onto a 2D plane. This dimensional transformation allows the system to maintain the immersive viewing capability of spherical images while extracting accurate location information by mapping points from curved spherical space to flat Cartesian space with known physical dimensions.
Solution Approach 2:
The patent introduces an intermediate coordinate transformation step that acts as a mediator between the spherical image format and the floor plan representation. By converting spherical coordinates to Cartesian coordinates through mathematical transformation, the system bridges the gap between immersive viewing format and accurate spatial measurement, enabling both functions to coexist.
2Adaptability or versatility
If all points are represented on internal surface of sphere with equal distance, then immersive viewing is achieved, but physical space information is lost
Solution Approach 1:
The patent recovers physical space information by transforming from the spherical coordinate system where all points appear equidistant to a Cartesian coordinate system that preserves actual distance relationships. The transformation uses the known camera position and orientation to map spherical image coordinates to real-world physical coordinates, thereby recovering the physical space information that was obscured in the spherical representation.
Solution Approach 2:
The patent changes the coordinate system parameters from spherical (azimuth, elevation, radius) to Cartesian (x, y, z) coordinates. This parameter transformation allows the system to maintain the immersive spherical viewing format while extracting accurate physical location data by applying mathematical conversion formulas that account for camera position, orientation, and the known geometry of the space being imaged.
3Area of stationary object
If spherical coordinate system is used, then complete coverage is achieved, but difficulty in identifying specific locations increases
Solution Approach 1:
The patent simplifies location identification by projecting 3D spherical coordinates onto a 2D Cartesian plane that represents the actual floor plan. This dimensional projection transforms the complex spherical coordinate system into a familiar 2D map format where locations can be easily identified, measured, and interpreted, while still maintaining complete coverage of the imaged space through the underlying spherical coordinate transformations.
Data Source
AI summary
A method and apparatus are provided for creating a floor plan from a spherical image. A spherical format is created of an image obtained by a camera, wherein the spherical format has a centre that corresponds to the position from which the image was obtained by the camera, and wherein a first surface represented in the image had a first orientation and was at a first distance from the camera when the image was obtained. A plurality of selected points are obtained in the spherical format, each defined by spherical coordinates consisting of a yaw angle and a pitch angle defining a line from the centre. A plane is identified that has the first orientation and that is at the first distance from the centre of the sphere. For each of the selected points, a location in a Cartesian coordinate system is identified where the line from the centre of the sphere to the selected point intersects with the first plane, two of the axes of the Cartesian coordinate system being parallel to the first plane. A floor plan is rendered using the locations, which represents the positions of the selected points on the first surface.