Marker-Based Mapping Using Cellular Reference Arrangements
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mapping methods using images from moving video cameras often result in low-quality, poorly defined, or improperly focused images, making quick and reliable mapping challenging.
Innovation Solution
A mapping method and system that utilize a specific reference arrangement with markers organized in cells, allowing for the use of simple markers and enabling reliable and quick identification of cells in video sequences, even with low-quality images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If images are acquired by moving video cameras to map real environments, then the acquisition process becomes easy and user behavior is minimally affected, but the image quality becomes medium/low with scarce definition and imperfect focusing
Solution Approach 1:
The patent introduces markers as intermediary objects placed in the real environment. These markers serve as mediators between the moving video camera and the mapping system, providing identifiable reference points that can be reliably detected even in low-quality moving images. The markers act as a bridge that allows accurate mapping despite the poor quality of images captured by handheld or wearable cameras.
2Productivity
If markers are organized in a specific reference arrangement with cells to enable quick identification, then mapping speed improves, but the complexity of the reference system increases
Solution Approach 1:
The patent divides the mapping environment into discrete cells, with each cell containing specific markers. This segmentation allows the system to process and identify locations independently and efficiently. By organizing markers in a grid-like cellular structure, the system can quickly determine which cell contains the user or object of interest, enabling rapid mapping without requiring complex continuous analysis of the entire environment.
Solution Approach 2:
Each cell in the reference arrangement has a specific local configuration of markers that distinguishes it from other cells. This local quality variation allows the system to identify different locations through simple pattern recognition rather than complex global analysis. Each cell's unique marker arrangement provides local identification capability, simplifying the overall mapping process.
3Ease of operation
If only a portion of a large environment is framed in the video sequence, then the mapping can be performed with limited field of view, but the ability to map the entire large environment is reduced
Solution Approach 1:
The patent pre-establishes a reference arrangement of markers and cells that covers the entire target environment before the mapping process begins. This preliminary setup allows the system to later reconstruct the full environment even when video frames only capture portions of it at any given time. The pre-defined cell structure provides a framework that guides the gradual construction of the complete environmental map from partial observations.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A mapping method comprising: - memorizing at least one reference image (6) of an environment to be mapped (8) containing a specific arrangement of a plurality of markers (10) organized in cells (11); wherein each cell (11) is identified by a marker (10) or by a combination of markers (10); the plurality of markers (10) comprising at least a number of different types of markers (10) equal to a type-number (K); - detecting, by a moving video camera (2), a video sequence (VIDEO DATA) wherein the environment to be mapped (8) is, at least in part, framed; - identifying in at least one frame of the video sequence (VIDEO DATA) one or more cells (11) being part of the specific arrangement of markers (10) of the reference image (6); - calculating, on the basis of the data regarding the identified cells, at least one homography (MAPPING DATA) for the perspective transformation of the coordinates acquired in the video sequence (VIDEO DATA) into coordinates in the reference image (6) and vice versa.