Marker Detection Using Coplanar Conics for Orientation Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current barcode markers are difficult to read due to their requirement for precise positioning and lack of self-calibration, leading to information loss and limited applications, especially in scenarios where objects must be scanned individually.
Innovation Solution
A marker system with a positioning contour of geometric shape, allowing detection and correction of the marker's orientation and position within an image, enabling the recovery of encoded data even under occluded or disturbed conditions, using coplanar conics and geometric signatures for decoding.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If barcode markers are used for object recognition, then object identification is enabled, but the markers are difficult to read and require precise positioning
Solution Approach 1:
The patent transitions from static barcode reading requiring fixed positioning to dynamic marker detection that adapts to various positions and orientations. The detection system automatically adjusts to the marker's location in the image plane, enabling reading from multiple angles and distances without manual repositioning.
Solution Approach 2:
The patent changes the reading parameters by introducing a positioning contour with geometric features (coplanar conics) that provide reference information for automatic position and orientation detection. This allows the system to adapt reading parameters based on the marker's actual position rather than requiring the marker to match predetermined reading conditions.
2Loss of information
If barcode markers are read by optical reading terminals, then data can be retrieved, but information is lost when the barcode is incorrectly positioned or deformed
Solution Approach 1:
The patent incorporates a positioning contour with geometric features that serve as a buffer against positioning errors and deformations. This contour provides redundant geometric information that allows the system to compensate for incorrect positioning or deformation of the coded data portion, preventing information loss before it occurs.
Solution Approach 2:
The positioning contour acts as an intermediary between the marker and the detection system. It provides geometric reference information that mediates the detection process, enabling the system to accurately locate and interpret the coded data even when the marker is deformed or incorrectly positioned, thus preventing information loss.
3Productivity
If operators manually position barcode markers in front of reading terminals, then reading can be performed, but the process is tedious and time-consuming
Solution Approach 1:
The patent enables the marker detection system to perform self-service by automatically detecting the marker's position and orientation through its geometric features. The system independently determines the marker's location in the image plane and adjusts reading parameters without requiring manual intervention, eliminating the time-consuming manual positioning process.
Solution Approach 2:
The patent replaces the mechanical manual positioning process with an automated optical-detection system. Instead of physically moving the marker to a predetermined position, the system uses image processing and geometric feature detection to automatically locate and read the marker, substituting mechanical operation with automated detection.
4Adaptability or versatility
If barcode markers require precise positioning, then accurate reading is possible, but the applications are limited to individual object scanning
Solution Approach 1:
The patent creates a universal marker detection system that can handle various applications beyond individual object scanning. The geometric positioning contour enables the system to detect and read multiple markers simultaneously in different positions and orientations, making it applicable to scenarios such as batch processing, conveyor belt scanning, and multi-object recognition.
Data Source
Figure 1~2
Figure 3~4
Figure 5~6H
AI summary
The invention relates to a method for the detection of a marker affixed to the surface of an object, comprising the following operations: acquisition (40) of a photographic image (10) of a zone containing at least one marker (11); extraction of contours from the photographic image; detection of a marker-positioning contour from among the aforementioned contours, which corresponds to a set of confocal conics having a predetermined form; modelling of an image of the confocal conics in the form of a matrix comprising at least two symmetric matrices of order 3; analysis of said matrices in order to determine a perspective correction for the photographic image; detection, in the perspective-corrected photographic image, of an indexing element associated graphically with the positioning contour of the marker, and rotation-correction of the photographic image; detection, in the perspective- and rotation-corrected photographic image, of encoded data graphically associated with the positioning contour of the marker, and decoding (70) of said encoded data. The invention also relates to a marker-detection system using said method.