Sensor Mapping to Global Coordinates via Marker Grid Homography
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object detection and tracking systems face challenges in real-time processing of multiple objects in large spaces, particularly in busy environments, due to computational intensity and the inability to determine physical locations of objects within images, and they struggle with handing off tracking information between sensors and distinguishing between closely spaced individuals.
Innovation Solution
A tracking system that generates homographies to map pixel locations from sensors to physical locations in a global coordinate system, allowing for efficient object tracking, shelf position calibration, and interaction detection using marker grids and weight sensors, enabling seamless handoff of tracking information and accurate assignment of items to individuals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Difficulty of detecting and measuring
If image processing techniques are used to identify objects in busy environments, then object identification capability is improved, but computational intensity increases significantly
Solution Approach 1:
The patent divides the identification process into two stages: first, detect key points (corners, intersections) of marker grids which are structurally defined and easier to identify; second, use these key points to determine physical locations. This segmentation reduces computational complexity compared to identifying all features of objects in busy environments.
Solution Approach 2:
The patent introduces marker grids as intermediary objects with known physical locations and distinctive visual patterns. These markers serve as mediators between the camera sensor and the physical space, enabling location determination without complex object recognition algorithms.
2Measurement precision
If feature comparison is performed for every person in an image to identify a specific person, then identification accuracy is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary action by detecting key points of marker grids and calculating their physical locations in advance. This preprocessing step creates a mapping between image coordinates and physical space coordinates, so that subsequent object identification only requires coordinate transformation rather than full feature comparison.
Solution Approach 2:
The patent creates a virtual copy of the physical space in the image coordinate system through homography transformation. This allows the system to work with transformed coordinates rather than performing complex feature matching, significantly reducing processing time while maintaining accuracy.
3Area of stationary object
If multiple cameras are installed to cover large physical spaces, then tracking coverage is improved, but system complexity increases
Solution Approach 1:
The patent merges information from multiple cameras by establishing a common global coordinate system. Each camera's marker grid detections are transformed into the global coordinate system using homography matrices, allowing seamless integration of data from multiple sensors without complex calibration procedures.
Solution Approach 2:
The marker grid system serves multiple functions: it provides reference points for homography calculation, enables location determination in any camera's field of view, and facilitates handoff between cameras. This universal reference system simplifies the multi-camera setup compared to dedicated calibration procedures for each sensor.
4Measurement precision
If information from each camera is processed independently and then combined, then tracking accuracy within each field of view is improved, but processing efficiency decreases
Solution Approach 1:
The patent transforms the problem from processing multiple independent 2D image coordinates to a unified 3D physical space coordinate system. By introducing the global coordinate system as an intermediate dimension, the system can efficiently combine information from multiple cameras through coordinate transformation rather than complex data fusion.
Data Source
AI summary
An object tracking system includes a sensor and a tracking system. The sensor is configured to capture a first frame of a global plane for at least a portion of a marker grid in a space. The tracking system is configured to receive a first coordinate in the global plane for a first corner of a marker grid, to determine a second coordinate in the global plane for the first marker on the marker grid, and to determine a third coordinate in the global plane where the second marker on the marker grid. The tracking system is further configured to determine a first pixel location for the first marker, to determine a second pixel location for the second marker, and to generate a homography based on the second coordinate for the first marker, the third coordinate for the second marker, the first pixel location, and the second pixel location.