Dual Optical Imaging Object Tracking for Barcode Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Checkout systems often fail to accurately identify items, either by misreading barcodes or incorrectly tagging items, leading to a need for improved item identification accuracy.
Innovation Solution
A method and system utilizing dual optical imaging assemblies and a controller to accurately track objects by mapping the location of an object in one image to its predicted location in another, filtering image data based on moving objects and stationary areas, and using timestamp correlations to enhance barcode reader accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single barcode reader is used, then the system is simple, but item identification accuracy is insufficient
Solution Approach 1:
The patent combines multiple optical imaging assemblies (first and second imaging assemblies with different FOVs) into a single barcode reader system. The controller integrates images from both imaging assemblies, correlating object locations across multiple fields of view to improve identification accuracy while maintaining a unified device structure.
Solution Approach 2:
The controller acts as an intermediary that receives images from multiple optical imaging assemblies, processes the image data, correlates object locations across different fields of view, and generates the final identification result. This mediator component enables accurate tracking without requiring complex direct integration between imaging assemblies.
2Measurement precision
If multiple optical imaging assemblies are used, then object tracking accuracy is improved, but data processing complexity increases
Solution Approach 1:
The system divides the imaging task into segments by using multiple optical imaging assemblies with different fields of view. Each imaging assembly captures a specific portion of the scanning area, and the controller segments the processing by first identifying objects in one FOV, then correlating their locations to predicted positions in other FOVs, reducing the overall processing complexity.
Solution Approach 2:
The controller performs preliminary actions by first decoding indicia in images from one optical imaging assembly to identify objects of interest, then uses this information to predict object locations in images from other imaging assemblies. This preliminary identification simplifies subsequent processing by focusing only on relevant objects rather than analyzing all image data from all assemblies simultaneously.
3Reliability
If all image data from multiple assemblies is processed, then comprehensive object detection is achieved, but processing time increases
Solution Approach 1:
Instead of processing all image data from multiple optical imaging assemblies equally, the system applies partial action by focusing processing resources on images where objects are actually detected. Once an object is identified in one FOV, the system only processes corresponding regions in other FOVs based on predicted locations, rather than analyzing entire images from all assemblies.
Solution Approach 2:
The system uses feedback mechanisms where the detection of objects in one field of view provides information that guides processing of other fields of view. The controller uses decoded indicia and object locations from initial image processing to generate predicted locations in subsequent images, creating a feedback loop that reduces redundant processing and accelerates overall detection while maintaining completeness.
Data Source
AI summary
Methods for accurate object tracking are disclosed herein. An example the method includes receiving, from a first optical imaging assembly having a first field of view (FOV), a first image captured over the first FOV and based on a decode of an indicia associated with an object of interest, identifying the object of interest within the first image. The method further includes determining a location of the object of interest within the first image and mapping the location of the object of interest within the first image to a predicted location of the object of interest within a second image, the second image being received from a second optical imaging assembly having a second FOV and the second image being captured over the second FOV.