Event-Based Barcode Localization for Faster Moving-Code Decoding

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional code readers face challenges in quickly identifying and decoding machine-readable indicia due to relative motion between the reader and the object, which is exacerbated by the computational complexity of spatial filter kernels used in localization algorithms.

Innovation Solution

Utilizing an event-based camera to acquire and group events, forming clusters to determine edges and bounding boxes around linear barcodes, thereby focusing on a region-of-interest for decoding.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If spatial filter kernels are used in localization algorithms to identify machine-readable indicia, then localization accuracy is improved, but processing speed deteriorates due to computational complexity

Engineering Contradiction:
Improvelocalization accuracyVSAvoidprocessing speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent segments the image processing task by dividing it into event-based preprocessing (capturing only luminance changes) and traditional image processing (applying spatial filters only to relevant regions). This segmentation allows the computationally intensive spatial filter kernels to operate only on event-triggered regions rather than the entire image, thereby maintaining localization accuracy while significantly improving processing speed for moving objects.

Inventive Principle:
Principle #1Segmentation

2Reliability

If conventional image processing methods are used to decode moving barcodes, then decoding completeness is improved, but decoding speed deteriorates due to the need to process the entire image

Engineering Contradiction:
Improvedecoding completenessVSAvoiddecoding time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent extracts only the regions containing machine-readable indicia by using event-based camera data to identify areas with luminance changes (which correspond to moving barcodes). This extraction allows the system to apply decoding algorithms only to these specific regions rather than processing the entire image, thereby maintaining decoding completeness while reducing decoding time for moving objects.

Inventive Principle:
Principle #2Taking out (Extraction)

3Reliability

If the entire image is processed to ensure no barcode is missed, then detection reliability is improved, but processing efficiency deteriorates

Engineering Contradiction:
Improvedetection reliabilityVSAvoidprocessing efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent performs preliminary action by using the event-based camera to pre-identify regions containing moving barcodes before applying traditional image processing algorithms. This preliminary detection step filters out irrelevant image regions, allowing subsequent processing to focus only on areas with potential barcodes, thereby maintaining detection reliability while significantly improving processing efficiency.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20260073171A1Event-based code localizer and method thereof executed by a code reader
Publication Date: 2026.03.12 DATALOGIC IP TECH
  • US20260073171A1 patent drawing
  • US20260073171A1 patent drawing
  • US20260073171A1 patent drawing

AI summary

One embodiment of a method of identifying a linear barcode may include acquiring multiple events from an event-based camera imaging an object on which a linear barcode is positioned within the scene. The events may be grouped to form clusters of the events. A box may be formed around the linear barcode so as to identify a region-of-interest in which to process the linear barcode for decoding, thereby increasing speed for decoding the linear barcode as the code reader may focus on the region-of-interest within the box. In an embodiment, edges of features may be identified from the group events. Consecutive edges with the same or similar angle may be identified, thereby being indicative of the linear barcode.