Symbology Accelerator Edge Processing for Object Tracking

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Centralized processing units in frictionless shopping systems struggle to process large volumes of image data quickly, leading to inaccurate tracking and potential failure in recognizing events such as object pickup or exit from a venue.

Innovation Solution

Deployment of detector stations with imaging assemblies, transceivers, and symbology accelerators that analyze image data to detect objects with symbols, transmit data packets to a remote server, and perform edge processing to reduce the processing burden on the central controller, allowing for more accurate tracking and efficient data analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a centralized processing unit is used to process image data, then the system structure is simple, but the processing speed is insufficient and tracking accuracy deteriorates

Engineering Contradiction:
Improvesystem structureVSAvoidprocessing speed
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The patent divides the centralized processing system into distributed detector stations, each equipped with its own symbology accelerator processor. This segmentation allows parallel processing of image data across multiple independent units, dramatically increasing overall processing speed while maintaining manageable complexity through modular architecture

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new processing dimension by adding dedicated symbology accelerator processors at the detector station level, creating a hierarchical processing structure that operates alongside the centralized controller. This dimensional addition enables simultaneous local and central processing, resolving the speed-accuracy contradiction

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Device complexity

If a centralized processing unit is used, then device complexity is low, but tracking accuracy and event recognition reliability worsen

Engineering Contradiction:
Improvesystem structureVSAvoidtracking accuracy
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

By segmenting the processing function into distributed detector stations with local symbology accelerators, the system achieves parallel processing that improves tracking accuracy and event recognition reliability while maintaining structural simplicity through standardized modular units

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The detector stations with symbology accelerator processors act as intermediaries between the imaging assemblies and the centralized controller, performing preliminary image analysis and symbol decoding to improve overall system reliability while reducing the burden on the central unit

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS10803607B2Systems and methods tracking objects within a venue using a symbology accelerator
Publication Date: 2020.10.13 ZEBRA TECHNOLOGIES CORP
  • US10803607B2 patent drawing
  • US10803607B2 patent drawing
  • US10803607B2 patent drawing

AI summary

An apparatus, system and method for tracking objects within a venue. A plurality of detector stations are disposed throughout the venue. Each detector station includes an imaging assembly, a transceiver, and a symbology accelerator having least one processor. The processor is configured to obtain image data captured by the imaging assembly and analyze the image data to detect one or more objects. Each of the one or more objects includes a symbol indicative of an object identifier. The processor is configured to decode each of the symbols to obtain the respective identifier and associate the detected objects or respective symbols with a respective physical location within the venue. For each of the one or more objects, the processor is configured to transmit, via the transceiver to a remote server, at least one data packet including the respective physical location and the identifier for the object.