Center Location in Target Object Regions via Connected Region Algorithms

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current image processing methods for locating the center of a target object region in virtual reality or augmented reality applications, such as eyeball tracking, are inefficient and require significant data storage, making them unsuitable for hardware implementation.

Innovation Solution

An image processing method that acquires a binary image of the target object region using a four-connected region algorithm and an octuple-connected region algorithm to extract the boundary line, determine connected regions, and calculate the center of the target object region, while allocating storage regions for efficient hardware implementation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If conventional image processing methods are used for locating the center of target object region, then the center can be located, but the processing efficiency is low and data storage requirements are significant

Engineering Contradiction:
Improveprocessing efficiencyVSAvoiddata storage requirements
Core Design Contradiction:
ProductivityVSQuantity of substance

Solution Approach 1:

The patent extracts only the essential boundary information of the target object using four-connected region algorithm, and further extracts connected region characteristics using octuple-connected region algorithm. This extraction of only necessary features (boundary points and connected regions) rather than processing the entire image reduces both computational load and storage requirements while maintaining center location accuracy.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent segments the image processing task into distinct stages: first extracting boundary lines using four-connected region algorithm, then identifying connected regions using octuple-connected region algorithm, and finally calculating the center from these segmented features. This segmentation allows each algorithm to work on simplified data structures rather than the complete image, improving efficiency and reducing storage needs.

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If complex algorithms are used for center location, then accuracy can be improved, but hardware implementation becomes difficult

Engineering Contradiction:
Improvecenter location accuracyVSAvoidhardware implementation complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces complex continuous mathematical operations with discrete digital algorithms suitable for hardware implementation. By using four-connected and octuple-connected region algorithms that operate on discrete pixel grids, the solution transforms the problem from continuous image processing to discrete digital logic operations, making it amenable to FPGA or ASIC implementation while maintaining precision.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent performs preliminary extraction of boundary points and connected regions before calculating the center location. This preliminary action simplifies the data structure to only essential features (boundary coordinates and connected region markers), reducing the computational complexity of the subsequent center calculation while preserving accuracy.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3767520B1Method, device, equipment and medium for locating center of target object region
Publication Date: 2024.02.07 BOE TECHNOLOGY GROUP CO LTD
  • EP3767520B1 patent drawingFigure 1~2
  • EP3767520B1 patent drawingFigure 3~4
  • EP3767520B1 patent drawingFigure 5A~5B

AI summary

There are provided in the present disclosure an image processing method, apparatus, device and medium for locating a center of a target object region. The image processing method includes: acquiring a binary image including the target object region; extracting a boundary line of the target object region from the binary image, wherein the boundary line includes a plurality of boundary points; selecting one of the plurality of boundary points as an initiation point, and determining a first connected region, wherein a starting point of the first connected region is the initiation point; determining the center of the target object region based on the first connected region.