Border Tracing Method for Low-Power Image Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing border detection algorithms are complex and resource-intensive, making them challenging to implement on devices with limited computing power, such as mobile phones, especially for real-time video processing, which affects battery life and efficiency.

Innovation Solution

A method for border detection in images that forms contiguous blocks of pixel positions, estimates border direction perpendicular to differing pixel conditions, and uses linear interpolation to store border locations, allowing for efficient tracing and reduced energy consumption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If complex border detection algorithms are used to achieve accurate border detection, then measurement precision is improved, but use of energy and device complexity increase

Engineering Contradiction:
Improveborder detection accuracyVSAvoidenergy consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent segments the image processing task by focusing only on border regions rather than processing the entire image. It identifies and processes only those pixel blocks where borders are likely to occur, dividing the computational workload into manageable segments that consume less energy while maintaining detection accuracy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by using different processing strategies for different regions of the image. It applies border detection algorithms only to specific blocks where borders are detected, rather than uniformly processing all image regions, thereby reducing overall energy consumption while preserving local detection precision.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If complex border detection algorithms are used to achieve accurate border detection, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
Improveborder detection accuracyVSAvoidalgorithm complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent reduces algorithmic complexity by segmenting the image into blocks and applying border detection only where necessary. This divides a potentially complex global processing task into simpler local operations that can be executed more efficiently on resource-constrained devices.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by performing border detection only on specific image blocks where borders are detected, rather than applying complex algorithms to the entire image. This partial processing approach maintains detection accuracy while reducing the overall computational complexity and resource requirements.

Inventive Principle:
Principle #16Partial or excessive action

3Productivity

If border detection is performed on real-time video to improve productivity, then productivity is improved, but use of energy and processing power increase

Engineering Contradiction:
Improvereal-time video processing capabilityVSAvoidenergy consumption
Core Design Contradiction:
ProductivityVSUse of energy by moving object

Solution Approach 1:

The patent enables real-time video processing by segmenting each video frame into blocks and applying border detection only to relevant blocks. This segmentation approach reduces the computational load per frame, allowing real-time processing while minimizing energy consumption on battery-powered devices.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies partial processing by focusing computational resources only on blocks where borders are detected in real-time video streams. This selective processing maintains high productivity for real-time applications while reducing overall energy consumption compared to processing entire video frames uniformly.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3143588B1Border tracing
Publication Date: 2019.07.31 STRING LABS
  • EP3143588B1 patent drawingFigure 1~2
  • EP3143588B1 patent drawingFigure 3~5
  • EP3143588B1 patent drawingFigure 6~7

AI summary

A method for scanning for borders in an image represented by pixels, the method including a first operation comprising: estimating an attribute for each of a first set of two adjacent pixel positions in the image; assessing whether a predetermined binary condition differs in respect of the two pixel positions, and if so determining that a border is present in the part of the image represented by pixels at those positions; and if a border is determined to be present in that part of the image, estimating the direction of the border as being perpendicular to a line joining the positions of the two pixels; and initiating tracing the border in that direction.