Circle Segment Detection Using Adaptive Resolution Accumulators

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current circle detection methods in driver assistance systems face challenges in achieving real-time processing and low resource/energy consumption, particularly when used on standard hardware like smartphones, due to high energy consumption and computational intensity.

Innovation Solution

The method involves detecting gradients, scaling gradient vectors with respective radii, and accumulating endpoints in accumulator arrays with reduced resolution for larger radii, allowing for faster processing and reduced memory requirements, thereby eliminating the need for specialized hardware.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If high-resolution accumulator arrays are used for circle detection, then detection precision is improved, but processing time increases and energy consumption increases

Engineering Contradiction:
Improvecircle detection precisionVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the circle detection process by creating multiple accumulator arrays with different resolutions, each dedicated to detecting circles of specific radius ranges. Small-radius circles use high-resolution arrays for precision, while large-radius circles use low-resolution arrays for speed, eliminating the need to process all data at maximum resolution.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different regions of the parameter space (radius ranges) are assigned different quality levels (resolutions). The patent applies high resolution locally to small-radius circle detection and low resolution locally to large-radius circle detection, optimizing the trade-off between precision and speed for each specific detection task.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If high-resolution accumulator arrays are used for circle detection, then detection precision is improved, but memory requirements increase

Engineering Contradiction:
Improvecircle detection precisionVSAvoidmemory requirements
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent divides the single large high-resolution accumulator array into multiple smaller arrays with different resolutions. This segmentation reduces the total memory footprint while maintaining high-resolution detection capability for small circles, as each array only stores data for its specific radius range.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Memory resources are allocated efficiently by assigning high resolution (more memory) only where needed (small-radius detection) and low resolution (less memory) where less precision is required (large-radius detection), optimizing overall memory utilization.

Inventive Principle:
Principle #3Local quality

3Device complexity

If standard hardware is used for circle detection, then device complexity is reduced, but processing speed decreases

Engineering Contradiction:
Improvehardware complexityVSAvoidprocessing speed
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The patent changes the resolution parameter of accumulator arrays based on the radius parameter being detected. This parameter adaptation allows standard hardware to achieve high processing speeds for large circles (using low-resolution arrays) while maintaining adequate precision for small circles, eliminating the need for specialized high-performance hardware.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP2887264B1Circle segment and form detection
Publication Date: 2018.10.03 FRAUNHOFER GESELLSCHAFT ZUR FORDERUNG DER ANGEWANDTEN FORSCHUNG EV
  • EP2887264B1 patent drawingFigure 1
  • EP2887264B1 patent drawingFigure 2
  • EP2887264B1 patent drawingFigure 3A

AI summary

A circular segment detection device is configured to detect gradients, yielding gradient vectors, and to scale these gradient vectors by their respective radii. The resulting endpoints of these scaled gradient vectors are then accumulated in accumulator arrays assigned to those radii. The resolution of the accumulator arrays decreases as the radius increases.