Parking Space Image Processing Near Oblique Line Markings

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing parking assist systems struggle to accurately detect parking spaces next to oblique line areas, as the edges extracted become extremely short, making it difficult to recognize these spaces.

Innovation Solution

The image processing device employs multiple cameras and a sophisticated edge detection system, including a marker detector, oblique line detector, and parking frame detector, to identify parking spaces by scanning images from various angles and filtering edge segments, thereby accurately distinguishing between parking spaces and no-parking/stopping areas.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If the apparatus extracts oblique edges inclined by a reference angle with respect to the lateral direction of the image, then the edge extraction method is simple, but the extracted edge in an oblique line area becomes extremely short, making it difficult to recognize the oblique line area

Engineering Contradiction:
Improveedge extraction simplicityVSAvoidedge length accuracy
Core Design Contradiction:
Ease of manufactureVSMeasurement precision

Solution Approach 1:

The edge detection process is divided into multiple stages: first extracting edges at a reference angle, then separately detecting oblique lines by scanning in multiple directions. This segmentation allows simple initial extraction while adding complexity only where needed to handle oblique line areas properly.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new detection dimension by scanning images in multiple directions (not just at a fixed reference angle) to detect oblique lines. This multi-directional scanning approach captures edges that would otherwise be missed or truncated, extending edge detection beyond the limitations of single-angle extraction.

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

2Productivity

If the apparatus uses traditional edge extraction methods, then the processing is fast, but it cannot accurately detect parking spaces next to oblique line areas

Engineering Contradiction:
Improveprocessing speedVSAvoidparking space detection accuracy
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent performs preliminary edge extraction at a reference angle to quickly identify potential edges, then applies additional oblique line detection only in areas where needed. This preliminary action maintains processing speed while ensuring accurate detection of parking spaces adjacent to oblique line areas.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent applies different detection strategies to different regions: standard edge extraction is used in most areas for speed, while multi-directional oblique line scanning is applied specifically in regions where oblique lines are detected, ensuring high accuracy where needed without sacrificing overall processing efficiency.

Inventive Principle:
Principle #3Local quality

3Device complexity

If the apparatus extracts edges without considering oblique line patterns, then the detection process is simple, but it cannot distinguish between parking spaces and no-parking/stopping areas

Engineering Contradiction:
Improvedetection process complexityVSAvoidarea type identification
Core Design Contradiction:
Device complexityVSLoss of information

Solution Approach 1:

The patent detects changes in edge orientation and pattern (analogous to color changes) to distinguish different area types. By analyzing the angular characteristics and continuity of edges, the system identifies oblique line patterns that indicate no-parking/stopping areas versus parking spaces, preserving critical identification information.

Inventive Principle:
Principle #32Color changes

Solution Approach 2:

The patent introduces oblique line detection as an intermediary step between basic edge extraction and final parking space identification. This intermediary analysis of edge patterns and orientations provides the additional information needed to distinguish area types without requiring a completely complex detection system.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3696723B1Image processing device and image processing method
Publication Date: 2023.11.08 FAURECIA CLARION ELECTRONICS CO LTD
  • EP3696723B1 patent drawingFigure 1
  • EP3696723B1 patent drawingFigure 2
  • EP3696723B1 patent drawingFigure 3

AI summary

An image processing device (100) is equipped with a marker detector (111), an oblique line detector (112), and a parking frame detector (113). The marker detector (111) extracts, from an image, positive and negative edge segments that are aligned next to each other at a predetermined interval as a pair, and detects a parking space division marker (200) based on the pair. The oblique line detector (112) detects an edge on one side of an edge segment (single-edge segment) that is not extracted as the pair, and detects a presumed straight line based on the single-edge segment connected with an oblique line. The parking frame detector (113) detects neighboring edge segments based on the positive and negative edge segments as well as the single-edge segment of the presumed straight line, and detects a parking space based on a distance between the neighboring edge segments.