Parking Frame Line Detection by Excluding Quasi-Edge Lines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional image processing devices face difficulties in correctly detecting partition lines due to the presence of working lines, which are mistakenly identified as edge points, leading to erroneous recognition of parking frames.
Innovation Solution
An image processing device comprising an extraction unit, a selection unit, and an exclusion unit that extracts and selects edge lines, identifies quasi-edge lines forming non-paint-out regions, and excludes them to accurately detect partition lines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If edge points are detected based on luminance value variations, then edge detection sensitivity is improved, but working lines are mistakenly detected as partition lines
Solution Approach 1:
The patent segments the detection process into multiple stages: initial edge point detection, candidate line extraction, and final partition line identification. By dividing the detection process, the system can apply different criteria at each stage to distinguish working lines from partition lines while maintaining edge detection sensitivity.
Solution Approach 2:
Instead of directly identifying partition lines from all detected edge lines, the patent inverts the approach by first identifying and excluding working lines based on their characteristic features (such as position relative to vehicle, luminance patterns), then detecting partition lines from the remaining candidates. This inversion resolves the contradiction by eliminating false positives before final detection.
2Adaptability or versatility
If all extracted edge lines are used for partition line detection, then detection coverage is improved, but detection accuracy deteriorates due to inclusion of quasi-edge lines
Solution Approach 1:
The patent extracts and excludes quasi-edge lines (working lines) from the set of all extracted edge lines before performing partition line detection. By removing these interfering elements, the system maintains broad detection coverage for actual partition lines while eliminating sources of detection error.
Solution Approach 2:
The patent applies different quality criteria to different regions of the image. Working lines typically appear in specific locations (such as near vehicle boundaries or in non-parking zones) with characteristic luminance properties. By applying location-aware and luminance-aware filtering, the system selectively excludes quasi-edge lines while preserving true partition lines.
Data Source
AI summary
An image processing device includes: an extraction unit which extracts edge lines based on image data taken by an imaging device by shooting a neighborhood of a vehicle; a selection unit which selects, as a pair of edge lines, edge lines that satisfy a prescribed condition from the extracted edge lines; an exclusion unit which, in a case where a non-paint-out region exists between the pair of edge lines, excludes quasi-edge lines that form the non-paint-out region from the pair of edge lines; and a detection unit which detects a partition line that partitions a parking frame based on the pair of edge lines from which the quasi-edge lines are excluded.