Vehicle Image Processing Device for Parking Space Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing devices for automatic driving systems often falsely detect parking spaces across stripe areas indicative of parking-unavailable zones, leading to incorrect parking space identification.
Innovation Solution
An image processing device equipped with a delimiting line detection unit, an exclusion determination unit, and a parking space detection unit, which identifies parallel lines adjacent to delimiting line candidates and designates areas with these lines as parking-unavailable, preventing the detection of parking spaces across stripe areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If delimiting line detection is performed based on image data to identify parking spaces, then parking space detection capability is improved, but false detection of parking spaces across stripe areas occurs
Solution Approach 1:
The detection area is segmented into multiple regions based on the detected stripe pattern. The exclusion determination unit divides the image into a first area (without stripe) and a second area (with stripe), allowing independent processing and detection decisions for each region. This segmentation prevents false detection across stripe areas while maintaining detection capability in valid parking zones.
Solution Approach 2:
The stripe area is extracted and identified as a separate entity from the parking space detection process. The exclusion determination unit extracts the stripe pattern detection result and uses it to generate an exclusion area that is removed from the parking space detection candidate regions, eliminating the source of false detection.
2Reliability
If stripe area detection is added to prevent false parking space detection, then detection reliability is improved, but device complexity increases
Solution Approach 1:
The stripe pattern detection function is merged with the existing delimiting line detection process. Both detections are performed using the same image data and processing pipeline, and the results are combined in the exclusion determination unit to generate the final parking space detection output, reducing overall system complexity.
Solution Approach 2:
The detection algorithm is designed to perform multiple functions: detecting delimiting lines, detecting stripe patterns, and determining exclusion areas, all within a single integrated processing system. This multi-functionality eliminates the need for separate dedicated stripe detection hardware or software modules.
Data Source
AI summary
An image processing device includes: a delimiting line detection unit configured to detect a delimiting line candidate based on image data obtained by capturing a surrounding of a vehicle; an exclusion determination unit configured to determine whether there is a parking-unavailable area in which parking of the vehicle is not permitted; and a parking space detection unit configured to detect the parking space based on the delimiting line candidate. In a case where plural parallel lines that are adjacent to the delimiting line candidate and that have a predetermined angle to the delimiting line candidate is detected, the exclusion determination unit regards an area in which the plural parallel lines are provided as the parking-unavailable area, and prohibits the parking space detection unit from detecting the parking space across the delimiting line candidate adjacent to the parking-unavailable area.