Parking Space Detection Using Motion Status and Contour-Machine Learning Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing parking space detection methods face challenges in stability and precision, particularly when dealing with varying angles of view, obstructions, low contrast, low illumination, and changes in lighting conditions, as well as movement of pedestrians and vehicles, which affect the accuracy and reliability of detection.
Innovation Solution
A parking space detection apparatus and method that combines contour and machine learning techniques, using motion statuses of images to ensure stability and performing clearing processing before using machine learning methods, allowing for efficient detection in various scenarios with high precision and noise suppression.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning methods are adopted for parking space detection, then detection precision is improved, but detection stability deteriorates under varying lighting conditions and scene changes
Solution Approach 1:
The system dynamically adapts the detection method based on scene conditions. When scene changes are detected (lighting variations, pedestrian movement, vehicle movement), the system switches from machine learning methods to contour detection methods, making the detection process dynamic and adaptive to environmental changes rather than static
Solution Approach 2:
The system changes the detection parameter (method selection) based on scene stability. By monitoring scene change parameters (lighting conditions, object movements), the system adjusts which detection algorithm to use, transforming from a fixed parameter approach to a variable parameter approach that optimizes for both precision and stability
2Productivity
If contour methods are adopted for parking space detection, then detection speed is improved, but detection precision deteriorates when parking spaces have many details or obstructions
Solution Approach 1:
The system dynamically selects between contour detection and machine learning detection based on scene complexity. When the scene is stable and simple, contour methods provide fast detection. When obstructions or complex details are present, the system switches to machine learning methods to maintain precision, making the detection speed adaptive rather than fixed
Solution Approach 2:
Scene change detection acts as an intermediary that determines which detection method to use. This intermediary mechanism analyzes scene conditions and mediates between the two detection methods, selecting the appropriate one based on current requirements for speed versus precision
3Measurement precision
If detection is performed on every frame, then detection precision is improved, but system resource consumption increases
Solution Approach 1:
Instead of continuous detection on every frame, the system performs detection periodically based on scene stability. When the scene is stable, detection is performed less frequently, conserving resources. When scene changes occur, detection frequency increases to maintain precision, creating a periodic rather than continuous detection pattern
Solution Approach 2:
The system uses scene change detection results to self-regulate its own detection frequency. By monitoring its own operational context, the system automatically adjusts resource allocation to detection tasks, performing full detection only when necessary rather than continuously consuming resources
Data Source
AI summary
Embodiments of the present disclosure provide a parking space detection apparatus and method, medium and electronic equipment, in which detection is performed based on motion statuses of images of parking spaces, thereby ensuring stability of the detection result; detection is performed by combining a contour method and a machine learning method, and clearing processing is performed before using the machine learning method when a scenario is unclear, to efficiently use advantages of the contour method and the machine learning method, with the processing speed being relatively fast and being applicable to various scenarios, and the detection precision is relatively high; and furthermore, performing the detection based on the stable image may suppress random noises, and improve the detection precision.