Parking Space Classification Using Deep Neural Network
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current parking assistance systems struggle to distinguish between legal and illegal parking spaces, often resulting in false positives and inability to determine correct parking maneuvers, especially with ultrasonic data, and require high computing capacity for camera-based systems.
Innovation Solution
A method utilizing a driver support system with a deep neural network (DNN) that classifies parking spaces into legal and illegal categories using a combination of first and second sensor data, including image data from a camera system, allowing for semi- or fully automatic parking maneuvers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ultrasonic sensors are used for parking space detection, then the system can detect parking-space-like partial regions, but it cannot distinguish between legal and illegal parking spaces resulting in high false positive rate
Solution Approach 1:
The patent combines ultrasonic sensor data with image data from camera systems to create a multi-sensor evaluation system. The classification unit integrates both data types to distinguish legal from illegal parking spaces, resolving the limitation of ultrasonic sensors alone which cannot differentiate parking space legality.
Solution Approach 2:
The patent introduces a classification unit as an intermediary component that processes and evaluates both ultrasonic sensor data and image data. This intermediary analyzes the combined information to determine whether detected parking-space-like regions are legal or illegal, thereby reducing false positives.
2Measurement precision
If camera systems with deep neural networks are used for parking space classification, then classification accuracy improves, but computational resource requirements increase
Solution Approach 1:
The system activates the deep neural network and full image processing only when ultrasonic sensors first detect a parking-space-like region. This partial action approach processes detailed image data only for promising candidates rather than continuously analyzing all surrounding areas, reducing overall computational load while maintaining high classification accuracy when needed.
Solution Approach 2:
The ultrasonic sensor system performs preliminary detection to identify potential parking spaces before the more computationally intensive camera system and deep neural network are activated. This preliminary filtering step reduces the number of regions requiring detailed image analysis, thereby lowering computational resource consumption.
Data Source
AI summary
The invention relates to a method for the classification of parking spaces in a surrounding region of a vehicle with a driver support system, wherein the vehicle comprises at least one first surroundings sensor and a second surroundings sensor, comprising the steps of receiving first sensor data out of the surrounding region by the driver support system from the at least one first surroundings sensor, recognizing a parking-space-like partial region of the surrounding region in the first sensor data, requesting second sensor data acquired by the at least one second surroundings sensor out of the parking-space-like partial region by the driver support system as soon as the parking-space-like partial region is recognized in the first sensor data, transmitting the requested second sensor data to a vehicle-side computing unit comprising a deep neural network (DNN), and classifying the parking-space-like partial region into categories with the DNN, wherein the categories comprise legal, parkable parking spaces and illegal, non-parkable parking spaces. The invention also relates to a driver support system, in particular a parking assistance system, for a vehicle for the acquisition of parking spaces. The invention further relates to a vehicle with a driver support system.