Parking Slot Detection Using Perception Maps and Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing parking systems face challenges in accurately identifying and localizing parking spots, especially in diverse environments with varying layouts and conditions, and lack adaptability without relying on pre-defined markings, and struggle with unstructured parking areas.
Innovation Solution
Utilizing elevated perception maps and Artificial Neural Networks (ANNs) to detect parking slot objects, incorporating multiple functional layers for infrastructure and object detection, and dynamically generating maps with real-time sensor data to enhance accuracy and adaptability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional sensor technologies and manual methods are used for parking detection, then the system complexity is low, but the measurement precision of parking space availability is inaccurate
Solution Approach 1:
The patent replaces traditional mechanical sensor technologies with computer vision algorithms that process visual data from cameras. The system uses image processing and neural networks to detect parking spaces, substituting physical sensors with optical-based computational methods that provide higher precision without proportionally increasing system complexity
Solution Approach 2:
The patent creates a digital representation (perception map) of the physical parking environment by processing visual images. This virtual copy allows the system to analyze and detect parking spaces in the digital model, achieving accurate detection through algorithmic processing rather than direct physical measurement
2Reliability
If basic sensor technologies are used, then the ease of operation is simple, but the reliability of parking information is poor
Solution Approach 1:
The patent introduces an intermediary perception map that processes and validates parking information before presenting it to users. This intermediate layer filters and verifies detection results, ensuring reliable information while maintaining simple user interaction through a unified interface that handles the complexity internally
3Loss of time
If manual parking search methods are used, then the device complexity is low, but the loss of time for finding parking spaces is high
Solution Approach 1:
The patent implements continuous real-time monitoring and detection of parking spaces using computer vision algorithms that process video streams or sequential images. The system continuously updates the perception map and notifies users of available spaces, eliminating the need for repeated manual searches and reducing total parking search time
Solution Approach 2:
The system provides automated detection, classification, and notification of parking spaces without requiring user intervention. The computer vision system independently identifies and tracks parking space availability, delivering information directly to users and eliminating time-consuming manual searching
Data Source
AI summary
A method, a computerized apparatus and a computer program product for parking slot detection. The method comprises obtaining an elevated perception map of a surrounding area around a vehicle. Each pixel in the elevated perception map is associated with a predetermined relative location to the vehicle. The elevated perception map comprises a plurality of functional layers. Values of pixels at different layers indicate an infrastructure segment or object located at corresponding relative locations to the vehicle. The method further comprises performing parking slot object detection in the elevated perception map. The parking slot object detection is performed using an Artificial Neural Network (ANN) to obtain one or more detected parking slot objects. The one or more detected parking slot objects are provided to autonomous driving systems and utilized to autonomously park vehicles in vacant parking slots that are selected therefrom.