Spatiotemporal Parking Occupancy Detection via Line Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current video-based parking occupancy detection systems are not fast or efficient enough for large-scale deployment, requiring significant computational resources and data transmission, which leads to high operational costs and delays in processing.
Innovation Solution
A spatiotemporal image processing system that acquires and processes video frames locally, performing geometric transformations, noise reduction, and joint chromatic transformations to generate occupancy data, allowing for efficient detection without the need for extensive training on specific vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional video-based parking occupancy detection systems are used, then occupancy detection can be performed, but processing speed is slow and computational resources are excessive
Solution Approach 1:
The patent segments the video processing task by extracting only specific lines or regions from each video frame rather than processing the entire frame. This selective extraction reduces the amount of data that needs to be analyzed while still capturing sufficient information for occupancy detection, thereby improving processing speed and reducing computational resource consumption.
Solution Approach 2:
The patent extracts only the necessary features from video frames - specifically, lines or regions containing parking space information - and discards the rest of the frame data. This extraction approach eliminates unnecessary computational overhead while maintaining detection accuracy, resolving the contradiction between processing speed and resource usage.
2Measurement precision
If video data is transmitted to centralized processing centers, then occupancy detection can be performed, but data transmission delays occur and operational costs increase
Solution Approach 1:
The patent performs occupancy detection processing locally at the edge devices (such as cameras or gateways) rather than transmitting all video data to centralized centers. This preliminary action of processing data at the source eliminates transmission delays and reduces operational costs, while still achieving accurate occupancy detection through the selective line extraction method.
3Adaptability or versatility
If machine learning-based methods are used for parking occupancy detection, then detection can be performed, but offline training phases are time-consuming and require extensive vehicle and background samples
Solution Approach 1:
The patent replaces complex machine learning-based detection mechanisms with a simpler geometric and image processing approach. By using line extraction, geometric transformations, and template matching, the system achieves occupancy detection without requiring time-consuming offline training phases or extensive labeled datasets, thus maintaining adaptability while eliminating the time loss associated with training.
Data Source
AI summary
A spatiotemporal system and method for parking occupancy detection. The system can generally include suitable image acquisition, processing, transmission and data storage devices configured to carry out the method which includes generating and processing spatiotemporal images to detect the presence of an object in a region of interest, such as a vehicle in a parking stall.