Video-Based Parking Detection Spatial Calibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for detecting available parking spaces in multi-space on-street parking configurations are costly and difficult to maintain, and existing video-based solutions do not accurately account for the effects of object location on the image plane, leading to noise and incorrect vehicle detection.
Innovation Solution
A video-based system performs spatial calibration to map pixel distances in video frames to actual distances, allowing for accurate detection and classification of vehicles and parking spaces by using Look Up Tables to resize spatial information and compute the length of objects and spaces between them.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor-based solutions are used for detecting available parking spaces, then detection accuracy is improved, but installation cost and maintenance cost increase
Solution Approach 1:
The patent replaces sensor-based mechanical detection systems with a video-based optical detection system. Instead of using expensive in-ground or ceiling sensors, the system uses standard video cameras to capture images of parking spaces and processes these images computationally to determine vehicle occupancy and space availability, thereby reducing hardware costs while maintaining detection accuracy
Solution Approach 2:
The patent creates a digital copy of the parking space environment through video imaging. By capturing visual information and processing it through image analysis algorithms, the system creates a virtual representation of parking space occupancy status, eliminating the need for physical sensors in each parking space while maintaining accurate detection
2Measurement precision
If sensor-based solutions are used for detecting available parking spaces, then detection accuracy is improved, but maintenance disruption to street traffic increases
Solution Approach 1:
The patent replaces in-ground or ceiling sensors that require physical access and maintenance in the parking region with a remotely located video camera system. The camera can be positioned away from the parking spaces and accessed without disrupting street traffic, while still providing accurate detection through image processing
3Device complexity
If video cameras are used to monitor parking spaces without spatial calibration, then device cost is reduced, but measurement precision deteriorates due to perspective distortion
Solution Approach 1:
The patent performs spatial calibration as a preliminary action before actual parking space detection. By first capturing images of calibration objects with known dimensions and computing the relationship between image pixel dimensions and real-world dimensions, the system establishes a conversion factor that corrects for perspective distortion. This preliminary calibration enables accurate measurement of parking spaces and vehicles without requiring expensive specialized hardware
Solution Approach 2:
The patent changes the parameter relationship between image pixels and real-world dimensions through calibration. By computing a scaling factor or transformation parameters from calibration images, the system adjusts the measurement parameters to account for camera perspective and focal length, enabling accurate measurement using standard video equipment
4Device complexity
If video cameras are used to monitor multiple parking spaces, then device cost is reduced, but measurement precision deteriorates due to objects appearing smaller at greater distances
Solution Approach 1:
The patent compensates for the perspective effect where objects appear smaller at greater distances by computing calibration parameters that account for the camera's field of view and focal length. These parameters are used to scale the measured pixel dimensions to accurate real-world dimensions, ensuring that vehicles and parking spaces at different distances are measured consistently and accurately
Data Source
AI summary
A method for determining parking availability includes receiving video data from a sequence of frames taken from an image capture device monitoring a parking area. The method includes detecting at least one object located in the parking area. The method includes determining boundaries of the parking area. The boundaries include at least an inner boundary relative to the image capture device and an outer boundary relative to the image capture device. The outer boundary is substantially parallel to the inner boundary. The method further includes computing a length of at least one of the object and a space between objects using an object pixel for each of the inner and outer boundaries. Using the computed length, The method includes determining a parking availability in the parking area. The method includes outputting a notice of the parking availability to a user.