Parking Space Detection Using Skewed Polygon Anchor Boxes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional CNNs for parking space detection use axis-aligned rectangular anchor boxes, which fail to accurately represent non-rectangular parking spaces due to perspective projection, necessitating additional processing to delineate their bounds.
Innovation Solution
Utilizing a CNN to determine corner points of skewed polygons, such as quadrilaterals, with confidence values predicting entrance likelihoods and displacement values to accurately delineate parking spaces, and computing minimum aggregate distance for positive sample identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If axis-aligned rectangular anchor boxes are used for parking space detection, then the CNN output is simple and straightforward, but additional processing is necessary to accurately identify the bounds of parking spaces due to perspective projection
Solution Approach 1:
The patent changes the geometric parameters of the anchor boxes from axis-aligned rectangles to skewed quadrilaterals that can rotate and skew to match the perspective projection of parking spaces. This allows the detection output to directly represent the actual shape and orientation of parking spaces in the image, eliminating the need for additional post-processing to correct for perspective distortion.
Solution Approach 2:
The patent introduces rotational and skewing dimensions to the anchor box representation, transforming it from a simple 2D axis-aligned rectangle to a more complex quadrilateral form that can accommodate perspective transformations. This dimensional enhancement allows the anchor boxes to directly model the projected shape of parking spaces without requiring subsequent geometric corrections.
2Measurement precision
If additional processing is performed to accurately delineate parking spaces from conventional CNN output, then detection accuracy improves, but detection speed decreases
Solution Approach 1:
The patent performs the perspective correction and shape adjustment actions in advance by using skewed quadrilateral anchor boxes that are pre-configured to match the expected perspective projection of parking spaces. This preliminary action eliminates the need for subsequent post-processing steps to correct the detection output, thereby maintaining high detection accuracy while improving processing speed.
3Measurement precision
If skewed quadrilateral anchor boxes are used to directly represent parking spaces, then detection accuracy improves, but the complexity of the detection system increases
Solution Approach 1:
The patent modifies the anchor box parameters to include skew and rotation capabilities, transforming them from simple rectangles to quadrilaterals that can represent perspective-projected parking spaces. This parameter change enables direct and accurate representation of parking space boundaries while maintaining a relatively straightforward detection framework.
Data Source
AI summary
A neural network may be used to determine corner points of a skewed polygon (e.g., as displacement values to anchor box corner points) that accurately delineate a region in an image that defines a parking space. Further, the neural network may output confidence values predicting likelihoods that corner points of an anchor box correspond to an entrance to the parking spot. The confidence values may be used to select a subset of the corner points of the anchor box and/or skewed polygon in order to define the entrance to the parking spot. A minimum aggregate distance between corner points of a skewed polygon predicted using the CNN(s) and ground truth corner points of a parking spot may be used simplify a determination as to whether an anchor box should be used as a positive sample for training.