Parking space camera height detection method based on edge detection and perspective transformation
A technology of perspective transformation and edge detection, applied in the field of parking camera recognition
Pending Publication Date: 2020-10-27
REDNOVA INNOVATIONS INC
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The object of the present invention is to: provide a parking space camera height detection method based on edge detection and perspective transformation, solve the problem of automatic camera height detection, and improve the parking space recognition effect
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0029] Such as figure 1 As shown, the present invention is based on the height detection method of the parking space camera of edge detection and perspective transformation, and this method specifically comprises the following steps:
[0030] Step 1: Capture the picture of the on-site parking space through the camera;
[0031] Step 2: Convert the image in step 1 to grayscale and smooth to reduce high-frequency noise;
[0032] Step 3: Use the canny function of opencv to identify all edges contained in the picture;
[0033] Step 4: Use the trapezoidal mask to cut out the location of the parking space in the picture, and remove all the content of the picture outside the trapezoidal mask;
[0034] Step 5: Use the Hough transform to find the edge lines in the picture, generate the border of the parking space, and obtain the visual map of the parking space;
[0035] Step 6: Calculate the coordinates of the junction points between the borders on both sides and the trapezoidal mask...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a parking space camera height detection method based on edge detection and perspective transformation, and relates to the field of parking camera shooting recognition. The method includes converting the picture into gray scale and smoothing to reduce high-frequency noise; identifying all edges contained in the picture by adopting a canny function of opencv; cutting out theposition of the parking space in the picture by using a trapezoidal mask, and completely removing the content of the picture except the trapezoidal mask; spotting edge lines in the picture through Hough transform, and forming a frame of the parking space; calculating the coordinates of the intersection points of the two side frames and the trapezoidal mask, and calculating the distance between thefront frame and the rear frame of the parking space, namely the visual length Lv of the parking space; and calculating the height H of the camera through the visual length Lv and by adopting a trigonometric function. The problem of automatic detection of the camera height is solved, and the parking space recognition effect is improved.
Description
technical field [0001] The invention relates to the field of parking camera recognition, in particular to a method for detecting the height of a parking camera based on edge detection and perspective transformation. Background technique [0002] The high-level video system is a system based on computer vision and deep artificial intelligence technology. Compared with traditional intelligent parking systems (such as geomagnetic induction), it has obvious advantages such as high accuracy and the ability to recognize license plates and vehicle characteristics. Existing high-level video systems generally use high-definition cameras and edge processing units to monitor roadside parking spaces in real time. If a vehicle enters or exits, it will collect license plate, vehicle parking time and other information for analysis and storage. [0003] In order to reduce system cost, each high-definition camera needs to monitor as many parking spaces as possible, and capture and recognize ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/13G06T7/70G06T5/00
CPCG06T7/0004G06T7/13G06T7/70G06T2207/10016G06T5/70
Inventor 王铭宇丁元一吴晨王堃
Owner REDNOVA INNOVATIONS INC