A kind of safety belt detection method
A detection method and technology for seat belts, applied in the field of intelligent transportation, can solve the problems of interfering with face detection, poor imaging quality of face images, and the influence of seat belt positioning, so as to reduce the false detection rate and missed detection rate, and improve the positioning accuracy. the effect of improving the accuracy
Active Publication Date: 2017-04-12
QINGDAO HISENSE TRANS TECH
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In the positioning part of the seat belt detection area, the face recognition technology is usually used to locate the driver's face, and the seat belt detection area is estimated according to the located face area, but the existence of the front window glass makes the people in the window The imaging quality of the face image is poor, the facial features are difficult to detect, and the detection is easy to fail; in addition, tree shades, sun visors, etc. will also interfere with face detection
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
[0043] Embodiment 1. The seat belt detection method of this embodiment mainly includes two parts: seat belt detection area positioning and seat belt positioning.
[0044] see figure 1 As shown, the specific steps for positioning the seat belt detection area are as follows:
[0045] Step 11: Start.
[0046] Step 12: Locate the rectangular area of the car body including the window according to the position and length of the license plate.
[0047] In the original bayonet picture, first locate the position of the license plate 3, then determine the coordinates (X0, Y0) of the center P0 of the license plate according to the position and length of the license plate 3; finally locate the rectangular area 1 of the car body including the window 2; the car body The scope of the rectangular area 1 is: the coordinates of P1 in the upper left corner of the rectangular area 1 of the car body are (X0-2W, Y0-5W), and the coordinates of P2 in the lower right corner are (X0+2W, Y0-2W), whe...
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 safety belt detection method which includes the steps of safety belt detection area location and safety belt location. Safety belt detection area location includes the steps that a rectangular car body area containing a car window is located according to the position and length of a license plate; an edge detection graph is obtained; an upper frame and a lower frame of the car window are selected from the edge detection graph; a right frame of the car window is selected; a rectangular area of a safety belt detection area is located. Safety belt location includes the steps that multiple communication areas are selected as safety belt candidate areas; edge detection is carried out on the safety belt detection area; line segments in each safety belt candidate area are detected by means of Hough transformation, wherein the included angle between each line segment and the horizontal line ranges from 30 degrees to 60 degrees; the confidence coefficient that every two line segments constitute a safety belt is calculated in each safety belt candidate area; the maximum confidence coefficient is selected, and whether the maximum confidence coefficient is within the safety belt is judged. According to the safety belt detection method, accuracy of safety belt detection area location and safety belt location is improved, so that accuracy of safety belt detection is improved.
Description
technical field [0001] The invention belongs to the technical field of intelligent transportation, and in particular relates to a safety belt detection method. Background technique [0002] Seat belt detection is an important part of vehicle violation detection in the field of intelligent transportation, which can effectively help traffic law enforcement officers to supervise the behavior of drivers wearing seat belts. [0003] At present, the seat belt detection method is mainly divided into two parts: seat belt detection area positioning and seat belt positioning. Seat belt detection area positioning is a prerequisite for seat belt positioning. In the positioning part of the seat belt detection area, the face recognition technology is usually used to locate the driver's face, and the seat belt detection area is estimated according to the located face area, but the existence of the front window glass makes the people in the window The imaging quality of the face image is p...
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 Patents(China)
IPC IPC(8): G06K9/00
CPCG06T7/11G06T7/13G06T7/168G06T2207/20061
Inventor 刘兵王国栋刘韶
Owner QINGDAO HISENSE TRANS TECH