Unlock instant, AI-driven research and patent intelligence for your innovation.

Vehicle face localization method and system

A positioning method and vehicle face technology, applied in the field of image recognition, can solve the problems of large vehicle shooting angle, incomplete vehicle body shooting, unable to effectively complete the vehicle face positioning, etc., achieving the effect of small calculation amount and improving positioning speed.

Active Publication Date: 2019-08-23
GUANGDONG ANJUBAO DIGITAL TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the special application scenario of the parking lot, there are often problems with large vehicle shooting angles and incomplete body shooting
Methods based on adboost or deep learning cannot effectively complete the positioning of car faces with large angles and incomplete body shots

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Vehicle face localization method and system
  • Vehicle face localization method and system
  • Vehicle face localization method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Embodiment 1 of the present invention provides a vehicle face positioning method, see figure 1 As shown in FIG. 1 , it is a schematic flow diagram of the implementation flow of the vehicle face positioning method in Embodiment 1 of the present invention. Such as figure 1 As shown, the vehicle face location method of the present embodiment 1 includes the following steps:

[0041] Step S101: Perform edge detection on the target image in the first direction to obtain an edge detection result map in the first direction, and the target image is an image for which vehicle face positioning is currently required;

[0042] Among them, the amount of data can be greatly reduced by performing edge detection on the target image, and information that can be considered irrelevant is eliminated, and important structural attribute information (texture information) in the target image is retained.

[0043] In one of the embodiments, the step of performing edge detection on the target i...

Embodiment 2

[0076] In order to achieve more accurate positioning of the vehicle face, Embodiment 2 of the present invention provides a vehicle face positioning method, see figure 2 As shown in FIG. 2 , it is a schematic flow diagram of the implementation flow of the vehicle face positioning method in Embodiment 2 of the present invention. Such as figure 2 As shown, the vehicle face positioning method in the second embodiment also includes the following steps on the basis of the first embodiment above:

[0077] Step S201: Perform affine transformation on the first vehicle face positioning result map according to the inclination angle of the connected domain to obtain the correction result of the first direction;

[0078] Specifically, by performing affine transformation on the first vehicle face positioning result map according to the inclination angle of the connected domain, the correction of the first direction of the vehicle face can be completed, and the correction result of the fi...

Embodiment 3

[0108] According to the vehicle face positioning method in the above embodiments, the present invention further provides a vehicle face positioning system. Figure 15 It is a schematic diagram of the composition and structure of the vehicle face positioning system according to the third embodiment of the present invention. Such as Figure 15 As shown, the vehicle face positioning system in Embodiment 3 includes a type edge detection unit 301, a texture acquisition unit 302, a projection unit 303, a search unit 304 and a rough positioning unit 305, wherein:

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

No PUM Login to View More

Abstract

The invention relates to a vehicle face positioning method and system, the method comprising: performing edge detection on a target image in a first direction to obtain an edge detection result map in the first direction, and the target image is an image currently requiring vehicle face positioning ; Acquire the texture-rich area map in the first direction according to the edge detection result map; project the texture-rich area map in the first direction to obtain the first projection histogram; project the texture-rich area map in the second direction to obtain the second direction Two projection histograms, the second direction is perpendicular to the first direction; search the peak area of ​​the first projection histogram to obtain the first peak area; search the peak area of ​​the second projection histogram to obtain the second peak area; according to the first peak area and the second peak area determine the first car face location result map. By adopting the scheme of the invention, the positioning of the vehicle face with a large angle and incomplete photographing of the vehicle body can be effectively and quickly completed.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a vehicle face positioning method and system. Background technique [0002] In vehicle feature analysis applications such as parking lot entrances and exits, in order to intelligently analyze unlicensed vehicles, it is necessary to determine the position of the vehicle face (the area from the lower end of the front hood of the vehicle to the bottom end of the vehicle). [0003] Most of the currently popular image-based vehicle positioning algorithms are based on adboost (iterative algorithm, the core idea of ​​which is to train different classifiers (weak classifiers) for the same training set, and then combine these weak classifiers to form a more efficient model. Strong final classifier (strong classifier)) or deep learning, adboost needs a complete vehicle profile to effectively detect the vehicle, and the algorithm based on deep learning also has certain requirement...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/32G06K9/46
CPCG06V20/584G06V10/25G06V10/44G06V10/507
Inventor 田飞王训平李文锋
Owner GUANGDONG ANJUBAO DIGITAL TECH