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

Image identification method

A technology of image recognition and recognition method, which is applied in the field of image recognition, can solve problems such as collision of vehicles in front, lack of target type, and inability to accurately determine vehicles in front, and achieve the effect of little noise influence

Inactive Publication Date: 2020-09-15
ANHUI HUITENG INTELLIGENT TRANSPORTATION TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The advanced driving assistance system is a system that uses the sensors installed in the car to perceive the surrounding environment during the driving process of the car, and through calculation and analysis to let the driver perceive possible dangers in advance, which can effectively increase the driving comfort of the car And safety, in the advanced driving assistance system, the position of the vehicle in front is important data. In one way, the distance of the vehicle in front can be measured by radar. However, the cost of radar is high, and there is no distinction between target types. The accurate determination of the position of the vehicle in front cannot be realized, but the image of the vehicle in front is obtained through the image acquisition device, and the position of the vehicle in front is obtained through image analysis. After the position of the vehicle in front is obtained, it cannot be compared with the position of the driving vehicle. It is very easy to collide with the vehicle in front when it is fast, so there is still potential danger

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
  • Image identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] A kind of image recognition method, its recognition method comprises the following steps:

[0027] A. Obtain the driving image of the vehicle to be identified;

[0028] B. Identify and record the overall shape of the vehicle and the bottom edge of the rear car in the image of the vehicle to be identified, and enter the information into the in-vehicle analysis sensor and computing center;

[0029] C. Calculate the distance between the analyzed and processed vehicle information and the driving vehicle, and obtain accurate data.

Embodiment 2

[0031] In embodiment one, add following operation:

[0032] In Step A, the following information will be identified in detail:

[0033] a. Vehicle geometry: When a road vehicle is viewed from the rear, it contains many horizontal structures such as rear windows, trunks, and bumpers. A vehicle detection method based on geometric structures can also be proposed; daytime vehicle positioning needs to consider the shadow problem under the vehicle. Its advantage is that all potential vehicles can be detected;

[0034] b. Shadows under the vehicle: the texture of the vehicle is smoother than that of the surrounding environment; almost all wheels are along the central axis, this feature can well distinguish the vehicle from the environment, and is less affected by noise;

[0035] c. Texture symmetry: almost all wheels are along the central axis, this feature can well distinguish the vehicle from the environment, and is less affected by noise;

[0036] d. Color information taillights...

Embodiment 3

[0042] In embodiment two, add following operation:

[0043] In step B, all the information of the vehicle entered into the computing center is analyzed and processed, and before the target object in the driving image of the vehicle to be recognized is recognized, the driving image of the vehicle to be recognized is preprocessed.

[0044] A kind of image recognition method, its recognition method comprises the following steps:

[0045] A. Obtain the driving image of the vehicle to be identified;

[0046] B. Identify and record the overall shape of the vehicle and the bottom edge of the rear car in the image of the vehicle to be identified, and enter the information into the in-vehicle analysis sensor and computing center;

[0047] C. Calculate the distance between the analyzed and processed vehicle information and the driving vehicle, and obtain accurate data.

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 discloses an image identification method. The identification method comprises the following steps: acquiring a driving image of a to-be-identified vehicle; identifying and recording theoverall shape of the vehicle and the bottom edge of the rear vehicle in the to-be-identified vehicle image, and inputting information into an in-vehicle analysis sensor and a computing center; and calculating the distance position between the analyzed and processed vehicle information and the driving vehicle. According to the invention, the front vehicle data obtained in the vehicle driving process and the vehicle driving images of other multiple target objects are processed; detailed information is analyzed and processed; accurate data obtainable, a driver can be reminded to carry out corresponding operation, meanwhile, an optical flow method can be adopted to calculate the relative movement of a vehicle and a background, the position of the vehicle can also be determined, and due to thefact that divergent optical flow can be generated, the method is more effective when the vehicle moving in the opposite direction is detected, and convergent flow generated when the vehicle leaves thevehicle or overtakes the vehicle can also be detected easily.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to an image recognition method. Background technique [0002] Image recognition refers to the technology of using computers to process, analyze and understand images to identify targets and objects in various modes. In general industrial use, industrial cameras are used to take pictures, and then software is used to make images according to the grayscale difference of the pictures. Further identification processing. [0003] The advanced driving assistance system is a system that uses the sensors installed in the car to perceive the surrounding environment during the driving process of the car, and through calculation and analysis to let the driver perceive possible dangers in advance, which can effectively increase the driving comfort of the car And safety, in the advanced driving assistance system, the position of the vehicle in front is important data. In one way, the ...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62G07C5/08
CPCG07C5/0866G06V20/56G06V2201/08G06F18/214
Inventor 冯程程
Owner ANHUI HUITENG INTELLIGENT TRANSPORTATION TECH CO LTD