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

Method and device for identifying road surface mark and monocular camera

A monocular camera and marking technology, applied in the field of intelligent transportation, can solve the problem of no road marking, and achieve the effect of accurately identifying road markings

Active Publication Date: 2020-08-11
毫末智行科技有限公司
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Therefore, there is currently no effective way to accurately recognize road markings in a visual camera system using a monocular camera

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
  • Method and device for identifying road surface mark and monocular camera
  • Method and device for identifying road surface mark and monocular camera
  • Method and device for identifying road surface mark and monocular camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] figure 2 is a schematic flowchart of the method for identifying road markings according to Embodiment 1 of the present invention. Such as figure 2 As shown, the method for identifying pavement markings may include the following steps:

[0059] Step S210, acquiring the original image captured by the monocular camera on the vehicle.

[0060] Step S220, determining the middle area where the object is located and the left and right areas located on both sides of the middle area in the original image.

[0061] In a preferred embodiment, the step S220 further includes: performing image preprocessing on the original image to obtain a corresponding difference image; acquiring edge points in the difference image; grouping to obtain several edge point groups; setting the middle area to include the edge point groups in the difference image; and setting the left area and the right area on the left and right sides of the middle area respectively.

[0062] The method of convertin...

Embodiment 2

[0086] The method of Embodiment 1 of the present invention can accurately identify road markings in most scenes, but in some very complex scenes, for example, when involving multiple types of point lines and cubic objects, the recognition of the method of Embodiment 1 of the present invention Reliability will be reduced. Among them, a ghost object is the most typical road marking, which can be a dotted line, but not a real cube object, because it can only be drawn on the road. In this regard, on the basis of the first embodiment, the second embodiment of the present invention introduces more parameters to better identify road markings.

[0087] Figure 6 It is a schematic flow chart of the method for identifying road markings in Embodiment 2 of the present invention. On the basis of the method in Embodiment 1, the method may further include the following steps:

[0088] Step S610, calculating the first intensity standard deviation.

[0089] Wherein, the first intensity stan...

Embodiment 3

[0120] On the basis of the first embodiment, the third embodiment of the present invention provides another method for recognizing road markings, which can be performed alone or in cooperation with the first embodiment to more comprehensively recognize the road markings. Figure 8 It is a schematic flow chart of the pavement marking recognition method in Embodiment 3 of the present invention, as Figure 8 As shown, the following steps may be included:

[0121] Step S810, performing image preprocessing on the original image to obtain a corresponding difference image.

[0122] Step S820, acquiring edge points in the difference image.

[0123] Step S830, grouping the edge points according to the continuity of the edge points, and estimating the edge line of the object according to each obtained group.

[0124] Figure 9 is a schematic diagram of grouping edge points in an embodiment of the present invention, wherein the formed edge group is defined as a combination of continuo...

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 the technical field of intelligent transportation, and provides a method and a device for identifying a road surface mark, and a monocular camera. The method comprises the following steps of: acquiring an original image shot by the monocular camera on a vehicle; determining a middle region where an object is located and a left region and a right region which are located onthe two sides of the middle region in the original image; acquiring image intensity distributions of the original image in the vertical direction in the left region, the right region and the middle region; and determining whether the object is a road surface mark by comparing the image intensities of the left region or the right region relative to the middle region. The method can achieve the purpose of accurately identifying the road surface mark.

Description

technical field [0001] The invention relates to the technical field of intelligent transportation, in particular to a method, a device and a monocular camera for recognizing road markings. Background technique [0002] At present, vehicles with AD (Autonomous driving, autonomous driving) functions or ADAS (Advanced Driver Assistance System, advanced driver assistance system) have begun to be gradually introduced to the market, which has greatly promoted the development of intelligent transportation. In the existing technology, the sensors supporting AD / ADAS mainly include radar, visual camera system, laser radar, ultrasonic sensor, etc. Among them, the visual camera system is the most widely used because it can obtain the same two-dimensional image information as human vision, and with the With the expansion of the application range, the requirements for the stereoscopic camera system in terms of detection rate, misidentification, and distance accuracy will become higher and...

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): G06K9/00G06K9/20G06K9/62
CPCG06V20/588G06V20/56G06V10/22G06F18/22G06V10/457G06V10/50G06T7/11G06V10/225G06T2207/10004G06T2207/30256
Inventor 宫原俊二
Owner 毫末智行科技有限公司