CN115220029B - Visibility recognition method and device and automobile - Google Patents

Visibility recognition method and device and automobile Download PDF

Info

Publication number
CN115220029B
CN115220029B CN202111413731.5A CN202111413731A CN115220029B CN 115220029 B CN115220029 B CN 115220029B CN 202111413731 A CN202111413731 A CN 202111413731A CN 115220029 B CN115220029 B CN 115220029B
Authority
CN
China
Prior art keywords
visibility
target object
value
standard
preset
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111413731.5A
Other languages
Chinese (zh)
Other versions
CN115220029A (en
Inventor
梁华文
詹灯辉
郑淳允
张文智
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Automobile Group Co Ltd
Original Assignee
Guangzhou Automobile Group Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangzhou Automobile Group Co Ltd filed Critical Guangzhou Automobile Group Co Ltd
Priority to CN202111413731.5A priority Critical patent/CN115220029B/en
Publication of CN115220029A publication Critical patent/CN115220029A/en
Application granted granted Critical
Publication of CN115220029B publication Critical patent/CN115220029B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/02Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
    • G01S13/06Systems determining position data of a target
    • G01S13/08Systems for measuring distance only
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88Radar or analogous systems specially adapted for specific applications
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88Lidar systems specially adapted for specific applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides a visibility recognition method, a visibility recognition device and an automobile, which comprise the steps of acquiring forward radar target object recognition data of the automobile and image data of a forward camera; determining a distance value between a target object and a current vehicle according to the forward radar target object identification data, and inquiring a preset visibility standard database through the distance value between the target object and the current vehicle to obtain a visibility standard value corresponding to the distance value between the target object and the current vehicle; determining a credible characteristic value of the target object through a preset recognition algorithm according to the image data of the forward camera; and comparing the credible characteristic value of the target object with the visibility standard value, and determining the current visibility value according to the comparison difference value. According to the invention, the distance between the target object and the vehicle millimeter wave radar is utilized, the image recognition is carried out through the camera and is compared with the standard visibility, so that the visibility of the distance between the current position and the target object is obtained, and the perception of the vehicle to the environment is improved.

Description

Visibility recognition method and device and automobile
Technical Field
The invention relates to the technical field of visibility recognition of vehicle driving assistance to environment, in particular to a visibility recognition method and device and an automobile.
Background
The visibility test equipment on the market at present is generally two kinds, namely a transmission instrument and a scattering instrument. A transmittometer is an instrument that calculates visibility by measuring transparency of the atmosphere, and the principle is to select a fixed reference and test the visibility therebetween. The scatterometer then directly measures the scattered light intensity from a small sample volume to derive visibility.
Visibility measuring equipment based on a transilluminator and a scatterometer has the following disadvantages for automobiles: additional hardware cost of the vehicle and related matched service cost are required to be increased; for the whole vehicle, the volume and the weight of the equipment are increased; the transilluminator and scatterometer are precision optical instruments suitable for mounting on non-moving objects. However, vibration is generated at any time in the running process of the vehicle, so that deformation is caused, and the precision of equipment is reduced; the current solution is only applicable where the relative positions of the test sample and the detector are fixed. If it is desired to achieve efficient visibility recognition without increasing costs and overcoming current vehicle usage conditions, it is desirable to consider if the visibility problem is addressed by vehicle radar and cameras.
Disclosure of Invention
The invention aims to provide a visibility recognition method, a visibility recognition device and an automobile, and solves the technical problem that if the visibility is recognized through an on-board radar and a camera.
In one aspect, a visibility identifying method is provided, including:
Acquiring forward radar target object identification data of a vehicle and image data of a forward camera, wherein the forward radar target object identification data at least comprises distance data of a target object and a current vehicle;
Determining a distance value between a target object and a current vehicle according to the forward radar target object identification data, and inquiring a preset visibility standard database through the distance value between the target object and the current vehicle to obtain a visibility standard value corresponding to the distance value between the target object and the current vehicle;
Determining a credible characteristic value of the target object through a preset recognition algorithm according to the image data of the forward camera;
and comparing the credible characteristic value of the target object with the visibility standard value, and determining the current visibility value according to the comparison difference value.
Preferably, the visibility standard database is obtained by:
selecting a training target object;
Under the condition that the standard visibility is 1, shooting an image of the training target object within a preset distance through a camera;
Carrying out gray square statistics on the training target object image through a preset statistical algorithm to obtain a credible characteristic value of the picture in the corresponding distance;
and forming a visibility standard database by the training objects, the corresponding distances and the corresponding credible characteristic values.
Preferably, the determining, according to the image data of the forward camera, the trusted characteristic value of the target object through a preset recognition algorithm specifically includes:
Reading image data of a forward camera;
Matching the images of the forward cameras through a preset image matching algorithm, and extracting pictures with common characteristics with the targets in the visibility standard database;
and carrying out gray square statistics on the extracted picture through a preset statistical algorithm to obtain a trusted characteristic value corresponding to the image data.
Preferably, the obtaining the current visibility value specifically includes:
outputting the difference between the credible characteristic value of the target object and the visibility standard value as light attenuation;
and inquiring a preset visibility standard database according to the obtained light attenuation to obtain the current visibility value.
On the other hand, a visibility recognition device is provided, so as to implement the visibility recognition method, which comprises the following steps:
The system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring forward radar target object identification data of a vehicle and image data of a forward camera, and the forward radar target object identification data at least comprises distance data of a target object and a current vehicle;
The standard value acquisition module is used for determining the distance value between the target object and the current vehicle according to the forward radar target object identification data, and inquiring a preset visibility standard database through the distance value between the target object and the current vehicle to obtain a visibility standard value corresponding to the distance value between the target object and the current vehicle;
The visibility determining module is used for determining a credible characteristic value of the target object through a preset recognition algorithm according to the image data of the forward camera; and comparing the credible characteristic value of the target object with the visibility standard value, and obtaining the current visibility value according to the comparison difference value.
Preferably, the standard value obtaining module is further used for selecting a training target object;
Under the condition that the standard visibility is 1, shooting an image of the training target object within a preset distance through a camera;
Carrying out gray square statistics on the training target object image through a preset statistical algorithm to obtain a credible characteristic value of the picture in the corresponding distance;
and forming a visibility standard database by one or more training objects, corresponding distances and corresponding credible characteristic values.
Preferably, the visibility determination module is further configured to read image data of the forward camera;
Matching the images of the forward cameras through a preset image matching algorithm, and extracting pictures with common characteristics with the targets in the visibility standard database;
and carrying out gray square statistics on the extracted picture through a preset statistical algorithm to obtain a trusted characteristic value corresponding to the image data.
Preferably, the visibility determination module is further configured to output a difference between the trusted characteristic value of the target object and the visibility standard value as an optical attenuation amount;
and inquiring a preset visibility standard database according to the obtained light attenuation to obtain the current visibility value.
On the other hand, the automobile is also provided, and the visibility is identified by the visibility identification method.
In summary, the embodiment of the invention has the following beneficial effects:
According to the visibility recognition method, the visibility recognition device and the automobile, the distance of the target object is recognized by utilizing the vehicle-mounted millimeter wave radar, then the image recognition is carried out through the camera and the image recognition is compared with the standard visibility, so that the visibility of the distance from the current position to the target object is obtained, the perception of the vehicle to the environment is improved, and the advanced driving assistance system of the vehicle can better serve the traveling of people.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that it is within the scope of the invention to one skilled in the art to obtain other drawings from these drawings without inventive faculty.
Fig. 1 is a schematic flow chart of a visibility recognition method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a visibility recognition device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings, for the purpose of making the objects, technical solutions and advantages of the present invention more apparent.
Fig. 1 is a schematic diagram of an embodiment of a visibility recognition method according to the present invention.
In this embodiment, the method comprises the steps of:
Acquiring forward radar target object identification data of a vehicle and image data of a forward camera, wherein the forward radar target object identification data at least comprises distance data of a target object and a current vehicle; the image data of the forward camera is the image data of the front of the vehicle collected by the vehicle-mounted camera, wherein the image data at least comprises the same target object as the forward radar target object identification data, and the image data is mainly used for determining the credible characteristic value of the real-time target object through the image data, so that the real-time visibility value is determined through comparison with the standard value; the radar in this embodiment includes at least millimeter wave radar. That is, the object identification data of the forward millimeter wave radar of the vehicle is called, so as to obtain the distance data between the object and the current vehicle, the update frequency of the distance data should be greater than or equal to the frame frequency of the camera, so as to obtain a more accurate distance d between the object and the camera within the same frame, and the data are directly transmitted to the bus by the radar sensor.
Further, determining a distance value between a target object and a current vehicle according to the forward radar target object identification data, and inquiring a preset visibility standard database through the distance value between the target object and the current vehicle to obtain a visibility standard value corresponding to the distance value between the target object and the current vehicle; that is, the distance value and the credible feature standard value of the target object in the case where the visibility is 1 are determined from the acquired vehicle forward millimeter wave radar target object identification data.
In a specific embodiment, the step of determining the visibility standard database includes: selecting a training target object; taking an image of the training target object within a preset distance through a camera under the condition that the standard visibility (GB/T33673 standard) is 1; carrying out gray square statistics on the training target object image through a preset statistical algorithm to obtain a credible characteristic value of the picture in the corresponding distance; and forming a visibility standard database by one or more training objects, corresponding distances and corresponding credible characteristic values. The target object is generally a license plate of a front vehicle, and the credible characteristic value is the requirement of GA36-2018 motor vehicle license plate of the people's republic of China on the license plate.
Further, determining a credible characteristic value of the target object through a preset recognition algorithm according to the image data of the forward camera; that is, the trusted characteristic value of the target object is picked up by the image recognition algorithm.
In a specific embodiment, reading image data of a forward camera; matching the images of the forward cameras through a preset image matching algorithm, and extracting pictures with common characteristics with the targets in the visibility standard database; and carrying out gray square statistics on the extracted picture through a preset statistical algorithm to obtain a trusted characteristic value corresponding to the image data. In this embodiment, the image data P0 of the forward camera can be read by the in-vehicle ECU; the vehicle-mounted ECU matches the images of the forward cameras through an image matching method, and cuts out a picture P1 with common characteristics with the target objects in the database; and carrying out gray square statistics on the P1 to obtain a trusted characteristic value of the picture in the corresponding distance.
Further, the credible characteristic value of the target object is compared with the visibility standard value, and the current visibility value is determined according to the comparison difference value. The method comprises the steps of comparing the picked-up credible characteristic image with visibility standard data of equal distance d to obtain light attenuation amounts of the picked-up credible characteristic image and the visibility standard data of equal distance d, and calculating the visibility according to the light attenuation amount in a specified distance of a root, wherein the calculation process can be calculated through a preset formula or can be obtained through inquiring a preset standard value in a preset standard database.
Fig. 2 is a schematic diagram of an embodiment of a visibility recognition device according to the present invention.
In this embodiment, it includes:
The data acquisition module is used for acquiring forward radar target object identification data of the vehicle and image data of a forward camera, wherein the forward radar target object identification data at least comprises distance data of a target object and a current vehicle.
The standard value acquisition module is used for determining the distance value between the target object and the current vehicle according to the forward radar target object identification data, and inquiring a preset visibility standard database through the distance value between the target object and the current vehicle to obtain a visibility standard value corresponding to the distance value between the target object and the current vehicle.
Specifically, the standard value acquisition module is also used for selecting a training target object; under the condition that the standard visibility is 1, shooting an image of the training target object within a preset distance through a camera; carrying out gray square statistics on the training target object image through a preset statistical algorithm to obtain a credible characteristic value of the picture in the corresponding distance; and forming a visibility standard database by the training objects, the corresponding distances and the corresponding credible characteristic values.
The visibility determining module is used for determining a credible characteristic value of the target object through a preset recognition algorithm according to the image data of the forward camera; and comparing the credible characteristic value of the target object with the visibility standard value, and obtaining the current visibility value according to the comparison difference value.
Specifically, the visibility determination module is further used for reading image data of the forward camera; matching the images of the forward cameras through a preset image matching algorithm, and extracting pictures with common characteristics with the targets in the visibility standard database; and carrying out gray square statistics on the extracted picture through a preset statistical algorithm to obtain a trusted characteristic value corresponding to the image data. The visibility determination module is further configured to output a difference between the trusted characteristic value of the target object and the visibility standard value as an optical attenuation amount; and inquiring a preset visibility standard database according to the obtained light attenuation to obtain the current visibility value.
The invention further provides an automobile, and the visibility is identified through the visibility identification method.
For the implementation process of the visibility recognition device and the automobile, reference may be made to the specific implementation process of the visibility recognition method, which is not described herein.
In summary, the embodiment of the invention has the following beneficial effects:
According to the visibility recognition method, the visibility recognition device and the automobile, the distance of the target object is recognized by utilizing the vehicle-mounted millimeter wave radar, then the image recognition is carried out through the camera and the image recognition is compared with the standard visibility, so that the visibility of the distance from the current position to the target object is obtained, the perception of the vehicle to the environment is improved, and the advanced driving assistance system of the vehicle can better serve the traveling of people.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.

Claims (7)

1. A visibility recognition method, comprising:
Acquiring forward radar target object identification data of a vehicle and image data of a forward camera, wherein the forward radar target object identification data at least comprises distance data of a target object and a current vehicle;
Determining a distance value between a target object and a current vehicle according to the forward radar target object identification data, and inquiring a preset visibility standard database through the distance value between the target object and the current vehicle to obtain a visibility standard value corresponding to the distance value between the target object and the current vehicle; the visibility standard value represents a credible characteristic value corresponding to the target object in a preset distance under standard visibility;
Determining a credible characteristic value of the target object through a preset recognition algorithm according to the image data of the forward camera; the determining the trusted characteristic value of the target object specifically includes: reading image data of a forward camera; matching the images of the forward cameras through a preset image matching algorithm, and extracting pictures with common characteristics with the targets in the visibility standard database; carrying out gray square statistics on the extracted picture through a preset statistical algorithm to obtain a trusted characteristic value corresponding to the image data;
and comparing the credible characteristic value of the target object with the visibility standard value, and determining the current visibility value according to the comparison difference value.
2. The method of claim 1, wherein the visibility criteria database is obtained by:
selecting a training target object;
Under the condition that the standard visibility is 1, shooting an image of the training target object within a preset distance through a camera;
Carrying out gray square statistics on the training target object image through a preset statistical algorithm to obtain a credible characteristic value of the picture in the corresponding distance;
and forming a visibility standard database by one or more training objects, corresponding distances and corresponding credible characteristic values.
3. The method of claim 2, wherein determining the current visibility value based on the comparison difference value comprises:
outputting the difference between the credible characteristic value of the target object and the visibility standard value as light attenuation;
and inquiring a preset visibility standard database according to the obtained light attenuation to obtain the current visibility value.
4. A visibility identifying device for implementing the method according to any one of claims 1-3, comprising:
The system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring forward radar target object identification data of a vehicle and image data of a forward camera, and the forward radar target object identification data at least comprises distance data of a target object and a current vehicle;
The standard value acquisition module is used for determining the distance value between the target object and the current vehicle according to the forward radar target object identification data, and inquiring a preset visibility standard database through the distance value between the target object and the current vehicle to obtain a visibility standard value corresponding to the distance value between the target object and the current vehicle; the visibility standard value represents a credible characteristic value corresponding to the target object in a preset distance under standard visibility;
The visibility determining module is used for determining a credible characteristic value of the target object through a preset recognition algorithm according to the image data of the forward camera; comparing the credible characteristic value of the target object with the visibility standard value, and obtaining a current visibility value according to the comparison difference value;
The determining the trusted characteristic value of the target object specifically includes: reading image data of a forward camera; matching the images of the forward cameras through a preset image matching algorithm, and extracting pictures with common characteristics with the targets in the visibility standard database; and carrying out gray square statistics on the extracted picture through a preset statistical algorithm to obtain a trusted characteristic value corresponding to the image data.
5. The apparatus of claim 4, wherein the standard value acquisition module is further configured to select a training target;
Under the condition that the standard visibility is 1, shooting an image of the training target object within a preset distance through a camera;
Carrying out gray square statistics on the training target object image through a preset statistical algorithm to obtain a credible characteristic value of the picture in the corresponding distance;
and forming a visibility standard database by the training objects, the corresponding distances and the corresponding credible characteristic values.
6. The apparatus of claim 5, wherein the visibility determination module is further configured to output a difference between the trusted characteristic value of the object and the visibility standard value as an amount of light attenuation;
and inquiring a preset visibility standard database according to the obtained light attenuation to obtain the current visibility value.
7. An automobile, characterized in that the visibility is identified by a method according to any one of claims 1-3.
CN202111413731.5A 2021-11-25 2021-11-25 Visibility recognition method and device and automobile Active CN115220029B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111413731.5A CN115220029B (en) 2021-11-25 2021-11-25 Visibility recognition method and device and automobile

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111413731.5A CN115220029B (en) 2021-11-25 2021-11-25 Visibility recognition method and device and automobile

Publications (2)

Publication Number Publication Date
CN115220029A CN115220029A (en) 2022-10-21
CN115220029B true CN115220029B (en) 2024-07-12

Family

ID=83606858

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111413731.5A Active CN115220029B (en) 2021-11-25 2021-11-25 Visibility recognition method and device and automobile

Country Status (1)

Country Link
CN (1) CN115220029B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110542909A (en) * 2019-09-03 2019-12-06 北京领骏科技有限公司 Atmospheric visibility detection method and electronic equipment
CN112017243A (en) * 2020-08-26 2020-12-01 大连信维科技有限公司 Medium visibility identification method

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4608631B2 (en) * 2005-06-08 2011-01-12 国立大学法人名古屋大学 Image processing device for vehicle, driving support device
DE102011105074A1 (en) * 2011-06-21 2011-12-22 Daimler Ag Method for determining visual range for vehicle, involves determining surrounding of vehicle by camera, where contrast dimensions are determined for object depicted in images, where visual range is determined from contrast dimensions
US10228460B1 (en) * 2016-05-26 2019-03-12 Rockwell Collins, Inc. Weather radar enabled low visibility operation system and method
JP6548147B2 (en) * 2017-02-21 2019-07-24 マツダ株式会社 Vehicle control device

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110542909A (en) * 2019-09-03 2019-12-06 北京领骏科技有限公司 Atmospheric visibility detection method and electronic equipment
CN112017243A (en) * 2020-08-26 2020-12-01 大连信维科技有限公司 Medium visibility identification method

Also Published As

Publication number Publication date
CN115220029A (en) 2022-10-21

Similar Documents

Publication Publication Date Title
US10726576B2 (en) System and method for identifying a camera pose of a forward facing camera in a vehicle
CN107202983B (en) Automatic braking method and system based on image recognition and millimeter wave radar fusion
CN102612634B (en) A calibration apparatus, a distance measurement system and a calibration method
EP1592985B1 (en) Device for a motor vehicle used for the three-dimensional detection of a scene inside or outside said motor vehicle
US7756298B2 (en) Image processing device for vehicle
CN104392629B (en) The method and apparatus of inspection vehicle distance
KR101735557B1 (en) System and Method for Collecting Traffic Information Using Real time Object Detection
CN110609274B (en) Distance measurement method, device and system
EP3252712B1 (en) Vision system and method for a motor vehicle
CN111452799B (en) Driving behavior evaluation method and system
CN114037972B (en) Target detection method, device, equipment and readable storage medium
WO2020064543A1 (en) Vision system and method for a motor vehicle
JP2020153797A (en) Detector, method for measuring distance, method for detection, program, and mobile body
CN115220029B (en) Visibility recognition method and device and automobile
CN117826179A (en) System and method for classifying and removing object artifacts in light detection and ranging point clouds to enhance detection
CN116148801A (en) Millimeter wave radar-based target detection method and system
CN114136356A (en) Parameter acquisition test system, method, device and computer readable storage medium
CN102589515A (en) Foggy-weather distance measurement method and device thereof as well as distance pre-warning method and device thereof
CN118363018A (en) Noise estimation method, integrated circuit and related equipment
CN111091077B (en) Vehicle speed detection method based on image correlation and template matching
CN209400694U (en) Vehicle ranging system based on binocular camera
CN105699981B (en) A kind of hardware and software fitting method for measuring ceiling of clouds and thickness
WO2024152952A1 (en) Method and apparatus for determining degree of bumping of road surface, and device, medium and vehicle
CN114114183A (en) Vehicle-mounted SAR speed estimation method, system and terminal based on deep learning
CN114279410A (en) Camera ranging method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant