CN104236866B - Car headlamp error information detection correcting method based on direction of traffic - Google Patents

Car headlamp error information detection correcting method based on direction of traffic Download PDF

Info

Publication number
CN104236866B
CN104236866B CN201410445638.6A CN201410445638A CN104236866B CN 104236866 B CN104236866 B CN 104236866B CN 201410445638 A CN201410445638 A CN 201410445638A CN 104236866 B CN104236866 B CN 104236866B
Authority
CN
China
Prior art keywords
headlamp
automobile
vehicle
traffic
characteristic point
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.)
Expired - Fee Related
Application number
CN201410445638.6A
Other languages
Chinese (zh)
Other versions
CN104236866A (en
Inventor
陈佩江
闵永军
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.)
Nanjing Forestry University
Original Assignee
Nanjing Forestry University
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 Nanjing Forestry University filed Critical Nanjing Forestry University
Priority to CN201410445638.6A priority Critical patent/CN104236866B/en
Publication of CN104236866A publication Critical patent/CN104236866A/en
Application granted granted Critical
Publication of CN104236866B publication Critical patent/CN104236866B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

The present invention is a kind of method that horizontal light beam direction of illumination measurement data to automatic tester for vehicle headlamp carries out error correction, is primarily adapted for use in vehicle performance test station the fully-automated synthesis to car headlamp.System is made up of the binocular camera installed in parking stall dead ahead to be checked, computer and headlamp aligner.The vehicle body characteristic point of automobile image is detected using morphological images processing method and Hough transform, the sequence of characteristic point three-dimensional coordinate is fitted, obtain vehicle traveling direction, angular deviation between analysis direction of traffic and traveling guidance line, is modified to the measurement data of the horizontal light beam direction of illumination of headlamp aligner.The present invention can carry out error correction automatically to the measurement data of car headlamp, improve the accuracy of testing result and the repeatability of measurement, be that the night safe traveling of automobile provides safeguard.

Description

Car headlamp error information detection correcting method based on direction of traffic
Technical field
The present invention relates to a kind of method that detection data to car headlamp carries out error correction, by analyzing vapour Angular deviation between the actual travel direction of car and the traveling guidance line of vehicle inspection station, the water to automatic tester for vehicle headlamp The measurement data of planar beam direction of illumination is modified, and reduces measurement error, and the present invention is right suitable for vehicle performance test station The fully-automated synthesis of car headlamp.
Background technology
Headlamp is to ensure one of vitals of automotive safety operation, and driving at night is played an important role safely.Before Illuminator detection is the big event evaluated to vehicle safety performance by vehicle inspection station, mainly detects the luminous strong of headlamp Whether degree and direction of illumination reach standard requirement, it is ensured that normally travel of the vehicle under night or visual condition unfavorable condition.
When detecting to headlamp on mobile testing line, usually using headlamp aligner, it is arranged on solid Determine on guide rail, tested vehicle opposite, light receiving surface and guide rail and the traveling guidance line of detector are parked in by certain measurement distance Vertically, and the longitudinal axis of vehicle are parallel with guide line.
The unqualified situation of detection of headlight mainly has two kinds:Luminous intensity is low and beam irradiation position deflection.Work as car Stand guide rail and traveling guidance line out of plumb not to timing, i.e. headlamp aligner, can cause headlight beam to shine Penetrate the measurement error in direction.This error causes the low qualified of detection of headlight, the consequence of testing result poor repeatability, Becoming affects one of factor of automobile at night safety traffic.Therefore, when detecting to car headlamp, in order to improve measurement The accuracy of data, needs to consider the problem that storing cycle is not positive, mainly has two kinds of solutions:Vehicle is ajusted and is repaiied with data Just.
Vehicle is ajusted and is referred to using auxiliary equipments such as automobile straightening devices, makes longitudinal direction of car axis and traveling guidance line weight Close, improve the accuracy of detection of headlight result, but this method increase testing cost, and the real-time for detecting is also poor.
Data correction is that the measurement data to headlamp aligner is corrected, using laser ranging technique or digital picture Treatment technology analyzes the longitudinal axis of automobile, compared with traveling guidance line, obtains the stand deviation of vehicle, to detecting number According to being modified.The method can reduce measurement error, but the longitudinal axis of vehicle are not necessarily consistent with travel direction, with headlamp Practical situations do not correspond.
The content of the invention
The present invention is a kind of data correcting method, on the basis of the travel direction of automobile, using machine vision technique, is analyzed Deviation between the actual travel direction of automobile and the traveling guidance line of vehicle inspection station, the automatically level to headlamp aligner The measurement data of Lighting direction is modified, and improves the accuracy of detection of headlight result and the repeatability of measurement.
The error correction principle of the present invention is as follows:
As shown in figure 1, when tested automobile is in preferable test position, should align with headlamp aligner 1, i.e., tested vapour The longitudinal axis (or travel direction) of car are vertical with headlamp aligner operation guide rail 2.But when actually detected, actual driving Direction 4 and preferably there is error unavoidably between traveling guidance line 3, it is assumed that both angular deviations are α, headlamp aligner is surveyed The headlamp horizontal light beam irradiation side-play amount for measuring is β, then actual side-play amount θ is:
Mono- α of θ=β (1)
In above formula, α, β, θ, just to represent left avertence, are negative indication right avertence.
The error correction scheme of the present invention is as follows:
As shown in Fig. 2 binocular camera 5 is arranged on parking stall dead ahead to be checked, in the state of vehicle steering is just returned, allow Automobile to be checked 6 travels about 3 meters from the slow straight ahead of original position, reaches detection of headlight and parks parking stall.During this period, clap The visual pattern of some frame automobiles is taken the photograph, computer 7 is transferred to, automobile image is processed by which, analyze the traveling side of automobile To calculating it and the angular deviation between traveling guidance line, the measurement result of automatic tester for vehicle headlamp entered according to this deviation Row amendment.
The process that implements of the present invention is divided into following five step:
(1) demarcation of Binocular Stereo Vision System
According to error correction scheme, system is built, carry out camera calibration, analyze the inner parameter of binocular camera, outer Portion's parameter and system structure parameter.
(2) the vehicle body feature point extraction of automobile image
During automobile slowly drives towards parking stall to be checked from original position, the vision of some frames is shot by binocular camera Image, is transferred to computer.Computer program is analyzed to the left and right two width image of every frame, obtains licence plate shape before automobile The coordinate at center, i.e. vehicle body characteristic point.
The extraction step of body of a motor car characteristic point is as follows:
1. Image semantic classification:The colored automobile image of collection is converted to gray level image, Jing histogram equalization processings increase The contrast of strong image, then it is filtered to remove noise.
2. rim detection:As before automobile, the background color of licence plate is had than larger contrast in gray scale with frame, image is entered Row rim detection.
3. noise remove:Jing after rim detection, in addition to license plate area, in image, also there is substantial amounts of transverse edge.In order to The interference that they are produced to License Plate is eliminated, choosing the element with vertical stratification carries out etching operation to image.
4. image smoothing:Rectangular configuration element opposite side edge image is taken to carry out closing operation of mathematical morphology, between eliminating in image Disconnected, elongated wide gap and little hole, and the fracture filled up in contour line, make edge contour more smooth.
5. license plate area is positioned:Jing after above-mentioned process, in addition to car plate region is obtained, it is also possible to there are other connections Region.According to the appearance and size feature of car plate, candidate region is further analyzed, extract license plate area.It is in China, most The overall size of front licence plate is 440mm × 140mm, i.e.,:Length-width ratio r of car plate be it is fixed, about 3.143.To each candidate regions Rectangle analysis is pressed in domain, and such as its length and width ratio is between [2.85,3.45], and closest to r, then regards as license plate area.
6. license plate outline is extracted:The gray level image of the license plate area to detecting carries out Hough transform, the horizontal sides of car plate Edge and vertical edge produce four peak points in transformation space.This four points correspond to four straight lines in artwork image space, constitute One rectangle, i.e., the profile of licence plate before automobile.
7. vehicle body feature point extraction:The profile of licence plate before automobile is analyzed, its centroid is extracted, as automobile Vehicle body characteristic point.
(3) direction of traffic analysis
Three-dimensional reconstruction is carried out to the vehicle body characteristic point of the left and right two width automobile image of every frame, is obtained in world coordinate system Coordinate.Sequence to being made up of vehicle body characteristic point three-dimensional coordinate is fitted, and obtains a straight line, i.e. the traveling side of automobile To.
(4) angular deviation of direction of traffic is calculated
Compare the actual travel direction of automobile and the traveling guidance line of vehicle inspection station, the angle calculated between them is inclined Difference.
(5) detection of headlight data correction
The measurement data of detection of headlight is read in, which is modified according to formula (1), is obtained actual headlamp horizon light Beam direction of illumination.
The present invention realized based on machine vision technique, can be to the horizontal light beam irradiation side of automatic tester for vehicle headlamp To measurement data corrected automatically, the accuracy of measurement can be effectively improved.Advantages of the present invention mainly has:
(1) present invention simply increased binocular camera on the basis of automatic tester for vehicle headlamp and computer analysis is soft Part, low cost.
(2) present invention is a kind of non-contact measurement, it is possible to achieve fully-automated synthesis, and easy and headlamp aligner Integrate.
(3) error correction benchmark of the invention is the travel direction of automobile, meets the actually used situation of headlamp.
Description of the drawings
Below in conjunction with accompanying drawing, the invention will be further described.
Fig. 1 is the error correction principle of the present invention.
Fig. 2 is the system architecture diagram of the present invention.
Fig. 3 is the flow chart that the car headlamp Lighting direction error of measured data of the present invention corrects program.
In the figures above 1-3,1:Headlamp aligner, 2:Headlamp aligner guide rail, 3:Vehicle performance test station Traveling guidance line (preferable longitudinal direction of car axis), 4:The actual travel direction of automobile, 5:Binocular camera, 6:Automobile to be checked, 7:Computer.
Specific embodiment
Car headlamp Lighting direction error information detection correcting system is built with reference to Fig. 2, in the enforcement of the present invention Example in, parking stall dead ahead to be checked arrange CMOS number binocular camera, liftoff about 1 meter.First, 16 width target figures are gathered Picture, is transferred to computer, and Jing computers program carries out camera calibration, obtains intrinsic parameters of the camera, external parameter and system Structural parameters, the initialization of completion system.Then, steering wheel return just in the state of, automobile slowly moves ahead from original position, stops Parking stall to be checked is put into, the visual pattern of ten frame automobiles during this period, is shot, the analysis of Jing computers program obtains the actual row of automobile Direction is sailed, the angular deviation of direction of traffic is calculated, the measurement data of automatic tester for vehicle headlamp is modified.Computer is performed Program it is as shown in Figure 3.Following table list three measurement data of automobile left headlamp beam level direction of illumination side-play amount and Correction result (unit for ').
Pendulous frequency Detection of headlight apparatus measuring value Direction of traffic angle excursion Result after amendment
1 53 31 22
2 -6 -38 32
3 18 -17 35

Claims (1)

1. a kind of car headlamp error information detection correcting method based on direction of traffic, it is characterised in that:Using by installing The system that binocular camera, computer and headlamp aligner in parking stall dead ahead to be checked is constituted, shoots in vehicle steering Return just in the state of, automobile from original position slowly drive towards parking stall to be checked during some frame automobiles visual pattern, computer Rim detection is carried out to the left and right two width automobile image of every frame and morphological images are processed, according to the length and width ratio of front licence plate about Beam, license plate area before extracting carry out Hough transform to the gray level image in the region, detect corresponding four straight lines in car plate edge, Front licence plate profile is obtained, its centroid is analyzed, as the vehicle body characteristic point of automobile, the left and right two width automobile image to every frame Vehicle body characteristic point carry out three-dimensional reconstruction, obtain the coordinate in world coordinate system, the three-dimensional coordinate sequence to vehicle body characteristic point It is fitted, obtains a straight line, as the actual travel direction of automobile, according between actual direction of traffic and traveling guidance line Angular deviation, carries out error correction to the measurement data of the horizontal light beam direction of illumination of headlamp aligner.
CN201410445638.6A 2014-09-01 2014-09-01 Car headlamp error information detection correcting method based on direction of traffic Expired - Fee Related CN104236866B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410445638.6A CN104236866B (en) 2014-09-01 2014-09-01 Car headlamp error information detection correcting method based on direction of traffic

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410445638.6A CN104236866B (en) 2014-09-01 2014-09-01 Car headlamp error information detection correcting method based on direction of traffic

Publications (2)

Publication Number Publication Date
CN104236866A CN104236866A (en) 2014-12-24
CN104236866B true CN104236866B (en) 2017-03-29

Family

ID=52225385

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410445638.6A Expired - Fee Related CN104236866B (en) 2014-09-01 2014-09-01 Car headlamp error information detection correcting method based on direction of traffic

Country Status (1)

Country Link
CN (1) CN104236866B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106197374B (en) * 2016-08-15 2020-05-08 临沂大学 Method for measuring deflection angle of automobile body
CN110298814A (en) * 2018-03-23 2019-10-01 苏州启铭臻楠电子科技有限公司 A kind of stage Adjustable head lamp sports coordination analysis method based on intelligent depth vision
CN110298880A (en) * 2018-03-23 2019-10-01 苏州启铭臻楠电子科技有限公司 A kind of stage Adjustable head lamp sports coordination analysis method based on intelligent monocular vision
CN111814560B (en) * 2020-06-10 2023-12-26 河南观潮智能科技有限公司 Parking space state identification method, system, medium and equipment

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19757760A1 (en) * 1997-12-23 1999-07-01 Bosch Gmbh Robert Device for determining the wheel and / or axle geometry of motor vehicles
DE19941034A1 (en) * 1999-08-28 2001-03-22 Bosch Gmbh Robert Adjustment device with an adjustment device for a headlight or for a distance sensor of a vehicle
CN2600787Y (en) * 2002-08-21 2004-01-21 张拥军 Device for measuring running trace of vehicle starting using digital image identification technology
WO2004102114A1 (en) * 2003-05-09 2004-11-25 Snap-On Incorporated Camera technique for adaptive cruise control (acc) sensor adjustment
CN103411565B (en) * 2013-08-29 2016-06-29 临沂大学 Automobile body inclination degree measurement method of small automobile

Also Published As

Publication number Publication date
CN104236866A (en) 2014-12-24

Similar Documents

Publication Publication Date Title
CN108444390B (en) Unmanned automobile obstacle identification method and device
CN104916163B (en) Parking space detection method
TWI408625B (en) Vehicle tracking system and tracking method thereof
CN104236866B (en) Car headlamp error information detection correcting method based on direction of traffic
CN106978774B (en) A kind of road surface pit slot automatic testing method
CN107796373B (en) Distance measurement method based on monocular vision of front vehicle driven by lane plane geometric model
CN103453836A (en) System and method for measuring vehicle outline dimensions based on machine vision and laser light curtain
CN103196418A (en) Measuring method of vehicle distance at curves
CN203489844U (en) System for measuring size of outer profile of vehicle based on machine vision and laser light screen
CN103411565B (en) Automobile body inclination degree measurement method of small automobile
CN106352817A (en) Non-contact four-wheel positioner and positioning method thereof
CN102393902A (en) Vehicle color detection method based on H_S two-dimensional histogram and regional color matching
CN102818544A (en) On-line measurement method for pitch circle center of automobile hub bolt hole and central eccentric distance of central hole
CN104239904A (en) Non-contact detection method for external outline of railway vehicle
CN105091748A (en) Measuring system for tolerance dimensions of railway vehicle
CN107688174A (en) A kind of image distance-finding method, system, storage medium and vehicle-mounted visually-perceptible equipment
CN103438809A (en) Vehicle-width measurement method and device based on area-array / linear-array cameras
KR20140076866A (en) Measurement Method and Apparatus for Measuring Curvature of Lane Using Behavior of Preceding Vehicle
JP2012022573A (en) Mobile body detection device
CN106813569A (en) A kind of automobile tire 3-D positioning method based on line-structured light
CN103884294A (en) Wide view field type infrared light three-dimensional morphology measurement method and device thereof
CN104321614B (en) Method and apparatus for carrying out the process for the orientation of at least one rail that determines measuring station
CN105510052A (en) Device and method for detecting automobile brake time sequence based on stereoscopic vision
CN106802243A (en) A kind of running out the way detection method, apparatus and system based on laser ranging
CN105043253A (en) Truck side protection guard installation size measurement system based on surface structure light technology and method thereof

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20170329

Termination date: 20170901

CF01 Termination of patent right due to non-payment of annual fee