CN109447003A - Vehicle checking method, device, equipment and medium - Google Patents
Vehicle checking method, device, equipment and medium Download PDFInfo
- Publication number
- CN109447003A CN109447003A CN201811291313.1A CN201811291313A CN109447003A CN 109447003 A CN109447003 A CN 109447003A CN 201811291313 A CN201811291313 A CN 201811291313A CN 109447003 A CN109447003 A CN 109447003A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- shadow region
- image
- candidate
- region
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention discloses a kind of vehicle checking method, device, equipment and media, are related to field of intelligent transportation technology.This method comprises: extracting the road image in road vehicle image between at least two lane lines；Actual size based on shadow region screens the candidate shadow region in road image, using the candidate shadow region by screening as vehicle bottom shadow region；Vehicle candidate region is determined according to the vehicle bottom shadow region in road image, and the vehicle's contour in vehicle candidate region is verified based on vehicle edge feature.A kind of vehicle checking method, device, equipment and medium provided in an embodiment of the present invention improve detection efficiency and accuracy rate to vehicle.
Description
Technical field
The present embodiments relate to field of intelligent transportation technology more particularly to a kind of vehicle checking method, device, equipment and
Medium.
Background technique
Vehicle assistant drive technology is also known as advanced driving assistance system (Advanced Driving Assistant
System, abbreviation ADAS).Vehicle assistant drive includes many functions, including the augmented reality based on direction guide line
(Augmented Reality, AR) navigation feature.Direction guide line is the guide line for being used to indicate vehicle heading.
It usually requires to detect front truck in ADAS application scenarios, for leading vehicle distance early warning and other AR of auxiliary
The follow-up works such as the displaying of effect.The prior art is typically based on vehicle image feature and carries out full figure search and filtering, with realization pair
The detection of front truck.
However, the above method is since it is desired that scan for full figure, it is low so as to cause detection efficiency.Again because of surrounding scenes
Influence, so causing Detection accuracy low.
Summary of the invention
The embodiment of the present invention provides a kind of vehicle checking method, device, equipment and medium, is imitated with the detection for improving to vehicle
Rate and accuracy rate.
In a first aspect, the embodiment of the invention provides a kind of vehicle checking methods, this method comprises:
Extract the road image in road vehicle image between at least two lane lines；
Actual size based on shadow region screens the candidate shadow region in road image, will pass through screening
Candidate shadow region as vehicle bottom shadow region；
Vehicle candidate region is determined according to the vehicle bottom shadow region in road image, and vehicle is waited based on vehicle edge feature
Vehicle's contour in favored area is verified.
Second aspect, the embodiment of the invention also provides a kind of vehicle detection apparatus, which includes:
Image zooming-out module, for extracting the road image in road vehicle image between at least two lane lines；
Shade screening module, for the actual size based on shadow region, to the candidate shadow region in road image into
Row screening, using the candidate shadow region by screening as vehicle bottom shadow region；
Vehicle determining module is based on vehicle for determining vehicle candidate region according to the vehicle bottom shadow region in road image
Edge feature verifies the vehicle's contour in vehicle candidate region.
The third aspect, the embodiment of the invention also provides a kind of equipment, the equipment includes:
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes the vehicle checking method as described in any in the embodiment of the present invention.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program realizes the vehicle checking method as described in any in the embodiment of the present invention when program is executed by processor.
Then the embodiment of the present invention is being mentioned by extracting the road image in road vehicle image between at least two lane lines
Vehicle detection is carried out in the road image taken.Interference the process eliminate lane line with exterior domain to vehicle detection, to mention
High vehicle detection efficiency and accuracy rate.
In addition, inventor discovery because imaging exist apart from camera it is closer imaging it is bigger, it is smaller to get over distance imaging apart from camera
The characteristics of, if directly screened using default vehicle bottom shade size range to shade, vehicle bottom shade probably because
Distance apart from camera is different, and the problem of be filtered out.Therefore, the embodiment of the present invention is right according to the actual size of shadow region
It is screened candidate shadow region in road image.To improve the determination accuracy rate of vehicle bottom shade.
Detailed description of the invention
Fig. 1 is a kind of flow chart for vehicle checking method that the embodiment of the present invention one provides；
Fig. 2 is a kind of flow chart of vehicle checking method provided by Embodiment 2 of the present invention；
Fig. 3 is a kind of vehicle detection effect diagram provided by Embodiment 2 of the present invention；
Fig. 4 is a kind of structural schematic diagram for vehicle detection apparatus that the embodiment of the present invention three provides；
Fig. 5 is a kind of structural schematic diagram for equipment that the embodiment of the present invention four provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is a kind of flow chart for vehicle checking method that the embodiment of the present invention one provides.The present embodiment is applicable to pair
The case where driving vehicle in road is detected.Typically be suitable for acquiring image capture device includes travelling
The image of front truck carries out the case where vehicle detection, and wherein described image acquisition equipment is mounted on this vehicle.This method can be by one
Vehicle detection apparatus is planted to execute, which can be realized by the mode of software and/or hardware.Referring to Fig. 1, the present embodiment provides
Vehicle checking method include:
Road image in S110, extraction road vehicle image between at least two lane lines.
Wherein, road vehicle image is the traveling of acquisition in road vehicle image.Road image is road vehicle figure
Image as between lane line.
Specifically, extracting the road image in road vehicle image between at least two lane lines includes:
If detecting to include two lane lines in road vehicle image, based on straight line where two lane lines to vehicle
Road is cut, and the image after cutting between two lane lines is as road image.
It, will be outermost at least three lane lines if detecting includes at least three lane lines in road vehicle image
Lane line cuts road vehicle based on straight line where cutting lane line, is located at after cutting and cuts out as lane line is cut
The image between lane line is cut as road image.
For example, detect in road vehicle image be located at vertical direction three lane lines, three lane lines from a left side to
The right side is successively are as follows: first lane line, Article 2 lane line and Article 3 lane line.By first lane line and Article 3 lane line
As cutting lane line.Purpose is, realizes the detection to standdle carrier road driving vehicle.
When parastate is presented in road vehicle image in the lane line detected, where two lane lines between straight line
Image will also include the sky image on horizon in addition to including land image.
To further decrease interference, before being cut based on lane line to road vehicle image, further includes:
Horizon detection is carried out to road vehicle image；
Based on the horizon detected, road vehicle image is cut；
Correspondingly, based on lane line road vehicle image cut include:
The image for after cutting including land is cut based on lane line.
S120, the actual size based on shadow region screen the candidate shadow region in road image, will pass through
The candidate shadow region of screening is as vehicle bottom shadow region.
Wherein, the actual size of shadow region is size of the shadow region under world coordinate system.Vehicle bottom shadow region is
Shadow region existing for vehicle bottom.
Specifically, the actual size based on shadow region screens the candidate shadow region in road image,
Using the candidate shadow region by screening as vehicle bottom shadow region, comprising:
Parameter based on image capture device maps to candidate shadow region in world coordinate system from image coordinate system,
Generate practical shadow region；
It is if the size of practical shadow region meets the size requirement of vehicle bottom shadow region, the candidate shadow region is true
It is set to vehicle bottom shadow region.
Wherein, the parameter of image capture device include image capture device internal reference and outer ginseng.The ruler of vehicle bottom shadow region
It is very little to require to be determined according to the actual size of vehicle bottom.
Further, the parameter based on image capture device maps to candidate shadow region from image coordinate system
In world coordinate system, before the practical shadow region of generation, further includes:
To road image binaryzation, wherein the threshold value of binaryzation is determined according to the gray value of vehicle bottom shade；
To the road image after binaryzation from track to vehicle into line scans；
Candidate shadow region is determined according to scanning result.
In other words, the road image after binaryzation also can be described as from track to vehicle into line scans:
From the bottom of road image to top into line scans.
The beneficial effect of the above method is, because vehicle bottom shadow region is at vehicle bottom, and vehicle bottom shadow region has with road surface
Significant difference, so vehicle bottom shadow region can easily and quickly be identified from bottom to up by being scanned.
S130, vehicle candidate region is determined according to the vehicle bottom shadow region in road image, is based on vehicle edge feature pair
Vehicle's contour in vehicle candidate region is verified.
Specifically, the vehicle bottom shadow region according in road image determines vehicle candidate region, comprising:
The width of vehicle bottom shadow region is determined as vehicle and estimates width；
Ratio based on vehicle width and height of car estimates width according to vehicle and determines that vehicle estimates height；
Width is estimated according to vehicle and vehicle estimates height and determines vehicle candidate region.
It, can also be with it is alternatively possible to directly estimate width according to vehicle and vehicle estimates height and determines vehicle candidate region
Width is estimated to vehicle and vehicle estimates the appropriate expansion of height progress size, using the region after expansion as candidate region.
Optionally, the vehicle's contour in vehicle candidate region is verified, may include:
It is verified according to vehicle edge feature, and/or, asymmetric authentication is carried out to vehicle's contour.
Because vehicle has fixed edge feature, carrying out verifying according to vehicle edge feature includes, according to detection
Distribution density and spacing to vehicle edge verify the vehicle's contour in candidate region.
It is symmetrical from vehicle from the angle of headstock or the tailstock.Feature accordingly carries out left and right pair to vehicle's contour
Claim verifying, is proved to be successful if symmetrical, otherwise authentication failed.
The technical solution of the embodiment of the present invention, by extracting the mileage chart in road vehicle image between at least two lane lines
Then picture carries out vehicle detection in the road image of extraction.The process eliminate lane line with exterior domain to vehicle detection
Interference, to improve vehicle detection efficiency and accuracy rate.
In addition, inventor discovery because imaging exist apart from camera it is closer imaging it is bigger, it is smaller to get over distance imaging apart from camera
The characteristics of, if directly screened using default vehicle bottom shade size range to shade, vehicle bottom shade probably because
Distance apart from camera is different, and the problem of be filtered out.Therefore, the embodiment of the present invention is right according to the actual size of shadow region
It is screened candidate shadow region in road image.To improve the determination accuracy rate of vehicle bottom shade.
Further, it is described the vehicle's contour in vehicle candidate region is verified based on vehicle edge feature after,
Further include:
If verification result meets vehicle identification requirement, it is determined that the vehicle's contour region is vehicle's contour region；
If verification result is unsatisfactory for vehicle identification requirement, vehicle detection is carried out to road image based on classifier.
Vehicle assert that requirement can specifically can be determines according to actual conditions, if vehicle bottom shade exists, and vehicle wheel
Exterior feature is proved to be successful, then regards as vehicle.
Classifier can be arbitrary classification device, typically can be the AdaBoost classifier based on haar feature.
For reality now due to when illumination reason does not have vehicle bottom shade, determination to vehicle candidate region is described to be based on vehicle
Before edge feature verifies the vehicle's contour in vehicle candidate region, further includes:
Vehicle candidate region is determined according to the edge detection results in road image.
Further, before the road image extracted in road vehicle image between at least two lane lines, further includes:
If the item number for the lane line that lane line is not detected or detects is one, virtual vehicle is determined according to this truck position
Diatom；
Parameter based on image capture device maps to determining virtual lane line in road vehicle image, generates vehicle
Lane line in road image.
Specifically, virtual lane line will be determined as away from current vehicle left side set distance, the straight line of the right set distance.
Embodiment two
Fig. 2 is a kind of flow chart of vehicle checking method provided by Embodiment 2 of the present invention.The present embodiment is to front truck
For carrying out vehicle detection, a kind of optinal plan of proposition.Referring to fig. 2, vehicle checking method provided in this embodiment includes:
Gray processing is carried out to the road vehicle image of acquisition, and the image after gray processing just cut out based on horizon
It cuts, generates pavement image；
Wherein, road vehicle image is divided into land and sky by horizon, and pavement image is only comprising land part
Image.
Road pavement image carries out lane detection, according to this truck position simulated roadway line if detecting failure；
Based on the lane line of the lane line or simulation that detect, road pavement image is cut, and extracts the road between lane line
Road image；
Road image is scanned from bottom to top, and the actual size based on the shadow region scanned is filtered, incited somebody to action
Shadow region after filter is as vehicle bottom shadow region；
Vehicle bottom shadow region if it exists, then using the width of vehicle bottom shadow region as vehicle width；
Ratio-dependent height of car based on vehicle width and height of car, estimates width according to vehicle and vehicle estimates height
It spends and determines vehicle candidate region；
Vehicle bottom shadow region is excluded from road image, horizontal edge detection is carried out to remaining area, and according to horizontal sides
The horizontal edge feature of edge testing result and vehicle back, determines vehicle candidate region；
The entropy of vehicle candidate region is calculated, and vehicle candidate region is filtered according to the entropy being calculated；
Wherein, what entropy reacted is the information content of image, and image texture is more, and entropy is bigger.
Specifically, vehicle's contour region is more with respect to the texture on road surface, if therefore vehicle candidate region entropy less than setting
Determine entropy, then filters out the vehicle candidate region.
Because vehicle back horizontal edge enriches and stable feature, horizontal edge in vehicle candidate region is utilized
The feature of distribution density and spacing verifies vehicle candidate region；
Bilateral symmetry based on vehicle carries out symmetry verifying to the vehicle candidate region by verifying；
If being proved to be successful to the symmetry of vehicle candidate region, and the vehicle candidate region is then assert there are vehicle bottom shade
The vehicle candidate region is vehicle, and exports the vehicle's contour in the vehicle candidate region, otherwise, road image is inputted vehicle
Detect the detection that vehicle is carried out in classifier.
Fig. 3 is a kind of vehicle detection effect diagram provided by Embodiment 2 of the present invention.In conjunction with Fig. 3, the above method may be used also
With summary are as follows: vehicle bottom shadow region 302 is determined based on two lane lines 301 detected,；According to vehicle bottom shadow region 302
The length-width ratio of width and vehicle estimates the general profile of vehicle；The general profile of vehicle is carried out adapting to expand to obtain vehicle time
Favored area 303；Vehicle candidate region 303 is verified；From the vehicle candidate region 303 being proved to be successful, examined according to edge
It surveys result and extracts vehicle actual profile 304.
The technical solution of the embodiment of the present invention is extracted from the road vehicle image of acquisition by the lane line based on detection
Then road image extracts vehicle bottom shade and vehicle bottom horizontal edge profile in road image, generate vehicle candidate region, finally
Vehicle candidate region is verified using the horizontal edge feature and symmetric characteristics of vehicle.To realize the standard to vehicle
Really, it rapidly extracts.This embodiment scheme is suitable for the higher application scenarios of performance requirement.
It should be noted that by the technical teaching of the present embodiment, those skilled in the art have motivation by above-described embodiment
Described in any embodiment carry out the combination of scheme, to realize the quick and precisely detection to vehicle.
Embodiment three
Fig. 4 is a kind of structural schematic diagram for vehicle detection apparatus that the embodiment of the present invention three provides.Referring to fig. 4, this implementation
The vehicle detection apparatus that example provides includes: image zooming-out module 10, shade screening module 20 and vehicle determining module 30.Wherein,
Image zooming-out module 10, for extracting the road image in road vehicle image between at least two lane lines；
Shade screening module 20, for the actual size based on shadow region, to the candidate shadow region in road image
It is screened, using the candidate shadow region by screening as vehicle bottom shadow region；
Vehicle determining module 30 is based on for determining vehicle candidate region according to the vehicle bottom shadow region in road image
Vehicle edge feature verifies the vehicle's contour in vehicle candidate region.
The technical solution of the embodiment of the present invention, by extracting the mileage chart in road vehicle image between at least two lane lines
Then picture carries out vehicle detection in the road image of extraction.The process eliminate lane line with exterior domain to vehicle detection
Interference, to improve vehicle detection efficiency and accuracy rate.
In addition, inventor discovery because imaging exist apart from camera it is closer imaging it is bigger, it is smaller to get over distance imaging apart from camera
The characteristics of, if directly screened using default vehicle bottom shade size range to shade, vehicle bottom shade probably because
Distance apart from camera is different, and the problem of be filtered out.Therefore, the embodiment of the present invention is right according to the actual size of shadow region
It is screened candidate shadow region in road image.To improve the determination accuracy rate of vehicle bottom shade.
Further, the shade screening module, comprising: coordinate system converting unit and size exclusion unit.
Wherein, coordinate system converting unit sits candidate shadow region from image for the parameter based on image capture device
Mark system maps in world coordinate system, generates practical shadow region；
Size exclusion unit will if the size for practical shadow region meets the size requirement of vehicle bottom shadow region
The candidate shadow region is determined as vehicle bottom shadow region.
Further, described device further include: binarization block, scan module and candidate shade determining module.
Wherein, binarization block sits candidate shadow region from image for the parameter based on image capture device
Mark system maps in world coordinate system, before generating practical shadow region, to road image binaryzation, and the wherein threshold value of binaryzation
It is determined according to the gray value of vehicle bottom shade；
Scan module, for the road image after binaryzation from track to vehicle into line scans；
Candidate shade determining module, for determining candidate shadow region according to scanning result.
Further, the vehicle determining module, comprising: vehicle width estimates unit, height of car estimates unit and time
Favored area determination unit.
Wherein, vehicle width estimates unit, estimates width for the width of vehicle bottom shadow region to be determined as vehicle；
Height of car estimates unit, and for the ratio based on vehicle width and height of car, it is true to estimate width according to vehicle
Determine vehicle and estimates height；
Candidate region determination unit, for estimating width according to vehicle and vehicle estimates height and determines vehicle candidate region.
Further, the vehicle determining module, comprising: vehicle authentication unit.
Wherein, vehicle authentication unit, for being verified according to vehicle edge feature, and/or, vehicle's contour is carried out pair
Claim verifying.
Further, described device further include: vehicle assert module and vehicle detection module.
Wherein, vehicle assert module, for it is described based on vehicle edge feature to the vehicle's contour in vehicle candidate region
After being verified, if verification result meets vehicle identification requirement, it is determined that the vehicle's contour region is vehicle's contour
Region；
Vehicle detection module, if being unsatisfactory for vehicle identification requirement for verification result, based on classifier to road image
Carry out vehicle detection.
Further, described device further include: lane line analog module and lane line determining module.
Wherein, lane line analog module, for the road between at least two lane lines in the extraction road vehicle image
Before image, if the item number for the lane line that lane line is not detected or detects is one, determined according to this truck position virtual
Lane line；
Determining virtual lane line is mapped to vehicle for the parameter based on image capture device by lane line determining module
In road image, the lane line in road vehicle image is generated.
Further, described device further include: candidate region determining module.
Wherein, candidate region determining module, for it is described based on vehicle edge feature to the vehicle in vehicle candidate region
Before profile is verified, vehicle candidate region is determined according to the edge detection results in road image.
Example IV
Fig. 5 is a kind of structural schematic diagram for equipment that the embodiment of the present invention four provides.Fig. 5, which is shown, to be suitable for being used to realizing this
The block diagram of the example devices 12 of invention embodiment.The equipment 12 that Fig. 5 is shown is only an example, should not be to of the invention real
The function and use scope for applying example bring any restrictions.
As shown in figure 5, equipment 12 is showed in the form of universal computing device.The component of equipment 12 may include but unlimited
In one or more processor or processing unit 16, system storage 28, connecting different system components, (including system is deposited
Reservoir 28 and processing unit 16) bus 18.
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be by equipment 12
The usable medium of access, including volatile and non-volatile media, moveable and immovable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Equipment 12 may further include it is other it is removable/nonremovable,
Volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for reading and writing irremovable
, non-volatile magnetic media (Fig. 5 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 5, use can be provided
In the disc driver read and write to removable non-volatile magnetic disk (such as " floppy disk "), and to removable anonvolatile optical disk
The CD drive of (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver can
To be connected by one or more data media interfaces with bus 18.Memory 28 may include at least one program product,
The program product has one group of (for example, at least one) program module, these program modules are configured to perform each implementation of the invention
The function of example.
Program/utility 40 with one group of (at least one) program module 42 can store in such as memory 28
In, such program module 42 include but is not limited to operating system, one or more application program, other program modules and
It may include the realization of network environment in program data, each of these examples or certain combination.Program module 42 is usual
Execute the function and/or method in embodiment described in the invention.
Equipment 12 can also be communicated with one or more external equipments 14 (such as keyboard, sensing equipment, display 24 etc.),
Can also be enabled a user to one or more equipment interacted with the equipment 12 communication, and/or with enable the equipment 12 with
One or more of the other any equipment (such as network interface card, modem etc.) communication for calculating equipment and being communicated.It is this logical
Letter can be carried out by input/output (I/O) interface 22.Also, equipment 12 can also by network adapter 20 and one or
The multiple networks of person (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet) communication.As shown,
Network adapter 20 is communicated by bus 18 with other modules of equipment 12.It should be understood that although not shown in the drawings, can combine
Equipment 12 use other hardware and/or software module, including but not limited to: microcode, device driver, redundant processing unit,
External disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize vehicle checking method provided by the embodiment of the present invention.
Embodiment five
The embodiment of the present invention five additionally provides a kind of computer readable storage medium, is stored thereon with computer program, should
The vehicle checking method as described in any in the embodiment of the present invention is realized when program is executed by processor, this method comprises:
Extract the road image in road vehicle image between at least two lane lines；
Actual size based on shadow region screens the candidate shadow region in road image, will pass through screening
Candidate shadow region as vehicle bottom shadow region；
Vehicle candidate region is determined according to the vehicle bottom shadow region in road image, and vehicle is waited based on vehicle edge feature
Vehicle's contour in favored area is verified.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool
There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (15)
1. a kind of vehicle checking method characterized by comprising
Extract the road image in road vehicle image between at least two lane lines；
Actual size based on shadow region screens the candidate shadow region in road image, will pass through the time of screening
Select shadow region as vehicle bottom shadow region；
Vehicle candidate region is determined according to the vehicle bottom shadow region in road image, based on vehicle edge feature to vehicle candidate regions
Vehicle's contour in domain is verified.
2. the method according to claim 1, wherein the actual size based on shadow region, to mileage chart
Candidate shadow region as in is screened, using the candidate shadow region by screening as vehicle bottom shadow region, comprising:
Parameter based on image capture device maps to candidate shadow region in world coordinate system from image coordinate system, generates
Practical shadow region；
If the size of practical shadow region meets the size requirement of vehicle bottom shadow region, the candidate shadow region is determined as
Vehicle bottom shadow region.
3., will candidate yin according to the method described in claim 2, it is characterized in that, the parameter based on image capture device
Shadow zone domain maps in world coordinate system from image coordinate system, before the practical shadow region of generation, further includes:
To road image binaryzation, wherein the threshold value of binaryzation is determined according to the gray value of vehicle bottom shade；
To the road image after binaryzation from track to vehicle into line scans；
Candidate shadow region is determined according to scanning result.
4. the method according to claim 1, wherein the vehicle bottom shadow region according in road image determines
Vehicle candidate region, comprising:
The width of vehicle bottom shadow region is determined as vehicle and estimates width；
Ratio based on vehicle width and height of car estimates width according to vehicle and determines that vehicle estimates height；
Width is estimated according to vehicle and vehicle estimates height and determines vehicle candidate region.
5. the method according to claim 1, wherein the vehicle edge feature that is based on is in vehicle candidate region
Vehicle's contour verified, comprising:
It is verified according to vehicle edge feature, and/or, asymmetric authentication is carried out to vehicle's contour.
6. the method according to claim 1, wherein the vehicle edge feature that is based on is in vehicle candidate region
Vehicle's contour verified after, further includes:
If verification result meets vehicle identification requirement, it is determined that the vehicle's contour region is vehicle's contour region；
If verification result is unsatisfactory for vehicle identification requirement, vehicle detection is carried out to road image based on classifier.
7. the method according to claim 1, wherein at least two lane lines in the extraction road vehicle image
Between road image before, further includes:
If the item number for the lane line that lane line is not detected or detects is one, virtual lane is determined according to this truck position
Line；
Parameter based on image capture device maps to determining virtual lane line in road vehicle image, generates vehicle road
Lane line in the image of road.
8. the vehicle edge feature that is based on is to vehicle candidate region according to the method described in claim 1, its feature is
In vehicle's contour verified before, further includes:
Vehicle candidate region is determined according to the edge detection results in road image.
9. a kind of vehicle detection apparatus characterized by comprising
Image zooming-out module, for extracting the road image in road vehicle image between at least two lane lines；
Shade screening module sieves the candidate shadow region in road image for the actual size based on shadow region
Choosing, using the candidate shadow region by screening as vehicle bottom shadow region；
Vehicle determining module is based on vehicle side for determining vehicle candidate region according to the vehicle bottom shadow region in road image
Edge feature verifies the vehicle's contour in vehicle candidate region.
10. device according to claim 9, which is characterized in that the shade screening module, comprising:
Coordinate system converting unit maps candidate shadow region from image coordinate system for the parameter based on image capture device
Into world coordinate system, practical shadow region is generated；
Size exclusion unit will be described if the size for practical shadow region meets the size requirement of vehicle bottom shadow region
Candidate shadow region is determined as vehicle bottom shadow region.
11. device according to claim 10, which is characterized in that described device further include:
Binarization block maps candidate shadow region from image coordinate system for the parameter based on image capture device
Into world coordinate system, before generating practical shadow region, to road image binaryzation, wherein the threshold value of binaryzation is according to vehicle bottom
The gray value of shade determines；
Scan module, for the road image after binaryzation from track to vehicle into line scans；
Candidate shade determining module, for determining candidate shadow region according to scanning result.
12. device according to claim 9, which is characterized in that the vehicle determining module, comprising:
Vehicle width estimates unit, estimates width for the width of vehicle bottom shadow region to be determined as vehicle；
Height of car estimates unit, for the ratio based on vehicle width and height of car, estimates width according to vehicle and determines vehicle
Estimate height；
Candidate region determination unit, for estimating width according to vehicle and vehicle estimates height and determines vehicle candidate region.
13. device according to claim 9, which is characterized in that the vehicle determining module, comprising:
Vehicle authentication unit, for being verified according to vehicle edge feature, and/or, asymmetric authentication is carried out to vehicle's contour.
14. a kind of equipment, which is characterized in that the equipment includes:
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now vehicle checking method as described in any in claim 1-7.
15. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The vehicle checking method as described in any in claim 1-7 is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811291313.1A CN109447003A (en) | 2018-10-31 | 2018-10-31 | Vehicle checking method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811291313.1A CN109447003A (en) | 2018-10-31 | 2018-10-31 | Vehicle checking method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109447003A true CN109447003A (en) | 2019-03-08 |
Family
ID=65550525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811291313.1A Pending CN109447003A (en) | 2018-10-31 | 2018-10-31 | Vehicle checking method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109447003A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110321828A (en) * | 2019-06-27 | 2019-10-11 | 四川大学 | A kind of front vehicles detection method based on binocular camera and vehicle bottom shade |
| WO2021129712A1 (en) * | 2019-12-24 | 2021-07-01 | 北京嘀嘀无限科技发展有限公司 | Vehicle verification method and system |
| CN113320546A (en) * | 2021-07-02 | 2021-08-31 | 恒大新能源汽车投资控股集团有限公司 | Shadow-based vehicle positioning method and control device, storage medium and vehicle |
| CN113723273A (en) * | 2021-08-26 | 2021-11-30 | 北京易华录信息技术股份有限公司 | Vehicle track information determination method and device and computer equipment |
| CN114187676A (en) * | 2021-12-02 | 2022-03-15 | 智慧起源机器人(苏州)有限公司 | Inspection method, device, equipment, system and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110279256A1 (en) * | 2004-12-23 | 2011-11-17 | Donnelly Corporation | Imaging system for vehicle |
| CN102610104A (en) * | 2012-03-16 | 2012-07-25 | 南京航空航天大学 | Onboard front vehicle detection method |
| CN102682455A (en) * | 2012-05-10 | 2012-09-19 | 天津工业大学 | Front vehicle detection method based on monocular vision |
| CN103481842A (en) * | 2013-09-09 | 2014-01-01 | 华南理工大学 | Method for switching vehicle detection and tracking modes |
| CN105922991A (en) * | 2016-05-27 | 2016-09-07 | 广州大学 | Lane departure early warning method and system based on generation of virtual lane lines |
-
2018
- 2018-10-31 CN CN201811291313.1A patent/CN109447003A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110279256A1 (en) * | 2004-12-23 | 2011-11-17 | Donnelly Corporation | Imaging system for vehicle |
| CN102610104A (en) * | 2012-03-16 | 2012-07-25 | 南京航空航天大学 | Onboard front vehicle detection method |
| CN102682455A (en) * | 2012-05-10 | 2012-09-19 | 天津工业大学 | Front vehicle detection method based on monocular vision |
| CN103481842A (en) * | 2013-09-09 | 2014-01-01 | 华南理工大学 | Method for switching vehicle detection and tracking modes |
| CN105922991A (en) * | 2016-05-27 | 2016-09-07 | 广州大学 | Lane departure early warning method and system based on generation of virtual lane lines |
Non-Patent Citations (3)
| Title |
|---|
| 朱英凯等: "基于改进车底阴影提取算法的前方运动车辆实时检测", 《测控技术与仪器仪表》 * |
| 王乐芬等: "基于阴影的前方车辆检测方法研究", 《仪器仪表与分析监测》 * |
| 齐美彬等: "基于车底阴影的前方运动车辆检测", 《电子测量与仪器学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110321828A (en) * | 2019-06-27 | 2019-10-11 | 四川大学 | A kind of front vehicles detection method based on binocular camera and vehicle bottom shade |
| WO2021129712A1 (en) * | 2019-12-24 | 2021-07-01 | 北京嘀嘀无限科技发展有限公司 | Vehicle verification method and system |
| CN113320546A (en) * | 2021-07-02 | 2021-08-31 | 恒大新能源汽车投资控股集团有限公司 | Shadow-based vehicle positioning method and control device, storage medium and vehicle |
| CN113723273A (en) * | 2021-08-26 | 2021-11-30 | 北京易华录信息技术股份有限公司 | Vehicle track information determination method and device and computer equipment |
| CN114187676A (en) * | 2021-12-02 | 2022-03-15 | 智慧起源机器人(苏州)有限公司 | Inspection method, device, equipment, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109447003A (en) | Vehicle checking method, device, equipment and medium | |
| CN103814306B (en) | Depth survey quality strengthens | |
| Shin et al. | A superparticle filter for lane detection | |
| US10373380B2 (en) | 3-dimensional scene analysis for augmented reality operations | |
| US9467645B2 (en) | System and method for recognizing parking space line markings for vehicle | |
| JP4426436B2 (en) | Vehicle detection device | |
| US9076047B2 (en) | System and method for recognizing parking space line markings for vehicle | |
| WO2017090326A1 (en) | Image processing device, image pickup device, apparatus control system, distribution data generation method, and program | |
| CN105488492B (en) | A kind of color image preprocess method, roads recognition method and relevant apparatus | |
| CN110163176A (en) | The recognition methods of lane line change location, device, equipment and medium | |
| JP4416039B2 (en) | Striped pattern detection system, striped pattern detection method, and striped pattern detection program | |
| JP5959073B2 (en) | Detection device, detection method, and program | |
| KR20160123668A (en) | Device and method for recognition of obstacles and parking slots for unmanned autonomous parking | |
| JP2004117078A (en) | Obstacle detection device and method | |
| CN111179152A (en) | Road sign identification method and device, medium and terminal | |
| JP2017162116A (en) | Image processing device, imaging device, movable body apparatus control system, image processing method and program | |
| JP6753134B2 (en) | Image processing device, imaging device, mobile device control system, image processing method, and image processing program | |
| US10235576B2 (en) | Analysis method of lane stripe images, image analysis device, and non-transitory computer readable medium thereof | |
| CN110147465A (en) | Image processing method, device, equipment and medium | |
| CN115240154A (en) | Method, device, equipment and medium for extracting point cloud features of parking lot | |
| CN109300322B (en) | Guideline drawing method, apparatus, device, and medium | |
| CN114519819A (en) | Remote sensing image target detection method based on global context awareness | |
| CN113763438B (en) | Point cloud registration method, device, equipment and storage medium | |
| CN110176000B (en) | Road quality detection method and device, storage medium and electronic equipment | |
| CN113989765A (en) | Detection method and detection device for rail obstacle and readable storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190308 |
|
| RJ01 | Rejection of invention patent application after publication |