CN107944425A - The recognition methods of road sign and device - Google Patents
The recognition methods of road sign and device Download PDFInfo
- Publication number
- CN107944425A CN107944425A CN201711317410.9A CN201711317410A CN107944425A CN 107944425 A CN107944425 A CN 107944425A CN 201711317410 A CN201711317410 A CN 201711317410A CN 107944425 A CN107944425 A CN 107944425A
- Authority
- CN
- China
- Prior art keywords
- road sign
- pixel
- classification information
- information
- described image
- 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
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/582—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of traffic signs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- G06V2201/09—Recognition of logos
Abstract
Recognition methods and device the disclosure is directed to a kind of road sign, belong to image identification technical field.Wherein, the recognition methods of road sign, including：Obtain the image for including road sign；Pixel is carried out respectively to the pixel in image in horizontal and vertical both direction to add up, the road sign included according to pixel accumulation result identification image.The implication representated by road sign can be identified exactly so that vehicle can drive safely according to road sign.
Description
Technical field
This disclosure relates to image identification technical field, more particularly to recognition methods and the device of a kind of road sign.
Background technology
It is unmanned to be used as frontier science and technology with the continuous development of science and technology, it has been known.Unmanned is exactly profit
Perceive vehicle-periphery with onboard sensor, and according to perceive obtained road, vehicle location and obstacle information come
Steering and the speed of vehicle are controlled, so as to enable the vehicle to reliably and securely travel on road.Wherein, how accurately
Ground identifies road sign, and controls vehicle to be travelled according to road sign, it has also become emphasis research topic.
The content of the invention
To overcome problem present in correlation technique, the disclosure provides recognition methods and the device of a kind of road sign.
According to the first aspect of the embodiment of the present disclosure, there is provided a kind of recognition methods of road sign, including：
Obtain the image for including road sign；
Pixel is carried out respectively in horizontal and vertical both direction to the pixel in described image to add up, and is tired out according to the pixel
The road sign for adding result identification described image to include.
The recognition methods of road sign as described above, to the pixel in described image in horizontal and vertical both direction point
Not carry out pixel add up, the road sign that includes of described image is identified according to the pixel accumulation result, including：
The region determined where the road sign is converted based on least significant difference algorithm LSD or HOUGH；
Reprojection is carried out to the region, and determines coordinate information of the road sign in described image；
The road sign is extracted according to the coordinate information.
The recognition methods of road sign as described above, is identifying that described image includes according to the pixel accumulation result
The road sign after, further include：
Determine the classification information of the road sign.
The recognition methods of road sign as described above, determines the classification information of the road sign, including：
Extract the feature of the road sign；
The feature is matched with training pattern trained in advance, to determine the classification information of the road sign.
The recognition methods of road sign as described above, before the classification information of the road sign is determined, further includes：
Gather road sign sample；
The road sign sample is instructed based on histograms of oriented gradients HOG and support vector machines learning model
Practice, and generate the training pattern.
The recognition methods of road sign as described above, carries out the region reprojection, and determines the road road sign
Aim at the coordinate information in described image, including：
Binaryzation is carried out to the region, to generate corresponding ROI region interested；
Transverse projection is carried out to the ROI region, and obtains the ordinate information of the road sign；
Longitudinal projection is carried out to the ROI region, and obtains the abscissa information of the road sign.
The recognition methods of road sign as described above, the classification information of the road sign to advance, turning left, turning right,
One kind in advancing or turn left, advance or turn right, advance or turn left or turning right.
The recognition methods of road sign as described above, after the classification information of the road sign is determined, further includes：
Prompt message corresponding with the classification information is provided.
According to the second aspect of the embodiment of the present disclosure, there is provided a kind of identification device of road sign, including：
Acquisition module, for obtaining the image for including road sign；
Processing module, adds up for carrying out pixel respectively in horizontal and vertical both direction to the pixel in described image,
The road sign included according to pixel accumulation result identification described image.
The identification device of road sign as described above, the processing module, including：
Determination unit, for based on where the definite road sign of least significant difference algorithm LSD or HOUGH conversion
Region；
Processing unit, for carrying out reprojection to the region, and determines the road sign in described image
Coordinate information；
Extraction unit, for extracting the road sign according to the coordinate information.
The identification device of road sign as described above, further includes：
Determining module, for according to the pixel accumulation result identify the road sign that includes of described image it
Afterwards, the classification information of the road sign is determined.
The identification device of road sign as described above, the determining module, is used for：
Extract the feature of the road sign；
The feature is matched with training pattern trained in advance, to determine the classification information of the road sign.
The identification device of road sign as described above, further includes：
Training module, for before the classification information of the road sign is determined, road sign sample being gathered, based on side
The road sign sample is trained to histogram of gradients HOG and support vector machines learning model, and generates the instruction
Practice model.
The identification device of road sign as described above, the processing unit, is used for：
Binaryzation is carried out to the region, to generate corresponding ROI region interested；
Transverse projection is carried out to the ROI region, and obtains the ordinate information of the road sign；
Longitudinal projection is carried out to the ROI region, and obtains the abscissa information of the road sign.
The identification device of road sign as described above, the classification information of the road sign to advance, turning left, turning right,
One kind in advancing or turn left, advance or turn right, advance or turn left or turning right.
The identification device of road sign as described above, further includes：
Module is provided, for after the classification information of the road sign is determined, there is provided corresponding with the classification information
Prompt message.
According to the third aspect of the embodiment of the present disclosure, there is provided a kind of identification device of road sign, including：
Processor；
For storing the memory of processor-executable instruction；
Wherein, the processor is configured as：
Obtain the image for including road sign；
Pixel is carried out respectively in horizontal and vertical both direction to the pixel in described image to add up, and is tired out according to the pixel
The road sign for adding result identification described image to include.
The technical scheme provided by this disclosed embodiment can include the following benefits：Road sign is included by obtaining
Image, and pixel is carried out respectively in horizontal and vertical both direction to the pixel in described image and is added up, according to the pixel
The road sign that accumulation result identification described image includes, can identify containing representated by road sign exactly
Justice so that vehicle can drive safely according to road sign.
It should be appreciated that the general description and following detailed description of the above are only exemplary and explanatory, not
The disclosure can be limited.
Brief description of the drawings
Attached drawing herein is merged in specification and forms the part of this specification, shows the implementation for meeting the present invention
Example, and for explaining the principle of the present invention together with specification.
Fig. 1 is a kind of flow chart of the recognition methods of road sign according to an exemplary embodiment.
Fig. 2 is the effect diagram of the image obtained.
Fig. 3 is the effect diagram in the region where road sign.
Fig. 4 is the effect diagram of the ROI region of generation.
Fig. 5 is generation transverse projection figure, determines the effect diagram of the ordinate scope of road sign.
Fig. 6 is the effect diagram for extracting road sign.
Fig. 7 is a kind of flow chart of the recognition methods of the road sign shown according to another exemplary embodiment.
Fig. 8 is a kind of flow chart of the recognition methods of road sign according to further example embodiment.
Fig. 9 is a kind of flow chart of the recognition methods of road sign according to another exemplary embodiment.
Figure 10 is a kind of identification device block diagram of road sign according to an exemplary embodiment.
Figure 11 is a kind of identification device block diagram of the road sign shown according to another exemplary embodiment.
Figure 12 is a kind of identification device block diagram of road sign according to further example embodiment.
Figure 13 is a kind of identification device block diagram of road sign according to another exemplary embodiment.
Figure 14 is a kind of block diagram of the identification device 100 of road sign according to an exemplary embodiment.
Embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Following description is related to
During attached drawing, unless otherwise indicated, the same numbers in different attached drawings represent the same or similar key element.Following exemplary embodiment
Described in embodiment do not represent and the consistent all embodiments of the present invention.On the contrary, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects being described in detail in claims, of the invention.
Fig. 1 is a kind of flow chart of the recognition methods of road sign according to an exemplary embodiment, such as Fig. 1 institutes
Show, the recognition methods of road sign, comprises the following steps；
In step S101, the image for including road sign is obtained.
Specifically, which can be obtained by vehicle-mounted camera, can also be obtained by automobile data recorder.Wherein,
The classification information of the road sign included in image can be advance, left-hand rotation, right-hand rotation, advance or left-hand rotation, advance or right-hand rotation, advance
Or left-hand rotation or right-hand rotation etc..
In step s 102, pixel is carried out respectively in horizontal and vertical both direction to the pixel in image to add up, according to
The road sign that pixel accumulation result identification image includes.
In one embodiment of the disclosure, first can be based on LSD (Least-Significant Difference, most
Small significant difference) algorithm or HOUGH conversion determine road sign where region, then can to the region carry out reprojection,
So that it is determined that the coordinate information of road sign in the picture, last according to obtained coordinate information extraction road sign.
Specifically, after the region where determining road sign, reprojection, i.e. transverse projection can be carried out to the region
And longitudinal projection.Added up by the way that horizontal pixel to the projection in both direction, can be carried out and the pixel of longitudinal direction adds up, finally
The road sign in image is identified by accumulated result.That is, carrying out binaryzation to region first, generation is corresponding
ROI region interested.Then, transverse projection is carried out to ROI region, and obtains the ordinate information of road sign.Finally, it is right
ROI region carries out longitudinal projection, and obtains the abscissa information of road sign.Based on ordinate information and abscissa information extraction
Go out road sign.
For example, multiple line segments in image as shown in Figure 2 can be identified by LSD algorithm, if wanting to determine road
Region where indicating, then need to filter out the line segment for not meeting preset rules.Assuming that when preset rules are tilted to the right for line segment
Angular range with transverse axis is between 45 degree to 70 degree, and the length of line segment is more than preset length T, then can determine that and meet default rule
Line segment then, and as the left side in region.Similarly, when line segment is tilted to the left and transverse axis angular range at 45 degree to 70
Between degree, and the length of line segment is more than preset length T ', then can determine that the line segment for meeting preset rules, and as region
Right edge.Using transverse axis as base, it may be determined that go out a delta-shaped region, as shown in figure 3, the delta-shaped region, that is, road sign
The region at place.Binaryzation is carried out to the delta-shaped region, so as to generate corresponding ROI region, as shown in Figure 4.Afterwards, it is right
ROI region carries out transverse projection, and white pixel that will be per a line is added, and it is corresponding can to generate road sign as shown in Figure 5
Transverse projection figure, thus can determine that the ordinate scope (altitude range of white pixel) of road sign.Wherein, white value
For 255.Similarly, then to ROI region longitudinal projection is carried out, i.e., be added the white pixel of each row, generation road sign corresponds to
Longitudinal projection figure, thus can determine that the abscissa scope (width range of white pixel) of road sign.In definite road road sign
After the coordinate range of will in the picture, road sign can be extracted according to obtained coordinate information, as shown in Figure 6.
To sum up, the recognition methods of road sign provided in this embodiment, by obtaining the image for including road sign, and it is right
Pixel in image carries out pixel in horizontal and vertical both direction and adds up respectively, is identified in image and wrapped according to pixel accumulation result
The road sign included, can identify the implication representated by road sign exactly so that vehicle can according to road sign into
Row safety traffic.
Fig. 7 is a kind of flow chart of the recognition methods of the road sign shown according to another exemplary embodiment, such as Fig. 7 institutes
Show, the recognition methods of road sign, including：
In step S101, the image for including road sign is obtained.
In step s 102, pixel is carried out respectively in horizontal and vertical both direction to the pixel in image to add up, according to
The road sign that pixel accumulation result identification image includes.
In step s 103, the classification information of road sign is determined.
In one embodiment of the disclosure, the feature of road sign is can extract, then by feature and instruction trained in advance
Practice model to be matched, so that it is determined that the classification information of road sign.As shown in fig. 6, the upper part of the road sign is wide, lower half
Part is narrow, and the latter half is located at the left side of top half.Pass through features described above, it may be determined that the classification information of road sign is the right side
Turn, thus can correctly identify the implication of road sign.Wherein, the noun in foregoing description direction such as upper and lower, left and right, be with
Vehicle or the direction that driver is the first visual angle.
In disclosure further example embodiment, as shown in figure 8, the recognition methods of road sign, further includes：
In step S104, before the classification information of road sign is determined, road sign sample is gathered, and based on side
Road sign sample is trained to histogram of gradients HOG and support vector machines learning model, and generates training pattern.
Specifically, road sign sample can be gathered, be then based on HOG (Histogram of Oriented Gradient,
Histograms of oriented gradients) and SVM (Support Vector Machine, support vector machines) learning model to road sign sample
It is trained, and generates training pattern, so as to determine that the classification of road sign provides data basis.Such as：It is elongated vertical
Line segment represents classification information to advance；Broken line to the right represents classification information for right-hand rotation etc..
In the another exemplary embodiment of the disclosure, as shown in figure 9, the recognition methods of road sign, further includes：
In step S105, after the classification information of road sign is determined, there is provided prompting corresponding with category information
Information.
Such as：Identify that the classification information of road markings to turn right, then can pass through the modes such as voice broadcast or text importing
The prompt message of " please turn right " is sent, driver can be reminded in time.
To sum up, the recognition methods of road sign provided in this embodiment, by obtaining the image for including road sign, and it is right
Image is handled, and extracts road sign, and identification road sign, and determines the classification information of road sign, can be accurate
Identify the implication representated by road sign in ground so that vehicle can drive safely according to road sign.
Figure 10 is a kind of identification device block diagram of road sign according to an exemplary embodiment, the road sign
Identification device can be implemented in combination with by software, hardware or both.As shown in Figure 10, the identification device bag of the road sign
Include acquisition module 11 and processing module 12.
Acquisition module 11 is configured as obtaining the image for including road sign.
Processing module 12 is configured as carrying out pixel respectively in horizontal and vertical both direction to the pixel in image adding up,
The road sign included according to pixel accumulation result identification image.
Wherein, processing module 12 includes determination unit 121, processing unit 122 and extraction unit 123.
Determination unit 121 is configured as determining road sign place based on least significant difference algorithm LSD or HOUGH conversion
Region.
Processing unit 122 is configured as carrying out region reprojection, and determines the coordinate letter of road sign in the picture
Breath.
Extraction unit 123 is configured as extracting road sign according to coordinate information.
On the identification device of the road sign in above-described embodiment, wherein modules have performed the concrete mode of operation
Through being described in detail in the embodiment of the recognition methods in relation to the road sign, explanation will be not set forth in detail herein.
To sum up, the identification device of road sign provided in this embodiment, by obtaining the image for including road sign, and it is right
Pixel in image carries out pixel in horizontal and vertical both direction and adds up respectively, is identified in image and wrapped according to pixel accumulation result
The road sign included, can identify the implication representated by road sign exactly so that vehicle can according to road sign into
Row safety traffic.
Figure 11 is a kind of identification device block diagram of the road sign shown according to another exemplary embodiment, the road sign
Identification device can be implemented in combination with by software, hardware or both.As shown in figure 11, the identification device of road sign,
Including：Acquisition module 11, processing module 12 and determining module 13.
Wherein, acquisition module 11, processing module 12 are consistent with the description of a upper embodiment, therefore do not repeat herein.
Determining module 13 is configured as after the road sign that image includes is identified according to pixel accumulation result, is determined
The classification information of road sign.
Figure 12 is a kind of identification device block diagram of road sign according to further example embodiment, the road sign
Identification device can be implemented in combination with by software, hardware or both.As shown in figure 12, the identification device of road sign,
Including：Acquisition module 11, processing module 12, determining module 13 and training module 14.
Wherein, acquisition module 11, processing module 12, determining module 13 are consistent with the description of a upper embodiment, therefore do not go to live in the household of one's in-laws on getting married herein
State.
Training module 14 is configured as in identification road sign, and before the classification information of definite road sign, gathers road
Road sign will sample, instructs road sign sample based on histograms of oriented gradients HOG and support vector machines learning model
Practice, and generate training pattern.
On the identification device of the road sign in above-described embodiment, wherein modules have performed the concrete mode of operation
Through being described in detail in the embodiment of the recognition methods in relation to the road sign, explanation will be not set forth in detail herein.
To sum up, the identification device of road sign provided in this embodiment, by gathering road sign sample, based on direction ladder
Degree histogram HOG and support vector machines learning model are trained road sign sample, and generate training pattern, can
To determine that the classification of road sign provides data basis, recognition result is more accurate.
Figure 13 is a kind of identification device block diagram of road sign according to another exemplary embodiment, the road sign
Identification device can be implemented in combination with by software, hardware or both.As shown in figure 13, the identification device of road sign,
Including：Acquisition module 11, processing module 12, determining module 13, training module 14 and offer module 15.
Wherein, acquisition module 11, processing module 12, determining module 13, training module 14 are consistent with the description of a upper embodiment,
Therefore do not repeat herein.
There is provided module 15 to be configured as after the classification information of road sign is determined, there is provided corresponding with classification information to carry
Show information.
On the identification device of the road sign in above-described embodiment, wherein modules have performed the concrete mode of operation
Through being described in detail in the embodiment of the recognition methods in relation to the road sign, explanation will be not set forth in detail herein.
To sum up, the identification device of road sign provided in this embodiment, by determine road sign classification information it
Afterwards, there is provided prompt message corresponding with classification information, in time can remind driver.
Figure 14 is a kind of block diagram of the identification device 100 of road sign according to an exemplary embodiment.
As shown in figure 14, device 100 can include following one or more assemblies：Processing component 102, memory 104, electricity
Power component 106, sensor component 108, and communication component 110.
Processing component 102 usually controls the integrated operation of the identification device 100 of road sign, such as leads to display, data
Letter, the associated operation of record operation.Processing component 102 can carry out execute instruction including one or more processors 120, with complete
Into all or part of step of above-mentioned method.In addition, processing component 102 can include one or more modules, easy to handle
Interaction between component 102 and other assemblies.
Memory 104 is configured as storing various types of data to support the behaviour in the identification device 100 of road sign
Make.The example of these data includes any application program or method for being operated on the identification device 100 of road sign
Instruction.Memory 104 can be realized by any kind of volatibility or non-volatile memory device or combinations thereof, such as quiet
State random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), the read-only storage of erasable programmable
Device (EPROM), programmable read only memory (PROM), read-only storage (ROM), magnetic memory, flash memory, disk or light
Disk.
Electric power assembly 106 provides electric power for the various assemblies of the identification device 100 of road sign.Electric power assembly 106 can be with
Including power-supply management system, one or more power supplys, and other generated with the identification device 100 for road sign, manage and point
The component being associated with electric power.
Sensor component 108 includes one or more sensors, each for being provided for the identification device 100 of road sign
The status assessment of aspect.Sensor component 108 can include acceleration transducer, pressure sensor, be configured to detection and add
Speed and pressure value.
Communication component 110 is configured to facilitate wired or wireless between the identification device 100 of road sign and other equipment
The communication of mode.The identification device 100 of road sign can access the wireless network based on communication standard, such as WiFi, 2G or 3G,
Or combinations thereof.In one exemplary embodiment, communication component 110 receives via broadcast channel and comes from external broadcasting management
The broadcast singal or broadcast related information of system.
In the exemplary embodiment, the identification device 100 of road sign can be by the special integrated electricity of one or more application
Road (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), scene
Programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for performing above-mentioned side
Method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instructing, example are additionally provided
Such as include the memory 104 of instruction, above-metioned instruction can be performed by the processor 120 of the identification device 100 of road sign to complete
The above method.For example, non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM,
Tape, floppy disk and optical data storage devices etc..
A kind of non-transitorycomputer readable storage medium, when the instruction in storage medium is by the identification device of road sign
Processor perform when so that the identification device of road sign is able to carry out a kind of recognition methods of road sign, road sign
Recognition methods include：
Obtain the image for including road sign；
Pixel is carried out respectively in horizontal and vertical both direction to the pixel in image to add up, and is known according to pixel accumulation result
The road sign that other image includes.
On the identification device of the road sign in above-described embodiment, wherein processor has performed the concrete mode of operation
It is described in detail in the embodiment of the identification device in relation to the road sign, explanation will be not set forth in detail herein.
Those skilled in the art will readily occur to the present invention its after considering specification and putting into practice invention disclosed herein
Its embodiment.This application is intended to cover the present invention any variations, uses, or adaptations, these modifications, purposes or
Person's adaptive change follows the general principle of the present invention and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.Description and embodiments are considered only as exemplary, and true scope and spirit of the invention are by following
Claim is pointed out.
It should be appreciated that the invention is not limited in the precision architecture for being described above and being shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present invention is only limited by appended claim.
Claims (17)
1. a kind of recognition methods of road sign, it is characterised in that comprise the following steps：
Obtain the image for including road sign；
Pixel is carried out respectively in horizontal and vertical both direction to the pixel in described image to add up, and is added up knot according to the pixel
The road sign that fruit identification described image includes.
2. the method as described in claim 1, it is characterised in that to the pixel in described image in horizontal and vertical both direction
Carry out pixel respectively to add up, the road sign included according to pixel accumulation result identification described image, including：
The region determined where the road sign is converted based on least significant difference algorithm LSD or HOUGH；
Reprojection is carried out to the region, and determines coordinate information of the road sign in described image；
The road sign is extracted according to the coordinate information.
3. the method as described in claim 1, it is characterised in that wrapped in described image is identified according to the pixel accumulation result
After the road sign included, further include：
Determine the classification information of the road sign.
4. method as claimed in claim 3, it is characterised in that determine the classification information of the road sign, including：
Extract the feature of the road sign；
The feature is matched with training pattern trained in advance, to determine the classification information of the road sign.
5. method as claimed in claim 4, it is characterised in that before the classification information of the road sign is determined, also wrap
Include：
Gather road sign sample；
The road sign sample is trained based on histograms of oriented gradients HOG and support vector machines learning model, and
Generate the training pattern.
6. method as claimed in claim 2, it is characterised in that reprojection is carried out to the region, and determines the road
Indicate the coordinate information in described image, including：
Binaryzation is carried out to the region, to generate corresponding ROI region interested；
Transverse projection is carried out to the ROI region, and obtains the ordinate information of the road sign；
Longitudinal projection is carried out to the ROI region, and obtains the abscissa information of the road sign.
7. the method as described in claim 1, it is characterised in that the classification information of the road sign is advance, turns left, is right
One kind in turning, advance or turn left, advance or turn right, advance or turn left or turning right.
8. method as claimed in claim 3, it is characterised in that after the classification information of the road sign is determined, also wrap
Include：
Prompt message corresponding with the classification information is provided.
A kind of 9. identification device of road sign, it is characterised in that including：
Acquisition module, for obtaining the image for including road sign；
Processing module, adds up for carrying out pixel respectively in horizontal and vertical both direction to the pixel in described image, according to
The road sign that the pixel accumulation result identification described image includes.
10. device as claimed in claim 9, it is characterised in that the processing module, including：
Determination unit, for based on the area where the definite road sign of least significant difference algorithm LSD or HOUGH conversion
Domain；
Processing unit, for carrying out reprojection to the region, and determines coordinate of the road sign in described image
Information；
Extraction unit, for extracting the road sign according to the coordinate information.
11. device as claimed in claim 9, it is characterised in that further include：
Determining module, for after the road sign that includes of described image is identified according to the pixel accumulation result,
Determine the classification information of the road sign.
12. device as claimed in claim 11, it is characterised in that the determining module, is used for：
Extract the feature of the road sign；
The feature is matched with training pattern trained in advance, to determine the classification information of the road sign.
13. device as claimed in claim 12, it is characterised in that further include：
Training module, for before the classification information of the road sign is determined, gathering road sign sample, based on direction ladder
Degree histogram HOG and support vector machines learning model are trained the road sign sample, and generate the trained mould
Type.
14. device as claimed in claim 10, it is characterised in that the processing unit, is used for：
Binaryzation is carried out to the region, to generate corresponding ROI region interested；
Transverse projection is carried out to the ROI region, and obtains the ordinate information of the road sign；
Longitudinal projection is carried out to the ROI region, and obtains the abscissa information of the road sign.
15. device as claimed in claim 9, it is characterised in that the classification information of the road sign is advance, turns left, is right
One kind in turning, advance or turn left, advance or turn right, advance or turn left or turning right.
16. device as claimed in claim 11, it is characterised in that further include：
Module is provided, for after the classification information of the road sign is determined, there is provided corresponding with the classification information to carry
Show information.
A kind of 17. identification device of road sign, it is characterised in that including：
Processor；
For storing the memory of processor-executable instruction；
Wherein, the processor is configured as：
Obtain the image for including road sign；
Pixel is carried out respectively in horizontal and vertical both direction to the pixel in described image to add up, and is added up knot according to the pixel
The road sign that fruit identification described image includes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711317410.9A CN107944425A (en) | 2017-12-12 | 2017-12-12 | The recognition methods of road sign and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711317410.9A CN107944425A (en) | 2017-12-12 | 2017-12-12 | The recognition methods of road sign and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107944425A true CN107944425A (en) | 2018-04-20 |
Family
ID=61943918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711317410.9A Pending CN107944425A (en) | 2017-12-12 | 2017-12-12 | The recognition methods of road sign and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107944425A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109141922A (en) * | 2018-09-03 | 2019-01-04 | 长安大学 | Unmanned vehicle ban traffic mark board independently perceives capacity test system and test method |
| CN109409247A (en) * | 2018-09-30 | 2019-03-01 | 百度在线网络技术（北京）有限公司 | Traffic sign recognition method and device |
| CN110281983A (en) * | 2019-06-28 | 2019-09-27 | 清华大学 | A kind of accurate shutdown system of track train of view-based access control model scene Recognition |
| CN111444749A (en) * | 2019-01-17 | 2020-07-24 | 杭州海康威视数字技术股份有限公司 | Method and device for identifying road surface guide mark and storage medium |
| CN111460861A (en) * | 2019-01-21 | 2020-07-28 | 阿里巴巴集团控股有限公司 | Road traffic sign identification method, device and identification equipment |
| CN112180395A (en) * | 2019-06-13 | 2021-01-05 | 北京百度网讯科技有限公司 | Extraction method, device and equipment of road mark and storage medium |
| CN113728370A (en) * | 2019-04-23 | 2021-11-30 | 株式会社电装 | Vehicle device, vehicle program, and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030206655A1 (en) * | 2002-05-06 | 2003-11-06 | Tun-Chi Huang | Method for determining an adjacency relation |
| CN104616275A (en) * | 2013-11-04 | 2015-05-13 | 北京兆维电子(集团)有限责任公司 | Defect detecting method and defect detecting device |
| US9372513B1 (en) * | 2013-09-27 | 2016-06-21 | Google Inc. | Coupling element for hinged electronic device |
| CN105719284A (en) * | 2016-01-18 | 2016-06-29 | 腾讯科技（深圳）有限公司 | Data processing method, device and terminal |
| CN105930791A (en) * | 2016-04-19 | 2016-09-07 | 重庆邮电大学 | Road traffic sign identification method with multiple-camera integration based on DS evidence theory |
| CN106022268A (en) * | 2016-05-23 | 2016-10-12 | 广州鹰瞰信息科技有限公司 | Identification method and device of speed limiting sign |
| CN106127211A (en) * | 2016-06-22 | 2016-11-16 | 北京小米移动软件有限公司 | Blank detection method and device |
| CN106446769A (en) * | 2015-08-11 | 2017-02-22 | 本田技研工业株式会社 | Systems and techniques for sign based localization |
-
2017
- 2017-12-12 CN CN201711317410.9A patent/CN107944425A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030206655A1 (en) * | 2002-05-06 | 2003-11-06 | Tun-Chi Huang | Method for determining an adjacency relation |
| US9372513B1 (en) * | 2013-09-27 | 2016-06-21 | Google Inc. | Coupling element for hinged electronic device |
| CN104616275A (en) * | 2013-11-04 | 2015-05-13 | 北京兆维电子(集团)有限责任公司 | Defect detecting method and defect detecting device |
| CN106446769A (en) * | 2015-08-11 | 2017-02-22 | 本田技研工业株式会社 | Systems and techniques for sign based localization |
| CN105719284A (en) * | 2016-01-18 | 2016-06-29 | 腾讯科技（深圳）有限公司 | Data processing method, device and terminal |
| CN105930791A (en) * | 2016-04-19 | 2016-09-07 | 重庆邮电大学 | Road traffic sign identification method with multiple-camera integration based on DS evidence theory |
| CN106022268A (en) * | 2016-05-23 | 2016-10-12 | 广州鹰瞰信息科技有限公司 | Identification method and device of speed limiting sign |
| CN106127211A (en) * | 2016-06-22 | 2016-11-16 | 北京小米移动软件有限公司 | Blank detection method and device |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109141922B (en) * | 2018-09-03 | 2020-08-11 | 长安大学 | Unmanned vehicle forbidden traffic sign board autonomous perception capability test system and test method |
| CN109141922A (en) * | 2018-09-03 | 2019-01-04 | 长安大学 | Unmanned vehicle ban traffic mark board independently perceives capacity test system and test method |
| CN109409247A (en) * | 2018-09-30 | 2019-03-01 | 百度在线网络技术（北京）有限公司 | Traffic sign recognition method and device |
| CN109409247B (en) * | 2018-09-30 | 2022-05-13 | 阿波罗智联(北京)科技有限公司 | Traffic sign identification method and device |
| CN111444749A (en) * | 2019-01-17 | 2020-07-24 | 杭州海康威视数字技术股份有限公司 | Method and device for identifying road surface guide mark and storage medium |
| CN111444749B (en) * | 2019-01-17 | 2023-09-01 | 杭州海康威视数字技术股份有限公司 | Method and device for identifying road surface guide mark and storage medium |
| CN111460861B (en) * | 2019-01-21 | 2023-05-19 | 阿里巴巴集团控股有限公司 | Road traffic sign recognition method, device and recognition equipment |
| CN111460861A (en) * | 2019-01-21 | 2020-07-28 | 阿里巴巴集团控股有限公司 | Road traffic sign identification method, device and identification equipment |
| CN113728370B (en) * | 2019-04-23 | 2023-09-22 | 株式会社电装 | Vehicle device, vehicle program, and storage medium |
| CN113728370A (en) * | 2019-04-23 | 2021-11-30 | 株式会社电装 | Vehicle device, vehicle program, and storage medium |
| CN112180395A (en) * | 2019-06-13 | 2021-01-05 | 北京百度网讯科技有限公司 | Extraction method, device and equipment of road mark and storage medium |
| CN112180395B (en) * | 2019-06-13 | 2023-04-07 | 北京百度网讯科技有限公司 | Extraction method, device and equipment of road mark and storage medium |
| CN110281983A (en) * | 2019-06-28 | 2019-09-27 | 清华大学 | A kind of accurate shutdown system of track train of view-based access control model scene Recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107944425A (en) | The recognition methods of road sign and device | |
| US10429841B2 (en) | Vehicle control method and apparatus and method and apparatus for acquiring decision-making model | |
| CN110826370B (en) | Method and device for identifying identity of person in vehicle, vehicle and storage medium | |
| JP2022505759A (en) | Methods and equipment for testing driver assistance systems | |
| CN108944939B (en) | Method and system for providing driving directions | |
| CN110188482B (en) | Test scene creating method and device based on intelligent driving | |
| CN110765807A (en) | Driving behavior analysis method, driving behavior processing method, driving behavior analysis device, driving behavior processing device and storage medium | |
| WO2020007589A1 (en) | Training a deep convolutional neural network for individual routes | |
| US11250279B2 (en) | Generative adversarial network models for small roadway object detection | |
| CN110675637A (en) | Vehicle illegal video processing method and device, computer equipment and storage medium | |
| CN113799770B (en) | Data processing method and device based on automatic driving | |
| CN113085894A (en) | Vehicle control method and device and automatic driving vehicle | |
| JP2022502750A (en) | Methods and devices for analyzing sensor data flows, as well as methods for guiding vehicles. | |
| CN111753592A (en) | Traffic sign recognition method, traffic sign recognition device, computer equipment and storage medium | |
| CN108304852B (en) | Method and device for determining road section type, storage medium and electronic device | |
| CN113516099A (en) | Traffic behavior recognition method and device, electronic equipment and storage medium | |
| CN113496213A (en) | Method, device and system for determining target perception data and storage medium | |
| CN111191482A (en) | Brake lamp identification method and device and electronic equipment | |
| CN110727269B (en) | Vehicle control method and related product | |
| CN112654998A (en) | Lane line detection method and device | |
| CN114693722B (en) | Vehicle driving behavior detection method, detection device and detection equipment | |
| CN111177878A (en) | Method, device and terminal for screening derivative simulation scenes | |
| CN111126336B (en) | Sample collection method, device and equipment | |
| CN113085861A (en) | Control method and device for automatic driving vehicle and automatic driving vehicle | |
| CN115311522A (en) | Target detection method and device for automatic driving, electronic equipment and 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 |