CN110110696A - Method and apparatus for handling information - Google Patents
Method and apparatus for handling information Download PDFInfo
- Publication number
- CN110110696A CN110110696A CN201910413380.4A CN201910413380A CN110110696A CN 110110696 A CN110110696 A CN 110110696A CN 201910413380 A CN201910413380 A CN 201910413380A CN 110110696 A CN110110696 A CN 110110696A
- Authority
- CN
- China
- Prior art keywords
- traffic signboard
- traffic
- point data
- bounding box
- grid
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- 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
- 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
The embodiment of the present disclosure discloses the method and apparatus for handling information.One specific embodiment of this method includes: to obtain the point data set and image of road；The encirclement frame of each of the combination traffic signboard being made of at least two traffic signboards traffic signboard is determined according to image；Based on the encirclement frame determined, the initial characterising parameter of at least two traffic signboards corresponding at least two bounding box on three-dimensional space is determined；The final characterising parameter of the corresponding bounding box of the traffic signboard is determined based on the initial characterising parameter of the corresponding bounding box of each traffic signboard, and the point data subclass for describing the traffic signboard is determined from point data set according to the bounding box that final characterising parameter determines.The embodiment, which realizes, identifies the combination traffic signboard in point data set.
Description
Technical field
The embodiment of the present disclosure is related to field of computer technology, and in particular to the method and apparatus for handling information.
Background technique
In the current of computer technology and information science high development, electronic map plays the effect that can not be substituted.It lifts
For example, high-precision map is one of the key technology for realizing automatic Pilot technology.It, can be by conducts such as laser radars in practice
The sensor of data acquisition, to obtain the point cloud data for generating high-precision map.In order to obtain high-precision map, need
Obtain the information of the traffic signboard of one of important component in high-precision map.In practical application scene, it sometimes appear that
The case where two or more traffic signboard close-packed arrays, this makes the traffic signboard extracting method based on point cloud data, can
The two or multiple traffic signboards be able to can be extracted as a whole, to cause the reduction of accuracy rate.
Summary of the invention
The embodiment of the present disclosure proposes the method and apparatus for handling information.
In a first aspect, the embodiment of the present disclosure provides a kind of method for handling information, this method comprises: obtaining road
Point data set and image；It is determined in the combination traffic signboard being made of at least two traffic signboards according to above-mentioned image
Each traffic signboard encirclement frame；Based on the encirclement frame determined, determine above-mentioned at least two traffic signboard three
The initial characterising parameter of corresponding at least two bounding box on dimension space；Based on the corresponding bounding box of each traffic signboard
Initial characterising parameter determines the final characterising parameter of the corresponding bounding box of the traffic signboard, and is joined according to above-mentioned final description
The determining bounding box of number determines the point data subclass for describing the traffic signboard from above-mentioned point data set.
In some embodiments, the above-mentioned initial characterising parameter based on the corresponding bounding box of each traffic signboard determines
The final characterising parameter of the corresponding bounding box of the traffic signboard, comprising: to the three-dimensional space where above-mentioned point data set into
Row grid dividing obtains at least one three-dimensional grid；Three-dimensional grid at least one above-mentioned three-dimensional grid is determined as abortive haul
Lattice or non-empty grid；Using the initial characterising parameter of the corresponding bounding box of each traffic signboard as the target letter pre-established
Several initial solutions determines the optimal solution of above-mentioned objective function, wherein above-mentioned objective function is the points for being included based on bounding box
According to quantity, empty number of grid and non-empty number of grid determine；Determining optimal solution is corresponding as the traffic signboard
The final characterising parameter of bounding box.
In some embodiments, the above-mentioned three-dimensional grid by least one above-mentioned three-dimensional grid is determined as abortive haul lattice or non-
Abortive haul lattice, comprising: for the three-dimensional grid at least one above-mentioned three-dimensional grid, determine the point data for including in the three-dimensional grid
Quantity whether be greater than preset amount threshold；In response to determining that it is default that the quantity for the point data for including in the three-dimensional grid is greater than
Amount threshold, determine the three-dimensional grid be non-empty grid；In response to determining the quantity for the point data for including in the three-dimensional grid
Less than or equal to preset amount threshold, determine that the three-dimensional grid is abortive haul lattice.
In some embodiments, the characterising parameter of bounding box includes the coordinate, length and maximum planes of central point
Normal vector.
In some embodiments, above-mentioned that the combination traffic being made of at least two traffic signboards is determined according to above-mentioned image
The encirclement frame of each of Sign Board traffic signboard, comprising: above-mentioned image is imported to the traffic signboard pre-established and is known
Other model obtains whether the traffic signboard for including in above-mentioned image is to combine the judging result of traffic signboard and above-mentioned
The corresponding encirclement frame of each of image traffic signboard, wherein above-mentioned traffic signboard identification model is used for detection image
The corresponding encirclement frame of traffic signboard and image at least two traffic signboards whether be combination traffic signboard.
Second aspect, the embodiment of the present disclosure provide it is a kind of for handling the device of information, above-mentioned apparatus include: obtain it is single
Member is configured to obtain the point data set and image of road；Recognition unit is configured to be determined according to above-mentioned image by least
The encirclement frame of each of the combination traffic signboard of two traffic signboard compositions traffic signboard；First determination unit,
It is configured to determine above-mentioned at least two traffic signboard corresponding at least two on three-dimensional space based on the encirclement frame determined
The initial characterising parameter of a bounding box；Second determination unit is configured to based on the corresponding bounding box of each traffic signboard
Initial characterising parameter determine the final characterising parameter of the corresponding bounding box of the traffic signboard, and according to above-mentioned final description
The bounding box that parameter determines determines the point data subclass for describing the traffic signboard from above-mentioned point data set.
In some embodiments, above-mentioned second determination unit includes: division module, is configured to above-mentioned point data set
The three-dimensional space at place carries out grid dividing, obtains at least one three-dimensional grid；First determining module, be configured to by it is above-mentioned extremely
Three-dimensional grid in a few three-dimensional grid is determined as abortive haul lattice or non-empty grid；Second determining module, being configured to will be each
Initial solution of the initial characterising parameter of the corresponding bounding box of a traffic signboard as the objective function pre-established, determines above-mentioned
The optimal solution of objective function, wherein above-mentioned objective function is the quantity for the point data for being included, empty number of grid based on bounding box
It is determined with non-empty number of grid；Third determining module, the optimal solution for being configured to determine are corresponding as the traffic signboard
Bounding box final characterising parameter.
In some embodiments, above-mentioned first determining module is further configured to: at least one above-mentioned three dimensional network
Three-dimensional grid in lattice, determines whether the quantity for the point data for including in the three-dimensional grid is greater than preset amount threshold；Response
It is greater than preset amount threshold in the quantity for determining the point data for including in the three-dimensional grid, determines that the three-dimensional grid is non-abortive haul
Lattice；In response to determine the three-dimensional grid in include point data quantity be less than or equal to preset amount threshold, determine this three
Dimension grid is abortive haul lattice.
In some embodiments, the characterising parameter of bounding box includes the coordinate, length and maximum planes of central point
Normal vector.
In some embodiments, above-mentioned recognition unit is further configured to: above-mentioned image is imported to the friendship pre-established
Logical Sign Board identification model obtains whether the traffic signboard for including in above-mentioned image is the judgement knot for combining traffic signboard
The corresponding encirclement frame of each of fruit and above-mentioned image traffic signboard, wherein above-mentioned traffic signboard identification model is used
Whether at least two traffic signboards in the corresponding encirclement frame of traffic signboard and image of detection image are that combination is handed over
Logical Sign Board.
The third aspect, the embodiment of the present disclosure provide a kind of equipment, which includes: one or more processors；Storage
Device is stored thereon with one or more programs, when said one or multiple programs are executed by said one or multiple processors
When, so that said one or multiple processors realize the method as described in implementation any in first aspect.
Fourth aspect, the embodiment of the present disclosure provide a kind of computer-readable medium, are stored thereon with computer program,
In, the method as described in implementation any in first aspect is realized when which is executed by processor.
The embodiment of the present disclosure provide the method and apparatus for handling information, first acquisition road point data set with
Image.Later, the traffic of each of the combination traffic signboard being made of at least two traffic signboards is determined according to image
The encirclement frame of Sign Board.Then, based on the encirclement frame determined, determine that at least two traffic signboards are corresponding on three-dimensional space
At least two bounding boxs initial characterising parameter.Finally, initially retouching based on the corresponding bounding box of each traffic signboard
Parameter is stated, determines the final characterising parameter of the corresponding bounding box of the traffic signboard, and the packet determined according to final characterising parameter
It encloses box and determines point data subclass for describing the traffic signboard from point data set.To realize based in image
The recognition result for combining traffic signboard, identifies the combination traffic signboard in point data set, to improve a little
The recognition accuracy of each traffic signboard of traffic signboard is combined in data acquisition system.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the disclosure is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that one embodiment of the disclosure can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method for handling information of the disclosure；
Fig. 3 a and Fig. 3 b are the schematic diagrames according to an application scenarios of the method for handling information of the disclosure；
Fig. 4 is the flow chart according to another embodiment of the method for handling information of the disclosure；
Fig. 5 is the structural schematic diagram according to one embodiment of the device for handling information of the disclosure；
Fig. 6 is adapted for the structural schematic diagram for the computer system for realizing the electronic equipment of the embodiment of the present disclosure.
Specific embodiment
The disclosure 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 related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the disclosure can phase
Mutually combination.The disclosure is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can the method for handling information using the embodiment of the present disclosure or the device for handling information
Exemplary system architecture 100.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications can be installed, such as electronic map class is answered on terminal device 101,102,103
With, electronic cartography class application, web browser applications, the application of shopping class, searching class application, instant messaging tools, mailbox
Client, social platform software etc..
Terminal device 101,102,103 can be hardware, be also possible to software.When terminal device 101,102,103 is hard
When part, it can be the various electronic equipments with point cloud data and image processing function, including but not limited to smart phone, plate
Computer, pocket computer on knee and desktop computer etc..When terminal device 101,102,103 is software, can install
In above-mentioned cited electronic equipment.Multiple softwares or software module may be implemented into (such as providing distributed clothes in it
Business), single software or software module also may be implemented into.It is not specifically limited herein.
Server 105 can be to provide the server of various services, such as the point data set and figure of the road to acquisition
As the background server handled.Background server can point data set to the road of acquisition and image carry out various points
Analysis processing, to determine the point data subclass for describing traffic signboard from point data set.
It should be noted that server 105 can be hardware, it is also possible to software.It, can when server 105 is hardware
To be implemented as the distributed server cluster that multiple servers form, individual server also may be implemented into.When server 105 is
When software, multiple softwares or software module (such as providing Distributed Services) may be implemented into, also may be implemented into single
Software or software module.It is not specifically limited herein.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
It should be noted that the embodiment of the present disclosure provided by for handle information method can by terminal device 101,
102, it 103 executes, can also be executed by server 105.Correspondingly, it can be set for handling the device of information in terminal device
101,102,103, it also can be set in server 105.
With continued reference to Fig. 2, the process of one embodiment of the method for handling information according to the disclosure is shown
200.The method for being used to handle information, comprising the following steps:
Step 201, the point data set and image of road are obtained.
In the present embodiment, for handle the method for information executing subject (such as terminal device shown in FIG. 1 101,
102,103 or server 105) can be by wired connection mode or radio connection from for collection point data acquisition system
The point data set of data acquisition equipment (for example, laser radar, three-dimensional laser scanner etc.) acquisition road.Meanwhile from figure
As acquisition equipment (for example, camera) obtains the image of road.Here, above-mentioned point data set and above-mentioned image are with for the moment
Between, same position acquisition.In practice, the point data acquisition equipment and image capture device being erected on acquisition vehicle can be same
When acquire road point cloud data and image.Here, point cloud data is point data set.As an example, in point data set
Point data may include three-dimensional coordinate and laser reflection intensity.In general, the three-dimensional coordinate of point data may include X-axis, Y-axis and
Information on Z axis.Here, laser reflection intensity can refer to the ratio of laser reflection energy Yu Laser emission energy.
Step 202, it is determined according to image each in the combination traffic signboard being made of at least two traffic signboards
The encirclement frame of a traffic signboard.
In the present embodiment, executing subject can identify the combination being made of at least two traffic signboards from image
Traffic signboard, and determine the encirclement frame of each of combination traffic signboard traffic signboard.Wherein, traffic signboard
Surrounding frame can refer to that the corresponding minimum rectangle of traffic signboard surrounds frame.Here, said combination traffic signboard may include
At least two traffic signboards, and the distance between the adjacent traffic signboard in above-mentioned at least two traffic signboard is less than
Preset threshold.As an example it is assumed that combination traffic signboard is made of tri- traffic signboards of A, B, C, and A, B, C are successively lateral
Arrangement, i.e. A and B are adjacent, and B and C are adjacent, then the distance between A and B are less than preset threshold, and the distance between B and C are less than default
Threshold value.As an example, executing subject can carry out target detection to image, for example, being based on SLIC (simple linear
Iterative clustering, simple linear iteraction cluster) algorithm, or the target detection technique based on deep learning
Deng identifying the combination traffic signboard in image, and calculate combination each of traffic signboard traffic signboard
Surround frame.
In some optional implementations of the present embodiment, above-mentioned steps 202 specific as follows can be carried out: image is led
Enter the traffic signboard identification model pre-established, obtains whether the traffic signboard for including in image is combination traffic signboard
Judging result and each of the image corresponding encirclement frame of traffic signboard.
In the present embodiment, above-mentioned image can be imported the traffic signboard identification model pre-established by executing subject,
To obtain whether the traffic signboard for including in above-mentioned image is the judging result for combining traffic signboard and above-mentioned image
Each of the corresponding encirclement frame of traffic signboard.Here, traffic signboard identification model can be used for the friendship of detection image
Whether at least two traffic signboards in the logical corresponding encirclement frame of Sign Board and image are combination traffic signboard.In this way,
Executing subject can be according to the output of traffic signboard identification model as a result, being identified from image by least two traffic marks
The combination traffic signboard of board composition, and determine the encirclement frame of each of combination traffic signboard traffic signboard.
As an example, above-mentioned traffic signboard identification model can be and be obtained based on deep learning network training.The depth
Degree learning network can be the neural network of a multilayer, may include convolutional layer, pond layer, full articulamentum and classifier etc.
Deng.In practice, can based on different production scenes and the characteristics of data, design by different depth, different number neuron,
The deep learning network that different convolution pond organizational forms is constituted.In the training deep learning network, firstly, it is necessary to obtain
Training sample set, wherein training sample may include that the mark of traffic signboard in road image and road image surrounds
Whether traffic signboard is the annotation results for combining traffic signboard in frame and road image.It later, can be by training sample
Mark corresponding with the road image of input is surrounded frame and annotation results as expectation as input by the road image in set
Output, training obtain traffic signboard identification model.
Step 203, based on the encirclement frame determined, determine at least two traffic signboards on three-dimensional space it is corresponding extremely
The initial characterising parameter of few two bounding boxs.
In the present embodiment, the encirclement frame based on each of above-mentioned at least two traffic signboard traffic signboard,
Executing subject can determine above-mentioned at least two traffic signboard on three-dimensional space corresponding at least two bounding box it is initial
Characterising parameter.As an example, executing subject is first for each of above-mentioned at least two traffic signboard traffic signboard
It can be according to the projection matrix of the true fix data sets of existing method to image.It later, will according to identified projection matrix
The encirclement frame of the traffic signboard carries out back projection's calculating, obtains the traffic signboard corresponding bounding box on three-dimensional space
Initial characterising parameter.Here, the characterising parameter of bounding box can be used for describing the information such as the position of bounding box, size.Generally, lead to
The characterising parameter for crossing bounding box can uniquely determine a bounding box.Traffic signboard can be in the corresponding bounding box of three-dimensional space
Refer to the corresponding external minimum rectangle of traffic signboard.In practice, due to the encirclement frame of traffic signboard identified and determination
Projection matrix there may be errors, so, based on the corresponding bounding box of traffic signboard for surrounding frame and projection matrix and obtaining
Initial characterising parameter may it is not accurate enough, need further to adjust.
In some optional implementations of the present embodiment, the characterising parameter of the corresponding bounding box of traffic signboard can be with
The normal vector of coordinate, length including central point and maximum planes.
As an example, bounding box Sign corresponding for any one traffic signboardi, its center point coordinate can be used
{Ctri:xi,yi,zi∈Ctri, shape description parameter { Shpi:lengthi,widthi,heighti∈ShpiAnd direction { Diri:
dxi,dyi,dzi∈DiriIndicate.Wherein, center point coordinate can refer to bounding box SigniGeometric center coordinate.Shape
Characterising parameter can be used for describing the length and width and height of bounding box.Direction can be used for describing the normal direction of maximum planes in bounding box
Amount.
Step 204, which is determined based on the initial characterising parameter of the corresponding bounding box of each traffic signboard
The final characterising parameter of the corresponding bounding box of board, and the bounding box determined according to final characterising parameter are true from point data set
Determine the point data subclass for describing the traffic signboard.
In the present embodiment, for each of above-mentioned at least two traffic signboard traffic signboard, executing subject
The corresponding bounding box of the traffic signboard can be determined based on the initial characterising parameter of the corresponding bounding box of the traffic signboard
Final characterising parameter.As an example, executing subject can by the initial characterising parameter of the corresponding bounding box of the traffic signboard into
The various processing of row, such as weight, be added with setting value etc., to obtain finally retouching for the corresponding bounding box of the traffic signboard
State parameter.Later, executing subject can the bounding box according to determined by final characterising parameter from point data set determination be used for
The point data subclass of the traffic signboard is described.Specifically, executing subject can be by point data set, final description ginseng
The point data that bounding box determined by number is covered is determined as point data subclass.
With continued reference to Fig. 3 a and 3b, Fig. 3 a and 3b are the application scenarios according to the method for handling information of the present embodiment
A schematic diagram.In the application scenarios of Fig. 3 a and 3b, Fig. 3 a is the image 301 for the road that electronic equipment obtains.Electronics is set
The standby point data set and image 301 for obtaining road first.Later, electronic equipment identifies three traffic marks from image 301
Know the combination traffic signboard of board composition, and determine the encirclement frame of each of combination traffic signboard traffic signboard,
It obtains surrounding frame 3011a, 3012a and 3013a.Then, encirclement frame 3011a, 3012a based on three traffic signboards and
3013a determines the initial characterising parameter of three traffic signboards corresponding three bounding boxs on three-dimensional space.Finally, for
Each of three traffic signboards traffic signboard, the initial description ginseng based on the corresponding bounding box of the traffic signboard
Number determines the final characterising parameter of the corresponding bounding box of the traffic signboard, and the bounding box determined according to final characterising parameter
The point data subclass for describing the traffic signboard is determined from point data set.Wherein, 3011b, 3012b in Fig. 3 b
Bounding box determined by being the corresponding final characterising parameter of three traffic signboards with 3013b.
The method provided by the above embodiment of the disclosure is realized based on the recognition result for combining traffic signboard in image,
Combination traffic signboard in point data set is identified, combines traffic signboard in point data set to improve
The recognition accuracy of each traffic signboard.
With further reference to Fig. 4, it illustrates the processes 400 of another embodiment of the method for handling information.The use
In the process 400 of the method for processing information, comprising the following steps:
Step 401, the point data set and image of road are obtained.
In the present embodiment, step 401 is similar with the step 201 of embodiment illustrated in fig. 2, and details are not described herein again.
Step 402, it is determined according to image each in the combination traffic signboard being made of at least two traffic signboards
The encirclement frame of a traffic signboard.
In the present embodiment, step 402 is similar with the step 202 of embodiment illustrated in fig. 2, and details are not described herein again.
Step 403, based on the encirclement frame for the traffic signboard determined, determine at least two traffic signboards in three-dimensional space
Between upper corresponding at least two bounding box initial characterising parameter.
In the present embodiment, step 403 is similar with the step 203 of embodiment illustrated in fig. 2, and details are not described herein again.
Step 404, grid dividing is carried out to the three-dimensional space where point data set, obtains at least one three-dimensional grid.
In the present embodiment, above-mentioned executing subject can carry out grid stroke to the three-dimensional space where above-mentioned point data set
Point, to obtain at least one three-dimensional grid.
Step 405, the three-dimensional grid at least one three-dimensional grid is determined as abortive haul lattice or non-empty grid.
In the present embodiment, for each of at least one above-mentioned three-dimensional grid three-dimensional grid, executing subject can be with
According to the quantity of point data included in the three-dimensional grid, determine that the three-dimensional grid is abortive haul lattice or non-empty grid.It needs
Bright, in the present embodiment specific implementation, step 404 and step 405 can be with Exactly-onces.
In some optional implementations of the present embodiment, above-mentioned steps 405 can specifically include the following contents:
Firstly, for the three-dimensional grid at least one three-dimensional grid, the point data for including in the three-dimensional grid is determined
Whether quantity is greater than preset amount threshold.
In this implementation, for each of at least one above-mentioned three-dimensional grid three-dimensional grid, executing subject can
To determine whether the quantity for the point data for including in the three-dimensional grid is greater than preset amount threshold.Here, data threshold can be with
It is set according to actual needs.
Then, it in response to determining that the quantity for the point data for including in the three-dimensional grid is greater than preset amount threshold, determines
The three-dimensional grid is non-empty grid.
In this implementation, if it is determined that the quantity for the point data for including in the three-dimensional grid is greater than preset quantity threshold
Value can then determine that the three-dimensional grid is non-empty grid.
Finally, in response to determining that the quantity for the point data for including in the three-dimensional grid is less than or equal to preset quantity threshold
Value determines that the three-dimensional grid is abortive haul lattice.
In this implementation, if it is determined that the quantity for the point data for including in the three-dimensional grid is less than or equal to preset
Amount threshold can then determine that the three-dimensional grid is abortive haul lattice.
Step 406, using the initial characterising parameter of the corresponding bounding box of each traffic signboard as the mesh pre-established
The initial solution of scalar functions determines the optimal solution of objective function.
In the present embodiment, executing subject can pre-define an objective function, as an example, objective function can be
It is determined based on quantity, empty number of grid and the non-empty number of grid for the point data that bounding box is included, for example, target letter
Number can beWherein, NptsFor bounding box SigniThe point data for including
Quantity；NoFor bounding box SigniThe quantity for the non-empty grid for including；NeFor bounding box SigniThe quantity for the abortive haul lattice for including.
Later, executing subject can be using the initial characterising parameter of the corresponding bounding box of each traffic signboard as the first of objective function
Begin solution, and by maximizing objective function, acquires the characterising parameter of optimal bounding box, that is, acquire the optimal solution of objective function.
Step 407, using determining optimal solution as the final characterising parameter of the corresponding bounding box of the traffic signboard.
In the present embodiment, executing subject can be corresponding as the traffic signboard using the optimal solution determined in step 406
Bounding box final characterising parameter.
Step 408, the bounding box determined according to final characterising parameter is determined from point data set for describing the traffic
The point data subclass of Sign Board.
In the present embodiment, executing subject can the bounding box according to determined by final characterising parameter from point data set
Determine the point data subclass for describing the traffic signboard.Specifically, executing subject can will be in point data set, most
The point data that bounding box determined by whole characterising parameter is covered is determined as point data subclass.
Figure 4, it is seen that the method for handling information compared with the corresponding embodiment of Fig. 2, in the present embodiment
Process 400 highlight the step that initial characterising parameter and objective function based on bounding box determine the final characterising parameter of bounding box
Suddenly.Thus, it is possible to which the final characterising parameter made is more accurate, traffic is combined to further improve in point data set
The recognition accuracy of each traffic signboard of Sign Board.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, present disclose provides one kind for handling letter
One embodiment of the device of breath, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in figure 5, the present embodiment includes: acquiring unit 501, recognition unit for handling the device 500 of information
502, the first determination unit 503 and the second determination unit 504.Wherein, acquiring unit 501 is configured to obtain the point data of road
Set and image；Recognition unit 502 is configured to determine the combination being made of at least two traffic signboards according to above-mentioned image
The encirclement frame of each of traffic signboard traffic signboard；First determination unit 503 is configured to based on the packet determined
Peripheral frame determines the initial description ginseng of above-mentioned at least two traffic signboard corresponding at least two bounding box on three-dimensional space
Number；Second determination unit 504 is configured to determine based on the initial characterising parameter of the corresponding bounding box of each traffic signboard
The final characterising parameter of the corresponding bounding box of the traffic signboard, and the bounding box that is determined according to above-mentioned final characterising parameter from
The point data subclass for describing the traffic signboard is determined in above-mentioned point data set.
In the present embodiment, for handling acquiring unit 501, the determination of recognition unit 502, first of the device 500 of information
The specific processing of unit 503 and the second determination unit 504 and its brought technical effect can refer to Fig. 2 corresponding embodiment respectively
Middle step 201, step 202, the related description of step 203 and step 204, details are not described herein.
In some optional implementations of the present embodiment, above-mentioned second determination unit 504 includes: division module (figure
In be not shown), be configured to where above-mentioned point data set three-dimensional space carry out grid dividing, obtain at least one three-dimensional
Grid；First determining module (not shown) is configured to determine the three-dimensional grid at least one above-mentioned three-dimensional grid
For abortive haul lattice or non-empty grid；Second determining module (not shown) is configured to each traffic signboard is corresponding
Initial solution of the initial characterising parameter of bounding box as the objective function pre-established, determines the optimal solution of above-mentioned objective function,
Wherein, above-mentioned objective function is that quantity, empty number of grid and the non-empty number of grid of the point data for being included are true based on bounding box
Fixed；Third determining module (not shown), the optimal solution for being configured to determine is as the corresponding packet of the traffic signboard
Enclose the final characterising parameter of box.
In some optional implementations of the present embodiment, above-mentioned first determining module is further configured to: for
It is pre- to determine whether the quantity for the point data for including in the three-dimensional grid is greater than for three-dimensional grid at least one above-mentioned three-dimensional grid
If amount threshold；In response to determining that the quantity for the point data for including in the three-dimensional grid is greater than preset amount threshold, determine
The three-dimensional grid is non-empty grid；In response to determining that it is preset that the quantity for the point data for including in the three-dimensional grid is less than or equal to
Amount threshold determines that the three-dimensional grid is abortive haul lattice.
In some optional implementations of the present embodiment, the characterising parameter of bounding box include the coordinate of central point, length,
Wide, high and maximum planes normal vector.
In some optional implementations of the present embodiment, above-mentioned recognition unit 502 is further configured to: will be above-mentioned
Image imports the traffic signboard identification model pre-established, obtains whether the traffic signboard for including in above-mentioned image is combination
The corresponding encirclement frame of each of the judging result of traffic signboard and above-mentioned image traffic signboard, wherein above-mentioned friendship
Logical traffic signboard corresponding encirclement frame of the Sign Board identification model for detection image and at least two traffic in image
Whether Sign Board is combination traffic signboard.
Below with reference to Fig. 6, it illustrates the electronic equipment that is suitable for being used to realize embodiment of the disclosure, (example is as shown in figure 1
Server or terminal device) 600 structural schematic diagram.Electronic equipment shown in Fig. 6 is only an example, should not be to the disclosure
Embodiment function and use scope bring any restrictions.
As shown in fig. 6, electronic equipment 600 may include processing unit (such as central processing unit, graphics processor etc.)
601, random access can be loaded into according to the program being stored in read-only memory (ROM) 602 or from storage device 608
Program in memory (RAM) 603 and execute various movements appropriate and processing.In RAM 603, it is also stored with electronic equipment
Various programs and data needed for 600 operations.Processing unit 601, ROM 602 and RAM603 are connected with each other by bus 604.
Input/output (I/O) interface 605 is also connected to bus 604.
In general, following device can connect to I/O interface 605: including such as touch screen, touch tablet, keyboard, mouse, taking the photograph
As the input unit 606 of head, microphone, accelerometer, gyroscope etc.；Including such as liquid crystal display (LCD), loudspeaker, vibration
The output device 607 of dynamic device etc.；Storage device 608 including such as tape, hard disk etc.；And communication device 609.Communication device
609, which can permit electronic equipment 600, is wirelessly or non-wirelessly communicated with other equipment to exchange data.Although Fig. 6 shows tool
There is the electronic equipment 600 of various devices, it should be understood that being not required for implementing or having all devices shown.It can be with
Alternatively implement or have more or fewer devices.Each box shown in Fig. 6 can represent a device, can also root
According to needing to represent multiple devices.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communication device 609, or from storage device 608
It is mounted, or is mounted from ROM 602.When the computer program is executed by processing unit 601, the implementation of the disclosure is executed
The above-mentioned function of being limited in the method for example.
It is situated between it should be noted that computer-readable medium described in embodiment of the disclosure can be computer-readable signal
Matter or computer readable storage medium either the two any combination.Computer readable storage medium for example can be with
System, device or the device of --- but being not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or it is any more than
Combination.The more specific example of computer readable storage medium can include but is not limited to: have one or more conducting wires
Electrical connection, portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type are programmable
Read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic are deposited
Memory device or above-mentioned any appropriate combination.In embodiment of the disclosure, computer readable storage medium, which can be, appoints
What include or the tangible medium of storage program that the program can be commanded execution system, device or device use or and its
It is used in combination.And in embodiment of the disclosure, computer-readable signal media may include in a base band or as carrier wave
The data-signal that a part is propagated, wherein carrying computer-readable program code.The data-signal of this propagation can be adopted
With diversified forms, including but not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal is situated between
Matter can also be any computer-readable medium other than computer readable storage medium, which can be with
It sends, propagate or transmits for by the use of instruction execution system, device or device or program in connection.Meter
The program code for including on calculation machine readable medium can transmit with any suitable medium, including but not limited to: electric wire, optical cable,
RF (radio frequency) etc. or above-mentioned any appropriate combination.
Above-mentioned computer-readable medium can be included in above-mentioned electronic equipment；It is also possible to individualism, and not
It is fitted into the electronic equipment.Above-mentioned computer-readable medium carries one or more program, when said one or more
When a program is executed by the electronic equipment, so that the electronic equipment: obtaining the point data set and image of road；According to above-mentioned figure
Encirclement frame as determining each of the combination traffic signboard being made of at least two traffic signboards traffic signboard；Base
In the encirclement frame determined, above-mentioned at least two traffic signboard corresponding at least two bounding box on three-dimensional space is determined
Initial characterising parameter；The traffic signboard pair is determined based on the initial characterising parameter of the corresponding bounding box of each traffic signboard
The final characterising parameter for the bounding box answered, and the bounding box that is determined according to above-mentioned final characterising parameter is from above-mentioned point data set
Middle determination is used to describe the point data subclass of the traffic signboard.
The behaviour for executing embodiment of the disclosure can be write with one or more programming languages or combinations thereof
The computer program code of work, 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 program design language
Speech.Program code can be executed fully on the user computer, partly be executed on the user computer, as an independence
Software package execute, part on the user computer part execute on the remote computer or completely in remote computer or
It is executed on server.In situations involving remote computers, remote computer can pass through the network of any kind --- packet
It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit
It is connected with ISP by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in embodiment of the disclosure can be realized by way of software, can also be passed through
The mode of hardware is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor
Including acquiring unit, recognition unit, the first determination unit and the second determination unit.Wherein, the title of these units is in certain feelings
The restriction to the unit itself is not constituted under condition, for example, acquiring unit is also described as " obtaining the point data collection of road
Close the unit with image ".
Above description is only the preferred embodiment of the disclosure and the explanation to institute's application technology principle.Those skilled in the art
Member it should be appreciated that embodiment of the disclosure involved in invention scope, however it is not limited to the specific combination of above-mentioned technical characteristic and
At technical solution, while should also cover do not depart from foregoing invention design in the case where, by above-mentioned technical characteristic or its be equal
Feature carries out any combination and other technical solutions for being formed.Such as disclosed in features described above and embodiment of the disclosure (but
It is not limited to) technical characteristic with similar functions is replaced mutually and the technical solution that is formed.
Claims (12)
1. a kind of method for handling information, comprising:
Obtain the point data set and image of road；
Each of the combination traffic signboard being made of at least two traffic signboards traffic mark is determined according to described image
Know the encirclement frame of board；
Based on the encirclement frame determined, at least two traffic signboard corresponding at least two packet on three-dimensional space is determined
Enclose the initial characterising parameter of box；
The corresponding encirclement of the traffic signboard is determined based on the initial characterising parameter of the corresponding bounding box of each traffic signboard
The final characterising parameter of box, and determined and used from the point data set according to the bounding box that the final characterising parameter determines
In the point data subclass for describing the traffic signboard.
2. described based on the initial of the corresponding bounding box of each traffic signboard according to the method described in claim 1, wherein
Characterising parameter determines the final characterising parameter of the corresponding bounding box of the traffic signboard, comprising:
Grid dividing is carried out to the three-dimensional space where the point data set, obtains at least one three-dimensional grid；
Three-dimensional grid at least one described three-dimensional grid is determined as abortive haul lattice or non-empty grid；
Using the initial characterising parameter of the corresponding bounding box of each traffic signboard as the initial of the objective function pre-established
Solution, determines the optimal solution of the objective function, wherein the objective function is the number for the point data for being included based on bounding box
What amount, empty number of grid and non-empty number of grid determined；
Using determining optimal solution as the final characterising parameter of the corresponding bounding box of the traffic signboard.
3. according to the method described in claim 2, wherein, the three-dimensional grid by least one described three-dimensional grid determines
For abortive haul lattice or non-empty grid, comprising:
For the three-dimensional grid at least one described three-dimensional grid, determine that the quantity for the point data for including in the three-dimensional grid is
It is no to be greater than preset amount threshold；
In response to determining that the quantity for the point data for including in the three-dimensional grid is greater than preset amount threshold, the three-dimensional grid is determined
For non-empty grid；
In response to determine the three-dimensional grid in include point data quantity be less than or equal to preset amount threshold, determine this three
Dimension grid is abortive haul lattice.
4. according to the method described in claim 1, wherein, the characterising parameter of bounding box include the coordinate of central point, length,
And the normal vector of maximum planes.
5. described to be determined according to described image by least two traffic signboard groups according to the method described in claim 1, wherein
At combination each of traffic signboard traffic signboard encirclement frame, comprising:
Described image is imported to the traffic signboard identification model pre-established, obtains the traffic signboard for including in described image
It whether is to combine each of judging result and the described image of the traffic signboard corresponding encirclement frame of traffic signboard,
Wherein, the traffic signboard identification model is in the corresponding encirclement frame of traffic signboard and image of detection image
Whether at least two traffic signboards are combination traffic signboard.
6. a kind of for handling the device of information, comprising:
Acquiring unit is configured to obtain the point data set and image of road；
Recognition unit is configured to determine the combination traffic signboard being made of at least two traffic signboards according to described image
Each of traffic signboard encirclement frame；
First determination unit is configured to determine at least two traffic signboard in three-dimensional based on the encirclement frame determined
The spatially initial characterising parameter of corresponding at least two bounding box；
Second determination unit, being configured to determine based on the initial characterising parameter of the corresponding bounding box of each traffic signboard should
The final characterising parameter of the corresponding bounding box of traffic signboard, and the bounding box that is determined according to the final characterising parameter is from institute
State the point data subclass determined in point data set for describing the traffic signboard.
7. device according to claim 6, wherein second determination unit includes:
Division module is configured to carry out grid dividing to the three-dimensional space where the point data set, obtains at least one
Three-dimensional grid；
First determining module is configured to the three-dimensional grid at least one described three-dimensional grid being determined as abortive haul lattice or non-empty
Grid；
Second determining module is configured to using the initial characterising parameter of the corresponding bounding box of each traffic signboard as in advance
The initial solution of the objective function of foundation determines the optimal solution of the objective function, wherein the objective function is based on bounding box
What the quantity for the point data for being included, empty number of grid and non-empty number of grid determined；
Third determining module, the optimal solution for being configured to determine is as the final description of the corresponding bounding box of the traffic signboard
Parameter.
8. device according to claim 7, wherein first determining module is further configured to:
For the three-dimensional grid at least one described three-dimensional grid, determine that the quantity for the point data for including in the three-dimensional grid is
It is no to be greater than preset amount threshold；
In response to determining that the quantity for the point data for including in the three-dimensional grid is greater than preset amount threshold, the three-dimensional grid is determined
For non-empty grid；
In response to determine the three-dimensional grid in include point data quantity be less than or equal to preset amount threshold, determine this three
Dimension grid is abortive haul lattice.
9. device according to claim 6, wherein the characterising parameter of bounding box include the coordinate of central point, length,
And the normal vector of maximum planes.
10. device according to claim 6, wherein the recognition unit is further configured to:
Described image is imported to the traffic signboard identification model pre-established, obtains the traffic signboard for including in described image
It whether is to combine each of judging result and the described image of the traffic signboard corresponding encirclement frame of traffic signboard,
Wherein, the traffic signboard identification model is in the corresponding encirclement frame of traffic signboard and image of detection image
Whether at least two traffic signboards are combination traffic signboard.
11. a kind of equipment, comprising:
One or more processors；
Storage device is stored thereon with 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
Now such as method as claimed in any one of claims 1 to 5.
12. a kind of computer-readable medium, is stored thereon with computer program, wherein real when described program is executed by processor
Now such as method as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910413380.4A CN110110696B (en) | 2019-05-17 | 2019-05-17 | Method and apparatus for processing information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910413380.4A CN110110696B (en) | 2019-05-17 | 2019-05-17 | Method and apparatus for processing information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110110696A true CN110110696A (en) | 2019-08-09 |
| CN110110696B CN110110696B (en) | 2022-07-05 |
Family
ID=67490789
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910413380.4A Active CN110110696B (en) | 2019-05-17 | 2019-05-17 | Method and apparatus for processing information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110110696B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112034488A (en) * | 2020-08-28 | 2020-12-04 | 北京海益同展信息科技有限公司 | Automatic target object labeling method and device |
| CN113450459A (en) * | 2020-03-25 | 2021-09-28 | 北京四维图新科技股份有限公司 | Method and device for constructing three-dimensional model of target object |
| CN114136333A (en) * | 2021-10-15 | 2022-03-04 | 阿波罗智能技术(北京)有限公司 | High-precision map road data generation method, device and equipment based on hierarchical features |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559507A (en) * | 2013-11-18 | 2014-02-05 | 沈阳工业大学 | Method for detecting traffic signs based on combination of color feature and shape feature |
| KR20140061156A (en) * | 2012-11-13 | 2014-05-21 | 한국건설기술연구원 | Position detecting method of road traffic sign |
| CN108734979A (en) * | 2017-04-20 | 2018-11-02 | 通用汽车环球科技运作有限责任公司 | Traffic lights detecting system and method |
| CN108846333A (en) * | 2018-05-30 | 2018-11-20 | 厦门大学 | Sign board landmark data collection generates and vehicle positioning method |
| CN109559528A (en) * | 2019-01-18 | 2019-04-02 | 吉林大学 | It is a kind of based on 3D laser radar from perception interactive formula traffic-control unit |
| CN109753949A (en) * | 2019-01-31 | 2019-05-14 | 南京邮电大学 | A kind of more form method for traffic sign detection based on deep learning |
-
2019
- 2019-05-17 CN CN201910413380.4A patent/CN110110696B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140061156A (en) * | 2012-11-13 | 2014-05-21 | 한국건설기술연구원 | Position detecting method of road traffic sign |
| CN103559507A (en) * | 2013-11-18 | 2014-02-05 | 沈阳工业大学 | Method for detecting traffic signs based on combination of color feature and shape feature |
| CN108734979A (en) * | 2017-04-20 | 2018-11-02 | 通用汽车环球科技运作有限责任公司 | Traffic lights detecting system and method |
| CN108846333A (en) * | 2018-05-30 | 2018-11-20 | 厦门大学 | Sign board landmark data collection generates and vehicle positioning method |
| CN109559528A (en) * | 2019-01-18 | 2019-04-02 | 吉林大学 | It is a kind of based on 3D laser radar from perception interactive formula traffic-control unit |
| CN109753949A (en) * | 2019-01-31 | 2019-05-14 | 南京邮电大学 | A kind of more form method for traffic sign detection based on deep learning |
Non-Patent Citations (3)
| Title |
|---|
| 孙殿柱 等: "基于遗传算法的散乱点云最小包围盒求解", 《北京航空航天大学学报》 * |
| 宁振伟 等: "《数字城市三维建模技术与实践》", 31 March 2014, 测绘出版社 * |
| 翟羽 等: "《现代测量学 第2版》", 31 July 2016, 北京：测绘出版社 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113450459A (en) * | 2020-03-25 | 2021-09-28 | 北京四维图新科技股份有限公司 | Method and device for constructing three-dimensional model of target object |
| CN113450459B (en) * | 2020-03-25 | 2024-03-22 | 北京四维图新科技股份有限公司 | Method and device for constructing three-dimensional model of target object |
| CN112034488A (en) * | 2020-08-28 | 2020-12-04 | 北京海益同展信息科技有限公司 | Automatic target object labeling method and device |
| CN112034488B (en) * | 2020-08-28 | 2023-05-02 | 京东科技信息技术有限公司 | Automatic labeling method and device for target object |
| CN114136333A (en) * | 2021-10-15 | 2022-03-04 | 阿波罗智能技术(北京)有限公司 | High-precision map road data generation method, device and equipment based on hierarchical features |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110110696B (en) | 2022-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112528977B (en) | Target detection method, target detection device, electronic equipment and storage medium | |
| CN108090916B (en) | Method and apparatus for tracking the targeted graphical in video | |
| CN108898185A (en) | Method and apparatus for generating image recognition model | |
| CN108304835A (en) | character detecting method and device | |
| CN110400363A (en) | Map constructing method and device based on laser point cloud | |
| CN109410253B (en) | For generating method, apparatus, electronic equipment and the computer-readable medium of information | |
| CN108492364A (en) | The method and apparatus for generating model for generating image | |
| CN110110696A (en) | Method and apparatus for handling information | |
| CN109740018A (en) | Method and apparatus for generating video tab model | |
| CN109815365A (en) | Method and apparatus for handling video | |
| CN109947989A (en) | Method and apparatus for handling video | |
| CN109242801A (en) | Image processing method and device | |
| CN110516678A (en) | Image processing method and device | |
| CN110033423A (en) | Method and apparatus for handling image | |
| CN109961032A (en) | Method and apparatus for generating disaggregated model | |
| CN110263209A (en) | Method and apparatus for generating information | |
| CN109325996A (en) | Method and apparatus for generating information | |
| CN109272050B (en) | Image processing method and device | |
| CN109754464A (en) | Method and apparatus for generating information | |
| CN109118456A (en) | Image processing method and device | |
| CN110070076A (en) | Method and apparatus for choosing trained sample | |
| CN110349161A (en) | Image partition method, device, electronic equipment and storage medium | |
| CN110222641A (en) | The method and apparatus of image for identification | |
| CN109285181A (en) | The method and apparatus of image for identification | |
| CN108573054A (en) | Method and apparatus for pushed information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |