CN109933635A - A kind of method and device updating map data base - Google Patents
A kind of method and device updating map data base Download PDFInfo
- Publication number
- CN109933635A CN109933635A CN201910112872.XA CN201910112872A CN109933635A CN 109933635 A CN109933635 A CN 109933635A CN 201910112872 A CN201910112872 A CN 201910112872A CN 109933635 A CN109933635 A CN 109933635A
- Authority
- CN
- China
- Prior art keywords
- updated
- section
- state
- current state
- road 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a kind of method and devices for updating map data base, it is related to technical field of data processing, this method comprises: the current state of the traffic element in the road image for passing through identification section to be updated, then the storage state of the traffic element in the section to be updated saved in the current state of the traffic element in section to be updated and map data base is compared, if comparing consistent, the storage state of the traffic element in the section to be updated saved in map data base is then updated using the current state of the traffic element in road image, otherwise map data base is not updated.Due to the traffic element for not needing to extract road image by way of manual work, and the current state of traffic element is compared with the storage state of the traffic element in map data base, and then update map data base, to on the one hand improve the update efficiency of map data base, human cost has on the other hand been saved.
Description
Technical field
The present embodiments relate to technical field of data processing more particularly to a kind of methods and dress for updating map data base
It sets.
Background technique
Numerous application scenarios of requirement with to(for) geo-spatial data gradually refines, scale and real time implementation, ground
The frequency of geographical information updating in chart database is also higher and higher.Currently, being updated in map data base using crowdsourcing mode
When geography information, traffic element is extracted from the data that crowdsourcing returns by way of manual work, map datum is then written
Library.As the data volume that crowdsourcing returns increasingly increases, since the mode efficiency of manual work is lower, cause to be difficult to meet fast pace
Map data base renewal frequency.
Summary of the invention
Due to extracting traffic element from the data that crowdsourcing returns by way of manual work, map datum is then written
The method in library, the low problem of operating efficiency, the embodiment of the invention provides a kind of method and devices for updating map data base.
On the one hand, the embodiment of the invention provides a kind of methods for updating map data base, comprising:
Obtain the road image in section to be updated；
The current state of the traffic element in the section to be updated is determined according to the road image in the section to be updated；
By section to be updated described in the current state of the traffic element in the section to be updated and the map data base
The storage state of traffic element be compared；
When the current state and the storage state are inconsistent, the storage shape is updated using the current state
State.
On the one hand, the embodiment of the invention provides a kind of devices for updating map data base, comprising:
Module is obtained, for obtaining the road image in section to be updated；
Identification module, for determining the traffic element in the section to be updated according to the road image in the section to be updated
Current state；
Comparison module, for by institute in the current state of the traffic element in the section to be updated and the map data base
The storage state for stating the traffic element in section to be updated is compared；
Update module is used for when the current state and the storage state are inconsistent, more using the current state
The new storage state.
On the one hand, the embodiment of the invention provides a kind of terminal devices, including at least one processing unit and at least one
A storage unit, wherein the storage unit is stored with computer program, when described program is executed by the processing unit,
So that the processing unit executes the step of method for updating map data base.
On the one hand, the embodiment of the invention provides a kind of computer-readable medium, being stored with can be executed by terminal device
Computer program, when described program is run on the terminal device so that the terminal device execute update map data base
Method the step of.
In the embodiment of the present invention, the current state of the traffic element in road image by identifying section to be updated, so
Afterwards by the traffic element in the section to be updated saved in the current state of the traffic element in section to be updated and map data base
Storage state is compared, if comparing unanimously, updates map datum using the current state of the traffic element in road image
The storage state of the traffic element in the section to be updated saved in library, does not otherwise update map data base.Due to not needing to pass through
The mode of manual work extracts the traffic element of road image, and by the friendship in the current state and map data base of traffic element
The storage state of logical element is compared, and then updates map data base, on the one hand improve the update of map data base
On the other hand efficiency has saved human cost.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly introduced, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill in field, without any creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is a kind of application scenario diagram that the embodiment of the present invention is applicable in；
Fig. 2 is a kind of flow diagram of method for updating map data base provided in an embodiment of the present invention；
Fig. 3 is a kind of schematic diagram of more new images provided in an embodiment of the present invention；
Fig. 4 is a kind of schematic diagram of road image provided in an embodiment of the present invention；
Fig. 5 is a kind of schematic diagram of road image provided in an embodiment of the present invention；
Fig. 6 is a kind of schematic diagram of road image provided in an embodiment of the present invention；
Fig. 7 is a kind of schematic diagram of road image provided in an embodiment of the present invention；
Fig. 8 is a kind of schematic diagram of road image provided in an embodiment of the present invention；
Fig. 9 is a kind of flow diagram of the method for the current state of determining traffic element provided in an embodiment of the present invention；
Figure 10 is a kind of flow diagram of multiclass classification method provided in an embodiment of the present invention；
Figure 11 is a kind of structural schematic diagram of device for updating map data base provided in an embodiment of the present invention；
Figure 12 is a kind of structural schematic diagram of terminal device provided in an embodiment of the present invention.
Specific embodiment
In order to which the purpose of the present invention, technical solution and beneficial effect is more clearly understood, below in conjunction with attached drawing and implementation
Example, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only used to explain this hair
It is bright, it is not intended to limit the present invention.
In order to facilitate understanding, noun involved in the embodiment of the present invention is explained below.
Map data base: map data base (cartographic database) is based on map digitizing data
Database, each element of the map content being stored in computer (such as control point, landforms, land type, settlement place, the hydrology,
Vegetation, communications and transportation, boundary etc.) digital information file, data base management system and other software and hardwares set.
Crowdsourcing: referring to the task that a company or mechanism are executed the past by employee, with freely voluntary form outsourcing
To the way of unspecific (and being usually large-scale) public volunteer.
During concrete practice, it was found by the inventors of the present invention that after obtaining the picture that crowdsourcing returns, using complete artificial
When the mode of operation extracts the traffic element in picture and inserts map data base, operating efficiency is lower.It is returned with crowdsourcing
Data volume increasingly increases, and manual work is difficult to meet allegro map data base renewal frequency.
It slightly arrives for this purpose, examining when chart database is updated over the ground, mainly the friendship of the road in update map data base
The storage state of logical element, if the state of traffic element changes, the storage of the traffic element in chart database over the ground
State is updated, and is not otherwise needed chart database over the ground and is updated.Therefore, it in the embodiment of the present invention, gets to be updated
It, can be with the current state of the traffic element in the road image in automatic identification section to be updated, later after the road image in section
Again by the storage shape of the traffic element in section to be updated in the current state of the traffic element in section to be updated and map data base
State is compared.When current state and storage state are inconsistent, state is updated storage using current state.Pass through automatic identification
The state of traffic element substitutes manual work in road image, and then updates map data base, on the one hand improve ground
The update efficiency of chart database, has on the other hand saved human cost.
The method of update map data base in the embodiment of the present invention can be applied to application scenarios as shown in Figure 1,
It include terminal device 101, server 102 in the application scenarios.
Terminal device 101 is the electronic equipment for having network communications capability, which can be smart phone, plate
Computer or portable personal computer etc..Terminal device 101 is connect by wireless network with server 102.In server 102
Including map data base, server 102 is in the server cluster that a server or several servers form or cloud computing
The heart.
When needing the road in chart database to be over the ground updated, the image that server 102 issues section to be updated is adopted
Set task.Crowdsourcing personnel can get Image Acquisition task by terminal device 101, and section acquisition to be updated is then gone to update
Image.Crowdsourcing personnel are sent to server 102 after can acquiring more new images by terminal device 101, or using other tools
The equipment acquisition more new images of standby image collecting function are simultaneously sent to server 102.Server 102 receive more new images it
Afterwards, more new images are cleaned, removal does not include the more new images of road, poor definition.Then it is cut from more new images
Then the road image in section to be updated out extracts the traffic element in section to be updated from the road image in section to be updated
Current state.Later again by the traffic in section to be updated in the current state of the traffic element in section to be updated and map data base
The storage state of element is compared.When current state and storage state are inconsistent, using the traffic element in section to be updated
Current state update the storage state of the traffic element in section to be updated in map data base, otherwise do not update map datum
Library.
Based on application scenario diagram shown in FIG. 1, the embodiment of the invention provides a kind of methods for updating map data base
The process of process, this method can be executed by the device of update map data base, and the device for updating map data base can be Fig. 1
Shown in server 102, as shown in Figure 2, comprising the following steps:
Step S201 obtains the road image in section to be updated.
Step S202 determines the current state of the traffic element in section to be updated according to the road image in section to be updated.
Specifically, a section to be updated may correspond to one or more road image, and traffic element includes but is not limited to
Speed limitation board hands over limit board, traffic lights, number of track-lines, road pavement state.It may include above-mentioned one in the road image in section to be updated
Kind or a variety of traffic elements.The road image in section to be updated is most freshly harvested road image, by detection road image
Traffic element can determine the current state of the traffic element in section to be updated.
Step S203, by the friendship in section to be updated in the current state of the traffic element in section to be updated and map data base
The storage state of logical element is compared.
Step S204 updates storage state using current state when current state and the storage state are inconsistent.
Specifically, when detecting multiple traffic elements in section to be updated, each traffic element that will test is worked as
Preceding state is compared with the storage state of traffic element corresponding in map data base, when comparing inconsistent, using current
State updates storage state.
Due to automatically extracting the current state of traffic element in road image when updating map data base, then with ground
The storage state of the traffic element in section to be updated is compared in chart database, updates map data base according to comparison result,
Traffic element without extracting road image by way of manual work, and by the current state and map of traffic element
The storage state of traffic element in database is compared, and then updates map data base, on the one hand improve map
The update efficiency of database, has on the other hand saved human cost.
Optionally, in above-mentioned steps S201, due to that may be updated to multiple sections in the same period, in order to just
Classify in the more new images that crowdsourcing personnel report, the corresponding location information of every more new images.Acquiring multiple more
After the location information of new images and multiple more new images, by the position of the location information in section to be updated and multiple more new images into
Row matching, determines the more new images in section to be updated from multiple more new images.Then from the more new images in section to be updated
It is cut into the road image in section to be updated.
Specifically, the location information of image to be updated can be the global positioning system (Global of collection point
Positioning System, abbreviation GPS) information.According to the GPS information of more new images and the position in known section to be updated
Confidence breath, more new images are adsorbed on corresponding section to be updated.One section to be updated corresponding one or more updates figure
Picture.When due to being updated in chart database over the ground, the state of the traffic element mainly on update road, and more new images
In may include road, further include other objects.Illustratively, as shown in figure 3, not only including road in more new images, also
Including trees, building etc..In order to improve the accuracy for extracting traffic element, can be cut from the more new images in section to be updated
Then the road image in section to be updated out extracts traffic element from road image again.The embodiment of the present invention at least provide with
The embodiment of the road image in section to be updated is cut into lower two kinds of more new images from section to be updated:
In a kind of possible embodiment, in order to filter out the interference of other objects of road both sides, while camera change is adapted to
Change biggish pitch angle problem, the height for the road image being cut into can be greater than width.Specifically, for resolution ratio 1080 × 720
More new images, from this more new images cut 160 × 240 region be used as road image, road image lower edge be update
The lower edge of image, the central point of road image are the central point of more new images.It, can be with for the more new images of other resolution ratio
Determined by reference data of the more new images of resolution ratio 1080 × 720, set the resolution ratio of any other more new images as
Mage_width × image_height, the width ratio A for calculating more new images and reference first and height are specific full than B
Foot states formula (1) and formula (2):
A=(mage_width)/1080 ... ... ... ... ... ... (1)
Wherein, A is the width ratio of more new images and reference.
B=(image_height)/720 ... ... ... ... ... ... (2)
Wherein, B is the height ratio of more new images and reference.
When A is greater than B, A is determined as to the cutting ratio C of more new images, otherwise B is determined as to the cutting ratio of more new images
Example C.
Then road image, specifically, mileage chart are cut into from more new images according to cutting ratio and reference data
The width of picture meets following formula (3):
Mage_width_roi=C*160 ... ... ... ... ... ... (3)
Wherein, mage_width_roi is the width of road image, and C is the cutting ratio of more new images.
The height of road image meets following formula (4):
Image_height_roi=C*240 ... ... ... ... ... ... (4)
Wherein, image_height_roi is the height of road image, and C is the cutting ratio of more new images.
The distance between lower edge of road image lower edge and more new images is 5*C, and the central point of road image is more
The central point of new images.
Illustratively, the resolution ratio of more new images as shown in Figure 2 is set as 1080 × 900, according to formula (1) and formula
(2) it can obtain, the width ratio A=1 of more new images and reference, the height ratio B=1.25 of more new images and reference.Due to
A is less than B, then the cutting ratio C=B=1.25 of more new images.Further, it can be obtained according to formula (3) and be cut from more new images
The width mage_width_roi=200 of the road image cut out can obtain the road being cut into from more new images according to formula (4)
The height image_height_roi=300 of road image.The distance between the lower edge of road image lower edge and more new images
It is 6.25, the central point of road image is that the central point of more new images is cut, and obtains the road image of Fig. 4 center choosing.
In a kind of possible embodiment, since in more new images, sometimes sky occupies very big in more new images
A part can first determine the vanishing point of the road in more new images to more accurately be cut into the image of road sections,
In, the vanishing point of road forms crosspoint by the extended line of road.It is then based on road vanishing point and is cut into road image.It is exemplary
Ground, for more new images shown in Fig. 2, it is first determined the vanishing point M of road in Fig. 2, then with flat with the lower edge of more new images
Top edge of capable and across vanishing point M straight line as road image, is made with the lower edge, left edge, right hand edge of more new images
It is cut for the lower edge, left edge, right hand edge of road image, obtains road image shown in fig. 5.
Due to being cut into the image of road sections from more new images after the more new images for acquiring section to be updated,
To reduce the range for extracting traffic element, the precision of the current state of subsequent identification traffic element is improved.
Optionally, in above-mentioned steps S 202, the embodiment of the present invention at least provides following two and determines section to be identified
The embodiment of the current state of traffic element:
In a kind of possible embodiment, for every road image in section to be updated, using neural network model
The current state for identifying the traffic element in road image, is then wanted according to the traffic in every road image in section to be updated
The current state of element determines the current state of the traffic element in section to be updated.
Specifically, section to be updated may include multiple road images, may include multiple traffic in every road image
Element.Neural network model includes but is not limited to model (MobileNetv1), the convolutional neural networks that depth separates convolution
(Convolutional neural networks, abbreviation CNN), depth convolutional neural networks (deep convolutional
Neural networks, abbreviation DCNN).Preparatory off-line training neural network model inputs road image after training
Trained neural network model obtains the classification results of road image and the confidence level of each classification.
Illustratively, traffic element is set as road pavement state, and road pavement state includes " 1- has been laid with ", " 2- is not
Laying " and " 3- is uncertain " three classes, the confidence threshold value of classification are 0.7.In advance acquisition road pavement state be " laying ",
The road image of " not being laid with " and " uncertain " is trained neural network model as training sample.After training,
Road image shown in fig. 6 is inputted into neural network model, the confidence level of output classification " 1- has been laid with " is 0.999988, classification
The confidence level of " 2- is not laid with " is 0.000006, and the confidence level of classification " 3- is uncertain " is 0.000006.Since " 1- has been spread classification
If " confidence level be greater than 0.7, then the classification of road image shown in fig. 6 be " 1- has been laid with ".By road image shown in Fig. 7
Neural network model is inputted, the confidence level of output classification " 1- has been laid with " is 0.116188, the confidence level of classification " 2- is not laid with "
It is 0.883812, the confidence level of classification " 3- is uncertain " is 0.000000.Since the confidence level of classification " 2- is not laid with " is greater than
0.7, then the classification of road image shown in Fig. 7 is " 2- is not laid with ".Road image shown in Fig. 8 is inputted into neural network mould
Type, the confidence level of output classification " 1- has been laid with " are 0.000016, and the confidence level of classification " 2- is not laid with " is 0.000001, classification
The confidence level of " 3- is uncertain " is 0.999983.Since the confidence level of classification " 3- uncertain " is greater than 0.7, then road shown in Fig. 8
The classification of road image is " 3- is uncertain ".
For speed limitation board, other traffic elements such as limit board, traffic lights, number of track-lines are handed over, it can also be using above method training
Then corresponding neural network model determines classification results in road image and each classification using neural network model
Confidence level.Wherein, for the traffic elements with word content such as speed limitation board, friendship limit board, neural network mould can be used
Whether type first identifies in road image speed limitation board, hands over limit board, then further identifies speed limitation board and hands over the text in limit board.
Illustratively, traffic element is set as speed limitation board, and speed limitation board state includes " 1- has been set ", " 2- is not set " and " 3-
It is uncertain " three classes.Acquisition speed limitation board state is the road image of " having set ", " not setting " and " uncertain " as training sample in advance
This, is trained neural network model.After training, using neural network model to the road image in section to be updated into
Row classification is further known using trained text in advance when the classification of the road image in section to be updated is " 1- has been set "
Specific file in speed limitation board in other model identification road image.When section to be updated road image classification be " 2- is not set " or
When " 3- is uncertain ", directly export.
In order to improve the traffic element for identifying section to be identified current state accuracy, section to be updated can be combined
Every road image in traffic element current state determine section to be updated traffic element current state.
Illustratively, traffic element is set as road pavement state.The road pavement state that section to be updated is arranged is " 1-
Be laid with " condition are as follows: the corresponding classification of road image be " 1- has been laid with " amount of images and road image total quantity ratio
Value is greater than first threshold, and the corresponding classification of road image is the amount of images of " 2- is not laid with " and the ratio of road image total quantity
Less than second threshold.The road pavement state that section to be updated is arranged is the condition of " 2- is not laid with " are as follows: road image is corresponding
Classification is that the amount of images of " 2- is not laid with " and the ratio of road image total quantity are greater than third threshold value, the corresponding class of road image
Not Wei " 1- has been laid with " amount of images and road image total quantity ratio less than the 4th threshold value.Specifically include following steps,
It is as shown in Figure 9:
Step S901 determines the corresponding classification of multiple road images in section to be updated using neural network model.
Step S902, judges whether the corresponding classification of multiple road images meets the road pavement state in section to be updated and be
The condition of " 1- has been laid with ", if so, S903 is thened follow the steps, it is no to then follow the steps S904.
The road pavement state in section to be updated is determined as " 1- has been laid with " by step S903, while determining road to be updated
The road pavement state of section is the confidence level of " 1- has been laid with ".
Step S904, judges whether the corresponding classification of multiple road images meets the road pavement state in section to be updated and be
The condition of " 2- is not laid with ", if so, S905 is thened follow the steps, it is no to then follow the steps S906.
The road pavement state in section to be updated is determined as " 2- is not laid with " by step S905, while determining road to be updated
The road pavement state of section is the confidence level of " 2- is not laid with ".
The road pavement state in section to be updated is determined as " 3- is uncertain " by step S906.
For speed limitation board, other traffic elements such as limit board, traffic lights, number of track-lines are handed over, can also be determined using the above method
The current state of the traffic element in section to be updated.Wherein, for traffic elements with word content such as speed limitation board, friendship limit boards
For, whether can there will be speed limitation board in road image and hand over limit board and speed limitation board and hand over the text in limit board as to be updated
The current state of the traffic element in section.
Illustratively, traffic element is set as speed limitation board, and the speed limitation board state that section to be updated is arranged is " 1- has been set "
Condition, the condition that the speed limitation board state in section to be updated is " 2- is not set ".Section to be updated is determined using neural network model
The corresponding classification of multiple road images.Judge whether the corresponding classification of multiple road images meets the speed limitation board state for updating section
For the condition of " 1- has been set ", if so, the speed limitation board state in section to be updated is determined as " 1- has been set ", while determining to be updated
The speed limitation board state in section is the confidence level of " 1- has been set ", then further integrates the speed limitation board identified in multiple road images
Text determines the text in the speed limitation board in section to be updated.Otherwise, judge the corresponding classification of multiple road images whether meet to
The speed limitation board state for updating section is the condition of " 2- is not set ", if so, the speed limitation board state in section to be updated is determined as " 2-
Do not set ", while determining that the speed limitation board state in section to be updated is the confidence level of " 2- is not set ".Otherwise by the speed limit in section to be updated
Board state is determined as " 3- is uncertain ".
The state that the traffic element in the road image in section to be updated is identified by neural network model, then in conjunction with more
The state of traffic element determines the state of the traffic element in section to be updated in road image, to improve identification road to be updated
The precision of the traffic element state of section.
It, may identical feelings on adjacent segments for the state of traffic element in alternatively possible embodiment
Condition, for example, the traffic element such as road pavement state, number of track-lines, the state in two neighboring section to be updated may be it is identical, because
This, can judge the traffic in section to be updated in combination with the current state of the traffic element in the section adjacent with section to be updated
The current state of element.Specifically: for every road image in section to be updated, mileage chart is identified using neural network model
The current state of traffic element as in.According to the current state of the traffic element in every road image in section to be updated,
And the current state of the traffic element in every road image in the section adjacent with section to be updated, determine section to be updated
Traffic element current state.
Specifically, it can be determined according to the current state of the traffic element in every road image in section to be updated to more
The first state of the traffic element in new section, the current state according to the traffic element in every of adjacent segments road image are true
The second state for determining adjacent segments judges whether first state and the second state identical, if so, by first state be determined as to
Update the current state of the traffic element in section.
Illustratively, traffic element is set as road pavement state, and road pavement state includes " 1- has been laid with ", " 2- is not
It is laid with " and " 3- is uncertain " three classes, acquiring road pavement state in advance is " laying ", " not being laid with " and " uncertain "
Road image is trained neural network model as training sample.After training, treated more using neural network model
Multiple road images in new section are classified, and determine the corresponding classification of every road image.When multiple road images are corresponding
It is when classification meets condition of the road pavement state in section to be updated for " 1- has been laid with ", the first state in section to be updated is true
It is set to " 1- has been laid with ", while obtains the second state of the adjacent segments in section to be updated.If the second state of adjacent segments
For " 1- has been laid with ", then the road pavement state in section to be updated is determined as " 1- has been laid with ", while determining section to be updated
Road pavement state be " 1- has been laid with " confidence level, otherwise the road pavement state in section to be updated is determined as to " 3- is not
It determines ".
When the road pavement state that the corresponding classification of multiple road images is unsatisfactory for section to be updated is " 1- has been laid with "
When condition, judge whether the corresponding classification of multiple road images meets the road pavement state in section to be updated for " 2- is not laid with "
Condition, if so, the first state in section to be updated is determined as " 2- is not laid with ", while obtaining the adjacent of section to be updated
Second state in section, if the second state of adjacent segments is " 2- is not laid with ", by the road pavement shape in section to be updated
State is determined as " 2- is not laid with ", while determining that the road pavement state in section to be updated is the confidence level of " 2- is not laid with ", otherwise
The road pavement state in section to be updated is determined as " 3- is uncertain ".
When the road pavement state that the corresponding classification of multiple road images is unsatisfactory for section to be updated is " 1- has been laid with "
Condition, and be unsatisfactory for section to be updated road pavement state be " 2- is not laid with " condition when, by the road in section to be updated
Laying state is determined as " 3- is uncertain ".
Due to when detecting the state of traffic element in section to be updated, in combination with traffic element in multiple road images
State and section to be updated adjacent segments traffic element state, effectively increase the state of identification traffic element
Accuracy.
Optionally, in above-mentioned steps S203 and step S204, for speed limitation board, the friendships with word content such as limit board are handed over
For logical element, by the traffic element in section to be updated in the current state of the traffic element in section to be updated and map data base
Storage state when being compared, while comparing speed limitation board state and corresponding text.For road pavement state, number of track-lines
For the traffic element without word content, directly by the current state and map datum of the traffic element in section to be updated
The storage state of the traffic element in section to be updated is compared in library.
In a kind of possible embodiment, when current state and the storage state are inconsistent, using current state
Update storage state.
Illustratively, traffic element is set as speed limitation board, and the speed limitation board state in section to be updated is " 1- has been set ", speed limitation board
In text be " speed limit 60km/h ".By the speed limit in section to be updated in the speed limitation board state in section to be updated and map data base
Board state is compared.
When the speed limitation board state in section to be updated in map data base is " 1- has been set ", then by the speed limitation board in section to be updated
Text " speed limit 60km/h " is compared with the speed limitation board text in section to be updated in map data base, if in map data base to
The speed limitation board text for updating section is " speed limit 80km/h ", then updates the speed limitation board text in section to be updated in map data base
For " speed limit 60km/h ".When the speed limitation board state in section to be updated in map data base is " 2- is not set ", then in map data base
The speed limitation board in middle addition section to be updated and the speed limitation board text " speed limit 60km/h " in section to be updated.
It is inconsistent with storage state in current state in a kind of possible embodiment, and the traffic in section to be updated
When the confidence level of the current state of element is greater than preset threshold, state is updated storage using current state.
Illustratively, traffic element is set as road pavement state, and the road pavement state in section to be updated is that " 1- has been spread
If ", the road pavement state in section to be updated is compared with the road pavement state in section to be updated in map data base.
When the road pavement state in section to be updated in map data base is " 2- is not laid with ", further judge to be updated
The road pavement state in section is whether the confidence level of " 1- has been laid with " is greater than preset threshold, if so, by map data base
The road pavement state in section to be updated is updated to " 1- has been laid with ".
Since the traffic in section to be updated in the current state and map data base of the traffic element in section to be updated is wanted
After the storage state of element is compared, when determining that current state and storage state are inconsistent, working as traffic element is further judged
Whether the confidence level of preceding state is greater than preset threshold, if so, map data base is just updated, to ensure that in map data base
The accuracy of data.
Optionally, when current state is consistent with storage state, map data base is not updated.
Illustratively, traffic element is set as speed limitation board, and the speed limitation board state in section to be updated is " 1- has been set ", speed limitation board
In text be " speed limit 60km/h ".By the speed limit in section to be updated in the speed limitation board state in section to be updated and map data base
Board state is compared.When the speed limitation board state in section to be updated in map data base is " 1- has been set ", and the text in speed limitation board
When word is " speed limit 60km/h ", map data base is not updated.
Illustratively, traffic element is set as road pavement state, and the road pavement state in section to be updated is that " 1- has been spread
If ", the road pavement state in section to be updated is compared with the road pavement state in section to be updated in map data base.
When the road pavement state in section to be updated in map data base is " 1- has been laid with ", map data base is not updated.
Due to being that small part traffic element changes on road, most traffic element still can keep script attribute,
Therefore by manually extracting traffic element, when being then compared with map data base, there are a large amount of unnecessary stressed operations,
Therefore by section to be updated in the current state of the traffic element in section to be updated and map data base in the embodiment of the present invention
The storage state of traffic element is compared, and when comparing consistent, does not update map data base, for manual work,
Workload is greatly reduced, operating efficiency is improved.
Optionally, inconsistent with storage state in current state, and the current state of the traffic element in section to be updated
When confidence level is not more than preset threshold, map data base is updated by the way of manually comparing.In addition working as traffic element
The case where preceding state recognition is " uncertain ", can also update map data base by the way of manually comparing.
Embodiment in order to preferably explain the present invention describes the embodiment of the present invention below with reference to specific implement scene and provides
A kind of update map data base method, set traffic element as road pavement state, road pavement state includes that " 1- has been spread
If ", " 2- is not laid with " and " 3- uncertain " three classes.In advance acquisition road pavement state be " laying ", " not being laid with " and
The road image of " uncertain " is trained neural network model as training sample.
The location information of multiple more new images and multiple more new images that crowdsourcing personnel upload is obtained, it is to be updated for one
Section determines multiple of section to be updated according to the location information in section to be updated and the location information of multiple more new images
More new images.Then it is cut into the image of road sections from every more new images, determines multiple mileage charts in section to be updated
Picture.Determine the road pavement state in section to be updated using multiclass classification process as shown in Figure 10 again later.
First classified based on individual road image, specifically: it is determined using trained neural network model to be updated
The classification results of every road image in section and the confidence level of each classification, then by the confidence level of classification and confidence level threshold
Value is compared, and determines the corresponding classification of road image.
Multiple road images are then based on to classify, specifically: the road pavement state that section to be updated is arranged is " 1-
Be laid with " condition are as follows: the corresponding classification of road image be " 1- has been laid with " amount of images and road image total quantity ratio
Value is greater than first threshold, and the corresponding classification of road image is the amount of images of " 2- is not laid with " and the ratio of road image total quantity
Less than second threshold.The road pavement state that section to be updated is arranged is the condition of " 2- is not laid with " are as follows: road image is corresponding
Classification is that the amount of images of " 2- is not laid with " and the ratio of road image total quantity are greater than third threshold value, the corresponding class of road image
Not Wei " 1- has been laid with " amount of images and road image total quantity ratio less than the 4th threshold value.Judge multiple road images pair
The road pavement the state whether classification answered meets section to be updated is the condition of " 1- has been laid with ", if so, by road to be updated
The road pavement state of section is determined as " 1- has been laid with ".Otherwise, judge whether the corresponding classification of multiple road images meets to more
The road pavement state in new section is the condition of " 2- is not laid with ", if so, the road pavement state in section to be updated is determined
For " 2- is not laid with ", the road pavement state in section to be updated is otherwise determined as " 3- is uncertain ".
Finally classified based on multiple sections to be updated, specifically: when the road pavement state in section to be updated is " 1-
It has been laid with " when, judge whether the road pavement state of the adjacent segments in section to be updated is " 1- has been laid with ", if so, will be to
The road pavement state for updating section is determined as " 1- has been laid with ", while determining that the road pavement state in section to be updated is " 1-
Be laid with " confidence level, otherwise the road pavement state in section to be updated is determined as to " 3- is uncertain ".When section to be updated
When road pavement state is " 2- is not laid with ", judge whether the road pavement state of the adjacent segments in section to be updated is that " 2- is not
It is laid with ", if so, the road pavement state in section to be updated is determined as " 2- is not laid with ", while determining section to be updated
Road pavement state is the confidence level of " 2- is not laid with ", otherwise the road pavement state in section to be updated is determined as to " 3- is not true
It is fixed ".
Further, by the road pavement in section to be updated in the road pavement state in section to be updated and map data base
State is compared, compare it is inconsistent, and the confidence level of the road pavement state in section to be updated be greater than preset threshold when, adopt
State is updated storage with current state, does not otherwise update map data base.
Due to automatically extracting the current state of traffic element in road image when updating map data base, then with ground
The storage state of the traffic element in section to be updated is compared in chart database, updates map data base according to comparison result,
Traffic element without extracting road image by way of manual work, and by the current state and map of traffic element
The storage state of traffic element in database is compared, and then updates map data base, on the one hand improve map
The update efficiency of database, has on the other hand saved human cost.
Based on the same technical idea, the embodiment of the invention provides a kind of device for updating map data base, such as Figure 11
Shown, which includes:
Module 1101 is obtained, for obtaining the road image in section to be updated；
Identification module 1102, for determining the traffic in the section to be updated according to the road image in the section to be updated
The current state of element；
Comparison module 1103, for by the current state of the traffic element in the section to be updated and the map data base
Described in the storage state of traffic element in section to be updated be compared；
Update module 1104 is used for when the current state and the storage state are inconsistent, using the current shape
State updates the storage state.
Optionally, module 1101 is obtained to be specifically used for:
Acquire the location information of multiple more new images and multiple more new images；
The position of the location information in the section to be updated and multiple more new images is matched, from it is described multiple
The more new images in the section to be updated are determined in more new images；
The road image in the section to be updated is cut into from the more new images in the section to be updated.
Optionally, identification module 1102 is specifically used for:
For every road image in the section to be updated, identified in the road image using neural network model
The current state of traffic element；
It is determined according to the current state of the traffic element in every road image in the section to be updated described to be updated
The current state of the traffic element in section.
Optionally, identification module 1102 is specifically used for:
For every road image in the section to be updated, identified in the road image using neural network model
The current state of traffic element；
According to the current state of the traffic element in every road image in the section to be updated, and with described to more
The current state of traffic element in every road image in the new adjacent section in section, determines the traffic in the section to be updated
The current state of element.
Optionally, comparison module 1103 is specifically used for:
It is inconsistent in the current state and the storage state, and the current shape of the traffic element in the section to be updated
When the confidence level of state is greater than preset threshold, the storage state is updated using the current state.
Optionally, update module 1104 is also used to:
When the current state is consistent with the storage state, the map data base is not updated.
Based on the same technical idea, the embodiment of the invention provides a kind of terminal devices, as shown in figure 12, including at least
One processor 1201, and the memory 1202 connecting at least one processor do not limit processing in the embodiment of the present invention
Specific connection medium between device 1201 and memory 1202 passes through bus between processor 1201 and memory 1202 in Figure 12
For connection.Bus can be divided into address bus, data/address bus, control bus etc..
In embodiments of the present invention, memory 1202 is stored with the instruction that can be executed by least one processor 1201, until
The instruction that a few processor 1201 is stored by executing memory 1202 can execute the side above-mentioned for updating map data base
Included step in method.
Wherein, processor 1201 is the control centre of terminal device, can use various interfaces and connection terminal is set
Standby various pieces are stored in memory 1202 by running or executing the instruction being stored in memory 1202 and calling
Data, to update map data base.Optionally, processor 1201 may include one or more processing units, processor
1201 can integrate application processor and modem processor, wherein the main processing operation system of application processor, user interface
With application program etc., modem processor mainly handles wireless communication.It is understood that above-mentioned modem processor
It can not be integrated into processor 1201.In some embodiments, processor 1201 and memory 1202 can be in same chips
Upper realization, in some embodiments, they can also be realized respectively on independent chip.
Processor 1201 can be general processor, such as central processing unit (CPU), digital signal processor, dedicated collection
At circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array or other
Perhaps transistor logic, discrete hardware components may be implemented or execute the present invention in fact for programmable logic device, discrete gate
Apply each method, step disclosed in example and logic diagram.General processor can be microprocessor or any conventional processing
Device etc..The step of method in conjunction with disclosed in the embodiment of the present invention, can be embodied directly in hardware processor and execute completion, or
With in processor hardware and software module combination execute completion.
Memory 1202 is used as a kind of non-volatile computer readable storage medium storing program for executing, can be used for storing non-volatile software journey
Sequence, non-volatile computer executable program and module.Memory 1202 may include the storage medium of at least one type,
It such as may include flash memory, hard disk, multimedia card, card-type memory, random access storage device (Random Access
Memory, RAM), static random-access memory (Static Random Access Memory, SRAM), may be programmed read-only deposit
Reservoir (Programmable Read Only Memory, PROM), read-only memory (Read Only Memory, ROM), band
Electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory,
EEPROM), magnetic storage, disk, CD etc..Memory 1202 can be used for carrying or storing have instruction or data
The desired program code of structure type and can by any other medium of computer access, but not limited to this.The present invention is real
Applying the memory 1202 in example can also be circuit or other devices that arbitrarily can be realized store function, for storing program
Instruction and/or data.
Based on the same inventive concept, the embodiment of the present invention also provides a kind of computer readable storage medium, the readable storage
Media storage has computer instruction, when the computer instruction is run on the terminal device, so that terminal device is executed as aforementioned
Update map data base method the step of.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the present invention
Form.It is deposited moreover, the present invention can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (10)
1. a kind of method for updating map data base characterized by comprising
Obtain the road image in section to be updated；
The current state of the traffic element in the section to be updated is determined according to the road image in the section to be updated；
By the friendship in section to be updated described in the current state of the traffic element in the section to be updated and the map data base
The storage state of logical element is compared；
When the current state and the storage state are inconsistent, the storage state is updated using the current state.
2. the method as described in claim 1, which is characterized in that the road image for obtaining section to be updated, comprising:
Acquire the location information of multiple more new images and multiple more new images；
The position of the location information in the section to be updated and multiple more new images is matched, from multiple described updates
The more new images in the section to be updated are determined in image；
The road image in the section to be updated is cut into from the more new images in the section to be updated.
3. the method as described in claim 1, which is characterized in that the road image according to the section to be updated determines institute
State the current state of the traffic element in section to be updated, comprising:
For every road image in the section to be updated, the traffic in the road image is identified using neural network model
The current state of element；
The section to be updated is determined according to the current state of the traffic element in every road image in the section to be updated
Traffic element current state.
4. the method as described in claim 1, which is characterized in that the road image according to the section to be updated determines institute
State the current state of the traffic element in section to be updated, comprising:
For every road image in the section to be updated, the traffic in the road image is identified using neural network model
The current state of element；
According to the current state of the traffic element in every road image in the section to be updated, and with the road to be updated
The current state of traffic element in every road image in the section of Duan Xianglin determines the traffic element in the section to be updated
Current state.
5. the method as described in claim 1, which is characterized in that described inconsistent in the current state and the storage state
When, the storage state is updated using the current state, comprising:
It is inconsistent in the current state and the storage state, and the current state of the traffic element in the section to be updated
When confidence level is greater than preset threshold, the storage state is updated using the current state.
6. method as claimed in claim 1 to 5, which is characterized in that further include:
When the current state is consistent with the storage state, the map data base is not updated.
7. a kind of device for updating map data base characterized by comprising
Module is obtained, for obtaining the road image in section to be updated；
Identification module, for determining that according to the road image in the section to be updated, the traffic element in the section to be updated is worked as
Preceding state；
Comparison module, for by described in the current state of the traffic element in the section to be updated and the map data base to
The storage state for updating the traffic element in section is compared；
Update module, for updating institute using the current state when the current state and the storage state are inconsistent
State storage state.
8. device as claimed in claim 7, which is characterized in that the update module is specifically used for: the current state with
The storage state is inconsistent, and the confidence level of the current state of the traffic element in the section to be updated is greater than preset threshold
When, the storage state is updated using the current state.
9. a kind of terminal device, which is characterized in that including at least one processing unit and at least one storage unit, wherein
The storage unit is stored with computer program, when described program is executed by the processing unit, so that the processing unit
Perform claim requires the step of 1~6 any claim the method.
10. a kind of computer-readable medium, which is characterized in that it is stored with the computer program that can be executed by terminal device, when
When described program is run on the terminal device, so that the terminal device perform claim requires the step of 1~6 any the method
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910112872.XA CN109933635A (en) | 2019-02-13 | 2019-02-13 | A kind of method and device updating map data base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910112872.XA CN109933635A (en) | 2019-02-13 | 2019-02-13 | A kind of method and device updating map data base |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109933635A true CN109933635A (en) | 2019-06-25 |
Family
ID=66985547
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910112872.XA Pending CN109933635A (en) | 2019-02-13 | 2019-02-13 | A kind of method and device updating map data base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109933635A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110334228A (en) * | 2019-07-09 | 2019-10-15 | 广西壮族自治区基础地理信息中心 | A kind of Internet Problems map screening method based on deep learning |
| CN111102988A (en) * | 2020-01-03 | 2020-05-05 | 北京汽车集团有限公司 | Map-based path planning method, server, vehicle-mounted terminal, and storage medium |
| CN111427904A (en) * | 2020-03-30 | 2020-07-17 | 北京四维图新科技股份有限公司 | High-precision map data updating method and device and electronic equipment |
| CN112380317A (en) * | 2021-01-18 | 2021-02-19 | 腾讯科技（深圳）有限公司 | High-precision map updating method and device, electronic equipment and storage medium |
| CN112419542A (en) * | 2020-12-07 | 2021-02-26 | 安徽江淮汽车集团股份有限公司 | Road error correction reporting method, device, equipment and storage medium |
| CN112883236A (en) * | 2021-02-26 | 2021-06-01 | 北京百度网讯科技有限公司 | Map updating method, map updating device, electronic equipment and storage medium |
| CN113434526A (en) * | 2021-06-25 | 2021-09-24 | 重庆紫光华山智安科技有限公司 | Road network data updating method and device, electronic equipment and storage medium |
| WO2022110126A1 (en) * | 2020-11-30 | 2022-06-02 | 华为技术有限公司 | Map verification method and related apparatus |
| WO2022116694A1 (en) * | 2020-12-01 | 2022-06-09 | 北京罗克维尔斯科技有限公司 | Method and apparatus for updating confidence of high-definition map |
| CN114993329A (en) * | 2022-06-23 | 2022-09-02 | 腾讯科技（深圳）有限公司 | Road data updating method and device |
| CN117270913A (en) * | 2023-11-08 | 2023-12-22 | 腾讯科技（深圳）有限公司 | Map updating method, device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106294383A (en) * | 2015-05-19 | 2017-01-04 | 北京四维图新科技股份有限公司 | A kind of map online updating method and device |
| CN107339996A (en) * | 2017-06-30 | 2017-11-10 | 百度在线网络技术（北京）有限公司 | Vehicle method for self-locating, device, equipment and storage medium |
| US20180144190A1 (en) * | 2015-12-22 | 2018-05-24 | Here Global B.V. | Method and apparatus for updating road map geometry based on received probe data |
| CN108121764A (en) * | 2016-11-26 | 2018-06-05 | 星克跃尔株式会社 | Image processing apparatus, image processing method, computer program and readable in computer recording medium |
-
2019
- 2019-02-13 CN CN201910112872.XA patent/CN109933635A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106294383A (en) * | 2015-05-19 | 2017-01-04 | 北京四维图新科技股份有限公司 | A kind of map online updating method and device |
| US20180144190A1 (en) * | 2015-12-22 | 2018-05-24 | Here Global B.V. | Method and apparatus for updating road map geometry based on received probe data |
| CN108121764A (en) * | 2016-11-26 | 2018-06-05 | 星克跃尔株式会社 | Image processing apparatus, image processing method, computer program and readable in computer recording medium |
| CN107339996A (en) * | 2017-06-30 | 2017-11-10 | 百度在线网络技术（北京）有限公司 | Vehicle method for self-locating, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 陆玲: "《图像目标分割方法》", 30 November 2016 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110334228A (en) * | 2019-07-09 | 2019-10-15 | 广西壮族自治区基础地理信息中心 | A kind of Internet Problems map screening method based on deep learning |
| CN111102988A (en) * | 2020-01-03 | 2020-05-05 | 北京汽车集团有限公司 | Map-based path planning method, server, vehicle-mounted terminal, and storage medium |
| CN111427904A (en) * | 2020-03-30 | 2020-07-17 | 北京四维图新科技股份有限公司 | High-precision map data updating method and device and electronic equipment |
| WO2022110126A1 (en) * | 2020-11-30 | 2022-06-02 | 华为技术有限公司 | Map verification method and related apparatus |
| WO2022116694A1 (en) * | 2020-12-01 | 2022-06-09 | 北京罗克维尔斯科技有限公司 | Method and apparatus for updating confidence of high-definition map |
| CN112419542B (en) * | 2020-12-07 | 2022-01-14 | 安徽江淮汽车集团股份有限公司 | Road error correction reporting method, device, equipment and storage medium |
| CN112419542A (en) * | 2020-12-07 | 2021-02-26 | 安徽江淮汽车集团股份有限公司 | Road error correction reporting method, device, equipment and storage medium |
| CN112380317A (en) * | 2021-01-18 | 2021-02-19 | 腾讯科技（深圳）有限公司 | High-precision map updating method and device, electronic equipment and storage medium |
| CN112380317B (en) * | 2021-01-18 | 2021-04-09 | 腾讯科技（深圳）有限公司 | High-precision map updating method and device, electronic equipment and storage medium |
| CN112883236A (en) * | 2021-02-26 | 2021-06-01 | 北京百度网讯科技有限公司 | Map updating method, map updating device, electronic equipment and storage medium |
| CN112883236B (en) * | 2021-02-26 | 2024-01-16 | 北京百度网讯科技有限公司 | Map updating method and device, electronic equipment and storage medium |
| CN113434526A (en) * | 2021-06-25 | 2021-09-24 | 重庆紫光华山智安科技有限公司 | Road network data updating method and device, electronic equipment and storage medium |
| CN114993329A (en) * | 2022-06-23 | 2022-09-02 | 腾讯科技（深圳）有限公司 | Road data updating method and device |
| CN117270913A (en) * | 2023-11-08 | 2023-12-22 | 腾讯科技（深圳）有限公司 | Map updating method, device, electronic equipment and storage medium |
| CN117270913B (en) * | 2023-11-08 | 2024-02-27 | 腾讯科技（深圳）有限公司 | Map updating method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109933635A (en) | A kind of method and device updating map data base | |
| CN109241846B (en) | Method and device for estimating space-time change of remote sensing image and storage medium | |
| CN106323301B (en) | Method and device for acquiring road information | |
| CN111553963B (en) | Meta-grid generation method and device based on geographic information | |
| DE102007045082A1 (en) | Apparatus and method for updating map data | |
| CN110796714A (en) | Map construction method, device, terminal and computer readable storage medium | |
| CN109815419B (en) | Interest point indexing method, device, medium and electronic equipment based on geographic position | |
| CN109688532A (en) | A kind of method and device dividing city function region | |
| CN104422451A (en) | Road recognition method and road recognition apparatus | |
| CN108225334A (en) | A kind of localization method and device based on three-dimensional live-action data | |
| CN112215205B (en) | Target identification method and device, computer equipment and storage medium | |
| CN110399445A (en) | A kind of processing method of point of interest, device and equipment | |
| CN110796135A (en) | Target positioning method and device, computer equipment and computer storage medium | |
| CN107861992A (en) | A kind of running route processing method and apparatus | |
| CN109840559A (en) | Method for screening images, device and electronic equipment | |
| CN108876440B (en) | Region dividing method and server | |
| CN110033012A (en) | A kind of production method for tracking target based on channel characteristics weighted convolution neural network | |
| CN109187548A (en) | A kind of rock cranny recognition methods | |
| CN114998744A (en) | Agricultural machinery track field segmentation method based on motion and vision dual-feature fusion | |
| CN117194600B (en) | Service-oriented geographic entity assembling method and system | |
| CN112581495A (en) | Image processing method, device, equipment and storage medium | |
| CN110472092A (en) | A kind of geographic positioning and system of Streetscape picture | |
| CN112738725B (en) | Real-time identification method, device, equipment and medium for target crowd in semi-closed area | |
| CN116972811A (en) | Unmanned aerial vehicle-based investigation method for small-scale vegetation biodiversity | |
| CN111476308A (en) | Remote sensing image classification method and device based on prior geometric constraint and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190625 |
|
| RJ01 | Rejection of invention patent application after publication |