Summary of the invention
The application provides a kind of high-precision map updating method, device and storage medium, to overcome existing map updating methodPresent in update timeliness not can guarantee, in fact it could happen that driving safety problem.
A kind of high-precision map updating method that the application first aspect provides, comprising:
The crowdsourcing image that crowdsourcing vehicle termination uploads is obtained, when each image carries corresponding vehicle termination acquisition described imageLocation information；
Based on the crowdsourcing image and high-precision map data base, Significant Change element and the institute of current high-precision map are determinedState the location information of Significant Change element；
It is whole to obtain the first vehicle for the location information of the location information and the Significant Change element that are carried according to each imageThe video data uploaded is gathered at end, the location of each vehicle termination and effective change in the first vehicle termination setThe position for changing element meets preset distance constraints；
The high-precision map data base is updated according to the video data that the first vehicle termination set uploads.
In the present embodiment, image and video letter that the update of high-precision map data base is uploaded based on crowdsourcing public vehiclesBreath, acquires without using expensive collecting vehicle, and renewal speed is fast, it is ensured that the timeliness of map rejuvenation avoids certainlyThe dynamic driving safety problem for driving vehicle and occurring
It is described to be based on the crowdsourcing image and high-precision map data base in a kind of possible design of first aspect, it determinesThe current Significant Change element of high-precision map and the location information of the Significant Change element out, comprising:
Each image in the crowdsourcing image is analyzed, determine map marker element in each image andThe location information of each map marker element；
Location information and the high-precision map data base based on each map marker element, judge each map identification elementWhether element is map variation element；
If the image of preset quantity changes element in identical geographical location map having the same, it is determined that the mapVariation element is Significant Change element, and the identical geographical location is the location information of the Significant Change element.
In the present embodiment, element is changed in identical geographical location map having the same based on the image of preset quantityMode, can accurately determine the Significant Change element in current high-precision map, effectively prevent vehicle termination send it is pseudo-It makes picture or hacker invades fraud or vehicle termination acquires the problems such as information is inaccurate.
In the alternatively possible design of first aspect, it is described according to each image carry location information and it is described effectivelyChange the location information of element, obtain the video data that the first vehicle termination set uploads, comprising:
The location information of the location information and the Significant Change element that are carried according to each image, determines described firstVehicle termination set；
Each vehicle termination into the first vehicle termination set sends video acquisition task, and the video acquisition is appointedBusiness includes pickup area range, and the Significant Change element is located within the scope of the pickup area；
Receive the video that each vehicle termination acquires within the scope of the pickup area in the first vehicle setData.
In the present embodiment, cloud server determines effective first vehicle termination set, and gets for high-precisionThe video data of map reconstruction has established optimized integration for timely updating for high-precision map.
In the above-mentioned possible design of first aspect, the location information carried according to each image and effective changeThe location information for changing element, determines the first vehicle termination set, comprising:
According to the location information that each image carries, determine that each image corresponds to the terminal essential information of vehicle termination,The terminal essential information includes following at least one: current location information, history driving trace information, Present navigation route letterBreath；
The terminal essential information that vehicle termination is corresponded to according to each image determines the first vehicle termination set.
Another in first aspect may design, the video counts uploaded according to the first vehicle termination setIt is updated according to the high-precision map data base, comprising:
Picture point cloud is created according to the video data that the first vehicle termination set uploads；
Based on the laser point cloud in the picture point cloud and the high-precision map data base, the Significant Change element is determinedEssential information；
According to high-precision map data base described in the update of basic information of the Significant Change element.
In the present embodiment, cloud server can update the Significant Change element in high-precision map to high-precision map numberAccording in library, have the characteristics that update in time, be easily achieved, at low cost, accuracy is high.
Another in first aspect may design, and the Significant Change element includes at least one of following element:Lane line, guardrail, curb, label and land marking.
The application second aspect provides a kind of high-precision map rejuvenation device, comprising: obtains module, processing module and updates mouldBlock；
The acquisition module, for obtaining the crowdsourcing image of crowdsourcing vehicle termination upload, each image carries corresponding vehicleTerminal acquires location information when described image；
The processing module determines current high-precision map for being based on the crowdsourcing image and high-precision map data baseSignificant Change element and the Significant Change element location information；
The acquisition module, the position of the location information and the Significant Change element that are also used to be carried according to each imageInformation obtains the video data that the first vehicle termination set uploads, each vehicle termination institute in the first vehicle termination setThe position at place and the position of the Significant Change element meet preset distance constraints；
The update module, the video data for being uploaded according to the first vehicle termination set is to the high-precision mapDatabase is updated.
In a kind of possible design of second aspect, the processing module, specifically for every in the crowdsourcing imageA image is analyzed, and determines the location information of the map marker element and each map marker element in each image,Location information and the high-precision map data base based on each map marker element, judge each map marker element whether beMap changes element, and preset quantity image in identical geographical location map having the same variation element, reallyThe fixed map variation element is Significant Change element, and the identical geographical location is that the position of the Significant Change element is believedBreath.
In the alternatively possible design of second aspect, the acquisition module comprises determining that unit and Transmit-Receive Unit；
The determination unit, the position letter of location information and the Significant Change element for being carried according to each imageBreath, determines the first vehicle termination set；
The Transmit-Receive Unit sends video acquisition for each vehicle termination into the first vehicle termination set and appointsBusiness, the video acquisition task includes pickup area range, and the Significant Change element is located within the scope of the pickup area, withAnd receive the video data that each vehicle termination acquires within the scope of the pickup area in the first vehicle set.
In the above-mentioned possible design of second aspect, the determination unit, specifically for the position carried according to each imageConfidence breath determines that each image correspond to the terminal essential information of vehicle termination, and the terminal essential information includes as follows at leastIt is a kind of: current location information, history driving trace information, Present navigation line information, and vehicle is corresponded to according to each imageThe terminal essential information of terminal determines the first vehicle termination set.
Another in second aspect may design, the update module, be specifically used for whole according to first vehicleThe video data that end set uploads creates picture point cloud, based on the laser in the picture point cloud and the high-precision map data basePoint cloud, determines the essential information of the Significant Change element, and the update of basic information institute according to the Significant Change elementState high-precision map data base.
The application third aspect provides a kind of high-precision map rejuvenation device, including processor, memory and is stored in describedOn memory and the computer program that can run on a processor, the processor realize such as above-mentioned first when executing described programMethod described in aspect and each possible design of first aspect.
The application fourth aspect provides a kind of storage medium, and instruction is stored in the storage medium, when it is in computerWhen upper operation, so that computer executes the method as described in first aspect and each possible design of first aspect.
High-precision map updating method, device and storage medium provided by the embodiments of the present application, it is whole by obtaining crowdsourcing vehicleThe crowdsourcing image uploaded is held, each image carries location information when corresponding vehicle termination acquisition described image, is based on above-mentioned crowdPacket image and high-precision map data base determine the Significant Change element of current high-precision map and the position of the Significant Change elementInformation, the location information of the location information and Significant Change element that carry further according to each image obtain the first vehicle termination collectionThe video data for closing biography carries out more high-precision map data base according to the video data that the first vehicle termination set uploadsNewly.In the technical solution, the image and video information that the update of high-precision map data base is uploaded based on crowdsourcing vehicle termination are not necessarily toIt is acquired using expensive collecting vehicle, renewal speed is fast, it is ensured that the timeliness of map rejuvenation avoids automatic Pilot vehicleThe driving safety problem occurred.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present applicationIn attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment isSome embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the artEvery other embodiment obtained without creative efforts, shall fall in the protection scope of this application.
High-precision map updating method provided by the embodiments of the present application mainly realizes high-precision map rejuvenation, tool with crowdsourcing modelBody, refer to the identification that the track of the social common vehicle of cloud large scale collection low cost is acquired with picture or intelligent vehicle endResult data carries out map visual data processing beyond the clouds, then completes the update of high-precision map data base.More with crowdsourcing modelNew high-precision map be able to solve high-precision map quickly, the problem of timely updating, improve the safety of automatic driving vehicle, solveIn the prior art since the timeliness of high-precision map rejuvenation not can guarantee, it is understood that there may be driving safety problem.
A kind of application scenarios schematic diagram of the embodiment of the present application is introduced below with reference to Fig. 1.Fig. 1 provides for the embodiment of the present applicationHigh-precision map updating method application scenarios schematic diagram.As shown in Figure 1, the application scenarios can in embodiments hereinTo include: crowdsourcing vehicle termination 11, pipeline 12, cloud server 13 and storage equipment 14.
Wherein, crowdsourcing vehicle termination 11 can be is made of large-scale common public vehicles, can also be by with dataThe intelligent vehicle of processing capacity and recognition capability composition, can also forming by common public vehicles and intelligent vehicle.
In practical applications, which can be network, i.e. crowdsourcing vehicle termination 11 passes through network for collected figureAs being uploaded to cloud server 13, the identification and processing of map marker element are executed by cloud server 13.Optionally, beyond the cloudsIt can determine effective change of current high-precision map in server 13 based on the image that crowdsourcing vehicle termination reports by crowdsourcing platformChange element, and executes the update work of high-precision map data base.
Optionally, which can be used for storing the image or GPS track information of crowdsourcing vehicle termination upload, alsoIt can be used for storing the map element information and map feature information of high-precision map.
Illustratively, which may include: crowdsourcing database, high-precision map data base and high-precision map featureLibrary.Wherein, crowdsourcing database is used to store the information such as image or the GPS track information of the upload of crowdsourcing vehicle termination, high-precision mapDatabase is used to store the element information of high-precision map, which is used to store the characteristic information of high-precision mapDeng.It is worth noting that the embodiment of the present application does not limit the concrete composition of storage equipment, can carry out according to the actual situationIt determines.
It should be noted that attached drawing 1 is only a kind of schematic diagram of application scenarios provided by the embodiments of the present application, institute in Fig. 1Show that the positional relationship between equipment is not limited in any way, for example, in fig. 1, storage equipment can relative to cloud serverTo be external memory, in other cases, storage equipment can also be placed in cloud server.
In the following, being described in detail by technical solution of the specific embodiment to the application.It should be noted that below thisSeveral specific embodiments can be combined with each other, may in certain embodiments no longer for the same or similar concept or processIt repeats.
Fig. 2 is the flow diagram of high-precision map updating method embodiment one provided by the embodiments of the present application.This is high-precisionlyFigure update method can be executed by cloud server, can also be executed by the crowdsourcing platform on cloud server.In the present embodimentThis method is executed with cloud server to be illustrated.As shown in Fig. 2, the high-precision map updating method may include steps of:
Step 21: obtaining the crowdsourcing image that crowdsourcing vehicle termination uploads, each image carries corresponding vehicle termination and acquires instituteState location information when image.
Optionally, in the present embodiment, cloud server can execute the high-precision map more under the triggering of applicationsNew method.Specifically, cloud server obtains the crowdsourcing image of crowdsourcing vehicle termination upload first.Specifically, cloud serverThe crowdsourcing image that crowdsourcing vehicle termination uploads can be directly obtained from the crowdsourcing database of storage equipment, also can receive crowdsourcingThe crowdsourcing image that vehicle termination directly reports, the embodiment of the present application are not defined the acquisition modes of crowdsourcing image, canWith determines according to actual conditions.
Illustratively, in the present embodiment, common public vehicles namely crowdsourcing vehicle termination are every a distance (such as 20Rice) image can be acquired by the acquisition equipment installed on vehicle and record the GPS rail of vehicle termination this moment on the imageMark location information, and uploaded to cloud server.
That is, each vehicle termination in crowdsourcing vehicle termination can upload one acquisition with the preset distance of every travelingThe image arrived can not also report the mode of image to be defined vehicle termination with real-time report, the embodiment of the present application, canWith determines according to actual conditions.
It is worth noting that including at least one image that each vehicle termination reports in above-mentioned crowdsourcing image, about everyThe amount of images that a vehicle termination reports, the embodiment of the present application are simultaneously not limited thereof.
Step 22: being based on the crowdsourcing image and high-precision map data base, determine the Significant Change member of current high-precision mapThe location information of element and the Significant Change element.
Optionally, in embodiments herein, cloud server can first divide the crowdsourcing image receivedAnalysis, determines map marker element from every image in crowdsourcing image, in conjunction with the ground pel in high-precision map data baseElement judges whether the map marker element in every image is map variation element and determines that the map in every image becomesChange element, finally based on the classification of map variation element and position in every image, changes element from the map in all imagesIn determine the current Significant Change element of high-precision map and the location information of effective map element.
Illustratively, in embodiments herein, map marker element includes but is not limited to road, lane line, markBoard, land marking etc., wherein road may include guardrail, curb etc., and label includes: road sign, indicative board, limit for height board etc.Various types, land marking include: to shunt mark, entrance mark, speed limit mark, in limited time mark etc..
Correspondingly, including above-mentioned road (guardrail, curb), lane line, mark in map marker element in the present embodimentWhen the classifications such as board, land marking, which also may include at least one of following element: lane line, guardrail, roadEdge, label and land marking.
It is worth noting that map marker element, map do not change element and Significant Change to the embodiment of the present applicationThe specific category and the form of expression of element are defined, and can be determined according to the concrete condition of practical application.
Step 23: the location information of the location information and the Significant Change element that are carried according to each image obtains firstThe video data that vehicle termination set uploads.
Wherein, in the first vehicle termination set the location of each vehicle termination and the map variation element positionMeet preset distance constraints.
Illustratively, in the present embodiment, the location information that cloud server is carried according to each image can be determinedThe location of each vehicle termination for uploading image is comformed packet vehicle termination in conjunction with the location information of the Significant Change elementIn determine the first vehicle termination set for meeting preset distance constraints.That is, each in the first vehicle termination setThe position of the location of vehicle termination and the Significant Change element meets preset distance constraints.
Illustratively, preset distance constraints can refer between vehicle termination position and Significant Change elementDistance is less than preset threshold.For example, a distance range is (for example, 100~200 meters before and after the Significant Change element positionDeng) in all vehicle terminations be all satisfied above-mentioned preset distance constraints.
Step 24: high-precision map data base being updated according to the video data that the first vehicle termination set uploads.
In embodiments herein, cloud server gets each vehicle termination in the first vehicle termination set and uploadsVideo data after, the three-dimensional reconstruction of high-precision map can be executed based on preset algorithm for reconstructing and above-mentioned video data, is obtainedPicture point cloud determines the basic of Significant Change element in conjunction with laser point cloud of high-precision map data base during creationInformation is updated high-precision map data base to be conducive to the essential information.
High-precision map updating method provided by the embodiments of the present application, the crowdsourcing figure uploaded by obtaining crowdsourcing vehicle terminationPicture, each image carry location information when corresponding vehicle termination acquisition described image, based on above-mentioned crowdsourcing image and high-precisionChart database determines the Significant Change element of current high-precision map and the location information of the Significant Change element, further according to everyThe location information of location information and Significant Change element that a image carries obtains the video counts that the first vehicle termination set uploadsAccording to, according to the first vehicle termination set upload video data high-precision map data base is updated.In the technical solution,The image and video information that the update of high-precision map data base is uploaded based on crowdsourcing public vehicles, are adopted without using expensiveCollect vehicle acquisition, renewal speed is fast, it is ensured that the timeliness of map rejuvenation avoids the driving safety of automatic driving vehicle appearanceProblem.
Illustratively, on the basis of the above embodiments, Fig. 3 is high-precision map updating method provided by the embodiments of the present applicationThe flow diagram of embodiment two.As shown in figure 3, in the present embodiment, above-mentioned steps 22 can be achieved by the steps of:
Step 31: each image in crowdsourcing image being analyzed, determines the map marker element in each imageAnd the location information of each map marker element.
Illustratively, in the present embodiment, after cloud server gets the crowdsourcing image of crowdsourcing vehicle termination transmission,Analysis and image recognition processing are carried out to each image in crowdsourcing image, identify the map marker element in each image.For example, the element informations such as lane line, road (guardrail, curb), label, land marking.
Optionally, it after cloud server determines the map marker element in each image, is also based on the image and takesThe location information of band determines the location information of the map marker element.
Step 32: location information and high-precision map data base based on each map marker element judge each ground iconKnow whether element is map variation element.
Illustratively, cloud server inquires high-precision map data base according to the location information of each map marker element,Whether the map element for judging the corresponding position in map data base is above-mentioned map marker element, if the two is consistent, reallyThe fixed map marker element is not map variation element, without any processing；If the two is inconsistent, it is determined that the map identification elementElement is that map changes element.
It is worth noting that cloud server can also incite somebody to action after the location information for determining each map marker elementEach map marker element and high-precision map data base carry out calculus of differences, judge the ground of each map marker element positionWhether pel element changes (including newly-increased, modification, delete etc.), and by the changed map of the map element of positionMarker element is determined as map variation element.
Step 33: if the image of preset quantity changes element in identical geographical location map having the same, it is determined thatIt is Significant Change element that the map, which changes element, and identical geographical location is the location information of Significant Change element.
It in the present embodiment, can be in conjunction with the map variation in other images for determining that each map changes elementElement judges whether have the image of preset quantity in identical geographical location to there is the map of the same category to become in crowdsourcing imageChange element, if so, thinking that map variation element is Significant Change element, correspondingly, above-mentioned identical geographical location is to haveThe location information of effect variation element.
It is worth noting that in the present embodiment, the image of above-mentioned preset quantity can be the different vehicles by preset quantityIssue, i.e., the vehicle termination of preset quantity think the same geographical location map marker element and high-precision map datumMap element variation having the same in library, it is determined that the map marker element in the same geographical location is Significant Change memberElement.
Optionally, which is the threshold value set in cloud server, for example, 3,5 is equivalent.The application is implementedExample is not defined the specific value of preset quantity, can be determines according to actual conditions.
High-precision map updating method provided by the embodiments of the present application, by dividing each image in crowdsourcing imageAnalysis, determines the location information of the map marker element and each map marker element in each image, is based on each mapThe location information of marker element and high-precision map data base judge whether each map marker element is map variation element, andAnd determine that the map changes element in identical geographical location map variation element having the same in the image of preset quantityFor Significant Change element, identical geographical location is the location information of Significant Change element.The technical solution can accurately reallyThe Significant Change element in current high-precision map is made, vehicle termination transmission forgery picture is effectively prevented or hacker's intrusion is madeThe problems such as false or vehicle termination acquisition information is inaccurate.
Illustratively, in embodiments herein, Fig. 4 is that high-precision map updating method provided by the embodiments of the present application is realApply the flow diagram of example three.As shown in figure 4, in the present embodiment, above-mentioned steps 23 can be achieved by the steps of:
Step 41: the location information of the location information and Significant Change element that are carried according to each image determines firstVehicle termination set.
Illustratively, in the present embodiment, the location information carried based on each image can be determined to report each figureAs vehicle termination where position, according to the location information of Significant Change element determine include the Significant Change element regionRange.Thus, by the position where judging each vehicle termination whether be located in the regional scope of the Significant Change element comeThe first vehicle termination set is determined, that is, the position of each vehicle termination in the first vehicle termination set is respectively positioned on effective changeIn the regional scope for changing element.
Optionally, the regional scope of the Significant Change element can be before and after the Significant Change element position one section away fromRange from composition.
Illustratively, in a kind of possible design of the present embodiment, which can also be achieved by the steps of:
Step A1: the location information carried according to each image determines that each image corresponds to the terminal base of vehicle terminationThis information, the terminal essential information include following at least one: current location information, history driving trace information, Present navigationLine information；
Step A2: corresponding to the terminal essential information of vehicle termination according to each image, determines the first vehicle termination set.
In the present embodiment, for common public vehicles, when user drive a certain vehicle go to from a certain departure place it is a certainWhen destination, under normal circumstances, the GPS function that can enable vehicle checks the traffic information of present road, route information etc..CauseAnd the GPS function that cloud server can be enabled based on vehicle obtains the current location information of the vehicle.
Further, when user is using current high-precision map inquiry route information from origin to destination or when leadingNavigate line information, and cloud server can determine the current location information of the vehicle termination, Present navigation line information.
In addition, cloud server is also based on the log-on message of the user, inquire when the user drives vehicle terminationHistory driving trace information.
So in the present embodiment, cloud server can correspond to vehicle termination based on each image of above-mentioned determinationOne of terminals essential informations such as current location information, history driving trace information, Present navigation line information are a variety of, reallyThe first vehicle termination set being located within the scope of the Significant Change element region is made, in the first vehicle termination setEach vehicle termination is for executing video acquisition task.
Step 42: each vehicle termination into the first vehicle termination set sends video acquisition task.
Wherein, which includes pickup area range, which is located at the pickup area rangeIt is interior.
Optionally, in the present embodiment, in order to Significant Change element region progress three-dimensional reconstruction, cloud serverNeed to send the video acquisition task including pickup area range, and above-mentioned Significant Change to the first determining vehicle termination setElement is located within the scope of the pickup area, and each vehicle termination in such first vehicle termination set can just be based on receivingThe video acquisition task acquire video data.
Step 43: receiving the video counts that each vehicle termination acquires within the scope of the pickup area in the first vehicle setAccording to.
Illustratively, each vehicle termination in the first vehicle set can be based on the video acquisition task received, reallyThe corresponding pickup area range of the video acquisition task is made, and acquisition includes effective dimensions of variability within the scope of the pickup areaVideo data including element.
High-precision map updating method provided by the embodiments of the present application, the location information carried according to each image and effectively changeThe location information for changing element, determines the first vehicle termination set, each vehicle termination hair into the first vehicle termination setVideo acquisition task is sent, the video counts that each vehicle termination acquires within the scope of the pickup area in the first vehicle set are receivedAccording to.In the technical solution, cloud server determines effective first vehicle termination set, and gets for high-precision map weightThe video data built has established optimized integration for timely updating for high-precision map.
Illustratively, in embodiments herein, Fig. 5 is that high-precision map updating method provided by the embodiments of the present application is realApply the flow diagram of example four.As shown in figure 5, in the present embodiment, above-mentioned steps 24 can be achieved by the steps of:
Step 51: picture point cloud is created according to the video data that the first vehicle termination set uploads.
Optionally, in the present embodiment, after cloud server gets the video data of the first vehicle termination set upload,Preset algorithm for reconstructing can be used, picture point cloud is created according to the video data received.
The embodiment of the present application is defined the specific implementation not to preset algorithm for reconstructing, for example, it can also be suitableWhen any one or more deep learning algorithms or model, for example, deep learning network or convolutional neural networks etc..It is specific realIt now can be determines according to actual conditions.
Illustratively, cloud server can using motion structure (structure-from-motion, SFM) algorithm orThe other types of 3 D visual algorithm for reconstructing of person, completes the three-dimensional reconstruction of high-precision map, obtains picture point cloud.
SFM algorithm is a kind of off-line algorithm that three-dimensional reconstruction is carried out based on the various unordered pictures being collected into.In this implementationIn the practical application of example, cloud server picks out the image of suitable three-dimensional reconstruction from the video information received first, soAfterwards based on the image creation picture point cloud selected.
It is worth noting that since the data volume that three-dimensional reconstruction needs is very big, but it is not possible that the modeling of full dose map element, instituteWith cloud server only models region relevant to Significant Change element or road, so that picture point cloud in the present embodimentCreation be possibly realized.
Step 52: based on the laser point cloud in the picture point cloud and high-precision map data base, determining Significant Change elementEssential information.
Illustratively, in the present embodiment, high-precision map data base can be the laser generated using centralized system chart-patternPoint cloud, so, cloud server can be carried out with the laser point cloud in picture point cloud created and high-precision map data baseMatch, some significant semantic features about high-precision map that matching is generated using centralized system chart-pattern, for example, such as lamp stand, shieldColumn, label etc., and then the essential information for needing the Significant Change element updated is extracted from above-mentioned picture point cloud.
Optionally, the essential information of Significant Change element may include: geometric position and the attribute letter of Significant Change elementCease isovector information.Wherein, which is specifically as follows geographical location (longitude and latitude) and coordinate, which includes:Colouring information and/or numerical value and/or guiding etc..
It is worth noting that the embodiment of the present application does not limit the specific manifestation shape of the essential information of effective dimensions of variability elementFormula, can be determines according to actual conditions.
Step 53: according to the high-precision map data base of the update of basic information of Significant Change element.
Optionally, in embodiments herein, cloud server is according to the basic letter of the Significant Change element extractedBreath, leads to too small amount of human assistance, can be updated in high-precision map data base.Illustratively, which can be withIt including but not limited to include the contents such as validation of information, information inspection, information adjustment on human-computer interaction interface, it can rootIt is determined according to actual conditions.
High-precision map updating method provided by the embodiments of the present application, the video data uploaded according to the first vehicle termination setIt creates picture point cloud and the base of Significant Change element is determined based on the laser point cloud in the picture point cloud and high-precision map data baseThis information, according to the high-precision map data base of the update of basic information of Significant Change element.In the technical solution, cloud server energyEnough Significant Change elements by high-precision map are updated into high-precision map data base, have update in time, be easily achieved, costFeature low, accuracy is high.
It is worth noting that the high-precision map rejuvenation of the embodiment of the present application can be summarized as the crowd uploaded based on crowdsourcing terminalPacket image finds the Significant Change element of high-precision map, further according to the first vehicle termination collection for meeting preset distance constraintsClose acquisition include effective dimensions of variability element video data, finally to obtained video data beyond the clouds server use it is preset heavyIt builds algorithm and carries out three-dimensional reconstruction, and extract the essential information of Significant Change element, to realize to high-precision map data baseIt updates.Program renewal speed is fast, is easily achieved, and reduces update difficulty, avoids driving of being likely to occur to a certain extentSail safety problem.
In another possible design of the application, the crowdsourcing terminal of the application can also be entirely with data processing, becomeChange identification etc. edges computing capability intelligent vehicle, at this moment, intelligent vehicle just can be to acquired image or video atReason determines that map changes element, is determined by the laser point cloud in the picture point cloud and high-precision map data base of three-dimensional creationThe essential information of Significant Change element out, then cloud server is sent it to, it is realized by cloud server or crowdsourcing platform highThe update of smart map data base.
Following is the application Installation practice, can be used for executing the application embodiment of the method.It is real for the application deviceUndisclosed details in example is applied, the application embodiment of the method is please referred to.
Fig. 6 is the structural schematic diagram of high-precision map rejuvenation Installation practice one provided by the embodiments of the present application.The device canTo be integrated in cloud server, can also be realized by the crowdsourcing platform on cloud server.As shown in fig. 6, this is high-precisionlyFigure updating device may include: to obtain module 61, processing module 62 and update module 63.
Wherein, the acquisition module 61, for obtaining the crowdsourcing image of crowdsourcing vehicle termination upload, each image, which carries, to be corresponded toVehicle termination acquires location information when described image；
The processing module 62 determines current high-precision map for being based on the crowdsourcing image and high-precision map data baseSignificant Change element and the Significant Change element location information；
The acquisition module 61, the position of the location information and the Significant Change element that are also used to be carried according to each imageInformation obtains the video data that the first vehicle termination set uploads, each vehicle termination institute in the first vehicle termination setThe position at place and the position of the Significant Change element meet preset distance constraints；
The update module 63, the video data for being uploaded according to the first vehicle termination set is to the high-precision mapDatabase is updated.
Illustratively, in a kind of possible design of the application, which is specifically used for the crowdsourcing imageIn each image analyzed, determine the position of the map marker element and each map marker element in each imageInformation, location information and the high-precision map data base based on each map marker element, judges each map marker elementWhether it is map variation element, and changes element in identical geographical location map having the same in the image of preset quantityWhen, determine that the map variation element is Significant Change element, the identical geographical location is the Significant Change elementLocation information.
Illustratively, in the alternatively possible design of the application, Fig. 7 be high-precision map provided by the embodiments of the present application moreThe structural schematic diagram of new equipment embodiment two.As shown in fig. 7, in the present embodiment, above-mentioned acquisition module 61 comprises determining that unit71 and Transmit-Receive Unit 72.
The determination unit 71, the position letter of location information and the Significant Change element for being carried according to each imageBreath, determines the first vehicle termination set；
The Transmit-Receive Unit 72 sends video acquisition for each vehicle termination into the first vehicle termination set and appointsBusiness, the video acquisition task includes pickup area range, and the Significant Change element is located within the scope of the pickup area, withAnd receive the video data that each vehicle termination acquires within the scope of the pickup area in the first vehicle set.
Illustratively, in the present embodiment, the determination unit 71 is believed specifically for the position carried according to each imageBreath determines that each image corresponds to the terminal essential information of vehicle termination, and the terminal essential information includes following at least one:Current location information, history driving trace information, Present navigation line information, and vehicle termination is corresponded to according to each imageTerminal essential information determines the first vehicle termination set.
Illustratively, another in the application may design, above-mentioned update module 63, be specifically used for according to described theThe video data that one vehicle termination set uploads creates picture point cloud, is based on the picture point cloud and the high-precision map data baseIn laser point cloud, determine the essential information of the Significant Change element, and the basic letter according to the Significant Change elementBreath updates the high-precision map data base.
Device provided by the embodiments of the present application can be used for executing method of the Fig. 2 into embodiment illustrated in fig. 5, realize formerReason is similar with technical effect, and details are not described herein.
It should be noted that it should be understood that the modules of apparatus above division be only a kind of logic function division,It can completely or partially be integrated on a physical entity in actual implementation, it can also be physically separate.And these modules can be withAll realized by way of processing element calls with software；It can also all realize in the form of hardware；It can also part mouldBlock realizes that part of module passes through formal implementation of hardware by way of processing element calls software.For example, determining module can be withFor the processing element individually set up, it also can integrate and realized in some chip of above-mentioned apparatus, in addition it is also possible to programThe form of code is stored in the memory of above-mentioned apparatus, is called by some processing element of above-mentioned apparatus and is executed above trueThe function of cover half block.The realization of other modules is similar therewith.Furthermore these modules completely or partially can integrate together, can alsoWith independent realization.Processing element described here can be a kind of integrated circuit, the processing capacity with signal.In the process of realizationIn, each step of the above method or the above modules can by the integrated logic circuit of the hardware in processor elements orThe instruction of software form is completed.
For example, the above module can be arranged to implement one or more integrated circuits of above method, such as:One or more specific integrated circuits (application specific integrated circuit, ASIC), or, oneOr multi-microprocessor (digital signal processor, DSP), or, one or more field programmable gate array(field programmable gate array, FPGA) etc..For another example, when some above module dispatches journey by processing elementWhen the form of sequence code is realized, which can be general processor, such as central processing unit (centralProcessing unit, CPU) or it is other can be with the processor of caller code.For another example, these modules can integrate oneIt rises, is realized in the form of system on chip (system-on-a-chip, SOC).
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof realIt is existing.When implemented in software, it can entirely or partly realize in the form of a computer program product.The computer programProduct includes one or more computer instructions.When loading on computers and executing the computer program instructions, all orIt partly generates according to process or function described in the embodiment of the present application.The computer can be general purpose computer, dedicated meterCalculation machine, computer network or other programmable devices.The computer instruction can store in computer readable storage mediumIn, or from a computer readable storage medium to the transmission of another computer readable storage medium, for example, the computerInstruction can pass through wired (such as coaxial cable, optical fiber, number from a web-site, computer, server or data centerUser's line (DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server orData center is transmitted.The computer readable storage medium can be any usable medium that computer can access orIt is comprising data storage devices such as one or more usable mediums integrated server, data centers.The usable medium can be withIt is magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard diskSolid state disk (SSD)) etc..
Fig. 8 is the structural schematic diagram of high-precision map rejuvenation Installation practice three provided by the embodiments of the present application.Such as Fig. 8 instituteShow, the apparatus may include processor 81, memory 82, communication interface 83 and system bus 84, the memory 82 and describedCommunication interface 83 connect with the processor 81 by the system bus 84 and completes mutual communication, the memory 82For storing computer executed instructions, the communication interface 83 is used for and other equipment are communicated, and the processor 81 executesThe scheme such as above-mentioned Fig. 2 to embodiment illustrated in fig. 5 is realized when the computer executed instructions.
The system bus mentioned in the Fig. 8 can be Peripheral Component Interconnect standard (peripheral componentInterconnect, PCI) bus or expanding the industrial standard structure (extended industry standardArchitecture, EISA) bus etc..The system bus can be divided into address bus, data/address bus, control bus etc..ForConvenient for indicating, only indicated with a thick line in figure, it is not intended that an only bus or a type of bus.Communication interfaceFor realizing the communication between database access device and other equipment (such as client, read-write library and read-only library).MemoryMay include random access memory (random access memory, RAM), it is also possible to further include nonvolatile memory(non-volatile memory), for example, at least a magnetic disk storage.
Above-mentioned processor can be general processor, including central processor CPU, network processing unit (networkProcessor, NP) etc.；It can also be digital signal processor DSP, application-specific integrated circuit ASIC, field programmable gate arrayFPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components.
Optionally, the embodiment of the present application also provides a kind of storage medium, and instruction is stored in the storage medium, when itsWhen being run on computer, so that computer executes the method such as above-mentioned Fig. 2 to embodiment illustrated in fig. 5.
Optionally, the embodiment of the present application also provides a kind of chip of operating instruction, and the chip is for executing above-mentioned Fig. 2 extremelyThe method of embodiment illustrated in fig. 5.
In the application, "at least one" refers to one or more, and " multiple " refer to two or more."and/or",The incidence relation of affiliated partner is described, indicates may exist three kinds of relationships, for example, A and/or B, can indicate: individualism A,Exist simultaneously A and B, the case where individualism B, wherein A, B can be odd number or plural number.Character "/" typicallys represent front and back and closesConnection object is a kind of relationship of "or"；In formula, character "/" indicates that forward-backward correlation object is the relationship of a kind of " being divided by ".At least one of " following (a) " or its similar expression, refer to these in any combination, including individual event (a) or complex itemAny combination of (a).For example, at least one (a) in a, b or c, can indicate: a, b, c, a-b, a-c, b-c or a-b-C, wherein a, b, c can be individually, be also possible to multiple.
It is understood that the area that the various digital numbers involved in embodiments herein only carry out for convenience of descriptionPoint, it is not intended to limit the range of embodiments herein.
It is understood that magnitude of the sequence numbers of the above procedures are not meant to execute in embodiments hereinSequence it is successive, the execution of each process sequence should be determined by its function and internal logic, without coping with embodiments hereinImplementation process constitutes any restriction.
Finally, it should be noted that the above various embodiments is only to illustrate the technical solution of the application, rather than its limitations；To the greatest extentPipe is described in detail the application referring to foregoing embodiments, those skilled in the art should understand that: its according toSo be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features intoRow equivalent replacement；And these are modified or replaceed, each embodiment technology of the application that it does not separate the essence of the corresponding technical solutionThe range of scheme.