CN117576370A

CN117576370A - Method and device for processing key point data, storage medium and electronic equipment

Info

Publication number: CN117576370A
Application number: CN202311518246.3A
Authority: CN
Inventors: 于冲
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2023-11-14
Filing date: 2023-11-14
Publication date: 2024-02-20

Abstract

The disclosure provides a method and a device for processing key point data, a storage medium and electronic equipment. Wherein the method comprises the following steps: determining a plurality of subareas from the target area according to the target area attribute of the target area, wherein the area of the subareas is related to the target area attribute; acquiring a first sub-region and a set of key points matched with at least one second sub-region adjacent to the first sub-region, wherein each object key point is used for indicating a road object; under the condition that the first key points and the second key points which meet the merging conditions are included in the key point set, merging the first key points and the second key points in the key point set according to target position information determined by the first position information and the second position information; the method and the device can be applied to scenes such as cloud technology and maps, and can also relate to technologies such as image processing and big data. The method and the device solve the technical problem that the object information of the road object acquired by the related technology is inaccurate.

Description

Method and device for processing key point data, storage medium and electronic equipment

Technical Field

The present invention relates to the field of maps, and in particular, to a method and apparatus for processing key point data, a storage medium, and an electronic device.

Background

Along with the development of technology, in the process of building a high-precision map, it is generally required to label object information of various road objects included in a road, where the road objects may include red and green light objects, street lamp objects, indication board objects, and the like, and the object information may include position information, type information, and the like of the objects.

In the process of collecting the object information of the road object, because the collection precision of different collection terminals is different, the object information obtained by different collection terminals for the same entity road object is usually different. That is, the object information of the road object acquired by the related art has an inaccurate technical problem.

In view of the above problems, no effective solution has been proposed at present.

Disclosure of Invention

The embodiment of the invention provides a method and a device for processing key point data, a storage medium and electronic equipment, which are used for at least solving the technical problem that the object information of a road object acquired by the related technology is inaccurate.

According to an aspect of the embodiment of the present invention, there is provided a method for processing key point data, including: determining a plurality of subareas from a target area according to the target area attribute of the target area, wherein the area of the subareas is related to the target area attribute; acquiring a first sub-region and a key point set matched with at least one second sub-region adjacent to the first sub-region, wherein the key point set comprises a plurality of object key points, and each object key point is used for indicating a road object; determining target position information according to first position information of the first key point and second position information of the second key point under the condition that the first key point and the second key point which meet the merging condition are included in the key point set; and carrying out merging operation on the first key point and the second key point in the key point set according to the target position information.

According to another aspect of the embodiment of the present invention, there is also provided a device for processing keypoint data, including: a first determining unit, configured to determine a plurality of sub-regions from a target region according to a target region attribute of the target region, where a region area of the sub-regions is associated with the target region attribute; the road system comprises an acquisition unit, a storage unit and a control unit, wherein the acquisition unit is used for acquiring a key point set matched with a first subarea and at least one second subarea adjacent to the first subarea, the key point set comprises a plurality of object key points, and each object key point is used for indicating a road object; a second determining unit configured to determine, when the first key point and the second key point that satisfy the merging condition are included in the set of key points, target position information based on first position information of the first key point and second position information of the second key point; and the merging unit is used for merging the first key point and the second key point in the key point set according to the target position information.

Optionally, the processing device of the key point data further includes: the first acquisition unit is used for acquiring a target key point set matched with the target area, wherein the target key point set comprises the object key points acquired by a plurality of terminals in the target area respectively; a matching unit, configured to, when a target road network corresponding to the target area is acquired, match the target key points included in the target key point set with road segment information included in the target road network, where the road segment information is used to indicate attribute information of a target road segment in the target road network; and a third determining unit, configured to determine a road segment identifier sequence corresponding to each of the object key points according to a matching result, where the road segment identifier sequence includes at least two road segment identifiers, and a positional relationship between the target road segment indicated by the road segment identifier and the corresponding object key point satisfies a matching condition.

Optionally, the second determining unit further includes: a first obtaining module, configured to obtain, when a first key point type of the first key point and a second key point type of the second key point match, the first position information of the first key point and the second position information of the second key point; the second obtaining module is configured to obtain a first link identification sequence corresponding to the first key point and a second link identification sequence corresponding to the second key point when the distance between the first location information and the key point indicated by the second location information is less than or equal to a first distance threshold; and the determining module is used for determining that the first key point and the second key point meet the merging condition under the condition that an identification intersection exists between the first road section identification sequence and the second road section identification sequence.

Optionally, the third determining unit is configured to: acquiring an object track corresponding to the object key point, wherein the object track is a travelling track corresponding to the terminal in the process of acquiring the object key point; acquiring a reference identification sequence for indicating the object track; and determining the road section identification sequence from the reference identification sequence, wherein the distance between the target road section indicated by the road section identification in the road section identification sequence and the object key point is smaller than or equal to a second distance threshold value.

Optionally, the third determining unit is further configured to at least one of: acquiring key point position information of the object key points; acquiring key point type information of the key points of the object, wherein the key point type information is used for indicating the object type of the road object; and acquiring the key point confidence of the key point of the object, wherein the key point confidence is used for indicating the accuracy of the key point type information identified based on the key point of the object.

Optionally, the first obtaining unit is configured to: acquiring a reference key point set acquired by a target terminal in a target time period, wherein the reference key point set comprises reference key points acquired respectively at a plurality of key point acquisition times; acquiring a track point set of the target terminal in the target time period, wherein the track point set comprises terminal track points respectively acquired at a plurality of track point acquisition times; updating key point information of the first reference key point and track point information of the corresponding terminal track point under the condition that the reference key point set comprises the first reference key point with the key point acquisition time and the track point acquisition time matched; and adding a reference terminal track point corresponding to the second reference key point into the track point set according to the key point information of the second reference key point under the condition that the reference key point set comprises the second reference key point with unmatched key point acquisition time and track point acquisition time.

Optionally, the first determining unit is configured to at least one of: determining a plurality of subareas from the target area according to the key point density of the target area, wherein the target area attribute comprises the key point density, and the area of the subareas has a negative correlation with the key point density; determining a plurality of subareas from the target area according to the traffic flow coefficient of the target area, wherein the target area attribute comprises the traffic flow coefficient, and the area of the subareas has a negative correlation with the traffic flow coefficient; and determining a plurality of subareas from the target area according to the road network density of the target area, wherein the target area attribute comprises the road network density, and the area of the subareas has a negative correlation with the road network density.

Optionally, the first determining unit is configured to: acquiring an circumscribed rectangular area matched with a target area; and performing quadtree division on the circumscribed rectangular region according to the target region attribute to determine a plurality of rectangular sub-regions, wherein the region area of the rectangular sub-regions is related to the target region attribute.

Optionally, the merging unit is configured to: acquiring first key point information of the first key point and second key point information of the second key point, wherein the first key point information comprises first key point attribute information and the first position information, and the second key point information comprises second key point attribute information and the second position information; determining third key point attribute information according to the first key point attribute information and the second key point attribute information, and taking the target position information as third key point position information; and adding a third key point in the key point set according to the third key point attribute information and the third key point position information.

Optionally, the merging unit is configured to: acquiring a first merging coefficient contained in first key point attribute information and a second merging coefficient contained in the second key point attribute information, wherein the first merging coefficient indicates that the first key points are merged according to a first number of original key points, and the second merging coefficient indicates that the second key points are merged according to a second number of original key points; and determining the target position information according to a weighted summation result of the first weight coefficient corresponding to the first merging coefficient and the first position information and a weighted summation result of the second weight coefficient corresponding to the second merging coefficient and the second position information.

Optionally, the merging unit is further configured to: when the third key point and the fourth key point which meet the merging condition are included in the key point set, determining reference position information according to third position information of the third key point and fourth position information of the fourth key point; combining the third key point and the fourth key point in the key point set according to the reference position information; when the two object keypoints satisfying the merging condition are not included in the set of keypoints, acquiring the set of keypoints matched by a third subregion and at least one fourth subregion adjacent to the third subregion from the plurality of subregions; and executing the merging operation on the object key points meeting the merging condition in the key point set.

Optionally, the processing device of the key point data is further configured to: acquiring a road image sequence acquired by a target terminal in the driving process, wherein the road image sequence comprises a plurality of road images which are sequenced according to the sequence of acquisition time; identifying a road object in the road image; when at least one road image identifies a target road object, determining a target road image with the largest image area occupied by the target road object from at least one road image; and determining the key points of the object according to the image information corresponding to the target road image, wherein the image information comprises image position information and acquisition time information.

Optionally, the processing device of the key point data is further configured to: acquiring reference position information of a reference key point under the condition that the reference terminal receives the reference key point acquired in the target area; determining a reference subarea from a plurality of subareas according to the reference position information; when a fifth key point meeting the merging condition with the reference key point is included in the reference key point set matched with the reference sub-region, the merging operation is performed on the reference key point and the fifth key point; and when the target key points which meet the merging condition with the reference key points are not included in the reference key point set matched with the reference sub-region, determining the reference key points as candidate key points, and configuring candidate confidence degrees for the candidate key points, wherein the candidate confidence degrees are determined according to the number of the reference key points which meet the merging condition with the candidate key points.

According to still another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium having a computer program stored therein, wherein the computer program is configured to execute the above-described processing method of the key point data when running.

According to yet another aspect of embodiments of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions so that the computer device performs the processing method of the key point data as above.

According to still another aspect of the embodiments of the present invention, there is also provided an electronic device including a memory in which a computer program is stored, and a processor configured to execute the above-described processing method of key point data by the above-described computer program.

In the embodiment of the invention, a plurality of subareas are determined from a target area according to the target area attribute of the target area, and the area of each subarea is associated with the target area attribute; acquiring a first sub-region and a set of key points matched with at least one second sub-region adjacent to the first sub-region, wherein each object key point is used for indicating a road object; under the condition that the first key points and the second key points meeting the merging condition are included in the key point set, merging operation is carried out on the first key points and the second key points in the key point set according to the target position information determined by the first position information and the second position information, and therefore the fact that under the condition that a plurality of key point information is obtained, merging processing is carried out on the plurality of key point information to improve accuracy of the key point information is achieved.

In the above embodiment of the present application, the target area is dynamically divided according to the area attribute characteristics of the target area, so as to obtain a plurality of sub-areas, and the key point processing is performed by taking the sub-areas as a unit, so that the processing efficiency is effectively improved by dynamically dividing the area of the area to be processed; in addition, in the process of carrying out key point data processing by taking the subareas as a unit, object key points are combined and updated pairwise according to the combination condition, so that the problem that the acquisition of the object information of the existing road object is inaccurate is solved by combining the position information of a plurality of key points to update and combine the key point information under the condition that a plurality of terminals respectively acquire different object key points of the same road object is solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:

FIG. 1 is a schematic diagram of a hardware environment of an alternative method of processing keypoint data according to an embodiment of the invention;

FIG. 2 is a flow chart of an alternative method of processing keypoint data according to an embodiment of the invention;

FIG. 3 is a schematic diagram of an alternative method of processing keypoint data according to an embodiment of the invention;

FIG. 4 is a schematic diagram of another alternative method of processing keypoint data according to an embodiment of the invention;

FIG. 5 is a schematic diagram of yet another alternative method of processing keypoint data according to an embodiment of the invention;

FIG. 6 is a schematic diagram of yet another alternative method of processing keypoint data in accordance with an embodiment of the invention;

FIG. 7 is a schematic diagram of yet another alternative method of processing keypoint data according to an embodiment of the invention;

FIG. 8 is a schematic diagram of yet another alternative method of processing keypoint data in accordance with embodiments of the invention;

FIG. 9 is a schematic diagram of yet another alternative method of processing keypoint data in accordance with an embodiment of the invention;

FIG. 10 is a schematic diagram of yet another alternative method of processing keypoint data according to an embodiment of the invention;

FIG. 11 is a flow chart of another alternative method of processing keypoint data according to an embodiment of the invention;

FIG. 12 is a schematic diagram of an alternative apparatus for processing keypoint data according to an embodiment of the invention;

Fig. 13 is a schematic structural view of an alternative electronic device according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For ease of understanding, the terms referred to in the embodiments of the present application are explained as follows:

intelligent transportation system (Intelligent Traffic System, ITS): the intelligent transportation system (Intelligent Transportation System) is a comprehensive transportation system which effectively and comprehensively applies advanced scientific technologies (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operation study, artificial intelligence and the like) to transportation, service control and vehicle manufacturing, and strengthens the connection among vehicles, roads and users, thereby forming a comprehensive transportation system which ensures safety, improves efficiency, improves environment and saves energy sources;

intelligent vehicle road collaboration system (Intelligent Vehicle Infrastructure Cooperative Systems, IVICS): the vehicle-road cooperative system is one development direction of Intelligent Traffic Systems (ITS). The vehicle-road cooperative system adopts advanced wireless communication, new generation internet and other technologies, carries out vehicle-vehicle and vehicle-road dynamic real-time information interaction in an omnibearing manner, develops vehicle active safety control and road cooperative management on the basis of full-time idle dynamic traffic information acquisition and fusion, fully realizes effective cooperation of human-vehicle roads, ensures traffic safety, improves traffic efficiency, and forms a safe, efficient and environment-friendly road traffic system;

Geographic information data: the data describing natural, social and humane landscapes with reference to the spatial position of the earth surface are directly or indirectly related to the data of a certain place relative to the earth, and are element files representing the natural phenomena and social phenomena of geographic position and distribution characteristics, including natural geographic data and socioeconomic data;

link: the real road network is abstracted in the electronic map, each section of road network is abstracted into a link, the link has coordinate point strings for marking the position of the link and a series of attributes at the same time, and the attributes (such as traffic sign, number of lanes, length, width and other information) on the section of road are marked.

In the related embodiment of the present application, the operations such as collecting and processing the related geographic information data all conform to the specification of the related normative file; and before the operations of collecting, processing and the like of the geographic information data, the authorization permission of the relevant main body is required to be obtained.

According to an aspect of the embodiments of the present application, a method for processing key point data is provided, and as an optional implementation manner, the method for processing key point data may be applied, but not limited to, to a processing hardware system of key point data formed by the server 112 and the vehicle-mounted terminal 102 as shown in fig. 1. As shown in fig. 1, the server 112 is connected to the in-vehicle terminal 102 through a network 110, which may include, but is not limited to: a wired network, a wireless network, wherein the wired network comprises: local area networks, metropolitan area networks, and wide area networks, the wireless network comprising: bluetooth, WIFI, and other networks that enable wireless communications. The vehicle-mounted terminal is further provided with a display 104, a processor 106 and a memory 108, wherein the display can be used for displaying an interactive interface of the vehicle-mounted client, the processor can be used for conducting encryption processing on geographic information data acquired through the vehicle-mounted terminal, and key point data for indicating a road object can be extracted according to the number of lines of geographic information data. In addition, the responsive feedback operation can be performed according to the user operation instruction; the memory is used for storing the ciphertext data obtained by the encryption processing.

It may be understood that, in the case where the vehicle-mounted terminal 102 collects the geographic information data in real time, the vehicle-mounted terminal 102 may process the geographic information data to obtain the key point data for indicating the road objects, then send the encrypted key point data to the server 112 through the network 110, and when the server 112 receives the key point data sent by the plurality of vehicle-mounted terminals 102, obtain a plurality of object key points for respectively indicating the plurality of road objects in the target area by performing the key point aggregation processing according to the key point set corresponding to the target area; the vehicle-mounted terminal 102 may receive the processing response result returned by the server 112 through the network 110, and further execute the subsequent vehicle-mounted service operation according to the received response result. The server 112 may be a single server, a server cluster composed of a plurality of servers, or a cloud server. The server 112 may be further divided into a first data processing environment configured with a first data security level and a second data processing environment configured with a second data security level, where the second data security level is higher than the first data security level, and where a data encryption operation is performed in the second data processing environment, and where a data forwarding operation or other non-encryption operation is performed in the first data processing environment.

The server 112 includes a database 114 and a processing engine 116. Wherein, the processing engine 116 is configured to forward and store the key point data in the first data processing environment; the database 114 may be used to store the key point data obtained after decryption.

In the hardware system shown in fig. 1, the method for processing the key point data may specifically include the following steps:

step S102, the vehicle-mounted terminal 102 collects key point data;

the in-vehicle terminal 102 then executes step S104 to send the key point data to the server 112 via the network 110;

step S106-S114 of the server 112, wherein the server 112 acquires a target key point set matched with the target area, and the target key point set comprises object key points acquired by a plurality of terminals in the target area respectively; determining a plurality of subareas from the target area according to the target area attribute of the target area, wherein the area of the subareas is related to the target area attribute; acquiring a key point set matched with a first sub-region and at least one second sub-region adjacent to the first sub-region, wherein the key point set comprises a plurality of object key points, and each object key point is used for indicating a road object; under the condition that a first key point and a second key point which meet the merging condition are included in the key point set, determining target position information according to first position information of the first key point and second position information of the second key point; and carrying out merging operation on the first key point and the second key point in the key point set according to the target position information.

As an optional implementation manner, as shown in fig. 2, the above method for processing the key point data may be applied to a server or a server cluster, and specifically may include the following steps:

s202, determining a plurality of subareas from a target area according to the target area attribute of the target area, wherein the area of the subareas is related to the target area attribute;

s204, acquiring a key point set matched with the first sub-region and at least one second sub-region adjacent to the first sub-region, wherein the key point set comprises a plurality of object key points, and each object key point is used for indicating a road object;

s206, determining target position information according to the first position information of the first key point and the second position information of the second key point under the condition that the first key point and the second key point which meet the combination condition are included in the key point set;

s208, merging the first key point and the second key point in the key point set according to the target position information.

It should be noted that, the target area in the step S202 may be a map area to be subjected to the keypoint drawing or updating. Further, the target area attribute may be an area characteristic for indicating the area of the land, and the area characteristic may be determined according to the collected related geographic information data of the target area. For example, in the case where the traffic flow data of the target area is acquired, the target area attribute may be a traffic flow parameter; under the condition of the collected regional people flow data of the target region, the target region attribute can be a people flow parameter; in the case where road network distribution data of the target area is collected, the target area attribute may be a road network density, and the road network density may be the number of road segments included in a unit area. Since the embodiments described above may be used to process the keypoint data of the object keypoints, in a preferred manner, the target region attribute may be a keypoint density, and the keypoint density may be the number of received keypoint information in a unit region area. The above types of target area attributes are merely exemplary, and the specific types of target area attributes are not limited in the specific embodiments.

After determining the attribute of the target area, the manner of determining the sub-area may be specifically determined according to an attribute parameter of the attribute of the target area, for example, may be determined according to the traffic flow parameter, determined according to the people flow parameter, determined according to the road network density, and determined according to the object key point density. In a preferred manner, in determining the sub-regions, the respective sub-regions may be determined based on a region area having a negative correlation with the object keypoint density. The above-mentioned negative correlation can be understood that the greater the object keypoint density in a sub-region, the smaller the region area of the sub-region. It can be understood that by the determination mode of the subareas, the target area can be divided into a plurality of data processing units (namely subareas), and the data processing units with larger data quantity are processed according to finer area of the areas, so that grading processing of the target area is realized, and the processing efficiency of processing the target key point data is improved.

In the step S204, the object key point may be used to indicate a road object in the target area. In particular, the road objects may include, but are not limited to, traffic light objects, sign objects, street light objects, etc. in a road. In this embodiment, the specific object type indicated by the object key point is not limited.

Alternatively, the key point information for determining the key point of the object may include, but is not limited to, location information (such as latitude and longitude information) of the key point, identification element information (such as an object type of the road object indicated by the key point), and the like. In a preferred manner, the object key point may be a vector Mark point, and specifically, the key point information of the vector Mark point may further include travel direction information (corresponding to a road direction in a road network) and corresponding Link information (i.e., road segment identification information of a corresponding road network segment), and the like.

It should be noted that, in the step S204, the key point obtaining manner of the object key point may include, but is not limited to, obtaining information based on GPS information, altitude information, navigation information, road condition information, and the like. The terminal device that may be used to collect the above-mentioned geographical information data may include, but is not limited to, a surveying operation device that may perform a surveying operation, a vehicle-mounted surveying operation device, a road camera device for acquiring road condition information, a road radar device, a road laser device, and the like. The specific type of the above-described geographical information data, and the specific type of the terminal device for collecting the above-described geographical information data are not limited in this embodiment.

Alternatively, the terminal device may be an application terminal loaded on a transportation device, for example, a vehicle application terminal loaded on a motor vehicle, a vehicle application terminal loaded on a non-motor vehicle, a train application terminal loaded on a train, or the like. Further, the application terminal may be used to provide services including, but not limited to, positioning, navigation, autopilot, road condition pre-warning, etc. for the user driving the transportation device. The specific type and specific service function of the vehicle-mounted terminal are not limited in this embodiment.

It should be noted that, the vehicle-mounted terminal may collect related geographic information data while providing services for users, and provide related services or execute related data collection services. The geographic information data may specifically include, but is not limited to, road image data, road scanning information, etc. collected by a vehicle-mounted camera, vehicle position information, altitude information, etc. collected by a vehicle-mounted GPS, vehicle running state information, etc. collected by a device such as a vehicle-mounted gyroscope, etc. As a specific way, the geographic information data may be related data acquired by a sensing device (such as a camera, a laser radar, a millimeter wave radar, etc.) disposed or hung on the transportation device. Optionally, the geographic information data may also be mapping geographic information data such as spatial coordinates, images, point clouds and attribute information thereof. It will be appreciated that the above data, such as account privacy relating to the subject account, needs to be properly maintained and handled, and, in addition, the above data is also a specific data type specified by the relevant normative file, and the above data needs to meet the requirements of relevant data compliance during the process of transmitting and handling the above data.

A preferred way of obtaining the object key points is described below:

before determining the plurality of sub-regions from the target region according to the target region attribute of the target region, the method further includes:

s1, acquiring a road image sequence acquired by a target terminal in a driving process, wherein the road image sequence comprises a plurality of road images which are sequenced according to the sequence of acquisition time;

s2, identifying a road object in the road image;

s3, determining a target road image with the largest image area occupied by the target road object from at least one road image under the condition that the target road object is identified by the at least one road image;

and S4, determining object key points according to image information corresponding to the target road image, wherein the image information comprises image position information and acquisition time information.

It can be understood that, in this embodiment, the key manner of acquiring the object may be specifically acquiring according to the road image acquired by the terminal during the driving process. Specifically, the terminal may be configured to collect road images at a target time interval, and upload an image sequence of the collected road images to the server after encryption processing. In the server, image objects in an image sequence of road images collected by each terminal are sequentially identified, and when the same road object is identified in a plurality of continuous road images, a road image with the largest image area occupied by the road object is determined as a target road image, object key points are determined according to the target road image, and key point information (such as the position information, the collection time information, the identification element information and the like) of the object key points is determined according to image information of the target road image.

Further, in the step S204, a first sub-region and at least one second sub-region adjacent to the first sub-region may be acquired from the plurality of sub-regions, and a set of object keypoints that match with the first sub-region and the second sub-region may be acquired. It will be appreciated that in the present embodiment, in performing the object keypoint merging operation, the minimum unit processed is determined by the object keypoint set that is matched by the first sub-region and the second sub-region adjacent to the first sub-region. The reason is that, after dividing the target area into a plurality of sub-areas, if the merging process of the object key points is performed only by traversing the sub-areas, the plurality of object key points which cross the sub-areas and indicate the same road object cannot be merged, so that the merging update effect is affected; through the step S204, the object key points in each sub-area can be combined with the object key points in the adjacent sub-areas to perform the merging update, so that the key point merging operation of each object key point can be ensured in the process of traversing each sub-area to perform the object key points.

In the above steps S206 and S208, it may be sequentially determined whether or not the two object keypoints satisfy the above merging condition in the above keypoint set. It should be noted that the merging condition may include, but is not limited to, a key point distance condition, a type condition, and the like. In the present embodiment, the specific condition contents of the above-described combination condition are not limited.

In the case that the first key point and the second key point are determined to meet the merging condition, the merging operation may be performed on the first key point and the second key point according to the target position information determined by the first position information of the first key point and the second position information of the second key point. The above-described merging operation may include, but is not limited to: combining the first key point and the second key point into a third key point, and determining third position information of the third key point according to the first position information of the first key point and the second position information of the second key point; the first key point is utilized to combine the second key point, namely, the first position information of the first key point is updated according to the target position information, and meanwhile, the second key point is deleted; it is also possible to merge the first keypoint with the second keypoint, i.e. update the second location information of the second keypoint according to the target location information while deleting the first keypoint. In the present embodiment, the specific mode of the above-described key point combining operation is not limited.

An alternative embodiment is described below in connection with fig. 3. As shown in fig. 3, the map area included in fig. 3 may be divided into a first sub-area, a second sub-area, and a third sub-area according to the key point density, wherein the first sub-area includes a key point a and a key point B; the second subarea comprises a key point C and a key point D; the first sub-area includes a key point E and a key point F. It can be seen that, in the present embodiment, since the density of the keypoints corresponding to the third sub-region is minimum, the area of the third sub-region is maximum.

In the merging process, the first subarea is firstly used as a current subarea, the second subarea and the third subarea which are adjacent to the first subarea are acquired, key points included in the first subarea are used as key points in a key point set, and then the object key points included in the first subarea are subjected to pairwise conditional judgment.

It should be noted that, assuming that the key point B and the key point C meet the merging condition, if traversing the first sub-region, the second sub-region and the third sub-region is adopted in the merging process to respectively merge the key points included in each sub-region, the key point B and the key point C respectively belong to different sub-regions, so that the key point B and the key point C cannot be merged, and the technical problem of inaccurate merging of the key points of the object occurs; through the above embodiment of the application, the first sub-region is used as the current sub-region, the second sub-region and the third sub-region adjacent to the first sub-region are obtained, and the key points included in the first sub-region are used as the key points in the key point set, so that the key point B and the key point C can be judged in the merging condition, effective merging is finally realized, and the accuracy of merging and updating of the key points is improved.

In an optional embodiment, before the acquiring the set of keypoints matched by the first sub-region and the at least one second sub-region adjacent to the first sub-region, the method further includes:

s1, acquiring a target key point set matched with a target area, wherein the target key point set comprises object key points acquired by a plurality of terminals in the target area respectively;

s2, under the condition that a target road network corresponding to a target area is obtained, matching is carried out according to the object key points included in the target key point set and road section information included in the target road network, wherein the road section information is used for indicating attribute information of a target road section in the target road network;

and S3, determining a road section identification sequence corresponding to each object key point according to the matching result, wherein the road section identification sequence comprises at least two road section identifications, and the position relationship between the target road section indicated by the road section identifications and the corresponding object key points meets the matching condition.

It can be understood that in this embodiment, before acquiring the set of key points matched by the first sub-region and at least one second sub-region adjacent to the first sub-region, link sequence matching may be performed on each object key point in the set of target key points matched with the target region, so as to determine whether the combining condition is satisfied based on the comparison result of the Link sequences in the process of combining the object key points.

In the step S2, the link information may be used to indicate attribute information of each target link, and the attribute information may include, but is not limited to, a coordinate point sequence corresponding to the link, the coordinate point sequence being used to identify a link position of the target link, and further the attribute information may include traffic sign information, lane number information, length information, width information, and the like on the link.

In a preferred manner, the road segment identification sequences that are in key match with the respective objects may be determined based on the coordinate point sequences in the above road segment information. For example, when the key point position information of each object key point is acquired, a plurality of target segments within a target distance threshold from the key point position information may be acquired, and the segment identification sequence may be determined according to the segment identifications of the plurality of target segments.

In an optional embodiment, the road segment identification sequence may further include an entry identification sequence and an exit identification sequence, and a road segment direction corresponding to the road segment sequence formed by the entry identification sequence may be a direction pointing to the object key point; the road section direction corresponding to the road section sequence formed by the exit identification sequence can be a direction away from the key point of the object.

In an alternative embodiment, in a case that the first keypoint and the second keypoint satisfying the merging condition are included in the set of keypoints, before determining the target position information according to the first position information of the first keypoint and the second position information of the second keypoint, the method further includes:

s1, under the condition that a first key point type of a first key point is matched with a second key point type of a second key point, acquiring first position information of the first key point and second position information of the second key point;

s2, under the condition that the distance between key points indicated by the first position information and the second position information is smaller than or equal to a first distance threshold value, acquiring a first road section identification sequence corresponding to the first key point and a second road section identification sequence corresponding to the second key point;

and S3, under the condition that an identification intersection exists between the first road section identification sequence and the second road section identification sequence, determining that the first key point and the second key point meet the merging condition.

It may be understood that, in this embodiment, the merging condition that the first keypoint and the second keypoint meet includes at least three aspects of contents: first, the first key point and the second key point of the second key point are matched (namely, the object types of the road objects respectively indicated by the first key point and the second key point are the same); secondly, the distance between the key points indicated by the first position information and the second position information is smaller than or equal to a first distance threshold value, namely the distance between the first position information and the second position information is required to be smaller than a certain condition; and finally, determining that the first key point and the second key point meet the merging condition according to the comparison result of the first road section identification sequence corresponding to the first key point and the second road section identification sequence corresponding to the second key point under the condition that the identification sequences corresponding to the first and second key points directly take an intersection.

It should be noted that, when the first segment identifier sequence includes a first entering identifier sequence and a first exiting identifier sequence, and the second segment identifier sequence includes a second entering identifier sequence and a second exiting identifier sequence, the comparison manner may be further determined that an identifier intersection exists between the first entering identifier sequence and the second entering identifier sequence, and an identifier intersection exists between the second exiting identifier sequence and the first exiting identifier sequence.

In an alternative embodiment, in the case that the first keypoint type of the first keypoint and the second keypoint type of the second keypoint do not match, determining that the first keypoint and the second keypoint do not meet the merging condition;

in an alternative embodiment, in the case that the distances between the key points indicated by the first position information and the second position information are greater than the first distance threshold, determining that the first key point and the second key point do not meet the merging condition;

in an alternative embodiment, it is determined that the first and second keypoints do not meet the merging condition in case there is no identification intersection between the first and second road segment identification sequences.

According to the embodiment of the application, the target key point set matched with the target area is obtained; under the condition that a target road network corresponding to a target area is obtained, matching is carried out according to the object key points included in the target key point set and road section information included in the target road network; determining a road section identification sequence corresponding to each object key point according to a matching result, further determining whether the first key point and the second key point are combined according to a comparison result of the first road section identification sequence corresponding to the first key point and the second road section identification sequence corresponding to the second key point, judging the combining condition according to the identification sequence, the key point distance and the key point type matched with each object key point, and further improving the combining accuracy of the object key points because the identification sequence can be used for indicating road network information where the object key points are located and the key point distance can be used for indicating whether the two are different key points generated by measuring errors or not.

In an optional embodiment, the determining the road segment identifier sequence corresponding to each object key point according to the matching result includes:

S1, acquiring an object track corresponding to an object key point, wherein the object track is a travel track corresponding to a terminal in the process of acquiring the object key point;

s2, acquiring a reference identification sequence for indicating the track of the object;

and S3, determining a road section identification sequence from the reference identification sequence, wherein the distance between the target road section indicated by the road section identification in the road section identification sequence and the object key point is smaller than or equal to a second distance threshold.

It should be noted that, the step S2 of obtaining the reference identifier sequence for indicating the track of the object may be specifically a process of matching the track where the key point of the object is located with the road segment in the road network. Specifically, an HMM algorithm (Hidden Markov Model ) may be employed, which may include: matching the track where the key points of the object are positioned with the road network; and obtaining a corresponding road network link (road section identifier) absorbed by the track, and obtaining a time sequence link string of the track according to the plurality of road network links (road section identifiers). Specifically, the link nearest to each track point can be calculated by traversing the track, and then the relation between the track point and the link is obtained.

As shown in fig. 4, assuming that the track where the current key point is located is a running track formed according to track points A, B … … H, correspondingly, the road segment information, which is determined in the road network according to the HMM algorithm and matches with the running track, is a road segment a, b, c, d, e, f, and further, it is determined that the reference identifier sequence corresponding to the object key point is a, b, c, d, e, f.

In an alternative embodiment, before determining the road segment identifier sequence from the reference identifier sequence, at least one of the following is further included:

firstly, acquiring key point position information of key points of an object;

obtaining key point type information of key points of the object, wherein the key point type information is used for indicating the object type of the road object;

and thirdly, acquiring the key point confidence coefficient of the key point of the object, wherein the key point confidence coefficient is used for indicating the accuracy of the key point type information identified based on the key point of the object.

One way of obtaining a link identification sequence matching the object keypoints is described below in connection with fig. 5.

In this embodiment, after the track and the road network are adsorbed by the above embodiment, mark identification point (i.e. the above object key point) information may be further extracted, including longitude and latitude where the Mark identification point is located, object type, confidence level, image frame size, etc.; further, as shown in fig. 5, four solid track points including track point 501 and hollow key points including Mark identification point 502 in the object track, the links included in the Link matched with the object track include: A. b, C, D, E, F. In this embodiment, the track where the Mark recognition point is located may be used as an entry Link string and an exit Link string after 60 meters (a threshold may be set as needed). Assuming that the five road segments A, B, C, D, E, F each include a range within 60m from the Mark identification point 502, the entering Link string is determined to be ABCDE, and the exiting Link string is determined to be EF.

In an alternative way, in order to reduce the matching error and the calculation amount in the matching process, the length of the road segments can be controlled, for example, the road segments exceeding 20m can be reserved, and the road segments less than or equal to 20m are removed from the sequence;

in another alternative, the road segments within the intersections in the sequence may also be culled. The road segments in the crossing point can be used for indicating the short-circuit segment connected with the middle of the main road segment in the large-scale crossing.

In an optional manner, the acquiring the target keypoint set matched with the target area includes:

s1, acquiring a reference key point set acquired by a target terminal in a target time period, wherein the reference key point set comprises reference key points acquired respectively at a plurality of key point acquisition times;

s2, acquiring a track point set of a target terminal in a target time period, wherein the track point set comprises terminal track points respectively acquired at a plurality of track point acquisition times;

s3, under the condition that the reference key point set comprises a first reference key point with the key point acquisition time matched with the track point acquisition time, updating key point information of the first reference key point, and updating track point information of a corresponding terminal track point;

And S4, under the condition that the reference key point set comprises a second reference key point with unmatched key point acquisition time and track point acquisition time, adding a reference terminal track point corresponding to the second reference key point into the track point set according to key point information of the second reference key point.

It will be appreciated that the track data and the key point data reported by the terminal may be preprocessed before determining the road segment identification sequences that match the key points of the respective objects.

Firstly, object key points reported by each terminal can be subjected to grouping processing, namely, the same type of identification points continuously identified by the same equipment in a period of time are divided into a group, and meanwhile, the point with the largest identification frame corresponding to the Mark identification point is regarded as the Mark identification point (the optimal frame cutting point);

and then track fusion processing is carried out, as shown in fig. 6, tracks of the same intelligent device are put together and are connected in sequence according to the sequence of time, and Mark identification points and track points are arranged and fused according to the sequence of sampling time.

Specifically, if there are a track point and a Mark identification point with the same time (for example, the identification point 601 corresponds to the track point 604, and the identification point 603 corresponds to the track point 606), the longitude and latitude of the track point are directly updated, that is, the identification point information of the corresponding identification point is added in the track point, and meanwhile, the track point information of the corresponding track point is added in the identification point; otherwise, the track points are fused by interpolation, for example, the Mark identification point sequence comprises the identification point 602, but the Link sequence corresponding to the track does not comprise the track point corresponding to the sampling time, the track point 605 is added in the track point, and the relevant information of the identification point 602 is added in the track point 605.

In an alternative manner, the manner of fusing the interpolation track points may be to create corresponding track points by interpolation according to track point information of the front track point and the rear track point. As shown in fig. 7, in the case where the sampling time information and the position information of the track points 701 and 702, and the time information of the track point 703 to be created are known, the manner of determining the position information of the track point 703 may be:

ratio＝(t _b -t _a )/(t _c -t _a )

X _b ＝X _a +(X _c -X _a )*ratio

Y _b ＝Y _a +(Y _c -Y _a )*ratio

wherein t is _b Sample time, X, for trace point 703 _b ，Y _b Position information of the track point 703; t is t _c X is the sampling time of trace point 702 _c ，Y _c Position information for the track point 702; t is t _a X is the sampling time of trace point 701 _a ，Y _a Is the positional information of the track point 701.

Optionally, during the preprocessing process, the abnormal points in the track point set and the key point set may be further processed, for example, the abnormal track points and Mark points may be deleted, specifically, the track points and Mark points where field deletion occurs, the track points and Mark points where values are in the unreasonable range of the field may be deleted, and so on.

In an optional embodiment, the determining a plurality of sub-regions from the target region according to the target region attribute of the target region includes at least one of:

Determining a plurality of subareas from a target area according to the key point density of the target area, wherein the target area attribute comprises the key point density, and the area of the subareas has a negative correlation with the key point density;

determining a plurality of subareas from a target area according to the traffic flow coefficient of the target area, wherein the attribute of the target area comprises the traffic flow coefficient, and the area of the subareas has a negative correlation with the traffic flow coefficient;

and determining a plurality of subareas from the target area according to the road network density of the target area, wherein the target area attribute comprises the road network density, and the area of the subareas has a negative correlation with the road network density.

It will be appreciated that the above embodiments of the present application provide a plurality of ways of determining a plurality of sub-areas, alternatively, the plurality of ways of determining a plurality of sub-areas may be any combination of the first, second and third ways. The present embodiment is not limited to the above-described specific manner of specifying the sub-region.

Optionally, the determining the plurality of sub-regions from the target region according to the target region attribute of the target region includes:

S1, acquiring an external rectangular area matched with a target area;

s2, performing quadtree division on the circumscribed rectangular area according to the target area attribute, and determining a plurality of rectangular sub-areas, wherein the area of the rectangular sub-areas is related to the target area attribute.

It is understood that in this embodiment, the target area may be divided into a plurality of rectangular sub-areas in a quadtree division manner. As shown in fig. 8, the rectangular target area may be divided into a plurality of sub-areas according to the key point density, and specifically may include a first sub-area 801 of a first area, a second sub-area 802 of a second area, a third sub-area 803 of a third area, and a fourth sub-area 804 of a fourth area. In this embodiment, the area of the sub-region may have a negative correlation with the keypoint density of the keypoints included in the sub-region, in other words, the first keypoint density of the first sub-region 801 is smaller than the second keypoint density of the second sub-region 802; the second keypoint density of the second subregion 802 is less than the third keypoint density of the third subregion 803; the third keypoint density of the third subregion 803 is smaller than the fourth keypoint density of the fourth subregion 804.

The process of determining a plurality of rectangular sub-areas by performing quadtree partitioning on the circumscribed rectangular area according to the target area attribute is further described below. First, a density interval corresponding to each region level may be determined, for example, a first level corresponds to a first key point density interval, a second level corresponds to a second key point density interval, a third level corresponds to a third key point density interval, and a fourth level corresponds to a fourth key point density interval, where the first key point density interval is less than the second key point density interval, the second key point density interval is less than the third key point density interval, and the third key point density interval is less than the fourth key point density interval.

Next, as shown in fig. 9, the target area is first divided into four sub-areas, which are respectively determined as a first sub-area 901 and a second sub-area 902 of the graph (a) in fig. 9, and a third sub-area 903 and a fourth sub-area 904 of the graph (b) in fig. 9;

acquiring the key point density corresponding to each sub-region, and if the key point densities corresponding to the first sub-region, the second sub-region and the third sub-region are all located in the first key point density interval and the key point density of the fourth sub-region is larger than the first key point density interval, reserving the first sub-region, the second sub-region and the third sub-region and continuously dividing the fourth sub-region into a fifth sub-region, a sixth sub-region, a seventh sub-region and an eighth sub-region which are located in a second level;

If the keypoint density of the eighth subregion is greater than the second keypoint density interval, dividing the eighth subregion into a ninth subregion, a tenth subregion, an eleventh subregion and a twelfth subregion at the third level, and comparing … … the keypoint density of the ninth subregion, the tenth subregion, the eleventh subregion and the twelfth subregion with the third keypoint density interval

And so on until it is determined that the keypoint density corresponding to each sub-region is adapted to the region level in which it is located.

According to the embodiment of the application, the circumscribed rectangular area matched with the target area is obtained; and performing quadtree division on the circumscribed rectangular region according to the target region attribute to determine a plurality of rectangular sub-regions, and further performing key point combination according to the key point set determined by the divided sub-regions, so that the key point combination and combination efficiency are improved.

In an optional embodiment, the merging operation of the first keypoint and the second keypoint in the set of keypoints according to the target location information includes:

s1, acquiring first key point information of a first key point and second key point information of a second key point, wherein the first key point information comprises first key point attribute information and first position information, and the second key point information comprises second key point attribute information and second position information;

S2, determining third key point attribute information according to the first key point attribute information and the second key point attribute information, and taking the target position information as third key point position information;

and S3, adding a third key point in the key point set according to the third key point attribute information and the third key point position information.

Optionally, in the foregoing embodiment, the first keypoint attribute information may include a first merging coefficient, where the first merging coefficient indicates that the first keypoint is obtained by merging according to the first number of original keypoints; the second key point attribute information may include a second merging coefficient, where the second merging coefficient indicates that the second key point is obtained by merging the second key points according to the second number of original key points.

For example, the first keypoint is obtained by merging according to 8 original keypoints, and the first merging coefficient is determined to be 8, and the second keypoint is obtained by merging according to 16 original keypoints, and the second merging coefficient is determined to be 16.

In the present embodiment, when a new third key point is determined, the third key point may be added to the set of key points instead of the first key point and the second key point, and third key point attribute information may be determined using the first key point attribute information and the second key point attribute information. For example, when the first merging coefficient is 8 and the second merging coefficient is 16, the third merging coefficient of the third key obtained by merging the first key point and the second key point is 24.

In addition, the key point position of the third key point may be determined according to the target position information. The manner of determining the target location information may include, but is not limited to, determining from a weighted average of the keypoint locations of the first keypoint and the second keypoint, or from an arithmetic average. In the present embodiment, the specific determination method of the target position information is not limited.

In a preferred embodiment, the determining the target location information according to the first location information of the first key point and the second location information of the second key point includes:

s1, acquiring a first merging coefficient contained in first key point attribute information and a second merging coefficient contained in second key point attribute information, wherein the first merging coefficient indicates that the first key points are merged according to a first number of original key points, and the second merging coefficient indicates that the second key points are merged according to a second number of original key points;

s2, determining target position information according to a weighted summation result of a first weight coefficient corresponding to the first merging coefficient and the first position information and a second weight coefficient corresponding to the second merging coefficient and the second position information.

It may be appreciated that in this embodiment, the position information of the third keypoint may be determined according to a weighted average of the keypoint positions of the first keypoint and the second keypoint, and specifically, the weight may be determined according to the above-mentioned combining coefficient. For example, when the first combining coefficient is 8 and the second combining coefficient is 16, in determining the position information of the third key point, the second weight of the key point position information of the second key point is higher than the first weight of the key point position information of the first key point.

Optionally, after the merging operation is performed on the first keypoint and the second keypoint in the keypoint set according to the target position information, the method further includes:

s1, under the condition that a third key point and a fourth key point which meet the combination condition are included in a key point set, determining reference position information according to third position information of the third key point and fourth position information of the fourth key point; combining the third key point and the fourth key point in the key point set according to the reference position information;

s2, acquiring a key point set matched with a third subarea and at least one fourth subarea adjacent to the third subarea from a plurality of subareas under the condition that two object key points meeting the merging condition are not included in the key point set; and executing the merging operation on the object key points meeting the merging condition in the key point set.

It can be understood that the merging operation can be continuously operated in a traversing manner until there is no sustainable merging point around the Mark recognition point, and then the final Mark is output as a real Mark recognition point.

The above-described embodiment will be specifically described with reference to fig. 9 and 10.

As shown in fig. 9 (a), in the case where the sub-areas adjacent to the first sub-area 901 are 8 second sub-areas 902 having the same size, the object keypoints included in the 8 second sub-areas 902 having the same size and the object keypoints included in the first sub-area 901 may be determined as the above-described set of keypoints; as shown in fig. 9 (b), in the case where the sub-areas adjacent to the third sub-area 903 are 6 fourth sub-areas 904 different in size, the object keypoints included in the 6 fourth sub-areas 904 different in size and the object keypoints included in the third sub-area 903 may be determined as the above-described set of keypoints;

after the key point set is determined, any two key points in the key point set can be traversed, and under the condition that the key point types of the two key points are different, the two key points are determined not to execute merging operation; under the condition that the key point distance of the key points of the two key points is larger than a distance threshold value, determining that the two key points do not execute merging operation;

Under the condition that the types of key points of the two key points are the same and the distance between the key points is smaller than or equal to a distance threshold value, link sequences corresponding to the two key points are further obtained, the Link sequences corresponding to the two key points are sequentially compared, and under the condition that sequence intersection exists between the Link sequences, the two key points are determined to be combined; otherwise, it is determined that no merging operation is performed on the two keypoints.

The merging mode is as follows:

wherein X is _new ，Y _new For the key point coordinates of the combined object key points, N indicates that the object key point a is generated by aggregation of N original object key points; m indicates that the object key points b are generated by aggregation of M original object key points. Marking the object key points a and b used by aggregation as used (i.e. not participating in subsequent merging operation), adding the newly generated object key points into the set to continue calculation

And continuously calculating until there is no sustainable merging point around the current object key point, and outputting the final Mark as a real object key point.

As shown in fig. 10, after merging the original object keypoints in the first keypoint set 1001 matched with the road segment B, an object keypoint 1003 may be obtained as a target keypoint corresponding to the first keypoint set 1001; after merging the original object keypoints in the second set of keypoints 1002 matching the road segments C, D, the object keypoints 1004 are obtained as target keypoints corresponding to the second set of keypoints 1004.

In an optional embodiment, after the merging operation is performed on the first keypoint and the second keypoint in the set of keypoints according to the target location information, the method further includes:

s1, under the condition that a reference key point acquired by a reference terminal in a target area is received, acquiring reference position information of the reference key point;

s2, determining a reference subarea from the plurality of subareas according to the reference position information;

s3, under the condition that a fifth key point meeting the merging condition with the reference key point is included in the reference key point set matched with the reference sub-region, merging the reference key point and the fifth key point;

and S4, under the condition that the reference key point set matched with the reference sub-region does not comprise the object key points meeting the merging condition with the reference key points, determining the reference key points as candidate key points, and configuring candidate confidence degrees for the candidate key points, wherein the candidate confidence degrees are determined according to the number of the reference key points meeting the merging condition with the candidate key points.

It can be understood that in this embodiment, after merging the object keypoints in the target area, dynamic clustering may be performed according to the streaming keypoint information uploaded by the reference terminal that is received later.

In the above embodiment, after the merging of the object keypoints in the target area is completed, the keypoint information of the reference keypoints uploaded by the reference terminal may be further obtained, and further merging operation may be performed based on the newly uploaded keypoint information. Specifically, if a fifth key point matched with the key point is found in the key point set in the corresponding sub-region, a merging operation is performed on the fifth key point and the currently received reference key point. It can be understood that, since the fifth key point may be obtained by combining a plurality of original key points and the reference key point is a single original key point, correspondingly, the position weight of the fifth key point is far higher than that of the reference key point, so that even if the combining operation is performed, the updated position information of the key point will not change greatly;

if an object key point matching the key point is found in the key point set in the corresponding sub-region, the reference key point can be used as a candidate key point. And configure the initial confidence. It will be appreciated that this confidence is used to characterize the accuracy of the keypoint. When the key point matched with the reference key point further appears in the subsequently received stream key point information, the confidence coefficient of the reference key point can be improved, and the reference key point is added to the key point set under the condition that the confidence coefficient is higher than a certain threshold value, so that the dynamic update of the key point information in the target area is realized.

A complete implementation of the present application is described below in conjunction with fig. 11.

S1102, mark identification points and track fusion preprocessing;

specifically, first, mark recognition points are grouped, namely Mark of the same type continuously recognized by the same device in a period of time is grouped, and the point with the largest Mark frame is regarded as Mark point (best frame cutting point); then track fusion is carried out, tracks of the same intelligent device are put together and are connected in sequence according to the sequence of time, mark points and track points are arranged and fused according to the sequence of sampling time; if the same track points exist, the longitude and latitude of the track points are directly updated, otherwise, the track points are fused through interpolation; then deleting the abnormal track points and Mark points, for example deleting the track points or Mark points with the field missing and the value in the unreasonable field range;

s1104, a track adsorbs a road network, and a mapping relation between track points and Link is established;

in the step, the track and the road network are adsorbed, and the track and the road network are matched by adopting an HMM algorithm; obtaining a corresponding road network Link adsorbed by the track, and obtaining a time sequence Link string of the track; traversing the track to calculate the nearest Link of each track point; and obtaining the relation between the track points and the Link.

S1106, extracting Mark identification point information;

the extracted Mark identification point information comprises longitude and latitude of the Mark point, element type, confidence coefficient, image frame size and the like; simultaneously acquiring the entering and exiting directions of Mark, wherein the Mark point track passes through 60 meters (can be adjusted according to the requirement) before and after being used as an entering Link string and an exiting Link string, and if the Link exceeds 20m, rejecting short Link; meanwhile, removing Link in the crossing point;

s1108, dividing the dynamic quadtree grids based on the density, and mapping Mark identification points to each grid;

because Mark densities of different areas are different, as shown in fig. 8, the circumscribed rectangle of the whole area is divided into four branches according to the Mark densities to obtain a multi-level grid so as to reduce the data volume of later calculation; wherein the inter-cell size of the grid may be determined to be within a plurality of intervals within 200m-1600 m.

S1110, extracting real vector Mark recognition points based on hierarchical aggregation.

The Link sequences corresponding to the two key points can be sequentially compared by dividing the incoming Link strings of the two Mark according to the 'I', and sequentially comparing whether intersection exists with the incoming Link strings.

The merging mode is as follows:

wherein X is _new ，Y _new For the key point coordinates of the combined object key points, N indicates that the object key point a is generated by aggregation of N original object key points; m indicates that the object key points b are generated by aggregation of M original object key points. Marking the object key points a and b used by aggregation as used (i.e. not participating in subsequent merging operation), adding the newly generated object key points into a set, and continuing to calculate;

The real mode of the method can be applied to map road updating, and in the crowdsourcing acquisition process of equipment, the real position and vector information of Mark in the real world are extracted through algorithm processing based on the identification information of a large number of pieces of equipment identified on the end; it may also be applied to floating car track data mining, ship track data mining, applications involving the results of passing tracks and identifying information. In the related embodiment of the present application, the operations such as collecting and processing the related geographic information data all conform to the specification of the related normative file; and before the operations of collecting, processing and the like of the geographic information data, the authorization permission of the relevant main body is required to be obtained.

The above embodiment of the present application proposes a method for extracting a position of a real point of a vector element based on grid acceleration. Firstly, preprocessing vector information which is identified and reported by intelligent equipment, then carrying out grid division on a target area, projecting vector element points into grids, traversing the grids in sequence, calculating the data of the current grid and the data of a plurality of nearby grids to obtain two vector elements with consistent in-out direction and nearest distance, and then carrying out fusion to generate a new Mark and participating in subsequent calculation; the iteration is continued until a true vector Mark element is obtained. Therefore, the processing efficiency is effectively improved by dynamically dividing the area of the area to be processed; in addition, in the process of carrying out key point data processing by taking the subareas as a unit, object key points are combined and updated pairwise according to the combination condition, so that the problem that the acquisition of the object information of the existing road object is inaccurate is solved by combining the position information of a plurality of key points to update and combine the key point information under the condition that a plurality of terminals respectively acquire different object key points of the same road object is solved.

It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present invention is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present invention. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present invention.

According to another aspect of the embodiment of the present invention, there is also provided a processing apparatus for processing keypoint data for implementing the above processing method for keypoint data. As shown in fig. 12, the apparatus includes:

a first determining unit 1202, configured to determine a plurality of sub-regions from a target region according to a target region attribute of the target region, where a region area of the sub-regions is associated with the target region attribute;

an obtaining unit 1204, configured to obtain a set of keypoints matched by a first sub-region and at least one second sub-region adjacent to the first sub-region, where the set of keypoints includes a plurality of object keypoints, and each object keypoint is used to indicate a road object;

A second determining unit 1206 configured to determine, in a case where the first keypoint and the second keypoint satisfying the merging condition are included in the set of keypoints, target position information based on the first position information of the first keypoint and the second position information of the second keypoint;

the merging unit 1208 is configured to perform a merging operation on the first keypoint and the second keypoint in the keypoint set according to the target location information.

Optionally, the second determining unit 1206 further includes: a first obtaining module, configured to obtain, when a first key point type of the first key point and a second key point type of the second key point match, the first position information of the first key point and the second position information of the second key point; the second obtaining module is configured to obtain a first link identification sequence corresponding to the first key point and a second link identification sequence corresponding to the second key point when the distance between the first location information and the key point indicated by the second location information is less than or equal to a first distance threshold; and the determining module is used for determining that the first key point and the second key point meet the merging condition under the condition that an identification intersection exists between the first road section identification sequence and the second road section identification sequence.

Optionally, the first determining unit 1202 is configured to at least one of: determining a plurality of subareas from the target area according to the key point density of the target area, wherein the target area attribute comprises the key point density, and the area of the subareas has a negative correlation with the key point density; determining a plurality of subareas from the target area according to the traffic flow coefficient of the target area, wherein the target area attribute comprises the traffic flow coefficient, and the area of the subareas has a negative correlation with the traffic flow coefficient; and determining a plurality of subareas from the target area according to the road network density of the target area, wherein the target area attribute comprises the road network density, and the area of the subareas has a negative correlation with the road network density.

Optionally, the first determining unit 1202 is configured to: acquiring an circumscribed rectangular area matched with a target area; and performing quadtree division on the circumscribed rectangular region according to the target region attribute to determine a plurality of rectangular sub-regions, wherein the region area of the rectangular sub-regions is related to the target region attribute.

Optionally, the merging unit 1208 is configured to: acquiring first key point information of the first key point and second key point information of the second key point, wherein the first key point information comprises first key point attribute information and the first position information, and the second key point information comprises second key point attribute information and the second position information; determining third key point attribute information according to the first key point attribute information and the second key point attribute information, and taking the target position information as third key point position information; and adding a third key point in the key point set according to the third key point attribute information and the third key point position information.

Optionally, the merging unit 1208 is configured to: acquiring a first merging coefficient contained in first key point attribute information and a second merging coefficient contained in the second key point attribute information, wherein the first merging coefficient indicates that the first key points are merged according to a first number of original key points, and the second merging coefficient indicates that the second key points are merged according to a second number of original key points; and determining the target position information according to a weighted summation result of the first weight coefficient corresponding to the first merging coefficient and the first position information and a weighted summation result of the second weight coefficient corresponding to the second merging coefficient and the second position information.

Optionally, the merging unit 1208 is further configured to: when the third key point and the fourth key point which meet the merging condition are included in the key point set, determining reference position information according to third position information of the third key point and fourth position information of the fourth key point; combining the third key point and the fourth key point in the key point set according to the reference position information; when the two object keypoints satisfying the merging condition are not included in the set of keypoints, acquiring the set of keypoints matched by a third subregion and at least one fourth subregion adjacent to the third subregion from the plurality of subregions; and executing the merging operation on the object key points meeting the merging condition in the key point set.

Alternatively, in this embodiment, the embodiments to be implemented by each unit module may refer to the embodiments of each method described above, which are not described herein again.

According to still another aspect of the embodiment of the present invention, there is also provided an electronic device for implementing the above-mentioned method for processing key point data, where the electronic device may be a terminal device or a server as shown in fig. 13. The present embodiment is described taking the electronic device as a terminal device as an example. As shown in fig. 13, the electronic device comprises a memory 1302 and a processor 1304, the memory 1302 having stored therein a computer program, the processor 1304 being arranged to perform the steps of any of the method embodiments described above by means of the computer program.

Alternatively, in this embodiment, the electronic device may be located in at least one network device of a plurality of network devices of the computer network.

Alternatively, in the present embodiment, the above-described processor may be configured to execute the following steps by a computer program:

s1, determining a plurality of subareas from a target area according to the target area attribute of the target area, wherein the area of the subareas is related to the target area attribute;

s2, acquiring a key point set matched with a first sub-region and at least one second sub-region adjacent to the first sub-region, wherein the key point set comprises a plurality of object key points, and each object key point is used for indicating a road object;

S3, under the condition that the key point set comprises a first key point and a second key point which meet the combination condition, determining target position information according to the first position information of the first key point and the second position information of the second key point;

s4, merging the first key point and the second key point in the key point set according to the target position information.

Alternatively, it will be understood by those skilled in the art that the structure shown in fig. 13 is only schematic, and the electronic device may also be a vehicle-mounted terminal, a smart phone (such as an Android mobile phone, an iOS mobile phone, etc.), a tablet computer, a palm computer, a mobile internet device (Mobile Internet Devices, MID), a PAD, etc. Fig. 13 is not limited to the structure of the electronic device described above. For example, the electronic device may also include more or fewer components (e.g., network interfaces, etc.) than shown in FIG. 13, or have a different configuration than shown in FIG. 13.

The memory 1302 may be configured to store software programs and modules, such as program instructions/modules corresponding to the method and apparatus for processing key point data in the embodiment of the present invention, and the processor 1304 executes the software programs and modules stored in the memory 1302, thereby executing various functional applications and processing the key point data, that is, implementing the method for processing the key point data. Memory 1302 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 1302 may further include memory located remotely from processor 1304, which may be connected to the terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof. The memory 1302 may be used for storing, but is not limited to, file information such as observation data and motion state prediction results. As an example, as shown in fig. 13, the memory 1302 may include, but is not limited to, a first determining unit 1202, an acquiring unit 1204, a second determining unit 1206, and a merging unit 1208 in the processing apparatus including the above-described key point data. In addition, other module units in the processing device of the key point data may be included, but are not limited to, and are not described in detail in this example.

Optionally, the transmission device 1306 is configured to receive or transmit data via a network. Specific examples of the network described above may include wired networks and wireless networks. In one example, the transmission means 1306 comprises a network adapter (Network Interface Controller, NIC) which can be connected to other network devices and routers via network lines so as to communicate with the internet or a local area network. In one example, the transmission device 1306 is a Radio Frequency (RF) module for communicating wirelessly with the internet.

In addition, the electronic device further includes: a display 1308 for displaying the observation data and the motion state prediction result; and a connection bus 1310 for connecting the respective module components in the above-described electronic device.

Alternatively, in this embodiment, it will be understood by those skilled in the art that all or part of the steps in the methods of the above embodiments may be performed by a program for instructing a terminal device to execute the steps, where the program may be stored in a computer readable storage medium, and the storage medium may include: flash disk, read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), magnetic or optical disk, and the like.

The integrated units in the above embodiments may be stored in the above-described computer-readable storage medium if implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the technical solution of the present invention may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing one or more computer devices (which may be personal computers, servers or network devices, etc.) to perform all or part of the steps of the above-described method of the various embodiments of the present invention.

In the foregoing embodiments of the present invention, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.

In the present embodiment, the term "module" or "unit" refers to a computer program or a part of a computer program having a predetermined function and working together with other relevant parts to achieve a predetermined object, and may be implemented in whole or in part by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Also, a processor (or multiple processors or memories) may be used to implement one or more modules or units. Furthermore, each module or unit may be part of an overall module or unit that incorporates the functionality of the module or unit.

In several embodiments provided in the present application, it should be understood that the disclosed client may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of the units, such as the above, is merely a logical function division, and may be implemented in another manner, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.

The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.

Claims

1. A method for processing key point data, comprising:

determining a plurality of subareas from a target area according to the target area attribute of the target area, wherein the area of the subareas is related to the target area attribute;

acquiring a first sub-region and a key point set matched with at least one second sub-region adjacent to the first sub-region, wherein the key point set comprises a plurality of object key points, and each object key point is used for indicating a road object;

determining target position information according to first position information of the first key point and second position information of the second key point under the condition that the first key point and the second key point which meet the merging condition are included in the key point set;

and carrying out merging operation on the first key point and the second key point in the key point set according to the target position information.

2. The method of claim 1, wherein prior to obtaining the set of keypoints that match the first sub-region and at least one second sub-region adjacent to the first sub-region, further comprising:

acquiring a target key point set matched with the target area, wherein the target key point set comprises the object key points acquired by a plurality of terminals in the target area respectively;

under the condition that a target road network corresponding to the target area is obtained, matching is carried out according to the object key points included in the target key point set and road section information included in the target road network, wherein the road section information is used for indicating attribute information of a target road section in the target road network;

and determining a road section identification sequence corresponding to each object key point according to a matching result, wherein the road section identification sequence comprises at least two road section identifications, and the position relationship between the target road section indicated by the road section identifications and the corresponding object key points meets a matching condition.

3. The method according to claim 2, wherein, in the case that the set of keypoints includes a first keypoint and a second keypoint satisfying a merging condition, before determining target position information according to the first position information of the first keypoint and the second position information of the second keypoint, further comprising:

Acquiring the first position information of the first key point and the second position information of the second key point under the condition that the first key point type of the first key point is matched with the second key point type of the second key point;

acquiring a first road segment identification sequence corresponding to the first key point and a second road segment identification sequence corresponding to the second key point under the condition that the key point distance indicated by the first position information and the second position information is smaller than or equal to a first distance threshold value;

and under the condition that an identification intersection exists between the first road section identification sequence and the second road section identification sequence, determining that the first key point and the second key point meet the merging condition.

4. The method of claim 2, wherein the determining the link identification sequence corresponding to each of the object keypoints according to the matching result comprises:

acquiring an object track corresponding to the object key point, wherein the object track is a travel track corresponding to the terminal in the process of acquiring the object key point;

acquiring a reference identification sequence for indicating the object track;

And determining the road section identification sequence from the reference identification sequence, wherein the distance between the target road section indicated by the road section identification in the road section identification sequence and the object key point is smaller than or equal to a second distance threshold value.

5. The method of claim 4, further comprising at least one of the following before determining the segment identification sequence from the reference identification sequence:

acquiring key point position information of the object key points;

obtaining key point type information of the object key points, wherein the key point type information is used for indicating the object type of the road object;

and obtaining the key point confidence of the key point of the object, wherein the key point confidence is used for indicating the accuracy of the key point type information identified based on the key point of the object.

6. The method of claim 2, wherein the obtaining the set of target keypoints that match the target region comprises:

acquiring a reference key point set acquired by a target terminal in a target time period, wherein the reference key point set comprises reference key points acquired respectively at a plurality of key point acquisition times;

Acquiring a track point set of the target terminal in the target time period, wherein the track point set comprises terminal track points respectively acquired at a plurality of track point acquisition times;

under the condition that the reference key point set comprises a first reference key point with the key point acquisition time and the track point acquisition time matched, updating key point information of the first reference key point, and updating track point information of the corresponding terminal track point;

and under the condition that the reference key point set comprises a second reference key point with unmatched key point acquisition time and track point acquisition time, adding a reference terminal track point corresponding to the second reference key point in the track point set according to the key point information of the second reference key point.

7. The method of claim 1, wherein the determining a plurality of sub-regions from the target region based on target region attributes of the target region comprises at least one of:

determining a plurality of subareas from the target area according to the key point density of the target area, wherein the target area attribute comprises the key point density, and the area of the subareas has a negative correlation with the key point density;

Determining a plurality of subareas from the target area according to the traffic flow coefficient of the target area, wherein the target area attribute comprises the traffic flow coefficient, and the area of the subareas has a negative correlation with the traffic flow coefficient;

8. The method of claim 7, wherein determining a plurality of sub-regions from a target region based on target region attributes of the target region comprises:

acquiring an circumscribed rectangular area matched with a target area;

and carrying out quadtree division on the circumscribed rectangular region according to the target region attribute to determine a plurality of rectangular sub-regions, wherein the region area of the rectangular sub-regions is associated with the target region attribute.

9. The method of claim 1, wherein the merging the first keypoint and the second keypoint of the set of keypoints according to the target location information comprises:

Acquiring first key point information of the first key point and second key point information of the second key point, wherein the first key point information comprises first key point attribute information and first position information, and the second key point information comprises second key point attribute information and second position information;

determining third key point attribute information according to the first key point attribute information and the second key point attribute information, and taking the target position information as third key point position information;

and adding a third key point in the key point set according to the third key point attribute information and the third key point position information.

10. The method of claim 9, wherein the determining target location information from the first location information of the first keypoint and the second location information of the second keypoint comprises:

acquiring a first merging coefficient contained in first key point attribute information and a second merging coefficient contained in second key point attribute information, wherein the first merging coefficient indicates that the first key points are merged according to a first number of original key points, and the second merging coefficient indicates that the second key points are merged according to a second number of original key points;

And determining the target position information according to a weighted summation result of the first weight coefficient corresponding to the first merging coefficient and the first position information and a weighted summation result of the second weight coefficient corresponding to the second merging coefficient and the second position information.

11. The method of claim 9, wherein after the merging operation of the first keypoint and the second keypoint in the set of keypoints according to the target location information, further comprises:

determining reference position information according to third position information of a third key point and fourth position information of a fourth key point under the condition that the third key point and the fourth key point which meet the merging condition are included in a key point set; combining the third key point and the fourth key point in the key point set according to the reference position information;

acquiring a third sub-region and the key point set matched with at least one fourth sub-region adjacent to the third sub-region from a plurality of sub-regions under the condition that two object key points meeting the merging condition are not included in the key point set; and executing the merging operation on the object key points meeting the merging condition in the key point set.

12. The method of claim 1, wherein before determining the plurality of sub-regions from the target region according to the target region attribute of the target region, further comprises:

acquiring a road image sequence acquired by a target terminal in the driving process, wherein the road image sequence comprises a plurality of road images which are sequenced according to the sequence of acquisition time;

identifying a road object in the road image;

under the condition that at least one road image identifies a target road object, determining a target road image with the largest image area occupied by the target road object from at least one road image;

and determining the object key points according to the image information corresponding to the target road image, wherein the image information comprises image position information and acquisition time information.

13. The method of claim 1, wherein after the merging operation of the first keypoint and the second keypoint in the set of keypoints according to the target location information, further comprises:

acquiring reference position information of a reference key point under the condition that the reference key point acquired by a reference terminal in the target area is received;

Determining a reference subarea from a plurality of subareas according to the reference position information;

carrying out the merging operation on the reference key point and the fifth key point under the condition that a fifth key point meeting the merging condition with the reference key point is included in the reference key point set matched with the reference sub-region;

and under the condition that the reference key point set matched with the reference sub-region does not comprise the object key point meeting the merging condition with the reference key point, determining the reference key point as a candidate key point, and configuring candidate confidence coefficient for the candidate key point, wherein the candidate confidence coefficient is determined according to the number of the reference key points meeting the merging condition with the candidate key point.

14. A processing apparatus for key point data, comprising:

a first determining unit, configured to determine a plurality of sub-regions from a target region according to a target region attribute of the target region, where a region area of the sub-regions is associated with the target region attribute;

the road object acquisition unit is used for acquiring a key point set matched with a first sub-area and at least one second sub-area adjacent to the first sub-area, wherein the key point set comprises a plurality of object key points, and each object key point is used for indicating a road object;

A second determining unit configured to determine, in a case where a first key point and a second key point that satisfy a merging condition are included in the set of key points, target position information according to first position information of the first key point and second position information of the second key point;

and the merging unit is used for merging the first key point and the second key point in the key point set according to the target position information.

15. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored program, wherein the program when run performs the method of any one of claims 1 to 13.

16. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method according to any of the claims 1 to 13 by means of the computer program.