CN116753935A

CN116753935A - Map image processing and map making method, device, equipment and storage medium

Info

Publication number: CN116753935A
Application number: CN202310513028.4A
Authority: CN
Inventors: 马薇薇; 张羽; 宋二非; 颜言
Original assignee: Autonavi Software Co Ltd
Current assignee: Autonavi Software Co Ltd
Priority date: 2023-05-08
Filing date: 2023-05-08
Publication date: 2023-09-15

Abstract

The present disclosure relates to a map image processing and map making method, apparatus, device, and storage medium. In at least one embodiment of the present disclosure, an intersection type of a target intersection can be identified by a road network hooking shape of the target intersection in a map, and a target intersection anchor feature of the target intersection in a satellite image is obtained, then, in a target road image corresponding to a target historical vehicle track matched with the target intersection, of a candidate intersection with the target intersection type corresponding to the target intersection, the candidate intersection anchor feature corresponding to the candidate intersection is extracted, and further, whether the target intersection exists in the road image corresponding to the target historical vehicle track is determined based on a matching result of the candidate intersection anchor feature and the target intersection anchor feature, so that double identification of the target intersection in the target road image based on the intersection type and the intersection anchor feature is realized, misjudgment of the intersection image is avoided, quality of navigation data is improved, and accuracy of navigation service is improved.

Description

Map image processing and map making method, device, equipment and storage medium

Technical Field

The embodiment of the disclosure relates to the technical field of maps, in particular to a map image processing and map making method, a map image processing device, map image processing equipment and a map making storage medium.

Background

The navigation service is a service that is used by the object to be navigated at a high frequency when driving out, specifically, the navigation service may provide a plurality of recommended navigation routes for the object to be navigated according to a starting point position and a destination position of the object to be navigated, and before the recommended navigation routes are performed for the object to be navigated, a navigation route for guiding the object to be navigated to travel from the starting point position to the destination position is generally generated for the object to be navigated based on map data of each map pre-marker.

At present, in the process of pre-marking map data of roads near a certain intersection in a map, the type of the intersection in the map is generally determined, then an intersection image with the same intersection type is found based on road image data collected by vehicles passing through the intersection in a history way, and further the map data is marked based on the intersection image. However, once the intersection image is judged to be wrong, the marked map data is wrong, the navigation data quality is seriously affected, and then the navigation service is wrong, so that the risks of detour, violation and the like of the vehicle are caused.

Disclosure of Invention

At least one embodiment of the present disclosure provides a map image processing and map making method, apparatus, device and storage medium.

In a first aspect, an embodiment of the present disclosure proposes a map image processing method, including:

based on the road network hooking shape of the target intersection in the map, identifying the intersection type of the target intersection to obtain the target intersection type corresponding to the target intersection;

acquiring the anchor point characteristics of a target intersection in a satellite image;

under the condition that a first intersection of a target intersection type exists in a target road image, extracting a first intersection anchor point characteristic corresponding to the first intersection from the target road image, wherein the target road image is a road image corresponding to a target historical driving track matched with the target intersection;

and determining whether the target intersection exists in the road image corresponding to the target historical driving track based on the matching result of the candidate intersection anchor characteristic and the target intersection anchor characteristic.

In a second aspect, an embodiment of the present disclosure further provides a map making method, including:

in the case where it is determined according to the map image processing method of the first aspect that the target intersection exists in the road image corresponding to the target historical track, a map corresponding to the target intersection is created according to the target road image, and the map is marked with map data corresponding to the target intersection.

In a third aspect, an embodiment of the present disclosure further proposes a map image processing apparatus, including:

the first subunit is used for identifying the type of the target intersection based on the road network hooking shape of the target intersection in the map, so as to obtain the type of the target intersection corresponding to the target intersection;

the second subunit is used for acquiring the anchor point characteristics of the target intersection in the satellite image;

the third subunit is used for extracting a first intersection anchor point characteristic corresponding to a first intersection from the target road image under the condition that the first intersection of the target intersection type exists in the target road image, wherein the target road image is a road image corresponding to a target historical driving track matched with the target intersection;

and the fourth subunit is used for determining whether the target intersection exists in the road image corresponding to the target historical driving track based on the matching result of the candidate intersection anchor characteristic and the target intersection anchor characteristic.

In a fourth aspect, an embodiment of the present disclosure further provides a map making apparatus, including:

a fifth subunit, configured to, when it is determined by the map image processing apparatus according to the third aspect that the target intersection exists in the road image corresponding to the target historical track, make a map corresponding to the target intersection according to the target road image, where the map is marked with map data corresponding to the target intersection.

In a fifth aspect, embodiments of the present disclosure further propose an electronic device, including a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to implement the steps of the map image processing method according to any embodiment of the first aspect or the map making method according to the second aspect.

In a sixth aspect, embodiments of the present disclosure further provide a computer-readable storage medium, where the computer-readable storage medium stores a program or instructions that cause a computer to perform the steps of the map image processing method according to any one of the embodiments of the first aspect or the map making method according to the second aspect.

In a seventh aspect, embodiments of the present disclosure also provide a computer program product comprising computer instructions which, when executed by a processor, implement the steps of the map image processing method according to any of the embodiments of the first aspect or the map making method according to the second aspect.

It can be seen that in at least one embodiment of the present disclosure, by means of a road network hooking shape of a target intersection in a map, an intersection type of the target intersection can be identified, and a target intersection anchor feature of the target intersection in a satellite image is obtained, after the target intersection belonging to the target intersection type is identified and the target intersection anchor feature corresponding to the target intersection is obtained, the candidate intersection anchor feature corresponding to the candidate intersection is extracted from a target road image corresponding to a target historical vehicle track matching the target intersection, which is a candidate intersection type, and further, whether the target intersection exists in the road image corresponding to the target historical vehicle track is determined based on a matching result of the candidate intersection anchor feature and the target intersection anchor feature, so that double identification of the target intersection in the target road image based on the intersection type and the intersection anchor feature is realized, error judgment of the intersection image is avoided, accuracy of pre-marked map data and quality of navigation data are improved, and accuracy of navigation service is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present disclosure, and other drawings may be obtained according to these drawings to those of ordinary skill in the art.

Fig. 1 is a schematic diagram of a map with intersections according to an embodiment of the disclosure;

FIG. 2 is a schematic diagram of a road image according to an embodiment of the disclosure;

fig. 3 is a flowchart of a map image processing method according to an embodiment of the disclosure;

FIG. 4 is a schematic view of a satellite image according to an embodiment of the disclosure;

fig. 5 is a flowchart of another map image processing method according to an embodiment of the disclosure;

FIG. 6 is a schematic view of another satellite image according to an embodiment of the disclosure;

fig. 7 is a flowchart of yet another map image processing method according to an embodiment of the disclosure;

FIG. 8 is a schematic illustration of another map of existing intersections provided by an embodiment of the present disclosure;

FIG. 9 is a schematic diagram of another road image provided by an embodiment of the present disclosure;

Fig. 10 is a schematic diagram of a map image processing apparatus according to an embodiment of the present disclosure;

FIG. 11 is a schematic diagram of a map making apparatus according to an embodiment of the present disclosure;

fig. 12 is an exemplary block diagram of an electronic device provided by an embodiment of the present disclosure.

Detailed Description

In order that the above-recited objects, features and advantages of the present disclosure may be more clearly understood, a more particular description of the disclosure will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. It is to be understood that the described embodiments are some, but not all, of the embodiments of the present disclosure. The specific embodiments described herein are to be considered in an illustrative rather than a restrictive sense. All other embodiments derived by a person of ordinary skill in the art based on the described embodiments of the present disclosure fall within the scope of the present disclosure.

It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.

Currently, in the process of pre-marking map data of roads near a certain intersection in a map, the intersection type of the intersection can be confirmed according to the road network hooking shape of the intersection to be judged in the map, as shown in fig. 1, the intersection to be judged in the frame in fig. 1 is the intersection to be judged, and the intersection type of the intersection can be confirmed to be a right-side hooking T-shaped intersection based on the road network hooking shape of the intersection in the map in fig. 1. Then, the road image data collected by the vehicles passing through the road junction in the history is shown in fig. 2, and the road image data collected by the vehicles passing through the road junction in the history can be identified in fig. 2. Thus, the marking of map data such as map road marking data can be performed based on the intersection image.

However, since the data track of the road image data may have an offset, the intersection image may be misjudged, and once the intersection image is misjudged, the pre-marked map data such as an error may seriously affect the quality of the navigation data, thereby causing an error of the navigation service.

The embodiment of the disclosure provides a map image processing and map making method, device, equipment or storage medium, which can realize double identification of a target intersection in a target road image based on intersection type and intersection anchor point characteristics, and can avoid judgment errors of the intersection image caused by historical vehicle track deviation of a reference image, so that the accuracy of pre-marked map data and the quality of navigation data are improved, and the accuracy of navigation service is improved.

Fig. 3 is a schematic flow chart of a map image processing method provided by an embodiment of the present disclosure, where an execution body of the map image processing method is an electronic device, and the electronic device includes, but is not limited to, a vehicle-mounted device, a desktop computer, a notebook computer, an all-in-one machine, a server, and the like, where the server may be an independent server, or may be a cluster of multiple servers, or may include a server built locally and a server erected at a cloud.

As shown in fig. 3, the map image processing method may include, but is not limited to, steps 302 to 308:

in step 302, based on the road network hooking shape of the target intersection in the map, the intersection type of the target intersection is identified, and the target intersection type corresponding to the target intersection is obtained.

The target intersection may be an intersection to be pre-marked with map data. The map may be a pre-collected road network map including the target intersection, where the road network map has a preset map scale and a preset map range. The preset map scale and the preset map range may be determined as needed, and are not limited herein.

In the embodiment of the disclosure, when the electronic device needs to match the intersection image of the target intersection, the electronic device can firstly identify the shape of the target intersection in the map, extract the road network hooking shape of the target intersection in the map, and then identify the intersection type of the target intersection based on the road network hooking shape of the target intersection in the map, so as to obtain the target intersection type corresponding to the target intersection.

Specifically, the electronic device may obtain a shape feature of the road network hooking shape after extracting the road network hooking shape of the target intersection in the map, and use the intersection type corresponding to the shape feature as the target intersection type corresponding to the target intersection, so as to implement intersection type identification of the target intersection.

Alternatively, the intersection types may include left-hand-hook T-junctions, right-hand-hook T-junctions, crossroads, main road entrances, main road exits, etc., without limitation.

Wherein, different crossing types can be associated with the shape characteristics of different road network hanging shapes in advance. For example, a left-hand-hitching T-junction may be associated with a shape feature that is T-shaped on the left side of the road, a right-hand-hitching T-junction may be associated with a shape feature that is T-shaped on the right side of the road, and so on.

Continuing to show in fig. 1, the framed intersection is the target intersection, the shape characteristic of the road network hooking shape can be confirmed to be the right side of the road and the intersection shape is T-shaped based on the road network hooking shape of the target intersection in the map in fig. 1, the intersection type corresponding to the shape characteristic can be confirmed to be the right side hooking T-shaped intersection, and the target intersection type corresponding to the target intersection is confirmed to be the right side hooking T-shaped intersection.

In step 304, the anchor point characteristics of the target intersection in the satellite image are obtained.

The satellite image may be a satellite image corresponding to the target intersection, and specifically may be a reference satellite image which is acquired in advance, includes the target intersection image, has a preset image proportion and a preset image range. The preset image proportion and the preset image range can be determined according to the needs, and are not limited herein.

In some embodiments, step 304 may specifically include: acquiring satellite images corresponding to the target intersections; and carrying out image analysis on the satellite image, and extracting the anchor point characteristics of the target intersection displayed in the satellite image.

The electronic device can acquire a satellite image corresponding to the latest updated target intersection, and conduct image analysis on the satellite image by utilizing a pre-trained image analysis model so as to extract the anchor point characteristics of the target intersection corresponding to the target intersection.

In other embodiments, the electronic device or other devices may also perform image analysis on the satellite image by using a pre-trained image analysis model, and pre-offline extract the target intersection anchor feature corresponding to the target intersection, so that the electronic device may directly obtain the target intersection anchor feature corresponding to the target intersection that has been manufactured offline.

In the disclosed embodiments, the target intersection anchor characteristics may include characteristics of at least one anchor type of: the anchor characteristics of the building, the point of interest POI, the road traffic facility, i.e. the target intersection may comprise anchor characteristics related to the target intersection of at least one anchor type of building, POI, road traffic facility, etc. The anchor point characteristics of the road traffic facility type can comprise facilities such as ground line type, road shape, building blocks and the like, the anchor point characteristics of the ground line type can comprise zebra stripes, guide lines, grid lines, triangular belts, diamond blocks and the like, and the anchor point characteristics of the road shape type can comprise special road shapes, bridges and the like.

As shown in fig. 4, in the case where the electronic device extracts the target intersection anchor feature corresponding to the target intersection online, the electronic device may identify that a diamond exists near the target intersection 401 in the satellite image, so that the diamond is used as the target intersection anchor feature corresponding to the target intersection.

In step 306, in the case that a candidate intersection of the target intersection type exists in the target road image, candidate intersection anchor point features corresponding to the candidate intersection are extracted from the target road image.

The target road image is a road image corresponding to a target historical driving track matched with the target intersection.

In some embodiments, the electronic device may screen at least one target historical vehicle track matching the target intersection from among the plurality of historical vehicle tracks. The historical driving track is a track line formed by connecting a plurality of position points of a road image acquired by a vehicle acquired by a GPS track recorder, and each position point at least comprises date, time, longitude, latitude and other information.

Specifically, the electronic device may calculate the matching degree of each historical driving track and the target intersection, for example, calculate the matching degree of each historical driving track and the target intersection based on the information of each position point of the historical driving track, and then use the historical driving track with the matching degree meeting the preset matching condition as the target historical driving track.

The preset matching condition may be that the matching degree is highest, or the matching degree reaches a preset degree threshold. The preset degree threshold may be set as needed, and is not limited herein.

Under the condition that the preset matching condition is the highest matching degree, the electronic equipment can screen out a historical track of the item mark; under the condition that the preset matching condition is that the matching degree reaches the preset degree threshold, the electronic equipment can screen out at least one item of history driving track.

Since the historical driving locus is a trajectory line formed by connecting a plurality of position points for collecting road images, each target historical driving locus can correspond to a plurality of road images.

Further, the electronic device may select at least one target road image from a plurality of road images corresponding to the target historical driving track, or all road images corresponding to the target historical driving track are all used as target road images, and extract candidate intersection anchor points corresponding to candidate intersections from each target road image respectively.

Under the condition that the electronic equipment selects at least one target road image from a plurality of road images corresponding to the target historical driving track, the electronic equipment can select one road image with the nearest distance between the position point and the target intersection as the target road image, and can also select at least one road image with the distance between the position point and the target intersection within a preset distance range as the target road image respectively. The preset distance range may be set as needed, and is not limited herein.

In the embodiment of the disclosure, the electronic device can identify whether the candidate intersection of the target intersection type exists in the road image corresponding to the target historical driving track under the condition that the target intersection anchor point characteristic corresponding to the target intersection is extracted.

If the target road image is one, under the condition that candidate intersections of the target intersection type exist in the target road image, carrying out image recognition on the target road image by utilizing a pre-trained image recognition model, and extracting candidate intersection anchor point characteristics corresponding to the candidate intersections; and under the condition that the candidate intersection of the target intersection type does not exist in the target road image, determining that the target intersection does not exist in the target road image.

If the number of the target road images is multiple, under the condition that a candidate intersection of a target intersection type exists in any one of the target road images, performing image recognition on the target road image with the candidate intersection by utilizing a pre-trained image recognition model, and extracting candidate intersection anchor point characteristics corresponding to the candidate intersection; and under the condition that candidate intersections of the target intersection type do not exist in the target road image, determining that the target intersection does not exist in the target road image.

Specifically, the candidate intersection anchor point features may include anchor point features related to the candidate intersection, which are at least one anchor point type of buildings, POIs, road traffic facilities, and the like, and are not described herein.

Continuing to show in fig. 2, the candidate intersection of the target intersection type in the target road image is the framed intersection, and the candidate intersection anchor point of the candidate intersection is characterized by a zebra crossing.

In step 308, based on the matching result of the candidate intersection anchor feature and the target intersection anchor feature, it is determined whether the target intersection exists in the road image corresponding to the target historical driving track.

In the embodiment of the disclosure, after the candidate intersection anchor point characteristics corresponding to the candidate intersection are extracted, the electronic equipment can judge whether the candidate intersection anchor point characteristics are matched with the target intersection anchor point characteristics, and further determine whether the target intersection exists in the road image corresponding to the target historical driving track based on the matching result of the candidate intersection anchor point characteristics and the target intersection anchor point characteristics, so that double identification of the target intersection in the target road image based on the intersection type and the intersection anchor point characteristics is realized.

Specifically, step 308 may specifically include:

in some embodiments, if the matching result is that the candidate intersection anchor feature matches the target intersection anchor feature, determining that the target intersection exists in the road image corresponding to the target historical driving track.

Optionally, if the target road image with the candidate intersection is one, if the matching result is that the candidate intersection anchor point feature is matched with the target intersection anchor point feature, determining that the target intersection exists in the road image corresponding to the target historical driving track, indicating that the track is available, and continuing the task of identifying the intersection of the track.

Optionally, if there are multiple target road images of the candidate intersection, if any candidate intersection anchor feature is matched with the target intersection anchor feature, determining that a target intersection exists in the road image corresponding to the target historical driving track, which indicates that the track is available, and continuing the task of identifying the intersection of the track.

In other embodiments, if the matching result is that the candidate intersection anchor feature does not match the target intersection anchor feature, it is determined that the target intersection does not exist in the road image corresponding to the target historical driving track.

Optionally, if the target road image with the candidate intersection is one, if the candidate intersection anchor point characteristic is not matched with the target intersection anchor point characteristic, determining that the target intersection does not exist in the road image corresponding to the target historical driving track, indicating that the track is not available, and ending the intersection identification task of the track.

Optionally, if there are multiple target road images of the candidate intersection, if all the candidate intersection anchor characteristics are not matched with the target intersection anchor characteristics, determining that no target intersection exists in the road images corresponding to the target historical driving track, indicating that the track is not available, and ending the task of identifying the intersection of the track.

Further, the electronic device can judge whether the candidate intersection anchor feature is matched with the target intersection anchor feature by judging whether the candidate intersection anchor feature is identical with the target intersection anchor feature.

As further shown in fig. 2 and fig. 4, the target intersection anchor point feature of the target intersection 401 in the satellite image is a diamond, the candidate intersection anchor point feature of the candidate intersection in the target road image is a zebra crossing, and the candidate intersection anchor point feature and the target intersection anchor point feature are different, so that the candidate intersection anchor point feature is not matched with the target intersection anchor point feature, it can be determined that the target intersection does not exist in the road image corresponding to the target historical driving track, and the target historical driving track is unavailable.

In the above embodiment, the intersection type of the target intersection can be identified through the intersection hanging shape of the target intersection in the map, the target intersection anchor point characteristic of the target intersection in the satellite image is obtained, after the target intersection belonging to the target intersection type is identified and the target intersection anchor point characteristic corresponding to the target intersection is obtained, the candidate intersection anchor point characteristic corresponding to the candidate intersection is extracted from the target road image corresponding to the target historical driving track matched with the target intersection of the candidate intersection type, and further, whether the target intersection exists in the road image corresponding to the target historical driving track is determined based on the matching result of the candidate intersection anchor point characteristic and the target intersection anchor point characteristic, so that double identification of the target intersection in the target road image based on the intersection type and the intersection anchor point characteristic is realized, judgment errors of the intersection image are avoided, and accuracy of pre-marked map data and quality of navigation data are improved, thereby accuracy of navigation service is improved.

In some embodiments of the present disclosure, after the step of determining that the target intersection exists in the road image corresponding to the target historical driving locus, the method may further include the steps of:

marking a target intersection in the target road image;

and identifying map data corresponding to the target intersection based on the marked target road image.

Specifically, the electronic device may detect a position of a candidate intersection having a candidate intersection anchor feature in a target road image in which the candidate intersection anchor feature matching the target intersection anchor feature is detected, mark a target intersection frame corresponding to the target intersection in the target road image based on the position, and further identify map data corresponding to the target intersection based on the marked target road image.

In some embodiments, the electronic device may identify image content within a preset image range around the target intersection frame, to obtain map data within the intersection range of the target intersection.

In other embodiments, the electronic device may also send the marked target road image to other devices, which identify map data for the target intersection in the intersection range based on the marked target road image, either by other devices or manually.

Wherein the map data is used to assist in generating the navigation route. For example, before a recommended navigation route is made for a navigation object, a navigation route for guiding the navigation object to travel from a start position to a destination position is generated for the navigation object based on map data.

The map data may include traffic marking information, marking prohibition information, and the like, among others. The traffic markings (e.g., double Huang Shixian) may be marked with markings that are not straddlable.

Therefore, in the above embodiment, the electronic device can more accurately identify and judge the road junction image, and further can accurately identify the map data corresponding to the target road junction based on the road junction image with high accuracy, thereby improving the accuracy of the navigation service.

In other embodiments of the present disclosure, after step 304, the electronic device may not be able to extract the target intersection anchor feature corresponding to the target intersection, where the electronic device may not be able to extract the target intersection anchor feature corresponding to the target intersection, further obtain the distance between the target intersection and the front-rear intersection in the map, extract the intersection shape feature of the candidate intersection from the target road image and/or determine the distance between the candidate intersection and the front-rear intersection in the case that the candidate intersection of the target intersection type exists in the target road image, then compare the road network hooking shape of the target intersection with the intersection shape feature of the candidate intersection, and/or compare the distance between the target intersection and the front-rear intersection with the distance between the candidate intersection and the front-rear intersection, so as to determine whether the candidate intersection is the same intersection as the target intersection, avoid an intersection image determining error, and improve the accuracy of the pre-marked map data and the quality of the navigation data, thereby improving the accuracy of the navigation service.

Based on the above embodiments, the scenario that other intersections with the same type as the target intersection exist in the satellite image is not considered, and for this scenario, fig. 5 is a schematic flow chart of another image processing method provided in the embodiment of the present disclosure, as shown in fig. 5, including steps 502 to 512:

in step 502, based on the road network hooking shape of the target intersection in the map, the intersection type of the target intersection is identified, and the target intersection type corresponding to the target intersection is obtained.

In step 504, a target intersection anchor feature of the target intersection in the satellite image is obtained.

In step 506, if there is a candidate intersection of the target intersection type in the target road image, candidate intersection anchor point features corresponding to the candidate intersection are extracted from the target road image, where the target road image is a road image corresponding to a target historical driving track matched with the target intersection.

Steps 502 to 506 are similar to steps 302 to 306 in the embodiment shown in fig. 3, and will not be described here.

In step 508, under the condition that other intersections other than the target intersection exist in the satellite image, other intersection anchor points corresponding to other intersections are obtained, wherein the other intersections belong to the target intersection type.

In the embodiment of the disclosure, the electronic device may further identify whether other intersections belonging to the target intersection type other than the target intersection exist in the satellite image, if so, acquire other intersection anchor characteristics corresponding to the other intersections from the satellite image, or not perform acquiring other intersection anchor characteristics corresponding to the other intersections.

In some embodiments, the step of obtaining the anchor point characteristics of other intersections corresponding to other intersections may specifically include: and carrying out image analysis on the satellite images, and extracting anchor point characteristics of other intersections corresponding to other intersections.

The electronic device can acquire a satellite image corresponding to the latest updated target intersection, and conduct image analysis on the satellite image by utilizing a pre-trained image analysis model so as to extract anchor point characteristics of other intersections corresponding to other intersections.

Optionally, the electronic device may use an image analysis model different from the extraction of the target intersection anchor feature to extract other intersection anchor features corresponding to other intersections, or may use one image analysis model to simultaneously extract the target intersection anchor feature and other intersection anchor features, which is not limited herein.

In other embodiments, the electronic device or other devices may perform image analysis on the satellite image by using a pre-trained image analysis model, and extract other intersection anchor features corresponding to other intersections offline in advance, so that the electronic device may directly obtain other intersection anchor features corresponding to other intersections that have been manufactured offline.

In particular, other intersection anchor characteristics may include characteristics of at least one anchor type of: buildings, POIs, road traffic facilities are not described in detail herein.

As shown in fig. 6, the electronic device may identify that a diamond exists near a target intersection 601 in the satellite image, so that the diamond is used as a target intersection anchor feature corresponding to the target intersection, and identify that another intersection 602 in the satellite image, which is connected to the T-type intersection on the other right side, has a zebra crossing on the other intersection 602, so that the zebra crossing is used as another intersection anchor feature corresponding to the other intersection.

In step 510, it is determined whether the target intersection exists in the road image corresponding to the target historical driving locus based on the matching result of the candidate intersection anchor feature and the target intersection anchor feature.

Step 510 is similar to step 308 of the embodiment shown in fig. 3, and will not be described herein.

In step 512, if the candidate intersection anchor feature matches the other intersection anchor feature in the case that the target intersection does not exist in the target road image, it is determined that the target historical vehicle track has an offset in the target direction, where the target direction is a direction of the target intersection determined based on the track advancing direction of the target historical vehicle track in the satellite image relative to the second intersection.

In the embodiment of the disclosure, after determining that the target intersection does not exist in the road image corresponding to the target historical driving track, the electronic device may further determine whether the candidate intersection anchor feature is matched with other intersection anchor features. If the candidate intersection anchor point characteristic is matched with other intersection anchor point characteristics, the fact that only one intersection belonging to the type of the target intersection exists in the road image corresponding to the target historical driving track, the intersection is other intersections except the target intersection is indicated, and further the target direction of the target intersection in the satellite image relative to other intersections can be determined based on the track advancing direction of the target historical driving track, and the deviation of the target historical driving track in the target direction is determined.

As further shown in fig. 2 and 6, the target intersection anchor feature of the target intersection 601 in the satellite image is a diamond, the candidate intersection anchor feature of the candidate intersection in the target road image is a zebra crossing, and the candidate intersection anchor feature and the target intersection anchor feature are not matched if the candidate intersection anchor feature and the target intersection anchor feature are different, so that it can be determined that the target intersection does not exist in the road image corresponding to the target historical driving track, and the target historical driving track is unavailable. Further, other intersection anchor points of other intersections 602 in the satellite image are zebra crossings, candidate intersection anchor points of candidate intersections in the target road image are zebra crossings, the candidate intersection anchor points are matched with the other intersection anchor points if the candidate intersection anchor points are the same, and the track advancing direction of the target historical track can be determined to be the direction from the target intersection to the other intersections in the satellite image based on the information of each position point of the target historical track, so that the longitudinal downward offset of the target historical track can be determined.

Therefore, in the above embodiment, the electronic device not only can more accurately recognize and judge the road image, but also can automatically determine the reject cause under the condition of rejecting the road image corresponding to the target historical track, thus providing a basis for subsequent root cause review.

On the basis of the above embodiment, a scene in which the number of intersections with the same intersection type in the map is different from the number of matched intersections identified in the road image is not considered, and for this scene, fig. 7 is a schematic flow diagram of still another image processing method provided in the embodiment of the present disclosure, as shown in fig. 7, including steps 702 to 712:

in step 702, the intersection type of the target intersection is identified based on the road network hooking shape of the target intersection in the map, so as to obtain the target intersection type corresponding to the target intersection.

Step 702 is similar to step 302 in the embodiment shown in fig. 3, and will not be described herein.

In step 704, the number of intersections having a road network hitching shape is detected in the map.

In the embodiment of the disclosure, after extracting the road network hooking shape of the target intersection in the map, the electronic device may further identify the intersection with the road network hooking shape in the map, so as to obtain the number of intersections with the road network hooking shape.

In some embodiments, the electronic device may identify, on a target road to which the target intersection belongs in the map, the number of intersections having the intersection hanging shape within a preset distance centered on the target intersection. The preset distance may be set as needed, and is not limited herein.

In other embodiments, the electronic device may identify the number of intersections having the road network-attached shape on the target road to which the target intersection belongs in the map.

In step 706, the target intersection anchor feature of the target intersection in the satellite image is obtained.

In step 708, if there is a candidate intersection of the target intersection type in the target road image, candidate intersection anchor characteristics corresponding to the candidate intersection are extracted from the target road image, where the target road image is a road image corresponding to a target historical vehicle track matched with the target intersection.

Steps 706 to 708 are similar to steps 304 to 306 in the embodiment shown in fig. 3, and will not be described here.

In step 710, it is determined whether the target intersection exists in the road image corresponding to the target historical track based on the matching result of the candidate intersection anchor feature and the target intersection anchor feature and the comparison result of the number of candidate intersections and the number of intersections.

In the embodiment of the disclosure, after the electronic equipment extracts the candidate intersection anchor point characteristics corresponding to the candidate intersection, the electronic equipment can judge whether the candidate intersection anchor point characteristics are matched with the target intersection anchor point characteristics, and if the matching result is that the candidate intersection anchor point characteristics are not matched with the target intersection anchor point characteristics, the electronic equipment determines that the target intersection does not exist in the road image corresponding to the target historical driving track; if the matching result is that the candidate intersection anchor point characteristic is matched with the target intersection anchor point characteristic, the number of the candidate intersections is further compared with the number of the intersections, whether the target intersections exist in the road image corresponding to the target historical driving track is further determined according to the comparison result of the number of the candidate intersections and the number of the intersections, and triple identification of the target intersections in the target road image based on the types of the intersections, the intersection anchor point characteristic and the number of the intersections is achieved.

In some embodiments, if the matching result is that the candidate intersection anchor feature matches the target intersection anchor feature, and the number of candidate intersections existing in the target road image is the same as the number of intersections, determining that the target intersection exists in the road image corresponding to the target historical driving track.

Optionally, if the target road image with the candidate intersection is one, if the candidate intersection anchor feature in the target road image is matched with the target intersection anchor feature, and the number of the candidate intersections with the candidate intersection anchor feature in the target road image is the same as the number of the intersections with the road network hanging shape in the map, determining that the target intersection exists in the road image corresponding to the target historical driving track, indicating that the track is available, and continuing the task of identifying the intersection of the track.

Optionally, if there are multiple target road images of the candidate intersection, if the candidate intersection anchor feature in at least one target road image is matched with the target intersection anchor feature, and the candidate intersection anchor feature and the candidate intersection with the candidate intersection anchor feature are de-duplicated, the number of the remaining candidate intersections with the candidate intersection anchor feature is the same as the number of intersections with the intersection hanging shape in the map, then it is determined that there are target intersections in the road image corresponding to the target historical driving track, it is indicated that the track is available, and the task of identifying the intersection of the track can be continued.

For example, the target intersection anchor point feature of the target intersection in the satellite image is a diamond, the candidate intersection anchor point feature of the candidate intersection in the target road image is a diamond, the candidate intersection anchor point feature and the target intersection anchor point feature are the same, the candidate intersection anchor point feature is matched with the target intersection anchor point feature, only one candidate intersection with the anchor point feature being the diamond exists in the road image corresponding to the target historical driving track, and only one target intersection belonging to the right-side hanging T-shaped intersection exists in the map, the target intersection exists in the road image corresponding to the target historical driving track, the fact that the track is available is indicated, and the task of identifying the intersection of the track can be continued.

In other embodiments, if the matching result is that the candidate intersection anchor feature matches the target intersection anchor feature, but the number of candidate intersections in the target road image is different from the number of intersections, determining whether the target intersection exists in the road image corresponding to the target historical driving track according to the road network related attribute of the target intersection in the map.

Optionally, if the number of the candidate intersections in the target road image is different from the number of the intersections in the map, which have the shape of the road network, if the candidate intersection anchor feature in the target road image matches the target intersection anchor feature, it is impossible to determine whether the target intersection exists in the road image corresponding to the target historical driving track, and further judgment is needed.

Optionally, if there are multiple candidate road images of the candidate intersection, if the candidate intersection anchor feature in at least one of the target road images is matched with the target intersection anchor feature, and after the candidate intersection anchor feature and the candidate intersection with the candidate intersection anchor feature are de-duplicated, the number of the remaining candidate intersections with the candidate intersection anchor feature is different from the number of intersections with the intersection hanging shape in the map, it is not possible to determine whether there are target intersections in the road image corresponding to the target historical driving track, and further judgment is needed.

In one example, the target intersection anchor point feature of the target intersection in the satellite image is a diamond, the candidate intersection anchor point feature of the candidate intersection in the target road image is a diamond, and the two candidate intersection anchor point features are the same, the candidate intersection anchor point feature is matched with the target intersection anchor point feature, but only one candidate intersection with the anchor point feature being the diamond exists in the road image corresponding to the target historical driving track, and as shown in fig. 8, two intersections belonging to the right-side hanging T-shaped intersection exist in the map, whether the target intersection exists in the road image corresponding to the target historical driving track cannot be determined, and further judgment is needed.

In another example, the target intersection anchor point feature of the target intersection in the satellite image is a diamond, the candidate intersection anchor point feature of the candidate intersection in the target road image is a diamond, and the candidate intersection anchor point feature and the target intersection anchor point feature are the same, so that the candidate intersection anchor point feature is matched with the target intersection anchor point feature, but as shown in fig. 9, two candidate intersections with the anchor point feature of the diamond exist in the road image corresponding to the target historical driving track, and only one intersection belonging to the right-side hanging T-shaped intersection exists in the map, so that whether the target intersection exists in the road image corresponding to the target historical driving track cannot be determined, and further judgment is needed.

Further, under the condition that whether the target intersection exists in the road image corresponding to the target historical driving track cannot be determined, the electronic device can determine whether the target intersection exists in the road image corresponding to the target historical driving track based on the road network related attribute of the target intersection in the map.

In some embodiments, the electronic device may acquire a road network related attribute of a target intersection carried by the map in the map, identify image contents within an intersection range of candidate intersections in the detected target road images of candidate intersection anchor features matched with the target intersection anchor features, so as to determine whether the intersection related attribute of the candidate intersection with the same road network related attribute exists, if so, determine the candidate intersection to which the intersection related attribute of the candidate intersection with the same road network related attribute belongs as the target intersection, and determine that the target intersection exists in the road image corresponding to the target historical driving track.

In other embodiments, the electronic device may further send the road image corresponding to the target historical driving track to other devices, and the other devices or the people determine whether the target intersection exists in the road image corresponding to the target historical driving track based on the road network related attribute of the target intersection in the map.

In particular, the road network related attribute and the intersection related attribute may include a building, a POI, whether the intersection is a closed intersection, and the like, without limitation.

In some embodiments of the present disclosure, after the electronic device detects the number of intersections with the road network hitching shape in the map in step 704, if the number of intersections is multiple, the electronic device may further extract the intersection anchor feature corresponding to the corresponding intersection from the satellite images corresponding to the intersections with the respective specific road network hitching shapes, and screen out the number of intersections with the intersection anchor feature identical to the target intersection anchor feature.

Further, after the candidate intersection anchor point characteristics corresponding to the candidate intersection are extracted, the electronic device can judge whether the candidate intersection anchor point characteristics are matched with the target intersection anchor point characteristics.

If the candidate road image with the candidate intersection is one, if the candidate intersection anchor point characteristic in the target road image is matched with the target intersection anchor point characteristic, and the number of the candidate intersections with the candidate intersection anchor point characteristic in the target road image is the same as the number of the intersections obtained by screening, determining that the target intersection exists in the road image corresponding to the target historical driving track, indicating that the track is available, and continuing the task of identifying the intersection of the track.

If the number of the candidate intersections in the target road image is different from the number of the intersections obtained by screening, whether the target intersections exist in the road image corresponding to the target historical driving track cannot be determined, and further judgment is needed.

If the number of the target road images with the candidate intersections is multiple, if the candidate intersection anchor point characteristics in at least one target road image are matched with the target intersection anchor point characteristics, and after the candidate intersection anchor point characteristics and the candidate intersections with the candidate intersection anchor point characteristics are de-duplicated, the number of the remaining candidate intersections with the candidate intersection anchor point characteristics is the same as the number of the intersections obtained by screening, the existence of the target intersections in the road image corresponding to the target historical driving track is determined, and the track is indicated to be available, so that the task of identifying the intersections of the track can be continued.

If there are multiple candidate road images of the candidate intersection, if the candidate intersection anchor point feature in at least one of the target road images is matched with the target intersection anchor point feature, and after the candidate intersection anchor point feature and the candidate intersection with the candidate intersection anchor point feature are de-duplicated, the number of the remaining candidate intersections with the candidate intersection anchor point feature is different from the number of the intersections obtained by screening, whether the target intersection exists in the road image corresponding to the target historical driving track cannot be determined, and further judgment is needed.

Therefore, in the above embodiment, the electronic device realizes multiple recognition of the target intersection in the target road image based on the intersection type, the intersection anchor point characteristics and the number of intersections, further avoids the erroneous judgment of the intersection image, and improves the accuracy of the pre-marked map data and the quality of the navigation data, thereby improving the accuracy of the navigation service. In addition, under the condition that whether the target intersection exists in the road image corresponding to the target historical driving track cannot be identified based on the characteristics, depth judgment can be carried out by combining the related attributes, more elements are associated, and accurate identification is achieved.

The embodiment of the disclosure also provides a map making method, and an execution subject of the map making method is electronic equipment, wherein the electronic equipment comprises, but is not limited to, vehicle-mounted equipment, a desktop computer, a notebook computer, an integrated machine, a server and the like, and the server can be an independent server, can also be a cluster of a plurality of servers, and can comprise a server built locally and a server erected at a cloud.

In an embodiment of the present disclosure, the map making method may include:

under the condition that the target intersection exists in the road image corresponding to the target historical driving track is determined according to the map image processing method, a map corresponding to the target intersection is manufactured according to the target road image. Wherein, the map is marked with map data corresponding to the target intersection.

Specifically, the electronic device may determine whether the target intersection exists in the road image corresponding to the target historical driving track based on the map image processing method provided in the above embodiment, and further make a map corresponding to the target intersection according to the target road image when determining that the target intersection exists in the road image corresponding to the target historical driving track, so that the map is marked with map data corresponding to the target intersection.

In the above embodiment, the road network hooking shape of the target intersection in the map can be used for identifying the intersection type of the target intersection, obtaining the target intersection anchor point characteristic of the target intersection in the satellite image, after identifying that the target intersection belongs to the target intersection type and obtaining the target intersection anchor point characteristic corresponding to the target intersection, extracting the candidate intersection anchor point characteristic corresponding to the candidate intersection in the target road image corresponding to the target historical driving track matched with the target intersection of the candidate intersection type, further determining whether the target intersection exists in the road image corresponding to the target historical driving track based on the matching result of the candidate intersection anchor point characteristic and the target intersection anchor point characteristic, and further manufacturing the map corresponding to the target intersection according to the target road image when determining that the target intersection exists in the road image corresponding to the target historical driving track, so that the map is marked with the map data corresponding to the target intersection, the error of judgment of the image is avoided, the accuracy of the pre-marked map data and the quality of the navigation data are improved, and the accuracy of the navigation service is improved.

The following will describe in detail the steps of creating a map corresponding to a target intersection from a target road image.

marking a target intersection in the target road image;

Wherein the map data is used to assist in generating the navigation route. For example, before a recommended navigation route is made for a navigation object, a navigation route for guiding the navigation object to travel from a start position to a destination position is generated for the navigation object based on the pre-marked map data.

In still other embodiments of the present disclosure, after the step of determining that the target intersection exists in the road image corresponding to the target historical driving locus, the method may further include the steps of: and acquiring map data corresponding to the target intersection obtained based on the target road image identification.

Specifically, the electronic device may directly acquire map data corresponding to the target intersection, which is obtained in advance based on the target road image recognition, according to the map image processing method provided in the above embodiment.

In still other embodiments of the present disclosure, after obtaining the map data corresponding to the target intersection, the electronic device may pre-mark the map data corresponding to the target intersection in the map to make the map corresponding to the target intersection, so that the map after making is marked with the map data corresponding to the target intersection, and further, the navigation service may generate, for the navigation object, a navigation route for guiding the navigation object to travel from the starting point position to the destination position according to the starting point position and the destination position of the object to be navigated, based on the marked and included various data information of the map after making.

It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of combinations of actions, but those skilled in the art can appreciate that the disclosed embodiments are not limited by the order of actions described, as some steps may occur in other orders or concurrently in accordance with the disclosed embodiments. In addition, those skilled in the art will appreciate that the embodiments described in the specification are all alternatives.

Fig. 10 is a schematic diagram of a map image processing apparatus provided in an embodiment of the present disclosure, where the map image processing apparatus may be applied to an electronic device, and the electronic device includes, but is not limited to, a vehicle-mounted device, a desktop computer, a notebook computer, an all-in-one machine, a server, and the like, where the server may be an independent server, or may be a cluster of multiple servers, and may include a server built locally and a server erected at a cloud. The map image processing apparatus provided by the embodiment of the present disclosure may execute the processing flow provided by each embodiment of the map image processing method, as shown in fig. 10, the map image processing apparatus includes: a first sub-unit 1002, a second sub-unit 1004, a third sub-unit 1006, and a fourth sub-unit 1008. The functions of each unit are described as follows:

A first subunit 1002, configured to identify an intersection type of a target intersection based on a road network hooking shape of the target intersection in a map, so as to obtain a target intersection type corresponding to the target intersection;

a second subunit 1004, configured to obtain a target intersection anchor feature of the target intersection in the satellite image;

a third subunit 1006, configured to extract, from a target road image, a candidate intersection anchor feature corresponding to a candidate intersection when a candidate intersection of a target intersection type exists in the target road image, where the target road image is a road image corresponding to a target historical driving track matched with the target intersection;

and a fourth subunit 1008, configured to determine whether the target intersection exists in the road image corresponding to the target historical driving track based on a matching result of the candidate intersection anchor feature and the target intersection anchor feature.

In some embodiments, the second subunit 1004 includes:

the first extraction unit is used for acquiring satellite images corresponding to the target intersection;

the second extraction unit is used for carrying out image analysis on the satellite images and extracting the anchor point characteristics of the target intersection displayed in the satellite images.

Wherein the target intersection anchor characteristics include characteristics of at least one anchor type of: buildings, point of interest POIs, road traffic facilities.

In some embodiments, the fourth subunit 1008 includes:

the first determining unit is used for determining that a target intersection exists in the road image corresponding to the target historical driving track if the matching result is that the candidate intersection anchor characteristic is matched with the target intersection anchor characteristic;

and the second determining unit is used for determining that the target intersection does not exist in the road image corresponding to the target historical driving track if the matching result is that the candidate intersection anchor characteristic is not matched with the target intersection anchor characteristic.

In some embodiments, the map image processing apparatus further includes:

a sixth subunit, configured to mark a target intersection in the target road image after determining that the target intersection exists in the road image corresponding to the target historical track;

and a seventh subunit, configured to identify map data corresponding to the target intersection based on the marked target road image, where the map data is used to assist in generating a navigation route.

In some embodiments, the map image processing apparatus further includes:

an eighth subunit for detecting, in the map, the number of intersections having an intersection hanging shape;

correspondingly, the first determining unit is specifically configured to determine that the target intersection exists in the road image corresponding to the target historical driving track if the matching result is that the candidate intersection anchor feature matches the target intersection anchor feature and the number of candidate intersections exists in the target road image is the same as the number of intersections.

In some embodiments, the map image processing apparatus further includes:

and the ninth subunit is configured to determine, if the matching result is that the candidate intersection anchor feature matches the target intersection anchor feature, but the number of candidate intersections in the target road image is different from the number of intersections, whether a target intersection exists in the road image corresponding to the target historical driving track according to the road network related attribute of the target intersection in the map.

In some embodiments, the map image processing apparatus further includes:

a tenth subunit, configured to obtain anchor point features of other intersections corresponding to other intersections when other intersections other than the target intersection exist in the satellite image, where the other intersections belong to the target intersection type;

and the eleventh subunit is configured to determine, after determining that the target intersection does not exist in the target road image, that the target historical vehicle track has a shift in the target direction if the candidate intersection anchor feature matches with other intersection anchor features, where the target direction is a direction of the target intersection determined based on the track advancing direction of the target historical vehicle track in the satellite image relative to other intersections.

In at least one embodiment of the present disclosure, an intersection type of a target intersection can be identified by a road network hooking shape of the target intersection in a map, and a target intersection anchor feature of the target intersection in a satellite image is obtained, after identifying that the target intersection belongs to the target intersection type and obtaining the target intersection anchor feature corresponding to the target intersection, the candidate intersection anchor feature corresponding to the candidate intersection is extracted from a target road image corresponding to a target historical vehicle track matching the target intersection, where the candidate intersection belongs to the target intersection type, and then, based on a matching result of the candidate intersection anchor feature and the target intersection anchor feature, whether the target intersection exists in the road image corresponding to the target historical vehicle track is determined, so that double identification of the target intersection in the target road image based on the intersection type and the intersection anchor feature is realized, error in judgment of the intersection image is avoided, accuracy of pre-marked map data and quality of navigation data are improved, and accuracy of navigation service is improved.

The details of the embodiments of the map image processing apparatus disclosed above may refer to the details of the embodiments of the map image processing method described above, so that the details are not repeated.

Fig. 11 is a schematic diagram of a map making apparatus provided by an embodiment of the present disclosure, where the map making apparatus may be applied to an electronic device, and the electronic device includes, but is not limited to, a vehicle device, a desktop computer, a notebook computer, an integrated machine, a server, and the like, where the server may be an independent server, or may be a cluster of multiple servers, or may include a server built locally and a server erected at a cloud. The map making apparatus provided in the embodiment of the present disclosure may execute the processing flow provided in each embodiment of the map making method, as shown in fig. 11, where the map making apparatus includes: the fifth subunit 1102 functions as follows:

and a fifth subunit, configured to, when it is determined by using the map image processing apparatus that the target intersection exists in the road image corresponding to the target historical track, make a map corresponding to the target intersection according to the target road image, where the map is marked with map data corresponding to the target intersection.

In the map making device disclosed by the embodiment of the invention, the road network hooking shape of the target intersection in the map can be used for identifying the type of the intersection of the target intersection, the target intersection anchor point characteristic of the target intersection in the satellite image is obtained, after the target intersection belonging to the type of the target intersection is identified and the target intersection anchor point characteristic corresponding to the target intersection is obtained, the candidate intersection anchor point characteristic corresponding to the candidate intersection is extracted from the target road image corresponding to the target historical driving track of the candidate intersection, and further, whether the target intersection exists in the road image corresponding to the target historical driving track is determined based on the matching result of the candidate intersection anchor point characteristic and the target intersection anchor point characteristic, and further, the map corresponding to the target intersection is made according to the target road image under the condition that the target intersection exists in the road image corresponding to the target historical driving track, so that the map is marked with the map data corresponding to the target intersection, the error in judgment of the image of the intersection is avoided, the accuracy of the pre-marked map data and the quality of the navigation data are improved, and the accuracy of the navigation service is improved.

For details of the map making apparatus embodiment disclosed above, reference may be made to details of the map making method embodiment described above, so that no further description is given for avoiding repetition.

Fig. 12 is an exemplary block diagram of an electronic device provided by an embodiment of the present disclosure. As shown in fig. 12, the electronic device includes: a memory 1201, a processor 1202 and a computer program stored on the memory 1201. It is to be understood that the memory 1201 in this embodiment may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories.

In some implementations, the memory 1201 stores the following elements, executable modules or data structures, or a subset thereof, or an extended set thereof: an operating system and application programs.

The operating system includes various system programs, such as a framework layer, a core library layer, a driving layer, and the like, and is used for realizing various basic tasks and processing hardware-based tasks. Applications, including various applications such as Media players (Media players), browsers (browses), etc., are used to implement various application tasks. A program implementing the image processing method provided by the embodiment of the present disclosure may be included in an application program.

In the embodiment of the present disclosure, the at least one processor 1202 is configured to execute the steps of the embodiments of the image processing method provided in the embodiment of the present disclosure by calling a program or an instruction stored in the at least one memory 1201, specifically, a program or an instruction stored in an application program.

The image processing method provided by the embodiment of the present disclosure may be applied to the processor 1202 or implemented by the processor 1202. The processor 1202 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the methods described above may be performed by integrated logic circuitry in hardware or instructions in software in the processor 1202. The processor 1202 described above may be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The steps of the image processing method provided in the embodiments of the present disclosure may be directly implemented as a hardware decoding processor or implemented by a combination of hardware and software modules in the decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 1201 and the processor 1202 reads the information in the memory 1201 and performs the steps of the method in combination with its hardware.

The embodiments of the present disclosure further provide a computer readable storage medium, where the computer readable storage medium stores a program or instructions, where the program or instructions cause a computer to perform steps such as the steps of the embodiments of the image processing method, and for avoiding repetition of the description, a description is omitted herein. Wherein the computer readable storage medium may be a non-transitory computer readable storage medium.

Embodiments of the present disclosure also provide a computer program product, which includes computer instructions stored in a non-transitory computer readable storage medium, which when executed by a processor, implement steps as embodiments of an image processing method, and are not described in detail herein for avoiding repetition of the description.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

Those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the disclosure and form different embodiments.

Those skilled in the art will appreciate that the descriptions of the various embodiments are each focused on, and that portions of one embodiment that are not described in detail may be referred to as related descriptions of other embodiments.

Although embodiments of the present disclosure have been described with reference to the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the disclosure, and such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A map image processing method, the method comprising:

based on the road network hooking shape of a target intersection in a map, identifying the intersection type of the target intersection to obtain the target intersection type corresponding to the target intersection;

acquiring the anchor point characteristics of the target intersection in the satellite image;

under the condition that a candidate intersection of the target intersection type exists in a target road image, extracting candidate intersection anchor point characteristics corresponding to the candidate intersection from the target road image, wherein the target road image is a road image corresponding to a target historical driving track matched with the target intersection;

and determining whether the target intersection exists in the road image corresponding to the target historical driving track based on a matching result of the candidate intersection anchor feature and the target intersection anchor feature.

2. The method of claim 1, wherein the obtaining the target intersection anchor feature of the target intersection in the satellite image comprises:

acquiring the satellite image corresponding to the target intersection;

performing image analysis on the satellite image, and extracting the anchor point characteristics of the target intersection displayed in the satellite image;

3. The method of claim 1, wherein the determining whether the target intersection exists in the road image corresponding to the target historical track based on the matching result of the candidate intersection anchor feature and the target intersection anchor feature comprises:

if the matching result is that the candidate intersection anchor point characteristic is matched with the target intersection anchor point characteristic, determining that the target intersection exists in the road image corresponding to the target historical driving track;

and if the matching result is that the candidate intersection anchor point characteristic is not matched with the target intersection anchor point characteristic, determining that the target intersection does not exist in the road image corresponding to the target historical driving track.

4. The method of claim 3, wherein after the determining that the target intersection exists in the road image corresponding to the target historical track following, the method further comprises:

marking the target intersection in the target road image;

and identifying map data corresponding to the target intersection based on the marked target road image, wherein the map data is used for assisting in generating a navigation route.

5. A method according to claim 3, wherein the method further comprises:

detecting the number of intersections with the road network hooking shape in the map;

the determining that the target intersection exists in the road image corresponding to the target historical driving track includes:

and if the number of the candidate intersections in the target road image is the same as the number of the intersections, determining that the target intersections exist in the road image corresponding to the target historical driving track.

6. The method of claim 5, wherein the method further comprises:

if the matching result is that the candidate intersection anchor point characteristic is matched with the target intersection anchor point characteristic, but the number of the candidate intersections in the target road image is different from the number of the intersections, determining whether the target intersections exist in the road image corresponding to the target historical driving track according to the road network related attribute of the target intersections in the map.

7. The method of claim 1, wherein the method further comprises:

under the condition that other intersections except the target intersection exist in the satellite image, other intersection anchor point characteristics corresponding to the other intersections are obtained, wherein the other intersections belong to the target intersection type;

Wherein the method further comprises:

and under the condition that the target intersection does not exist in the target road image, if the candidate intersection anchor point characteristic is matched with the other intersection anchor point characteristic, determining that the target historical vehicle track has an offset in a target direction, wherein the target direction is the direction of the target intersection determined based on the track advancing direction of the target historical vehicle track in the satellite image relative to the other intersections.

8. A method of mapping, the method comprising:

in the case where it is determined according to the map image processing method of claims 1 to 7 that there is a target intersection in the road image corresponding to the target historical track, a map corresponding to the target intersection is created from the target road image, the map being marked with map data corresponding to the target intersection.

9. A map image processing apparatus, the apparatus comprising:

the first subunit is used for identifying the type of the road junction of the target road junction based on the road network hooking shape of the target road junction in the map, so as to obtain the type of the target road junction corresponding to the target road junction;

A third subunit, configured to extract, from a target road image, candidate intersection anchor features corresponding to the candidate intersection when the candidate intersection of the target intersection type exists in the target road image, where the target road image is a road image corresponding to a target historical driving track matched with the target intersection;

and the fourth subunit is used for determining whether the target intersection exists in the road image corresponding to the target historical driving track based on the matching result of the candidate intersection anchor feature and the target intersection anchor feature.

10. A map making apparatus, the apparatus comprising:

a fifth subunit, configured to, when it is determined by the map image processing apparatus according to claim 8 that the target intersection exists in the road image corresponding to the target historical track, create, from the target road image, a map corresponding to the target intersection, where the map is marked with map data corresponding to the target intersection.

11. An electronic device comprising a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to implement the map image processing method of any one of claims 1 to 7 or the steps of the map making method of claim 8.

12. A computer-readable storage medium storing a program or instructions that cause a computer to execute the map image processing method according to any one of claims 1 to 7 or the steps of the map making method according to claim 8.