CN117808873A

CN117808873A - Redundant road detection method, device, electronic equipment and storage medium

Info

Publication number: CN117808873A
Application number: CN202410232136.9A
Authority: CN
Inventors: 刘巍; 高树峰
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2024-03-01
Filing date: 2024-03-01
Publication date: 2024-04-02
Anticipated expiration: 2044-03-01
Also published as: CN117808873B

Abstract

The application discloses a redundant road detection method, a redundant road detection device, electronic equipment and a storage medium. The embodiment of the application relates to the technical field of electronic maps and the like. The method comprises the following steps: according to the remote sensing image, determining the observable proportion of the road to be analyzed in the remote sensing image; determining the traffic flow density corresponding to the road to be analyzed according to the times of taking each position point in the area indicated by the position information as a locating point and the number of moving tracks passing through each position point; determining the road similarity corresponding to the road to be analyzed according to the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map; and determining a redundant detection result of the road to be analyzed in the first electronic map according to at least two of the observable proportion, the traffic flow density and the road similarity. According to the method, multi-angle analysis of redundancy detection is realized, and the accuracy of redundancy judgment is effectively improved.

Description

Redundant road detection method, device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the technical field of electronic maps, and in particular, to a redundant road detection method, a redundant road detection device, an electronic device, and a storage medium.

Background

Redundant roads refer to roads that exist in an electronic map but do not exist in the real world, and the reasons for the redundant roads are usually building construction, road diversion and other factors, so that the original roads are abandoned or rebuilt. The related art has the problem that the accuracy of redundant road detection is low.

Disclosure of Invention

In view of this, an embodiment of the present application provides a redundant road detection method, a device, an electronic apparatus, and a storage medium.

In a first aspect, an embodiment of the present application provides a redundant road detection method, where the method includes: acquiring a remote sensing image of an area indicated by the presentation position information based on the position information of the road to be analyzed presented in the first electronic map; according to the remote sensing image, determining the observable proportion of the road to be analyzed in the remote sensing image; determining the traffic flow density corresponding to the road to be analyzed according to the times of taking each position point in the area indicated by the position information as a locating point and the number of moving tracks passing through each position point; determining the road similarity corresponding to the road to be analyzed according to the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map; and determining a redundant detection result of the road to be analyzed in the first electronic map according to at least two of the observable proportion, the traffic flow density and the road similarity.

In a second aspect, an embodiment of the present application provides a redundant road detection apparatus, including: the acquisition module is used for acquiring a remote sensing image of an area indicated by the presentation position information based on the position information of the road to be analyzed presented in the first electronic map; the first determining module is used for determining the observable proportion of the road to be analyzed in the remote sensing image according to the remote sensing image; the second determining module is used for determining the traffic flow density corresponding to the road to be analyzed according to the times of taking each position point in the area indicated by the position information as a locating point and the number of moving tracks passing through each position point; the third determining module is used for determining the road similarity corresponding to the road to be analyzed according to the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map; and the result determining module is used for determining a redundant detection result of the road to be analyzed in the first electronic map according to at least two of the observable proportion, the traffic flow density and the road similarity.

Optionally, the second determining module is further configured to determine a traffic flow value of each location point according to the number of times that each location point in the area indicated by the location information is used as a locating point and the number of moving tracks passing through each location point; generating a traffic flow diagram corresponding to the road to be analyzed based on traffic flow values of all the position points, wherein the traffic flow diagram comprises target pixels representing all the position points in the area indicated by the position information; the pixel value of the target pixel is determined according to the traffic flow value of the position point corresponding to the target pixel; and determining the traffic flow density corresponding to the road to be analyzed according to the traffic flow map corresponding to the road to be analyzed.

Optionally, the second determining module is further configured to select at least one first reference pixel from the target pixels in the traffic flow map; determining a neighborhood pixel region of each first reference pixel in the traffic flow chart; determining a reference pixel value of each first reference pixel according to the pixel value of each pixel in the neighborhood pixel region of each first reference pixel; and determining the traffic flow density corresponding to the road to be analyzed according to the reference pixel value of each first reference pixel in the traffic flow diagram.

Optionally, the second determining module is further configured to transform the traffic flow value of each location point into the target interval, so as to obtain a target traffic flow value corresponding to each location point; and taking the target traffic flow value corresponding to each position point as the pixel value of the target pixel corresponding to each position point to generate a traffic flow diagram corresponding to the road to be analyzed, wherein the target pixels are arranged in the traffic flow diagram according to the relative positions of the corresponding position points in the area indicated by the position information.

Optionally, the second determining module is further configured to perform gap reduction processing on traffic flow values of the location points to obtain a first intermediate traffic flow value of the location points; the gap reduction processing is used for reducing the difference between traffic flow values corresponding to different position points; normalizing the first intermediate traffic flow value of each position point into a target interval to obtain a second intermediate traffic flow value of each position point; and rounding the first intermediate traffic flow value of each position point to obtain a target traffic flow value corresponding to each position point.

Optionally, the first determining module is further configured to perform binarization processing on the remote sensing image to obtain a binarized image; the pixel values of the pixels representing the road in the binarized image are different from the pixel values of the pixels representing the non-road; selecting at least one second reference pixel from a target pixel region in the binarized image; the target pixel area is a pixel area of an area indicated by the presentation position information in the binarized image; determining a neighborhood pixel region of each second reference pixel in the binarized image; and determining the observable proportion of the road to be analyzed in the remote sensing image according to the pixel value of each pixel in the neighborhood pixel region of each second reference pixel in the binarized image.

Optionally, a pixel value of a pixel for representing a road in the binarized image is a target pixel value; the first determining module is further configured to determine, according to a duty ratio of a pixel whose pixel value is a target pixel value in a neighborhood pixel region of each second reference pixel in the binarized image, a road point attribute corresponding to each second reference pixel, where the road point attribute is a positive road point attribute or a negative road point attribute; and determining the observable proportion of the road to be analyzed in the remote sensing image according to the number of the second reference pixels of the positive road point attribute and the number of the second reference pixels of the negative road point attribute.

Optionally, the road shape information of the road to be analyzed in the first electronic map includes position information of each of a plurality of first shape points, and the shape information of the area indicated by the position information in the second electronic map includes position information of each of a plurality of second shape points; the third determining module is further used for determining a matched shape point matched with each first shape point from a plurality of second shape points; determining relative parameters between the first shape point and the corresponding matching shape point according to the position information of the first shape point and the position information of the corresponding matching shape point, wherein the relative parameters comprise relative distance and relative angle; determining the similarity between the road shape information and the shape information according to the relative parameters between each first shape point and the corresponding matching shape point; and determining the road similarity corresponding to the road to be analyzed according to the similarity.

Optionally, the result determining module is further configured to obtain a redundant detection result of the road to be analyzed being the redundant road in the first electronic map if the observable ratio is smaller than the observable ratio threshold, the traffic density is smaller than the traffic density threshold, and the road similarity is smaller than the road similarity threshold.

Optionally, the result determining module is further configured to input an observable ratio, a traffic flow density and a road similarity corresponding to the road to be analyzed into the redundant road analysis model, so as to obtain a probability value of predicting the road to be analyzed as the redundant road; if the probability value of the road to be analyzed predicted as the redundant road is smaller than the probability threshold value, obtaining a redundant detection result that the road to be analyzed is not the redundant road in the first electronic map; and if the probability value of the road to be analyzed predicted as the redundant road is not less than the probability threshold value, obtaining a redundant detection result of the road to be analyzed as the redundant road in the first electronic map.

Optionally, the result determining module is further configured to delete the road to be analyzed in the first electronic map if the redundant detection result is that the road to be analyzed is a redundant road in the first electronic map.

In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory; the memory has stored thereon computer readable instructions which, when executed by the processor, implement the method described above.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having computer-readable instructions stored thereon, which when executed by a processor, implement the above-described method.

In a fifth aspect, embodiments of the present application provide a computer program product comprising computer instructions which, when executed by a processor, implement the above-described method.

The embodiment of the application provides a redundant road detection method, a device, electronic equipment and a storage medium, wherein in the application, the observable proportion of a road to be analyzed in a remote sensing image is determined according to the remote sensing image; determining the traffic flow density corresponding to the road to be analyzed according to the times of taking each position point in the area indicated by the position information as a locating point and the number of moving tracks passing through each position point; determining the road similarity corresponding to the road to be analyzed according to the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map; then, according to at least two of observable proportion, traffic flow density and road similarity, a redundant detection result of the road to be analyzed in the first electronic map is determined, so that whether the road to be analyzed is redundant or not is judged by combining remote sensing images, the number of times of taking the position points as positioning points, the number of moving tracks passing through the position points and at least three of road information in four different forms of shape information of the road to be analyzed in the electronic map, multi-angle analysis of redundant detection is realized, and the mode of detecting the redundant road only through the road similarity in different electronic maps is intersected.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 shows a schematic diagram of an application scenario applicable to an embodiment of the present application;

FIG. 2 is a flow chart illustrating a redundant road detection method according to one embodiment of the present application;

FIG. 3 is a schematic diagram of a remote sensing image and a corresponding binarized image according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a neighborhood pixel region of a second reference pixel according to an embodiment of the present application;

fig. 5 is a schematic diagram showing a positional relationship between a position point and a corresponding target pixel in an embodiment of the present application;

FIG. 6 is a schematic diagram of a locating point and track and a corresponding traffic flow map in an embodiment of the present application;

FIG. 7 is a schematic diagram of a neighborhood pixel region of a first reference pixel according to an embodiment of the present application;

Fig. 8 shows a schematic diagram of an electronic map and a road network according to an embodiment of the present application;

FIG. 9 is a schematic diagram of a redundant road detection process in an embodiment of the present application;

FIG. 10 illustrates a block diagram of a redundant road detection apparatus according to one embodiment of the present application;

fig. 11 shows a block diagram of an electronic device for performing a redundant road detection method according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

In the following description, the terms "first", "second", and the like are merely used to distinguish similar objects and do not represent a particular ordering of the objects, it being understood that the "first", "second", and the like may be interchanged with one another, if permitted, to enable embodiments of the application described herein to be practiced otherwise than as illustrated or described herein.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the present application. It should be noted that: references herein to "a plurality" means two or more. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., a and/or B may represent: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.

In the embodiment of the application, the map is acquired by the agreement of the personnel to which the map belongs, and the collection, the use, the processing and the storage of the remote sensing image, the road element, the positioning point and other information are in accordance with the regulations of the region.

The application discloses a redundant road detection method, a device, electronic equipment and a storage medium, which relate to the technology of an electronic map, and can detect the redundant road of the road presented in the electronic map and delete the road detected and determined to be the redundant road in the electronic map based on the method of the application.

The intelligent transportation system (Intelligent Traffic System, ITS), also called intelligent transportation system (Intelligent Transportation System), is a comprehensive transportation system which uses advanced scientific technology (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operation study, artificial intelligence, etc.) effectively and comprehensively for transportation, service control and vehicle manufacturing, and enhances the connection among vehicles, roads and users, thereby forming a comprehensive transportation system for guaranteeing safety, improving efficiency, improving environment and saving energy.

The intelligent vehicle-road cooperative system (Intelligent Vehicle Infrastructure Cooperative Systems, IVICS), which is simply called a vehicle-road cooperative system, is one development direction of an Intelligent Transportation System (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 all directions, 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 people and vehicles and roads, ensures traffic safety, improves traffic efficiency, and forms a safe, efficient and environment-friendly road traffic system.

As shown in fig. 1, an application scenario applicable to the embodiments of the present application includes a terminal 20 and a server 10, where the terminal 20 and the server 10 are connected through a wired network or a wireless network. The terminal 20 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart home appliance, a vehicle-mounted terminal, an aircraft, a wearable device terminal, a virtual reality device, and other terminal devices capable of performing page presentation, or other applications (e.g., an instant messaging application, a shopping application, a search application, a game application, a forum application, a map traffic application, etc.) running other applications capable of invoking redundant road detection methods.

The server 10 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs (Content Delivery Network, content delivery networks), basic cloud computing services such as big data and artificial intelligent platforms, and the like. The server 10 may be used to provide services for applications running at the terminal 20.

The terminal 20 may send the position information of the road to be analyzed to the server 10, the server 10 obtains a remote sensing image of an area indicated by the position information, the number of times that each position point in the area indicated by the position information is used as a positioning point, the number of moving tracks passing through each position point, the shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map, and then the server 10 determines the observable proportion of the road to be analyzed in the remote sensing image according to the remote sensing image; determining the traffic flow density corresponding to the road to be analyzed according to the times of taking each position point in the area indicated by the position information as a locating point and the number of moving tracks passing through each position point; determining the road similarity corresponding to the road to be analyzed according to the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map; and then, the server 10 determines a redundant detection result of the road to be analyzed in the first electronic map according to at least two of the observable proportion, the traffic flow density and the road similarity, returns the redundant detection result to the terminal 20, and deletes the road to be analyzed in the first electronic map when the terminal 20 is that the road to be analyzed is the redundant road in the first electronic map.

In another embodiment, the terminal 20 may be configured to execute the method of the present application to obtain a redundant detection result of the road to be analyzed in the first electronic map, and delete the road to be analyzed in the first electronic map when the redundant detection result is that the road to be analyzed is the redundant road in the first electronic map.

For convenience of description, in the following embodiments, an example in which the redundant road detection method is performed by the electronic apparatus will be described.

Referring to fig. 2, fig. 2 shows a flowchart of a redundant road detection method according to an embodiment of the present application, where the method may be used in an electronic device, and the electronic device may be the terminal 20 or the server 10 in fig. 1, and the method may include:

s110, acquiring a remote sensing image of an area indicated by the presentation position information based on the position information of the road to be analyzed presented in the first electronic map.

The road to be analyzed is a road to be subjected to redundancy analysis in the first electronic map, and the road to be analyzed may not correspond to an actual road in a real environment. The position information of the road to be analyzed may refer to position data indicating an actual area corresponding to the road to be analyzed in a real environment, and the position data may be coordinates or longitude and latitude coordinates in a world coordinate system.

In general, the first electronic map includes many roads, and the data processing amount for performing redundancy detection on all the roads in the first electronic map is large, so that the resource consumption is high, and therefore, the road to be analyzed can be selected from the first electronic map according to the selection rule. The selection rules may include selecting a road near the construction area as the road to be analyzed, selecting a road in a region of lower traffic density as the road to be analyzed, selecting a road in a remote region as the road to be analyzed, and the like.

In an embodiment, the location information of the road to be analyzed may be obtained from the first electronic map, and for each road presented on the first electronic map, the location information of the road is associated, and the location information of the road includes location information of each location point in the area where the road is located, where the location information may be longitude and latitude.

The area indicated by the position information of the road to be analyzed refers to an area covered by the position information of the road to be analyzed in an actual environment, and the remote sensing image of the area indicated by the position information can be shot through an aircraft (such as an airplane or an unmanned aerial vehicle) or through a satellite. The remote sensing image may include at least an area indicated by the location information of the road to be analyzed, and may further include other areas than the area indicated by the location information of the road to be analyzed. For example, a building A1 and a park A2 exist around an area indicated by the position information of the road to be analyzed, and the remote sensing image may further include the building A1 and the park A2.

It can be understood that the number of the roads to be analyzed may be plural, and when the areas indicated by the position information of the roads to be analyzed are closer, the roads to be analyzed may correspond to one remote sensing image, that is, the remote sensing image includes the areas indicated by the position information of the roads to be analyzed, so that it is not necessary to separately obtain the remote sensing image for the areas indicated by the position information of each road to be analyzed, and the remote sensing image obtaining cost and the remote sensing image obtaining efficiency are saved.

S120, according to the remote sensing image, the observable proportion of the road to be analyzed in the remote sensing image is determined.

The observable proportion of the road to be analyzed in the remote sensing image is used for indicating the possibility that the road to be analyzed is observed in the remote sensing image, and the higher the observable proportion of the road to be analyzed in the remote sensing image is, the higher the possibility that the road to be analyzed is observed in the remote sensing image is, the lower the observable proportion of the road to be analyzed in the remote sensing image is, and the lower the possibility that the road to be analyzed is observed in the remote sensing image is.

In some embodiments, S120 may include: performing binarization processing on the remote sensing image to obtain a binarized image; the pixel values of the pixels representing the road in the binarized image are different from the pixel values of the pixels representing the non-road; selecting at least one second reference pixel from a target pixel region in the binarized image; the target pixel area is a pixel area of an area indicated by the presentation position information in the binarized image; determining a neighborhood pixel region of each second reference pixel in the binarized image; and determining the observable proportion of the road to be analyzed in the remote sensing image according to the pixel value of each pixel in the neighborhood pixel region of each second reference pixel in the binarized image. The pixel value of the pixel in the binarized image representing the road may be a target pixel value, the pixel value of the pixel in the binarized image representing the non-road may be a specified pixel value, the target pixel value is different from the specified pixel value, the target pixel value may be 1, for example, and the specified pixel value may be 0, for example.

In the case where the target pixel value is 1 and the specified pixel value is 0, a binarized image obtained based on the remote sensing image shown as a in fig. 3 is shown as b in fig. 3.

In some embodiments, the remote sensing image may be further subjected to road segmentation by using a road segmentation model to determine a road region and a non-road region from the remote sensing image, and then the pixel values of the pixels in the road region are adjusted to target pixel values, and the pixel values of the pixels in the non-road region are adjusted to specified pixel values, so as to obtain a binarized image. The road segmentation model can be obtained by training a neural network model.

After the binarized image is obtained, an area corresponding to an area indicated by the position information of the road to be analyzed may be determined as a target pixel area from the binarized image. For example, an area (which is an image area of one block) in the binarized image that matches an area indicated by position information (which is an actual area) of the road to be analyzed may be regarded as the target pixel area.

In this embodiment, at least one second reference pixel is selected in the target pixel region, and at least one second reference pixel may be selected in a region that matches a region indicated by the center line position information of the road to be analyzed (the region is a line) determined in the target pixel region.

After the target pixel area is obtained, at least one second reference pixel may be selected in the target pixel area. For example, the target pixel area may be divided into a plurality of first blocks, each first block is selected as a second reference pixel, and the size of each first block may be determined based on the image size of the remote sensing image (or the binarized image) and the actual area of the indicated actual area, for example, the image size of the remote sensing image (or the binarized image) is 1000×1000 pixels, and the actual area of the indicated actual area of the remote sensing image (or the binarized image) is 400 square meters, and then the size of each first block in the target pixel area is 50×50 pixels.

As another example, in the target pixel area, a pixel is selected as a second reference pixel every first number of pixels in an area matched with the area indicated by the central line position information of the road to be analyzed (the area is a line), wherein the first number can be determined based on the image size of the remote sensing image (or the binarized image) and the actual area of the indicated actual area, for example, the image size of the remote sensing image (or the binarized image) is 1000×1000 pixels, and the actual area of the actual area indicated by the remote sensing image (or the binarized image) is 400×square meters, and then the first number is 49.

After obtaining the second reference pixels, determining a neighborhood pixel region of each second reference pixel in the binarized image, wherein the neighborhood pixel region of the second reference pixels refers to a pixel region surrounding the second reference pixels in the binarized image, and the neighborhood pixel region of the second reference pixels comprises the second reference pixels and the neighborhood pixels (i.e. pixels directly adjacent to or indirectly adjacent to the second reference pixels) of the second reference pixels.

For example, a rectangular pixel region may be constructed in the binarized image with each second reference pixel as a neighborhood pixel region corresponding to each second reference pixel, and for example, a closed pixel region (may be a closed pixel region of any shape) including each second reference pixel may be constructed in the binarized image as a neighborhood pixel region corresponding to each second reference pixel. The area of the neighborhood pixel region corresponding to the second reference pixel is set based on the requirement, and the area of the neighborhood pixel region corresponding to the second reference pixel is 5×5 pixels.

As shown in fig. 4, from the partial pixel region 40 of the binarized image corresponding to the region indicated by the position information of the road to be analyzed, an image road line 41 corresponding to the region indicated by the center line position information of the road to be analyzed is determined, the pixels through which the image road line 41 passes in the binarized image constitute a candidate pixel region, and then three second reference pixels (the pixels where the three black filled circles are located are regarded as second reference pixels) are determined from the candidate pixel region: the second reference pixel 42, the second reference pixel 43 and the second reference pixel 44 respectively construct a 5×5 neighborhood pixel region with the three second reference pixels as the centers, so as to obtain neighborhood pixel regions corresponding to the three second reference pixels respectively: a neighborhood pixel region 421 of the second reference pixel 42, a neighborhood pixel region 422 of the second reference pixel 43, and a neighborhood pixel region 423 of the second reference pixel 44.

And obtaining a neighborhood pixel region corresponding to each second reference pixel, and determining the observable proportion of the road to be analyzed in the remote sensing image according to the pixel value of each pixel in the neighborhood pixel region corresponding to each second reference pixel.

Under the condition that the pixel value of the pixel used for representing the road in the binarized image is a target pixel value, according to the pixel value of each pixel in the neighborhood pixel region of each second reference pixel in the binarized image, the method for determining the observable proportion of the road to be analyzed in the remote sensing image comprises the following steps: determining a road point attribute corresponding to each second reference pixel according to the duty ratio of the pixel with the pixel value of the neighborhood pixel region of each second reference pixel in the binarized image as a target pixel value, wherein the road point attribute is a positive road point attribute or a negative road point attribute; and determining the observable proportion of the road to be analyzed in the remote sensing image according to the number of the second reference pixels of the positive road point attribute and the number of the second reference pixels of the negative road point attribute.

And counting the number of pixels with the pixel value being the target pixel value in the neighborhood pixel area corresponding to each second reference pixel, determining the duty ratio of the pixels with the pixel value being the target pixel value in the neighborhood pixel area corresponding to the second reference pixel, determining the road point attribute of the second reference pixel with the duty ratio reaching the proportion threshold value as a positive road point attribute, and determining the road point attribute of the second reference pixel with the proportion not reaching the proportion threshold value as a negative road point attribute, wherein the proportion threshold value can be set based on requirements, for example, 1/2.

The road point attribute of the second reference pixel is used for indicating that the position of the second reference pixel in the actual environment is high or low in probability of being a road, namely, if the road point attribute of the second reference pixel is positive road point attribute, the probability that the position of the second reference pixel in the actual environment is a road is higher, and if the road point attribute of the second reference pixel is negative road point attribute, the probability that the position of the second reference pixel in the actual environment is a road is lower. In the present application, for each second reference pixel, if the number of pixels representing the road in the neighborhood pixel region of the second reference pixel is greater, the probability that the corresponding position of the second reference pixel in the actual environment is the road is higher, otherwise, if the number of pixels representing the non-road in the neighborhood pixel region of the second reference pixel is greater, the probability that the corresponding position of the second reference pixel in the actual environment is not the road is higher. Therefore, in the above-described embodiment, the road point attribute of the second reference pixel is determined in combination with the number of pixels whose pixel values are the target pixel values (i.e., pixels representing the road) in the neighborhood pixel region including the second reference pixel, that is, the road point attribute is determined with reference to the pixel value of the second reference pixel itself and the pixel values of the neighboring pixels of the second reference pixel, it is possible to ensure the accuracy of the road point attribute determined for the second reference pixel, as compared with determining the road point attribute of the second reference pixel based on only the pixel value of the second reference pixel.

After the road point attributes of all the second reference pixels in the target pixel area corresponding to the road to be analyzed are determined, the observable proportion of the road to be analyzed in the remote sensing image is determined according to the number of the second reference pixels with the positive road point attributes and the number of the second reference pixels with the negative road point attributes. For example, the ratio of the number of the second reference pixels of the positive road point attribute to the number of the second reference pixels of the negative road point attribute may be determined as an observable ratio of the road to be analyzed in the remote sensing image, and for example, the ratio of the number of the second reference pixels of the positive road point attribute to the number of all the second reference pixels in the target pixel region corresponding to the road to be analyzed may be determined as an observable ratio of the road to be analyzed in the remote sensing image.

For example, when determining the ratio of the number of the second reference pixels of the positive road point attribute to the number of the second reference pixels of the negative road point attribute as the observable ratio of the road to be analyzed in the remote sensing image, the calculation process of the observable ratio of the road to be analyzed in the remote sensing image refers to formula one, which is as follows:

(one)

Wherein,for the observable proportion of the road to be analyzed in the remote sensing image,/->The number of second reference pixels being a forward road point attribute,/->Is a negative road point attributeIs used for the second reference pixel number.

S130, determining the traffic flow density corresponding to the road to be analyzed according to the times of taking each position point in the area indicated by the position information as the locating point and the number of moving tracks passing through each position point.

One location point in the area indicated by the location information of the road to be analyzed may refer to one actual area in the area indicated by the location information of the road to be analyzed. For example, one location point in the area indicated by the location information of the road to be analyzed may refer to a square area of 4 square meters in the area indicated by the location information of the road to be analyzed.

If, during the positioning process, the position of the positioning object in the actual environment is positioned (or can be understood as being absorbed) to a position point in the actual environment, the position point is represented in the electronic map as a positioning point. The number of times that each position point is used as a locating point is the number of times that the position point is located in the electronic map. Wherein the positioning object may be a pedestrian or a vehicle or the like. For example, if a pedestrian carrying a mobile phone is positioned 2 times by the positioning software of the mobile phone in the position point b1, and the vehicle is positioned 3 times by the positioning software of the mobile phone when the vehicle is in the position point b1, the number of times that the position point b1 is used as the positioning point is 5.

In the present application, since redundant road detection is performed on the road to be analyzed presented in the first electronic map, the number of times that each location point in the area indicated by the location information of the road to be analyzed is used as the locating point can be acquired in the location navigation system that provides the location navigation service based on the first electronic map. Similarly, the number of moving tracks passing through each position point can also be obtained from a positioning navigation system providing positioning navigation service based on the first electronic map.

Every time the moving track of the positioning object passes through the position point, the number of times of the moving track passing through the position point is increased by 1. For example, if the number of moving tracks of the vehicle passing through the position point b2 is 3 and the number of moving tracks of the pedestrian passing through the position point b2 is 6, the number of moving tracks passing through the position point b1 is 9.

The traffic flow density of the road to be analyzed can reflect the traffic condition of the area indicated by the position information of the analyzed road, namely, the higher the traffic flow density of an area is, the higher the probability that the area is the road for the object to pass through, otherwise, the lower the traffic flow density of an area is, and the lower the probability that the area is the road for the object to pass through is. Therefore, for the road to be analyzed, if the traffic flow density of the road to be analyzed is higher, the probability that the road to be analyzed exists in the actual environment is higher (i.e., the probability that the road to be analyzed is a non-redundant road is higher), whereas if the traffic flow density is lower, the probability that the road to be analyzed exists in the actual environment is lower, and the probability that the road to be analyzed is a redundant road is lower.

In this embodiment, a target period may be set, and the number of times each position point in the area indicated by the position information in the target period is set as a locating point and the number of moving tracks passing through each position point may be counted as the number of times the position point required in S120 is set as a locating point and the number of moving tracks passing through each position point, for example, the target period may be 2023, 1, 4, or 2023, 1, 13.

In some embodiments, after the number of times that each position point is used as a locating point and the number of moving tracks passing through each position point are obtained, an average value of the number of times that each position point is used as a locating point can be determined as a locating density of the locating point, an average value of the number of moving tracks passing through each position point can be determined as a track density, and a traffic flow density corresponding to the road to be analyzed is determined according to the locating density and the track density. For example, the positioning density and the track density of each position point are summed to obtain the density and the value of the position point, and the density and the value of the position point in the area indicated by the position information of the road to be analyzed are averaged or summed to obtain the traffic flow density corresponding to the road to be analyzed.

In still other embodiments, S130 may further include: determining the traffic flow value of each position point according to the times of taking each position point in the area indicated by the position information as the locating point and the number of moving tracks passing through each position point; generating a traffic flow diagram corresponding to the road to be analyzed based on traffic flow values of all the position points, wherein the traffic flow diagram comprises target pixels representing all the position points in the area indicated by the position information; the pixel value of the target pixel is determined according to the traffic flow value of the position point corresponding to the target pixel; and determining the traffic flow density corresponding to the road to be analyzed according to the traffic flow map corresponding to the road to be analyzed.

In some embodiments, each location point in the area indicated by the location information may calculate the sum of the number of times the location point is used as a locating point and the number of times the location point moves along the track, to obtain the traffic flow value of the location point; then, the traffic flow values of the position points are transformed into a target interval, and a target traffic flow value corresponding to each position point is obtained; and taking the target traffic flow value corresponding to each position point as the pixel value of the target pixel corresponding to each position point to generate a traffic flow diagram corresponding to the road to be analyzed, wherein the target pixels are arranged in the traffic flow diagram according to the relative positions of the corresponding position points in the area indicated by the position information. The target interval may be a value range of a pixel value, for example, 0 to 255, and the target interval may be 0 to 255.

In some embodiments, the traffic flow value of each location point may be normalized to the target interval to obtain a third intermediate traffic flow value for each location point; and rounding the third intermediate traffic flow value of each position point to obtain a target traffic flow value corresponding to each position point.

Based on the foregoing, it is known that the traffic flow value of the location point is required to be used for determining the pixel value of the target pixel corresponding to the location point, so the target interval may be 0 to 255, and the determined target traffic flow value needs to be an integer, so after the traffic flow value of the location point is obtained, the traffic flow value corresponding to the location point needs to be normalized to be within the target interval of 0 to 255, so as to obtain a third intermediate traffic flow value corresponding to each location point, and then, the rounding process needs to be performed on the third intermediate traffic flow value corresponding to each location point, and the rounded result is used as the target traffic flow value corresponding to the location point. The rounding process may be an up-rounding process or a down-rounding process.

In still other embodiments, the traffic flow values of the location points may be subjected to a gap reduction process to obtain a first intermediate traffic flow value for each location point; the gap reduction processing is used for reducing the difference between traffic flow values corresponding to different position points; normalizing the first intermediate traffic flow value of each position point into a target interval to obtain a second intermediate traffic flow value of each position point; and rounding the first intermediate traffic flow value of each position point to obtain a target traffic flow value corresponding to each position point.

In this embodiment, for each location point, a logarithmic operation may be performed on the traffic flow value corresponding to each location point, so as to implement a gap reduction process on the traffic flow value corresponding to each location point, to obtain a first intermediate traffic flow value corresponding to each location point, where the logarithmic function of the logarithmic operation may beOr->Wherein->May refer to the traffic flow value corresponding to the pixel.

Based on the foregoing, it is known that the traffic flow value of the location point is required to be used for determining the pixel value of the target pixel corresponding to the location point, so the target interval may be 0 to 255, and the determined target traffic flow value needs to be an integer, so after the first intermediate traffic flow value of the location point is obtained, the first intermediate traffic flow value corresponding to the location point needs to be normalized to be within the target interval of 0 to 255, so as to obtain the second intermediate traffic flow value corresponding to each location point, and then the second intermediate traffic flow value corresponding to each location point needs to be rounded, and the rounded result is used as the target traffic flow value corresponding to the location point. The rounding process may be an up-rounding process or a down-rounding process.

For example, the gap-reduction process is performed by a logarithmic functionWhen the target interval is 0-255, the process of determining the target traffic flow value of each location point according to the traffic flow value of each location point may be as shown in formula two, where formula two is as follows:

(II)

Wherein,for the target traffic flow value corresponding to the location point, < >>Maximum value of traffic flow value for location point in area indicated by location information of road to be analyzed,/>For the minimum value of the traffic flow value of the location point in the area indicated by the location information of the road to be analyzed,/->A traffic flow value for a location point in the area indicated by the location information of the road to be analyzed.

After the target traffic flow value of each position point is obtained, a target pixel can be determined for each position point, the target traffic flow value of each position point is used as the pixel value of the corresponding target pixel, and the corresponding target pixels of each position point are arranged according to the relative position of each position point in the area indicated by the position information of the road to be analyzed, so that a traffic flow map corresponding to the road to be analyzed is constructed.

For example, as shown by a in fig. 5, the position point s2, the position point s3, the position point s4, and the position point s5 are arranged around the position point s1, and in the obtained traffic flow chart, as shown by b in fig. 5, the target pixel s21 corresponding to the position point s2, the target pixel s31 corresponding to the position point s3, the target pixel s41 corresponding to the position point s4, and the target pixel s51 corresponding to the position point s5 are arranged around the target pixel s11 corresponding to the position point s 1.

Generally, the area formed by the target pixels is not a regular area, so, in order to make the traffic flow map more regular, an initial image may be obtained, a pixel at the center of the initial image is taken as a target pixel corresponding to a key position point in the area indicated by the position information of the road to be analyzed (may be a center-most position point in the area indicated by the position information of the road to be analyzed), the target pixels corresponding to the key position points are taken as bases, according to the arrangement between the position points in the area indicated by the position information of the road to be analyzed, the target pixels corresponding to the position points in the area indicated by the position information of the road to be analyzed are determined from the initial image, then, the pixel value of the target pixels in the initial image is adjusted to the target traffic flow of the corresponding position points, and the pixel values of other pixels in the initial image except for the target pixels are adjusted to preset pixel values (for example, the preset pixel values may be 0), so as to obtain the initial image with the adjusted pixel values as the traffic flow map.

The method comprises the steps that a region indicated by position information of a road to be analyzed can be shot through a camera or electronic equipment provided with the camera, and a shot image is obtained and used as the initial image. The initial image may include at least an area indicated by the position information of the road to be analyzed, and the initial image may further include other areas than the area indicated by the position information of the road to be analyzed. For example, a building A3 and a park A4 exist around the area indicated by the position information of the road to be analyzed, and the initial image may further include the building A3 and the park A4.

As shown in fig. 6, a in fig. 6 shows a schematic view of the anchor point and the movement trace, and b in fig. 6 shows a schematic view of the traffic flow map determined based on a in fig. 6 showing the anchor point and the movement trace.

As can be seen from the foregoing, the road to be analyzed in the traffic flow chart corresponds to the target pixel, so that at least one first reference pixel can be selected from the target pixels in the traffic flow chart; determining a neighborhood pixel region of each first reference pixel in the traffic flow chart; determining a reference pixel value of each first reference pixel according to the pixel value of each pixel in the neighborhood pixel region of each first reference pixel; and determining the traffic flow density corresponding to the road to be analyzed according to the reference pixel value of each first reference pixel in the traffic flow diagram.

In other embodiments, determining the traffic flow density corresponding to the road to be analyzed according to the traffic flow map may include: selecting at least one first reference pixel from all target pixels of the traffic flow chart; determining a neighborhood pixel region of each first reference pixel in the traffic flow chart; determining a reference pixel value of each first reference pixel according to the pixel value of each pixel in the neighborhood pixel region of each first reference pixel; and determining the traffic flow density corresponding to the road to be analyzed according to the reference pixel value of each first reference pixel in the traffic flow diagram.

In general, the number of target pixels in the traffic flow chart is large, in order to improve the data processing efficiency, at least one first reference pixel may be selected from the target pixels in the traffic flow chart, and then the traffic flow density corresponding to the road to be analyzed is determined according to the pixel values of the pixels in the neighborhood pixel region of the first reference pixel.

For example, a pixel region formed by the target pixels in the traffic flow map may be taken as an effective flow region, and at least one first reference pixel may be selected in the effective flow region. For example, the center line position information of the road to be analyzed may be determined according to the position information of the road to be analyzed, and then at least one first reference pixel may be selected from an area (a line in the traffic flow map) that matches an area (the area is a line) indicated by the center line position information of the road to be analyzed in the effective flow area; as another example, at least one first reference pixel may be selected directly in the active traffic region.

For example, the effective flow area may be divided into a plurality of second blocks, one pixel is selected as the first reference pixel in each second block, and the size of each second block may be determined based on the image size of the initial image (or traffic flow map) and the actual area of the indicated actual area, for example, the actual area of the indicated actual area of the initial image (or traffic flow map) is 400 square meters, and the image size of the initial image (or traffic flow map) is 1000×1000 pixels, and the size of each second block in the effective flow area is 50×50 pixels.

As another example, a pixel may be selected as a first reference pixel every second number of pixels in an area matching an area indicated by the center line position information of the road to be analyzed in the effective traffic area, where the second number may be determined based on an image size of the initial image (or traffic flow chart) and an actual area of the indicated actual area, for example, the actual area of the indicated actual area of the initial image (or traffic flow chart) is 400 square meters, and the image size of the initial image (or traffic flow chart) is 1000×1000 pixels, and then the second number is 49.

After the first reference pixels are obtained, a neighborhood pixel region of each first reference pixel is determined in the traffic flow diagram. The neighborhood pixel region of the first reference pixel refers to a pixel region surrounding the first reference pixel in the traffic flow map, and the neighborhood pixel region of the first reference pixel includes the first reference pixel and the neighborhood pixels of the first reference pixel (i.e., pixels directly adjacent to or indirectly adjacent to the first reference pixel).

For example, a rectangular pixel region may be constructed in the traffic flow chart with each first reference pixel as a neighborhood pixel region corresponding to each first reference pixel, and for example, a closed pixel region (may be a closed pixel region of any shape) including each first reference pixel may be constructed in the traffic flow chart as a neighborhood pixel region corresponding to each first reference pixel. The area of the neighborhood pixel region corresponding to the first reference pixel is determined based on the actual area indicated by each pixel in the initial image (or the traffic flow chart), for example, the actual area indicated by each pixel in the initial image (or the traffic flow chart) is 0.04 square meter, and then the area of the neighborhood pixel region corresponding to the first reference pixel is 5×5 pixels.

Obtaining a neighborhood pixel region corresponding to each first reference pixel, and summing pixel values of pixels in the neighborhood pixel region corresponding to each first reference pixel to obtain a reference pixel value of each first reference pixel of a road to be analyzed; then, the reference pixel values of the first reference pixels in the traffic flow chart are averaged to obtain the traffic flow density corresponding to the road to be analyzed, and at this time, the traffic flow density calculation process corresponding to the road to be analyzed refers to formulas III and IV, wherein the formulas III and IV are as follows:

(III)

(IV)

Wherein,for the reference pixel value corresponding to the first reference pixel, n is the total number of pixels in the neighborhood pixel region corresponding to the first reference pixel, +.>For the pixel value of each pixel in the neighborhood pixel region corresponding to the first reference pixel, m is the total number of the first reference pixels selected for the road to be analyzed, < + >>And the traffic flow density corresponding to the road to be analyzed.

As shown in fig. 7, based on the traffic flow map, the pixels through which the line 50 passes in the traffic flow map are determined to form a candidate traffic flow area, in the candidate traffic flow area, the first reference pixel 51, the first reference pixel 52 and the first reference pixel 53 are determined, respectively, a 5×5 neighborhood pixel area is constructed by taking the 3 first reference pixels as the center, so as to obtain a neighborhood pixel area 511 of the first reference pixel 51, a neighborhood pixel area 521 of the first reference pixel 52 and a neighborhood pixel area 531 of the first reference pixel 53, wherein each box in the neighborhood pixel area represents one pixel, the value in the box is a pixel value, the traffic flow density of the pixel corresponding to the first reference pixel 51 (the pixel value of which is 45) is 20.12, the traffic flow density of the pixel corresponding to the first reference pixel 52 (the pixel value of which is 55) is 489, the traffic flow density of the pixel corresponding to the first reference pixel 53 (the pixel value of which is 90) is 510, and at this time, the traffic density of the road to be analyzed is 500.7.

And S140, determining the road similarity corresponding to the road to be analyzed according to the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map.

The second electronic map may refer to a different electronic map than the first electronic map. The road shape information may refer to line information of a road to be analyzed in the electronic map, and may be indicated by shape points, one of which refers to a point in the electronic map for describing one actual position point in the actual environment. At this time, the shape information of the road in the electronic map is described by a shape point string (the shape point string may be a point string constituted by each shape point in the center line of the road to be analyzed), and the shape information may include a plurality of shape points and position information of each shape point; for example, the shape information of the road may be the longitude and latitude values of representative points of [ (lon_1, lat_1), (lon_2, lat_2), (lon_3, lat_3) … ], lon and lat. The road shape information of the road to be analyzed can be directly obtained from the first electronic map.

In some embodiments, the area indicated by the position information of the road to be analyzed may be determined based on the position information of the road to be analyzed presented in the first electronic map, and then the shape information of the area indicated by the position information of the road to be analyzed in the second electronic map may be acquired. For example, a shape point string for describing the center line of the object may be acquired as shape information of the area indicated by the position information of the road to be analyzed in the second electronic map; the target center line may refer to a center line of the road to be analyzed in an extending direction in a region indicated by the position information of the road to be analyzed; for example, the road to be analyzed is in the east-west direction, a center line in the east-west direction in the region indicated by the position information of the road to be analyzed is taken as a target center line, and then a shape point string describing the target center line is acquired as the shape information of the region indicated by the position information of the road to be analyzed in the second electronic map.

In other embodiments, a target area including an area indicated by the position information of the road to be analyzed may be obtained, then a local electronic map located in the target area in the second electronic map is obtained, the road shapes of the roads are drawn according to the position information of the roads in the local electronic map, so as to obtain a road network shape corresponding to the local electronic map, and then shape information of each road shape in the road network shape is obtained as shape information of the area indicated by the position information of the road to be analyzed in the second electronic map. The shape information of the area indicated by the position information of the road to be analyzed in the second electronic map is 1, the shape information of the area indicated by the position information of the road to be analyzed in the second electronic map is a plurality of road shapes in the road network shape, and the shape information of the area indicated by the position information of the road to be analyzed in the second electronic map is a plurality of road shapes.

As shown in fig. 8, a in fig. 8 shows a schematic diagram of an electronic map corresponding to a target area, a in fig. 8 shows a schematic diagram of an electronic map of a target area, and b in fig. 8 shows a road network shape corresponding to a in fig. 8.

After the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map are obtained, the road similarity corresponding to the road to be analyzed can be determined according to the similarity between the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information of the road to be analyzed in the second electronic map.

For example, the second electronic map is one, and the shape information of the region indicated by the position information of the road to be analyzed in the second electronic map is also one, then the similarity between the shape information of the road to be analyzed in the first electronic map and the shape information of the region indicated by the position information in the second electronic map is directly calculated and is used as the road similarity corresponding to the road to be analyzed.

For another example, the second electronic map is one, and the shape information of the region indicated by the position information of the road to be analyzed in the second electronic map is a plurality of, then the similarity between the shape information of the road to be analyzed in the first electronic map and each corresponding shape information of the region indicated by the position information in the second electronic map is directly calculated, and then the maximum value in the calculated similarity is obtained and is used as the road similarity corresponding to the road to be analyzed.

For example, the number of the second electronic maps is multiple, the similarity between the road shape information of the road to be analyzed in the first electronic map and the corresponding shape information of the region indicated by the position information of the road to be analyzed in the second electronic map is determined and calculated for each second electronic map, the similarity is used as the single map similarity corresponding to the second electronic map (if the number of the shape information of the region indicated by the position information of the road to be analyzed in the second electronic map is multiple, the similarity between the road shape information of the road to be analyzed and the road shape information of the road to be analyzed in the first electronic map is determined for each shape information of the region indicated by the position information of the road to be analyzed in the second electronic map, then the maximum value is selected from the similarities between the road shape information of the road to be analyzed and the road shape information of the road to be analyzed in the first electronic map, and the single map corresponding to the second electronic map is used as the single similarity corresponding to the second electronic map, and then the single map similarity corresponding to the road to be analyzed is averaged to obtain the road similarity corresponding to be analyzed.

In some embodiments, the road shape information of the road to be analyzed in the first electronic map includes position information of each of a plurality of first shape points, and the shape information of the area indicated by the position information in the second electronic map includes position information of each of a plurality of second shape points; according to the similarity between the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map, determining the road similarity corresponding to the road to be analyzed comprises the following steps: determining a matching shape point matching each of the first shape points from the plurality of second shape points; determining relative parameters between the first shape point and the corresponding matching shape point according to the position information of the first shape point and the position information of the corresponding matching shape point, wherein the relative parameters comprise relative distance and relative angle; determining the similarity between the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map according to the relative parameters between each first shape point and the corresponding matched shape point; and determining the road similarity corresponding to the road to be analyzed according to the similarity between the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map.

In this embodiment, for each first shape point, a second shape point closest to the first shape point is obtained as a matching shape point matching the first shape point, and then a relative distance and a relative angle between the first shape point and the corresponding matching shape point are determined as relative parameters between the first shape point and the corresponding matching shape point according to the position information of the first shape point and the position information of the corresponding matching shape point.

Traversing all the first shape points, determining relative parameters between each first shape point and the corresponding matching shape point, then carrying out weighted summation on relative distance and relative angle between each first shape point and the corresponding matching shape point (the relative distance and the relative angle can be values set based on requirements, wherein the relative distance can be greater than the relative angle), obtaining similarity parameters corresponding to each first shape point, and carrying out summation or averaging on the similarity parameters corresponding to each first shape point to obtain the similarity between the road shape information of the road to be analyzed in the first electronic map and the shape information of the region indicated by the position information in the second electronic map.

And finally, the similarity between the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map can be used as the road similarity corresponding to the road to be analyzed.

The similarity between the road shape information of the road to be analyzed in the first electronic map and the shape information of the region indicated by the position information in the second electronic map may be a number between [0-1], the greater the number is, the higher the similarity is, the more likely the actual region represented by the two shape information from different electronic maps is the same road in the real world, and otherwise, the different roads in the real world are. For the road to be analyzed, if the road to be analyzed is also found in other electronic maps, the probability that the road to be analyzed is a redundant road in the first electronic map is lower, otherwise, if the road to be analyzed is not found in other maps, the probability that the road to be analyzed is a redundant road in the first electronic map is higher.

And S150, determining a redundant detection result of the road to be analyzed in the first electronic map according to at least two of the observable proportion, the traffic flow density and the road similarity.

After the observable proportion of the road to be split in the remote sensing image, the traffic flow density corresponding to the road to be analyzed and the corresponding road similarity are obtained, the redundant detection result of the road to be analyzed in the first electronic map can be comprehensively determined according to at least two of the three information. The redundancy detection result is used for indicating whether the road to be analyzed is a redundant road in the first electronic map. If the road to be analyzed is a redundant road in the first electronic map, the road to be analyzed presented in the first electronic map does not exist in the actual environment; if the road to be analyzed is not a redundant road in the first electronic map, the road to be analyzed presented in the first electronic map is presented in the actual environment.

When the observable ratio is smaller than the observable ratio threshold, the road to be analyzed is hard to observe in the remote sensing image, and the possibility that the road to be analyzed is a redundant road is high; when the traffic flow density is smaller than the traffic flow density threshold value, the method indicates that positioning points and moving tracks appearing in the road to be analyzed are fewer, and the possibility that the road to be analyzed is a redundant road is higher; and under the condition that the road similarity is smaller than the road similarity threshold, the probability that the road to be analyzed appears in other electronic maps is lower, and the probability that the road to be analyzed is a redundant road is higher.

Therefore, in some embodiments, at least two of the observable proportion, the traffic flow density and the road similarity may be obtained, and at least one of the obtained at least two is smaller than the corresponding threshold value, so as to obtain a redundant detection result that the road to be analyzed is a redundant road in the first electronic map. For example, obtaining at least two of the observable proportion and the traffic flow density, and obtaining a redundant detection result that the road to be analyzed is a redundant road in the first electronic map when any one of the observable proportion is smaller than an observable proportion threshold value and the traffic flow density is smaller than a traffic flow density threshold value occurs; for another example, at least two of the two are observable proportion and road similarity, and when any one of the observable proportion and the road similarity is smaller than an observable proportion threshold value and the road similarity is smaller than a road similarity threshold value, a redundant detection result that the road to be analyzed is a redundant road in the first electronic map is obtained.

In another embodiment, the observable ratio, the traffic flow density and the road similarity may be obtained, and when at least one of the observable ratio is smaller than the observable ratio threshold, the traffic flow density is smaller than the traffic flow density threshold and the road similarity is smaller than the road similarity threshold occurs, a redundant detection result that the road to be analyzed is a redundant road in the first electronic map is obtained; in another embodiment, when at least two of the observable ratio is smaller than the observable ratio threshold, the traffic density is smaller than the traffic density threshold, and the road similarity is smaller than the road similarity threshold, a redundant detection result that the road to be analyzed is a redundant road in the first electronic map may be obtained; in still another embodiment, the redundant detection result of the road to be analyzed on the first electronic map as the redundant road may be obtained when the observable ratio is smaller than the observable ratio threshold, the traffic density is smaller than the traffic density threshold, and the road similarity is smaller than the road similarity threshold. The observable ratio threshold, the traffic flow density threshold, and the road similarity threshold may be values set based on requirements, which are not limited in this application.

In some embodiments, at least two of the observable proportion, the traffic flow density and the road similarity corresponding to the road to be analyzed may be input into a redundant road analysis model, so as to obtain a probability value that the road to be analyzed is predicted to be a redundant road; if the probability value of the road to be analyzed predicted as the redundant road is smaller than the probability threshold value, obtaining a redundant detection result that the road to be analyzed is not the redundant road in the first electronic map; and if the probability value of the road to be analyzed predicted as the redundant road is not less than the probability threshold value, obtaining a redundant detection result of the road to be analyzed as the redundant road in the first electronic map. Wherein, the redundant road analysis model can be a logistic regression model, a neural network model and the like, and the probability threshold can be 0.7, 0.6, 0.8 and the like.

For example, a neural network model initialized by parameters may be obtained, sample data is obtained, the sample data includes sample related data corresponding to a sample road (the sample related data includes at least two of an observable ratio, a traffic density, and a road similarity corresponding to the sample road) and a redundancy label (the sample road is a redundancy road, the redundancy label is 1, the sample road is not a redundancy road, the redundancy label is 0, and the sample data may also include at least two of an observable ratio, a traffic density, and a road similarity of the sample road), the neural network model initialized by parameters is trained by the sample data, and the trained neural network model is obtained as a redundancy road analysis model. At this time, at least two of the observable proportion, the traffic flow density and the road similarity (at least two corresponding to the sample related data, for example, the sample related data is the observable proportion, the traffic flow density corresponding to the sample road, and the road similarity corresponding to the sample road are directly input into the redundant road analysis model, and for example, the sample related data is the observable proportion, the traffic flow density and the road similarity corresponding to the sample road, and the observable proportion, the traffic flow density and the road similarity corresponding to the sample road are input into the redundant road analysis model, so as to obtain the probability value of predicting the road to be analyzed as the redundant road.

For example, a logistic regression model initialized by parameters can be obtained, and the sample data is used for training the logistic regression model initialized by the parameters according to the sample data, wherein the sample data corresponds to the sample related data, and the sample data corresponds to the observable proportion, traffic flow density and road similarity of the sample road. At this time, the observable proportion, traffic flow density and road similarity corresponding to the road to be analyzed are directly input into a redundant road analysis model to obtain the score of the road to be analyzed as the redundant road, and then the score of the road to be analyzed as the redundant road is calculated to obtain the probability value of the road to be analyzed predicted as the redundant road. The process of determining the probability value of the road to be analyzed predicted as the redundant road by the redundant road analysis model based on the logistic regression model can be expressed as a formula five and a formula six, wherein the formula five and the formula six are as follows:

(V)/(V)>

(six)

Wherein,scoring redundant roads for the road to be analyzed, < ->、/>、/>、/>Training for redundant road analysis modelTraining the determined weight parameters +.>、/>、/>、/>The method can be solved by an optimization method such as Newton method based on sample data; />The probability value of the redundant road is predicted for the road to be analyzed, and the probability value is a floating point number between (0 and 1); e is a natural constant. / >For the observable proportion of the road to be analyzed, +.>For the traffic flow density corresponding to the road to be analyzed, < >>And the similarity of the roads corresponding to the roads to be analyzed is obtained.

After obtaining the probability value of the road to be analyzed predicted as the redundant road, if the probability value of the road to be analyzed predicted as the redundant road is smaller than the probability threshold value, obtaining a redundant detection result that the road to be analyzed is not the redundant road in the first electronic map; and if the probability value of the road to be analyzed predicted as the redundant road is not less than the probability threshold value, obtaining a redundant detection result of the road to be analyzed as the redundant road in the first electronic map.

It should be noted that when the redundant detection result of the road to be analyzed in the first electronic map is determined according to the two of the observable proportion, the traffic flow density and the road similarity corresponding to the road to be analyzed, the other road not used may not be acquired. For example, when the other one that is not used is an observable ratio corresponding to the road to be analyzed, the remote sensing image may not be analyzed (i.e., S110-S120 are not performed); as another example, when the other one that is not used is the traffic flow density corresponding to the road to be analyzed, the analysis of the traffic flow density may not be performed (i.e., S130 is not performed); for another example, if the other one that is not used is the road similarity, the analysis of the road similarity may not be performed (i.e., S140 is not performed).

In this embodiment, if there are multiple roads to be analyzed, respective redundant detection results may be determined for each road to be analyzed according to the foregoing manners of S110-S150, which are not described herein.

Table 1 shows the accuracy of redundant road analysis for non-isolated roads by different methods, table 1 is as follows:

TABLE 1

Wherein, the related art [1] means: isolated roads in the existing road network are mined from the topological connectivity perspective as redundant roads. The limitation of the method is that non-isolated redundant roads in the road network cannot be identified, so that the method has the accuracy of judging the redundant roads of the non-isolated roads as 0.

The related art [2] means: and determining the similarity of the form points of the road lines and the remote sensing road lines in the road network as the judgment basis of the redundant road. Although the method can excavate non-isolated redundant roads, the influence of the road track and remote sensing precision deviation on the redundant road judgment is not considered. For example, even if a road is not observable on the remote sensing image, when a track passes on the road, it can be deduced that the road still exists, and the road cannot be deleted as a redundant road. Therefore, the redundancy check of the related art [2] is also low in accuracy.

As can be seen from table 1, in this embodiment, by combining four different types of road information, namely the remote sensing image, the number of times of taking the location point as the locating point, the number of moving tracks passing through each location point, and the shape information of the road to be analyzed in the electronic map, it is determined whether the road to be analyzed is redundant, and the accuracy is high.

In the application, the observable proportion of a road to be analyzed in a remote sensing image is determined according to the remote sensing image; determining the traffic flow density corresponding to the road to be analyzed according to the times of taking each position point in the area indicated by the position information as a locating point and the number of moving tracks passing through each position point; determining the road similarity corresponding to the road to be analyzed according to the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map; then, according to at least two of observable proportion, traffic flow density and road similarity, a redundant detection result of the road to be analyzed in the first electronic map is determined, so that whether the road to be analyzed is redundant or not is judged by combining remote sensing images, the number of times of taking the position points as positioning points, the number of moving tracks passing through the position points and at least three of road information in four different forms of shape information of the road to be analyzed in the electronic map, multi-angle analysis of redundant detection is realized, and the mode of detecting the redundant road only through the road similarity in different electronic maps is intersected.

In an embodiment, after S150, the method may further include:

and if the redundant detection result is that the road to be analyzed is the redundant road in the first electronic map, deleting the road to be analyzed in the first electronic map.

As shown in fig. 9, based on the position information of the road to be analyzed, a remote sensing image presenting the area indicated by the position information is acquired, the number of times each position point in the area indicated by the position information is used as a locating point and the number of moving tracks passing through each position point are determined, and road networks of the target area in the first electronic map and the second electronic map are determined.

The road feature of the remote sensing image (i.e. the pixel values of the pixels in the respective neighborhood pixel region of the second reference pixel in the previous embodiment) may be determined based on the remote sensing image: pixel values of pixels in respective neighborhood pixel regions of at least one second reference pixel are determined. And then, according to the road characteristics of the remote sensing image, determining the observable proportion of the remote sensing image related redundant road characteristics, namely the road to be analyzed, in the remote sensing image.

The trajectory and anchor point road characteristics (i.e., the traffic flow map in the foregoing embodiment) may be determined based on the number of times the location point is regarded as an anchor point and the number of moving trajectories through each location point: and constructing a traffic flow chart by taking the position points as the times of locating points and the number of moving tracks passing through each position point. And then determining the related redundant road characteristics of the track and the locating point, namely the traffic flow density corresponding to the road to be analyzed, according to the road characteristics of the track and the locating point.

The road shape characteristics (that is, the road shape information of the road to be analyzed in the foregoing embodiment in the first electronic map and the shape information of the area indicated by the position information in the second electronic map) may be determined based on the road network of the target area in the first electronic map and the road network in the second electronic map: and determining the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map based on the road network of the target area in the first electronic map and the road network of the second electronic map. And then determining the road shape related redundant road characteristics, namely the road similarity, according to the road shape characteristics.

And then, combining the remote sensing image related redundant road characteristics (the observable proportion of the road to be analyzed in the remote sensing image), the track and positioning point related redundant road characteristics (the traffic flow density corresponding to the road to be analyzed) and the road shape related redundant road characteristics (the road similarity corresponding to the road to be analyzed) to carry out redundant road judgment.

And if the road to be analyzed is determined to be the redundant road in the first electronic map, deleting the road to be analyzed in the first electronic map directly, and if the road to be analyzed is determined not to be the redundant road in the first electronic map, keeping the road to be analyzed in the first electronic map.

If the electronic map includes redundant roads, the navigation path may include redundant roads when the navigation path is planned through the electronic map. If one road exists in the navigation path and is not in the real world, the user finds that the road does not exist when arriving at the road position, and then the user needs to bypass other roads to arrive at the destination, which greatly influences the user experience. Therefore, in this embodiment, after the road to be analyzed is determined to be the redundant road, the road to be analyzed is deleted in the first electronic map, so that the first electronic map is more accurate and effective, the situation that the first electronic map is inaccurate due to the existence of the redundant road in the first electronic map, and when the navigation path is planned according to the first electronic map to include the redundant road, a user needs to bypass to reach the destination is avoided, and the use experience of the first electronic map is improved.

Meanwhile, the road to be analyzed is deleted from the first electronic map, so that the data volume of the first electronic map is reduced, the invalid redundant road is prevented from occupying extra storage space, and the available storage space of the electronic equipment is increased.

Referring to fig. 10, fig. 10 shows a block diagram of a redundant road detection apparatus according to an embodiment of the present application, and an apparatus 1100 includes:

An obtaining module 1110, configured to obtain, based on location information of a road to be analyzed that is presented in the first electronic map, a remote sensing image of an area indicated by the presentation location information;

the first determining module 1120 is configured to determine an observable proportion of the road to be analyzed in the remote sensing image according to the remote sensing image;

a second determining module 1130, configured to determine a traffic flow density corresponding to the road to be analyzed according to the number of times that each location point in the area indicated by the location information is used as a locating point and the number of moving tracks passing through each location point;

a third determining module 1140, configured to determine a road similarity corresponding to the road to be analyzed according to the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map;

the result determining module 1150 is configured to determine a redundant detection result of the road to be analyzed in the first electronic map according to at least two of the observable ratio, the traffic density and the road similarity.

Optionally, the second determining module 1130 is further configured to determine a traffic flow value of each location point according to the number of times that each location point in the area indicated by the location information is used as a locating point and the number of moving tracks passing through each location point; generating a traffic flow diagram corresponding to the road to be analyzed based on traffic flow values of all the position points, wherein the traffic flow diagram comprises target pixels representing all the position points in the area indicated by the position information; the pixel value of the target pixel is determined according to the traffic flow value of the position point corresponding to the target pixel; and determining the traffic flow density corresponding to the road to be analyzed according to the traffic flow map corresponding to the road to be analyzed.

Optionally, the second determining module 1130 is further configured to select at least one first reference pixel from the target pixels in the traffic flow map; determining a neighborhood pixel region of each first reference pixel in the traffic flow chart; determining a reference pixel value of each first reference pixel according to the pixel value of each pixel in the neighborhood pixel region of each first reference pixel; and determining the traffic flow density corresponding to the road to be analyzed according to the reference pixel value of each first reference pixel in the traffic flow diagram.

Optionally, the second determining module 1130 is further configured to transform the traffic flow value of each location point into the target interval, so as to obtain a target traffic flow value corresponding to each location point; and taking the target traffic flow value corresponding to each position point as the pixel value of the target pixel corresponding to each position point to generate a traffic flow diagram corresponding to the road to be analyzed, wherein the target pixels are arranged in the traffic flow diagram according to the relative positions of the corresponding position points in the area indicated by the position information.

Optionally, the second determining module 1130 is further configured to perform a gap reduction process on the traffic flow values of the location points, to obtain a first intermediate traffic flow value of each location point; the gap reduction processing is used for reducing the difference between traffic flow values corresponding to different position points; normalizing the first intermediate traffic flow value of each position point into a target interval to obtain a second intermediate traffic flow value of each position point; and rounding the first intermediate traffic flow value of each position point to obtain a target traffic flow value corresponding to each position point.

Optionally, the first determining module 1120 is further configured to perform binarization processing on the remote sensing image to obtain a binarized image; the pixel values of the pixels representing the road in the binarized image are different from the pixel values of the pixels representing the non-road; selecting at least one second reference pixel from a target pixel region in the binarized image; the target pixel area is a pixel area of an area indicated by the presentation position information in the binarized image; determining a neighborhood pixel region of each second reference pixel in the binarized image; and determining the observable proportion of the road to be analyzed in the remote sensing image according to the pixel value of each pixel in the neighborhood pixel region of each second reference pixel in the binarized image.

Optionally, a pixel value of a pixel for representing a road in the binarized image is a target pixel value; the first determining module 1120 is further configured to determine, according to a duty ratio of a pixel having a pixel value of a neighborhood pixel area of each second reference pixel in the binarized image as a target pixel value, a road point attribute corresponding to each second reference pixel, where the road point attribute is a positive road point attribute or a negative road point attribute; and determining the observable proportion of the road to be analyzed in the remote sensing image according to the number of the second reference pixels of the positive road point attribute and the number of the second reference pixels of the negative road point attribute.

Optionally, the road shape information of the road to be analyzed in the first electronic map includes position information of each of a plurality of first shape points, and the shape information of the area indicated by the position information in the second electronic map includes position information of each of a plurality of second shape points; a third determining module 1140 further configured to determine a matching shape point from the plurality of second shape points that matches each of the first shape points; determining relative parameters between the first shape point and the corresponding matching shape point according to the position information of the first shape point and the position information of the corresponding matching shape point, wherein the relative parameters comprise relative distance and relative angle; determining the similarity between the road shape information and the shape information according to the relative parameters between each first shape point and the corresponding matching shape point; and determining the road similarity corresponding to the road to be analyzed according to the similarity.

Optionally, the result determining module 1150 is further configured to obtain a redundant detection result of the road to be analyzed being a redundant road in the first electronic map if the observable ratio is less than the observable ratio threshold, the traffic density is less than the traffic density threshold, and the road similarity is less than the road similarity threshold.

Optionally, the result determining module 1150 is further configured to input an observable ratio, a traffic flow density, and a road similarity corresponding to the road to be analyzed into the redundant road analysis model, so as to obtain a probability value of the road to be analyzed predicted as the redundant road; if the probability value of the road to be analyzed predicted as the redundant road is smaller than the probability threshold value, obtaining a redundant detection result that the road to be analyzed is not the redundant road in the first electronic map; and if the probability value of the road to be analyzed predicted as the redundant road is not less than the probability threshold value, obtaining a redundant detection result of the road to be analyzed as the redundant road in the first electronic map.

Optionally, the result determining module 1150 is further configured to delete the road to be analyzed in the first electronic map if the redundant detection result is that the road to be analyzed is a redundant road in the first electronic map.

It should be noted that, in the present application, the device embodiment and the foregoing method embodiment correspond to each other, and specific principles in the device embodiment may refer to the content in the foregoing method embodiment, which is not described herein again.

Fig. 11 shows a block diagram of an electronic device for performing a redundant road detection method according to an embodiment of the present application. The electronic device may be the server 10 or the terminal 20 in fig. 1, and it should be noted that, the computer system 1200 of the electronic device shown in fig. 11 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.

As shown in fig. 11, the computer system 1200 includes a central processing unit (Central Processing Unit, CPU) 1201 which can perform various appropriate actions and processes, such as performing the methods in the above-described embodiments, according to a program stored in a Read-Only Memory (ROM) 1202 or a program loaded from a storage section 1208 into a random access Memory (Random Access Memory, RAM) 1203. In the RAM 1203, various programs and data required for the system operation are also stored. The CPU1201, ROM1202, and RAM 1203 are connected to each other through a bus 1204. An Input/Output (I/O) interface 1205 is also connected to bus 1204.

The following components are connected to the I/O interface 1205: an input section 1206 including a keyboard, a mouse, and the like; an output portion 1207 including a Cathode Ray Tube (CRT), a liquid crystal display (Liquid Crystal Display, LCD), and a speaker, etc.; a storage section 1208 including a hard disk or the like; and a communication section 1209 including a network interface card such as a LAN (Local Area Network ) card, a modem, or the like. The communication section 1209 performs communication processing via a network such as the internet. The drive 1210 is also connected to the I/O interface 1205 as needed. A removable medium 1211 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed on the drive 1210 as needed, so that a computer program read out therefrom is installed into the storage section 1208 as needed.

In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network via the communication portion 1209, and/or installed from the removable media 1211. When executed by a Central Processing Unit (CPU) 1201, performs the various functions defined in the system of the present application.

It should be noted that, the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (Erasable Programmable Read Only Memory, EPROM), flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Where each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present application may be implemented by means of software, or may be implemented by means of hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.

As another aspect, the present application also provides a computer-readable storage medium that may be included in the electronic device described in the above embodiments; or may exist alone without being incorporated into the electronic device. The computer readable storage medium carries computer readable instructions which, when executed by a processor, implement the method of any of the above embodiments.

According to one aspect of embodiments of the present application, there is provided a computer program product comprising computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the electronic device to perform the method of any of the embodiments described above.

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 works together with other relevant parts to achieve a predetermined object, and may be implemented in whole or in part by using software, hardware (e.g., a processing circuit or a memory), or a combination thereof, and as such, a processor (or 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 of the module or unit function.

It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit, in accordance with embodiments of the present application. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a usb disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause an electronic device (may be a personal computer, a server, a touch terminal, or a network device, etc.) to perform the method according to the embodiments of the present application.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, one of ordinary skill in the art will appreciate that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not drive the essence of the corresponding technical solutions to depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A redundant roadway detection method, the method comprising:

acquiring a remote sensing image of an area indicated by the position information based on the position information of the road to be analyzed presented in the first electronic map;

according to the remote sensing image, determining the observable proportion of the road to be analyzed in the remote sensing image;

determining the traffic flow density corresponding to the road to be analyzed according to the times of taking each position point in the area indicated by the position information as a locating point and the number of moving tracks passing through each position point;

determining the road similarity corresponding to the road to be analyzed according to the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map;

and determining a redundant detection result of the road to be analyzed in the first electronic map according to at least two of the observable proportion, the traffic flow density and the road similarity.

2. The method according to claim 1, wherein the determining the traffic density corresponding to the road to be analyzed according to the number of times each location point in the area indicated by the location information is used as a locating point and the number of moving tracks passing through each location point comprises:

Determining the traffic flow value of each position point according to the times of taking each position point in the area indicated by the position information as a locating point and the number of moving tracks passing through each position point;

generating a traffic flow diagram corresponding to the road to be analyzed based on the traffic flow value of each position point, wherein the traffic flow diagram comprises target pixels representing each position point in the area indicated by the position information; the pixel value of the target pixel is determined according to the traffic flow value of the position point corresponding to the target pixel;

and determining the traffic flow density corresponding to the road to be analyzed according to the traffic flow map corresponding to the road to be analyzed.

3. The method according to claim 2, wherein the determining the traffic density corresponding to the road to be analyzed according to the traffic flow map corresponding to the road to be analyzed includes:

selecting at least one first reference pixel from target pixels of the traffic flow map;

determining a neighborhood pixel region of each first reference pixel in the traffic flow chart;

determining a reference pixel value of each first reference pixel according to the pixel value of each pixel in the neighborhood pixel region of each first reference pixel;

And determining the traffic flow density corresponding to the road to be analyzed according to the reference pixel value of each first reference pixel in the traffic flow map.

4. The method according to claim 2, wherein the generating a traffic flow map corresponding to the road to be analyzed based on the traffic flow values of the location points includes:

transforming the traffic flow value of each position point into a target interval to obtain a target traffic flow value corresponding to each position point;

and generating a traffic flow diagram corresponding to the road to be analyzed by taking the target traffic flow value corresponding to each position point as the pixel value of the target pixel corresponding to each position point, wherein the target pixels are arranged in the traffic flow diagram according to the relative positions of the corresponding position points in the area indicated by the position information.

5. The method of claim 4, wherein transforming the traffic flow value of each location point into the target interval to obtain the target traffic flow value corresponding to each location point comprises:

performing gap reduction processing on the traffic flow values of the position points to obtain first intermediate traffic flow values of the position points; the gap reduction processing is used for reducing the difference between traffic flow values corresponding to different position points;

Normalizing the first intermediate traffic flow value of each position point to a target interval to obtain a second intermediate traffic flow value of each position point;

and rounding the first intermediate traffic flow value of each position point to obtain a target traffic flow value corresponding to each position point.

6. The method of claim 1, wherein said determining an observable proportion of the road to be analyzed in the remote sensing image from the remote sensing image comprises:

performing binarization processing on the remote sensing image to obtain a binarized image; the pixel values of the pixels representing the road in the binarized image are different from the pixel values of the pixels representing the non-road;

selecting at least one second reference pixel from a target pixel region in the binarized image; the target pixel area is a pixel area presenting an area indicated by the position information in the binarized image;

determining a neighborhood pixel region of each second reference pixel in the binarized image;

and determining the observable proportion of the road to be analyzed in the remote sensing image according to the pixel value of each pixel in the neighborhood pixel region of each second reference pixel in the binarized image.

7. The method according to claim 6, wherein a pixel value of a pixel for representing a road in the binarized image is a target pixel value;

the determining the observable proportion of the road to be analyzed in the remote sensing image according to the pixel values of each pixel in the neighborhood pixel region of each second reference pixel in the binarized image comprises the following steps:

determining a road point attribute corresponding to each second reference pixel according to the duty ratio of a pixel with a pixel value being a target pixel value in a neighborhood pixel region of each second reference pixel in the binarized image, wherein the road point attribute is a positive road point attribute or a negative road point attribute;

and determining the observable proportion of the road to be analyzed in the remote sensing image according to the number of the second reference pixels of the positive road point attribute and the number of the second reference pixels of the negative road point attribute.

8. The method according to claim 1, wherein the road shape information of the road to be analyzed in the first electronic map includes position information of each of a plurality of first shape points, and the shape information of the area indicated by the position information in the second electronic map includes position information of each of a plurality of second shape points;

The determining the road similarity corresponding to the road to be analyzed according to the similarity between the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map comprises the following steps:

determining a matching shape point from the plurality of second shape points that matches each of the first shape points;

determining relative parameters between the first shape point and the corresponding matching shape point according to the position information of the first shape point and the position information of the corresponding matching shape point, wherein the relative parameters comprise relative distance and relative angle;

determining the similarity between the road shape information and the shape information according to the relative parameters between each first shape point and the corresponding matching shape point;

and determining the road similarity corresponding to the road to be analyzed according to the similarity.

9. The method of claim 1, wherein the determining a redundant detection result of the road to be analyzed in the first electronic map according to at least two of the observable ratio, the traffic density, and the road similarity comprises:

And if the observable ratio is smaller than an observable ratio threshold, the traffic flow density is smaller than a traffic flow density threshold and the road similarity is smaller than a road similarity threshold, obtaining a redundant detection result that the road to be analyzed is a redundant road in the first electronic map.

10. The method of claim 1, wherein the determining a redundant detection result of the road to be analyzed in the first electronic map according to at least two of the observable ratio, the traffic density, and the road similarity comprises:

inputting the observable proportion, traffic flow density and road similarity corresponding to the road to be analyzed into a redundant road analysis model to obtain a probability value of the road to be analyzed predicted as the redundant road;

if the probability value of the road to be analyzed predicted as the redundant road is smaller than a probability threshold value, obtaining a redundant detection result that the road to be analyzed is not the redundant road in the first electronic map;

and if the probability value of the road to be analyzed predicted as the redundant road is not less than the probability threshold value, obtaining a redundant detection result of the road to be analyzed as the redundant road in the first electronic map.

11. The method of claim 1, wherein after determining the redundant detection result of the road to be analyzed in the first electronic map according to the observable ratio, traffic density, and road similarity, the method further comprises:

and if the redundancy detection result is that the road to be analyzed is a redundant road in the first electronic map, deleting the road to be analyzed in the first electronic map.

12. A redundant roadway detection apparatus, the apparatus comprising:

the acquisition module is used for acquiring a remote sensing image of an area indicated by the position information based on the position information of the road to be analyzed presented in the first electronic map;

the first determining module is used for determining the observable proportion of the road to be analyzed in the remote sensing image according to the remote sensing image;

the second determining module is used for determining the traffic flow density corresponding to the road to be analyzed according to the times of taking each position point in the area indicated by the position information as a locating point and the number of moving tracks passing through each position point;

the third determining module is used for determining the road similarity corresponding to the road to be analyzed according to the road shape information of the road to be analyzed in the first electronic map and the shape information of the area indicated by the position information in the second electronic map;

And the result determining module is used for determining a redundant detection result of the road to be analyzed in the first electronic map according to at least two of the observable proportion, the traffic flow density and the road similarity.

13. An electronic device, comprising:

a processor;

a memory having stored thereon computer readable instructions which, when executed by the processor, implement the method of any of claims 1-11.

14. A computer readable storage medium having computer readable instructions stored thereon, which when executed by a processor, implement the method of any of claims 1-11.

15. A computer program product comprising computer instructions which, when executed by a processor, implement the method of any of claims 1-11.