CN110796715A - Electronic map labeling method, device, server and storage medium - Google Patents

Electronic map labeling method, device, server and storage medium Download PDF

Info

Publication number
CN110796715A
CN110796715A CN201910792495.9A CN201910792495A CN110796715A CN 110796715 A CN110796715 A CN 110796715A CN 201910792495 A CN201910792495 A CN 201910792495A CN 110796715 A CN110796715 A CN 110796715A
Authority
CN
China
Prior art keywords
images
image
landmark
electronic map
results
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201910792495.9A
Other languages
Chinese (zh)
Other versions
CN110796715B (en
Inventor
陈超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN201910792495.9A priority Critical patent/CN110796715B/en
Publication of CN110796715A publication Critical patent/CN110796715A/en
Application granted granted Critical
Publication of CN110796715B publication Critical patent/CN110796715B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/20—Drawing from basic elements, e.g. lines or circles
    • G06T11/206—Drawing of charts or graphs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/60—Editing figures and text; Combining figures or text
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20021—Dividing image into blocks, subimages or windows

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Processing Or Creating Images (AREA)

Abstract

The invention provides an electronic map labeling method, an electronic map labeling device, a server and a storage medium, and belongs to the technical field of navigation. The method comprises the following steps: respectively splicing the plurality of first images and the plurality of second images to obtain a plurality of verification code images, wherein the second images are images comprising target characters, and the plurality of first images are sub-images obtained by segmenting the images of the landmark entities to be labeled; displaying a plurality of verification code images to a plurality of first users, and determining a plurality of first identification results of the first images according to the obtained identification results; determining the labeling information of the landmark entity according to a plurality of first recognition results of a plurality of first images; and marking the landmark entity on the electronic map according to the marking information. Because the subimage of the image of the landmark entity is displayed in the form of the verification code image, the identification and the labeling of the landmark entity with higher identification difficulty can be automatically completed, thereby greatly reducing the labor cost and improving the efficiency and the accuracy of the labeling.

Description

Electronic map labeling method, device, server and storage medium
Technical Field
The present invention relates to the field of navigation technologies, and in particular, to an electronic map labeling method, an electronic map labeling device, a server, and a storage medium.
Background
With the development of navigation technology, navigation software has become a necessity for people to travel at home. Wherever you want to go, the user can input the destination by only turning on the navigation software, and then can reach the destination according to the route marked on the electronic map by the navigation software. However, the electronic map in the current navigation software only marks the names of the main road and the landmark building, and still is inconvenient for accurate navigation.
In order to make navigation more accurate, when an electronic map is manufactured, an image acquisition device is generally used for acquiring images on two sides of each road, then an image recognition device is used for carrying out image recognition on the acquired images of the landmark entities, so as to obtain the labeling information of the landmark entities, and the labeling information is labeled in the electronic map, so that the content labeled on the electronic map is richer. For example, an image acquisition vehicle is used for shooting a picture of a signboard of a store approaching a street, and then characters in the signboard are used as annotation information of the store through an image recognition device.
The technical scheme has the following problems that because the content in the acquired image of the landmark entity does not have a fixed design rule or the shooting angle of the acquired image of the landmark entity is too large, the identification difficulty of partial images is high, the content in the image cannot be accurately identified by the image identification device, and the landmark entity corresponding to the image cannot be labeled on the electronic map.
Disclosure of Invention
The embodiment of the invention provides an electronic map labeling method, an electronic map labeling device, a server and a storage medium, which are used for solving the problem that at present, because the content in the collected image of a landmark entity is not provided with a fixed design rule or the shooting angle of the collected image of the landmark entity is too large, the difficulty in recognizing partial images is high, the image recognition equipment cannot accurately recognize the content in the image, and therefore the landmark entity corresponding to the image cannot be labeled on an electronic map. The technical scheme is as follows:
in one aspect, an electronic map labeling method is provided, and the method includes:
respectively splicing a plurality of first images and a plurality of second images to obtain a plurality of verification code images, wherein the second images comprise target characters, and the first images are sub-images obtained by segmenting the images of the landmark entities to be labeled;
displaying the verification code images to a plurality of first users, and determining a plurality of first identification results of the first images according to the obtained identification results;
determining the labeling information of the landmark entity according to a plurality of first recognition results of the plurality of first images;
and according to the labeling information, labeling the landmark entity on the electronic map.
In another aspect, an electronic map labeling apparatus is provided, the apparatus including:
the system comprises a splicing module, a storage module and a processing module, wherein the splicing module is used for respectively splicing a plurality of first images and a plurality of second images to obtain a plurality of verification code images, the second images are images comprising target characters, and the first images are sub-images obtained by segmenting images of landmark entities to be labeled;
the display module is used for displaying the verification code images to a plurality of first users and determining a plurality of first identification results of the first images according to the obtained identification results;
a first determining module, configured to determine, according to a plurality of first recognition results of the plurality of first images, annotation information of the landmark entity;
and the marking module is used for marking the landmark entity on the electronic map according to the marking information.
In one possible implementation, the apparatus further includes:
and the second determination module is used for determining a plurality of first users within a preset distance range from the landmark entity according to the geographical position information of the landmark entity.
In another possible implementation manner, the presentation module is further configured to present, for each verification code image, a second image portion in the verification code image to at least one first user in the plurality of first users; and when the information input by any first user is consistent with the target character included in the second image, displaying a first image part in the verification code image to the first user.
In another possible implementation manner, the presentation module is further configured to delete the recognition result fed back by the first user, which is out of a preset distance range from the landmark entity; for each first image, selecting a second recognition result corresponding to the first image from the rest recognition results; and taking the recognition result with the highest proportion in the second recognition results as the first recognition result of the first image.
In another possible implementation manner, the first determining module is further configured to arrange the plurality of first images according to a target order to obtain a third image, where the target order is an arrangement order of the first images in the image of the landmark entity; determining second text content, wherein the second text content comprises a target option and at least one interference item, and the target option is composed of first recognition results of the plurality of first images according to the target sequence; presenting the third image and the second textual content to a plurality of second users; and when the second user selecting the target option exceeds a target percentage, using the target option as the labeling information of the landmark entity.
In another possible implementation manner, the display module is further configured to divide each of the obtained recognition results into a first image recognition result corresponding to a first image and a second image recognition result corresponding to a second image; when the second image recognition result is inconsistent with the target character included in the corresponding second image, deleting the recognition result corresponding to the second image recognition result; for each first image, selecting a third recognition result comprising the first image recognition result corresponding to the first image from the rest recognition results; and determining a first recognition result of the first image according to at least one third recognition result corresponding to the first image.
In another possible implementation manner, the first determining module is further configured to determine an arrangement order of the plurality of first images in the image of the landmark entity; arranging a plurality of first recognition results of the plurality of first images according to the arrangement sequence; and taking the first text content obtained after arrangement as the labeling information of the landmark entity.
In another aspect, a server is provided, which includes a processor and a memory, where the memory is used to store program codes, and the program codes are loaded and executed by the processor to implement the operations executed in the electronic map labeling method in the embodiment of the present invention.
In another aspect, a storage medium is provided, in which program codes for executing an electronic map labeling method in an embodiment of the present invention are stored.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
the method comprises the steps of obtaining a plurality of verification code images by splicing a plurality of sub-images of an image of a landmark entity to be labeled with a plurality of second images including target characters, displaying the plurality of verification code images to a plurality of first users, determining a plurality of first identification results of the plurality of first images based on the obtained identification results of the plurality of first users, determining labeling information of the landmark entity according to the plurality of first identification results, and finally labeling the landmark entity on an electronic map according to the labeling information. Because the sub-images of the landmark entities are displayed in the form of the verification code images, and the marking information of the landmark entities is determined according to the identification results of the first users, the identification and marking of the landmark entities with high identification difficulty can be automatically completed, so that the labor cost is greatly reduced, and the marking efficiency and accuracy are improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a block diagram illustrating an electronic map service system 100 according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an electronic map labeling method according to an embodiment of the present invention;
fig. 3 is a schematic split view of an image of a landmark entity according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating a verification code input interface according to an embodiment of the present invention;
fig. 5 is a block diagram of an electronic map labeling apparatus according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a server according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
The embodiment of the invention mainly relates to a scene for manufacturing an electronic map. Besides roads, the electronic map also comprises landmark entities, and the landmark entities can be malls, hospitals, residential buildings, shops, signposts, bus stop boards, subway stations and the like. The more landmark entities marked in the electronic map, the more detailed the electronic map is, for example, the names of the marginal shops are all marked on the electronic map; the less landmark entities labeled in the electronic map, the more schematic the electronic map is, for example, only a large mall, a hospital, a museum, etc. are labeled. That is, the detailed degree of the electronic map is positively correlated with the number of the landmark entities marked on the electronic map.
In order to make the electronic map as detailed as possible, landmark entities in the electronic map need to be labeled as much as possible when the electronic map is manufactured. Before labeling the landmark entity, it is necessary to capture an image of the landmark entity through an image capturing device, for example, a street shop, a subway station, a bus station, a shopping mall, a hospital, etc. are captured through an image capturing vehicle, or a special photographer captures an image of each landmark entity. After the image of the landmark entity is acquired, the acquired image of the landmark entity can be identified through image identification equipment, and the image of the landmark entity which cannot be identified, such as an image with an overlarge shooting angle, blurred image, stain trace, light spot, obscure words, artistic words or self-made words, needs to be identified through the method provided by the embodiment of the invention.
In the embodiment of the invention, the server can divide the image of the landmark entity to be labeled into a plurality of sub-images, process the sub-images and send the sub-images to a plurality of users in the form of the verification codes, the verification code images are displayed on the terminals used by the users, and the server determines the labeling information of the image of the landmark entity based on the obtained identification result, so that the landmark entity is labeled on the electronic map.
Fig. 1 is a block diagram of an electronic map service system 100 according to an embodiment of the present invention, and referring to fig. 1, the electronic map service system includes a plurality of terminals 101 and an electronic map service platform 102.
The terminal 101 is connected to the electronic map service platform 102 through a wireless network or a wired network. The terminal 101 may be at least one of a smartphone, a gaming console, a desktop computer, a tablet computer, and a laptop portable computer. The terminal 101 is installed with a plurality of applications, wherein at least one target application can be used for displaying the verification code image.
The electronic map service platform 102 includes one server or a plurality of servers. The electronic map service platform 102 is used for providing a verification code service for a target application program. Optionally, the electronic map service platform 102 may undertake a primary electronic map labeling work, and the terminal 101 undertakes a secondary electronic map labeling work; or the thermal remediation platform 102 can undertake secondary electronic map labeling work, and the terminal 101 undertakes primary electronic map labeling work; or the terminal 101 may solely undertake the electronic map annotation process.
Optionally, the electronic map service platform 102 includes: the system comprises an access server, a database and a marking server. The access server is used to provide access services for the terminal 101. The marking server is used for providing background services related to the kicking electronic map marking. The annotation server can be one or more. When the number of the annotation servers is multiple, there are at least two annotation servers for providing different services, and/or there are at least two annotation servers for providing the same service, for example, providing the same service in a load balancing manner, which is not limited in the embodiment of the present application. The database is used for storing the images of the landmark entities to be labeled, the first image, the second image, the verification code image and the like.
Fig. 2 is a schematic diagram of an electronic map labeling method according to an embodiment of the present invention, as shown in fig. 2.
The method comprises the following steps:
201. the server respectively splices the plurality of first images and the plurality of second images to obtain a plurality of verification code images, the second images are images including target characters, and the plurality of first images are sub-images obtained by splitting images of the landmark entity to be annotated.
The target characters included in the second image can be english characters, chinese characters, numeric characters, latin characters, and the like. The correspondence of the second image to the target character included therein may be stored in a database of the electronic map service platform. The image of the landmark entity is the image acquired by the image acquisition device, and the image can be stored in a database of the electronic map service platform.
Optionally, in this step, there are various ways for the server to segment the image of the landmark entity to be annotated to obtain a plurality of sub-images, for example, the server may segment the image of the landmark entity uniformly to obtain a plurality of sub-images with the same size; the server can also divide the image of the landmark entity according to content distribution to obtain a plurality of sub-images containing different contents; the server can also segment the image of the landmark entity according to the content contour to obtain a plurality of sub-images comprising independent characters.
For example, referring to fig. 3, fig. 3 is a schematic split view of an image of a landmark entity according to an embodiment of the present invention. The server segments the image of the landmark entity according to the outline of the content to obtain 3 sub-images, namely 3 first images: a first image a, a first image B and a first image C.
Optionally, in this step, the multiple first images and the multiple second images may be stitched in multiple ways, for example, the server may respectively stitch each first image and a preset number of second images to obtain a verification code image including the first image and any one of the second images, or the server may stitch each first image and at least one of the second images to obtain a verification code image including the first image and at least one of the second images, or the server may stitch each first image and any one of the second images according to a preset layout to obtain multiple verification code images including the first image and the second image, where layouts of each verification code image are different. The first image and the second image have a plurality of splicing ways, which are not listed.
For example, the server extracts 4 second images from the database. The server splices the 3 first images and the 4 second images respectively to obtain 12 verification code images, and each verification code image comprises a first image and a second image. If the server splices any two of each first image and 4 second images, 18 verification code images can be obtained. The verification code image obtained as described above is a verification code image without taking the layout of the first image and the second image into consideration. If the layout modes of the first image and the second image are considered, at least two layout modes exist for one first image and one second image, and at least 2 verification code images can be obtained through splicing; and at least six layout modes are provided for one first image and two second images, namely at least 6 verification code images can be obtained by splicing.
202. The server determines a plurality of first users within a preset distance range from the landmark entity according to the geographical position information of the landmark entity.
Optionally, in this step, the server may extract the geographic location information of the landmark entity from the database. Specifically, the server may determine the geographic location information of the landmark entity according to the correspondence between the image of the landmark entity and the geographic location information stored in the database.
Optionally, in this step, the server may determine the location of the user who needs to authenticate the service by determining the location of the terminal. Specifically, the server may determine the geographical location information of the user according to an IP (Internet Protocol Address) Address of a terminal used by the user; alternatively, the server may determine the geographical location information of the user based on the location of the access server to which the terminal has access.
Optionally, in this step, the server may determine the straight-line distance between the user and the landmark entity according to the geographic location information of the landmark entity and the geographic location information of the user. When the server determines that the straight-line distance between any user and the landmark entity is within the preset distance range, the user can be used as the first user. The preset distance range may be 1 km, 2 km, or 5 km, which is not specifically limited in the embodiment of the present invention. By selecting a user within a preset distance range from the landmark entity as the first user, the first user can be enabled to more accurately recognize the content in the image of the landmark entity.
For example, the landmark entity to be labeled is a coffee shop, the image recognition device cannot recognize the name on the coffee shop signboard, but users around the coffee shop or users who frequently visit the coffee shop can accurately recognize the name on the coffee shop signboard, and therefore, the server may regard users within 1 km from the coffee shop as the first user.
203. The server presents a plurality of captcha images to a plurality of first users.
In this step, for each of the plurality of first users, the server may send any one of the verification code images to the first user, and the terminal used by the first user displays a verification code input interface on the screen after receiving the verification code image, where the verification code input interface includes the verification code image and the input box. The verification code input interface is used for realizing verification services, and the verification services can be applied to various scenes, such as online game anti-addiction verification, shared wireless network verification, take-out order extraction verification, anti-bill-swiping verification and the like.
For example, referring to fig. 4, fig. 4 is a schematic diagram of a verification code input interface according to an embodiment of the present invention. When a first user requests to connect to a shared wireless network through a terminal, the terminal can display a verification code input interface comprising a verification code image to the first user; when a first user plays online games through a terminal for a preset time, the terminal can display a verification code input interface comprising a verification code image to the first user; when a first user draws a purchased takeaway at a store through a terminal, the terminal may present a passcode entry interface including a passcode image to the first user.
Optionally, in this step, the server may directly present the verification code image to the first user through the terminal to authenticate the user, and the server may further present the verification image to the first user through the terminal step by step to authenticate the user.
In an alternative implementation manner, the step of displaying the verification image by the server in steps may be: for each of the captcha images, the server may present a second image portion of the captcha image to at least one first user of the plurality of first users, and present the first image portion of the captcha image to any first user when information input by the first user is consistent with a target character included in the second image. The verification image is displayed step by step, so that the first user can identify the first image under the condition that the second image is identified correctly, the first user is ensured to fill in the verification information seriously, and the identification accuracy of the first image can be improved.
For example, user a needs an authentication service, the server may first transmit the second image portion in the authentication image to the terminal of user a, user a inputs the authentication code, the terminal transmits the authentication code input by the user to the server, and when the server determines that the received authentication code matches the target character in the second image, the server transmits the first image to the terminal.
It should be noted that, the server may also send the verification code image and the target character of the second image included in the verification code image to the terminal, the terminal displays the second image portion in the verification code image and verifies the information input by the user, and when the information input by any user is consistent with the target character included in the second image, the terminal displays the first image portion in the verification code image to the first user.
It should be noted that the server may also directly display a plurality of verification code images to a plurality of third users who need verification services, without performing a user screening process based on geographic locations, may also achieve the identification purpose, and may also reduce the processing pressure of the server. Of course, if the processing capability of the server is strong, the server may screen out a plurality of first users from the plurality of third users needing the verification service, and display a plurality of verification code images to the plurality of first users, because the screened out plurality of first users are within a preset distance range from the landmark entity, the first users will be familiar with the landmark entity, and thus the recognition result is more accurate.
204. And the server determines a plurality of first recognition results of the plurality of first images according to the obtained recognition results.
In this step, the server may receive the recognition results returned by the plurality of first users, and use the received recognition results as a plurality of first recognition results of the plurality of first images, and the server may further screen the received recognition results, thereby determining the plurality of first recognition results of the plurality of first images. The server can acquire information input by a plurality of first users in an input box of a verification code input interface of the terminal, and the acquired information is used as an identification result.
Optionally, in this step, if the server does not perform the user screening process in steps 202 to 203, that is, the identification result obtained by the server is not the identification results of the plurality of first users within the preset distance range from the landmark entity, but is the identification results of the plurality of third users, the server may screen the obtained identification result based on the preset distance range, so as to determine the plurality of first identification results of the plurality of first images.
In an optional implementation manner, the step of the server screening the obtained recognition results based on the preset distance range to determine a plurality of first recognition results of the plurality of first images may be: the server may delete the recognition result fed back by the first user out of the preset distance range from the landmark entity, and for each first image, the server may select a second recognition result corresponding to the first image from the remaining recognition results, and use a recognition result with the highest proportion in the second recognition results as the first recognition result of the first image. The obtained identification results are screened through the preset distance range, and the accuracy of the screened identification results is higher because the screened identification results are the identification results of the first user within the preset distance range.
For example, the server receives 48 identification results corresponding to 12 verification code images, wherein the 12 verification code images are obtained by respectively stitching 3 first images and 4 second images, and each verification code image corresponds to 4 identification results. Because 12 recognition results are fed back by the first user beyond the preset distance range from the landmark entity, the server deletes the recognition results and then remains 36 recognition results. The server selects 3 identification results corresponding to 3 verification code images including the first image A from the remaining 36 identification results, extracts 3 second identification results corresponding to the first image A from the 3 identification results, and takes the identification result A as the first identification result of the first image because 2 identification results A and 1 identification result B are available in the 3 second identification results.
Optionally, in this step, if the server displays the verification code image to the first user in a manner that the terminal displays the verification image to the first user step by step, the identification result obtained by the server only includes the identification result of the first image. If the server directly shows the verification code image to the first user, the information input by the first user comprises the identification result of the first image and the identification result of the second image. Since the first user may have an error in the second image, the server may filter the acquired recognition result according to the recognition result of the second image, so as to determine a plurality of first recognition results of the plurality of first images.
In an optional implementation manner, the step of, by the server, screening the obtained recognition results according to the recognition result of the second image, so as to determine a plurality of first recognition results of the plurality of first images may be: the server may divide each of the acquired recognition results into a first image recognition result corresponding to the first image and a second image recognition result corresponding to the second image. And when the second image recognition result is inconsistent with the target character included in the corresponding second image, deleting the recognition result corresponding to the second image recognition result. For each first image, the server may select at least one third recognition result from the remaining recognition results, the third recognition result including the first image recognition result corresponding to the first image, and determine the first recognition result of the first image according to the at least one third recognition result. Wherein, the server may use the recognition result with the highest proportion in the remaining 3 recognition results as the recognition result of the first image. By screening the acquired recognition results according to the recognition result of the second image, the accuracy of the rest recognition results is high after the recognition result with the recognition error is deleted because the possibility that the first image is correctly recognized when the second image is wrongly recognized is low.
For example, the server receives 48 identification results of 12 verification code images, where the 12 verification code images are obtained by respectively stitching 3 first images and 4 second images, and each verification code image corresponds to 4 identification results. The server divides each recognition result of the 48 recognition results into a first image recognition result and a second image recognition result. The server deletes, from the 48 recognition results, the recognition results in which the 12 second image recognition results are inconsistent with the target character included in the corresponding second image, and the remaining 36 recognition results. The server selects 3 third recognition results corresponding to 3 verification code images including the first image a from the remaining 36 recognition results. Since there are 2 recognition results a and 1 recognition result B in the remaining 3 third recognition results, the recognition result a is taken as the first recognition result of the first image.
In a possible implementation manner, the server may further screen the obtained recognition result based on the preset distance range, and then screen the obtained recognition result according to the recognition result of the second image, so as to determine a plurality of first recognition results of the plurality of first images. The specific implementation manner can be obtained by combining the two possible implementation manners, and is not described herein again. By combining the two screening methods, the remaining recognition results are more accurate.
205. The server determines the labeling information of the landmark entity according to a plurality of first recognition results of a plurality of first images.
In this step, the server may rank the plurality of first recognition results of the plurality of first images, and use the ranked first recognition results as the annotation information of the landmark entity. The server can also perform secondary verification on a plurality of first identification results of a plurality of first images so as to determine the annotation information of the landmark entity.
In an optional implementation manner, the step of arranging, by the server, the plurality of first recognition results of the plurality of first images to serve as the tagging information of the landmark entity may be: the server may determine an arrangement order of the first images in the image of the landmark entity, arrange the plurality of first recognition results of the plurality of first images according to the arrangement order, and use a first text content obtained after arrangement as the annotation information of the landmark entity. The arranged first recognition result is directly used as the labeling information of the landmark entity, so that the labeling information can be conveniently and quickly obtained.
For example, if the first recognition result of the first image a is "a", the first recognition result of the first image B is "B", the first recognition result of the first image C is "C", the first recognition result of the first image D is "D", and the arrangement order of the first images in the image of the landmark entity is BACD, the plurality of first recognition results are arranged in the arrangement order to obtain the first text content "BACD", and the annotation information of the landmark entity is "BACD".
In an alternative implementation manner, the step of performing, by the server, secondary verification on the plurality of first recognition results of the plurality of first images so as to determine the annotation information of the landmark entity may be: the server may arrange the plurality of first images in a target order, which is an arrangement order of the first images in the images of the landmark entities, to obtain the third image. The server may determine a second text content comprising a target option consisting of the first recognition results of the plurality of first images in a target order and at least one distracter. The server may present the third image and the second text content to a plurality of second users, and when the second user selecting the target option exceeds a target percentage, the server may regard the target option as the tagging information of the landmark entity. The determining manner of the second user may be the same as the determining manner of the first user, or may be different from the determining manner of the first user, which is not limited in this embodiment of the present invention. The target percentage may be 70%, 80%, or 90%. The labeling information of the landmark entity is determined in a secondary verification mode, so that the obtained labeling information is more accurate.
For example, the first recognition result of the first image a is "a", the first recognition result of the first image B is "B", the first recognition result of the first image C is "C", the first recognition result of the first image D is "D", the arrangement order of the first images in the images of the landmark entities is BACD, and the third image is obtained by arranging the first image a, the first image B, the first image C, and the first image D in this arrangement order. According to the arrangement sequence, a target option BACD can be obtained, and interference items ABCD, BECD and BADE are generated. The server displays the third image and the second text file to a plurality of second users, receives selection results returned by the plurality of second users, and takes the BACD as the annotation information of the landmark entity when more than 90% of the second users selecting the BACD are selected.
206. And the server marks the landmark entity on the electronic map according to the marking information.
In this step, after obtaining the annotation information of the landmark entity, the server may label the annotation information on the electronic map, so as to label the landmark entity.
In an optional implementation manner, the server may set a priority of the annotation information during annotation, where the priority is used to indicate a display priority of the annotation information, and the annotation information with a high display priority may be preferentially displayed on the electronic map. Wherein the display priority is positively correlated with the importance degree of the landmark entity, or the display priority is correlated with the use habit of the user. By setting the display priority, the annotation information of the landmark entity is neatly layered when displayed, and the displayed content is prevented from being too much.
For example, the label information of the hospital is "XXX hospital", the label information of the coffee shop is "XX coffee", the label information of the place collected by the user is "XX company", and since the importance degree of the hospital is greater than that of the coffee shop and the place collected by the user is a place frequently visited by the user, the display priority of "XXX hospital" is greater than that of "XX company", and the display priority of "XX company" is greater than that of "XX coffee". When the user adjusts the display scale of the electronic map to be large, the landmark entities displayed by the electronic map are too many, and the XXX hospital and the XX company are preferentially displayed according to the display priority, and when the user adjusts the display scale of the electronic map to be small, the XX coffee can be displayed.
In the embodiment of the invention, a plurality of verification code images are obtained by respectively splicing a plurality of sub-images of an image of a landmark entity to be labeled with a plurality of second images comprising target characters, the plurality of verification code images are displayed to a plurality of first users, a plurality of first identification results of the plurality of first images are determined based on the obtained identification results of the plurality of first users, labeling information of the landmark entity is determined according to the plurality of first identification results, and finally the landmark entity is labeled on an electronic map according to the labeling information. Because the sub-images of the landmark entities are displayed in the form of the verification code images, and the marking information of the landmark entities is determined according to the identification results of the first users, the identification and marking of the landmark entities with high identification difficulty can be automatically completed, so that the labor cost is greatly reduced, and the marking efficiency and accuracy are improved.
Fig. 5 is a block diagram of an electronic map annotation apparatus according to an embodiment of the present invention. As shown in fig. 5, the apparatus includes: a splicing module 501, a display module 502, a first determination module 503 and a labeling module 504.
The splicing module 501 is configured to splice a plurality of first images and a plurality of second images to obtain a plurality of verification code images, where the second images are images including target characters, and the plurality of first images are sub-images obtained by segmenting an image of a landmark entity to be annotated;
a display module 502, configured to display a plurality of verification code images to a plurality of first users, and determine a plurality of first identification results of the plurality of first images according to the obtained identification results;
a first determining module 503, configured to determine, according to a plurality of first recognition results of the plurality of first images, tagging information of the landmark entity;
and the labeling module 504 is configured to label the landmark entity on the electronic map according to the labeling information.
In one possible implementation, the apparatus further includes:
and the second determining module is used for determining a plurality of first users within a preset distance range from the landmark entity according to the geographical position information of the landmark entity.
In another possible implementation manner, the presenting module 502 is further configured to present, for each of the captcha images, a second image portion in the captcha image to at least one first user of the plurality of first users; and when the information input by any first user is consistent with the target character included in the second image, displaying the first image part in the verification code image to the first user.
In another possible implementation manner, the presentation module 502 is further configured to delete the recognition result fed back by the first user that is outside the preset distance range from the landmark entity; for each first image, selecting a second recognition result corresponding to the first image from the rest recognition results; and taking the recognition result with the highest proportion in the second recognition results as the first recognition result of the first image.
In another possible implementation manner, the first determining module 503 is further configured to arrange the plurality of first images according to a target order to obtain a third image, where the target order is an arrangement order of the first images in the image of the landmark entity; determining second text content, wherein the second text content comprises a target option and at least one interference item, and the target option is composed of first recognition results of a plurality of first images according to a target sequence; presenting the third image and the second text content to a plurality of second users; and when the second user selecting the target option exceeds the target percentage, the target option is used as the labeling information of the landmark entity.
In another possible implementation manner, the displaying module 502 is further configured to divide each of the obtained recognition results into a first image recognition result corresponding to the first image and a second image recognition result corresponding to the second image; deleting the recognition result corresponding to the second image recognition result when the second image recognition result is inconsistent with the target character included in the corresponding second image; for each first image, selecting a third recognition result comprising the first image recognition result corresponding to the first image from the remaining recognition results; and determining the first recognition result of the first image according to at least one third recognition result corresponding to the first image.
In another possible implementation manner, the first determining module 503 is further configured to determine an arrangement order of the plurality of first images in the image of the landmark entity; arranging a plurality of first recognition results of a plurality of first images according to an arrangement sequence; and taking the first text content obtained after arrangement as the labeling information of the landmark entity.
The method comprises the steps of obtaining a plurality of verification code images by splicing a plurality of sub-images of an image of a landmark entity to be labeled with a plurality of second images including target characters, displaying the plurality of verification code images to a plurality of first users, determining a plurality of first identification results of the plurality of first images based on the obtained identification results of the plurality of first users, determining labeling information of the landmark entity according to the plurality of first identification results, and finally labeling the landmark entity on an electronic map according to the labeling information. Because the sub-images of the landmark entities are displayed in the form of the verification code images, and the marking information of the landmark entities is determined according to the identification results of the first users, the identification and marking of the landmark entities with high identification difficulty can be automatically completed, so that the labor cost is greatly reduced, and the marking efficiency and accuracy are improved.
Fig. 6 is a schematic structural diagram of a server 600 according to an embodiment of the present invention. As shown in fig. 6, the server 600 may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 601 and one or more memories 602, where at least one instruction is stored in the memory 602, and is loaded and executed by the processor 601 to implement the methods provided by the above method embodiments. Of course, the server may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input/output, and the server may also include other components for implementing the functions of the device, which are not described herein again.
Those skilled in the art will appreciate that the architecture shown in FIG. 6 does not constitute a limitation on server 600, and may include more or fewer components than those shown, or combine certain components, or employ a different arrangement of components.
The embodiment of the present invention also provides a computer-readable storage medium, which is applied to a server, and the computer-readable storage medium stores a program code, and the program code is loaded and executed by a processor of the server to implement the operations executed by the server in the electronic map labeling method of the above embodiment.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a storage medium, such as a read-only memory, a magnetic disk or an optical disk.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent replacements, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. An electronic map labeling method is characterized by comprising the following steps:
respectively splicing a plurality of first images and a plurality of second images to obtain a plurality of verification code images, wherein the second images comprise target characters, and the first images are sub-images obtained by segmenting the images of the landmark entities to be labeled;
displaying the verification code images to a plurality of first users, and determining a plurality of first identification results of the first images according to the obtained identification results;
determining the labeling information of the landmark entity according to a plurality of first recognition results of the plurality of first images;
and according to the labeling information, labeling the landmark entity on the electronic map.
2. The method of claim 1, wherein prior to presenting the plurality of captcha images to the plurality of first users, the method further comprises:
and determining a plurality of first users within a preset distance range from the landmark entity according to the geographical position information of the landmark entity.
3. The method of claim 1, wherein said presenting the plurality of captcha images to a plurality of first users comprises:
for each captcha image, presenting a second image portion of the captcha image to at least one first user of the plurality of first users;
and when the information input by any first user is consistent with the target character included in the second image, displaying a first image part in the verification code image to the first user.
4. The method according to claim 1, wherein the determining a plurality of first recognition results of the plurality of first images according to the obtained recognition results comprises:
deleting the recognition result fed back by the first user within a preset distance range from the landmark entity;
for each first image, selecting a second recognition result corresponding to the first image from the rest recognition results;
and taking the recognition result with the highest proportion in the second recognition results as the first recognition result of the first image.
5. The method of claim 1, wherein determining the annotation information of the landmark entity according to the first recognition results of the first images comprises:
arranging the plurality of first images according to a target sequence to obtain a third image, wherein the target sequence is the arrangement sequence of the first images in the images of the landmark entities;
determining second text content, wherein the second text content comprises a target option and at least one interference item, and the target option is composed of first recognition results of the plurality of first images according to the target sequence;
presenting the third image and the second textual content to a plurality of second users;
and when the second user selecting the target option exceeds a target percentage, using the target option as the labeling information of the landmark entity.
6. The method according to claim 1, wherein the determining a plurality of first recognition results of the plurality of first images according to the obtained recognition results comprises:
dividing each identification result in the obtained identification results into a first image identification result corresponding to a first image and a second image identification result corresponding to a second image;
when the second image recognition result is inconsistent with the target character included in the corresponding second image, deleting the recognition result corresponding to the second image recognition result;
for each first image, selecting a third recognition result comprising the first image recognition result corresponding to the first image from the rest recognition results;
and determining a first recognition result of the first image according to at least one third recognition result corresponding to the first image.
7. The method of claim 1, wherein determining the annotation information of the landmark entity according to the first recognition results of the first images comprises:
determining an arrangement order of the plurality of first images in the image of the landmark entity;
arranging a plurality of first recognition results of the plurality of first images according to the arrangement sequence;
and taking the first text content obtained after arrangement as the labeling information of the landmark entity.
8. An electronic map labeling apparatus, comprising:
the system comprises a splicing module, a storage module and a processing module, wherein the splicing module is used for respectively splicing a plurality of first images and a plurality of second images to obtain a plurality of verification code images, the second images are images comprising target characters, and the first images are sub-images obtained by segmenting images of landmark entities to be labeled;
the display module is used for displaying the verification code images to a plurality of first users and determining a plurality of first identification results of the first images according to the obtained identification results;
a first determining module, configured to determine, according to a plurality of first recognition results of the plurality of first images, annotation information of the landmark entity;
and the marking module is used for marking the landmark entity on the electronic map according to the marking information.
9. A server, characterized in that it comprises a processor and a memory for storing program code, which is loaded by the processor and executes the electronic map annotation method of any one of claims 1 to 7.
10. A computer-readable storage medium for storing a program code for executing the electronic map labeling method according to any one of claims 1 to 7.
CN201910792495.9A 2019-08-26 2019-08-26 Electronic map labeling method, device, server and storage medium Active CN110796715B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910792495.9A CN110796715B (en) 2019-08-26 2019-08-26 Electronic map labeling method, device, server and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910792495.9A CN110796715B (en) 2019-08-26 2019-08-26 Electronic map labeling method, device, server and storage medium

Publications (2)

Publication Number Publication Date
CN110796715A true CN110796715A (en) 2020-02-14
CN110796715B CN110796715B (en) 2023-11-24

Family

ID=69427081

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910792495.9A Active CN110796715B (en) 2019-08-26 2019-08-26 Electronic map labeling method, device, server and storage medium

Country Status (1)

Country Link
CN (1) CN110796715B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101196994A (en) * 2007-12-26 2008-06-11 腾讯科技（深圳）有限公司 Image content recognizing method and recognition system
CN101388078A (en) * 2008-09-27 2009-03-18 腾讯科技（深圳）有限公司 Text identification method and device based on verification
CN105678293A (en) * 2015-12-30 2016-06-15 成都数联铭品科技有限公司 Complex image and text sequence identification method based on CNN-RNN
CN108108443A (en) * 2017-12-21 2018-06-01 深圳市数字城市工程研究中心 Character marking method of street view video, terminal equipment and storage medium
CN108737329A (en) * 2017-04-16 2018-11-02 韦建峰 A kind of verification method and generating means
CN108764208A (en) * 2018-06-08 2018-11-06 Oppo广东移动通信有限公司 Image processing method and device, storage medium, electronic equipment

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101196994A (en) * 2007-12-26 2008-06-11 腾讯科技（深圳）有限公司 Image content recognizing method and recognition system
CN101388078A (en) * 2008-09-27 2009-03-18 腾讯科技（深圳）有限公司 Text identification method and device based on verification
CN105678293A (en) * 2015-12-30 2016-06-15 成都数联铭品科技有限公司 Complex image and text sequence identification method based on CNN-RNN
CN108737329A (en) * 2017-04-16 2018-11-02 韦建峰 A kind of verification method and generating means
CN108108443A (en) * 2017-12-21 2018-06-01 深圳市数字城市工程研究中心 Character marking method of street view video, terminal equipment and storage medium
CN108764208A (en) * 2018-06-08 2018-11-06 Oppo广东移动通信有限公司 Image processing method and device, storage medium, electronic equipment

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
LUKAS BARTH等: "Temporal Map Labeling: A New Unified Framework with Experiments" *
胡翔: "三维全景拼接技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 04, pages 138 - 1026 *
陈兴华: "在线电子地图海量标注与表面注记的研究", vol. 12, no. 4 *

Also Published As

Publication number Publication date
CN110796715B (en) 2023-11-24

Similar Documents

Publication Publication Date Title
US9710946B2 (en) Method and apparatus for displaying point of interest
US9934254B2 (en) Terminal apparatus, information processing system, and information processing method
US10650264B2 (en) Image recognition apparatus, processing method thereof, and program
KR101343609B1 (en) Apparatus and Method for Automatically recommending Application using Augmented Reality Data
US20230260274A1 (en) Image display system, terminal, method, and program for determining a difference between a first image and a second image
CN108197198B (en) Interest point searching method, device, equipment and medium
US20090161963A1 (en) Method. apparatus and computer program product for utilizing real-world affordances of objects in audio-visual media data to determine interactions with the annotations to the objects
CN105517679B (en) Determination of the geographic location of a user
CN109040960A (en) A kind of method and apparatus for realizing location-based service
CN107870961B (en) Method and system for searching and sorting space objects and computer readable storage device
KR101062929B1 (en) Method, terminal, and computer-readable recording medium for supporting collection of object included in the image which is taken
CN109374002A (en) Air navigation aid and system, computer readable storage medium
EP3299971A1 (en) Method and system for remote management of location-based spatial object
CN110647603B (en) Image annotation information processing method, device and system
CN109522503B (en) Tourist attraction virtual message board system based on AR and LBS technology
KR20190124436A (en) Method for searching building based on image and apparatus for the same
CN105845020B (en) A kind of live-action map production method and device
US10123094B1 (en) Location-based movie identification systems and methods
CN105787111A (en) Private map making method based on user interest
CN109752001A (en) Navigation system, method and apparatus
CN110796715B (en) Electronic map labeling method, device, server and storage medium
TW201923549A (en) System of digital content as in combination with map service and method for producing the digital content
KR20210094396A (en) Application for searching service based on image and searching server therefor
Astawa et al. Augmented Reality Mobile Application Base On Marker Object
US20210374621A1 (en) Information processing apparatus and non-transitory computer readable medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant