CN112925861A - Position reference line generation method and device and interest point position determination method and device - Google Patents
Position reference line generation method and device and interest point position determination method and device Download PDFInfo
- Publication number
- CN112925861A CN112925861A CN201911242717.6A CN201911242717A CN112925861A CN 112925861 A CN112925861 A CN 112925861A CN 201911242717 A CN201911242717 A CN 201911242717A CN 112925861 A CN112925861 A CN 112925861A
- Authority
- CN
- China
- Prior art keywords
- road
- target
- acquisition
- closed area
- building block
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Remote Sensing (AREA)
- Instructional Devices (AREA)
Abstract
The invention discloses a position reference line generation method, and a method and a device for determining a position of a point of interest. The position reference line generation method comprises the following steps: acquiring a closed area positioned on a preset acquisition side of an acquisition road based on map data; obtaining a closed region where interest points can fall as a target closed region; and generating a position reference line of the collected road based on the target closed area. A position reference line can be provided for the release of the interest points, so that the problem that the coordinates of the collected interest points are inaccurate is solved.
Description
Technical Field
The invention relates to the technical field of electronic maps, in particular to a method for generating a position reference line and a method and a device for determining a position of an interest point.
Background
A Point of Interest (POI) in an electronic map may correspond to a house, a shop, a mailbox, a bus station, a tourist attraction, etc. in the real world. Currently, a map data producer collects POIs in a crowd-sourced manner to obtain collection data for generating POIs, where the collection data at least includes: the system comprises an image which is acquired through a camera of the acquisition equipment and used for recording information such as names, addresses and the like of POIs, and position information of the POIs acquired through a positioning module of the acquisition equipment. The position information of the outdoor POI is generally GPS position information of the POI acquired by a GPS receiver integrated with an acquisition device, but since GPS signals are easily affected by environmental factors, the latitude and longitude coordinates recorded in the GPS position information of the POI may drift, lag, and the like, which may cause deviation between the map position coordinate of the POI finally produced and the actual position coordinate, and how to eliminate the deviation, so that the map position coordinate of the POI and the actual position coordinate tend to be consistent is a problem to be solved by those in the art.
Disclosure of Invention
In view of the above, the present invention is proposed in order to provide a method of generating a position reference line, a method and an apparatus for determining a position of a point of interest that overcome or at least partially solve the above problems.
In a first aspect, an embodiment of the present invention provides a method for generating a position reference line, including:
acquiring a closed area positioned on a preset acquisition side of an acquisition road based on map data;
obtaining a closed region where interest points can fall as a target closed region;
and generating a position reference line of the acquisition road based on the target closed region.
In some optional embodiments, obtaining the closed area located on the preset collection side of the collection road based on the map data includes:
acquiring a road which is positioned on a preset acquisition side of the acquisition road and has a distance to the acquisition road not exceeding a preset distance threshold value from the map data as a target road;
acquiring a building block which is positioned on a preset acquisition side of the acquisition road and has a distance between a lower sideline of the building block and the acquisition road not exceeding a preset distance threshold value from map data as a target building block, wherein the lower sideline of the building block is a sideline closest to the acquisition road in the sidelines of the acquisition road;
and dividing a geographical area on a preset acquisition side of the acquisition road into more than one closed area based on the target road and the target building block.
In some optional embodiments, based on the target road and the target building block, dividing a geographic area located on a preset acquisition side of the acquisition road into more than one closed area specifically includes:
determining the area covered by each target building block as a closed area;
if the upper edge line of the target building block is provided with a target road along the direction far away from the acquisition road, the target road and the upper edge line and the left and right edge lines of the target building block form a closed area along the extension lines of the directions far away from the acquisition road;
if another target building block exists along the upper edge line of the target building block in the direction far away from the acquisition road, the extension lines of the upper edge line, the left edge line and the right edge line of the target building block and the lower edge line of the other target building block form a closed area;
if a target road is arranged between the lower edge line of the target building block and the acquisition road, the target road and the lower edge line, the left edge line and the right edge line of the target building block form a closed area along the extension line of the direction close to the acquisition road;
if no target road exists between the lower edge line of the target building block and the acquisition road, the lower edge line, the left edge line and the right edge line of the target building block form a closed area along the extension line of the direction close to the acquisition road and the acquisition road;
and if the target building block is provided with another adjacent target building block within a preset distance along the direction of the acquisition road, obtaining a closed area according to the position relation of the sidelines of the two target building blocks.
In some optional embodiments, the obtaining of the closed region where the interest point can be located as the target closed region specifically includes:
when a building block is searched in the closed area, determining that the closed area is a closed area of a touchable interest point;
and when no building block can be searched in the closed area, acquiring a satellite image picture of the closed area, and determining the closed area as the closed area of the touchable interest point when a building is recognized in the satellite image picture by utilizing a pre-trained building classification model.
In some optional embodiments, the building classification model is pre-trained by:
marking whether buildings exist in the satellite image picture samples;
acquiring satellite image picture samples marked as buildings and satellite image picture samples marked as no buildings in a set proportion from the marked satellite image picture samples;
and training the building classification model by using the acquired satellite image picture sample.
In some optional embodiments, further comprising:
if the building classification model cannot identify whether buildings exist in the satellite image picture, identifying whether the closed area is a closed area formed by the surrounding of the ascending and descending roads, if so, acquiring attribute parameters of the closed area, and determining whether buildings exist in the closed area by using a pre-trained decision tree.
In some optional embodiments, the decision tree is pre-trained by:
marking whether buildings exist in closed area samples divided based on map data;
obtaining a closed area sample marked with a building and a closed area sample marked with no building in a set proportion from the marked closed area;
and training the decision tree by using the acquired attribute parameters of the closed region sample.
In some optional embodiments, generating the position reference line of the acquisition road based on the target closed region includes:
acquiring vertical lines perpendicular to the acquisition road in the target closed area according to a preset interval, and acquiring reference points of the vertical lines in the direction close to the acquisition road on each vertical line;
and taking the connection line of the reference points as a position reference line of the acquisition road.
In some optional embodiments, after acquiring the closed region located on the preset acquisition side of the acquisition road, the method further includes:
and deleting the closed region with the area smaller than a preset area threshold value.
In a second aspect, an embodiment of the present invention provides a method for determining a location of a point of interest, including:
generating a position reference line by using the generating method of the position reference line;
and determining a projection point of the interest point on the position reference line with the nearest distance, and taking the projection point as the position point of the interest point.
In a third aspect, an embodiment of the present invention provides an apparatus for generating a position reference line, including:
the first acquisition module is used for acquiring a closed area on a preset acquisition side of an acquisition road based on map data;
the second acquisition module is used for acquiring a closed region of the touchable interest point as a target closed region;
and the generating module is used for generating a position reference line of the acquisition road based on the target closed region acquired by the second acquiring module.
In a fourth aspect, an embodiment of the present invention provides an apparatus for determining a location of a point of interest, including:
the generating module is used for generating the position reference line by using the generating method of the position reference line;
and the releasing module is used for determining a projection point of the interest point on the position reference line with the nearest distance and taking the projection point as the position point of the interest point.
In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which computer instructions are stored, and when the instructions are executed by a processor, the method for generating a position reference line or the method for determining a position of a point of interest is implemented.
In a sixth aspect, an embodiment of the present invention provides a server, including: the device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the method for generating the position reference line or the method for determining the position of the interest point.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
the position reference line generation method provided by the embodiment of the invention is characterized in that a closed area at a preset collection side of a collection road is obtained based on map data; obtaining a closed region where interest points can fall as a target closed region; and generating a position reference line of the collected road based on the target closed area. A position reference line can be provided for the release of the interest points, so that the problem that the coordinates of the collected interest points are inaccurate is solved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flowchart illustrating a method for generating a position reference line according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a building classification model training process according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating an example of generating position reference lines according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a method for determining a position of a point of interest according to a second embodiment of the present invention;
FIG. 5 is a diagram illustrating a partition of a closed region according to a second embodiment of the present invention;
fig. 6 is a diagram illustrating another example of dividing a closed region according to a second embodiment of the present invention;
FIG. 7 is a flowchart illustrating a decision tree training process according to a second embodiment of the present invention;
FIG. 8 is a schematic structural diagram of an apparatus for generating a position reference line according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of an apparatus for determining a location of interest in an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In order to solve the problem of inaccurate coordinates of the collected interest points in the prior art, embodiments of the present invention provide a method for generating a position reference line, a method for determining a location of an interest point, and a device thereof, which can provide a reference line for a release position of an interest point to overcome the problem of inaccurate coordinates of the collected interest points.
Example one
An embodiment of the present invention provides a method for generating a position reference line, where the generated position reference line is mainly used for determining a position of an interest point, and a flow of the method is shown in fig. 1, and the method includes the following steps:
step S11: and acquiring a closed area positioned on a preset acquisition side of the acquisition road based on the map data.
Specifically, according to a pre-designated collection road, a preset collection side of the collection road in the electronic map is divided into a plurality of closed areas.
The collected road is a reference road used for determining a target closed region where the release position of the point of interest is located, and the collected road may be determined in advance according to information such as the length of the road, the extending direction of the road, node data of the road, and the like, and a road with a long length, an extending method close to a straight line, and distribution density of the node data meeting requirements is generally selected as the collected road.
Acquiring a closed area positioned at a preset acquisition side of an acquisition road, wherein the closed area can be determined as an area to be divided within a distance threshold range preset at the preset acquisition side of the acquisition road in an electronic map; and searching closed elements in the area to be divided, and dividing a plurality of closed areas according to the closed elements and the acquisition roads. The preset acquisition side of the acquisition road is the left side or the right side of the acquisition road, and is generally the side with more buildings; the preset distance threshold may be determined according to an empirical value, and in general, the preset distance threshold may be set to 60 meters; the closure element may be a road, a block, a water system, or the like.
The method for dividing the closed region is described in detail in the second embodiment.
Step S12: and acquiring a closed region where the interest point can be located as a target closed region.
In one embodiment, the method may include, when a floor block is searched for within the closed region, determining the closed region as a closed region of the fallen interest point; when no building block can be searched in the closed area, a satellite image picture of the closed area is obtained, and when a building is identified in the satellite image picture by utilizing a pre-trained building classification model, the closed area is determined to be the closed area where the interest point can be located.
The building classification model, as shown in fig. 2, may be trained in advance in the following manner:
step S21: and marking whether buildings exist in the satellite image picture samples.
The satellite image information is downloaded through the frame coordinates of the closed region and is made into a satellite image picture with a preset resolution, for example, 224 × 224 picture. And marking whether buildings exist in the plurality of satellite image picture samples by using a binary classification method.
Step S22: and acquiring a satellite image picture sample marked as a building and a satellite image picture sample marked as no building in a set proportion from the marked satellite image picture samples.
Since there is a high possibility that a building exists in a closed region in general, it is necessary to screen a plurality of labeled satellite image picture samples, and the ratio of the selected satellite image picture sample labeled as having a building to the selected satellite image picture sample labeled as having no building may be 1 to 1.
Step S23: and training a building classification model by using the acquired satellite image picture sample.
For the closed area with the missing building information, the closed area with the building can be determined as the target closed area with the interest point through satellite image information completion and further whether the building information exists or not.
Specifically, the building classification model may be a GoogleNet model, or may be another classification model.
Step S13: and generating a position reference line of the collected road based on the target closed area.
In one embodiment, vertical lines perpendicular to the acquisition road are acquired in the target closed area at preset intervals, and a reference point of the vertical line is acquired in a direction close to the acquisition road on each vertical line; and taking the connecting line of the reference points as a position reference line of the collected road.
Specifically, the reference point may be an equal division point of each perpendicular line, or may be a point where the distance acquisition road on each perpendicular line is a set distance, and the specific rule for determining the reference point is not limited in this embodiment.
Referring to fig. 3, for a target closed area ABCD located on the collection side of a collection road L, vertical lines perpendicular to the collection road L, namely a vertical line E1, a vertical line E2 and a vertical line E3 … …, are acquired at preset intervals within the target closed area ABCD, and a reference point 1/3, a bisector point F1, a bisector point F2 and a bisector point F3 … … of the vertical lines are acquired in a direction close to the collection road on each vertical line; and taking the connecting line of the bisector as a position reference line F of the collection road L.
According to the scheme provided by the embodiment of the invention, the closed area at the preset acquisition side of the acquisition road is acquired based on the map data; obtaining a closed region where interest points can fall as a target closed region; and generating a position reference line of the collected road based on the target closed area. The system can provide a position reference line for the delivery of the interest points so as to overcome the problems of inaccurate coordinates of the collected interest points and even road crossing.
Example two
The second embodiment of the present invention provides a specific implementation flow of a method for generating a position reference line, which is shown in fig. 4 and includes the following steps:
step S41: and acquiring a closed area positioned on a preset acquisition side of the acquisition road based on the map data.
In one embodiment, a road, which is located on a preset collection side of a collection road and has a distance to the collection road not exceeding a preset distance threshold, may be obtained from the map data as a target road; acquiring a building block which is positioned on a preset acquisition side of an acquisition road and has a distance from a lower line of the building block to the acquisition road not exceeding a preset distance threshold value from map data as a target building block; and dividing a geographical area on a preset acquisition side of the acquisition road into more than one closed area based on the target road and the target building block.
Specifically, the lower edge of the target building block is one of the edges along the collection road closest to the collection road.
The target road and the target building block are closed elements of the closed area, and optionally, a water system which is located on a preset acquisition side of the acquisition road and has a distance to the acquisition road not exceeding a preset distance threshold value may be acquired as the target water system, and the target water system is also used as a closed element of the closed area. And finally, dividing the geographical area of the preset acquisition side of the acquisition road into more than one closed area based on each closed element and the acquisition road.
Dividing a geographical area on a preset acquisition side of an acquisition road into more than one closed area based on the target road and the target building block, specifically, the following conditions may be included:
firstly, determining an area covered by each target building block as a closed area.
Referring to the target block CDEF in (1) in fig. 5, (2) the target block ABCD and the target block EFGH in (3), and (4) the target block ABCD and the target block GHIJ in (4), each may be separately divided into an enclosed area according to the boundary of the target block.
Secondly, if the upper edge line of the target building block has a target road along the direction far away from the acquisition road:
the upper side line, the left side line and the right side line of the target road and the target building block form a closed area along the extension line of the direction far away from the acquisition road.
In fig. 5(1), the upper edge line of the target building block CDEF has a target road along the direction far from the acquisition road, and the target road and the upper edge line and the left and right edge lines of the target building block CDEF form an enclosed area ABCD along the extension lines of the direction far from the acquisition road.
And thirdly, if the upper edge line of the target building block is provided with another target building block along the direction far away from the acquisition road:
the upper edge line of the target building block, the extension lines of the left and right edge lines and the lower edge line of another target building block form a closed area.
In fig. 5(2), if another target block ABCD exists along the upper line of the target block EFGH along the direction away from the acquisition road, the extension lines of the upper line, the left line and the right line of the target block EFGH and the lower line of the another target block ABCD form an enclosed area.
When two target building blocks are staggered and adjacent along the direction perpendicular to the acquisition road, an adjacent side line, an extension line and the extension lines of the left side line and the right side line form a closed area, which is shown as a closed area EFGC in (5) of FIG. 5.
Optionally, when the two target building blocks are adjacent to each other in the direction perpendicular to the collection road and the distance between the adjacent edge lines is smaller than the preset distance, the area between the adjacent edge lines may be ignored, or the area between the adjacent edge lines may be evenly divided into the closed areas adjacent to each other on both sides.
If a target road exists between the lower edge line of the target building block and the collection road:
the lower side line, the left side line and the right side line of the target road and the target building block form a closed area along the extension line of the direction close to the acquisition road.
In fig. 5(3), a target road is located between the lower edge line of the target building block ABCD and the collecting road, and the target road and the extension lines of the lower edge line, the left edge line and the right edge line of the target building block ABCD along the direction close to the collecting road form a closed area CDEF.
Fifth, there is no target road between the lower line of the target building block and the collection road:
the lower side line, the left side line and the right side line of the target building block form a closed area along the extension line of the direction close to the collection road and the collection road.
In fig. 5(1), if there is no target road between the lower edge of the target building block CDEF and the collecting road, the lower edge, the left edge, and the right edge of the target building block CDEF extend along the direction close to the collecting road, and the collecting road form a closed area EFGH. In addition, the closed region GHIJ in (2) of fig. 5, the closed region CDEF and the closed region IJKL in (4) belong to the case (c).
And sixthly, the target building block is provided with another adjacent target building block within a preset distance along the direction of the acquisition road:
and obtaining a closed area according to the position relation of the side lines of the two target building blocks.
When the distance between the adjacent edge lines of two adjacent target building blocks is greater than the set threshold, the two adjacent edge lines and two edge lines perpendicular to one of the adjacent edge lines form a closed area along an extension line toward the other target building block.
In fig. 5(4), another adjacent target building block GHIJ exists in the target building ABCD along the direction of the collection road within the preset distance, and the borderlines BC and GJ and the borderlines AB and CD perpendicular to the borderline BC form a closed area BCJG along the extension line toward the another target building block GHIJ.
When two target building blocks are staggered and adjacent along the direction of the acquisition road, an adjacent side line, an extension line and extension lines of an upper side line and a lower side line form a closed area, which is shown as a closed area MGNC in (6) of fig. 5.
Optionally, when the two target building blocks are adjacent to each other along the direction of the collection road and the distance between the adjacent edge lines is smaller than the preset distance, the area between the adjacent edge lines may be ignored, or the area between the adjacent edge lines may be evenly divided into the closed areas adjacent to each other on both sides.
Step S42: it is determined whether buildings can be searched within the enclosed area.
If yes, go to step S44; if not, go to step S43.
Step S43: and acquiring satellite image pictures of the closed area, and identifying whether buildings exist in the satellite image pictures or not by utilizing a pre-trained building classification model.
Specifically, a building classification model trained in advance is used for judging whether a building exists in a satellite image picture, and firstly, a result of whether the building exists in the satellite image picture and the accuracy of the result are obtained, for example, the result is '80% existing', which indicates that the building exists in the satellite image picture and the accuracy is 80%; then judging whether the obtained accuracy is not less than a preset accuracy threshold value; if yes, determining whether the obtained result of the building is credible; if not, determining that the obtained result of whether the building exists is not credible, namely, determining whether the building exists in the satellite image picture by using the building classification model.
If the building classification model is used to identify the buildings in the satellite image picture, executing step S46; if the building classification model is used to identify that no building exists in the satellite image picture, executing step S47; if the building classification model is used, it is not possible to identify whether there is a building in the satellite image picture, and step S48 is performed.
Step S44: and determining the closed region as a target closed region of the touchable interest point.
Step S45: and generating a position reference line of the collected road based on the target closed area.
Step S46: and judging whether the area of the closed area is larger than a preset area threshold value.
If yes, go to step S44; if not, go to step S47.
Step S47: and determining the closed region as a non-target closed region.
I.e. to determine the closed area is not a touchable point of interest.
Step S48: and identifying whether the closed area is a closed area surrounded by the uplink and downlink roads.
The enclosed area enclosed by the ascending and descending roads means that two parallel roads in the enclosed elements of the enclosed area are in ascending and descending relation, that is, the two roads are the same or similar in name, are close in distance and are nearly parallel in extending direction. The specific rule for determining the uplink and downlink roads may be other rules, and this embodiment is not limited.
Referring to fig. 6, when the collection road is a road 1, the closed area divided at the collection side includes a closed area 1, a closed area 2, and the like; however, when the collection road is road 2, the closed area divided on the collection side is also an area between road 1 and road 2.
When the judgment of step S48 is yes, step S49 is performed; when the step S48 determines no, step S47 is executed.
Step S49: and acquiring attribute parameters of the closed area, and determining whether buildings exist in the closed area or not by utilizing a pre-trained decision tree.
The Decision Tree may be an iterative Decision Tree algorithm (iterative Boosting Decision Tree) or other Decision trees.
Referring to FIG. 7, the decision tree may be pre-trained by:
step S71: and marking whether buildings exist in the closed area sample divided based on the map data.
Step S72: and obtaining a closed area sample marked with a building and a closed area sample marked with no building according to a set proportion from the marked closed area.
The ratio of the selected sample labeled with the building to the sample labeled with no building may be 1 to 1.
Step S73: and acquiring the attribute parameters of each screened sample.
The attribute parameters may specifically include:
1. the area of the enclosed area, and whether buildings are in the enclosed area.
2. The attributes of the up and down roads of the closed area are as follows: such as road status, road rendering level, road extension direction, length and width of the road, construction status, riding level, and road level. Wherein the road state may include: normal pass 0 (default), in-construction 1, no pass 2, and pre-open pass 3; the rendering level may include: not investigated 0 (default): a trunk road 1 and a secondary trunk road 2; the direction of extension (direction of passage) may include: bidirectional passage 1, forward passage 2, reverse passage 3 and bidirectional forbidding passage 4; the construction state may include: non-construction 1, (bidirectional) construction 2, positive construction 3 and negative construction 4; the riding grade can include: not investigated 0 (default), private 1, recommended 2, normal 3, not recommended 4, recommended prohibited 5, and mandatory prohibited 6; the road grade may include: expressway 41000, national road 42000, urban expressway 43000, urban main road 44000, urban secondary main road 45000, urban common road 47000, provincial road 51000, county road 52000, county road 53000, county and county interior road 54000 and minor road 49000.
3. Whether the same attributes of the up-road and the down-road of the closed area are consistent or not, for example: whether the rendering levels of the upper road and the lower road are consistent, whether the construction states of the upper road and the lower road are consistent, whether the riding levels of the upper road and the lower road are consistent, and whether the road levels of the upper road and the lower road are consistent.
Step S74: and training a decision tree by using the acquired attribute parameters of the closed region sample.
When the determination of step S49 is yes, step S46 is performed; when the determination of step S49 is no, step S47 is performed.
Based on the inventive concept of the present invention, an embodiment of the present invention further provides a method for determining a location of a point of interest, including:
generating a position reference line by using the generating method of the position reference line; and determining a projection point of the interest point on the position reference line with the nearest distance, and taking the projection point as the position point of the interest point.
Based on the inventive concept of the present invention, an embodiment of the present invention further provides a device for generating a position reference line, where the structure of the device is shown in fig. 8, and the device includes:
the first acquisition module 81 is used for acquiring a closed area on a preset acquisition side of an acquisition road based on map data;
a second obtaining module 82, configured to obtain a closed region where the interest point can be located as a target closed region;
and a generating module 83, configured to generate a position reference line of the acquired road based on the target closed region acquired by the second acquiring module 82.
In some embodiments, the first obtaining module 81 is specifically configured to:
acquiring a road which is positioned on a preset acquisition side of the acquisition road and has a distance to the acquisition road not exceeding a preset distance threshold value from the map data as a target road; acquiring a building block which is positioned on a preset acquisition side of the acquisition road and has a distance between a lower sideline of the building block and the acquisition road not exceeding a preset distance threshold value from map data as a target building block, wherein the lower sideline of the building block is a sideline closest to the acquisition road in the sidelines of the acquisition road; and dividing a geographical area on a preset acquisition side of the acquisition road into more than one closed area based on the target road and the target building block.
In some embodiments, the first obtaining module 81 is specifically configured to:
determining the area covered by each target building block as a closed area; if the upper edge line of the target building block is provided with a target road along the direction far away from the acquisition road, the target road and the upper edge line and the left and right edge lines of the target building block form a closed area along the extension lines of the directions far away from the acquisition road; if another target building block exists along the upper edge line of the target building block in the direction far away from the acquisition road, the extension lines of the upper edge line, the left edge line and the right edge line of the target building block and the lower edge line of the other target building block form a closed area; if a target road is arranged between the lower edge line of the target building block and the acquisition road, the target road and the lower edge line, the left edge line and the right edge line of the target building block form a closed area along the extension line of the direction close to the acquisition road; if no target road exists between the lower edge line of the target building block and the acquisition road, the lower edge line, the left edge line and the right edge line of the target building block form a closed area along the extension line of the direction close to the acquisition road and the acquisition road; and if the target building block is provided with another adjacent target building block within a preset distance along the direction of the acquisition road, obtaining a closed area according to the position relation of the sidelines of the two target building blocks.
In some embodiments, the second obtaining module 82 is specifically configured to:
when a building block is searched in the closed area, determining that the closed area is a closed area of a touchable interest point; and when no building block can be searched in the closed area, acquiring a satellite image picture of the closed area, and determining the closed area as the closed area of the touchable interest point when a building is recognized in the satellite image picture by utilizing a pre-trained building classification model.
In some embodiments, the second obtaining module 82 is further configured to:
if the building classification model cannot identify whether buildings exist in the satellite image picture, identifying whether the closed area is a closed area formed by the surrounding of the ascending and descending roads, if so, acquiring attribute parameters of the closed area, and determining whether buildings exist in the closed area by using a pre-trained decision tree.
In some embodiments, the generating module 83 is specifically configured to:
according to a preset interval, acquiring vertical lines perpendicular to the acquisition road in the target closed area, and acquiring reference points of the vertical lines in the direction close to the acquisition road on each vertical line; and taking the connection line of the reference points as a position reference line of the acquisition road.
In some embodiments, the apparatus further includes a deleting module 84, configured to delete the closed region with an area smaller than a preset area threshold after the first obtaining module 81 obtains the closed region on the preset collection side of the collection road.
Based on the inventive concept of the present invention, an embodiment of the present invention further provides an apparatus for determining a location of a point of interest, where the structure is shown in fig. 9, and the apparatus includes:
a generating module 91, configured to generate a position reference line by using the position reference line generating method;
and the releasing module 92 is configured to determine a projection point of the interest point on the position reference line closest to the interest point, and use the projection point as the position point of the interest point.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Based on the same inventive concept, embodiments of the present invention further provide a computer-readable storage medium, on which computer instructions are stored, and when the instructions are executed by a processor, the method for generating the position reference line or the method for determining the position of the point of interest is implemented.
Based on the same inventive concept, an embodiment of the present invention further provides a server, including: the device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the method for generating the position reference line or the method for determining the position of the interest point.
Unless specifically stated otherwise, terms such as processing, computing, calculating, determining, displaying, or the like, may refer to an action and/or process of one or more processing or computing systems or similar devices that manipulates and transforms data represented as physical (e.g., electronic) quantities within the processing system's registers and memories into other data similarly represented as physical quantities within the processing system's memories, registers or other such information storage, transmission or display devices. Information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.
It should be understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not intended to be limited to the specific order or hierarchy presented.
In the foregoing detailed description, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments of the subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, invention lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. Of course, the processor and the storage medium may reside as discrete components in a user terminal.
For a software implementation, the techniques described herein may be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes may be stored in memory units and executed by processors. The memory unit may be implemented within the processor or external to the processor, in which case it can be communicatively coupled to the processor via various means as is known in the art.
What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the aforementioned embodiments, but one of ordinary skill in the art may recognize that many further combinations and permutations of various embodiments are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".
Claims (13)
1. A method for generating a position reference line, comprising:
acquiring a closed area positioned on a preset acquisition side of an acquisition road based on map data;
obtaining a closed region where interest points can fall as a target closed region;
and generating a position reference line of the acquisition road based on the target closed region.
2. The method of claim 1, wherein obtaining an enclosed area on a preset collection side of a collection road based on map data comprises:
acquiring a road which is positioned on a preset acquisition side of the acquisition road and has a distance to the acquisition road not exceeding a preset distance threshold value from the map data as a target road;
acquiring a building block which is positioned on a preset acquisition side of the acquisition road and has a distance between a lower sideline of the building block and the acquisition road not exceeding a preset distance threshold value from map data as a target building block, wherein the lower sideline of the building block is a sideline closest to the acquisition road in the sidelines of the acquisition road;
and dividing a geographical area on a preset acquisition side of the acquisition road into more than one closed area based on the target road and the target building block.
3. The method according to claim 2, wherein dividing a geographical area on a preset collection side of a collection road into more than one closed area based on the target road and the target building block specifically comprises:
determining the area covered by each target building block as a closed area;
if the upper edge line of the target building block is provided with a target road along the direction far away from the acquisition road, the target road and the upper edge line and the left and right edge lines of the target building block form a closed area along the extension lines of the directions far away from the acquisition road;
if another target building block exists along the upper edge line of the target building block in the direction far away from the acquisition road, the extension lines of the upper edge line, the left edge line and the right edge line of the target building block and the lower edge line of the other target building block form a closed area;
if a target road is arranged between the lower edge line of the target building block and the acquisition road, the target road and the lower edge line, the left edge line and the right edge line of the target building block form a closed area along the extension line of the direction close to the acquisition road;
if no target road exists between the lower edge line of the target building block and the acquisition road, the lower edge line, the left edge line and the right edge line of the target building block form a closed area along the extension line of the direction close to the acquisition road and the acquisition road;
and if the target building block is provided with another adjacent target building block within a preset distance along the direction of the acquisition road, obtaining a closed area according to the position relation of the sidelines of the two target building blocks.
4. The method according to claim 1, wherein the obtaining of the closed region where the point of interest can be located as the target closed region specifically includes:
when a building block is searched in the closed area, determining that the closed area is a closed area of a touchable interest point;
and when no building block can be searched in the closed area, acquiring a satellite image picture of the closed area, and determining the closed area as the closed area of the touchable interest point when a building is recognized in the satellite image picture by utilizing a pre-trained building classification model.
5. The method of claim 4, wherein the building classification model is pre-trained by:
marking whether buildings exist in the satellite image picture samples;
acquiring satellite image picture samples marked as buildings and satellite image picture samples marked as no buildings in a set proportion from the marked satellite image picture samples;
and training the building classification model by using the acquired satellite image picture sample.
6. The method of claim 4, further comprising:
if the building classification model cannot identify whether buildings exist in the satellite image picture, identifying whether the closed area is a closed area formed by the surrounding of the ascending and descending roads, if so, acquiring attribute parameters of the closed area, and determining whether buildings exist in the closed area by using a pre-trained decision tree.
7. The method of claim 6, wherein the decision tree is pre-trained by:
marking whether buildings exist in closed area samples divided based on map data;
obtaining a closed area sample marked with a building and a closed area sample marked with no building in a set proportion from the marked closed area;
and training the decision tree by using the acquired attribute parameters of the closed region sample.
8. The method of any one of claims 1 to 7, wherein generating a position reference line of the acquisition road based on the target closed area comprises:
according to a preset interval, acquiring vertical lines perpendicular to the acquisition road in the target closed area, and acquiring reference points of the vertical lines in the direction close to the acquisition road on each vertical line;
and taking the connection line of the reference points as a position reference line of the acquisition road.
9. The method according to any one of claims 1 to 7, wherein after the obtaining of the closed area located at the preset collection side of the collection road, further comprising:
and deleting the closed region with the area smaller than a preset area threshold value.
10. A method for determining a location of a point of interest, comprising:
generating a position reference line by using the method for generating a position reference line according to any one of claims 1 to 9;
and determining a projection point of the interest point on the position reference line with the nearest distance, and taking the projection point as the position point of the interest point.
11. An apparatus for generating a position reference line, comprising:
the first acquisition module is used for acquiring a closed area on a preset acquisition side of an acquisition road based on map data;
the second acquisition module is used for acquiring a closed region of the touchable interest point as a target closed region;
and the generating module is used for generating a position reference line of the acquisition road based on the target closed region acquired by the second acquiring module.
12. An apparatus for determining a location of a point of interest, comprising:
a generating module, configured to generate a position reference line by using the method for generating a position reference line according to any one of claims 1 to 9;
and the releasing module is used for determining a projection point of the interest point on the position reference line with the nearest distance and taking the projection point as the position point of the interest point.
13. A computer-readable storage medium having stored thereon computer instructions, which when executed by a processor, implement a method of generating a position reference line according to any one of claims 1 to 9 or a method of determining a position of interest according to claim 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911242717.6A CN112925861A (en) | 2019-12-06 | 2019-12-06 | Position reference line generation method and device and interest point position determination method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911242717.6A CN112925861A (en) | 2019-12-06 | 2019-12-06 | Position reference line generation method and device and interest point position determination method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112925861A true CN112925861A (en) | 2021-06-08 |
Family
ID=76161721
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911242717.6A Pending CN112925861A (en) | 2019-12-06 | 2019-12-06 | Position reference line generation method and device and interest point position determination method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112925861A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117112587A (en) * | 2023-10-19 | 2023-11-24 | 腾讯科技（深圳）有限公司 | Map data processing method, device, medium and equipment |
-
2019
- 2019-12-06 CN CN201911242717.6A patent/CN112925861A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117112587A (en) * | 2023-10-19 | 2023-11-24 | 腾讯科技（深圳）有限公司 | Map data processing method, device, medium and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7155321B2 (en) | Crack analysis data editing device, crack analysis data editing method, and crack analysis data editing program | |
| JP5833567B2 (en) | Time and / or accuracy dependent weights for network generation in digital maps | |
| US8953838B2 (en) | Detecting ground geographic features in images based on invariant components | |
| CN109815300B (en) | Vehicle positioning method | |
| CN111325788B (en) | Building height determination method based on street view picture | |
| CN113034566B (en) | High-precision map construction method and device, electronic equipment and storage medium | |
| Hochmair | Spatial association of geotagged photos with scenic locations | |
| US10762660B2 (en) | Methods and systems for detecting and assigning attributes to objects of interest in geospatial imagery | |
| CN102208013A (en) | Scene matching reference data generation system and position measurement system | |
| CN105806351A (en) | Road information prediction method and device | |
| CN104422451A (en) | Road recognition method and road recognition apparatus | |
| CN111380544A (en) | Method and device for generating map data of lane line | |
| WO2022077949A1 (en) | Data processing method and device | |
| CN105912659A (en) | Map generation method and electronic device | |
| US10809072B1 (en) | Computationally efficient distance-based score approximations | |
| CN109544443A (en) | A kind of route drawing generating method and device | |
| CN115497036A (en) | Waterlogging depth calculation method and system and readable storage medium | |
| CN115546551A (en) | Deep learning-based geographic information extraction method and system | |
| JP2012215442A (en) | Own position determination system, own position determination program, own position determination method | |
| CN112925861A (en) | Position reference line generation method and device and interest point position determination method and device | |
| CN113496182B (en) | Road extraction method and device based on remote sensing image, storage medium and equipment | |
| US20210270629A1 (en) | Method and apparatus for selecting a path to a destination | |
| CN113064958B (en) | Urban planning design survey data establishment processing method based on image-transmission video processing technology and data analysis | |
| CN114065055A (en) | Intelligent tour route recommendation method and query system thereof | |
| JP2013186464A (en) | Picture data provision system |
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 |