CN112200012A - Map data processing method and device and electronic equipment - Google Patents
Map data processing method and device and electronic equipment Download PDFInfo
- Publication number
- CN112200012A CN112200012A CN202010968537.2A CN202010968537A CN112200012A CN 112200012 A CN112200012 A CN 112200012A CN 202010968537 A CN202010968537 A CN 202010968537A CN 112200012 A CN112200012 A CN 112200012A
- Authority
- CN
- China
- Prior art keywords
- satellite
- image
- target
- area
- slice
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 30
- 238000013145 classification model Methods 0.000 claims description 85
- 238000012549 training Methods 0.000 claims description 79
- 238000012360 testing method Methods 0.000 claims description 69
- 230000011218 segmentation Effects 0.000 claims description 32
- 238000005192 partition Methods 0.000 claims description 24
- 230000008569 process Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000003321 amplification Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- 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
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the disclosure provides a map data processing method and device and electronic equipment. The method comprises the following steps: acquiring a satellite slice image corresponding to a target area; identifying the satellite slice images, and determining a target satellite slice image containing a removal area in the satellite slice images; performing area identification processing on the target satellite slice image, and determining a removal area in the target satellite slice image; and acquiring the network node in the relocation area, and deleting the network node in the electronic map. The embodiment of the disclosure can improve the accuracy of verifying the network nodes in the electronic map, save a large amount of labor cost and improve the efficiency of verifying the network nodes.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of map data processing, in particular to a map data processing method and device and electronic equipment.
Background
Map data is mainly composed of points and lines, where a Point is a Point of Information (POI), and in the map data, a POI may be a house, a shop, a bus station, etc.
For a shop POI, it is currently common to verify the shop POI in the electronic map by combining order data to determine whether to go offline in the electronic map, or by manually verifying the shop POI, for example, the order of the shop POI is zero within a period of time, and the shop POI is in the electronic map, however, during the period of time, the shop may be in a state of suspended business, which may result in a lower verification accuracy of the shop POI. The manual verification method consumes a lot of manpower, and the verification period is long.
Disclosure of Invention
Embodiments of the present disclosure provide a map data processing method, an apparatus, and an electronic device, so as to improve accuracy of verifying a network node in an electronic map, save a large amount of labor cost, and improve efficiency of verifying the network node.
According to a first aspect of embodiments of the present disclosure, there is provided a map data processing method, including:
acquiring a satellite slice image corresponding to a target area;
identifying the satellite slice images, and determining a target satellite slice image containing a removal area in the satellite slice images;
performing area identification processing on the target satellite slice image, and determining a removal area in the target satellite slice image;
and acquiring the network node in the relocation area, and deleting the network node in the electronic map.
Optionally, the identifying the satellite slice image and determining the target satellite slice image including the relocation region in the satellite slice image includes:
inputting the satellite slice images into a target image classification model;
and acquiring a satellite slice image containing a removal area output by the target image classification model, and taking the satellite slice image containing the removal area as the target satellite slice image.
Optionally, before the inputting the satellite slice image into the target image classification model, the method further includes:
acquiring a first training sample and a first test sample; the first training sample and the first testing sample are both satellite slice image samples containing a removal area;
training an initial image classification model through the first training sample to obtain a trained image classification model;
testing the trained image classification model through the first test sample to obtain the classification accuracy rate corresponding to the trained image classification model;
and taking the trained image classification model as the target image classification model under the condition that the classification accuracy is greater than a first threshold value.
Optionally, the performing region identification processing on the target satellite slice image to determine a relocation region in the target satellite slice image includes:
inputting the target satellite slice image into a target area identification model;
acquiring a segmented image which is output by the target area recognition model and corresponds to the target satellite slice image and contains an area segmentation identifier;
and determining a removal area in the segmentation image according to the area segmentation identification in the segmentation image.
Optionally, before the inputting the target satellite slice image into the target region identification model, the method further includes:
acquiring a second training sample and a second test sample; the second training sample and the second testing sample are both satellite slice image samples containing a removal area;
training the initial region recognition model through the second training sample to obtain a trained region recognition model;
testing the trained area recognition model through the second test sample to obtain the partition accuracy rate corresponding to the trained area recognition model;
and under the condition that the partition accuracy is greater than a second threshold value, taking the trained region identification model as the target region identification model.
According to a second aspect of embodiments of the present disclosure, there is provided a map data processing apparatus including:
the satellite image acquisition module is used for acquiring a satellite slice image corresponding to the target area;
the target image determining module is used for identifying the satellite slice images and determining the target satellite slice images containing the removal areas in the satellite slice images;
the removal area determining module is used for carrying out area identification processing on the target satellite slice image and determining a removal area in the target satellite slice image;
and the network node deleting module is used for acquiring the network nodes in the removal area and deleting the network nodes in the electronic map.
Optionally, the target image determination module comprises:
a satellite image input unit for inputting the satellite slice image to a target image classification model;
and the target image acquisition unit is used for acquiring the satellite slice image which is output by the target image classification model and contains the removal area, and taking the satellite slice image containing the removal area as the target satellite slice image.
Optionally, the method further comprises:
the first sample acquisition module is used for acquiring a first training sample and a first test sample; the first training sample and the first testing sample are both satellite slice image samples containing a removal area;
the first training model acquisition module is used for training an initial image classification model through the first training sample to obtain a trained image classification model;
the classification accuracy rate obtaining module is used for testing the trained image classification model through the first test sample to obtain the classification accuracy rate corresponding to the trained image classification model;
and the image classification model obtaining module is used for taking the trained image classification model as the target image classification model under the condition that the classification accuracy is greater than a first threshold value.
Optionally, the relocation area determination module includes:
a target image input unit for inputting the target satellite slice image to a target region identification model;
a segmented image acquisition unit, configured to acquire a segmented image including a region segmentation identifier corresponding to the target satellite slice image output by the target region identification model;
and the removal area determining unit is used for determining the removal area in the segmentation image according to the area segmentation identification in the segmentation image.
Optionally, the method further comprises:
the second sample acquisition module is used for acquiring a second training sample and a second test sample; the second training sample and the second testing sample are both satellite slice image samples containing a removal area;
the second training model acquisition module is used for training the initial region identification model through the second training sample to obtain a trained region identification model;
the partition accuracy obtaining module is used for testing the trained area identification model through the second test sample to obtain the partition accuracy corresponding to the trained area identification model;
and the target identification model acquisition module is used for taking the trained area identification model as the target area identification model under the condition that the partition accuracy is greater than a second threshold value.
According to a third aspect of embodiments of the present disclosure, there is provided an electronic apparatus including:
a processor, a memory and a computer program stored on the memory and executable on the processor, the processor implementing the map data processing method of any one of the above when executing the program.
According to a fourth aspect of embodiments of the present disclosure, there is provided a readable storage medium, wherein instructions, when executed by a processor of an electronic device, enable the electronic device to perform any one of the map data processing methods described above.
The embodiment of the disclosure provides a map data processing scheme, which includes the steps of acquiring a satellite slice image corresponding to a target area, identifying the satellite slice image, determining the target satellite slice image including a set attribute area in the satellite slice image, performing area segmentation processing on the target satellite slice image, determining a relocation area in the target satellite slice image, acquiring a network node located in the relocation area, and deleting the network node in an electronic map. According to the method and the device for verifying the network nodes in the electronic map, the satellite map is combined to identify the removal area, the network nodes located in the removal area are deleted in the electronic map, the accuracy of the identification of the removal area can be improved by adopting the satellite map identification mode, the accuracy of verifying the network nodes in the electronic map is further improved, the network nodes are not required to be verified manually, a large amount of labor cost can be saved, and the network node verification efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the description of the embodiments of the present disclosure will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
FIG. 1 is a flowchart illustrating steps of a method for processing map data according to an embodiment of the present disclosure;
fig. 2 is a flowchart illustrating steps of another map data processing method according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a partition of a migrated region and a non-migrated region according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a map data processing apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of another map data processing apparatus according to an embodiment of the present disclosure.
Detailed Description
Technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present disclosure, belong to the protection scope of the embodiments of the present disclosure.
Example one
Referring to fig. 1, a flowchart illustrating steps of a map data processing method provided by an embodiment of the present disclosure is shown, and as shown in fig. 1, the map data processing method may specifically include the following steps:
step 101: and acquiring a satellite slice image corresponding to the target area.
The method and the device for identifying the removal area can be applied to a scene that the removal area is identified by combining with the satellite image and the network node in the removal area in the electronic map is offline.
The target area refers to an area in the electronic map that needs to be verified by the network node, in this example, the target area may be one province area, such as "beijing", "shanghai", or the like, may also be multiple provinces areas, may also be one or more country areas, or the like, and specifically, may be determined according to business requirements, which is not limited in this embodiment.
The satellite image is an image obtained by detecting the reflection of electromagnetic waves and the electromagnetic waves emitted by objects on the earth surface in space through a satellite, extracting the information of the objects, completing the remote identification of the objects, and performing information conversion and identification on the electric waves.
The satellite image has a plurality of levels, different amplification levels correspond to satellite images of different levels, details in the satellite images are clearer when the levels are higher, and the levels of the satellite image can be divided into 21 levels, namely 1-21 levels.
The satellite image is formed by splicing a plurality of tile images, each tile image is a satellite slice image, and each level of tile image corresponds to pictures with different definitions.
In this embodiment, the satellite slice image corresponding to the target area is a tile image, and in order to ensure the definition of the image, an 18-level tile image is preferably used as the satellite slice image in this example, and of course, in a specific implementation, a 19-level, 20-level or 21-level tile image may also be used as the satellite slice image, and specifically, the implementation may be determined according to business requirements, which is not limited in this embodiment.
When a network node in a target area in the electronic map is verified, a satellite slice image corresponding to the target area is acquired.
After the satellite slice image corresponding to the target area is acquired, step 102 is executed.
Step 102: and identifying the satellite slice images, and determining the target satellite slice images containing the removal area in the satellite slice images.
The target satellite slice image is an image including a relocation region in a satellite slice image corresponding to a target region, and the satellite slice image corresponding to the target region includes, for example: after the four images are identified, if the images 1, 2, 3, and 4 include a migration area, the images 1, 3, and 4 are set as target satellite slice images.
It should be understood that the above examples are only examples for better understanding of the technical solutions of the embodiments of the present disclosure, and are not to be taken as the only limitation to the embodiments.
After the satellite slice image corresponding to the target area is obtained, the satellite slice image may be identified to determine that the satellite slice image includes the target satellite slice image of the relocation area, and specifically, the identification process will be described in detail in the following second embodiment, which is not described herein again.
After the satellite slice image is identified and the target satellite slice image including the relocation area in the satellite slice image is determined, step 103 is executed.
Step 103: and carrying out region identification processing on the target satellite slice image, and determining a removal region in the target satellite slice image.
The migrated region is a region in a migrated state in the target satellite slice image.
After the target satellite slice image is obtained, the region identification processing may be performed on the target satellite slice image to identify an removed region and a non-removed region in the target satellite slice image, and a region identification model obtained through pre-training may be used in a specific region identification process to identify the removed region and the non-removed region in the target satellite slice image.
After the region identification process is performed on the target satellite slice image to determine the relocation region in the target satellite slice image, step 104 is performed.
Step 104: and acquiring the network node in the relocation area, and deleting the network node in the electronic map.
The network node refers to a POI point located in the relocation area, and in this embodiment, the network node may be a node such as a shop, a house, a bus station, and the like, and specifically, may be determined according to a service requirement, which is not limited in this embodiment.
After identifying the relocation area in the target satellite slice image, the network node in the relocation area may be obtained, and the network node may be deleted in the electronic map, for example, as shown in fig. 3, the relocation area in the identified target satellite slice image is area 1, the non-relocation area is area 2, node 3 is a network node located in area 1, and node 4 is a network node located in area 2, at this time, node 3 may be deleted in the electronic map, and node 4 does not need to perform processing.
According to the method and the device for identifying the network node, the satellite image is adopted to identify the removal area, so that the identification accuracy of the removal area can be improved, and the accuracy of verifying the network node is improved.
According to the map data processing method provided by the embodiment of the disclosure, a satellite slice image corresponding to a target area is obtained, the satellite slice image is identified, the target satellite slice image including a set attribute area in the satellite slice image is determined, the target satellite slice image is subjected to area segmentation processing, a relocation area in the target satellite slice image is determined, a network node in the relocation area is obtained, and the network node is deleted in an electronic map. According to the method and the device for verifying the network nodes in the electronic map, the satellite map is combined to identify the removal area, the network nodes located in the removal area are deleted in the electronic map, the accuracy of the identification of the removal area can be improved by adopting the satellite map identification mode, the accuracy of verifying the network nodes in the electronic map is further improved, the network nodes are not required to be verified manually, a large amount of labor cost can be saved, and the network node verification efficiency is improved.
Example two
Referring to fig. 2, a flowchart illustrating steps of another map data processing method provided in an embodiment of the present disclosure is shown, and as shown in fig. 2, the map data processing method may specifically include the following steps:
step 201: and acquiring a satellite slice image corresponding to the target area.
The method and the device for identifying the removal area can be applied to a scene that the removal area is identified by combining with the satellite image and the network node in the removal area in the electronic map is offline.
The target area refers to an area in the electronic map that needs to be verified by the network node, in this example, the target area may be one province area, such as "beijing", "shanghai", or the like, may also be multiple provinces areas, may also be one or more country areas, or the like, and specifically, may be determined according to business requirements, which is not limited in this embodiment.
The satellite image is an image obtained by detecting the reflection of electromagnetic waves and the electromagnetic waves emitted by objects on the earth surface in space through a satellite, extracting the information of the objects, completing the remote identification of the objects, and performing information conversion and identification on the electric waves.
The satellite image has a plurality of levels, different amplification levels correspond to satellite images of different levels, details in the satellite images are clearer when the levels are higher, and the levels of the satellite image can be divided into 21 levels, namely 1-21 levels.
The satellite image is formed by splicing a plurality of tile images, each tile image is a satellite slice image, and each level of tile image corresponds to pictures with different definitions.
In this embodiment, the satellite slice image corresponding to the target area is a tile image, and in order to ensure the definition of the image, an 18-level tile image is preferably used as the satellite slice image in this example, and of course, in a specific implementation, a 19-level, 20-level or 21-level tile image may also be used as the satellite slice image, and specifically, the implementation may be determined according to business requirements, which is not limited in this embodiment.
When a network node in a target area in the electronic map is verified, a satellite slice image corresponding to the target area is acquired.
After the satellite slice image corresponding to the target area is acquired, step 102 is executed.
Step 202: and inputting the satellite slice images to a target image classification model.
The target image classification model refers to a model trained in advance for identifying whether the satellite image includes the removed region. In this example, the target image classification model may be a resnet101 model or the like.
The training process for the target image classification model may be described in detail in conjunction with the following specific implementation.
In a specific implementation manner of the present disclosure, before the step 202, the method may further include:
step M1: acquiring a first training sample and a first test sample; the first training sample and the first test sample are both satellite slice image samples containing an area of relocation.
In this embodiment, the first training sample refers to a sample used for training the image classification model.
The first test sample is a sample for testing the trained image classification model.
The first training sample and the first test sample are both satellite slice images containing the region of relocation.
When the image classification model needs to be trained, a first training sample with a first quantity and a first test sample with a second quantity may be obtained, and it can be understood that the first quantity and the second quantity may be the same or different, specifically, specific numerical values of the first quantity and the second quantity may be preset according to business requirements, which is not limited in this embodiment.
After the first training sample and the first test sample are acquired, step M2 is performed.
Step M2: and training an initial image classification model through the first training sample to obtain a trained image classification model.
The initial image classification model refers to a classification model that has not been trained.
After the first training samples are obtained, the initial image classification model may be trained by using the first training samples to obtain a trained image classification model, specifically, when the number of the first training samples is 500, 500 first training samples are sequentially input to the initial image classification model to train the initial image classification model, and after the 500 first training samples are trained, the trained image classification model is obtained.
After the initial image classification model is trained by the first training sample to obtain the trained image classification model, step M3 is performed.
Step M3: and testing the trained image classification model through the first test sample to obtain the classification accuracy corresponding to the trained image classification model.
After the initial image classification model is trained to obtain the trained image classification model, the trained image classification model may be tested by using the first test sample to obtain the classification accuracy of the trained image classification model, for example, when the first test sample is 1000 samples, the 1000 samples may be sequentially input to the trained image classification model, the image including the migrated region may be output by the trained image classification model, and when the number of the images including the migrated region output by the trained image classification model is 800, the classification accuracy may be obtained by calculating from the number of the output images including the migrated region and the total number of the test samples, where the classification accuracy is 800/1000 × 100% to 80%.
It should be understood that the above examples are only examples for better understanding of the technical solutions of the embodiments of the present disclosure, and are not to be taken as the only limitation to the embodiments.
After the classification accuracy corresponding to the trained image classification model is obtained, step M4 is executed.
Step M4: and taking the trained image classification model as the target image classification model under the condition that the classification accuracy is greater than a first threshold value.
The first threshold is a threshold preset by a service person and used for determining whether the classification accuracy of the trained image classification model meets the requirement, and a specific numerical value of the first threshold may be determined according to the service requirement, which is not limited in this embodiment.
After the classification accuracy of the trained image classification model is obtained, the classification accuracy may be compared with a first threshold.
Under the condition that the classification accuracy is less than or equal to the first threshold, the first training sample may be continuously obtained to continuously train the trained image classification model, and specifically, the training test process may refer to the foregoing implementation manner, which is not described herein again.
Under the condition that the classification accuracy is greater than the first threshold, the trained image classification model can accurately identify the satellite slice image containing the removal area, and at the moment, the trained image classification model can be used as a target image classification model.
After the satellite slice images are input to the target image classification model, step 203 is performed.
Step 203: and acquiring a satellite slice image containing a removal area output by the target image classification model, and taking the satellite slice image containing the removal area as the target satellite slice image.
After the satellite slice image is input to the target image classification model, the satellite slice image including the relocation region output by the target image classification model may be acquired, and the satellite slice image including the relocation region may be taken as the target satellite slice image.
After the target satellite slice image is acquired, step 204 is performed.
Step 204: and inputting the target satellite slice image into a target area identification model.
The target region identification model refers to a model for identifying a region of relocation in a satellite slice image. In this embodiment, the target region identification model may be a maskrcnn model or the like.
The training process for target area recognition may be described in detail in conjunction with the following specific implementation.
In another specific implementation manner of the present disclosure, before the step 204, the method may further include:
step N1: acquiring a second training sample and a second test sample; the second training sample and the second test sample are both satellite slice image samples containing an area of relocation.
In this embodiment, the second training sample refers to a sample used for training the region recognition model.
The second test sample is a sample for testing the trained region identification model.
The second training sample and the second testing sample are both satellite slice image samples including region segmentation identifiers of a migrated region and a non-migrated region, in this example, the region segmentation identifiers may be identifiers such as a segmentation line for dividing the migrated region and the non-migrated region in the satellite slice image, or may be color segmentation identifiers, specifically, the region segmentation identifiers may be determined according to business requirements, which is not limited in this embodiment.
When the region identification model needs to be trained, a second training sample and a second testing sample can be obtained, and then step N2 is performed.
Step N2: and training the initial region recognition model through the second training sample to obtain a trained region recognition model.
The initial region identification model is a model for identifying a migrated region that has not been trained.
After the second training samples are obtained, the initial region identification model may be trained through the second training samples to obtain a trained region identification model, specifically, when the number of the second training samples is 800, the 800 second training samples may be sequentially input to the initial region identification model to train the initial region identification model, and after the training of the initial region identification model by using the 800 second training samples is completed, the trained region identification model may be obtained.
After the trained region identification model is obtained, step N3 is performed.
Step N3: and testing the trained area identification model through the second test sample to obtain the partition accuracy rate corresponding to the trained area identification model.
The partition accuracy refers to the accuracy of the trained region identification model obtained by testing the trained region identification model by using the test sample.
After obtaining the trained region identification model, the trained region identification model may be tested by the second test sample to obtain the partition accuracy corresponding to the trained region identification model, for example, when the second test sample is 1000 samples, the 1000 samples may be sequentially input to the trained region identification model, so that the trained region identification model outputs the removed region in the second test sample, further matching the removed area in the output second test sample with the removed area divided by the second test sample in advance, determining the accurately divided test sample according to the matching result, when the number of the test samples accurately divided in the removal area is 950, the calculation can be performed according to the number of the output test samples accurately divided and the total number of the test samples, to obtain the partition accuracy, the partition accuracy at this time was 950/1000 × 100%: 95%.
It is to be understood that the above examples are only examples set forth for a better understanding of the technical solutions of the embodiments of the present disclosure, and are not to be taken as the only limitations on the embodiments of the present disclosure.
After the partition accuracy corresponding to the trained region identification model is obtained, step N4 is executed.
Step N4: and under the condition that the partition accuracy is greater than a second threshold value, taking the trained region identification model as the target region identification model.
The second threshold is a threshold preset by a service person and used for determining whether the trained region identification model can accurately divide the removed region in the satellite slice image, and a specific value of the second threshold may be determined according to a service requirement, which is not limited in this embodiment.
After the partition accuracy is obtained, the partition accuracy may be compared to a second threshold.
Under the condition that the partition accuracy is less than or equal to the second threshold, the second training sample may be continuously obtained, so that the obtained second training sample is used to continue training the trained region identification model, specifically, the training test process may be described in detail in combination with the above implementation process, and this embodiment is not described herein again.
Under the condition that the partition accuracy is greater than the second threshold, it indicates that the trained region identification model can accurately partition the removed region and the non-removed region in the satellite slice image, and at this time, the trained region identification model can be used as a target region identification model.
After the target satellite slice image is input to the target region identification model, step 205 is performed.
Step 205: and acquiring a segmented image which comprises a region segmentation identifier and corresponds to the target satellite slice image output by the target region identification model.
After the target satellite slice image is input to the target area recognition model, the target area recognition model may process the target satellite slice image to divide the removed area and the non-removed area in the target satellite slice image, so as to obtain a segmented image including an area segmentation identifier.
After the segmented image including the region segmentation markers corresponding to the target satellite slice image output by the target region identification model is acquired, step 206 is performed.
Step 206: and determining a removal area in the segmentation image according to the area segmentation identification in the segmentation image.
After the segmented image is obtained, a removal area in the segmented image may be determined according to an area segmentation identifier in the segmented image, for example, as shown in fig. 3, the area segmentation identifier is a line identifier, at this time, the removal area in the segmented image is an area 1, and the non-removal area is an area 2.
After the region partition identifier in the segmented image is determined, the step 207 is executed.
Step 207: and acquiring the network node in the relocation area, and deleting the network node in the electronic map.
The network node refers to a POI point located in the relocation area, and in this embodiment, the network node may be a node such as a shop, a house, a bus station, and the like, and specifically, may be determined according to a service requirement, which is not limited in this embodiment.
After identifying the relocation area in the target satellite slice image, the network node in the relocation area may be obtained, and the network node may be deleted in the electronic map, for example, as shown in fig. 3, the relocation area in the identified target satellite slice image is area 1, the non-relocation area is area 2, node 3 is a network node located in area 1, and node 4 is a network node located in area 2, at this time, node 3 may be deleted in the electronic map, and node 4 does not need to perform processing.
According to the method and the device for identifying the network node, the satellite image is adopted to identify the removal area, so that the identification accuracy of the removal area can be improved, and the accuracy of verifying the network node is improved.
According to the map data processing method provided by the embodiment of the disclosure, a satellite slice image corresponding to a target area is obtained, the satellite slice image is identified, the target satellite slice image including a set attribute area in the satellite slice image is determined, the target satellite slice image is subjected to area segmentation processing, a relocation area in the target satellite slice image is determined, a network node in the relocation area is obtained, and the network node is deleted in an electronic map. According to the method and the device for verifying the network nodes in the electronic map, the satellite map is combined to identify the removal area, the network nodes located in the removal area are deleted in the electronic map, the accuracy of the identification of the removal area can be improved by adopting the satellite map identification mode, the accuracy of verifying the network nodes in the electronic map is further improved, the network nodes are not required to be verified manually, a large amount of labor cost can be saved, and the network node verification efficiency is improved.
EXAMPLE III
Referring to fig. 4, a schematic structural diagram of a map data processing apparatus provided in an embodiment of the present disclosure is shown, and as shown in fig. 4, the map data processing apparatus 300 may specifically include the following modules:
a satellite image obtaining module 310, configured to obtain a satellite slice image corresponding to a target region;
a target image determining module 320, configured to identify the satellite slice image, and determine a target satellite slice image including a relocation area in the satellite slice image;
an relocation area determination module 330, configured to perform area identification processing on the target satellite slice image, and determine a relocation area in the target satellite slice image;
and the network node deleting module 340 is configured to acquire a network node located in the relocation area, and delete the network node in the electronic map.
The map data processing device provided by the embodiment of the disclosure identifies the satellite slice image by acquiring the satellite slice image corresponding to the target area, determines the target satellite slice image containing the set attribute area in the satellite slice image, performs area segmentation processing on the target satellite slice image, determines the relocation area in the target satellite slice image, acquires the network node located in the relocation area, and deletes the network node in the electronic map. According to the method and the device for verifying the network nodes in the electronic map, the satellite map is combined to identify the removal area, the network nodes located in the removal area are deleted in the electronic map, the accuracy of the identification of the removal area can be improved by adopting the satellite map identification mode, the accuracy of verifying the network nodes in the electronic map is further improved, the network nodes are not required to be verified manually, a large amount of labor cost can be saved, and the network node verification efficiency is improved.
Example four
Referring to fig. 5, a schematic structural diagram of another map data processing apparatus provided in an embodiment of the present disclosure is shown, and as shown in fig. 5, the map data processing apparatus 400 may specifically include the following modules:
a satellite image obtaining module 410, configured to obtain a satellite slice image corresponding to a target region;
a target image determining module 420, configured to identify the satellite slice image, and determine a target satellite slice image including a relocation area in the satellite slice image;
an relocation area determination module 430, configured to perform area identification processing on the target satellite slice image, and determine a relocation area in the target satellite slice image;
and a network node deleting module 440, configured to acquire a network node located in the relocation area, and delete the network node in the electronic map.
Optionally, the target image determination module 420 includes:
a satellite image input unit 421 for inputting the satellite slice image to a target image classification model;
a target image obtaining unit 423, configured to obtain a satellite slice image including a removal region output by the target image classification model, and use the satellite slice image including the removal region as the target satellite slice image.
Optionally, the method further comprises:
the first sample acquisition module is used for acquiring a first training sample and a first test sample; the first training sample and the first testing sample are both satellite slice image samples containing a removal area;
the first training model acquisition module is used for training an initial image classification model through the first training sample to obtain a trained image classification model;
the classification accuracy rate obtaining module is used for testing the trained image classification model through the first test sample to obtain the classification accuracy rate corresponding to the trained image classification model;
and the image classification model obtaining module is used for taking the trained image classification model as the target image classification model under the condition that the classification accuracy is greater than a first threshold value.
Optionally, the relocation area determination module 430 includes:
a target image input unit 431 for inputting the target satellite slice image to a target region recognition model;
a segmented image acquisition unit 432, configured to acquire a segmented image including a region segmentation identifier corresponding to the target satellite slice image output by the target region identification model;
a relocation area determination unit 433, configured to determine a relocation area in the segmented image according to the area segmentation identifier in the segmented image.
Optionally, the method further comprises:
the second sample acquisition module is used for acquiring a second training sample and a second test sample; the second training sample and the second testing sample are both satellite slice image samples containing a removal area;
the second training model acquisition module is used for training the initial region identification model through the second training sample to obtain a trained region identification model;
the partition accuracy obtaining module is used for testing the trained area identification model through the second test sample to obtain the partition accuracy corresponding to the trained area identification model;
and the target identification model acquisition module is used for taking the trained area identification model as the target area identification model under the condition that the partition accuracy is greater than a second threshold value.
The map data processing device provided by the embodiment of the disclosure identifies the satellite slice image by acquiring the satellite slice image corresponding to the target area, determines the target satellite slice image containing the set attribute area in the satellite slice image, performs area segmentation processing on the target satellite slice image, determines the relocation area in the target satellite slice image, acquires the network node located in the relocation area, and deletes the network node in the electronic map. According to the method and the device for verifying the network nodes in the electronic map, the satellite map is combined to identify the removal area, the network nodes located in the removal area are deleted in the electronic map, the accuracy of the identification of the removal area can be improved by adopting the satellite map identification mode, the accuracy of verifying the network nodes in the electronic map is further improved, the network nodes are not required to be verified manually, a large amount of labor cost can be saved, and the network node verification efficiency is improved.
An embodiment of the present disclosure also provides an electronic device, including: a processor, a memory and a computer program stored on the memory and executable on the processor, the processor implementing the map data processing method of the foregoing embodiment when executing the program.
Embodiments of the present disclosure also provide a readable storage medium, in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform the map data processing method of the foregoing embodiments.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present disclosure are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the embodiments of the present disclosure as described herein, and any descriptions of specific languages are provided above to disclose the best modes of the embodiments of the present disclosure.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the disclosure may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the disclosure, various features of the embodiments of the disclosure are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that is, claimed embodiments of the disclosure require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of an embodiment of this disclosure.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
The various component embodiments of the disclosure may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be understood by those skilled in the art that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in a motion picture generating device according to an embodiment of the present disclosure. Embodiments of the present disclosure may also be implemented as an apparatus or device program for performing a portion or all of the methods described herein. Such programs implementing embodiments of the present disclosure may be stored on a computer readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit embodiments of the disclosure, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the disclosure may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The above description is only for the purpose of illustrating the preferred embodiments of the present disclosure and is not to be construed as limiting the embodiments of the present disclosure, and any modifications, equivalents, improvements and the like that are made within the spirit and principle of the embodiments of the present disclosure are intended to be included within the scope of the embodiments of the present disclosure.
The above description is only a specific implementation of the embodiments of the present disclosure, but the scope of the embodiments of the present disclosure is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the embodiments of the present disclosure, and all the changes or substitutions should be covered by the scope of the embodiments of the present disclosure. Therefore, the protection scope of the embodiments of the present disclosure shall be subject to the protection scope of the claims.
Claims (10)
1. A map data processing method, comprising:
acquiring a satellite slice image corresponding to a target area;
identifying the satellite slice images, and determining a target satellite slice image containing a removal area in the satellite slice images;
performing area identification processing on the target satellite slice image, and determining a removal area in the target satellite slice image;
and acquiring the network node in the relocation area, and deleting the network node in the electronic map.
2. The method of claim 1, wherein the identifying the satellite slice images and determining the target satellite slice image containing the relocation region in the satellite slice images comprises:
inputting the satellite slice images into a target image classification model;
and acquiring a satellite slice image containing a removal area output by the target image classification model, and taking the satellite slice image containing the removal area as the target satellite slice image.
3. The method of claim 2, further comprising, prior to said inputting the satellite slice images to a target image classification model:
acquiring a first training sample and a first test sample; the first training sample and the first testing sample are both satellite slice image samples containing a removal area;
training an initial image classification model through the first training sample to obtain a trained image classification model;
testing the trained image classification model through the first test sample to obtain the classification accuracy rate corresponding to the trained image classification model;
and taking the trained image classification model as the target image classification model under the condition that the classification accuracy is greater than a first threshold value.
4. The method according to claim 1, wherein the performing a region identification process on the target satellite slice image to determine a region of relocation in the target satellite slice image comprises:
inputting the target satellite slice image into a target area identification model;
acquiring a segmented image which is output by the target area recognition model and corresponds to the target satellite slice image and contains an area segmentation identifier;
and determining a removal area in the segmentation image according to the area segmentation identification in the segmentation image.
5. The method of claim 4, further comprising, prior to said inputting the target satellite slice image to a target region identification model:
acquiring a second training sample and a second test sample; the second training sample and the second testing sample are both satellite slice image samples containing a removal area;
training the initial region recognition model through the second training sample to obtain a trained region recognition model;
testing the trained area recognition model through the second test sample to obtain the partition accuracy rate corresponding to the trained area recognition model;
and under the condition that the partition accuracy is greater than a second threshold value, taking the trained region identification model as the target region identification model.
6. A map data processing apparatus, characterized by comprising:
the satellite image acquisition module is used for acquiring a satellite slice image corresponding to the target area;
the target image determining module is used for identifying the satellite slice images and determining the target satellite slice images containing the removal areas in the satellite slice images;
the removal area determining module is used for carrying out area identification processing on the target satellite slice image and determining a removal area in the target satellite slice image;
and the network node deleting module is used for acquiring the network nodes in the removal area and deleting the network nodes in the electronic map.
7. The apparatus of claim 6, wherein the target image determination module comprises:
a satellite image input unit for inputting the satellite slice image to a target image classification model;
and the target image acquisition unit is used for acquiring the satellite slice image which is output by the target image classification model and contains the removal area, and taking the satellite slice image containing the removal area as the target satellite slice image.
8. The apparatus of claim 7, further comprising:
the first sample acquisition module is used for acquiring a first training sample and a first test sample; the first training sample and the first testing sample are both satellite slice image samples containing a removal area;
the first training model acquisition module is used for training an initial image classification model through the first training sample to obtain a trained image classification model;
the classification accuracy rate obtaining module is used for testing the trained image classification model through the first test sample to obtain the classification accuracy rate corresponding to the trained image classification model;
and the image classification model obtaining module is used for taking the trained image classification model as the target image classification model under the condition that the classification accuracy is greater than a first threshold value.
9. An electronic device, comprising:
a processor, a memory and a computer program stored on the memory and executable on the processor, the processor implementing the map data processing method according to any one of claims 1 to 5 when executing the program.
10. A readable storage medium, characterized in that instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the map data processing method according to any one of method claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010968537.2A CN112200012A (en) | 2020-09-15 | 2020-09-15 | Map data processing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010968537.2A CN112200012A (en) | 2020-09-15 | 2020-09-15 | Map data processing method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112200012A true CN112200012A (en) | 2021-01-08 |
Family
ID=74015101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010968537.2A Pending CN112200012A (en) | 2020-09-15 | 2020-09-15 | Map data processing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112200012A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080298638A1 (en) * | 2007-05-31 | 2008-12-04 | Tohru Miyazaki | Map change detection device, map change detection method, and program |
| CN108052876A (en) * | 2017-11-28 | 2018-05-18 | 广东数相智能科技有限公司 | Regional development appraisal procedure and device based on image identification |
| JP2018097506A (en) * | 2016-12-12 | 2018-06-21 | 株式会社日立製作所 | Satellite image processing system and method |
| CN108764090A (en) * | 2018-05-18 | 2018-11-06 | 腾讯大地通途（北京）科技有限公司 | It is a kind of regionality unusual fluctuation determine method, apparatus, server and storage medium |
| CN110555352A (en) * | 2018-06-04 | 2019-12-10 | 百度在线网络技术（北京）有限公司 | interest point identification method, device, server and storage medium |
| CN111241881A (en) * | 2018-11-29 | 2020-06-05 | 中国移动通信集团四川有限公司 | Method, apparatus, device and medium for region identification |
| WO2020155518A1 (en) * | 2019-02-03 | 2020-08-06 | 平安科技（深圳）有限公司 | Object detection method and device, computer device and storage medium |
-
2020
- 2020-09-15 CN CN202010968537.2A patent/CN112200012A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080298638A1 (en) * | 2007-05-31 | 2008-12-04 | Tohru Miyazaki | Map change detection device, map change detection method, and program |
| JP2018097506A (en) * | 2016-12-12 | 2018-06-21 | 株式会社日立製作所 | Satellite image processing system and method |
| CN108052876A (en) * | 2017-11-28 | 2018-05-18 | 广东数相智能科技有限公司 | Regional development appraisal procedure and device based on image identification |
| CN108764090A (en) * | 2018-05-18 | 2018-11-06 | 腾讯大地通途（北京）科技有限公司 | It is a kind of regionality unusual fluctuation determine method, apparatus, server and storage medium |
| CN110555352A (en) * | 2018-06-04 | 2019-12-10 | 百度在线网络技术（北京）有限公司 | interest point identification method, device, server and storage medium |
| CN111241881A (en) * | 2018-11-29 | 2020-06-05 | 中国移动通信集团四川有限公司 | Method, apparatus, device and medium for region identification |
| WO2020155518A1 (en) * | 2019-02-03 | 2020-08-06 | 平安科技（深圳）有限公司 | Object detection method and device, computer device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107742093B (en) | Real-time detection method, server and system for infrared image power equipment components | |
| CN110910343A (en) | Method and device for detecting pavement cracks and computer equipment | |
| CN110110627B (en) | Real-time target detection method for computing resource limitation platform deployment | |
| CN109543680A (en) | Location determining method, appliance arrangement and the medium of point of interest | |
| CN110032916A (en) | A kind of method and apparatus detecting target object | |
| CN111353580B (en) | Training method of target detection network, electronic equipment and storage medium | |
| CN115409069A (en) | Village and town building identification method, classification method, device, electronic equipment and medium | |
| CN111340015B (en) | Positioning method and device | |
| CN111753870B (en) | Training method, device and storage medium of target detection model | |
| CN111402413A (en) | Three-dimensional visual positioning method and device, computing equipment and storage medium | |
| CN109300139A (en) | Method for detecting lane lines and device | |
| CN109858318A (en) | The classification recognition methods of landscape image and device | |
| CN109460365A (en) | A kind of system performance testing method, apparatus, equipment and storage medium | |
| CN117703023A (en) | Seamless paving method for rock plates/tiles | |
| CN111914863B (en) | Target detection method, device, terminal equipment and computer readable storage medium | |
| CN112200012A (en) | Map data processing method and device and electronic equipment | |
| CN110069997B (en) | Scene classification method and device and electronic equipment | |
| CN110705398A (en) | Mobile-end-oriented test paper layout image-text real-time detection method | |
| CN110782390A (en) | Image correction processing method and device and electronic equipment | |
| CN111383337B (en) | Method and device for identifying objects | |
| CN106303161B (en) | A kind of image processing method and electronic equipment | |
| CN110457705B (en) | Method, device, equipment and storage medium for processing point of interest data | |
| CN113570341A (en) | Distribution network equipment information input method and device | |
| CN112802028A (en) | Image processing method and device for mediastinal organ segmentation | |
| CN113065071B (en) | Product information recommendation method and computer equipment |
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 |