CN110674834A - Geo-fence identification method, device, equipment and computer-readable storage medium - Google Patents
Geo-fence identification method, device, equipment and computer-readable storage medium Download PDFInfo
- Publication number
- CN110674834A CN110674834A CN201810717814.5A CN201810717814A CN110674834A CN 110674834 A CN110674834 A CN 110674834A CN 201810717814 A CN201810717814 A CN 201810717814A CN 110674834 A CN110674834 A CN 110674834A
- Authority
- CN
- China
- Prior art keywords
- sample
- information
- geo
- fence
- feature vector
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012360 testing method Methods 0.000 claims abstract description 63
- 230000002093 peripheral effect Effects 0.000 claims abstract description 46
- 239000013598 vector Substances 0.000 claims description 148
- 238000013527 convolutional neural network Methods 0.000 claims description 26
- 238000013528 artificial neural network Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 17
- 230000015654 memory Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 4
- 239000003086 colorant Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a geo-fence identification method, a device, equipment and a computer-readable storage medium, wherein the method comprises the following steps: acquiring a test image to be identified, wherein the test image at least comprises: at least one target area, peripheral road network information of the target area and population thermodynamic information of the target area; extracting characteristic parameters of the test image according to the target area, the peripheral road network information and the population thermal information; and acquiring the geo-fence information in the test image by adopting a pre-configured geo-fence identification model according to the characteristic parameters. According to the scheme, the geo-fence information of the test image is identified based on the feature parameters of the peripheral road network information and the population thermal information, so that the geo-fence information of the test image can be identified, more accurate indicativity can be given in the geo-fence identification process, the road is prevented from being divided into geo-fences for the blind purpose, and the accuracy of geo-fence identification can be obviously improved.
Description
Technical Field
The present invention relates to the field of geo-fencing technologies, and in particular, to a geo-fence identification method, apparatus, device, and computer-readable storage medium.
Background
Geofences refer to polygons that encompass a target area on a two-dimensional plane, i.e., a virtual geofence that encloses a virtual geographic boundary. The handset may receive automatic notifications and alerts when the handset enters, leaves, or is active within a particular geographic area. With geo-fencing, a location social networking site can help users automatically register when entering a certain region. The method can be applied to the scenes of security protection, intelligent going out and visiting and the like. The application scenarios all involve safety problems, so that the accurate identification and discovery of the geofence are of great significance to the wide application of the geofence.
Existing geofence identification methods generally include the following: manual labeling, a clustering algorithm based on user positions, satellite image boundary detection and the like; wherein, the manual marking processing cost is higher, and the method is not suitable for wide-range popularization. The clustering algorithm based on the user position also has some problems, for example, parameters of the clustering algorithm need to be manually adjusted, and proper parameters cannot be automatically obtained; roads are easily divided into geofences in densely populated areas, and even multiple areas are merged across roads. And the single satellite image data needs to do a lot of extra cleaning work, such as eliminating the interference of cloud layers and the like.
Therefore, the existing geo-fence identification scheme is high in cost or inaccurate in identification result.
Disclosure of Invention
The invention provides a geo-fence identification method, a device, equipment and a computer readable storage medium, which can identify geo-fence information of a test image based on characteristic parameters of peripheral road network information and population thermodynamic information, can give more accurate indication in the process of geo-fence identification, avoid dividing roads into geo-fences for blind purposes, and further remarkably improve the accuracy of geo-fence identification.
The invention provides a geo-fence identification method in a first aspect, which comprises the following steps: acquiring a test image to be identified, wherein the test image at least comprises: at least one target area, peripheral road network information of the target area and population thermodynamic information of the target area; extracting characteristic parameters of the test image according to the target area, the peripheral road network information and the population thermal information; and acquiring the geo-fence information in the test image by adopting a pre-configured geo-fence identification model according to the characteristic parameters.
Optionally, the extracting the feature parameters of the test image according to the target area, the peripheral road network information, and the population thermal information specifically includes: respectively extracting a first feature vector corresponding to the target area, a second feature vector corresponding to the peripheral road network information and a third feature vector corresponding to the population thermal information; and splicing the first feature vector, the second feature vector and the third feature vector to obtain the feature parameters.
Optionally, before the acquiring the test image to be identified, the method further includes: obtaining a sample image, wherein the sample image comprises at least one sample area, sample geo-fence information of the sample area, sample peripheral road network information and sample population thermodynamic information; establishing the geo-fence identification model based on a neural network from the sample images.
Optionally, the neural network is a convolutional neural network; the establishing of the geo-fence identification model based on the neural network according to the sample image specifically includes: extracting a feature vector corresponding to the sample geo-fence information as an expected sample label of the convolutional neural network; respectively extracting a first sample characteristic vector corresponding to the sample area, a second sample characteristic vector corresponding to the sample peripheral road network information and a third sample characteristic vector corresponding to the sample population thermal information; splicing the first sample characteristic vector, the second sample characteristic vector and the third sample characteristic vector to obtain a total sample vector; and inputting the expected sample label and the total sample vector as training data into the convolutional neural network for training to obtain the geo-fence identification model.
Optionally, the second sample feature vector and the feature vector corresponding to the sample geo-fence information are binary vectors.
A second aspect of the present invention provides a geo-fence identification apparatus comprising: a first obtaining module, configured to obtain a test image to be identified, where the test image at least includes: at least one target area, peripheral road network information of the target area and population thermodynamic information of the target area; the extraction module is used for extracting the characteristic parameters of the test image according to the target area, the peripheral road network information and the population thermal information; and the identification module is used for acquiring the geo-fence information in the test image by adopting a pre-configured geo-fence identification model according to the characteristic parameters.
Optionally, the extracting module is specifically configured to: respectively extracting a first feature vector corresponding to the target area, a second feature vector corresponding to the peripheral road network information and a third feature vector corresponding to the population thermal information; and splicing the first feature vector, the second feature vector and the third feature vector to obtain the feature parameters.
Optionally, the method further comprises: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a sample image, and the sample image comprises at least one sample area, sample geo-fence information of the sample area, sample peripheral road network information and sample population thermodynamic information; and the establishing module is used for establishing the geo-fence identification model based on the neural network according to the sample image.
Optionally, the neural network is a convolutional neural network; the establishing module is specifically configured to: extracting a feature vector corresponding to the sample geo-fence information as an expected sample label of the convolutional neural network; respectively extracting a first sample characteristic vector corresponding to the sample area, a second sample characteristic vector corresponding to the sample peripheral road network information and a third sample characteristic vector corresponding to the sample population thermal information; splicing the first sample characteristic vector, the second sample characteristic vector and the third sample characteristic vector to obtain a total sample vector; and inputting the expected sample label and the total sample vector as training data into the convolutional neural network for training to obtain the geo-fence identification model.
Optionally, the second sample feature vector and the feature vector corresponding to the sample geo-fence information are binary vectors.
A third aspect of the present invention provides a geo-fence identification apparatus comprising: a memory; a processor; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to perform the method of the first aspect of the invention and any of its alternatives.
A fourth aspect of the present invention provides a computer-readable storage medium comprising: a program which, when run on a computer, causes the computer to perform the method of the first aspect of the invention and any of its alternatives.
According to the method, the device, the equipment and the computer readable storage medium for identifying the geo-fence, the geo-fence identification model is configured in advance, then the test image to be identified is obtained, the characteristic parameters of the test image are extracted based on the peripheral road network information and the population thermodynamic information, the characteristic parameters are input into the geo-fence identification model for identification, and therefore the geo-fence information in the test image can be obtained. The geo-fence information of the test image is identified based on the characteristic parameters of the peripheral road network information and the population thermal information, so that more accurate indicativity can be given in the geo-fence identification process, roads are prevented from being divided into geo-fences for the blind purpose, and the accuracy of geo-fence identification can be obviously improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart illustrating a geofence identification method, according to an exemplary embodiment of the present invention;
fig. 2 is a flowchart illustrating a geo-fence identification method according to another exemplary embodiment of the present invention;
FIG. 3 is a block diagram of a geo-fence identification device shown in an exemplary embodiment of the present invention;
fig. 4 is a block diagram of a geo-fence identification device according to another exemplary embodiment of the present invention;
fig. 5 is a block diagram illustrating a geo-fence identification device in accordance with an exemplary embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a flowchart illustrating a geo-fence identification method according to an exemplary embodiment of the present invention.
As shown in fig. 1, the execution subject of the embodiment is a geo-fence identification apparatus, which may be integrated in a terminal, where the terminal may be an electronic device such as a mobile phone and a tablet computer. The present embodiment provides a geo-fence identification method, which includes the following steps:
step 101: acquiring a test image to be identified, wherein the test image at least comprises: at least one target area, peripheral road network information of the target area and population thermodynamic information of the target area.
The test image may be an image of a specific location acquired in real time by the acquisition device, or may be a history image, which is not limited in this embodiment. The target area may be, for example, a building, a park, or a piece of area manually marked in the test image in advance, and the representation form of the target area is not limited in this embodiment.
In this step, a test image is first obtained, and test data may be acquired in real time by an acquisition device, for example, an image of a certain area is acquired in real time by a camera of a mobile phone as the test image. The test image may also be obtained directly from other storage devices or from the terminal's own storage module. The test images include, but are not limited to: at least one target area, peripheral road network information of the target area and population thermodynamic information of the target area.
Step 102: extracting characteristic parameters of the test image according to the target area, the peripheral road network information and the population heat power information;
the characteristic parameters may be represented in a vector or matrix manner, or may be represented in other manners, which is not limited in this embodiment.
In this step, feature parameters of the test image are extracted based on the surrounding road network information and the population thermodynamic information, because in an actual application scenario, a building is taken as an example of a target area, a geofence of a building generally takes the surrounding road network of the building or the building edge as a geofence boundary, and a population thermodynamic diagram can represent personnel distribution in the building, and the edge of the population distribution is generally the edge of the building, the geofence information of the test image is identified based on the surrounding road network information and the feature parameters of the population thermodynamic information, so that a more accurate indication can be given in the geofence identification process, roads are prevented from being divided into geofences for a blind purpose, and the accuracy of geofence identification can be significantly improved.
Step 103: and acquiring the geo-fence information in the test image by adopting a pre-configured geo-fence identification model according to the characteristic parameters.
In this step, the geo-fence identification model may be pre-configured as needed, and when in use, the geo-fence information in the test image may be output only by inputting the characteristic parameters of the test image into the geo-fence identification model. Therefore, a large amount of manual marks are not needed, roads cannot be divided into the geographic fences, and the identification precision of the geographic fences is greatly improved.
According to the geo-fence identification method provided by the invention, the geo-fence identification model is configured in advance, then the test image to be identified is obtained, the characteristic parameters of the test image are extracted based on the peripheral road network information and the population thermodynamic information, and the characteristic parameters are input into the geo-fence identification model for identification, so that the geo-fence information in the test image can be obtained. The geo-fence information of the test image is identified based on the characteristic parameters of the peripheral road network information and the population thermal information, so that more accurate indicativity can be given in the geo-fence identification process, roads are prevented from being divided into geo-fences for the blind purpose, and the accuracy of geo-fence identification can be obviously improved.
Fig. 2 is a flowchart illustrating a geo-fence identification method according to another exemplary embodiment of the present invention.
As shown in fig. 2, the present embodiment provides a geo-fence identification method, which is based on the geo-fence identification method shown in an exemplary embodiment of the present invention, and further includes steps of specifically extracting feature parameters, establishing a geo-fence identification model, and the like. The method comprises the following steps:
step 201: and acquiring a sample image, wherein the sample image comprises at least one sample area, sample geo-fence information of the sample area, sample peripheral road network information and sample population thermodynamic information.
In this step, the sample image may be an image in which the electronic fence information has been determined, or geo-fence information in which some pictures are manually marked in a small amount may be used as the sample image; this embodiment does not limit this; the sample image includes, but is not limited to, at least one sample region and sample geofence information, sample perimeter road network information, and sample population thermodynamic information for the sample region. The sample area may be a building or a park, such as a building or a park, for example, and this embodiment is not limited at the very least.
Step 202: and establishing a geographic fence identification model based on the neural network according to the sample image.
The neural network is an artificial neural network, is an operation model and has a self-learning function. The network has a self-learning function, for example, when image recognition is realized, the network can slowly learn to recognize similar images through the self-learning function only by inputting a plurality of different image templates and corresponding recognition results into the artificial neural network. The self-learning function is of particular importance for the prediction.
In this step, the sample image obtained in step 201 is input to a neural network for self-learning, so that a geo-fence identification model based on the neural network can be established.
Further, the neural network may be a convolutional neural network. Step 202 may specifically include: extracting a feature vector corresponding to the sample geo-fence information as an expected sample label of the convolutional neural network; respectively extracting a first sample characteristic vector corresponding to the sample area, a second sample characteristic vector corresponding to the road network information around the sample, and a third sample characteristic vector corresponding to the thermodynamic information of the sample population; splicing the first sample characteristic vector, the second sample characteristic vector and the third sample characteristic vector to obtain a total sample vector; and inputting the expected sample labels and the total sample vectors as training data into a convolutional neural network for training to obtain a geo-fence identification model.
In this step, the feature vector may be used to characterize the feature parameters of the sample image; specifically, feature vectors corresponding to the sample geofence information can be extracted as expected sample labels for the convolutional neural network. In an actual application scenario, assume that the image specification of a sample region in a sample image is n × m pixels (n and m are positive integers, respectively), and RGB three channels. Its sample geofence can be represented by a black-and-white image of n x m, with black portions representing the sample geofence, and the image feature vectors extracted. Where the sample geofence needs to closely encompass the sample area. Optionally, the image of the sample geofence can be processed into a binary vector of dimension n × m as the expected sample label for the convolutional neural network.
And then extracting a first sample characteristic vector corresponding to the sample area, a second sample characteristic vector corresponding to the road network information around the sample, and a third sample characteristic vector corresponding to the thermodynamic information of the sample population. Optionally, the feature vector corresponding to the second sample feature vector and the sample geo-fence information is a binary vector. Specifically, assume that the image specification of the sample region in the sample image is n × m pixels (n, m are positive integers, respectively), RGB three channels. The image of the sample region may be processed into a vector having dimensions 3 x n x m (n, m may each take on values from 0 to 255 integer values) as a first sample feature vector. Because geofencing is often bounded by surrounding road networks, sample surrounding road network information for a sample area can be processed in analogy to sample geofencing information; namely, the sample peripheral road network of the sample region can be represented by using a black-white image of n × m, and the binary feature vector of the image is extracted as a second sample feature vector, wherein the road is represented by using a black part. The sample population thermodynamic information can be represented in 256-level gray scale images of n x m, where darker colors indicate greater population density. The sample population thermal image may be processed into a vector of n x m and values ranging from 0 to 255 integer values as a third sample feature vector.
And finally, splicing the first sample characteristic vector, the second sample characteristic vector and the third sample characteristic vector to obtain a total sample vector. And inputting the expected sample labels and the total sample vectors as training data into a convolutional neural network for training to obtain a geo-fence identification model. Namely, a vector with the dimension of 3 x n x m and the value of 0-255 integer value corresponding to the sample area, a vector with the dimension of n x m and the value of binary vector corresponding to the road network information around the sample, and a vector with the dimension of n x m and the value of 0-255 integer value corresponding to the sample population thermal information are directly spliced into a vector with the dimension of 5 x n x m as the total characteristic vector. Then, the expected sample labels and the total sample vectors are input into the convolutional neural network as training data to be trained, and various parameters of the convolutional neural network can be configured according to experience in the process. In the training process, the output value of the convolutional neural network is compared with the expected sample label, and when the difference value of the output value and the expected sample label is smaller than or equal to a preset threshold value, the convolutional neural network at the moment can be determined as a qualified geo-fence identification model. The total feature vector of the sample image based on the peripheral road network information and the population thermodynamic information can give more accurate indicativity in the process of establishing the geo-fence identification model, so that the output of the identification model is closer to the real geo-fence distribution state, and the accuracy of the identification model can be improved. The road is prevented from being divided into the geo-fences for the blind purpose, and therefore the accuracy of geo-fence identification can be remarkably improved.
Step 203: acquiring a test image to be identified, wherein the test image at least comprises: at least one target area, peripheral road network information of the target area and population thermodynamic information of the target area. See the description of step 101 in the above embodiments for details.
Step 204: and respectively extracting a first feature vector corresponding to the target area, a second feature vector corresponding to the peripheral road network information and a third feature vector corresponding to the population thermal information.
In this step, similar to the extraction method of the feature vector in step 202, the feature vector can also be used to represent the feature parameters of the test image; specifically, in an actual application scenario, it is assumed that an image specification of a target region in a test image is n × m pixels (n and m are positive integers, respectively), and RGB three channels. The image of the target region may be processed into a vector with dimensions 3 x n x m (n, m may take on integer values of 0-255, respectively), which is taken as the first feature vector. Since the geofence often uses the surrounding road network as the boundary, the surrounding road network information of the target area can be represented by using a black-and-white image of n × m, and then the binary feature vector of the image is extracted as the second feature vector, wherein the road is represented by using the black part. Demographic thermal information can be represented in 256-level gray scale images of n x m, where darker colors indicate greater population density. The population thermal image may be processed into a vector of n x m and taking values of 0-255 integer values as a third feature vector.
Step 205: and splicing the first feature vector, the second feature vector and the third feature vector to obtain feature parameters.
In this step, the vectors with the dimension of 3 × n × m and the integer values of 0 to 255, the vectors with the dimension of n × m and the binary vector, and the vectors with the dimension of n × m and the integer values of 0 to 255, which correspond to the target areas extracted in step 204, are directly spliced into one vector with the dimension of 5 × n × m as the characteristic parameter of the test image. In practical application, the geofence generally takes a peripheral road network of a target area or an edge of the target area as a geofence boundary, a population thermodynamic diagram can represent personnel distribution in the target area, and the edge of the population distribution is usually the edge of the target area, so that the geofence information of the test image is identified based on characteristic parameters of the peripheral road network information and the population thermodynamic information, more accurate indication can be given in the geofence identification process, roads are prevented from being divided into the geofence for blind purposes, and the accuracy of geofence identification can be further remarkably improved.
Step 206: and acquiring the geo-fence information in the test image by adopting a pre-configured geo-fence identification model according to the characteristic parameters. See step 103 of the above embodiments for a detailed description.
The geofence identification method provided in this embodiment includes obtaining a sample image including at least one sample area and sample geofence information thereof, sample peripheral road network information, and sample population thermodynamic information, training a convolutional neural network according to the sample image to obtain a geofence identification model, and then identifying a test image by using the identification model to obtain geofence information of the test image. The sample images all contain peripheral road network information and population thermodynamic information, so that more accurate indicativity can be given in the process of establishing the geo-fence identification model, roads are prevented from being divided into geo-fences in a blind manner, and the identification precision of the identification model is improved. And then can show the accuracy that promotes geofence discernment.
Fig. 3 is a block diagram illustrating a geo-fence identification device in accordance with an exemplary embodiment of the present invention.
As shown in fig. 3, the present embodiment provides a geo-fence identification apparatus, which may be integrated in a terminal, the apparatus including: a first acquisition module 301, an extraction module 302 and an identification module 303.
The first obtaining module 301 is configured to obtain a test image to be identified, where the test image at least includes: at least one target area, peripheral road network information of the target area and population thermodynamic information of the target area;
the extraction module 302 is used for extracting characteristic parameters of the test image according to the target area, the peripheral road network information and the population thermodynamic information;
the identification module 303 is configured to obtain the geofence information in the test image according to the characteristic parameters by using a preconfigured geofence identification model.
The details of the above modules are described in the embodiment corresponding to fig. 1.
Fig. 4 is a block diagram illustrating a geo-fence identification device in accordance with another exemplary embodiment of the present invention.
As shown in fig. 4, the geo-fence identification apparatus provided in this embodiment is based on the geo-fence identification apparatus shown in the exemplary embodiment shown in fig. 3, and further includes:
optionally, the extracting module 302 is specifically configured to: respectively extracting a first feature vector corresponding to a target area, a second feature vector corresponding to peripheral road network information and a third feature vector corresponding to population thermal information; and splicing the first feature vector, the second feature vector and the third feature vector to obtain feature parameters.
Optionally, the method further comprises: a second obtaining module 401, configured to obtain a sample image, where the sample image includes at least one sample area, sample geofence information of the sample area, sample peripheral road network information, and sample population thermodynamic information; a building module 402 for building a neural network-based geofence identification model from the sample images.
Optionally, the neural network is a convolutional neural network; the establishing module 402 is specifically configured to: extracting a feature vector corresponding to the sample geo-fence information as an expected sample label of the convolutional neural network; respectively extracting a first sample characteristic vector corresponding to the sample area, a second sample characteristic vector corresponding to the road network information around the sample, and a third sample characteristic vector corresponding to the thermodynamic information of the sample population; splicing the first sample characteristic vector, the second sample characteristic vector and the third sample characteristic vector to obtain a total sample vector; and inputting the expected sample labels and the total sample vectors as training data into a convolutional neural network for training to obtain a geo-fence identification model.
Optionally, the feature vector corresponding to the second sample feature vector and the sample geo-fence information is a binary vector.
The details of the above modules are described in the corresponding embodiment of fig. 2.
An embodiment of the present invention further provides a geo-fence recognition apparatus, including: a memory; a processor; and a computer program; wherein the computer program is stored in the memory and configured to execute the geo-fence identification method of the present invention as illustrated in fig. 1 for one exemplary embodiment or the geo-fence identification method of the present invention as illustrated in fig. 2 for another exemplary embodiment by the processor.
Fig. 5 is a block diagram illustrating a geo-fence identification device in accordance with an exemplary embodiment of the present invention.
As shown in fig. 5, the present embodiment provides a geo-fence identification apparatus, including: at least one processor 51 and a memory 52, in fig. 5, the processor 51 and the memory 52 are connected by a bus 50, the memory 52 stores instructions executable by the at least one processor 51, and the instructions are executed by the at least one processor 51 to cause the at least one processor 51 to perform the geo-fence recognition method of fig. 1 or fig. 2 as in the above embodiments.
The relevant description may be understood by referring to the relevant description and effect corresponding to the steps in fig. 1 to fig. 2, and redundant description is not repeated here.
An embodiment of the present invention further provides a computer-readable storage medium, including: a program which, when run on a computer, causes the computer to perform all or part of the process of the method of the corresponding embodiment of fig. 1 or 2 described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (12)
1. A geo-fence identification method, comprising:
acquiring a test image to be identified, wherein the test image at least comprises: at least one target area, peripheral road network information of the target area and population thermodynamic information of the target area;
extracting characteristic parameters of the test image according to the target area, the peripheral road network information and the population thermal information;
and acquiring the geo-fence information in the test image by adopting a pre-configured geo-fence identification model according to the characteristic parameters.
2. The method according to claim 1, wherein the extracting feature parameters of the test image according to the target area, the peripheral road network information, and the population thermal information specifically comprises:
respectively extracting a first feature vector corresponding to the target area, a second feature vector corresponding to the peripheral road network information and a third feature vector corresponding to the population thermal information;
and splicing the first feature vector, the second feature vector and the third feature vector to obtain the feature parameters.
3. The method according to claim 1 or 2, further comprising, before said acquiring a test image to be identified:
obtaining a sample image, wherein the sample image comprises at least one sample area, sample geo-fence information of the sample area, sample peripheral road network information and sample population thermodynamic information;
establishing the geo-fence identification model based on a neural network from the sample images.
4. The method of claim 3, wherein the neural network is a convolutional neural network; the establishing of the geo-fence identification model based on the neural network according to the sample image specifically includes:
extracting a feature vector corresponding to the sample geo-fence information as an expected sample label of the convolutional neural network;
respectively extracting a first sample characteristic vector corresponding to the sample area, a second sample characteristic vector corresponding to the sample peripheral road network information and a third sample characteristic vector corresponding to the sample population thermal information;
splicing the first sample characteristic vector, the second sample characteristic vector and the third sample characteristic vector to obtain a total sample vector;
and inputting the expected sample label and the total sample vector as training data into the convolutional neural network for training to obtain the geo-fence identification model.
5. The method of claim 4, wherein the second sample feature vector and the feature vector to which the sample geofence information corresponds are binary vectors.
6. A geo-fence identification device comprising:
a first obtaining module, configured to obtain a test image to be identified, where the test image at least includes: at least one target area, peripheral road network information of the target area and population thermodynamic information of the target area;
the extraction module is used for extracting the characteristic parameters of the test image according to the target area, the peripheral road network information and the population thermal information;
and the identification module is used for acquiring the geo-fence information in the test image by adopting a pre-configured geo-fence identification model according to the characteristic parameters.
7. The apparatus of claim 6, wherein the extraction module is specifically configured to:
respectively extracting a first feature vector corresponding to the target area, a second feature vector corresponding to the peripheral road network information and a third feature vector corresponding to the population thermal information;
and splicing the first feature vector, the second feature vector and the third feature vector to obtain the feature parameters.
8. The apparatus of claim 6 or 7, further comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a sample image, and the sample image comprises at least one sample area, sample geo-fence information of the sample area, sample peripheral road network information and sample population thermodynamic information;
and the establishing module is used for establishing the geo-fence identification model based on the neural network according to the sample image.
9. The apparatus of claim 8, wherein the neural network is a convolutional neural network; the establishing module is specifically configured to:
extracting a feature vector corresponding to the sample geo-fence information as an expected sample label of the convolutional neural network;
respectively extracting a first sample characteristic vector corresponding to the sample area, a second sample characteristic vector corresponding to the sample peripheral road network information and a third sample characteristic vector corresponding to the sample population thermal information;
splicing the first sample characteristic vector, the second sample characteristic vector and the third sample characteristic vector to obtain a total sample vector;
and inputting the expected sample label and the total sample vector as training data into the convolutional neural network for training to obtain the geo-fence identification model.
10. The apparatus of claim 9, wherein the second sample feature vector and the feature vector to which the sample geofence information corresponds are binary vectors.
11. A geo-fence identification device, comprising:
a memory; a processor; and a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor for the method of any one of claims 1 to 5.
12. A computer-readable storage medium, comprising: program which, when run on a computer, causes the computer to perform the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810717814.5A CN110674834A (en) | 2018-07-03 | 2018-07-03 | Geo-fence identification method, device, equipment and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810717814.5A CN110674834A (en) | 2018-07-03 | 2018-07-03 | Geo-fence identification method, device, equipment and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110674834A true CN110674834A (en) | 2020-01-10 |
Family
ID=69065382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810717814.5A Pending CN110674834A (en) | 2018-07-03 | 2018-07-03 | Geo-fence identification method, device, equipment and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110674834A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111681382A (en) * | 2020-05-28 | 2020-09-18 | 天津市三源电力设备制造有限公司 | Method for detecting temporary fence crossing in construction site based on visual analysis |
| CN111861257A (en) * | 2020-07-30 | 2020-10-30 | 北京恒华龙信数据科技有限公司 | Method and device for identifying hollow village based on power data thermodynamic diagram |
| CN114077978A (en) * | 2020-08-14 | 2022-02-22 | 北京三快在线科技有限公司 | Store arrival identification method and device, storage medium and electronic equipment |
| CN116030079A (en) * | 2023-03-29 | 2023-04-28 | 北京嘀嘀无限科技发展有限公司 | Geofence partitioning method, device, computer equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063509A (en) * | 2014-07-09 | 2014-09-24 | 武汉大学 | Information pushing system and method based on mobile geofence |
| CN105934650A (en) * | 2013-12-05 | 2016-09-07 | 电子湾有限公司 | A geo-fence system |
| US20170222962A1 (en) * | 2009-08-03 | 2017-08-03 | Picpocket, Inc. | Geofencing of obvious geographic locations and events |
| CN107423690A (en) * | 2017-06-26 | 2017-12-01 | 广东工业大学 | A kind of face identification method and device |
| CN107506738A (en) * | 2017-08-30 | 2017-12-22 | 深圳云天励飞技术有限公司 | Feature extracting method, image-recognizing method, device and electronic equipment |
| CN107978110A (en) * | 2017-12-06 | 2018-05-01 | 中国科学院上海技术物理研究所 | Fence intelligence identifying system in place and recognition methods based on images match |
| CN108038880A (en) * | 2017-12-20 | 2018-05-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for handling image |
-
2018
- 2018-07-03 CN CN201810717814.5A patent/CN110674834A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170222962A1 (en) * | 2009-08-03 | 2017-08-03 | Picpocket, Inc. | Geofencing of obvious geographic locations and events |
| CN105934650A (en) * | 2013-12-05 | 2016-09-07 | 电子湾有限公司 | A geo-fence system |
| CN104063509A (en) * | 2014-07-09 | 2014-09-24 | 武汉大学 | Information pushing system and method based on mobile geofence |
| CN107423690A (en) * | 2017-06-26 | 2017-12-01 | 广东工业大学 | A kind of face identification method and device |
| CN107506738A (en) * | 2017-08-30 | 2017-12-22 | 深圳云天励飞技术有限公司 | Feature extracting method, image-recognizing method, device and electronic equipment |
| CN107978110A (en) * | 2017-12-06 | 2018-05-01 | 中国科学院上海技术物理研究所 | Fence intelligence identifying system in place and recognition methods based on images match |
| CN108038880A (en) * | 2017-12-20 | 2018-05-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for handling image |
Non-Patent Citations (1)
| Title |
|---|
| 成凯: "基于移动终端传感器的室内地理围栏的研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111681382A (en) * | 2020-05-28 | 2020-09-18 | 天津市三源电力设备制造有限公司 | Method for detecting temporary fence crossing in construction site based on visual analysis |
| CN111861257A (en) * | 2020-07-30 | 2020-10-30 | 北京恒华龙信数据科技有限公司 | Method and device for identifying hollow village based on power data thermodynamic diagram |
| CN114077978A (en) * | 2020-08-14 | 2022-02-22 | 北京三快在线科技有限公司 | Store arrival identification method and device, storage medium and electronic equipment |
| CN116030079A (en) * | 2023-03-29 | 2023-04-28 | 北京嘀嘀无限科技发展有限公司 | Geofence partitioning method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110660066B (en) | Training method of network, image processing method, network, terminal equipment and medium | |
| CN108885698B (en) | Face recognition method and device and server | |
| CN110795976B (en) | Method, device and equipment for training object detection model | |
| US20230081645A1 (en) | Detecting forged facial images using frequency domain information and local correlation | |
| CN110674834A (en) | Geo-fence identification method, device, equipment and computer-readable storage medium | |
| CN109472264B (en) | Method and apparatus for generating an object detection model | |
| CN111444744A (en) | Living body detection method, living body detection device, and storage medium | |
| CN109116129B (en) | Terminal detection method, detection device, system and storage medium | |
| CN111553302B (en) | Key frame selection method, device, equipment and computer readable storage medium | |
| CN110599554A (en) | Method and device for identifying face skin color, storage medium and electronic device | |
| CN111445442B (en) | Crowd counting method and device based on neural network, server and storage medium | |
| CN110599514A (en) | Image segmentation method and device, electronic equipment and storage medium | |
| CN114005019A (en) | Method for identifying copied image and related equipment thereof | |
| US20240119714A1 (en) | Image recognition model training method and apparatus | |
| CN111898544B (en) | Text image matching method, device and equipment and computer storage medium | |
| CN116363538B (en) | Bridge detection method and system based on unmanned aerial vehicle | |
| CN115223022B (en) | Image processing method, device, storage medium and equipment | |
| CN116958582A (en) | Data processing method and related device | |
| CN113569771B (en) | Video analysis method and device, electronic equipment and storage medium | |
| CN115115552A (en) | Image correction model training method, image correction device and computer equipment | |
| CN110827243B (en) | Method and device for detecting abnormity of coverage area of grid beam | |
| CN109583453B (en) | Image identification method and device, data identification method and terminal | |
| CN111339459A (en) | Information processing method, server, terminal and computer storage medium | |
| CN116778534B (en) | Image processing method, device, equipment and medium | |
| CN113052827B (en) | Crowd counting method and system based on multi-branch expansion convolutional neural network |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200110 |