CN112989100B - Indoor positioning method and device based on image fingerprint - Google Patents
Indoor positioning method and device based on image fingerprint Download PDFInfo
- Publication number
- CN112989100B CN112989100B CN201911296673.5A CN201911296673A CN112989100B CN 112989100 B CN112989100 B CN 112989100B CN 201911296673 A CN201911296673 A CN 201911296673A CN 112989100 B CN112989100 B CN 112989100B
- Authority
- CN
- China
- Prior art keywords
- image
- pyramid
- matching degree
- level
- fingerprint
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/587—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses an indoor positioning method and device based on image fingerprints. Wherein the method comprises the following steps: acquiring a first position image uploaded by a client, and establishing a first image pyramid based on the first position image; calculating the image matching degree between each image in the first image pyramid and the image of the corresponding level of the second image pyramid in the pre-constructed image fingerprint library layer by layer from the topmost layer, wherein the image matching degree obtained by calculation of each layer is used for screening the second image pyramid of the next layer participating in the image matching degree calculation, and generating the final image matching degree corresponding to the bottommost layer of the first image pyramid; and determining a second image pyramid matched with the first image pyramid according to the generated final image matching degree, and determining the position of a fingerprint point with an association relation with the matched second image pyramid as the indoor position of the user, so that accurate indoor positioning can be realized, the accuracy of indoor positioning is improved, the cost is low, and the applicability is wider.
Description
Technical Field
The invention relates to the technical field of communication, in particular to an indoor positioning method and device based on image fingerprints.
Background
With rapid transition in the age, the scientific technology rapidly develops, the information service quality efficiency is improved, and the demands of people for positioning are increasing; the indoor position positioning can not be realized through satellite positioning under the indoor environment because no satellite signal exists, and meanwhile, under the complex environment, the positioning demands of places such as libraries, shops, hospitals, gymnasiums, underground garages, goods warehouses and the like on personnel and articles are increasing.
The existing indoor positioning technology is divided into a neighbor method and a trilateral (angular) measurement method from the implementation scheme, and the specific method is as follows:
neighbor method: directly selecting the position of the AP with the maximum signal strength, wherein the positioning result is the position of the currently connected AP stored in a hot spot position database;
trilateral (angular) measurement: and obtaining the distance or angle between the target and the AP through various parameters of the signals, and calculating the position by using a geometric method. Including time of arrival methods, relative time of arrival methods, angle of arrival methods, ranging methods based on signal strength, and hybrid algorithms thereof.
However, the existing indoor positioning method has certain defects, which are mainly expressed in that:
1. the neighbor method is simple and quick to realize, but the positioning precision is not guaranteed, the beacon deployment density is depended, the cost is high, and the precision is poor.
2. Trilateral (angular) measurement methods have higher theoretical accuracy, but have various limitations, so that the positioning accuracy in the actual process cannot be ensured, and specific reasons are as follows: 1. for common equipment, the parameters such as time and angle are difficult to obtain; 2. the indoor environment is complex, refraction, scattering and other conditions caused by shielding of obstacles, walls and the like exist in the signal propagation process, meanwhile, the multipath effect of the signal can greatly reduce the accuracy of distance and angle measurement, and the calculation precision cannot be guaranteed; 3. trilateration requires accurate location of beacons, and in some scenarios there may be errors in the positioning results if the accurate location of beacons is not available.
Disclosure of Invention
In view of the foregoing, embodiments of the present invention are directed to providing an indoor positioning method and apparatus based on image fingerprint that overcomes or at least partially solves the foregoing problems.
According to an aspect of the embodiment of the present invention, there is provided an indoor positioning method based on image fingerprint, including:
acquiring a first position image uploaded by a client, and establishing a first image pyramid based on the first position image;
calculating the image matching degree between each image in the first image pyramid and the image of the corresponding level of the second image pyramid in the pre-constructed image fingerprint library layer by layer from the topmost layer, wherein the image matching degree obtained by calculation of each layer is used for screening the second image pyramid of the next layer participating in the image matching degree calculation, and generating the final image matching degree corresponding to the bottommost layer of the first image pyramid;
and determining a second image pyramid matched with the first image pyramid according to the generated final image matching degree, and determining the position of a fingerprint point with an association relation with the matched second image pyramid as the indoor position of the user.
According to another aspect of the embodiment of the present invention, there is provided an indoor positioning device based on image fingerprint, including:
the building module is suitable for obtaining a first position image uploaded by the client and building a first image pyramid based on the first position image;
the computing module is suitable for computing the image matching degree between each image in the first image pyramid and the image of the corresponding level of the second image pyramid in the pre-built image fingerprint library layer by layer from the topmost layer, wherein the image matching degree obtained by computing each layer is used for screening the second image pyramid of the next layer participating in the image matching degree computation, and generating the final image matching degree corresponding to the bottommost layer of the first image pyramid;
and the determining module is suitable for determining a second image pyramid matched with the first image pyramid according to the generated final image matching degree, and determining the position of a fingerprint point with an association relationship with the matched second image pyramid as the indoor position of the user.
According to yet another aspect of an embodiment of the present invention, there is provided a computing device including: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface are communicated with each other through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the indoor positioning method based on the image fingerprint.
According to still another aspect of the embodiments of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to perform operations corresponding to the image fingerprint-based indoor positioning method described above.
According to the scheme provided by the invention, accurate indoor positioning can be realized, the accuracy of indoor positioning is improved, and compared with the traditional mode of realizing indoor positioning through Bluetooth, WIFI and other technologies, the indoor positioning method and device are free from deployment of any equipment, low in cost and better in applicability.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and may be implemented according to the content of the specification, so that the technical means of the embodiments of the present invention can be more clearly understood, and the following specific implementation of the embodiments of the present invention will be more apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 shows a flowchart of an indoor positioning method based on image fingerprints provided by an embodiment of the invention;
FIG. 2A is a flowchart of an indoor positioning method based on image fingerprint according to another embodiment of the present invention;
FIG. 2B is a schematic view of an image pyramid;
fig. 3 is a schematic structural diagram of an indoor positioning device based on image fingerprints according to an embodiment of the present invention;
FIG. 4 illustrates a schematic diagram of a computing device provided by an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 shows a flowchart of an indoor positioning method based on image fingerprints according to an embodiment of the present invention. As shown in fig. 1, the method comprises the steps of:
step S101, a first position image uploaded by a client is obtained, and a first image pyramid is built based on the first position image.
Specifically, when the user enters an indoor location, for example, a mall, a library, a hospital, a gym, an underground garage, or the like, there may be a need for indoor positioning, at this time, the user may collect a first position image of a current position using a camera, upload the collected first position image to a server, the server obtains the first position image uploaded by the client, and then establish a first image pyramid based on the obtained first position image. Wherein the first image pyramid is a series of image sets with progressively lower resolutions arranged in pyramid shapes and derived from the same first position image.
Step S102, starting from the topmost layer, calculating the image matching degree between each image in the first image pyramid and the image of the corresponding level of the second image pyramid in the pre-built image fingerprint library layer by layer, wherein the image matching degree obtained by calculation of each layer is used for screening the second image pyramid of the next layer participating in the image matching degree calculation, and generating the final image matching degree corresponding to the bottommost layer of the first image pyramid.
In this embodiment, an image fingerprint library is pre-constructed, where the image fingerprint library stores locations where indoor locations can be used as fingerprint points and corresponding second image pyramids in association.
After the first image pyramid is built, calculating the image matching degree between each image in the first image pyramid and the image of the corresponding level of the second image pyramid in the pre-built image fingerprint library layer by layer from the top layer to the bottom layer, namely calculating the image matching degree between the image in the first image pyramid and the image in the second image pyramid under the same level, wherein the image matching degree obtained by calculation of each layer is used for screening the second image pyramid of the next layer participating in the image matching degree calculation, generating the final image matching degree corresponding to the bottom layer of the first image pyramid, and further improving the indoor positioning efficiency by screening the second image pyramid participating in the image matching degree calculation so as to reduce the indoor positioning efficiency.
Step S103, determining a second image pyramid matched with the first image pyramid according to the generated final image matching degree, and determining the position of a fingerprint point with an association relationship with the matched second image pyramid as the indoor position of the user.
After the final image matching degree corresponding to the bottommost layer of the first image pyramid is generated, the indoor position of the user can be determined based on the final image matching degree, specifically, a second image pyramid matched with the first image pyramid is determined according to the generated final image matching degree, for example, the second image pyramid corresponding to the highest final image matching degree is determined as the second image pyramid matched with the first image pyramid, then, the position of the fingerprint point having the association relationship with the second image pyramid is determined, and the position is determined as the indoor position of the user. The fingerprint points are the position points used as indoor positioning references.
According to the scheme provided by the invention, accurate indoor positioning can be realized, the accuracy of indoor positioning is improved, and compared with the traditional mode of realizing indoor positioning through Bluetooth, WIFI and other technologies, the indoor positioning method and device are free from deployment of any equipment, low in cost and better in applicability.
Fig. 2A is a flowchart of an indoor positioning method based on image fingerprint according to another embodiment of the present invention. As shown in fig. 2A, the method includes the steps of:
step S201, a first position image uploaded by a client is obtained, the first position image is used as a 0 th-level image, N-1-level dimension reduction processing is carried out on the first position image, and a first image pyramid with N levels is obtained.
Specifically, when the user enters an indoor location, such as a mall, a library, a hospital, a gym, an underground garage, or the like, there may be a need for indoor positioning, at this time, the user may collect a first position image of a current position using a camera, upload the collected first position image to a server, the server obtains the first position image uploaded by the client, and then the server establishes a first image pyramid based on the obtained first position image.
The first image pyramid is generated by using an average smoothing filter, wherein the working principle of the average smoothing filter is as follows: and (3) carrying out average processing on the image by a grid by grid in 2X 2 dimensions, solving the average value of gray values of 4 pixels, and sampling the gray values into 1 pixel, thereby obtaining an image with half reduced resolution and dimension. Considering the relationship between the number of image pyramid layers and the matching speed and accuracy, it is preferable to create a 4-layer image pyramid, as shown in fig. 2B.
The method comprises the steps that a first position image uploaded by a client is located and acquired and is an MxN-dimensional image, the first position image is located to be a 0-th-level image, and dimension reduction processing is carried out on the first position image once to obtain an (M/2) -x (N/2) -level 1 image; and performing dimension reduction on the 1-level image again to obtain a (M/4) 2-level image (N/4), and the like to obtain a (M/8) 3-level image (N/8). The 4-level image is a set of image pyramids with resolution from high to low and dimension from large to small. Wherein, the image pixel gray value and the image rank coordinate of each image in the image pyramid can be calculated according to the following method:
wherein:the X-coordinate of the image of the nth level;
the Y coordinate of the image of the nth level;
the coordinates of the nth level are->Gray scale values of the image of (a).
The n-1 th level has the coordinates +.>Gray scale values of the image of (a).
After the first image pyramid is built, calculating the image matching degree between each image in the first image pyramid and the image of the corresponding level of the second image pyramid in the pre-built image fingerprint library layer by layer from the top layer, wherein the image matching degree obtained by calculation of each layer is used for screening the second image pyramid of the next layer participating in the calculation of the image matching degree, and generating the final image matching degree corresponding to the bottom layer of the first image pyramid, wherein when the image matching degree is calculated, a mean value removing normalization product correlation algorithm (Mean Normalized product correlation, MNPRD) can be used for calculating, and the algorithm is specifically as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,for the corresponding level of image S in the second image pyramid in the image fingerprint library u,v Gray mean value of>Is the gray-scale average of the image T of the corresponding level in the first image pyramid. When the image T and the image S u,v When matching, and no error occurs, theoretically R (u, v) has a maximum of 1 when image T and image S u,v When there is no match, R (u, v) is smaller; wherein, the larger R (u, v), the greater the similarity between the two graphs.
Specifically, the image matching degree can be calculated by the method in step S202 to step S204:
step S202, calculating the image matching degree between the N-1 level image in the first image pyramid and the image of the corresponding level of the second image pyramid in the pre-constructed image fingerprint library, screening the second image pyramid based on the calculated image matching degree, and taking the screened second image pyramid as a calculation object of the N-2 level image matching degree.
In this step, for the N-1 th level image in the first image pyramid, the image matching degree between the N-1 th level image in the first image pyramid and the N-1 th level image of any second image pyramid in the pre-built image fingerprint library is calculated respectively, specifically, the image matching degree is calculated by using a mean-removing normalization product correlation algorithm, then, the calculated image matching degrees are sorted in a descending order, a certain number of second image pyramids, for example, 10 second image pyramids are sorted according to the sorting result, wherein the sorted second image pyramids are used as calculation objects of the N-2 th level image matching degree, that is, the image matching degree between the N-2 th level image in the first image pyramid and the N-2 th level image in the sorted second image pyramid is calculated when the N-2 th level image matching degree is calculated.
The method for constructing the image fingerprint library is as follows: acquiring position information of fingerprint points uploaded by a client and corresponding second position images; taking the second position image as a 0 th-level image, and performing N-1 level dimension reduction on the second position image to obtain a second image pyramid with N levels; and establishing an association relation between the positions of the second image pyramid and the fingerprint points to obtain an image fingerprint library.
Loading an indoor map on a client, clicking fingerprint points on the map, acquiring longitude and latitude information of the fingerprint points, calling a camera to shoot a second position image according to the north, northeast, east, southeast, southwest, west and northwest directions, uploading the position information of the fingerprint points and the corresponding second position image to a server, and acquiring the position information of the fingerprint points and the corresponding second position image uploaded by the client by the server. Wherein the location information of the fingerprint points includes one or more of the following information: fingerprint point number, longitude information, latitude information, location image number, location image orientation, as shown in table 1:
table 1:
in order to improve the matching efficiency, a second image pyramid needs to be constructed for the second position image corresponding to each fingerprint point, and specifically, the second image pyramid can be generated by using an average smoothing filter, where the working principle of the average smoothing filter is as follows: and (3) carrying out average processing on the image by a grid by grid in 2X 2 dimensions, solving the average value of gray values of 4 pixels, and sampling the gray values into 1 pixel, thereby obtaining an image with half reduced resolution and dimension. The relationship between the number of layers of the image pyramid and the matching speed and precision is comprehensively considered, and the 4-layer image pyramid is preferably established.
The second position image uploaded by the client is positioned and acquired as an MxN dimension image, the second position image is positioned as a 0 th level image, and the second position image is subjected to one-time dimension reduction processing to obtain a 1 level image of (M/2) ×N/2; and performing dimension reduction on the 1-level image again to obtain a (M/4) 2-level image (N/4), and the like to obtain a (M/8) 3-level image (N/8). The 4-level image is a set of image pyramids with resolution from high to low and dimension from large to small. Wherein, the image pixel gray value and the image rank coordinate of each image in the image pyramid can be calculated according to the following method:
wherein:the X-coordinate of the image of the nth level;
the Y coordinate of the image of the nth level;
the coordinates of the nth level are->Gray scale values of the image of (a).
The n-1 th level has the coordinates +.>Gray scale values of the image of (a).
And processing each second position image as above to obtain a plurality of second image pyramids, and then associating the obtained second image pyramids with the positions of the fingerprint points to generate an image fingerprint library.
In addition, the distance between any two fingerprint points can be calculated based on the position information of the fingerprint points, and a fingerprint point distance table can be generated. The fingerprint point distance table records the mapping relation between the distance and the weight.
Step S203, from the N-2 level to the 1 level, calculating the image matching degree between the image and the image of the corresponding level of the screened second image pyramid for each level of image in the first image pyramid, screening the second image pyramid based on the calculated image matching degree, and taking the screened second image pyramid as the calculation object of the image matching degree of the next level.
In this step, from the N-2 th level to the 1 st level, calculating, for each level of image in the first image pyramid, an image matching degree between the image and the image of the corresponding level of the screened second image pyramid, for example, for the N-2 th level, calculating an image matching degree between the N-2 th level image in the first image pyramid and the N-2 th level image in the screened second image pyramid by using a de-averaging normalization product correlation algorithm; for the 1 st level, calculating the image matching degree between the 1 st level image in the first image pyramid and the 1 st level image in the screened second image pyramid by using a mean value removal normalized product correlation algorithm, after calculating the image matching degree of each level, sorting the calculated image matching degrees in a descending order, and screening a certain number of second image pyramids, for example, 5 or 3 second image pyramids according to the sorting result. Wherein the number of second image pyramids screened at a time may be in a decreasing trend.
Step S204, for the 0 th level image in the first image pyramid, calculating the image matching degree between the image and the image of the corresponding level of the screened second image pyramid.
And calculating the image matching degree between the 0 th-level image of the first image pyramid and the 0 th-level image of the screened second image pyramid by using a mean-removing normalization product correlation algorithm.
The following describes the image matching degree calculation process using a 4-layer image pyramid as an example:
and step 1, calculating the image matching degree between the 3 rd-level image of the first image pyramid and the 3 rd-level images of all the second image pyramids in the image fingerprint library by using a mean value removal normalization product correlation algorithm.
And 2, sorting the image matching degree of the level 3 in a descending order.
And step 3, acquiring a second image pyramid with the image matching degree of which is ranked at the top 10.
And 4, calculating the image matching degree between the 2 nd-level image of the first image pyramid and the 2 nd-level image of the second image pyramid with the rank of 10 by using a mean value removal normalization product correlation algorithm.
And 5, sorting the image matching degree of the level 2 in a descending order.
And 6, acquiring a second image pyramid with the image matching degree ranked 5 at the front.
And 7, calculating the image matching degree between the 1 st-level image of the first image pyramid and the 1 st-level image of the second image pyramid with the rank of 5 by using a mean value removal normalization product correlation algorithm.
And 8, sorting the image matching degree of the level 1 in a descending order.
And 9, acquiring a second image pyramid with the image matching degree of the top 3.
And step 10, calculating the image matching degree between the 0 th-level image of the first image pyramid and the 0 th-level image of the second image pyramid with the rank of 3 by using a mean value removal normalization product correlation algorithm.
Alternatively, the indoor position of the user may be determined based on the image matching degree of level 0, for example, the image matching degree of level 0 is sorted in a descending order, the second image pyramid corresponding to the highest image matching degree is determined as the second image pyramid matched with the first image pyramid, then the position of the fingerprint point having the association relationship with the second image pyramid is determined, and the position is determined as the indoor position of the user.
In order to determine the indoor position of the user more accurately, the present embodiment may also perform position calibration based on the historical indoor position of the user, specifically, the methods in steps S205-S208 may be utilized:
step S205, a user history indoor position is acquired.
The user's user history indoor location is obtained, where the last located user history indoor location can be obtained.
Step S206, calculating the distance between the position of the fingerprint point which has the association relation with the second image pyramid participating in the 0 th-level image matching degree calculation of the first image pyramid and the indoor position of the user history.
In connection with the above illustration, it is considered that there are 3 second image pyramids participating in the 0 th level image matching degree calculation of the first image pyramid, the positions of fingerprint points having an association relationship with the 3 second image pyramids are determined first, and then the distances between the positions of the 3 fingerprint points and the indoor positions of the user history are calculated, wherein the longitude and latitude information of each position can be determined, and therefore, the distances between the positions of the 3 fingerprint points and the indoor positions of the user history can be calculated based on the longitude and latitude information. Here 3 distances are calculated.
Step S207, inquiring a pre-generated fingerprint point distance table to obtain weights corresponding to the distances.
The fingerprint point distance table is generated in advance, the fingerprint point distance table records the mapping relation between the distances and the weights, as shown in table 2, the calculated distances are used for inquiring the fingerprint point distance table, the weights corresponding to 3 distances can be obtained, for example, the 3 distances are respectively: 2. 4, 6, then the corresponding weights can be determined to be 1.0, 1.1, 1.2, respectively.
Table 2:
step S208, weighting calculation is carried out on the matching degree of the weight and the 0 th-level image, the weighting calculation results are ordered, a second image pyramid matched with the first image pyramid is determined according to the ordering results, and the position of a fingerprint point with an association relation with the matched second image pyramid is determined as the indoor position of the user.
After the weight is determined, weighting calculation is performed on the matching degree of the weight and the 0 th-level image, for example, the product of the matching degree of the 0 th-level image and the corresponding weight is calculated, the weighted calculation results are ordered, for example, descending order is performed, a second image pyramid with the highest weighted calculation result is determined and used as a second image pyramid matched with the first image pyramid, the position of a fingerprint point with an association relation with the matched second image pyramid is determined as the indoor position of the user, and therefore indoor positioning is completed.
According to the scheme provided by the invention, the image matching degree is calculated layer by layer, the second image pyramid is screened based on the image matching degree, the indoor positioning efficiency is improved, the indoor positioning is performed in combination with the historical indoor position of the user, the positioning accuracy is further improved, and compared with the traditional mode of realizing indoor positioning through Bluetooth, WIFI and other technologies, the indoor positioning method has the advantages that no equipment is required to be deployed, the cost is low, no external data source is required to assist, the indoor positioning experience can be realized through a mobile phone with a camera, and the indoor positioning method has wide applicability.
Fig. 3 is a schematic structural diagram of an indoor positioning device based on image fingerprints according to an embodiment of the present invention. As shown in fig. 3, the apparatus includes: a building module 301, a calculating module 302, a determining module 303.
The establishing module 301 is adapted to acquire a first location image uploaded by the client, and establish a first image pyramid based on the first location image;
the computing module 302 is adapted to compute, layer by layer, an image matching degree between each image in the first image pyramid and an image of a corresponding level of the second image pyramid in the pre-built image fingerprint library from the topmost layer, wherein the image matching degree obtained by each layer computation is used for screening the second image pyramid of the next layer participating in the image matching degree computation, and generating a final image matching degree corresponding to the bottommost layer of the first image pyramid;
the determining module 303 is adapted to determine a second image pyramid matching the first image pyramid according to the generated final image matching degree, and determine the position of the fingerprint point having an association relationship with the matched second image pyramid as the indoor position of the user.
Optionally, the first image pyramid has N levels, where N levels are respectively from 0 level to N-1 level from the bottommost level to the topmost level;
the computing module is further adapted to: aiming at the N-1 level image in the first image pyramid, calculating the image matching degree between the image and the image of the corresponding level of the second image pyramid in the pre-constructed image fingerprint library, screening the second image pyramid based on the calculated image matching degree, and taking the screened second image pyramid as a calculation object of the N-2 level image matching degree;
calculating the image matching degree between each level of image in the first image pyramid and the image of the corresponding level of the screened second image pyramid from the N-2 level to the 1 level, screening the second image pyramid based on the calculated image matching degree, and taking the screened second image pyramid as a calculation object of the image matching degree of the next level;
aiming at the 0 th level image in the first image pyramid, calculating the image matching degree between the image and the image of the corresponding level of the screened second image pyramid;
the determination module is further adapted to: and sequencing the image matching degree corresponding to the 0 th level, and determining a second image pyramid matched with the first image pyramid according to the sequencing result.
Optionally, the determination module is further adapted to: acquiring a user history indoor position;
calculating the distance between the position of the fingerprint point with the association relation with the second image pyramid which participates in the final image matching degree calculation corresponding to the bottommost layer of the first image pyramid and the indoor position of the user history;
inquiring a pre-generated fingerprint point distance table to obtain weights corresponding to the distances;
and carrying out weighted calculation on the weight and the final image matching degree, sequencing the weighted calculation results, and determining a second image pyramid matched with the first image pyramid according to the sequencing results.
Optionally, the setup module is further adapted to: and taking the first position image as a 0 th-level image, and performing N-1-level dimension reduction processing on the first position image to obtain a first image pyramid with N levels.
Optionally, the apparatus further comprises: the image fingerprint library construction module is suitable for acquiring the position information of the fingerprint points uploaded by the client and the corresponding second position images;
taking the second position image as a 0 th-level image, and performing N-1 level dimension reduction on the second position image to obtain a second image pyramid with N levels;
and establishing an association relation between the positions of the second image pyramid and the fingerprint points to obtain an image fingerprint library.
Optionally, the apparatus further comprises: and the fingerprint point distance table generating module is suitable for calculating the distance between any two fingerprint points based on the position information of the fingerprint points and generating a fingerprint point distance table.
Optionally, the location information of the fingerprint points includes one or more of the following information: fingerprint point number, longitude information, latitude information, location image number, location image orientation.
According to the scheme provided by the invention, accurate indoor positioning can be realized, the accuracy of indoor positioning is improved, and compared with the traditional mode of realizing indoor positioning through Bluetooth, WIFI and other technologies, the indoor positioning method and device are free from deployment of any equipment, low in cost and better in applicability.
The embodiment of the invention provides a non-volatile computer storage medium, which stores at least one executable instruction, and the computer executable instruction can execute the indoor positioning method based on image fingerprints in any of the method embodiments.
FIG. 4 illustrates a schematic diagram of a computing device according to an embodiment of the present invention, and the embodiment of the present invention is not limited to a specific implementation of the computing device.
As shown in fig. 4, the computing device may include: a processor 402, a communication interface (Communications Interface) 404, a memory 406, and a communication bus 408.
Wherein: processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408. A communication interface 404 for communicating with network elements of other devices, such as clients or other servers. The processor 402 is configured to execute the program 410, and may specifically perform relevant steps in the image fingerprint based indoor positioning method embodiment for a computing device.
In particular, program 410 may include program code including computer-operating instructions.
The processor 402 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included by the computing device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
Memory 406 for storing programs 410. Memory 406 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
Program 410 may be specifically configured to cause processor 402 to perform the image fingerprint based indoor positioning method of any of the method embodiments described above. The specific implementation of each step in the procedure 410 may refer to corresponding descriptions in the corresponding steps and units in the indoor positioning embodiment based on image fingerprint, which are not described herein. It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus and modules described above may refer to corresponding procedure descriptions in the foregoing method embodiments, which are not repeated herein.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It will be appreciated that the teachings of embodiments of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the embodiments of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention 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 above description of exemplary embodiments of the invention, various features of the embodiments of the invention 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 construed as reflecting the intention that: i.e., an embodiment of the invention that is claimed, requires 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 this invention.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. 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. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units 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.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components according to embodiments of the present invention may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). Embodiments of the present invention may also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the embodiments of the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, 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 invention 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 use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specifically stated.
Claims (8)
1. An indoor positioning method based on image fingerprints comprises the following steps:
acquiring a first position image uploaded by a client, and establishing a first image pyramid based on the first position image;
calculating the image matching degree between each image in the first image pyramid and the image of the corresponding level of the second image pyramid in the pre-constructed image fingerprint library layer by layer from the topmost layer, wherein the image matching degree obtained by calculation of each layer is used for screening the second image pyramid of the next layer participating in the image matching degree calculation, and generating the final image matching degree corresponding to the bottommost layer of the first image pyramid; the method for constructing the image fingerprint library comprises the following steps: acquiring position information of fingerprint points uploaded by a client and corresponding second position images; taking the second position image as a 0 th-level image, and performing N-1-level dimension reduction on the second position image to obtain a second image pyramid with N levels; establishing an association relation between the positions of the second image pyramid and the fingerprint points to obtain an image fingerprint library;
acquiring a user history indoor position; calculating the distance between the position of the fingerprint point with the association relation with the second image pyramid which participates in the final image matching degree calculation corresponding to the bottommost layer of the first image pyramid and the indoor position of the user history; inquiring a pre-generated fingerprint point distance table to obtain weights corresponding to the distances; and carrying out weighted calculation on the weight and the final image matching degree, sequencing the weighted calculation results, determining a second image pyramid matched with the first image pyramid according to the sequencing result, and determining the position of a fingerprint point with an association relationship with the matched second image pyramid as the indoor position of the user.
2. The method of claim 1, wherein the first image pyramid has N levels, from bottom-most to top-most levels 0 to N-1, respectively;
calculating, layer by layer, an image matching degree between each image in the first image pyramid and an image of a corresponding level of the second image pyramid in the pre-built image fingerprint library from the topmost layer, wherein the image matching degree obtained by calculation of each layer is used for screening the second image pyramid of the next layer participating in the image matching degree calculation, and generating a final image matching degree corresponding to the bottommost layer of the first image pyramid further comprises:
aiming at the N-1 level image in the first image pyramid, calculating the image matching degree between the image and the image of the corresponding level of the second image pyramid in the pre-constructed image fingerprint library, screening the second image pyramid based on the calculated image matching degree, and taking the screened second image pyramid as a calculation object of the N-2 level image matching degree;
calculating the image matching degree between each level of image in the first image pyramid and the image of the corresponding level of the screened second image pyramid from the N-2 level to the 1 level, screening the second image pyramid based on the calculated image matching degree, and taking the screened second image pyramid as a calculation object of the image matching degree of the next level;
and aiming at the 0 th-level image in the first image pyramid, calculating the image matching degree between the image and the image of the corresponding level of the screened second image pyramid.
3. The method of claim 1 or 2, wherein the establishing a first image pyramid based on the first location image further comprises:
and taking the first position image as a 0 th-level image, and performing N-1-level dimension reduction processing on the first position image to obtain a first image pyramid with N levels.
4. The method according to claim 1 or 2, wherein the method further comprises:
and calculating the distance between any two fingerprint points based on the position information of the fingerprint points, and generating a fingerprint point distance table.
5. The method of claim 1 or 2, wherein the location information of the fingerprint points includes one or more of the following information: fingerprint point number, longitude information, latitude information, location image number, location image orientation.
6. An indoor positioning device based on image fingerprint, comprising:
the building module is suitable for obtaining a first position image uploaded by the client and building a first image pyramid based on the first position image;
the computing module is suitable for computing the image matching degree between each image in the first image pyramid and the image of the corresponding level of the second image pyramid in the pre-built image fingerprint library layer by layer from the topmost layer, wherein the image matching degree obtained by computing each layer is used for screening the second image pyramid of the next layer participating in the image matching degree computation, and generating the final image matching degree corresponding to the bottommost layer of the first image pyramid; the method for constructing the image fingerprint library comprises the following steps: acquiring position information of fingerprint points uploaded by a client and corresponding second position images; taking the second position image as a 0 th-level image, and performing N-1-level dimension reduction on the second position image to obtain a second image pyramid with N levels; establishing an association relation between the positions of the second image pyramid and the fingerprint points to obtain an image fingerprint library;
the determining module is suitable for acquiring the historical indoor position of the user; calculating the distance between the position of the fingerprint point with the association relation with the second image pyramid which participates in the final image matching degree calculation corresponding to the bottommost layer of the first image pyramid and the indoor position of the user history; inquiring a pre-generated fingerprint point distance table to obtain weights corresponding to the distances; and carrying out weighted calculation on the weight and the final image matching degree, sequencing the weighted calculation results, determining a second image pyramid matched with the first image pyramid according to the sequencing result, and determining the position of a fingerprint point with an association relationship with the matched second image pyramid as the indoor position of the user.
7. A computing device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform operations corresponding to the image fingerprint based indoor positioning method according to any one of claims 1-5.
8. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the image fingerprint based indoor positioning method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911296673.5A CN112989100B (en) | 2019-12-16 | 2019-12-16 | Indoor positioning method and device based on image fingerprint |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911296673.5A CN112989100B (en) | 2019-12-16 | 2019-12-16 | Indoor positioning method and device based on image fingerprint |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112989100A CN112989100A (en) | 2021-06-18 |
| CN112989100B true CN112989100B (en) | 2023-07-18 |
Family
ID=76343509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911296673.5A Active CN112989100B (en) | 2019-12-16 | 2019-12-16 | Indoor positioning method and device based on image fingerprint |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112989100B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009148411A1 (en) * | 2008-06-06 | 2009-12-10 | Agency For Science, Technology And Research | Method and system for maintaining a database of reference images |
| CN104462199A (en) * | 2014-10-31 | 2015-03-25 | 中国科学院自动化研究所 | Near-duplicate image search method in network environment |
| CN107248174A (en) * | 2017-05-15 | 2017-10-13 | 西安电子科技大学 | A kind of method for tracking target based on TLD algorithms |
| CN108573269A (en) * | 2017-10-24 | 2018-09-25 | 北京金山云网络技术有限公司 | Image characteristic point matching method, coalignment, electronic equipment and storage medium |
| CN108650625A (en) * | 2018-05-17 | 2018-10-12 | 重庆邮电大学 | Distributing antenna system localization method based on fast run-up library |
| CN109919190A (en) * | 2019-01-29 | 2019-06-21 | 广州视源电子科技股份有限公司 | Algorism of Matching Line Segments method, apparatus, storage medium and terminal |
-
2019
- 2019-12-16 CN CN201911296673.5A patent/CN112989100B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009148411A1 (en) * | 2008-06-06 | 2009-12-10 | Agency For Science, Technology And Research | Method and system for maintaining a database of reference images |
| CN104462199A (en) * | 2014-10-31 | 2015-03-25 | 中国科学院自动化研究所 | Near-duplicate image search method in network environment |
| CN107248174A (en) * | 2017-05-15 | 2017-10-13 | 西安电子科技大学 | A kind of method for tracking target based on TLD algorithms |
| CN108573269A (en) * | 2017-10-24 | 2018-09-25 | 北京金山云网络技术有限公司 | Image characteristic point matching method, coalignment, electronic equipment and storage medium |
| CN108650625A (en) * | 2018-05-17 | 2018-10-12 | 重庆邮电大学 | Distributing antenna system localization method based on fast run-up library |
| CN109919190A (en) * | 2019-01-29 | 2019-06-21 | 广州视源电子科技股份有限公司 | Algorism of Matching Line Segments method, apparatus, storage medium and terminal |
Non-Patent Citations (1)
| Title |
|---|
| 基于Android平台的WiFi定位系统的研究与设计;高峰;《中国优秀硕士学位论文全文数据库信息科技辑》;I136-1083 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112989100A (en) | 2021-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107782322B (en) | Indoor positioning method and system and indoor map establishing device thereof | |
| US20180372852A1 (en) | Method and apparatus for calibration between laser radar and camera, device and storage medium | |
| CN108628904B (en) | Path coding method, similar path searching method, similar path coding device, similar path searching device and electronic equipment | |
| JP6676082B2 (en) | Indoor positioning method and system, and device for creating the indoor map | |
| CN110838125B (en) | Target detection method, device, equipment and storage medium for medical image | |
| CN108875537B (en) | Object detection method, device and system and storage medium | |
| CN108876804B (en) | Matting model training and image matting method, device and system and storage medium | |
| CN111091417B (en) | Site selection method and device | |
| US20170219370A1 (en) | Landmark Identification from Point Cloud Generated from Geographic Imagery Data | |
| CN106529538A (en) | Method and device for positioning aircraft | |
| CN107851196B (en) | Image pattern matching method and device | |
| CN111652054B (en) | Joint point detection method, gesture recognition method and device | |
| US20130328931A1 (en) | System and Method for Mobile Identification of Real Property by Geospatial Analysis | |
| CN113589306B (en) | Positioning method, positioning device, electronic equipment and storage medium | |
| WO2015165071A1 (en) | Identifying entities to be investigated using storefront recognition | |
| CN111880144B (en) | Positioning method, device, equipment and storage medium | |
| KR20120112293A (en) | Apparatus and method for detecting position of moving unit | |
| CN112362059B (en) | Positioning method and device for mobile carrier, computer equipment and medium | |
| CN110057355B (en) | Indoor positioning method, device and system and computing equipment | |
| CN112989100B (en) | Indoor positioning method and device based on image fingerprint | |
| CN115457202B (en) | Method, device and storage medium for updating three-dimensional model | |
| CN110288646A (en) | A kind of human dimension calculation method and device based on image | |
| CN110636439A (en) | Position acquisition method and device | |
| CN115393423A (en) | Target detection method and device | |
| CN111982152B (en) | Point cloud map quantification method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |