CN114792340A - Indoor positioning method, system, storage medium and electronic equipment - Google Patents
Indoor positioning method, system, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN114792340A CN114792340A CN202210480399.2A CN202210480399A CN114792340A CN 114792340 A CN114792340 A CN 114792340A CN 202210480399 A CN202210480399 A CN 202210480399A CN 114792340 A CN114792340 A CN 114792340A
- Authority
- CN
- China
- Prior art keywords
- image
- preset
- panoramic image
- splitting
- acquisition mode
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/77—Determining position or orientation of objects or cameras using statistical methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Studio Devices (AREA)
Abstract
The application discloses an indoor positioning method, an indoor positioning system, a storage medium and electronic equipment. Through the scheme, the indoor panoramic image is acquired by using the preset panoramic equipment which can be equipment with lower cost such as a panoramic camera, so that the cost of acquiring the indoor image in the map building process is reduced, the scene within the range of 360 degrees can be shot by the preset panoramic equipment, the efficiency of acquiring the indoor image is improved, the comprehensiveness of building the indoor map is ensured, and the phenomenon of missing of the built map is avoided. In addition, different resolution ratio cameras can be simulated to collect images through different splits of the panoramic image, so that different maps can be constructed according to actual use requirements, and the flexibility of constructing indoor maps is improved.
Description
Technical Field
The present disclosure relates to the field of positioning technologies, and in particular, to an indoor positioning method, system, storage medium, and electronic device.
Background
When a user is in an unfamiliar indoor environment and the GPS positioning is inaccurate, it is difficult to know which position and direction the user is located in indoors. At this time, the application of visual navigation is necessary.
The application of realizing visual navigation is mainly to realize visual positioning through a tracking system of a mobile terminal. The realization of visual positioning needs to collect images of indoor scenes to construct maps indoors.
At present, the collection modes for collecting the images of indoor scenes mainly comprise monocular camera and inertial sensor collection, laser radar collection and the like. The above-mentioned method for acquiring indoor images has the following disadvantages:
in the acquisition mode of the monocular camera and the inertial sensor, because the angle of view of the monocular camera is relatively small, the lens needs to be continuously turned around in order to shoot comprehensively, so that the shooting angles and directions are ensured as many as possible, the efficiency is low, and a map shot and constructed by the monocular camera has certain defects. In the acquisition mode of the laser radar, the method is relatively higher in cost.
Therefore, the acquisition mode for acquiring the indoor image in the process of constructing the indoor map has high cost and low efficiency, and the constructed map has a missing phenomenon.
Disclosure of Invention
In view of this, the present application discloses an indoor positioning method, system, storage medium, and electronic device, which aim to improve the efficiency of acquiring an indoor image, ensure the comprehensiveness of constructing an indoor map, avoid a missing phenomenon in the constructed map, and improve the flexibility of constructing an indoor map.
In order to achieve the purpose, the technical scheme disclosed by the method is as follows:
the application discloses a first aspect of an indoor positioning method, which comprises the following steps:
acquiring an image to be positioned, wherein the image to be positioned is acquired indoors;
positioning the image to be positioned through a preset indoor map which is constructed in advance to obtain a positioning result; the preset indoor map is obtained by constructing a key frame position and a local characteristic point of an original panoramic image acquired in advance; the original panoramic image is a panoramic image acquired indoors through a preset panoramic device; the local feature points are extracted after being split from the original panoramic image; and the positioning result is used for representing the pose of the image to be positioned in the preset indoor map.
Preferably, the process for constructing the indoor map is preset, and includes:
acquiring an original panoramic image;
performing pose estimation on a key frame in the original panoramic image by a preset pose estimation method to obtain a key frame pose;
splitting the original panoramic image in a preset splitting mode to obtain a plurality of split images;
extracting local feature points from the split images;
recombining the split images to obtain a target panoramic image; the target panoramic image is used for representing the recombined panoramic image;
determining an acquisition mode of the image to be positioned, and splitting the target panoramic image based on the acquisition mode to obtain an image in a preset form corresponding to the acquisition mode;
distributing each local characteristic point to the image in the preset form;
and constructing a preset indoor map according to the key frame pose and the distributed preset form image.
Preferably, the collecting mode includes a horizontal screen collecting mode and a vertical screen collecting mode, splitting the target panoramic image based on the collecting mode to obtain an image of a preset form corresponding to the collecting mode, including:
when the acquisition mode is the horizontal screen acquisition mode, splitting the target panoramic image to obtain a horizontal screen image corresponding to the horizontal screen acquisition mode;
and when the acquisition mode is the vertical screen acquisition mode, splitting the target panoramic image to obtain a vertical screen image corresponding to the vertical screen acquisition mode.
Preferably, the positioning the image to be positioned through a preset indoor map which is constructed in advance to obtain a positioning result, including:
extracting a query frame from the image to be positioned;
extracting a feature vector from the image to be positioned; the feature vector is used for obtaining a preset candidate key frame set from a preset image library;
performing feature matching on the query frame of the image to be positioned and each candidate frame of the candidate key frame set to obtain an initial matching result; the initial matching result is the result of feature matching between the query frame and each candidate frame;
screening the initial matching result through a preset screening rule to obtain target characteristic points; the target feature points are two-dimensional feature points;
matching the target characteristic points with preset characteristic points to obtain a target matching result; the preset feature points are three-dimensional feature points in a preset feature library; the target matching result is used for prompting the matching of the target characteristic point and the preset characteristic point;
calculating the target matching result through a preset algorithm to obtain a positioning result; and the positioning result is used for indicating the pose of the image to be positioned in the preset indoor map.
Preferably, after the positioning of the image to be positioned is performed through the pre-established preset indoor map to obtain a positioning result, the method further includes:
and displaying the positioning result in preset equipment.
A second aspect of the present application discloses an indoor positioning system, the system comprising:
the device comprises an acquisition unit, a positioning unit and a positioning unit, wherein the acquisition unit is used for acquiring an image to be positioned, and the image to be positioned is acquired indoors;
the positioning unit is used for positioning the image to be positioned through a pre-constructed preset indoor map to obtain a positioning result; the preset indoor map is obtained by constructing a key frame position and posture and local feature points of an original panoramic image acquired in advance; the original panoramic image is an indoor panoramic image acquired through a preset panoramic device; the local feature points are extracted after being split from the original panoramic image; and the positioning result is used for representing the pose of the image to be positioned in the preset indoor map.
Preferably, the positioning unit for presetting the construction process of the indoor map comprises:
the acquisition module is used for acquiring an original panoramic image;
the estimation module is used for carrying out pose estimation on the key frames in the original panoramic image through a preset pose estimation method to obtain key frame poses;
the first splitting module is used for splitting the original panoramic image in a preset splitting mode to obtain a plurality of split images;
a first extraction module, configured to extract local feature points from the multiple split images;
the recombination module is used for recombining the split images to obtain a target panoramic image; the target panoramic image is used for representing the recombined panoramic image;
the second splitting module is used for determining the acquisition mode of the image to be positioned and splitting the target panoramic image based on the acquisition mode to obtain an image in a preset form corresponding to the acquisition mode;
the distribution module is used for distributing each local characteristic point to the image in the preset form;
and the construction module is used for constructing a preset indoor map according to the key frame pose and the distributed preset form image.
Preferably, the second splitting module includes:
the first splitting sub-module is used for splitting the target panoramic image to obtain a cross screen image corresponding to the cross screen acquisition mode when the acquisition mode is the cross screen acquisition mode;
and the second splitting sub-module is used for splitting the target panoramic image to obtain a vertical screen image corresponding to the vertical screen acquisition mode when the acquisition mode is the vertical screen acquisition mode.
A third aspect of the present application discloses a storage medium, which is characterized in that the storage medium includes stored instructions, and when the instructions are executed, the apparatus where the storage medium is located is controlled to execute the indoor positioning method according to any one of the first aspect.
A fourth aspect of the present application discloses an electronic device, comprising a memory, and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by the one or more processors to perform the indoor positioning method according to any one of the first aspect.
According to the technical scheme, the indoor positioning method, the indoor positioning system, the storage medium and the electronic device are used for obtaining an image to be positioned, the image to be positioned is collected indoors and obtained, the image to be positioned is positioned through a preset indoor map which is constructed in advance, a positioning result is obtained, the preset indoor map is obtained through construction of a key frame position and a local feature point of an original panoramic image which is obtained in advance, the original panoramic image is collected through the preset panoramic device, the local feature point is extracted after the original panoramic image is split, and the positioning result is used for representing the position and posture of the image to be positioned in the preset indoor map. Through the scheme, the indoor panoramic image is acquired by using the preset panoramic equipment which can be equipment with lower cost such as a panoramic camera, so that the cost of acquiring the indoor image in the process of constructing the map is reduced, the scene within the range of 360 degrees can be shot by the preset panoramic equipment, the efficiency of acquiring the indoor image is improved, the comprehensiveness of constructing the indoor map is ensured, and the phenomenon of missing the constructed map is avoided. In addition, different resolution cameras can be simulated to collect images through different splits of the panoramic image, so that different maps are constructed according to actual use requirements, and the flexibility of constructing indoor maps is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application 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, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flowchart of an indoor positioning method disclosed in an embodiment of the present application;
FIG. 2 is a schematic diagram of an original panoramic image disclosed in an embodiment of the present application;
fig. 3 is a schematic diagram of splitting an original panoramic image disclosed in an embodiment of the present application;
FIG. 4 is a schematic illustration of a 3SFM map as disclosed in embodiments herein;
fig. 5 is a schematic structural diagram of an indoor positioning system disclosed in an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
As known from the background art, the existing method for acquiring the indoor images in the map building process has high cost and low acquisition efficiency, and the constructed map has a deletion phenomenon.
In order to solve the above problems, an embodiment of the application discloses an indoor positioning method, an indoor positioning system, a storage medium and an electronic device, wherein a preset panoramic device is used for collecting an indoor panoramic image, and the preset panoramic device can be a panoramic camera or other devices with low cost, so that the cost of collecting an indoor image in a mapping process is reduced. In addition, different resolution cameras can be simulated to collect images through different splits of the panoramic image, so that different maps are constructed according to actual use requirements, and the flexibility of constructing indoor maps is improved. The specific implementation is illustrated by the following examples.
Referring to fig. 1, a schematic flow chart of an indoor positioning method disclosed in an embodiment of the present application is shown, where the indoor positioning method mainly includes the following steps:
s101: and acquiring an image to be positioned, and acquiring the image to be positioned indoors.
In S101, an image to be positioned acquired by a user indoors through a mobile device is acquired.
The mobile device may be a mobile phone, a tablet computer, or the like.
S102: positioning an image to be positioned through a pre-constructed preset indoor map to obtain a positioning result; the method comprises the steps that a preset indoor map is obtained by constructing a key frame position and a local characteristic point of an original panoramic image which are obtained in advance; the original panoramic image is an indoor panoramic image acquired through a preset panoramic device; the local characteristic points are obtained by splitting and extracting the original panoramic image; and the positioning result is used for representing the pose of the image to be positioned in the preset indoor map.
In order to form a relationship between a two-dimensional space and a three-dimensional space, an indoor map needs to be constructed three-dimensionally, and generally, the three-dimensional construction method of the indoor map is mainly based on a Structure From Motion (SFM) method.
SFM is a photogrammetric sequence image technique for predicting three-dimensional structures from two-dimensional image sequences possibly combined with local motion signals, a phenomenon that can recover three-dimensional structures from the two-dimensional motion field of a moving object or scene projection.
The construction process of the specific preset indoor map is shown as A1-A8.
A1: and acquiring an original panoramic image.
In the acquisition process, an original panoramic image is acquired through a preset panoramic device.
The original panoramic image shows the surrounding environment as much as possible through a wide-angle representation means and forms of painting, photos, videos, three-dimensional models and the like. Specific to the original panoramic image, reference is made to fig. 2, and fig. 2 is a schematic diagram of the original global image.
The preset panoramic equipment can be a panoramic camera, other panoramic shooting equipment and the like. The preset global device is not specifically limited in this application.
A2: and performing pose estimation on the key frame in the original panoramic image by a preset pose estimation method to obtain the pose of the key frame.
The preset pose estimation method may be synchronous positioning And Mapping (SLAM), or may be another pose estimation method. The determination of the preset pose estimation method is set by a technician according to actual conditions, and the method is not particularly limited in the present application. The SLAM method is preferably selected in the preset pose estimation method.
The method mainly uses a frame OpenVSlam method of a visual SLAM with high availability and expansibility to track the feature points in the original panoramic image, calculates the pose of the key frame in the original panoramic image and records the pose.
A3: splitting the original panoramic image through a preset splitting mode to obtain a plurality of split images.
The common map construction scheme does not accept the panoramic image, so that the original panoramic image is split, and different splits can be performed according to the requirements of the map construction scene.
The common preset splitting mode can be the splitting of the sky box or the splitting of other forms. The preset splitting mode is set by technical personnel according to actual conditions, and the method is not particularly limited in the application. The preset splitting mode of the application is preferably used for splitting the sky box.
The original panoramic image is split in a sky box splitting manner, which can be seen in fig. 3, where fig. 3 shows a schematic diagram of splitting the original panoramic image in the sky box splitting manner.
A4: each local feature point is extracted from the plurality of split images.
The local feature points are local expressions of image features, can reverse the local specificity of the image, and are suitable for matching, searching and other applications of the image.
A5: recombining the split images to obtain a target panoramic image; and the target panoramic image is used for representing the recombined panoramic image.
A6: and determining the acquisition mode of the image to be positioned, splitting the target panoramic image based on the acquisition mode, and obtaining the image in the preset form corresponding to the acquisition mode.
The acquisition mode comprises a horizontal screen acquisition mode and a vertical screen acquisition mode.
The preset form image includes a landscape screen image and a portrait screen image.
And when the acquisition mode is a horizontal screen acquisition mode, splitting the target panoramic image to obtain a horizontal screen image corresponding to the horizontal screen acquisition mode.
And when the acquisition mode is the vertical screen acquisition mode, splitting the target panoramic image to obtain a vertical screen image corresponding to the vertical screen acquisition mode.
The image data (the image to be positioned) can be retrieved by splitting the image data into a horizontal screen image or a vertical screen image, for example, the image to be acquired is acquired by a horizontal screen, but when the image is used by a user, if the image is shot by a vertical screen, the image can not be retrieved accurately, and the pose estimation deviation is caused.
A7: and distributing each local characteristic point to the image in a preset form.
A8: and constructing a preset indoor map through the key frame pose and the distributed preset form image.
The preset indoor map may be a 3SFM map or a map in other forms, and the determination of the preset indoor map is set by a technician according to an actual situation, which is not specifically limited in the present application. The preset indoor map of the present application is preferably a 3SFM map.
Specifically, the structure of the 3SFM map can be referred to fig. 4, and fig. 4 is a schematic diagram of the 3SFM map.
In fig. 4, p1(x, y), p2(x, y), and p3(x, y) are two-dimensional feature points.
p1(x, y, z), p2(x, y, z) and p3(x, y, z) are three-dimensional feature points.
C1, C2, and C3 are cameras.
The same point is shot by cameras (C1, C2 and C3) with different poses, and the same point is triangulated to obtain the specific position of the three-dimensional characteristic point. For example, with C1 cameras, C2 cameras and C3 cameras of different poses, p1, p1 and p3 are photographed to obtain the positions thereof (p1(x, y), p2(x, y) and p3(x, y)), and the positions of p1, p1 and p3 in three-dimensional space, namely p1(x, y, z), p2(x, y, z) and p3(x, y, z) are obtained.
Specifically, the process of positioning the image to be positioned through the pre-established preset indoor map to obtain the positioning result is shown as B1-B6.
B1: and extracting a query frame from the image to be positioned.
When an image to be positioned transmitted by a user is received, feature extraction is carried out on the image to be positioned, and a frame is inquired.
B2: extracting a characteristic vector from an image to be positioned; the feature vector is used for obtaining a preset candidate key frame set from a preset image library.
And finding a candidate key frame set closest to the feature vector of the user picture data in the collected image library according to the feature vector.
B3: performing feature matching on the query frame of the image to be positioned and each candidate frame of the candidate key frame set to obtain an initial matching result; the initial matching result is the result of feature matching between the query frame and each candidate frame.
B4: screening out the initial matching result through a preset screening out rule to obtain target characteristic points; the target feature points are two-dimensional feature points.
And performing feature matching on each candidate frame in the candidate key frame set and the query frame, and screening out the feature points by using the optimal and suboptimal proportion to obtain the target feature points.
The preset screening rule can be a rule with optimal and suboptimal proportion, and can also be other screening rules. The preset screening rule is set by a technician according to actual conditions, and the application is not specifically limited.
B5: matching the target characteristic points with preset characteristic points to obtain a target matching result; the preset feature points are three-dimensional feature points in a preset feature library; and the target matching result is used for prompting the matching of the target characteristic point and the preset characteristic point.
The target feature points are two-dimensional feature points reserved after being screened out through a preset screening rule.
B6: calculating a target matching result through a preset algorithm to obtain a positioning result; and the positioning result is used for indicating the pose of the image to be positioned in the preset indoor map.
The preset algorithm may be a RANSAC algorithm + PnP algorithm, or a RANSAC algorithm, etc. The preset algorithm is set by a technician according to actual conditions, and the application is not limited specifically. The preset algorithm of the present application is preferably a RANSAC algorithm + PnP algorithm.
And calculating the target matching result through the RANSAC algorithm and the PnP algorithm to obtain the position and the pose of the image to be positioned in the preset indoor map.
And displaying the positioning result in preset equipment.
The preset device can be a mobile phone device, a tablet computer and the like. The preset equipment is not specifically limited in this scheme.
In the embodiment of the application, the indoor panoramic image is collected by the aid of the preset panoramic equipment, the preset panoramic equipment can be equipment with lower cost such as a panoramic camera, so that the cost of collecting the indoor image in the map building process is reduced, the scene within a 360-degree range can be shot by the preset panoramic equipment, the efficiency of collecting the indoor image is improved, the comprehensiveness of building the indoor map is ensured, and the phenomenon of missing of the built map is avoided. In addition, different resolution ratio cameras can be simulated to collect images through different splits of the panoramic image, so that different maps can be constructed according to actual use requirements, and the flexibility of constructing indoor maps is improved.
Based on the indoor positioning method disclosed in fig. 1 in the above embodiment, an indoor positioning system is correspondingly disclosed in the embodiment of the present application, and as shown in fig. 5, the indoor positioning system mainly includes an obtaining unit 501 and a positioning unit 502.
The acquiring unit 501 is configured to acquire an image to be positioned, where the image to be positioned is acquired indoors.
The positioning unit 502 is configured to position an image to be positioned through a preset indoor map that is constructed in advance, so as to obtain a positioning result; the method comprises the steps that a preset indoor map is obtained by constructing a key frame position and a local characteristic point of an original panoramic image which are obtained in advance; the original panoramic image is an indoor panoramic image acquired through a preset panoramic device; the local feature points are obtained by extracting after splitting the original panoramic image; and the positioning result is used for representing the pose of the image to be positioned in the preset indoor map.
Further, the positioning unit 502 for presetting the construction process of the indoor map includes an obtaining module, an estimating module, a first splitting module, a first extracting module, a recombining module, a second splitting module, a distributing module, and a constructing module.
And the acquisition module is used for acquiring the original panoramic image.
And the estimation module is used for estimating the pose of the key frame in the original panoramic image by a preset pose estimation method to obtain the pose of the key frame.
The first splitting module is used for splitting the original panoramic image in a preset splitting mode to obtain a plurality of split images.
And the first extraction module is used for extracting each local feature point from the split images.
The recombination module is used for recombining the split images to obtain a target panoramic image; and the target panoramic image is used for representing the recombined panoramic image.
And the second splitting module is used for determining the acquisition mode of the image to be positioned, splitting the target panoramic image based on the acquisition mode and obtaining the image in the preset form corresponding to the acquisition mode.
And the distribution module is used for distributing each local characteristic point to the image in the preset form.
And the construction module is used for constructing a preset indoor map through the key frame poses and the distributed images in the preset form.
Further, the second split module includes a first split sub-module and a second split sub-module.
And the first splitting submodule is used for splitting the target panoramic image when the acquisition mode is the horizontal screen acquisition mode to obtain a horizontal screen image corresponding to the horizontal screen acquisition mode.
And the second splitting submodule is used for splitting the target panoramic image when the acquisition mode is the vertical screen acquisition mode to obtain a vertical screen image corresponding to the vertical screen acquisition mode.
Further, the positioning unit 502 includes a second extraction module, a third extraction module, a first matching module, a screening module, a second matching module, and a calculation module.
And the second extraction module is used for extracting the query frame from the image to be positioned.
The third extraction module is used for extracting a characteristic vector from the image to be positioned; the feature vector is used for obtaining a preset candidate key frame set from a preset image library.
The first matching module is used for performing feature matching on the query frame of the image to be positioned and each candidate frame of the candidate key frame set to obtain an initial matching result; the initial matching result is the result of feature matching between the query frame and each candidate frame.
The screening module is used for screening the initial matching result through a preset screening rule to obtain a target characteristic point; the target feature points are two-dimensional feature points.
The second matching module is used for matching the target characteristic points with the preset characteristic points to obtain a target matching result; the preset feature points are three-dimensional feature points in a preset feature library; and the target matching result is used for prompting the matching of the target characteristic point and the preset characteristic point.
The calculation module is used for calculating a target matching result through a preset algorithm to obtain a positioning result; and the positioning result is used for indicating the pose of the image to be positioned in the preset indoor map.
Further, the indoor positioning system also comprises a display unit.
And the display unit is used for displaying the positioning result in the preset equipment.
In the embodiment of the application, the preset panoramic equipment is used for acquiring indoor panoramic images, and can be lower-cost equipment such as a panoramic camera, so that the cost of acquiring indoor images in the process of constructing the map is reduced, and the scene within a range of 360 degrees can be shot by the preset panoramic equipment, so that the efficiency of acquiring the indoor images is improved, the comprehensiveness of constructing the indoor map is ensured, and the phenomenon of missing the constructed map is avoided. In addition, different resolution cameras can be simulated to acquire images through different splits of the panoramic image, so that different maps are constructed according to actual use requirements, and the flexibility of constructing indoor maps is improved.
The embodiment of the application further provides a storage medium, which comprises a stored instruction, wherein when the instruction runs, the device where the storage medium is located is controlled to execute the indoor positioning method.
The embodiment of the present application further provides an electronic device, which is shown in fig. 6 and specifically includes a memory 601 and one or more instructions 602, where the one or more instructions 602 are stored in the memory 601 and configured to be executed by one or more processors 603 to execute the one or more instructions 602 to perform the indoor positioning method.
The specific implementation procedures and derivatives thereof of the above embodiments are within the scope of the present application.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing is only a preferred embodiment of the present application and it should be noted that, as will be apparent to those skilled in the art, numerous modifications and adaptations can be made without departing from the principles of the present application and such modifications and adaptations are intended to be considered within the scope of the present application.
Claims (10)
1. An indoor positioning method, characterized in that the method comprises:
acquiring an image to be positioned, wherein the image to be positioned is acquired indoors;
positioning the image to be positioned through a preset indoor map which is constructed in advance to obtain a positioning result; the preset indoor map is obtained by constructing a key frame position and a local characteristic point of an original panoramic image acquired in advance; the original panoramic image is a panoramic image acquired indoors through a preset panoramic device; the local characteristic points are obtained by splitting and extracting the original panoramic image; and the positioning result is used for representing the pose of the image to be positioned in the preset indoor map.
2. The method of claim 1, wherein presetting a construction process of the indoor map comprises:
acquiring an original panoramic image;
performing pose estimation on a key frame in the original panoramic image by a preset pose estimation method to obtain a key frame pose;
splitting the original panoramic image in a preset splitting mode to obtain a plurality of split images;
extracting local feature points from the split images;
recombining the split images to obtain a target panoramic image; the target panoramic image is used for representing the recombined panoramic image;
determining an acquisition mode of the image to be positioned, and splitting the target panoramic image based on the acquisition mode to obtain an image in a preset form corresponding to the acquisition mode;
distributing each local feature point to the image in the preset form;
and constructing a preset indoor map according to the key frame pose and the distributed preset form image.
3. The method according to claim 2, wherein the acquisition modes include a horizontal screen acquisition mode and a vertical screen acquisition mode, and the splitting the target panoramic image based on the acquisition modes to obtain an image in a preset form corresponding to the acquisition modes comprises:
when the acquisition mode is the horizontal screen acquisition mode, splitting the target panoramic image to obtain a horizontal screen image corresponding to the horizontal screen acquisition mode;
and when the acquisition mode is the vertical screen acquisition mode, splitting the target panoramic image to obtain a vertical screen image corresponding to the vertical screen acquisition mode.
4. The method according to claim 1, wherein the positioning the image to be positioned through a pre-established preset indoor map to obtain a positioning result comprises:
extracting a query frame from the image to be positioned;
extracting a feature vector from the image to be positioned; the feature vector is used for obtaining a preset candidate key frame set from a preset image library;
performing feature matching on the query frame of the image to be positioned and each candidate frame of the candidate key frame set to obtain an initial matching result; the initial matching result is the result of feature matching between the query frame and each candidate frame;
screening the initial matching result through a preset screening rule to obtain a target characteristic point; the target feature points are two-dimensional feature points;
matching the target characteristic points with preset characteristic points to obtain a target matching result; the preset feature points are three-dimensional feature points in a preset feature library; the target matching result is used for prompting the matching of the target characteristic point and the preset characteristic point;
calculating the target matching result through a preset algorithm to obtain a positioning result; and the positioning result is used for indicating the pose of the image to be positioned in the preset indoor map.
5. The method according to claim 1, wherein after the positioning the image to be positioned through the pre-constructed preset indoor map to obtain a positioning result, the method further comprises:
and displaying the positioning result in preset equipment.
6. An indoor positioning system, the system comprising:
the device comprises an acquisition unit, a positioning unit and a positioning unit, wherein the acquisition unit is used for acquiring an image to be positioned, and the image to be positioned is acquired indoors;
the positioning unit is used for positioning the image to be positioned through a preset indoor map which is constructed in advance to obtain a positioning result; the preset indoor map is obtained by constructing a key frame position and posture and local feature points of an original panoramic image acquired in advance; the original panoramic image is a panoramic image acquired indoors through a preset panoramic device; the local feature points are extracted after being split from the original panoramic image; and the positioning result is used for representing the pose of the image to be positioned in the preset indoor map.
7. The system of claim 6, wherein the locating unit for presetting the construction process of the indoor map comprises:
the acquisition module is used for acquiring an original panoramic image;
the estimation module is used for estimating the pose of the key frame in the original panoramic image by a preset pose estimation method to obtain the pose of the key frame;
the first splitting module is used for splitting the original panoramic image in a preset splitting mode to obtain a plurality of split images;
the first extraction module is used for extracting each local feature point from the plurality of split images;
the recombination module is used for recombining the split images to obtain a target panoramic image; the target panoramic image is used for representing the recombined panoramic image;
the second splitting module is used for determining the acquisition mode of the image to be positioned and splitting the target panoramic image based on the acquisition mode to obtain an image in a preset form corresponding to the acquisition mode;
the distribution module is used for distributing each local characteristic point to the image in the preset form;
and the construction module is used for constructing a preset indoor map according to the key frame pose and the distributed preset form image.
8. The system of claim 7, wherein the second splitting module comprises:
the first splitting sub-module is used for splitting the target panoramic image to obtain a cross screen image corresponding to the cross screen acquisition mode when the acquisition mode is the cross screen acquisition mode;
and the second splitting sub-module is used for splitting the target panoramic image to obtain a vertical screen image corresponding to the vertical screen acquisition mode when the acquisition mode is the vertical screen acquisition mode.
9. A storage medium comprising stored instructions, wherein the instructions, when executed, control a device on which the storage medium is located to perform the indoor positioning method of any one of claims 1 to 5.
10. An electronic device comprising a memory and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by the one or more processors to perform the indoor positioning method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210480399.2A CN114792340A (en) | 2022-05-05 | 2022-05-05 | Indoor positioning method, system, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210480399.2A CN114792340A (en) | 2022-05-05 | 2022-05-05 | Indoor positioning method, system, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114792340A true CN114792340A (en) | 2022-07-26 |
Family
ID=82462387
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210480399.2A Pending CN114792340A (en) | 2022-05-05 | 2022-05-05 | Indoor positioning method, system, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114792340A (en) |
-
2022
- 2022-05-05 CN CN202210480399.2A patent/CN114792340A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10740975B2 (en) | Mobile augmented reality system | |
| US11557083B2 (en) | Photography-based 3D modeling system and method, and automatic 3D modeling apparatus and method | |
| TWI494898B (en) | Extracting and mapping three dimensional features from geo-referenced images | |
| Yahyanejad et al. | Incremental mosaicking of images from autonomous, small-scale uavs | |
| CN110874818B (en) | Image processing and virtual space construction method, device, system and storage medium | |
| CN102338639A (en) | Information processing device and information processing method | |
| KR20170094030A (en) | System and Method for providing mapping of indoor navigation and panorama pictures | |
| CN102831816B (en) | Device for providing real-time scene graph | |
| US20210264666A1 (en) | Method for obtaining photogrammetric data using a layered approach | |
| US8509522B2 (en) | Camera translation using rotation from device | |
| JP2017212510A (en) | Image management device, program, image management system, and information terminal | |
| CN112465907A (en) | Indoor visual navigation method and system | |
| KR101574636B1 (en) | Change region detecting system using time-series aerial photograph captured by frame type digital aerial camera and stereoscopic vision modeling the aerial photograph with coordinate linkage | |
| CN114549766B (en) | Real-time AR visualization method, device, equipment and storage medium | |
| CN115601496A (en) | AR-assisted three-dimensional map scale recovery method and system | |
| JP2016053961A (en) | Information processing device, information processing method, and program | |
| JP2016194783A (en) | Image management system, communication terminal, communication system, image management method, and program | |
| JP5817012B2 (en) | Information processing apparatus, information processing method, and program | |
| JP2020071854A (en) | Image processing apparatus, image processing method, and program | |
| CN114792340A (en) | Indoor positioning method, system, storage medium and electronic equipment | |
| EP3882846B1 (en) | Method and device for collecting images of a scene for generating virtual reality data | |
| CN111581322A (en) | Method, device and equipment for displaying interest area in video in map window | |
| CA3102860C (en) | Photography-based 3d modeling system and method, and automatic 3d modeling apparatus and method | |
| US20240087157A1 (en) | Image processing method, recording medium, image processing apparatus, and image processing system | |
| CN110966988B (en) | Three-dimensional distance measurement method, device and equipment based on double-panoramic image automatic matching |
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 |