CN116309811A - Internet streetscape photo geographic position identification positioning method, storage medium and equipment - Google Patents
Internet streetscape photo geographic position identification positioning method, storage medium and equipment Download PDFInfo
- Publication number
- CN116309811A CN116309811A CN202211277844.1A CN202211277844A CN116309811A CN 116309811 A CN116309811 A CN 116309811A CN 202211277844 A CN202211277844 A CN 202211277844A CN 116309811 A CN116309811 A CN 116309811A
- Authority
- CN
- China
- Prior art keywords
- street view
- internet
- streetscape
- scale
- candidate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims abstract description 5
- 230000009466 transformation Effects 0.000 claims abstract description 5
- 238000005259 measurement Methods 0.000 claims abstract description 4
- 238000012216 screening Methods 0.000 claims abstract description 4
- 239000013598 vector Substances 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 5
- 230000006835 compression Effects 0.000 claims description 4
- 238000007906 compression Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000013139 quantization Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 3
- 238000005538 encapsulation Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241000282412 Homo Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
- G06V20/38—Outdoor scenes
- G06V20/39—Urban scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Remote Sensing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a geographic position identifying and positioning method, a storage medium and computer equipment for an Internet streetscape photo, wherein the method comprises the following steps: s1, acquiring large-scale street view image data, extracting features of the large-scale street view image data, and forming a large-scale street view image feature index library; s2, extracting features of the Internet streetscape photo by adopting the same feature extraction method as that in the S1, performing similarity measurement calculation with a large-scale streetscape image feature library, and rapidly searching matched candidate streetscape images; s3, performing feature matching on the Internet streetscape photo and the rapidly searched candidate streetscape image, obtaining a homonymous matching point pair of the candidate image and the Internet streetscape photo, and screening the Internet streetscape photo and the candidate streetscape image pair with the best matching quality; and S4, calculating affine transformation parameters of the images through the matching point pairs of the candidate street view images and the internet street view images, so as to calculate the geographic coordinates of the internet street view images.
Description
Technical Field
The invention relates to the field of remote sensing, in particular to the technical field of remote sensing image positioning.
Background
With the development of smart city construction, the approaches to obtain spatial location information are increasing. Eighty percent of the socioeconomic activity of humans is statistically related to spatial geographic location information. Currently, the application of human beings to geospatial information is also more and more widespread, and the geospatial data is often used for analysis and utilization, so that great economic benefits are brought. In recent years, street view maps have come into public life, and provide more convenience for life, and street view images have the characteristics of wide coverage, high coverage density, detailed expression content, high acquisition efficiency and the like: in terms of coverage, street view pictures already cover most cities around the world. In terms of coverage density, street view pictures already cover all levels of road networks of cities at high density, visual pictures formed between adjacent sampling points can be connected in a seamless manner, and complete expression of urban street material space is formed. In terms of expressing content, street view pictures express the actual state of urban mass space in a human view in an exhaustive and fine manner. For example, the highest size of google streetscape can reach 6656×13312 pixels, the fine degree of spatial expression of urban substances by the streetscape picture is guaranteed by the higher definition picture, and under the further support of related artificial intelligence technology, the accurate extraction of scene semantic targets and the efficient understanding of scene contents are realized. Street view image coverage is more and more rich in recent two years, and can be obtained through an open source approach. However, the currently used street view image searching geographic position identification method is low in efficiency and poor in identification accuracy.
Disclosure of Invention
Therefore, the invention realizes the geographic position identification and positioning method of the Internet street view photo based on the large-scale street view data as a reference. Offline feature extraction is carried out on the large-scale street view data, an index library is established by utilizing a similarity retrieval tool, large-scale candidate street view image retrieval is carried out, and image retrieval efficiency is improved; and performing feature matching on the candidate street view images obtained by searching and the Internet street view photos, obtaining an image pair with highest matching quality, calculating the accurate geographic coordinates of each pixel of the Internet street view photos by using the most similar candidate street view image coordinates, and realizing the geographic position identification of any Internet street view photo.
The embodiment of the invention provides a geographic position identifying and positioning method for an Internet street view photo, which comprises the following steps:
s1, acquiring large-scale street view image data, extracting characteristics of the large-scale street view image data, establishing an efficient index file by adopting a similarity index tool, establishing a similarity index file, and forming a large-scale street view image characteristic index library;
s2, extracting features of the Internet streetscape photo by adopting the same feature extraction method as that in the S1, performing similarity measurement calculation with a large-scale streetscape image feature library, and rapidly searching matched candidate streetscape images;
s3, performing feature matching on the Internet streetscape photo and the rapidly searched candidate streetscape image, obtaining a homonymous matching point pair of the candidate image and the Internet streetscape photo, and screening the Internet streetscape photo and the candidate streetscape image pair with the best matching quality;
and S4, calculating affine transformation parameters of the images through the matching point pairs of the candidate street view images and the internet street view images, so as to calculate the geographic coordinates of the internet street view images.
In an alternative embodiment, in S4, further includes: and calculating the geographic coordinates of each pixel point by adopting an interpolation method, so as to realize the accurate positioning of the Internet street view photo.
In an alternative embodiment, in S1, a crawler technology is used to obtain from a street view API of a map service provider, and the obtained street view image and metadata information are stored in a warehouse according to a unified naming rule.
In an alternative embodiment, in S2: and calling an index API to quickly retrieve the matched candidate street view images.
In an alternative embodiment, dense feature extraction is fine-tuned using a resnet-50 network.
In an alternative embodiment, the extracting features of the large-scale street view image data includes: and constructing a discrete scale pyramid for the street view image, and extracting the characteristics of each scale image to obtain the characteristics describing the areas with different sizes and the different receptive fields.
In an alternative embodiment, the similarity indexing tool comprises:
vector compression and query calculation are carried out by adopting a vector quantization method, and the region of interest is positioned on the vector in the whole space to be positioned in a vector subspace.
In an alternative embodiment, the interpolation method is a bilinear interpolation method.
Another aspect of an embodiment of the present invention also provides a computer readable storage medium storing computer program code, which when executed by a computer device, performs the identifying and locating method according to any one of the above.
Another aspect of the embodiment of the present invention further provides a computer device, including: a memory and a processor;
the memory is used for storing computer instructions;
the processor executes the computer instructions stored in the memory to cause the computer device to perform any of the above identified location methods.
The invention has the following technical effects:
1. according to the invention, on the basis of performing offline feature extraction on the large-scale street view data, an index library is established by utilizing a similarity retrieval tool, and large-scale candidate street view image retrieval is performed, so that the image retrieval efficiency is improved; and performing feature matching on the candidate street view images obtained by searching and the Internet street view photos, obtaining an image pair with highest matching quality, calculating the accurate geographic coordinates of each pixel of the Internet street view photos by using the most similar candidate street view image coordinates, and realizing the geographic position identification of any Internet street view photo.
2. In the invention, dense feature extraction adopts a resnet-50 network for fine adjustment, and the discrimination capability of local expression is improved through fine adjustment, so that deep features are obtained. The network is trained with already paired data. Meanwhile, in order to cope with larger scale differences, a discrete scale pyramid is constructed on the street view image, and feature extraction is carried out on each scale image to obtain features describing areas with different sizes and different receptive fields. The feature points have enough abstract and can obtain higher positioning precision.
3. The invention adopts a similarity indexing tool: firstly, vector compression and query calculation are carried out by adopting a vector quantization method, the efficiency of distance calculation is improved, secondly, the region of interest is positioned on the full-space vector, and the region of interest is positioned to a vector subspace, so that the vector to be searched is calculated only in a plurality of subspaces of interest, the distance is not calculated on all the vectors of the space, and the searching efficiency is further improved.
4. For the case that the resolution of the reference street view image is lower than that of the Internet street view image, the geographic coordinates of each pixel point cannot be calculated in a matching mode due to inconsistent image resolution, and the geographic coordinates of each pixel point can be calculated in an interpolation mode.
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 is a flowchart for identifying geographic locations of Internet street view photographs in an embodiment of the invention;
FIG. 2 is a schematic diagram of a dense feature extraction network in an embodiment of the invention;
FIG. 3 is a schematic diagram of an index build data flow in an embodiment of the invention;
FIG. 4 is a flowchart of index api encapsulation in an embodiment of the invention;
FIG. 5 is a diagram of a bi-interpolation method in an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The large-scale street view image refers to a large number of street view images with geographic coordinate information.
The internet street view image in the invention refers to a street view image with obvious ground objects acquired on the internet, and does not necessarily have geographic coordinates.
FIG. 1 is a flowchart for identifying geographic locations of Internet street view photographs in an embodiment of the invention;
FIG. 2 is a schematic diagram of a dense feature extraction network in an embodiment of the invention;
FIG. 3 is a schematic diagram of an index build data flow in an embodiment of the invention;
FIG. 4 is a flowchart of index api encapsulation in an embodiment of the invention
FIG. 5 is a diagram of a bi-interpolation method in an embodiment of the invention.
The embodiment of the invention provides a geographic position identifying and positioning method for an Internet street view photo, which comprises the following steps: referring to figure 1 of the drawings in which,
s1, acquiring large-scale street view image data, extracting characteristics of the large-scale street view image data, establishing an efficient index file by adopting a similarity index tool, establishing a similarity index file, and forming a large-scale street view image characteristic index library;
specifically, the large-scale street view image data can be acquired and processed by utilizing a crawler technology from a street view API of a map service provider, and then the acquired street view image and metadata information are stored in a warehouse according to a unified naming rule.
And performing offline feature extraction on the obtained and stored large-scale street view image data, extracting features of the large-scale street view image data, and then establishing an efficient index file by adopting a similarity index tool to form a large-scale street view image feature index library which is used as an Internet street view photo reference image quick index library.
The street view (image) acquisition method comprises the following steps: the acquisition of the street view image with the geographic coordinate information is a precondition for geographic positioning based on the street view image. Currently there are a large number of open-sourced street view image datasets on the network, such as Google-Landmarks datasets containing over 100 tens of thousands of street view images with GPS coordinates, involving 12894 landmark buildings. In addition, a large number of street view data acquisition can be carried out through hundred-degree street view and google street view images, and a street view image feature library can be constructed. For part of key areas, the street view images can be acquired and updated in real time by adopting a vehicle-mounted camera acquisition mode.
S2, extracting features of the Internet streetscape photo by adopting the same feature extraction method as that in the S1, performing similarity measurement calculation with a large-scale streetscape image feature library, and calling an index API to quickly search out matched candidate streetscape images;
s3, performing feature matching on the Internet streetscape photo and the rapidly searched candidate streetscape image, obtaining a homonymous matching point pair of the candidate image and the Internet streetscape photo, and screening the Internet streetscape photo and the candidate streetscape image pair with the best matching quality;
and S4, calculating affine transformation parameters of the images through the matching point pairs of the candidate street view images and the internet street view images, so as to calculate the geographic coordinates of the internet street view images.
Specifically, as the street view image is provided with the geographic coordinates, the geographic coordinates of the street view image are assigned to the corresponding points of the street view picture after being matched with the Internet street view image.
And calculating affine transformation parameters of the images through the matching point pairs of the candidate street view images and the Internet street view images, so as to calculate the geographic coordinates of the Internet street view images, and calculating the geographic coordinates of each pixel point by adopting an interpolation method for the Internet street view images with higher resolution, thereby realizing the accurate positioning of the Internet street view images.
The invention discloses a geographic position identification and positioning method for an Internet street view photo based on large-scale street view data as a reference. Offline feature extraction is carried out on the large-scale street view data, an index library is established by utilizing a similarity retrieval tool, large-scale candidate street view image retrieval is carried out, and image retrieval efficiency is improved; and performing feature matching on the candidate street view images obtained by searching and the Internet street view photos, obtaining an image pair with highest matching quality, calculating the accurate geographic coordinates of each pixel of the Internet street view photos by using the most similar candidate street view image coordinates, and realizing the geographic position identification of any Internet street view photo.
The invention adopts a dense feature extraction network: the previous layers of the convolutional network have very small receptive fields, and the obtained characteristics are local characteristics such as edges, corner points and the like of the relative bottom layer, but the positioning accuracy is higher; the deeper the network layer number is, the more abstract the extracted features are, the more global the information is, the more interference caused by the heterogeneous images can be resisted, but the poorer the positioning accuracy is. Therefore, in order to enable the feature points to have enough abstract and obtain higher positioning accuracy, the dense feature extraction adopts a resnet-50 network for fine adjustment, and the discrimination capability of local expression is improved through fine adjustment, so that deep features are obtained. The network is trained with already paired data. Meanwhile, in order to cope with larger scale differences, a discrete scale pyramid is constructed on the street view image, and feature extraction is carried out on each scale image to obtain features describing areas with different sizes and different receptive fields. A scale range of from 0.25 to 2.0 is provided, using 8 different scales of 0.25, 0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0 respectively.
Fig. 2 is a dense feature extraction network, divided into three sections: the left side is the ResNet50 overall structure, the middle is the ResNet50 each Stage concrete structure, and the right side is the Bottleneck concrete structure.
(1) The ResNet50 overall structure shows the Backbone portion of ResNet without the global average pooling layer and full connectivity layer in ResNet;
(2) ResNet is divided into 5 stages, wherein Stage 0 has a relatively simple structure, is used for preprocessing an INPUT, and the last 4 stages are all composed of Bottleneck and have relatively similar structures. Stage1 contains 3 bottlenecks, the remaining 3 stages respectively including 4, 6, 3 bottlenecks;
(3) The network uses a structure of 2 types of Bottleneck, 2 types of Bottleneck corresponding to 2 cases respectively: the number of input and output channels is the same (BTNK 2), and the number of input and output channels is different (BTNK 1).
Referring to fig. 3 for index build data flow, fig. 4 is an index API encapsulation flow diagram, in which an original vector set is built and encapsulated into an index file (index file) and cached in memory before using the similarity search to search for similarity of query vectors, providing real-time query computation. Two processes are required to be trained and added when constructing an index file for the first time. There may be an add operation to implement the incremental index if a new vector needs to be added to the index file.
The invention adopts a similarity indexing tool: firstly, vector compression and query calculation are carried out by adopting a vector quantization method, the efficiency of distance calculation is improved, secondly, the region of interest is positioned on the full-space vector, and the region of interest is positioned to a vector subspace, so that the vector to be searched is calculated only in a plurality of subspaces of interest, the distance is not calculated on all the vectors of the space, and the searching efficiency is further improved.
In order to acquire the geographic coordinates of each pixel point of the street view image, the Internet street view image in the invention preferably adopts a bilinear interpolation method:
(1) Converting the geographic coordinates of the street view image to the Internet street view image through the matching point pairs, and then calculating the geographic coordinates of each pixel point by adopting an interpolation method;
(2) Because the resolution of the images is inconsistent, if the resolution of the reference street view image is lower than that of the Internet street view image, the geographic coordinates of each pixel point can not be calculated in a matching mode, and the geographic coordinates of each pixel point can be calculated in an interpolation mode.
As shown in FIG. 5, Q is known 11 、Q 12 、Q 21 、Q 22 Data points (points of known geographical coordinates) and P points to be interpolated (points of geographical coordinates to be calculated), we consider the values at these points as pixel points on the image, provided we want to obtain the value of the unknown function f at point p= (x, y), assuming we know the function f at Q 11 ＝(x1,y1)，Q 12 ＝(x1,y2),Q 21 = (x 2, y 1) and Q 22 Values of four points= (x 2, y 2).
Firstly, linear interpolation is carried out in the x direction to obtain R1 and R2:
then, linear interpolation is carried out in the y direction to obtain P:
the geographical coordinates f (x, y) at the internet picture (x, y) are thus obtained.
The geographic position identifying and positioning method for the Internet street view photo can be deployed in computer equipment.
The computer device may include: input unit, processor unit, communication unit, memory cell, output unit and power supply.
The input unit is used for inputting or importing data.
The storage unit, namely a memory, is used for storing computer instructions and can store a large-scale street view image characteristic index library formed by processing;
and the processor executes the computer instructions stored in the memory so that the computer equipment executes the geographic position identification and positioning method of the Internet street view photo.
The output unit is used for outputting an execution result.
The computer device provided by the embodiment of the application can be used for executing the geographic position identifying and positioning method of the internet street view photo in the previous embodiment.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions in accordance with the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line), or wireless (e.g., infrared, wireless, microwave, etc.). Computer readable storage media can be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc., that contain an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk), etc.
It will be appreciated that in addition to the foregoing, some conventional structures and conventional methods are included, and as such are well known, they will not be described in detail. But this does not mean that the structures and methods do not exist in the present invention.
It will be appreciated by those skilled in the art that while a number of exemplary embodiments of the invention have been shown and described herein in detail, many other variations or modifications which are in accordance with the principles of the invention may be directly ascertained or inferred from the present disclosure without departing from the spirit and scope of the invention. Accordingly, the scope of the present invention should be understood and deemed to cover all such other variations or modifications.
Claims (10)
1. The geographic position identification and positioning method for the Internet streetscape photo is characterized by comprising the following steps of:
s1, acquiring large-scale street view image data, extracting characteristics of the large-scale street view image data, establishing an efficient index file by adopting a similarity index tool, establishing a similarity index file, and forming a large-scale street view image characteristic index library;
s2, extracting features of the Internet streetscape photo by adopting the same feature extraction method as that in the S1, performing similarity measurement calculation with a large-scale streetscape image feature index library, and rapidly searching out matched candidate streetscape images;
s3, performing feature matching on the Internet streetscape photo and the candidate streetscape image, obtaining a homonymous matching point pair of the candidate image and the Internet streetscape photo, and screening the Internet streetscape photo and the candidate streetscape image pair with the best matching quality;
and S4, calculating affine transformation parameters of the images through the matching point pairs of the candidate street view images and the internet street view images, so as to calculate the geographic coordinates of the internet street view images.
2. The identification positioning method as claimed in claim 1, further comprising, in S4: and calculating the geographic coordinates of each pixel point by adopting an interpolation method, and finishing the accurate positioning of the Internet street view photo.
3. The identification positioning method as claimed in claim 1, further comprising, in S1: and obtaining a street view image from the street view API of the map service provider by utilizing a crawler technology, and warehousing and storing the obtained street view image and metadata information according to a unified naming rule.
4. A method of identifying and locating as claimed in claim 3, wherein in S2: and calling an index API to quickly retrieve the matched candidate street view images.
5. The identification positioning method of claim 1, wherein dense feature extraction is fine-tuned using a resnet-50 network.
6. The identification positioning method of claim 1, wherein the extracting features of the large-scale street view image data comprises: and constructing a discrete scale pyramid for the street view image, and extracting the characteristics of each scale image to obtain the characteristics describing the areas with different sizes and the different receptive fields.
7. The identification positioning method as claimed in claim 1, wherein the similarity indexing means comprises:
vector compression and query calculation are carried out by adopting a vector quantization method, and the region of interest is positioned on the vector in the whole space to be positioned in a vector subspace.
8. The identification positioning method of claim 1, wherein the interpolation method is a bilinear interpolation method.
9. A computer readable storage medium, characterized in that the computer readable storage medium stores computer program code which, when executed by a computer device, performs the identification positioning method according to any of the preceding claims 1-8.
10. A computer device, comprising: a memory and a processor;
the memory is used for storing computer instructions;
the processor executes the computer instructions stored in the memory to cause the computer device to perform the identification positioning method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211277844.1A CN116309811A (en) | 2022-10-19 | 2022-10-19 | Internet streetscape photo geographic position identification positioning method, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211277844.1A CN116309811A (en) | 2022-10-19 | 2022-10-19 | Internet streetscape photo geographic position identification positioning method, storage medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116309811A true CN116309811A (en) | 2023-06-23 |
Family
ID=86796537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211277844.1A Pending CN116309811A (en) | 2022-10-19 | 2022-10-19 | Internet streetscape photo geographic position identification positioning method, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116309811A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133325A (en) * | 2017-05-05 | 2017-09-05 | 南京大学 | A kind of internet photo geographical space localization method based on streetscape map |
| CN114241464A (en) * | 2021-11-30 | 2022-03-25 | 武汉大学 | Cross-view image real-time matching geographic positioning method and system based on deep learning |
| CN114972506A (en) * | 2022-05-05 | 2022-08-30 | 武汉大学 | Image positioning method based on deep learning and street view image |
-
2022
- 2022-10-19 CN CN202211277844.1A patent/CN116309811A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133325A (en) * | 2017-05-05 | 2017-09-05 | 南京大学 | A kind of internet photo geographical space localization method based on streetscape map |
| CN114241464A (en) * | 2021-11-30 | 2022-03-25 | 武汉大学 | Cross-view image real-time matching geographic positioning method and system based on deep learning |
| CN114972506A (en) * | 2022-05-05 | 2022-08-30 | 武汉大学 | Image positioning method based on deep learning and street view image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107133325B (en) | Internet photo geographic space positioning method based on street view map | |
| US8018458B2 (en) | Close-packed uniformly adjacent, multiresolutional overlapping spatial data ordering | |
| Luo et al. | Geotagging in multimedia and computer vision—a survey | |
| JP5654127B2 (en) | Object recognition using incremental feature extraction | |
| Hu et al. | GeoAI at ACM SIGSPATIAL: progress, challenges, and future directions | |
| US8352480B2 (en) | Methods, apparatuses and computer program products for converting a geographical database into a map tile database | |
| US9292766B2 (en) | Techniques for ground-level photo geolocation using digital elevation | |
| US20090083275A1 (en) | Method, Apparatus and Computer Program Product for Performing a Visual Search Using Grid-Based Feature Organization | |
| Cheng et al. | A data-driven point cloud simplification framework for city-scale image-based localization | |
| Ghouaiel et al. | Coupling ground-level panoramas and aerial imagery for change detection | |
| CN113487523B (en) | Method and device for optimizing graph contour, computer equipment and storage medium | |
| US11341183B2 (en) | Apparatus and method for searching for building based on image and method of constructing building search database for image-based building search | |
| CN113988147B (en) | Multi-label classification method and device for remote sensing image scene based on graph network, and multi-label retrieval method and device | |
| CN104486585A (en) | Method and system for managing urban mass surveillance video based on GIS | |
| GB2534903A (en) | Method and apparatus for processing signal data | |
| CN113808269A (en) | Map generation method, positioning method, system and computer readable storage medium | |
| CN116309811A (en) | Internet streetscape photo geographic position identification positioning method, storage medium and equipment | |
| Liu et al. | CMLocate: A cross‐modal automatic visual geo‐localization framework for a natural environment without GNSS information | |
| Gu et al. | Deep learning-based image geolocation for travel recommendation via multi-task learning | |
| Chu et al. | A news picture geo-localization pipeline based on deep learning and street view images | |
| CN114241313A (en) | Method, apparatus, medium, and program product for extracting road boundary | |
| CN111372211A (en) | Smart phone WiFi indoor positioning method based on ensemble learning | |
| CN115641499B (en) | Photographing real-time positioning method, device and storage medium based on street view feature library | |
| Tang et al. | Automatic geo‐localization framework without GNSS data | |
| Abdulkadhem et al. | Geo-localization of videobased on proposed LBP-SVD method |
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 |