CN110503123B - Image positioning method, device, computer equipment and storage medium - Google Patents
Image positioning method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110503123B CN110503123B CN201810475696.1A CN201810475696A CN110503123B CN 110503123 B CN110503123 B CN 110503123B CN 201810475696 A CN201810475696 A CN 201810475696A CN 110503123 B CN110503123 B CN 110503123B
- Authority
- CN
- China
- Prior art keywords
- image
- geographic position
- geographic
- similar
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Processing Or Creating Images (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a positioning method, a positioning device, computer equipment and a storage medium for images. The method comprises the following steps: acquiring an image to be positioned; obtaining a plurality of similar images matched with the image to be positioned through image matching; obtaining the geographic position corresponding to each similar image; grouping the similar images according to the geographic positions corresponding to the similar images; acquiring a similar image with the maximum similarity with the image to be positioned in each group of similar images as a target image; and determining the geographic position corresponding to the image to be positioned according to the geographic position corresponding to each target image. The method can automatically locate the destination displayed in the image, and the locating information is comprehensive and has higher precision.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to an image positioning method, an image positioning device, a computer device, and a storage medium.
Background
With the improvement of living standard, activities such as traveling, dining, shopping and the like have become choices for more people. Photographs published on a network platform, pictures published in magazines, scenic postcards and the like are all references for people to select travel, dining and shopping destinations. Even the user wants to take a picture of the same view.
There may be cases where: the user sees an image (e.g., photograph, picture, postcard) and is not aware of the actual location of the destination or view where the image is displayed, and is unable to go to the destination or view where the image is displayed.
At present, no technical scheme is available for positioning images so as to cope with the above situations and provide positioning information for users.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an image positioning method, apparatus, computer device, and storage medium that are capable of positioning the position of a destination or a viewing place where an image is displayed.
An image positioning method, the method comprising:
acquiring an image to be positioned;
obtaining a plurality of similar images matched with the image to be positioned through image matching;
obtaining the geographic position corresponding to each similar image;
grouping the similar images according to the geographic positions corresponding to the similar images;
acquiring a similar image with the maximum similarity with the image to be positioned in each group of similar images as a target image;
and determining the geographic position corresponding to the image to be positioned according to the geographic position corresponding to each target image.
In one embodiment, the obtaining, through image matching, a similar image matched with the image to be localized includes: identifying a reference target in an image to be positioned; and obtaining the image matched with the reference target as a similar image matched with the image to be positioned.
In one embodiment, the grouping the similar images according to the geographic locations corresponding to the similar images includes: searching a geographic position corresponding to the reference target; if the geographic position corresponding to the similar image is found, grouping the similar images according to the distance between the geographic position corresponding to the similar image and the geographic position corresponding to the reference target, wherein the distance between the geographic position corresponding to the similar image belonging to the same grouping and one geographic position corresponding to the reference target meets the set distance condition; and if the geographic position corresponding to the similar image is not found, clustering the geographic position corresponding to the similar image.
In one embodiment, searching a geographic position corresponding to the reference target; if the geographic position corresponding to the similar image is found, grouping the similar images according to the distance between the geographic position corresponding to the similar image and the geographic position corresponding to the reference target, wherein the distance between the geographic position corresponding to the similar image belonging to the same grouping and one geographic position corresponding to the reference target meets the set distance condition; if not, determining a coordinate area covering the geographic position in a geographic coordinate system where the acquired geographic position is located; dividing the coordinate region into a plurality of unit regions; and carrying out grouping processing on the similar images based on the unit areas, wherein the similar images of which the corresponding geographic positions fall into the same unit area belong to the same group.
In one embodiment, the grouping the similar images according to the geographic locations corresponding to the similar images further includes: packets with a number of similar images less than a set threshold are filtered.
In one embodiment, the similarity includes a framing pose similarity, and the method further includes: calculating the similarity of the framing postures of each similar image and the image to be positioned according to the acquired at least one framing posture information: framing pitch angle, framing horizontal angle, framing height, framing fixture parameters.
In one embodiment, before determining the geographic location corresponding to the image to be located according to the geographic location corresponding to each target image, the method further includes: and correcting the corresponding geographic position according to the framing height of each target image, wherein the corrected geographic position comprises a horizontal position and a height position.
In one embodiment, the determining the geographic location corresponding to the image to be located according to the geographic location corresponding to each target image includes: in a geographic coordinate system where the geographic position corresponding to each target image is located, respectively determining a target area based on the geographic position corresponding to each target image; and selecting the target geographic position in each target area as the geographic position corresponding to the image to be positioned according to a preset rule.
In one embodiment, the method further comprises: transmitting the geographic positions corresponding to the plurality of to-be-positioned images to a terminal; receiving a geographic position selected by a terminal, and generating a navigation path according to the geographic position selected by the terminal; and sending the navigation path to a terminal for display.
An image positioning apparatus, the apparatus comprising:
the image acquisition module is used for acquiring an image to be positioned;
the similar image searching module is used for obtaining a plurality of similar images matched with the image to be positioned through image matching;
the geographic position acquisition module is used for acquiring geographic positions corresponding to the similar images;
the image grouping processing module is used for grouping similar images according to the obtained geographic position;
the target image determining module is used for acquiring a similar image with the maximum similarity with the image to be positioned in each group of similar images as a target image;
and the positioning processing module is used for determining the geographic position corresponding to the image to be positioned according to the geographic position corresponding to each target image.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
Acquiring an image to be positioned;
obtaining a plurality of similar images matched with the image to be positioned through image matching;
obtaining the geographic position corresponding to each similar image;
grouping the similar images according to the geographic positions corresponding to the similar images;
acquiring a similar image with the maximum similarity with the image to be positioned in each group of similar images as a target image;
and determining the geographic position corresponding to the image to be positioned according to the geographic position corresponding to each target image.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring an image to be positioned;
obtaining a plurality of similar images matched with the image to be positioned through image matching;
obtaining the geographic position corresponding to each similar image;
grouping the similar images according to the geographic positions corresponding to the similar images;
acquiring a similar image with the maximum similarity with the image to be positioned in each group of similar images as a target image;
and determining the geographic position corresponding to the image to be positioned according to the geographic position corresponding to each target image.
The image positioning method, the image positioning device, the computer equipment and the storage medium can automatically position the destination displayed in the image, and the positioning information is comprehensive and has higher precision. If the image content of the two images is similar, then the geographic locations of the two images are likely to be the same or related, and in addition, the greater the similarity of the two images, the closer the geographic location of the destination it displays. Based on the two points, the embodiment of the application can determine the geographic position of the image to be positioned by means of the geographic position of the similar image similar to the image to be positioned. There may be multiple similar images that can be found, and the geographic locations corresponding to the similar images are not identical, and multiple geographic locations may be provided to the user as alternatives to their travel destination.
Drawings
FIG. 1 is an application environment diagram of an image positioning method in one embodiment;
FIG. 2 is a flow chart of an image positioning method in one embodiment;
FIG. 3 is a flow diagram of packet processing steps in one embodiment;
FIG. 4 is a schematic diagram of determining a target image based on sliding window stepping in another embodiment;
FIG. 5 is a block diagram of an image positioning apparatus in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The image positioning method provided by the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 uploads the image to be positioned to the server 104; the server 104 obtains images to be positioned, obtains similar images matched with the images to be positioned through image matching, obtains geographic positions corresponding to the similar images, groups the similar images according to the obtained geographic positions, obtains similar images with the maximum similarity with the images to be positioned in each group of similar images as target images, and determines geographic positions corresponding to the images to be positioned according to the geographic positions corresponding to each target image. The terminal 102 may be, but not limited to, various vehicle terminals, personal computers, notebook computers, smartphones, tablet computers, and portable wearable devices, and the server 104 may be implemented by a stand-alone server or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, an image positioning method is provided, and the method is applied to the server in fig. 1 for illustration, and includes the following steps:
step 202, an image to be positioned is acquired.
The server acquires an image to be positioned from the terminal. Taking a vehicle-mounted terminal as an example, a user sends an image to be positioned to the vehicle-mounted terminal through a smart phone, a flash memory and other devices, and the vehicle-mounted terminal reports the image to be positioned to a server.
The image to be positioned may be a photo or a picture downloaded by the user through a network, or may be a photo (for example, a postcard, a photo, a magazine picture, etc.) taken by the user using a camera of a device such as a smart phone.
Step 204, obtaining a similar image matched with the image to be positioned through image matching.
Wherein, the similar images of the image to be positioned refer to images of which the result of image matching meets the preset requirement.
The server may acquire the image from the network through crawler and other technologies, so as to find the similar image. The server may also look up similar images from a local image database.
The embodiment of the application does not specifically limit the preset requirement, can be determined according to actual needs, and can also be determined by means of simulation, fitting and the like. The embodiment of the application does not limit the specific implementation manner of image matching.
And 206, obtaining the geographic position corresponding to the similar image.
Wherein the geographic location may be, but is not limited to, geographic coordinate information (e.g., latitude and longitude information), and the like. The data format may be, but is not limited to, GPS (Global Positioning System ) information.
Step 208, grouping the similar images according to the obtained geographic positions.
Step 210, obtaining a similar image with the maximum similarity with the image to be positioned in each group of similar images as a target image.
For example, two groups of similar images are obtained in step 208, the similarity between the similar images and the image to be positioned is calculated, and an image with the highest similarity is selected from each group of similar images as the target image.
Step 212, determining the geographic position corresponding to the image to be positioned according to the geographic position corresponding to each target image.
The geographic position corresponding to the image to be positioned can be a position coordinate point or a position area.
According to the image positioning method, the destination displayed in the image can be automatically positioned, positioning information is comprehensive, and accuracy is high. If the image content of the two images is similar, then the geographic locations of the two images are likely to be the same or related, and in addition, the greater the similarity of the two images, the closer the geographic location of the destination it displays. Based on the two points, the embodiment of the application can determine the geographic position of the image to be positioned by means of the geographic position of the similar image similar to the image to be positioned. There may be multiple similar images that can be found, and the geographic locations corresponding to the similar images are not identical, and multiple geographic locations may be provided to the user as alternatives to their travel destination. For example, the destination of the image to be positioned is the eiffel tower, the searched image displayed with the eiffel tower is photographed in paris in france at a certain geographic position, and the searched image is photographed in a certain theme park in beijing at a certain geographic position. To fully identify the target location (i.e., the geographic location to which the target image corresponds), similar images may be grouped by geographic location. In order to improve the accuracy of position identification, a target image with the maximum similarity with the image to be positioned is found in each group, and the geographic position of the image to be positioned is determined according to the geographic position of the target image.
The above steps are described in detail below.
In the embodiment of the present application, there are various implementations of the step 204. For example, a reference object in the image to be positioned is identified, and an image matching the reference object is obtained as a similar image matching the image to be positioned.
In practice, the viewing range of an image may be large, including multiple locations. For example, a pending image includes the eiffel tower and also includes other structures that are far apart from the eiffel tower. In this case, one of the reference targets may be selected as the reference target, and image matching may be performed based on the reference target.
Specifically, the image to be positioned can be subjected to image recognition, a plurality of reference targets are recognized, the reference targets are displayed to a user through a display screen, and one of the reference targets is selected by the user. The method comprises the steps that a terminal can identify a reference target in an image to be positioned, the reference target selected by a user is sent to a server, the server can also identify the reference target, a plurality of identified reference targets are sent to the terminal, the reference targets are displayed to the user through a display screen of the terminal, and the terminal and the user determine a final reference target through man-machine interaction and send the final reference target to the server.
The image recognition can be carried out on the image to be positioned, a plurality of reference targets are recognized, and one reference target is selected from the plurality of reference targets according to a preset rule. Wherein, the predetermined rule can be determined according to actual needs. The terminal can identify the reference target in the image to be positioned, and the selected reference target is sent to the server, or the server can identify the reference target.
The image hierarchy of the image to be positioned can also be determined based on the depth of field, and the reference object is identified within a predetermined image hierarchy or image hierarchy range.
Interference targets, such as people, animals, etc., may also be filtered when identifying the reference targets.
The implementation manner of identifying the reference target in the image to be positioned can also refer to the identification manner of the POI (Point of Interest, interest point).
After the reference target of the image to be positioned is identified in the above manner, the image matched with the reference target is obtained as a similar image matched with the image to be positioned.
The image matching can be performed only according to the reference target, and then a similar image is obtained. Image matching may also be performed based on the entire image content of the image to be located, but with higher weights given to the reference targets.
The similar image matched with the image to be positioned is obtained through the reference target, which is equivalent to giving higher weight to the reference target when the images are matched, so that the accuracy of searching the similar image can be improved, and finally the accuracy of positioning is improved. For example, the image display to be located includes the eiffel tower, as well as sky, surrounding scenes, characters, and the like. If the Eiffel iron towers are not identified, indiscriminate matching is carried out on the basis of the whole image content, and the similar images obtained by matching are likely to not contain the Eiffel iron towers; if the Eiffel tower is identified and then image matching is carried out based on the Eiffel tower, the possibility that similar images do not contain the Eiffel tower is greatly reduced.
In this embodiment of the present application, the implementation manner of step 206 is various, for example, the geographic location of the similar image may be obtained from the data of the similar image, or the geographic location of the similar image may be obtained from the text, audio and video associated with the similar image.
For example, the similar image is an electronic photograph, the data of the electronic photograph includes a geographic location, and the geographic location is obtained from the data of the electronic photograph. For example, a similar image is an image crawled from a social network that is published with text that includes a geographic location from which the geographic location is obtained. For example, a similar image is an image crawled from a social network that is published with a geographic location stamp from which the geographic location was obtained.
Some images may not have corresponding geographic locations, and in step 204, images having corresponding geographic locations may be found and filtered out.
In this embodiment of the present application, the implementation manner of the step 208 is various, for example, a clustering algorithm is used to perform grouping processing on the geographic locations corresponding to the similar images. For another example, a coordinate area covering the acquired geographic position may be divided into a plurality of unit areas in the geographic coordinate system, and grouping processing may be performed based on the divided unit areas. For another example, similar images may be grouped according to the geographic location corresponding to the reference object in the image to be located.
Regardless of the manner of identifying the reference object, a specific implementation manner of grouping similar images according to the geographic position corresponding to the reference object in the image to be positioned may refer to a flow shown in fig. 3, and specifically includes the following steps:
step 302, searching a geographic position corresponding to the reference target.
In this embodiment of the present application, the correspondence between the plurality of reference targets and the geographic locations may be pre-stored in a local database of the server or a database in communication with the server. Correspondingly, the step is to search the geographic position corresponding to the reference target in the database. The geographic position corresponding to the reference target can be searched on the network by using the techniques such as a crawler.
Where a reference target may correspond to multiple geographic locations.
It should be noted that if step 204 does not match the image based on the reference object, then a step of identifying the reference object in the similar image is included prior to step 302.
If so, step 304 is executed to group the similar images according to the distance between the geographic position corresponding to the similar image and the geographic position corresponding to the reference target. The distance between the geographic position corresponding to the similar images belonging to the same group and the same geographic position corresponding to the reference target meets the set distance condition.
The distance between the geographic position corresponding to the similar image and the geographic position corresponding to the reference target may be a spatial linear distance, or may be a spatial walking/riding/driving distance, or may be a euclidean distance, or the like.
If the reference object has only one corresponding geographic location, then a grouping of similar images is obtained in this step. If the reference object corresponds to two or more geographic locations, then groupings of two or more similar images may be obtained in this step.
The present embodiment is not limited to the distance condition. For example, the distance condition is that the distance between the geographic position corresponding to the similar image and a certain geographic position corresponding to the reference target is smaller than a set value.
Through the step, not only grouping of similar images is realized, but also filtering of noise (similar images with distances which do not meet the distance condition) can be realized, so that the operand of the subsequent processing process is reduced, and the positioning accuracy is improved.
If not, executing step 306, and clustering the geographic positions corresponding to the similar images.
In another implementation manner, if the geographic position corresponding to the reference target is not found, a coordinate area can be determined according to the obtained geographic position in a geographic coordinate system where the obtained geographic position is located, and the coordinate area covers the obtained geographic position; dividing the coordinate region into a plurality of unit regions; the similar images are grouped based on the cell areas. Wherein similar images whose corresponding geographic locations fall within the same cell region belong to the same group.
The implementation of determining the coordinate area according to the obtained geographic position is various. Taking a geographical position including a horizontal position (a horizontal position is a coordinate position on a coordinate X-Y plane, which is a horizontal plane), determining coordinates of each horizontal position, and further determining a coordinate region of a rectangle (other shapes such as a circle are also possible), wherein a boundary of the coordinate region on the X axis is a maximum value and a minimum value of X-axis coordinates in each horizontal position, and a boundary of the coordinate region on the Y axis is a maximum value and a minimum value of Y-axis coordinates in each horizontal position.
The coordinate areas can be determined and grouped in the electronic map.
Wherein the size of the cell area may be, but is not limited to being, determined according to the size of the reference target.
In the embodiment of the application, the packets with the number of similar images smaller than the set threshold value can be filtered. Wherein the threshold value may be determined according to actual needs. By the implementation mode, similar images with smaller correlation can be filtered, and noise interference is reduced.
If grouping is performed based on the unit area, the specific implementation manner of the grouping filtering may be: the first N packets are selected as packets of similar images obtained after the packet processing in descending order of the number of similar images. N is an integer not less than 1, and the specific value is determined according to actual needs.
The similar image obtained by the method provided by the embodiment of the application may be a noise image. For example, the image display content to be located includes eiffel towers, and the similar image found according to the step 202 also includes eiffel towers, but the similar image is obtained by the uploading user in Tianjin using a smart phone to perform a flip, the geographic position corresponding to the similar image is a certain position of Tianjin, and the similar image belongs to the noise image. Generally, after the grouping process, the number of images of the group in which the noise image is located is small. Therefore, the purpose of reducing noise interference can be achieved by filtering a small number of packets (the specific number threshold is determined according to the actual situation).
In the embodiment of the present application, there are various implementations of the step 210. For example, the geographic locations corresponding to each similar image are mapped to a geographic coordinate system (which may be, but is not limited to being, mapped to an electronic map); in a geographic coordinate system, respectively determining a reference area for each group of similar images; as shown in fig. 4, in each reference area, by means of stepping through the sliding window, each step is performed, an image with the maximum similarity in the sliding window is determined, and then the target image is determined.
Wherein the reference area of each set of similar images covers the geographic location corresponding to the set of similar images.
The embodiment of the application does not limit the size, shape and stepping length of the sliding window. Preferably, the shape of the sliding window is the same as the shape of the reference area. The sliding window (e.g., rectangular thick line frame in fig. 4) may traverse the entire reference area in a predetermined order (e.g., order indicated by arrow in fig. 4), or the reference area may be further divided into a plurality of unit areas, and the sliding window scans only the unit areas containing the geographic locations (e.g., dots in fig. 4) corresponding to the similar images.
If the user sees an image, he wants to take a picture from the same viewing position with reference to the image, as well as going to the destination displayed in the image. In view of this, the similarity in step 210 may include a view similarity. The view finding similarity refers to similarity calculated based on view finding posture information. Correspondingly, calculating the framing similarity between each similar image after grouping processing and the image to be positioned according to the acquired at least one framing gesture information. The framing pose information may be, but is not limited to, a combination of: framing pitch angle, framing horizontal angle, framing height, framing fixture parameters, and the like.
The view finding pitching angle refers to a pitching angle of an image photographing device during view finding. For an image obtained by a non-photographing mode (for example, drawing), the pitching angle of the view of the virtual photographing apparatus can be equivalently obtained according to the perspective relation of the display content of the image, the focus position and the like.
The view-finding horizontal angle refers to a horizontal angle when a photographic apparatus of an image is found. For an image obtained by a non-photographing mode (for example, drawing), a horizontal angle of view of the virtual photographing apparatus can be equivalently obtained according to a perspective relationship of the display content of the image, a focus position and the like.
The viewing height refers to the height difference between the shooting equipment of the image and the reference object relative to the horizontal plane. For an image obtained by a non-photographing mode (for example, drawing), the viewing height of the virtual photographing apparatus can be equivalently obtained according to the perspective relationship of the display content of the image, the focus position and the like.
The viewfinder device parameters refer to parameters such as a focal length, an aperture, and the like when the photographing device photographs an image.
The view-finding pitching angle and the view-finding horizontal angle can be calculated by an image processing mode, but are not limited to the method. For example, the framing pitch angle and the framing horizontal angle are calculated based on the reference target. The framing height may be calculated based on parameters such as, but not limited to, the framing pitch angle, and may be obtained from image data. The viewfinder device parameters may be, but are not limited to being, obtained from the image data.
In this embodiment, the similarity in step 210 may further include similarity of image content. For example, the reference object in the image to be positioned is subjected to image matching with a similar image, so that the similarity of the image content is calculated.
As described above, in the embodiment of the present application, the geographic location corresponding to the image may include a height location. Correspondingly, according to the embodiment of the application, the geographic positions corresponding to the target images can be corrected according to the framing heights of the target images. Then, in the step 212, the geographic position corresponding to the image to be located is determined according to the corrected geographic position corresponding to the target image. Specifically, if the geographic position corresponding to the target image does not include the height position, the geographic position is corrected by adding the height position to the geographic position; if the geographic position corresponding to the target image comprises the height position, the geographic position is corrected by replacing the original height position.
The height position is a height coordinate perpendicular to the horizontal plane, and can be an absolute height or a relative height.
If the similarity of the framing gestures is calculated in the embodiment of the present application, the geographical position corresponding to the target image may be corrected by using the framing height calculated in the process.
Based on any of the embodiments described above, there are a variety of specific implementations of step 212. For example, the geographic position corresponding to each target image may be used as the geographic position corresponding to the image to be positioned; the preset target geographic position, the distance of which meets the set condition, of which is corresponding to the target image can be searched for as the geographic position corresponding to the image to be positioned according to the geographic position corresponding to each target image; the target area can be respectively determined based on the geographic position corresponding to each target image in the geographic coordinate system where the geographic position corresponding to each target image is located; and selecting the target geographic position in each target area as the geographic position corresponding to the image to be positioned according to a preset rule.
The preset target geographic position is a geographic position marked in advance on the electronic map, such as a station, a parking lot and the like.
The target area may be, but not limited to, a target area of a rectangle (or other shape such as a circle) with a preset range determined by centering on the geographic position corresponding to the target image. If the target image is determined in step 210 by sliding the window, the target area may also be the coverage area of the sliding window when the target image is found.
The setting conditions for selecting the preset target geographic position may be, but are not limited to: the straight line is nearest, the walking distance is nearest, the nearest parking lot, the nearest bus station, the nearest shooting recommended place, and the like.
After the geographic position corresponding to the image to be positioned is obtained by adopting the method provided by the embodiment of the application, if the user wants to go, a navigation path can be provided for the user, or a reasonable destination can be provided for the user. For example, the geographic location corresponding to the target image is a location where the vehicle is difficult to reach, in which case, the above implementation manner may be adopted to use the parking lot near the geographic location as the geographic location corresponding to the image to be located.
On the basis of any embodiment, the server may generate a navigation path based on each geographic location corresponding to the obtained to-be-located image, and send the navigation path to the terminal. The server can also send each geographic position corresponding to the image to be positioned to the terminal, the terminal displays each geographic position to the user through the display screen, receives the geographic position selected by the user based on man-machine interaction operation, sends the geographic position to the server, and the server generates a navigation path according to the geographic position selected by the user and returns the navigation path to the terminal. The server can also send each geographic position corresponding to the image to be positioned to the terminal, the terminal displays each geographic position to the user through the display screen, receives the geographic position selected by the user based on man-machine interaction operation, and generates a navigation path and displays the navigation path to the user through the display screen.
It should be understood that, although the steps in the flowcharts of fig. 2 and 3 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2 and 3 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily occur in sequence, but may be performed alternately or alternately with at least a portion of the other steps or sub-steps of other steps.
In one embodiment, as shown in fig. 5, there is provided an image positioning apparatus including: an image acquisition module 501, a similar image lookup module 502, a geographic location acquisition module 503, an image grouping processing module 504, a target image determination module 505, and a positioning processing module 506, wherein:
an image acquisition module 501, configured to acquire an image to be positioned;
A similar image searching module 502, configured to obtain, through image matching, a plurality of similar images that are matched with the image to be localized;
a geographic position obtaining module 503, configured to obtain a geographic position corresponding to the similar image;
an image grouping processing module 504, configured to group similar images according to the obtained geographic location;
a target image determining module 505, configured to obtain, as a target image, a similar image with the greatest similarity with the image to be positioned in each group of similar images;
and the positioning processing module 506 is configured to determine a geographic location corresponding to the image to be positioned according to the geographic location corresponding to each target image.
The positioning device for the image can automatically position the destination displayed in the image, and positioning information is comprehensive and high in accuracy. If the image content of the two images is similar, then the geographic locations of the two images are likely to be the same or related, and in addition, the greater the similarity of the two images, the closer the geographic location of the destination it displays. Based on the two points, the embodiment of the application can determine the geographic position of the image to be positioned by means of the geographic position of the similar image similar to the image to be positioned. There may be multiple similar images that can be found, and the geographic locations corresponding to the similar images are not identical, and multiple geographic locations may be provided to the user as alternatives to their travel destination. For example, the destination of the image to be positioned is the eiffel tower, the searched image displayed with the eiffel tower is photographed in paris in france at a certain geographic position, and the searched image is photographed in a certain theme park in beijing at a certain geographic position. To fully identify the target location (i.e., the geographic location to which the target image corresponds), similar images may be grouped by geographic location. In order to improve the accuracy of position identification, a target image with the maximum similarity with the image to be positioned is found in each group, and the geographic position of the image to be positioned is determined according to the geographic position of the target image.
In one embodiment, the similar image searching module is specifically configured to: identifying a reference target in an image to be positioned; and obtaining the image matched with the reference target as a similar image matched with the image to be positioned.
In one embodiment, the image packet processing module is specifically configured to: searching a geographic position corresponding to the reference target; if the geographic position corresponding to the similar image is found, grouping the similar images according to the distance between the geographic position corresponding to the similar image and the geographic position corresponding to the reference target, wherein the distance between the geographic position corresponding to the similar image belonging to the same grouping and one geographic position corresponding to the reference target meets the set distance condition; and if the geographic position corresponding to the similar image is not found, clustering the geographic position corresponding to the similar image.
In one embodiment, the image packet processing module is specifically configured to: searching a geographic position corresponding to the reference target; if the geographic position corresponding to the similar image is found, grouping the similar images according to the distance between the geographic position corresponding to the similar image and the geographic position corresponding to the reference target, wherein the distance between the geographic position corresponding to the similar image belonging to the same grouping and one geographic position corresponding to the reference target meets the set distance condition; if not, determining a coordinate area covering the geographic position in a geographic coordinate system where the acquired geographic position is located; dividing the coordinate region into a plurality of unit regions; and grouping the similar images based on the unit areas, wherein the similar images with corresponding geographic positions falling into the same unit area belong to the same group.
In one embodiment, the image packet processing module is further to: packets with a number of similar images less than a set threshold are filtered.
In one embodiment, the camera module further includes a camera pose similarity calculating module, configured to calculate camera pose similarity between each similar image and the image to be positioned according to at least one of the following acquired camera pose information: framing pitch angle, framing horizontal angle, framing height, framing fixture parameters.
In one embodiment, the system further comprises a geographic position correction module, which is used for correcting the corresponding geographic position according to the framing height of each target image, wherein the corrected geographic position comprises a horizontal position and a height position.
In one embodiment, the positioning processing module is specifically configured to: in a geographic coordinate system where the geographic position corresponding to each target image is located, respectively determining a target area based on the geographic position corresponding to each target image; and selecting the target geographic position in each target area as the geographic position corresponding to the image to be positioned according to a preset rule.
In one embodiment, the system further comprises a navigation path generation module, configured to send geographic locations corresponding to the plurality of to-be-located images to a terminal; receiving a geographic position selected by a terminal, and generating a navigation path according to the geographic position selected by the terminal; and sending the navigation path to a terminal for display.
For specific limitations of the image positioning apparatus, reference may be made to the above limitations of the image positioning method, and no further description is given here. The various modules in the image locating apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing data required during execution of the computer program for image localization. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an image positioning method.
It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring an image to be positioned;
obtaining a plurality of similar images matched with the image to be positioned through image matching;
obtaining the geographic position corresponding to each similar image;
grouping the similar images according to the geographic positions corresponding to the similar images;
acquiring a similar image with the maximum similarity with the image to be positioned in each group of similar images as a target image;
and determining the geographic position corresponding to the image to be positioned according to the geographic position corresponding to each target image.
In one embodiment, when the processor executes the step of implementing "obtaining a similar image matched with an image to be localized through image matching", the specific implementation manner is as follows: identifying a reference target in an image to be positioned; and obtaining the image matched with the reference target as a similar image matched with the image to be positioned.
In one embodiment, when the processor executes the computer program to implement the step of grouping similar images according to the obtained geographic location, the specific implementation manner is as follows:
searching a geographic position corresponding to the reference target; if the geographic position corresponding to the similar image is found, grouping the similar images according to the distance between the geographic position corresponding to the similar image and the geographic position corresponding to the reference target, wherein the distance between the geographic position corresponding to the similar image belonging to the same grouping and one geographic position corresponding to the reference target meets the set distance condition; and if the geographic position corresponding to the similar image is not found, clustering the geographic position corresponding to the similar image.
In one embodiment, when the processor executes the computer program to implement the step of grouping similar images according to the obtained geographic location, the specific implementation manner is as follows: searching a geographic position corresponding to the reference target; if the geographic position corresponding to the similar image is found, grouping the similar images according to the distance between the geographic position corresponding to the similar image and the geographic position corresponding to the reference target, wherein the distance between the geographic position corresponding to the similar image belonging to the same grouping and one geographic position corresponding to the reference target meets the set distance condition; if not, determining a coordinate area covering the geographic position in a geographic coordinate system where the acquired geographic position is located; dividing the coordinate region into a plurality of unit regions; and grouping the similar images based on the unit areas, wherein the similar images with corresponding geographic positions falling into the same unit area belong to the same group.
In one embodiment, when the processor executes the computer program to implement the "group similar images by geographic location" step, further execution is performed: filtering packets for which the number of similar images is less than a set threshold
In one embodiment, the processor when executing the computer program further performs the steps of: calculating the similarity of the framing postures of each similar image and the image to be positioned according to the obtained at least one framing posture information: framing pitch angle, framing horizontal angle, framing height, framing fixture parameters. Wherein the similarity includes a framing pose similarity.
In one embodiment, the processor when executing the computer program further performs the steps of: and correcting the corresponding geographic position according to the framing height of each target image, wherein the corrected geographic position comprises a horizontal position and a height position.
In one embodiment, when the processor executes the step of "determining the geographic position corresponding to the image to be located according to the geographic position corresponding to each target image", the specific implementation manner is as follows: in a geographic coordinate system where the geographic position corresponding to each target image is located, respectively determining a target area based on the geographic position corresponding to each target image; and selecting the target geographic position in each target area as the geographic position corresponding to the image to be positioned according to a preset rule.
In one embodiment, the processor when executing the computer program further performs the steps of: transmitting the geographic positions corresponding to the plurality of to-be-positioned images to a terminal; receiving a geographic position selected by a terminal, and generating a navigation path according to the geographic position selected by the terminal; and sending the navigation path to a terminal for display.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring an image to be positioned;
obtaining a plurality of similar images matched with the image to be positioned through image matching;
obtaining the geographic position corresponding to each similar image;
grouping the similar images according to the geographic positions corresponding to the similar images;
acquiring a similar image with the maximum similarity with the image to be positioned in each group of similar images as a target image;
and determining the geographic position corresponding to the image to be positioned according to the geographic position corresponding to each target image.
The specific implementation steps of the computer program when executed by the processor may refer to the description of any method embodiment described above, and will not be repeated herein.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (11)
1. An image positioning method, the method comprising:
acquiring an image to be positioned;
obtaining a plurality of similar images matched with the image to be positioned through image matching;
obtaining the geographic position corresponding to each similar image;
grouping the similar images according to the geographic positions corresponding to the similar images;
acquiring a similar image with the maximum similarity with the image to be positioned in each group of similar images as a target image;
And determining the geographic position corresponding to the image to be positioned according to the geographic position corresponding to each target image.
2. The method of claim 1, wherein the obtaining, by image matching, a similar image that matches the image to be localized comprises:
identifying a reference target in an image to be positioned;
and obtaining the image matched with the reference target as a similar image matched with the image to be positioned.
3. The method of claim 2, wherein grouping the similar images by their corresponding geographic locations comprises:
searching a geographic position corresponding to the reference target; if the geographic position corresponding to the similar image is found, grouping the similar images according to the distance between the geographic position corresponding to the similar image and the geographic position corresponding to the reference target, wherein the distance between the geographic position corresponding to the similar image belonging to the same grouping and one of the geographic positions corresponding to the reference target meets a set distance condition; if not, clustering the geographic positions corresponding to the similar images; or alternatively, the process may be performed,
searching a geographic position corresponding to the reference target; if the geographic position corresponding to the similar image is found, grouping the similar images according to the distance between the geographic position corresponding to the similar image and the geographic position corresponding to the reference target, wherein the distance between the geographic position corresponding to the similar image belonging to the same grouping and one of the geographic positions corresponding to the reference target meets a set distance condition; if not, determining a coordinate area covering the geographic position in a geographic coordinate system where the acquired geographic position is located; dividing the coordinate region into a plurality of unit regions; and grouping the similar images based on the unit areas, wherein the similar images with corresponding geographic positions falling into the same unit area belong to the same group.
4. The method of claim 3, wherein the grouping the similar images by their corresponding geographic locations further comprises:
packets with a number of similar images less than a set threshold are filtered.
5. The method of any one of claims 1-4, wherein the similarity comprises a framing pose similarity, the method further comprising:
calculating the similarity of the framing postures of each similar image and the image to be positioned according to the acquired at least one framing posture information:
framing pitch angle, framing horizontal angle, framing height, framing fixture parameters.
6. The method of claim 5, wherein before determining the geographic location corresponding to the image to be located according to the geographic location corresponding to each of the target images, the method further comprises:
and correcting the corresponding geographic position according to the framing height of each target image, wherein the corrected geographic position comprises a horizontal position and a height position.
7. The method of claim 5, wherein determining the geographic location corresponding to the image to be located from the geographic locations corresponding to each of the target images comprises:
In a geographic coordinate system where the geographic position corresponding to each target image is located, respectively determining a target area based on the geographic position corresponding to each target image;
and selecting the target geographic position in each target area as the geographic position corresponding to the image to be positioned according to a preset rule.
8. The method of claim 7, wherein the method further comprises:
transmitting the geographic positions corresponding to the plurality of to-be-positioned images to a terminal;
receiving a geographic position selected by a terminal, and generating a navigation path according to the geographic position selected by the terminal;
and sending the navigation path to a terminal for display.
9. An image positioning apparatus, the apparatus comprising:
the image acquisition module is used for acquiring an image to be positioned;
the similar image searching module is used for obtaining a plurality of similar images matched with the image to be positioned through image matching;
the geographic position acquisition module is used for acquiring geographic positions corresponding to the similar images;
the image grouping processing module is used for grouping similar images according to the obtained geographic position;
the target image determining module is used for acquiring a similar image with the maximum similarity with the image to be positioned in each group of similar images as a target image;
And the positioning processing module is used for determining the geographic position corresponding to the image to be positioned according to the geographic position corresponding to each target image.
10. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1-8 when the computer program is executed.
11. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810475696.1A CN110503123B (en) | 2018-05-17 | 2018-05-17 | Image positioning method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810475696.1A CN110503123B (en) | 2018-05-17 | 2018-05-17 | Image positioning method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110503123A CN110503123A (en) | 2019-11-26 |
| CN110503123B true CN110503123B (en) | 2023-07-25 |
Family
ID=68584747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810475696.1A Active CN110503123B (en) | 2018-05-17 | 2018-05-17 | Image positioning method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110503123B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111159459B (en) * | 2019-12-04 | 2023-08-11 | 恒大恒驰新能源汽车科技(广东)有限公司 | Landmark positioning method, landmark positioning device, computer equipment and storage medium |
| CN113066121A (en) * | 2019-12-31 | 2021-07-02 | 深圳迈瑞生物医疗电子股份有限公司 | Image analysis system and method for identifying repeat cells |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001052175A (en) * | 1999-08-06 | 2001-02-23 | Olympus Optical Co Ltd | Image retrieving device |
| JP2002245071A (en) * | 2001-02-15 | 2002-08-30 | Sony Corp | Device and method for managing image, image database unit and storage medium |
| JP2006260405A (en) * | 2005-03-18 | 2006-09-28 | Ricoh Co Ltd | Image information updating system, image inputting device, image processing device, image updating device, image information updating method, image information updating program, and recording medium recording the program |
| CN102651748A (en) * | 2011-02-23 | 2012-08-29 | 上海博路信息技术有限公司 | Photo sharing system on basis of geographic position |
| JP2014067409A (en) * | 2012-09-10 | 2014-04-17 | Canon Marketing Japan Inc | Information processing apparatus, information processing system, control method thereof and program |
| US9613455B1 (en) * | 2014-11-02 | 2017-04-04 | Google Inc. | Local georeferenced data |
| CN107545006A (en) * | 2016-06-28 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | A kind of method, equipment and system for being used to establishing or updating image positional data storehouse |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008310446A (en) * | 2007-06-12 | 2008-12-25 | Panasonic Corp | Image retrieval system |
| US8150098B2 (en) * | 2007-12-20 | 2012-04-03 | Eastman Kodak Company | Grouping images by location |
| JP5505723B2 (en) * | 2010-03-31 | 2014-05-28 | アイシン・エィ・ダブリュ株式会社 | Image processing system and positioning system |
| JP5062498B2 (en) * | 2010-03-31 | 2012-10-31 | アイシン・エィ・ダブリュ株式会社 | Reference data generation system and position positioning system for landscape matching |
| US8774528B2 (en) * | 2010-09-24 | 2014-07-08 | Kodak Alaris Inc. | Method of selecting important digital images |
| JP2016119508A (en) * | 2014-12-18 | 2016-06-30 | 株式会社東芝 | Method, system and program |
| CN107133325B (en) * | 2017-05-05 | 2020-01-07 | 南京大学 | Internet photo geographic space positioning method based on street view map |
| CN107563366A (en) * | 2017-07-26 | 2018-01-09 | 安徽讯飞爱途旅游电子商务有限公司 | A kind of localization method and device, electronic equipment |
-
2018
- 2018-05-17 CN CN201810475696.1A patent/CN110503123B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001052175A (en) * | 1999-08-06 | 2001-02-23 | Olympus Optical Co Ltd | Image retrieving device |
| JP2002245071A (en) * | 2001-02-15 | 2002-08-30 | Sony Corp | Device and method for managing image, image database unit and storage medium |
| JP2006260405A (en) * | 2005-03-18 | 2006-09-28 | Ricoh Co Ltd | Image information updating system, image inputting device, image processing device, image updating device, image information updating method, image information updating program, and recording medium recording the program |
| CN102651748A (en) * | 2011-02-23 | 2012-08-29 | 上海博路信息技术有限公司 | Photo sharing system on basis of geographic position |
| JP2014067409A (en) * | 2012-09-10 | 2014-04-17 | Canon Marketing Japan Inc | Information processing apparatus, information processing system, control method thereof and program |
| US9613455B1 (en) * | 2014-11-02 | 2017-04-04 | Google Inc. | Local georeferenced data |
| CN107545006A (en) * | 2016-06-28 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | A kind of method, equipment and system for being used to establishing or updating image positional data storehouse |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110503123A (en) | 2019-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8768107B2 (en) | Matching an approximately located query image against a reference image set | |
| US9582937B2 (en) | Method, apparatus and computer program product for displaying an indication of an object within a current field of view | |
| EP3502621B1 (en) | Visual localisation | |
| US8774527B1 (en) | Matching an approximately located query image against a reference image set using cellular base station and wireless access point information | |
| US20220270323A1 (en) | Computer Vision Systems and Methods for Supplying Missing Point Data in Point Clouds Derived from Stereoscopic Image Pairs | |
| US9317966B1 (en) | Determine heights/shapes of buildings from images with specific types of metadata | |
| CN110858414A (en) | Image processing method and device, readable storage medium and augmented reality system | |
| US20150130833A1 (en) | Map superposition method and electronic device | |
| CN110503123B (en) | Image positioning method, device, computer equipment and storage medium | |
| CN111159459B (en) | Landmark positioning method, landmark positioning device, computer equipment and storage medium | |
| CN111062875B (en) | Coordinate conversion method and device for air panoramic roaming data | |
| CN104102732B (en) | Picture showing method and device | |
| CN112215964A (en) | Scene navigation method and device based on AR | |
| CN109034214B (en) | Method and apparatus for generating a mark | |
| CN116228860A (en) | Target geographic position prediction method, device, equipment and storage medium | |
| CN110796706A (en) | Visual positioning method and system | |
| CN113366420B (en) | Image processing method, computer-readable storage medium, and computer device | |
| CN106951553A (en) | A kind of address locating methods and device | |
| KR102272757B1 (en) | System and method for producing panoramic image and video | |
| JP2006178804A (en) | Object information providing method and object information providing server | |
| KR102555668B1 (en) | Method of generating map and visual localization using the map | |
| KR20220154556A (en) | Photography system for surpporting to picture for mobile terminal and method thereof | |
| AU2013248183B2 (en) | Matching an approximately located query image against a reference image set | |
| CN114937219A (en) | Augmented reality vehicle positioning method, device and equipment | |
| CN104750721A (en) | Image processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |