CN110503123A - Image position method, device, computer equipment and storage medium - Google Patents
Image position method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110503123A CN110503123A CN201810475696.1A CN201810475696A CN110503123A CN 110503123 A CN110503123 A CN 110503123A CN 201810475696 A CN201810475696 A CN 201810475696A CN 110503123 A CN110503123 A CN 110503123A
- Authority
- CN
- China
- Prior art keywords
- image
- geographical location
- similar
- corresponding geographical
- similar image
- 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.)
- Granted
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)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application involves a kind of for the localization method of image, device, computer equipment and storage medium.The described method includes: obtaining bit image undetermined；By images match, multiple similar images with the images match to be positioned are obtained；Obtain the corresponding geographical location of each similar image；Similar image is grouped according to similar image corresponding geographical location；Obtain in every group of similar image with the maximum similar image of similarity of the bit image undetermined as target image；The corresponding geographical location of the bit image undetermined is determined according to the corresponding geographical location of each target image.The destination shown in image can be positioned automatically using this method, location information is comprehensively and precision is higher.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of image position method, device, computer equipment and
Storage medium.
Background technique
With the improvement of living standards, the activity such as travel outdoors, have dinner, doing shopping has become the selection of more people.Network
The picture published on the photo issued on platform, magazine, postcard with a picture etc. can all become people's selection and travel, have dinner, purchase
The reference of object destination.Even, user wishes to shoot the identical photo found a view.
It may be the case that user sees piece image (such as above-mentioned photo, picture, postcard), it is not known that should
The physical location of destination shown by image or ground of finding a view, also can not just go to destination shown by image or find a view ground.
There is presently no technical solutions can position to image, to cope with above situation, provides positioning letter for user
Breath.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of image position method, device, computer equipment and
Storage medium positions so as to the position to destination shown by image or ground of finding a view.
A kind of image position method, which comprises
Obtain bit image undetermined；
By images match, multiple similar images with the images match to be positioned are obtained；
Obtain the corresponding geographical location of each similar image；
Similar image is grouped according to similar image corresponding geographical location；
Obtain in every group of similar image with the maximum similar image of similarity of the bit image undetermined as target figure
Picture；
The corresponding geographical location of the bit image undetermined is determined according to the corresponding geographical location of each target image.
It is described by images match in one of the embodiments, obtain the similar diagram with the images match to be positioned
Picture, comprising: identify the reference target in bit image undetermined；Obtain with the matched image of the reference target as with it is described undetermined
The matched similar image of bit image.
It is described in one of the embodiments, that similar image is grouped according to similar image corresponding geographical location,
It include: to search the corresponding geographical location of the reference target；If finding, according to the corresponding geographical location of similar image with it is described
The distance in the corresponding geographical location of reference target, is grouped similar image, and the similar image for belonging to same packets is corresponding
Geographical location meets set distance condition at a distance from a corresponding geographical location with the reference target；It is right if not finding
The corresponding geographical location of similar image carries out clustering processing.
The corresponding geographical location of the reference target is searched in one of the embodiments,；If finding, according to similar diagram
As corresponding geographical location at a distance from corresponding geographical location, is grouped similar image, belongs to phase with the reference target
The corresponding geographical location of similar image with grouping meets setting with the reference target at a distance from a corresponding geographical location
Distance condition；If not finding, is determined in the geographic coordinate system where the geographical location of acquisition and cover the geographical location
Coordinates regional；The coordinates regional is divided into multiple unit areas；Domain is grouped similar image based on the cellular zone
Processing, the similar image that corresponding geographical location falls into same unit area belong to same packets.
It is described in one of the embodiments, that similar image is grouped according to similar image corresponding geographical location,
Further comprise: filtering similar image quantity is less than the grouping of given threshold.
The similarity includes posture similarity of finding a view, this method further include: according to acquisition in one of the embodiments,
Following at least one find a view posture information, calculate the posture similarity of finding a view of each similar image Yu the bit image undetermined: taking
Scape pitch angle, level angle of finding a view, find a view height, equipment parameter of finding a view.
In one of the embodiments, it is described determined according to the corresponding geographical location of each target image it is described undetermined
Before the corresponding geographical location of bit image, this method further include: respectively according to the height of finding a view of each target image, correct corresponding
Geographical location, revised geographical location include horizontal position and height and position.
In one of the embodiments, it is described determined according to the corresponding geographical location of each target image it is described undetermined
The corresponding geographical location of bit image, comprising: in the geographic coordinate system where the corresponding geographical location of each target image,
Target area is determined respectively based on the corresponding geographical location of each target image；According to scheduled rule, respectively each
Selection target geographical location is as the corresponding geographical location of the bit image undetermined in target area.
This method in one of the embodiments, further include: send out the corresponding geographical location of multiple bit images undetermined
It send to terminal；The geographical location for receiving terminal selection generates guidance path according to the geographical location of terminal selection；It will be described
Guidance path is sent to terminal and is shown.
A kind of image positioning device, described device include:
Image collection module, for obtaining bit image undetermined；
Similar image searching module, for obtaining multiple similar to the images match to be positioned by images match
Image；
Geographical location obtains module, for obtaining the corresponding geographical location of the similar image；
Image PHM packet handling module, for being grouped according to the geographical location of acquisition to similar image；
Target image determining module, it is maximum with the similarity of the bit image undetermined in every group of similar image for obtaining
Similar image as target image；
Localization process module, for determining the bit image undetermined according to the corresponding geographical location of each target image
Corresponding geographical location.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
Obtain bit image undetermined；
By images match, multiple similar images with the images match to be positioned are obtained；
Obtain the corresponding geographical location of each similar image；
Similar image is grouped according to similar image corresponding geographical location；
Obtain in every group of similar image with the maximum similar image of similarity of the bit image undetermined as target figure
Picture；
The corresponding geographical location of the bit image undetermined is determined according to the corresponding geographical location of each target image.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
Obtain bit image undetermined；
By images match, multiple similar images with the images match to be positioned are obtained；
Obtain the corresponding geographical location of each similar image；
Similar image is grouped according to similar image corresponding geographical location；
Obtain in every group of similar image with the maximum similar image of similarity of the bit image undetermined as target figure
Picture；
The corresponding geographical location of the bit image undetermined is determined according to the corresponding geographical location of each target image.
It is above-mentioned for the localization method of image, device, computer equipment and storage medium, can be automatically to being shown in image
Destination positioned, location information comprehensively and precision it is higher.If the picture material of two images is similar, then the two figures
The geographical location of picture is likely to identical or related, in addition, the similarity of two images is bigger, the geographical position of the destination of display
It sets closer.Based on the above two o'clock, the embodiment of the present application can be by the geographical position of similar image similar with bit image undetermined
Set the geographical location for determining bit image undetermined.The similar image that can be found may have multiple, and similar image is correspondingly
Reason position is not quite similar, and multiple geographical locations are provided to user as its Reiseziel alternatively.
Detailed description of the invention
Fig. 1 is the applied environment figure of image position method in one embodiment；
Fig. 2 is the flow diagram of image position method in one embodiment；
Fig. 3 is the flow diagram of packet transaction step in one embodiment；
Fig. 4 is the schematic diagram for determining target image in another embodiment based on sliding window stepping；
Fig. 5 is the structural block diagram of image positioning device in one embodiment；
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Image position method provided by the present application can be applied in application environment as shown in Figure 1.Wherein, terminal 102
It is communicated by network with server 104.Bit image undetermined is uploaded to server 104 by terminal 102；Server 104 obtains
Bit image undetermined obtains the similar image with the images match to be positioned by images match, obtains similar image correspondingly
Manage position, similar image is grouped according to the geographical location of acquisition, obtain in every group of similar image with bit image undetermined
The maximum similar image of similarity as target image, bitmap undetermined is determined according to the corresponding geographical location of each target image
As corresponding geographical location.Wherein, terminal 102 can be, but not limited to be various car-mounted terminals, personal computer, notebook electricity
Brain, smart phone, tablet computer and portable wearable device, server 104 can be either multiple with independent server
The server cluster of server composition is realized.
In one embodiment, as shown in Fig. 2, providing a kind of image position method, it is applied in Fig. 1 in this way
It is illustrated for server, comprising the following steps:
Step 202, bit image undetermined is obtained.
Wherein, server obtains bit image undetermined from terminal.By taking car-mounted terminal as an example, user passes through smart phone, flash memory
Etc. equipment bit image undetermined is sent to car-mounted terminal, bit image undetermined is reported to server again by car-mounted terminal.
Wherein, bit image undetermined can be the photo or picture that user is downloaded by network, is also possible to user and uses intelligence
The photo (such as reproduction postcard, photo, magazine picture etc.) of the camera shooting of the equipment such as energy mobile phone.
Step 204, by images match, the similar image with images match to be positioned is obtained.
Wherein, the similar image of bit image undetermined refers to that the result of images match meets the image of pre-provisioning request.
Wherein, server can with but be not limited only to by the technologies such as crawler from network obtain image, and then search similar diagram
Picture.Server can also search similar image from local image data base.
The embodiment of the present application does not limit pre-provisioning request specifically, can also can pass through determine according to actual needs
The modes such as emulation, fitting determine.The embodiment of the present application is not defined the specific implementation of images match.
Step 206, the corresponding geographical location of above-mentioned similar image is obtained.
Wherein, geographical location can with but be not limited only to be geographic coordinate information (such as latitude and longitude information) etc..Its data
Format can with but be not limited only to be GPS (Global Positioning System, global positioning system) information.
Step 208 is grouped similar image according to the geographical location of acquisition.
Step 210, obtain in every group of similar image with the maximum similar image of similarity of bit image undetermined as mesh
Logo image.
For example, obtaining two groups of similar images by step 208, then these similar images and bit image undetermined are calculated separately
Similarity selects the maximum image of similarity as target image respectively in every group of similar image.
Step 212 determines the corresponding geographical location of bit image undetermined according to the corresponding geographical location of each target image.
Wherein, the corresponding geographical location of bit image undetermined can be position coordinates point, be also possible to the band of position.
In the above-mentioned localization method for image, the destination shown in image can be positioned automatically, positioning letter
Breath is comprehensively and precision is higher.If the picture material of two images is similar, then the geographical location of the two images is likely to identical
Or it is related, in addition, the similarity of two images is bigger, the geographical location of the destination of display is closer.Based on the above two o'clock,
The embodiment of the present application can determine the geography of bit image undetermined by the geographical location of similar image similar with bit image undetermined
Position.The similar image that can be found may have multiple, and the corresponding geographical location of similar image is not quite similar, multiple geography
Position is provided to user as its Reiseziel alternatively.For example, the destination that bit image undetermined is shown is Ai Fei
That steel tower, in Paris, FRA, corresponding geographical location is bar for the shooting that the image for showing Eiffel Tower found has
Certain position of multitude, in Beijing theme park, corresponding geographical location is Beijing position for some shootings.In order to identify comprehensively
Target position (i.e. the corresponding geographical location of target image), can be grouped similar image according to geographical location.In order to mention
The precision of high position identification, found in each grouping with the maximum target image of the similarity of bit image undetermined, according to the mesh
The geographical location of logo image determines the geographical location of bit image undetermined.
Above steps is described in detail below.
In the embodiment of the present application, there are many implementations of above-mentioned steps 204.For example, identifying the ginseng in bit image undetermined
Target is examined, is obtained with the matched image of reference target as the similar image with images match to be positioned.
In practical application, the viewfinder range of image may be very big, wherein including multiple places.For example, in certain image undetermined
It also include other farther away buildings of meeting with Eiffel Tower including Eiffel Tower.In this case, it can choose wherein one
It is a to be used as reference target, and then images match is carried out based on the reference target.
Specifically, image recognition can be carried out to image to be positioned, several reference targets are identified, by these reference targets
User is showed by display screen, one of reference target is selected by user.Wherein it is possible to by terminal recognition bit image undetermined
In reference target, and by user select reference target be sent to server, can also be identified, will be identified by server
Obtained several reference targets are sent to terminal, show user by the display screen of terminal, and pass through people by terminal and user
Machine interaction determines final reference target, is sent to server.
Can also to image to be positioned carry out image recognition, identify several reference targets, if according to it is scheduled rule from
A reference target is selected in dry reference target.Wherein, scheduled rule can be determine according to actual needs.Wherein it is possible to by
Reference target in terminal recognition bit image undetermined, and select reference target be sent to server, can also by server into
Row identification.
The image hierarchy that bit image undetermined can also be determined according to the depth of field, in scheduled image hierarchy or image hierarchy range
Interior identification reference target.
When identifying reference target, jamming target, such as personage, animal etc. can also be filtered.
Wherein, identify that the implementation of the reference target in bit image undetermined can also be referring to POI (Point of
Interest, point of interest) identification method.
After the reference target for identifying bit image undetermined through the above way, obtain and the matched image conduct of reference target
With the similar image of images match to be positioned.
Wherein it is possible to carry out images match according only to reference target, and then obtain similar image.It can also be based on undetermined
The all images content of bit image carries out images match, but assigns higher weight for reference target.
Similar image with images match to be positioned is obtained by reference to target, is equivalent in images match, for reference
Target imparts higher weight, and then the accuracy of similar image lookup can be improved, the final accuracy for improving positioning.Example
Such as, image to be positioned shows that content includes Eiffel Tower, also includes sky, surrounding scenes, personage etc..If nonrecognition its
In Eiffel Tower, but indiscriminate matching is carried out based on whole image content, the similar image matched is likely to
Not comprising Eiffel Tower；If identifying Eiffel Tower, and then images match is carried out based on Eiffel Tower, then largely
Reduce a possibility that similar image is not comprising Eiffel Tower.
In the embodiment of the present application, there are many implementations of above-mentioned steps 206, for example, can be from the data of similar image
The middle geographical location for obtaining similar image, can also obtain similar image from the associated text of similar image, audio-video etc.
Geographical location.
For example, similar image is electronic photo, it include geographical location in the data of the electronic photo, then from the electronic photo
Data in obtain geographical location.For example, similar image is the image crawled from social networks, the image with include geographical position
The text set is issued together, then geographical location is obtained from the text.For example, similar image is the figure crawled from social networks
Picture, the image are issued together with geographical location marker, then obtain geographical location from the geographical location marker.
Some images may be without corresponding geographical location, and in step 204, can search has corresponding geographical location
Image filters out the image in no corresponding geographical location.
In the embodiment of the present application, there are many implementations of above-mentioned steps 208, for example, using clustering algorithm to similar diagram
As corresponding geographical location is grouped processing.In another example the geographical location that can be obtained covering in geographic coordinate system
Coordinates regional is divided into multiple unit areas, and the unit area based on division is grouped processing.For another example can be according to undetermined
The corresponding geographical location of reference target is grouped similar image in bit image.
No matter which kind of mode is used to identify reference target, according to the corresponding geographical location pair of reference target in bit image undetermined
The specific implementation that similar image is grouped is referred to process shown in Fig. 3, specifically comprises the following steps:
Step 302 searches the corresponding geographical location of reference target.
It, can be in the local data base of server or the database with server communication in advance in the embodiment of the present application
Save the corresponding relationship in multiple reference targets and geographical location.Correspondingly, the step is to search in above-mentioned database with reference to mesh
Mark corresponding geographical location.The corresponding geographical location of reference target can also be searched on network by technologies such as crawlers.
Wherein, a reference target may correspond to multiple geographical locations.
If should be pointed out that, step 204 carries out images match not according to reference target, before step 302, also
Include the steps that identifying the reference target in similar image.
If finding, execute step 304, according to the corresponding geographical location of similar image correspondingly with above-mentioned reference target
The distance for managing position, is grouped similar image.Wherein, belong to the corresponding geographical location of similar image of same packets and be somebody's turn to do
The distance in the corresponding same geographical location of reference target meets set distance condition.
Wherein, the corresponding geographical location of similar image can be spatially at a distance from corresponding geographical location with reference target
Linear distance, be also possible to walking// garage's distance of riding spatially, can also be Euclidean distance etc..
If reference target only has a corresponding geographical location, the grouping of a similar image is obtained in the step.If
Reference target corresponds to two even more than two geographical locations, then available two or even more than two phases in the step
Like the grouping of image.
The condition of adjusting the distance is not defined the present embodiment.For example, distance condition be the corresponding geographical location of similar image with
The distance in certain corresponding geographical location of reference target is less than setting value.
By the step, the grouping to similar image is not only realized, can also realize that (distance is unsatisfactory for distance to noise
The similar image of condition) filtering, with reduce subsequent processes operand, improve positioning accuracy.
If not finding, executes step 306, clustering processing is carried out to the corresponding geographical location of similar image.
It, can also be in the geography of acquisition if not finding the corresponding geographical location of reference target in another implementation
Coordinates regional is determined according to the geographical location of acquisition in geographic coordinate system where position, the geography that coordinates regional covering obtains
Position；The coordinates regional is divided into multiple unit areas；Similar image is grouped based on unit area.Wherein, corresponding
Geographical location fall into the similar image of same unit area and belong to same packets.
Wherein, there are many implementations that coordinates regional is determined according to the geographical location of acquisition.It include water with geographical location
For prosposition sets (horizontal position refers to, using horizontal plane as coordinate X-Y plane, coordinate position on the coordinate plane), really
The coordinate of fixed each horizontal position, and then determine the coordinates regional of a rectangle (being also possible to the other shapes such as circle), the coordinate
Boundary of the region in X-axis is the maximum value and minimum value of the X axis coordinate in each horizontal position, and coordinates regional is in Y-axis
Boundary is the maximum value and minimum value of the Y axis coordinate in each horizontal position.
Wherein, specifically coordinates regional can be determined in electronic map and realize grouping.
Wherein, the size of unit area can with but be not limited only to according to the size of reference target determine.
In the embodiment of the present application, the grouping that similar image quantity is less than given threshold can also be filtered.Wherein it is possible to according to
It is actually needed and determines the threshold value.By this implementation, the lesser similar image of correlation can be filtered out, it is dry to reduce noise
It disturbs.
If being grouped based on unit area, the specific implementation of packet filtering be may is that according to similar image quantity
Descending, select top n to be grouped grouping as the similar image obtained after packet transaction.N is the integer not less than 1, tool
Body value is determine according to actual needs.
It may be noise image using the similar image that method provided by the embodiments of the present application is got.For example, to be positioned
Image show content include Eiffel Tower, certain similar image found according to above-mentioned steps 202 also includes Ai Feier iron
Tower, but the similar image is that its uploader is obtained in Tianjin using smart phone reproduction, the corresponding geographical position of the similar image
It is set to Tianjin position, which belongs to noise image.In general, after packet transaction, grouping where noise image,
Its image quantity.Therefore, the grouping of filtering negligible amounts (particular number threshold value is determines according to actual conditions) can be passed through
Achieve the purpose that reduce noise jamming.
In the embodiment of the present application, there are many implementations of above-mentioned steps 210.For example, correspondingly by each similar image
Reason position is mapped to geographic coordinate system (can with but be not limited only to be mapped in electronic map)；In geographic coordinate system, for every
Group similar image determines reference zone respectively；As shown in figure 4, in each reference zone, by way of sliding window stepping, every time
Stepping determines the maximum image of similarity in sliding window, and then determines target image.
Wherein, the reference zone of every group of similar image covers the corresponding geographical location of this group of similar image.
The embodiment of the present application is not defined sliding window size, shape, stepping length.Preferably, the shape and ginseng of sliding window
The shape in examination district domain is identical.Sliding window (such as the rectangle bold box in Fig. 4) can be according to predetermined order (sequence as shown in Fig. 4 arrow)
Entire reference zone is traversed, reference zone can also be further divided into several unit areas, sliding window is only scanned comprising similar
The unit area in the corresponding geographical location of image (dot in such as Fig. 4).
User sees certain image, if not being intended merely to go to the destination shown in image, it is also desirable to referring to the image from phase
Same position shooting photo of finding a view.In view of this, the similarity in above-mentioned steps 210 may include similarity of finding a view.Wherein, it takes
Scape similarity refers to the similarity being calculated based on posture information of finding a view.Correspondingly, being found a view appearance according at least one of acquisition
State information calculates the similarity of finding a view of each similar image and bit image undetermined after packet transaction.Find a view posture information can with but not
It is only limitted to combine: pitch angle of finding a view, level angle of finding a view, find a view height, equipment parameter etc. of finding a view.
Wherein, pitch angle of finding a view refers to the pitch angle when shooting equipment of image is found a view.For non-shooting mode (example
As drawn) obtained image, show that perspective relation, the focal position etc. of content equivalent can also virtually be shot according to image
The pitch angle that equipment is found a view.
Level angle of finding a view refers to the level angle when shooting equipment of image is found a view.Non-shooting mode (such as is drawn
System) obtained image, show that perspective relation, the focal position etc. of content equivalent can also obtain virtually shooting equipment according to image
The level angle found a view.
Height of finding a view refers to the shooting equipment and the difference in height of reference target with respect to the horizontal plane of image.For non-shooting side
The image that formula (such as drafting) obtains shows that perspective relation, the focal position etc. of content equivalent can also obtain void according to image
Quasi- shooting equipment is found a view highly.
Equipment parameter of finding a view refer to shooting equipment shooting figure as when focal length, aperture etc. parameter.
Wherein, find a view pitch angle, find a view level angle can by but calculate in a manner of being not limited only to through image procossing
It arrives.For example, calculating find a view pitch angle and level angle of finding a view based on reference target.Find a view height can with but be not limited only to basis
The parameters such as pitch angle of finding a view are calculated, and can also obtain from image data.Equipment parameter of finding a view can with but be not limited only to
It is obtained from image data.
In the embodiment of the present application, the similarity in step 210 can also include the similarity of picture material.For example, will be to
The reference target and similar image positioned in image carries out images match, to calculate the similarity of picture material.
As described above, the corresponding geographical location of image may include height and position in the embodiment of the present application.Correspondingly, this
Application embodiment can also correct respectively the corresponding geographical position of each target image according to the height of finding a view of each target image
It sets.So, in above-mentioned steps 212, bit image undetermined is specifically determined according to the corresponding revised geographical location of target image
Corresponding geographical location.Specifically, if not including height and position in the corresponding geographical location of target image, amendment geographical location is
Finger increases to height and position in geographical location；If including height and position in the corresponding geographical location of target image, correct ground
Reason position refers to the original height and position of replacement.
Wherein, height and position is perpendicular to the height coordinate of horizontal plane, can be absolute altitude, is also possible to relatively high
Degree.
Wherein, if calculating posture similarity of finding a view in the embodiment of the present application, it can use what this was calculated in the process
Height of finding a view is modified the corresponding geographical location of target image.
On the basis of above-mentioned any embodiment, there are many specific implementations of step 212.For example, can will be each
The corresponding geographical location of target image is used as the corresponding geographical location of bit image undetermined；Each target image pair can also be directed to
The goal-selling geographical location for meeting at a distance from corresponding geographical location with target image and imposing a condition is searched in the geographical location answered
As the corresponding geographical location of bit image undetermined；It can also be in the geography where the corresponding geographical location of each target image
In coordinate system, target area is determined based on the corresponding geographical location of each target image respectively；According to scheduled rule, exist respectively
Selection target geographical location is as the corresponding geographical location of bit image undetermined in each target area.
Wherein, goal-selling geographical location is the geographical location marked in advance on the electronic map, such as station, parking lot
Deng.
Wherein, according to the corresponding geographical location of target image determine target area can with but be not limited only to be with target image
Centered on corresponding geographical location, the target area of the rectangle (or the other shapes such as circle) of preset range is determined.If step 210
In determine target image by way of sliding window stepping, which can also be when finding target image, sliding window covering
Region.
Wherein, select goal-selling geographical location setting condition can with but be not limited only to be: linear distance recently, walking
Recommend place etc. apart from nearest, nearest parking lot, nearest bus stop, apart from nearest shooting.
After obtaining the corresponding geographical location of bit image undetermined using mode provided by the embodiments of the present application, if before user wishes
It is past, guidance path can also be provided for user, or provide reasonable destination for user.For example, target image is correspondingly
Reason position is that garage is difficult to the position reached, in this case, above-mentioned implementation can be used the geographic vicinity
Parking lot is as the corresponding geographical location of bit image undetermined.
On the basis of above-mentioned any embodiment, server can be based on the obtained corresponding each geography of bit image undetermined
Position generates guidance path respectively and is sent to terminal.Server can also be by the corresponding each geographical location of bit image undetermined
It is sent to terminal, each geographical location is showed into user by display screen by terminal, and receive and use based on man-machine interactive operation
The geographical location of family selection, is sent to server, and the geographical location that server is selected according to user generates guidance path and returns
To terminal.The corresponding each geographical location of bit image undetermined can also be sent to terminal by server, by terminal by each geography
Position shows user by display screen, and the geographical location of user's selection is received based on man-machine interactive operation, user's selection
Geographical location generates guidance path and shows user by display screen.
It should be understood that although each step in the flow chart of Fig. 2 and Fig. 3 is successively shown according to the instruction of arrow,
But these steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly state otherwise herein, these
There is no stringent sequences to limit for the execution of step, these steps can execute in other order.Moreover, in Fig. 2 and Fig. 3
At least part step may include that perhaps these sub-steps of multiple stages or stage are not necessarily same to multiple sub-steps
One moment executed completion, but can execute at different times, and the execution in these sub-steps or stage sequence is also not necessarily
Be successively carry out, but can at least part of the sub-step or stage of other steps or other steps in turn or
Alternately execute.
In one embodiment, as shown in figure 5, providing a kind of image positioning device, comprising: image collection module 501,
Similar image searching module 502, geographical location obtain module 503, image PHM packet handling module 504, target image determining module
505 and localization process module 506, in which:
Image collection module 501, for obtaining bit image undetermined；
Similar image searching module 502, for obtaining multiple phases with the images match to be positioned by images match
Like image；
Geographical location obtains module 503, for obtaining the corresponding geographical location of the similar image；
Image PHM packet handling module 504, for being grouped according to the geographical location of acquisition to similar image；
Target image determining module 505, for obtaining the similarity with the bit image undetermined in every group of similar image
Maximum similar image is as target image；
Localization process module 506, it is described to be positioned for being determined according to the corresponding geographical location of each target image
The corresponding geographical location of image.
The above-mentioned positioning device for image can automatically position the destination shown in image, location information
Comprehensively and precision is higher.If the picture material of two images is similar, then the geographical location of the two images be likely to it is identical or
Correlation, in addition, the similarity of two images is bigger, the geographical location of the destination of display is closer.Based on the above two o'clock, originally
Application embodiment can determine the geographical position of bit image undetermined by the geographical location of similar image similar with bit image undetermined
It sets.The similar image that can be found may have multiple, and the corresponding geographical location of similar image is not quite similar, multiple geography positions
It sets and is provided to user as its Reiseziel alternatively.For example, the destination that bit image undetermined is shown is Ai Feier
Steel tower, in Paris, FRA, corresponding geographical location is Paris for the shooting that the image for showing Eiffel Tower found has
Certain position, in Beijing theme park, corresponding geographical location is Beijing position for some shootings.In order to identify mesh comprehensively
Cursor position (i.e. the corresponding geographical location of target image), can be grouped similar image according to geographical location.In order to improve
Position identification precision, found in each grouping with the maximum target image of the similarity of bit image undetermined, according to the target
The geographical location of image determines the geographical location of bit image undetermined.
In one embodiment, similar image searching module is specifically used for: identifying the reference target in bit image undetermined；
It obtains with the matched image of the reference target as the similar image with the images match to be positioned.
In one embodiment, image PHM packet handling module is specifically used for: searching the corresponding geography of the reference target
Position；It is right according to the corresponding geographical location of similar image with the reference target at a distance from corresponding geographical location if finding
Similar image is grouped, and the corresponding geographical location of similar image for belonging to same packets is one corresponding with the reference target
The distance in geographical location meets set distance condition；If not finding, the corresponding geographical location of similar image is carried out at cluster
Reason.
In one embodiment, image PHM packet handling module is specifically used for: searching the corresponding geography of the reference target
Position；It is right according to the corresponding geographical location of similar image with the reference target at a distance from corresponding geographical location if finding
Similar image is grouped, and the corresponding geographical location of similar image for belonging to same packets is one corresponding with the reference target
The distance in geographical location meets set distance condition；If not finding, in the geographic coordinate system where the geographical location of acquisition
Determine the coordinates regional for covering the geographical location；The coordinates regional is divided into multiple unit areas；Based on the unit
Region is grouped similar image, and the similar image that corresponding geographical location falls into same unit area belongs to same packets.
In one embodiment, image PHM packet handling module is further used for: filtering similar image quantity is less than setting threshold
The grouping of value.
It in one embodiment, further include posture similarity calculation module of finding a view, for according to following at least the one of acquisition
Posture information of finding a view is planted, calculate the posture similarity of finding a view of each similar image Yu the bit image undetermined: pitch angle of finding a view takes
Scape level angle, find a view height, equipment parameter of finding a view.
It in one of the embodiments, further include geographical location correction module, for taking according to each target image respectively
Scape height, corrects corresponding geographical location, and revised geographical location includes horizontal position and height and position.
Localization process module is specifically used in one of the embodiments: in the corresponding geography of each target image
In geographic coordinate system where position, target area is determined based on the corresponding geographical location of each target image respectively；It presses
According to scheduled rule, respectively in each target area selection target geographical location as the corresponding geography of the bit image undetermined
Position.
In one of the embodiments, further include guidance path generation module, is used for multiple bit images pair undetermined
The geographical location answered is sent to terminal；The geographical location for receiving terminal selection is generated according to the geographical location of terminal selection
Guidance path；The guidance path is sent to terminal to show.
Specific about image positioning device limits the restriction that may refer to above for image position method, herein not
It repeats again.Modules in above-mentioned image positioning device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 6.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is used to store data needed for the Computer Program Implementation Process for framing.The computer is set
Standby network interface is used to communicate with external terminal by network connection.To realize when the computer program is executed by processor
A kind of image position method.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor perform the steps of when executing computer program
Obtain bit image undetermined；
By images match, multiple similar images with the images match to be positioned are obtained；
Obtain the corresponding geographical location of each similar image；
Similar image is grouped according to similar image corresponding geographical location；
Obtain in every group of similar image with the maximum similar image of similarity of the bit image undetermined as target figure
Picture；
The corresponding geographical location of the bit image undetermined is determined according to the corresponding geographical location of each target image.
In one embodiment, processor executes computer program realization and " by images match, obtains and bit image undetermined
When matched similar image " step, specific implementation are as follows: identify the reference target in bit image undetermined；It obtains and the ginseng
The image of object matching is examined as the similar image with the images match to be positioned.
In one embodiment, processor executes computer program and realizes " according to the geographical location of acquisition to similar image
Be grouped " step when, specific implementation are as follows:
Search the corresponding geographical location of the reference target；If finding, according to the corresponding geographical location of similar image with
The distance in the corresponding geographical location of the reference target, is grouped similar image, belongs to the similar image pair of same packets
The geographical location answered meets set distance condition at a distance from a corresponding geographical location with the reference target；If not searching
It arrives, clustering processing is carried out to the corresponding geographical location of similar image.
In one embodiment, processor executes computer program and realizes " according to the geographical location of acquisition to similar image
Be grouped " step when, specific implementation are as follows: search the corresponding geographical location of the reference target；If finding, according to phase
At a distance from corresponding geographical location, similar image is grouped with the reference target like the corresponding geographical location of image, is belonged to
Meet at a distance from a corresponding geographical location in the corresponding geographical location of similar image of same packets with the reference target
Set distance condition；If not finding, the covering geographical position is determined in the geographic coordinate system where the geographical location of acquisition
The coordinates regional set；The coordinates regional is divided into multiple unit areas；Domain carries out similar image based on the cellular zone
Grouping, the similar image that corresponding geographical location falls into same unit area belong to same packets.
In one embodiment, processor executes computer program realization and " divides according to geographical location similar image
When group " step, further execute: filtering similar image quantity is less than the grouping of given threshold
In one embodiment, also performed the steps of when processor executes computer program according to acquisition with down toward
Few one kind is found a view posture information, and the posture similarity of finding a view of each similar image Yu the bit image undetermined: pitch angle of finding a view is calculated
It spends, level angle of finding a view, find a view height, equipment parameter of finding a view.Wherein, above-mentioned similarity includes posture similarity of finding a view.
In one embodiment, it also performs the steps of respectively when processor executes computer program according to each target figure
The height of finding a view of picture, corrects corresponding geographical location, revised geographical location includes horizontal position and height and position.
In one embodiment, processor executes computer program and realizes " correspondingly according to each target image
Reason position determine the corresponding geographical location of the bit image undetermined " step when, specific implementation are as follows: in each target figure
As in the geographic coordinate system where corresponding geographical location, determined respectively based on the corresponding geographical location of each target image
Target area；According to scheduled rule, respectively in each target area selection target geographical location as the bitmap undetermined
As corresponding geographical location.
In one embodiment, also performing the steps of when processor executes computer program will be multiple described to be positioned
The corresponding geographical location of image is sent to terminal；The geographical location for receiving terminal selection, the geographical position selected according to the terminal
Set generation guidance path；The guidance path is sent to terminal to show.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
Obtain bit image undetermined；
By images match, multiple similar images with the images match to be positioned are obtained；
Obtain the corresponding geographical location of each similar image；
Similar image is grouped according to similar image corresponding geographical location；
Obtain in every group of similar image with the maximum similar image of similarity of the bit image undetermined as target figure
Picture；
The corresponding geographical location of the bit image undetermined is determined according to the corresponding geographical location of each target image.
Wherein, step is specifically executed when computer program is executed by processor is referred to above-mentioned any means embodiment
Description, details are not described herein again.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (11)
1. a kind of image position method, which comprises
Obtain bit image undetermined；
By images match, multiple similar images with the images match to be positioned are obtained；
Obtain the corresponding geographical location of each similar image；
Similar image is grouped according to similar image corresponding geographical location；
Obtain in every group of similar image with the maximum similar image of similarity of the bit image undetermined as target image；
The corresponding geographical location of the bit image undetermined is determined according to the corresponding geographical location of each target image.
2. the method according to claim 1, wherein described pass through images match, acquisition and the bitmap undetermined
As matched similar image, comprising:
Identify the reference target in bit image undetermined；
It obtains with the matched image of the reference target as the similar image with the images match to be positioned.
3. according to the method described in claim 2, it is characterized in that, it is described according to the corresponding geographical location of similar image to similar
Image is grouped, comprising:
Search the corresponding geographical location of the reference target；If finding, according to the corresponding geographical location of similar image with it is described
The distance in the corresponding geographical location of reference target, is grouped similar image, and the similar image for belonging to same packets is corresponding
Geographical location meets set distance condition at a distance from one of them corresponding described geographical location with the reference target；If not looking into
It finds, clustering processing is carried out to the corresponding geographical location of similar image；Alternatively,
Search the corresponding geographical location of the reference target；If finding, according to the corresponding geographical location of similar image with it is described
The distance in the corresponding geographical location of reference target, is grouped similar image, and the similar image for belonging to same packets is corresponding
Geographical location meets set distance condition at a distance from one of them corresponding described geographical location with the reference target；If not looking into
It finds, the coordinates regional for covering the geographical location is determined in the geographic coordinate system where the geographical location of acquisition；It will be described
Coordinates regional is divided into multiple unit areas；Domain is grouped similar image based on the cellular zone, corresponding geographical location
The similar image for falling into same unit area belongs to same packets.
4. according to the method described in claim 3, it is characterized in that, it is described according to the corresponding geographical location of similar image to similar
Image is grouped, further includes:
Filter the grouping that similar image quantity is less than given threshold.
5. method according to any one of claims 1 to 4, which is characterized in that the similarity is similar including posture of finding a view
Degree, this method further include:
It is found a view posture information according to the following at least one of acquisition, calculates the appearance of finding a view of each similar image Yu the bit image undetermined
State similarity:
Find a view pitch angle, level angle of finding a view, find a view height, equipment parameter of finding a view.
6. according to the method described in claim 5, it is characterized in that, described according to the corresponding geographical position of each target image
It sets before determining the corresponding geographical location of the bit image undetermined, this method further include:
Respectively according to the height of finding a view of each target image, corresponding geographical location is corrected, revised geographical location includes level
Position and height and position.
7. according to the method described in claim 5, it is characterized in that, described according to the corresponding geographical position of each target image
It sets and determines the corresponding geographical location of the bit image undetermined, comprising:
In the geographic coordinate system where the corresponding geographical location of each target image, it is based on each target image pair
The geographical location answered determines target area respectively；
According to scheduled rule, selection target geographical location is corresponding as the bit image undetermined in each target area respectively
Geographical location.
8. the method according to the description of claim 7 is characterized in that this method further include:
The corresponding geographical location of multiple bit images undetermined is sent to terminal；
The geographical location for receiving terminal selection generates guidance path according to the geographical location of terminal selection；
The guidance path is sent to terminal to show.
9. a kind of image positioning device, which is characterized in that described device includes:
Image collection module, for obtaining bit image undetermined；
Similar image searching module, for obtaining multiple similar images with the images match to be positioned by images match；
Geographical location obtains module, for obtaining the corresponding geographical location of the similar image；
Image PHM packet handling module, for being grouped according to the geographical location of acquisition to similar image；
Target image determining module, for obtaining the maximum phase of similarity with the bit image undetermined in every group of similar image
Like image as target image；
Localization process module, for determining that the bit image undetermined is corresponding according to the corresponding geographical location of each target image
Geographical location.
10. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In when the processor executes the computer program the step of any one of realization claim 1~8 the method.
11. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method according to any one of claims 1 to 8 is realized when being executed by processor.
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 true CN110503123A (en) | 2019-11-26 |
| CN110503123B 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) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111159459A (en) * | 2019-12-04 | 2020-05-15 | 恒大新能源汽车科技(广东)有限公司 | Landmark positioning method, 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 (15)
| 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 |
| JP2008310446A (en) * | 2007-06-12 | 2008-12-25 | Panasonic Corp | Image retrieval system |
| US20090161962A1 (en) * | 2007-12-20 | 2009-06-25 | Gallagher Andrew C | Grouping images by location |
| US20110243457A1 (en) * | 2010-03-31 | 2011-10-06 | Aisin Aw Co., Ltd. | Scene matching reference data generation system and position measurement system |
| US20110242319A1 (en) * | 2010-03-31 | 2011-10-06 | Aisin Aw Co., Ltd. | Image processing system and position measurement system |
| US20120076427A1 (en) * | 2010-09-24 | 2012-03-29 | Stacie L Hibino | Method of selecting important digital images |
| 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 |
| US20160179846A1 (en) * | 2014-12-18 | 2016-06-23 | Kabushiki Kaisha Toshiba | Method, system, and computer readable medium for grouping and providing collected image content |
| US9613455B1 (en) * | 2014-11-02 | 2017-04-04 | Google Inc. | Local georeferenced data |
| 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 |
| 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 |
| 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 (15)
| 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 |
| JP2008310446A (en) * | 2007-06-12 | 2008-12-25 | Panasonic Corp | Image retrieval system |
| US20090161962A1 (en) * | 2007-12-20 | 2009-06-25 | Gallagher Andrew C | Grouping images by location |
| US20110242319A1 (en) * | 2010-03-31 | 2011-10-06 | Aisin Aw Co., Ltd. | Image processing system and position measurement system |
| US20110243457A1 (en) * | 2010-03-31 | 2011-10-06 | Aisin Aw Co., Ltd. | Scene matching reference data generation system and position measurement system |
| US20120076427A1 (en) * | 2010-09-24 | 2012-03-29 | Stacie L Hibino | Method of selecting important digital images |
| 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 |
| US20160179846A1 (en) * | 2014-12-18 | 2016-06-23 | Kabushiki Kaisha Toshiba | Method, system, and computer readable medium for grouping and providing collected image content |
| 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 |
| 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 |
| 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 |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111159459A (en) * | 2019-12-04 | 2020-05-15 | 恒大新能源汽车科技(广东)有限公司 | Landmark positioning method, device, computer equipment and storage medium |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110503123B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110645986B (en) | Positioning method and device, terminal and storage medium | |
| CN103440318B (en) | The landscape identifying system of mobile terminal | |
| CN102647449B (en) | Based on the intelligent photographic method of cloud service, device and mobile terminal | |
| CN101924992B (en) | Method, system and equipment for acquiring scene information through mobile terminal | |
| US8768107B2 (en) | Matching an approximately located query image against a reference image set | |
| CN109520500B (en) | Accurate positioning and street view library acquisition method based on terminal shooting image matching | |
| CN103226575A (en) | Image processing method and device | |
| US8774527B1 (en) | Matching an approximately located query image against a reference image set using cellular base station and wireless access point information | |
| CN103067856A (en) | Geographic position locating method and system based on image recognition | |
| Fedorov et al. | A framework for outdoor mobile augmented reality and its application to mountain peak detection | |
| CN103249142A (en) | Locating method, locating system and mobile terminal | |
| KR100971778B1 (en) | Method, system and computer-readable recording medium for matching of panoramic image using graph structure | |
| CN105005960A (en) | Method, apparatus and system for obtaining watermarking picture | |
| JPWO2012046671A1 (en) | Positioning system | |
| CN111664848B (en) | Multi-mode indoor positioning navigation method and system | |
| CN108876806A (en) | Method for tracking target and system, storage medium and equipment based on big data analysis | |
| CN110503123A (en) | Image position method, device, computer equipment and storage medium | |
| US20150130833A1 (en) | Map superposition method and electronic device | |
| CN110095119A (en) | Distributing indoor locating system and distributing indoor orientation method | |
| CN111159459B (en) | Landmark positioning method, landmark positioning device, computer equipment and storage medium | |
| CN111527375B (en) | Planning method and device for surveying and mapping sampling point, control terminal and storage medium | |
| US20210390737A1 (en) | Location determination in a gps-denied environment with user annotation | |
| KR20180133052A (en) | Method for authoring augmented reality contents based on 360 degree image and video | |
| CN110796706A (en) | Visual positioning method and system | |
| CN116228860A (en) | Target geographic position prediction method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |