CN105701767A - Panoramic image constructing device and method - Google Patents
Panoramic image constructing device and method Download PDFInfo
- Publication number
- CN105701767A CN105701767A CN201410709262.5A CN201410709262A CN105701767A CN 105701767 A CN105701767 A CN 105701767A CN 201410709262 A CN201410709262 A CN 201410709262A CN 105701767 A CN105701767 A CN 105701767A
- Authority
- CN
- China
- Prior art keywords
- image
- bunch
- panoramic picture
- described image
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The present invention relates to a panoramic image constructing device and method. The device comprises a search module which is configured to search images which are associated with the keyword which expresses scene information in a network, an extracting module which is configured to extract the feature of the image, an generating module which is configured to cluster the images according to the feature and generate image clusters, and a connecting module which is configured to connecting the image clusters so as to construct a panoramic image. Through the device and the method, the obtainment of the associated images for constructing the panoramic image can be completed without human labor, the construction of the panoramic image is no longer dependent on GPS information, a user can construct the panoramic image of any time, and the construction of the panoramic image is not limited by location and landscape information but extends to any dynamic scene.
Description
Technical field
The present invention relates to a kind of panoramic picture construction device and method。
Background technology
There is the overlapping technology that image mosaic is general image as a kind of by one group in panoramic picture constructing technology, is widely used in a lot of fields, for instance be applied to the synthesis of panorama landscape, 3D digital map navigation, remote sensing images reconstruction etc.。But traditional panoramic picture constructing technology splices mainly for several given superimposed images, for instance, utilize image acquisition and splicing that handheld camera carries out along fixed-direction。
There is following defect in these methods: 1., when the image deficiency gathered, 360 degree of panoramas are by not available；2. people is that to select sliceable image be necessary step。Meanwhile, although " streetscape " technology is widely used in scene panorama, it yet suffers from following defect: 1. the GPS information of dependency graph picture；2. can only give the panorama of the scene of certain special time (acquisition time such as image)；3. it is generally used for the panorama of the images such as landscape place, and the panorama mosaic of multitask scene (such as scenes such as activity, celebrations) can not be given。
For the defect existed in prior art, it is proposed to the application。
Summary of the invention
Brief overview about the present invention given below, in order to the basic comprehension about certain aspects of the invention is provided。Should be appreciated that this general introduction is not that the exhaustive about the present invention is summarized。It is not intended to determine the key of the present invention or pith, and nor is it intended to limit the scope of the present invention。It is only intended to and provides some concept in simplified form, in this, as the preamble in greater detail discussed after a while。
One main purpose of the present invention is in that to provide a kind of panoramic picture construction device and method, to overcome or alleviated by existing problem。
According to an aspect of the invention, it is provided a kind of panoramic picture construction device, including: search module, it is configured on network and searches for the image relevant to the keyword representing scene information；Extraction module, is configured to extract the feature of the described image searched；Generation module, is configured to by being clustered by the described image searched according to described feature, generates image bunch；And concatenation module, it is configured to splice described image bunch, to build panoramic picture。
According to another aspect of the present invention, it is provided that a kind of panoramic picture construction method, including search is relevant with the keyword of expression scene information on network image；Extract the feature of the described image searched；By being clustered by the described image searched according to described feature, generate image bunch；And described image bunch is spliced, to build panoramic picture。
It addition, embodiments of the invention additionally provide the computer program for realizing said method。
Additionally, embodiments of the invention additionally provide the computer program of at least computer-readable medium form, on it, record has the computer program code for realizing said method。
Method and apparatus according to embodiments of the present invention。Acquisition for building the associated picture of panoramic picture need not be accomplished manually, the structure of panoramic picture eliminates the reliance on GPS information, user can build the panoramic picture of any time, and the structure of panoramic picture is no longer limited to place, landscape information, but extends to any dynamic scene。
By below in conjunction with the accompanying drawing detailed description to highly preferred embodiment of the present invention, these and the further advantage of the present invention will be apparent from。
Accompanying drawing explanation
Below with reference to the accompanying drawings illustrate embodiments of the invention, the above and other objects, features and advantages of the present invention can be more readily understood that。Parts in accompanying drawing are intended merely to and illustrate principles of the invention。In the accompanying drawings, same or similar technical characteristic or parts will adopt same or similar accompanying drawing labelling to represent。
Fig. 1 is the flow chart schematically showing panoramic picture construction method according to an embodiment of the invention；
Fig. 2 illustrates the example of Affinity diagram；
Fig. 3 is the block diagram schematically showing panoramic picture construction device according to an embodiment of the invention；
Fig. 4 is the block diagram of a kind of possible exemplary construction schematically showing the concatenation module in Fig. 3；
Fig. 5 is the block diagram of a kind of possible exemplary construction schematically showing the Affinity diagram construction unit in Fig. 4；
Fig. 6 is the block diagram of a kind of possible exemplary construction schematically showing the concatenation unit in Fig. 4；
Fig. 7 is the block diagram schematically showing panoramic picture construction device according to another embodiment of the present invention；
Fig. 8 is the block diagram schematically showing panoramic picture construction device according to still another embodiment of the invention；And
Fig. 9 illustrates the structure chart of the citing of the computing equipment that may be used for panoramic picture construction method and the device implementing the present invention。
Detailed description of the invention
Embodiments of the invention are described with reference to the accompanying drawings。Can combine with the element shown in one or more other accompanying drawing or embodiment and feature at the element described in the accompanying drawing of the present invention or a kind of embodiment and feature。It should be noted that, for purposes of clarity, accompanying drawing and eliminate expression and the description of unrelated to the invention, parts known to persons of ordinary skill in the art and process in illustrating。
Fig. 1 is the flow chart schematically showing panoramic picture construction method according to an embodiment of the invention。Referring to Fig. 1, panoramic picture construction method according to an embodiment of the invention is described。
In step S101, the image that search is relevant to the keyword representing scene information on network。Specifically, user can input keyword on the networks such as such as the Internet, and this keyword is usually scene information。Then the image that search is relevant to this keyword on that network。By searching for, it is possible to find substantial amounts of associated picture。If the associated picture lazy weight found, then other image library can also be used to obtain enough associated pictures。
In step s 102, the feature of the image searched is extracted。Specifically, such as SURF (Speed-UpRobustFeatures can be passed through, accelerate robust features), SIFT (Scale-invariantFeatureTransform, scale invariant feature is changed), the feature operator image to searching such as FREAK (FastRetinaKeypoint, quick retina key point) feature carry out feature extraction。
In step s 103, by being clustered by the image searched according to the feature extracted, generate image bunch。Alternatively, in cluster process, if there is the image of image tag or Time Inconsistency, then by the image of this image tag or Time Inconsistency, on network searched to the little image of frequency filter。Alternatively, above-mentioned keyword can include image tag and at least one in the time further。If keyword includes image tag and at least one in the time, then before clustering, it is possible to be filtered by the image that in the image searched and image tag or time are not inconsistent。
In step S104, image bunch is spliced, to build panoramic picture。
Specifically, in the process spliced, match each other to build Affinity diagram by the image in image bunch being carried out by image bunch, wherein, the summit of Affinity diagram is one of image in image bunch, and the limit of Affinity diagram represents there is matching relationship between summit, and the weight on limit is the matching degree of image。It is alternatively possible to first the multiimage in image bunch is merged, so that being absent from multiimage in image bunch。Then, the image in the image bunch of merging treatment is matched each other, to build Affinity diagram。
Finally, by Affinity diagram, image bunch is spliced。Specifically, based on the searched frequency arrived on each comfortable network of the image in image bunch, the image in image bunch is ranked up, wherein, using image in image bunch, that the searched frequency arrived is the highest on network as datum mark。Then, based on datum mark, by Affinity diagram is carried out dynamic programming, it is determined that the splicing relation of the image in Affinity diagram, the connecting method minimum to obtain matching error。Such as, Fig. 2 illustrates the example of Affinity diagram。By Affinity diagram is carried out dynamic programming, it is determined that the splicing relation of image in Affinity diagram, obtain the connecting method that matching error is minimum。Such as, in above-mentioned DP process, it is possible to use following formula 1:
Formula 1
viIt is the forerunner summit of summit i, WijIt is connect the weight on the limit of summit i and j, represents the matching degree of i and j, IiAnd IjRepresenting the image of summit i and j respectively, N (i) is all of its neighbor summit of summit i。By Affinity diagram, select the optimum splicing transition matrix between summit, to realize panoramic picture synthesis。Then, with the connecting method that obtained matching error is minimum, image bunch is spliced。
It is of course also possible to manually delete the one or more images constituting panoramic picture。And based on other image not deleted, that constitute in the image of panoramic picture and the image that searches, rebuild panoramic picture。
Panoramic picture construction method according to embodiments of the present invention, the acquisition of the associated picture building panoramic picture need not be accomplished manually, the structure of panoramic picture eliminates the reliance on GPS information, user can build the panoramic picture of any time, and the structure of panoramic picture is no longer limited to place, landscape information, but extends to any dynamic scene。
Referring to Fig. 3, panoramic picture construction device 300 according to an embodiment of the invention is described。
Fig. 3 is the block diagram schematically showing panoramic picture construction device 300 according to an embodiment of the invention。Wherein, illustrate only part closely-related with the present invention for brevity。In panoramic picture construction device 300, it is possible to perform above with reference to the panoramic picture construction method described by Fig. 1。As it is shown on figure 3, panoramic picture construction device 300 can include search module 301, extraction module 302, generation module 303 and concatenation module 304。
Specifically, search module 301 can search for the image relevant to the keyword representing scene information on network。This keyword can also include image tag and at least one in the time。Extraction module 302 can extract the feature of the image searched。Generation module 303 can pass through to be clustered by the image searched according to this feature, generates image bunch。Image bunch can be spliced by concatenation module 304, to build panoramic picture。
It addition, generation module 303 can in cluster process, if there is the image of image tag or Time Inconsistency, then by the image of image tag or Time Inconsistency, on network searched to the little image of frequency filter。
A kind of possible exemplary construction of concatenation module 304 in Fig. 3 is described referring to Fig. 4。
Fig. 4 is the block diagram of a kind of possible exemplary construction schematically showing the concatenation module 304 in Fig. 3。As shown in Figure 4, concatenation module 304 may further include Affinity diagram construction unit 401 and concatenation unit 402。
Specifically, image in image bunch can be matched each other to build Affinity diagram by Affinity diagram construction unit 401, and wherein, the summit of Affinity diagram is one of image in image bunch, the limit of Affinity diagram represents there is matching relationship between summit, and the weight on limit is the matching degree of the image in image bunch。
Concatenation unit 402 can pass through Affinity diagram and be spliced by image bunch。
A kind of possible exemplary construction of Affinity diagram construction unit 401 in Fig. 4 is described referring to Fig. 5。
Fig. 5 is the block diagram of a kind of possible exemplary construction schematically showing the Affinity diagram construction unit 401 in Fig. 4。As it is shown in figure 5, Affinity diagram construction unit 401 may further include merging unit 501 and matching unit 502。
Specifically, merging unit 501 can merge the multiimage in image bunch, so that being absent from multiimage in image bunch。Image in the image bunch of merging treatment can be matched each other by matching unit 502, to build Affinity diagram。
A kind of possible exemplary construction of concatenation unit 402 in Fig. 4 is described referring to Fig. 6。
Fig. 6 is the block diagram of a kind of possible exemplary construction schematically showing the concatenation unit 402 in Fig. 4。As shown in Figure 6, concatenation unit 402 may further include sequence subelement 601, connecting method determines subelement 602 and splicing subelement 603。
Specifically, the image in image bunch based on the searched frequency arrived on each comfortable network of the image in image bunch, can be ranked up by sequence subelement 601, wherein, using image in image bunch, that the searched frequency arrived is the highest on network as datum mark。
Connecting method determine subelement 602 can based on datum mark, by Affinity diagram is carried out dynamic programming, it is determined that the splicing relation of the image in Affinity diagram, the connecting method minimum to obtain matching error。
Image bunch can be spliced by splicing subelement 603 with connecting method。
Fig. 7 is the block diagram schematically showing panoramic picture construction device 700 according to another embodiment of the present invention。As it is shown in fig. 7, panoramic picture construction device 700 may further include filtering module 701。The image that in the image searched and image tag or time are not inconsistent before generation module 303 clusters, can be filtered by filtering module 701。
Fig. 8 is the block diagram schematically showing panoramic picture construction device 800 according to still another embodiment of the invention。As shown in Figure 8, panoramic picture construction device 800 may further include manual removing module 801 and panoramic picture reconstruction module 802。
Specifically, manual removing module 801 can manually delete the one or more images constituting panoramic picture。Panoramic picture rebuilds module 802 based on other image in image not deleted, that constitute panoramic picture and the image searched, can rebuild panoramic picture。
Panoramic picture construction device according to embodiments of the present invention, the acquisition of the associated picture building panoramic picture need not be accomplished manually, the structure of panoramic picture eliminates the reliance on GPS information, user can build the panoramic picture of any time, and the structure of panoramic picture is no longer limited to place, landscape information, but extends to any dynamic scene。
The ultimate principle of the present invention is described above in association with specific embodiment, but, it is to be noted, for those of ordinary skill in the art, it will be appreciated that whole or any steps of methods and apparatus of the present invention or parts, can in any calculation element (including processor, storage medium etc.) or the network of calculation element, being realized with hardware, firmware, software or their combination, this is that those of ordinary skill in the art use their basic programming skill can be achieved with when the explanation having read the present invention。
Therefore, the purpose of the present invention can also be realized by one program of operation or batch processing on any calculation element。Calculation element can be known fexible unit。Therefore, the purpose of the present invention can also realize only by the program product providing the program code comprising the method for realization or device。It is to say, such program product also constitutes the present invention, and storage has the storage medium of such program product also to constitute the present invention。Obviously, storage medium can be any known storage medium or any storage medium developed in the future。
When realizing embodiments of the invention by software and/or firmware, from storage medium or network to the computer with specialized hardware structure, such as the general purpose computer 900 shown in Fig. 9 installs the program constituting this software, this computer is when being provided with various program, it is possible to perform various function etc.。
In fig .9, CPU (CPU) 901 is according to the program stored in read only memory (ROM) 902 or the program various process of execution being loaded into random access memory (RAM) 903 from storage part 908。In RAM903, also according to needing to store the data required when CPU901 performs various process etc.。CPU901, ROM902 and RAM903 are via bus 904 link each other。Input/output interface 905 also link is to bus 904。
Components described below link is to input/output interface 905: importation 906 (including keyboard, mouse etc.), output part 907 (include display, such as cathode ray tube (CRT), liquid crystal display (LCD) etc., and speaker etc.), storage part 908 (including hard disk etc.), communications portion 909 (including NIC such as LAN card, modem etc.)。Communications portion 909 performs communication process via network such as the Internet。As required, driver 910 also can link to input/output interface 905。Detachable media 911 such as disk, CD, magneto-optic disk, semiconductor memory etc. are installed in driver 910 as required so that the computer program read out is installed in storage part 908 as required。
When realizing above-mentioned series of processes by software, the program constituting software is installed from network such as the Internet or storage medium such as detachable media 911。
It will be understood by those of skill in the art that this storage medium be not limited to shown in Fig. 9 wherein have program stored therein and equipment distributes the detachable media 911 of the program that provides a user with separately。The example of detachable media 911 comprises disk (comprising floppy disk (registered trade mark)), CD (comprising compact disc read-only memory (CD-ROM) and digital universal disc (DVD)), magneto-optic disk (comprising mini-disk (MD) (registered trade mark)) and semiconductor memory。Or, storage medium can be hard disk of comprising etc., wherein computer program stored in ROM902, storage part 908, and is distributed to user together with the equipment comprising them。
The present invention also proposes the program product that a kind of storage has the instruction code of machine-readable。When instruction code is read by machine and performs, above-mentioned method according to embodiments of the present invention can be performed。
Correspondingly, the storage medium being used for carrying the program product of the instruction code that above-mentioned storage has machine-readable is also included within disclosure of the invention。Storage medium includes but not limited to floppy disk, CD, magneto-optic disk, storage card, memory stick etc.。
It addition, some is for the method and apparatus of tool kit according to an embodiment of the invention, it is possible to expand the use scope of combination。
It should be appreciated by those skilled in the art that in this exemplified being illustrative of, the invention is not limited in this。
Software, firmware, hardware or its combination is may be embodied as an example, each step of said method and all modules of the said equipment and/or unit, and as the part in relevant device。In said apparatus all modules, unit when being configured by the mode of software, firmware, hardware or its combination spendable specific means or mode be well known to those skilled in the art, do not repeat them here。
As an example, when being realized by software or firmware, to the computer (such as the general purpose computer 900 shown in Fig. 9) with specialized hardware structure, the program constituting this software can be installed from storage medium or network, this computer is when being provided with various program, it is possible to perform various functions etc.。
Herein above in the description of the specific embodiment of the invention, the feature described for a kind of embodiment and/or illustrate can use in one or more other embodiment in same or similar mode, combined with the feature in other embodiment, or substitute the feature in other embodiment。
It should be emphasized that term " include/comprise " refers to the existence of feature, key element, step or assembly herein when using, but it is not precluded from the existence of one or more further feature, key element, step or assembly or additional。
Additionally, the method for the present invention be not limited to specifications described in time sequencing perform, it is also possible to according to other time sequencing ground, concurrently or independently executable。Therefore, the technical scope of the present invention is not construed as limiting by the execution sequence of the method described in this specification。
Although the present invention having been disclosed already by the description of specific embodiments of the invention above, however, it is to be understood that those skilled in the art can design the various amendments to the present invention, improvement or equivalent in the spirit and scope of claims。These amendments, improvement or equivalent should also be as being to be considered as included in protection scope of the present invention。
About the embodiment including above example, also disclose following remarks:
1. 1 kinds of panoramic picture construction devices of remarks, including:
Search module, is configured on network and searches for the image relevant to the keyword representing scene information；
Extraction module, is configured to extract the feature of the described image searched；
Generation module, is configured to by being clustered by the described image searched according to described feature, generates image bunch；And
Concatenation module, is configured to splice described image bunch, to build panoramic picture。
The remarks 2. panoramic picture construction device according to remarks 1, wherein, described concatenation module farther includes:
Affinity diagram construction unit, it is configured to match each other to build Affinity diagram by the image in described image bunch, wherein, the summit of described Affinity diagram is one of image in described image bunch, the limit of described Affinity diagram represents there is matching relationship between described summit, and the weight on described limit is the matching degree of the image in described image bunch；And
Concatenation unit, is configured to be spliced by described image bunch by described Affinity diagram。
The remarks 3. panoramic picture construction device according to remarks 2, wherein, described Affinity diagram construction unit farther includes:
Merging subelement, being configured to merge the multiimage in described image bunch, so that being absent from multiimage in described image bunch；And
Coupling subelement, is configured to match each other the image in the described image bunch of merging treatment, to build Affinity diagram。
The remarks 4. panoramic picture construction device according to remarks 2, wherein, described concatenation unit farther includes:
Sequence subelement, it is configured to based on the searched frequency arrived on each comfortable network of the image in described image bunch, image in described image bunch is ranked up, wherein, using image in described image bunch, that the searched frequency arrived is the highest on network as datum mark；
Connecting method determines subelement, is configured to based on described datum mark, by described Affinity diagram is carried out dynamic programming, it is determined that the splicing relation of the image in described Affinity diagram, the connecting method minimum to obtain matching error；And
Splicing subelement, is configured to be spliced by described image bunch with described connecting method。
The remarks 5. panoramic picture construction device according to any one in remarks 1 to 4, wherein, described generation module is in cluster process, if there is the image of image tag or Time Inconsistency, then by the image of described image tag or Time Inconsistency, on network searched to the little image of frequency filter。
The remarks 6. panoramic picture construction device according to any one in remarks 1 to 4, wherein, described keyword also includes image tag and at least one in the time。
The remarks 7. panoramic picture construction device according to remarks 6, farther includes:
Filtering module, is configured to before described generation module clusters, and is filtered by the image that in the described image searched and image tag or time are not inconsistent。
The remarks 8. panoramic picture construction device according to any one in remarks 1 to 4, farther includes:
Manual removing module, is configured to manually delete the one or more images constituting described panoramic picture；And
Panoramic picture rebuilds module, is configured to, based on other image in image not deleted, that constitute described panoramic picture and the described image that searches, rebuild panoramic picture。
9. 1 kinds of panoramic picture construction methods of remarks, including:
The image that search is relevant to the keyword representing scene information on network；
Extract the feature of the described image searched；
By being clustered by the described image searched according to described feature, generate image bunch；And
Described image bunch is spliced, to build panoramic picture。
The remarks 10. panoramic picture construction method according to remarks 9, wherein, carries out splicing by described image bunch and farther includes:
Match each other to build Affinity diagram by the image in described image bunch, wherein, the summit of described Affinity diagram is one of image in described image bunch, and the limit of described Affinity diagram represents there is matching relationship between described summit, and the weight on described limit is the matching degree of the image in described image bunch；And
By described Affinity diagram, described image bunch is spliced。
The remarks 11. panoramic picture construction method according to remarks 10, wherein, matches each other to build Affinity diagram by the image in described image bunch and farther includes:
Multiimage in described image bunch is merged, so that being absent from multiimage in described image bunch；And
Image in the described image bunch of merging treatment is matched each other, to build Affinity diagram。
The remarks 12. panoramic picture construction method according to remarks 10, wherein, carries out splicing by described Affinity diagram by described image bunch and farther includes:
Based on the searched frequency arrived on each comfortable network of the image in described image bunch, the image in described image bunch is ranked up, wherein, using image in described image bunch, that the searched frequency arrived is the highest on network as datum mark；
Based on described datum mark, by described Affinity diagram is carried out dynamic programming, it is determined that the splicing relation of the image in described Affinity diagram, the connecting method minimum to obtain matching error；And
With described connecting method, described image bunch is spliced。
The remarks 13. panoramic picture construction method according to any one in remarks 9 to 12, wherein, in cluster process, if there is the image of image tag or Time Inconsistency, then by the image of described image tag or Time Inconsistency, on network searched to the little image of frequency filter。
The remarks 14. panoramic picture construction method according to any one in remarks 9 to 12, wherein, described keyword also includes image tag and at least one in the time。
The remarks 15. panoramic picture construction method according to remarks 14, wherein, before clustering, is filtered the image that in the described image searched and image tag or time are not inconsistent。
The remarks 16. panoramic picture construction method according to any one in remarks 9 to 12, further comprising the steps of:
Manually delete the one or more images constituting described panoramic picture；And
Based on other image in image not deleted, that constitute described panoramic picture and the described image that searches, rebuild panoramic picture。
Claims (10)
1. a panoramic picture construction device, including:
Search module, is configured on network and searches for the image relevant to the keyword representing scene information；
Extraction module, is configured to extract the feature of the described image searched；
Generation module, is configured to by being clustered by the described image searched according to described feature, generates image bunch；And
Concatenation module, is configured to splice described image bunch, to build panoramic picture。
2. panoramic picture construction device according to claim 1, wherein, described concatenation module farther includes:
Affinity diagram construction unit, it is configured to match each other to build Affinity diagram by the image in described image bunch, wherein, the summit of described Affinity diagram is one of image in described image bunch, the limit of described Affinity diagram represents there is matching relationship between described summit, and the weight on described limit is the matching degree of the image in described image bunch；And
Concatenation unit, is configured to be spliced by described image bunch by described Affinity diagram。
3. panoramic picture construction device according to claim 2, wherein, described Affinity diagram construction unit farther includes:
Merging subelement, being configured to merge the multiimage in described image bunch, so that being absent from multiimage in described image bunch；And
Coupling subelement, is configured to match each other the image in the described image bunch of merging treatment, to build Affinity diagram。
4. panoramic picture construction device according to claim 2, wherein, described concatenation unit farther includes:
Sequence subelement, it is configured to based on the searched frequency arrived on each comfortable network of the image in described image bunch, image in described image bunch is ranked up, wherein, using image in described image bunch, that the searched frequency arrived is the highest on network as datum mark；
Connecting method determines subelement, is configured to based on described datum mark, by described Affinity diagram is carried out dynamic programming, it is determined that the splicing relation of the image in described Affinity diagram, the connecting method minimum to obtain matching error；And
Splicing subelement, is configured to be spliced by described image bunch with described connecting method。
5. panoramic picture construction device according to claim 1, wherein, described generation module is in cluster process, if there is the image of image tag or Time Inconsistency, then by the image of described image tag or Time Inconsistency, on network searched to the little image of frequency filter。
6. panoramic picture construction device according to claim 1, wherein, described keyword also includes image tag and at least one in the time。
7. panoramic picture construction device according to claim 6, farther includes:
Filtering module, is configured to before described generation module clusters, and is filtered by the image that in the described image searched and image tag or time are not inconsistent。
8. panoramic picture construction device according to claim 1, farther includes:
Manual removing module, is configured to manually delete the one or more images constituting described panoramic picture；And
Panoramic picture rebuilds module, is configured to, based on other image in image not deleted, that constitute described panoramic picture and the described image that searches, rebuild panoramic picture。
9. a panoramic picture construction method, including:
The image that search is relevant to the keyword representing scene information on network；
Extract the feature of the described image searched；
By being clustered by the described image searched according to described feature, generate image bunch；And
Described image bunch is spliced, to build panoramic picture。
10. panoramic picture construction method according to claim 9, wherein, carries out splicing by described image bunch and farther includes:
Match each other to build Affinity diagram by the image in described image bunch, wherein, the summit of described Affinity diagram is one of image in described image bunch, and the limit of described Affinity diagram represents there is matching relationship between described summit, and the weight on described limit is the matching degree of the image in described image bunch；And
By described Affinity diagram, described image bunch is spliced。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410709262.5A CN105701767A (en) | 2014-11-28 | 2014-11-28 | Panoramic image constructing device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410709262.5A CN105701767A (en) | 2014-11-28 | 2014-11-28 | Panoramic image constructing device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105701767A true CN105701767A (en) | 2016-06-22 |
Family
ID=56230410
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410709262.5A Pending CN105701767A (en) | 2014-11-28 | 2014-11-28 | Panoramic image constructing device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105701767A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107045730A (en) * | 2017-03-06 | 2017-08-15 | 青岛鹏海软件有限公司 | A kind of multidimensional exhibition system and method for digital culture scene or image |
| TWI636424B (en) * | 2017-08-28 | 2018-09-21 | 鴻海精密工業股份有限公司 | Device and method for generating panorama image |
| CN110019886A (en) * | 2017-08-28 | 2019-07-16 | 富泰华工业（深圳）有限公司 | Full-view image generating means and method |
| CN110969574A (en) * | 2018-09-29 | 2020-04-07 | 广州汽车集团股份有限公司 | Vehicle-mounted panoramic map creation method and device |
| CN111984852A (en) * | 2019-05-21 | 2020-11-24 | 微软技术许可有限责任公司 | Generative image acquisition |
| CN114596413A (en) * | 2022-05-07 | 2022-06-07 | 武汉天际航信息科技股份有限公司 | Image time sequence splicing method, three-dimensional image model establishing method and device |
| CN116740325A (en) * | 2023-08-16 | 2023-09-12 | 广州和音科技文化发展有限公司 | Image stitching method and system based on exhibition hall scene three-dimensional effect design |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011101849A1 (en) * | 2010-02-17 | 2011-08-25 | Photoccino Ltd. | System and method for creating a collection of images |
| CN102426705A (en) * | 2011-09-30 | 2012-04-25 | 北京航空航天大学 | Behavior splicing method of video scene |
| CN103390275A (en) * | 2013-07-19 | 2013-11-13 | 香港应用科技研究院有限公司 | Dynamic image splicing method |
-
2014
- 2014-11-28 CN CN201410709262.5A patent/CN105701767A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011101849A1 (en) * | 2010-02-17 | 2011-08-25 | Photoccino Ltd. | System and method for creating a collection of images |
| CN102426705A (en) * | 2011-09-30 | 2012-04-25 | 北京航空航天大学 | Behavior splicing method of video scene |
| CN103390275A (en) * | 2013-07-19 | 2013-11-13 | 香港应用科技研究院有限公司 | Dynamic image splicing method |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107045730A (en) * | 2017-03-06 | 2017-08-15 | 青岛鹏海软件有限公司 | A kind of multidimensional exhibition system and method for digital culture scene or image |
| CN107045730B (en) * | 2017-03-06 | 2023-10-24 | 青岛鹏海软件有限公司 | Multi-dimensional display system and method for digital cultural scene or image |
| TWI636424B (en) * | 2017-08-28 | 2018-09-21 | 鴻海精密工業股份有限公司 | Device and method for generating panorama image |
| CN110019886A (en) * | 2017-08-28 | 2019-07-16 | 富泰华工业（深圳）有限公司 | Full-view image generating means and method |
| US10380719B2 (en) | 2017-08-28 | 2019-08-13 | Hon Hai Precision Industry Co., Ltd. | Device and method for generating panorama image |
| CN110969574A (en) * | 2018-09-29 | 2020-04-07 | 广州汽车集团股份有限公司 | Vehicle-mounted panoramic map creation method and device |
| CN111984852A (en) * | 2019-05-21 | 2020-11-24 | 微软技术许可有限责任公司 | Generative image acquisition |
| CN114596413A (en) * | 2022-05-07 | 2022-06-07 | 武汉天际航信息科技股份有限公司 | Image time sequence splicing method, three-dimensional image model establishing method and device |
| CN116740325A (en) * | 2023-08-16 | 2023-09-12 | 广州和音科技文化发展有限公司 | Image stitching method and system based on exhibition hall scene three-dimensional effect design |
| CN116740325B (en) * | 2023-08-16 | 2023-11-28 | 广州和音科技文化发展有限公司 | Image stitching method and system based on exhibition hall scene three-dimensional effect design |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105701767A (en) | Panoramic image constructing device and method | |
| US8676001B2 (en) | Automatic discovery of popular landmarks | |
| US10789418B2 (en) | Batch generation of links to documents based on document name and page content matching | |
| KR101494826B1 (en) | Error Checking System for Digital Map | |
| JP2008197814A (en) | Translation verification method, device, and program for resource file | |
| JP2011028757A (en) | Method and apparatus for representing and searching for an object in an image, and computer-readable storage medium for storing computer-executable process step for executing the method | |
| CN106293964A (en) | The call method of a kind of application program and device | |
| JP5426938B2 (en) | Information processing apparatus and information processing method | |
| CN111666100A (en) | Software framework generation method and device, electronic equipment and storage medium | |
| JP5275087B2 (en) | Program generating apparatus and block diagram generating apparatus | |
| KR20110125184A (en) | File server for extracting and displaying file list on client, method of providing display on client, and computer program executable on file server | |
| CN113268188B (en) | Task processing method, device, equipment and storage medium | |
| JP5587744B2 (en) | Program component search method, program component search system, and component search program | |
| JP2000276338A (en) | Method and system for visual programming, and recording medium for visual programming | |
| JP5600826B1 (en) | Unstructured data processing system, unstructured data processing method and program | |
| CN115439640A (en) | Virtual model cloning method and device | |
| CN106681965A (en) | Method and system for marking abnormal formula | |
| JP5846853B2 (en) | Support system, support method, and support program | |
| JP4895373B2 (en) | Software product reuse method and system | |
| JP2009134342A (en) | Function specification automatic generation device | |
| JP2017184139A (en) | Editing apparatus, editing method and program | |
| US20070136000A1 (en) | Apparatus and method for searching protein active site | |
| JP5898043B2 (en) | History information display program and history information display device | |
| CN115629787A (en) | Path sequence similarity calculation system and method for service flow model expansion tree | |
| JPH11175562A (en) | Information retrieving device and method therefor and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160622 |
|
| WD01 | Invention patent application deemed withdrawn after publication |