WO2016011763A1 - 图像展现方法、装置、设备及非易失性计算机存储介质 - Google Patents
图像展现方法、装置、设备及非易失性计算机存储介质 Download PDFInfo
- Publication number
- WO2016011763A1 WO2016011763A1 PCT/CN2014/093382 CN2014093382W WO2016011763A1 WO 2016011763 A1 WO2016011763 A1 WO 2016011763A1 CN 2014093382 W CN2014093382 W CN 2014093382W WO 2016011763 A1 WO2016011763 A1 WO 2016011763A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- candidate image
- image
- candidate
- tool
- images
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Definitions
- the present invention relates to a Location Based Service (LBS) technology, and more particularly to an image presentation method, apparatus, device, and non-volatile computer storage medium.
- LBS Location Based Service
- the terminal integrates more and more functions, so that the system function list of the terminal contains more and more corresponding applications (Application, APP).
- Some applications involve some Location Based Service (LBS), also known as location services, such as Baidu maps.
- LBS Location Based Service
- the server corresponding to the application stores a large number of Point of Interest (POI) data to provide an LBS query-based query result to the application, that is, the client.
- POI Point of Interest
- the interest point data may include text data of name information, category information, geographical location information (ie, longitude, latitude, etc.).
- the actual POI does not have an iconic name sign to explicitly indicate the POI, etc.
- the text data presented to the user may not satisfy the user's real
- the positioning intention is such that the user needs to perform the positioning operation repeatedly through the application, which increases the data interaction between the application and the query engine, thereby causing an increase in the processing load of the query engine.
- aspects of the present invention provide an image display method, apparatus, device, and non-volatile computer storage medium for reducing the processing load of a query engine.
- An aspect of the present invention provides an image display method, including:
- N candidate images are obtained as the recommended image
- M is an integer greater than or equal to 1
- N is greater than or equal to 1, according to the shooting position of each of the M candidate images and the position of the target object.
- the candidate image includes a first candidate image; and the obtained according to a shooting position of the M candidate images and a location where the target object is located Before N candidate images are used as recommended images, they also include:
- the candidate image further includes a second candidate image; the shooting position according to the M candidate images and the location of the target object, Before obtaining N candidate images as the recommended image, Also includes:
- the photographing position of the second candidate image is obtained according to the photographing position of the first candidate image, the relative positioning information of the photographing tool of the first candidate image, and the relative positioning information of the photographing tool of the second candidate image.
- the relative positioning information of the shooting tool and the relative positioning information of the shooting tool of the second candidate image include:
- the presenting the recommended image includes:
- the recommended image is presented in at least one of a map annotation manner and an image mode.
- an image display apparatus comprising:
- a location obtaining unit for obtaining a location of the target object
- an image obtaining unit configured to obtain N candidate images as the recommended image according to the shooting position of each of the M candidate images and the position of the target object, where M is an integer greater than or equal to 1, and N is An integer greater than or equal to 1, and less than or equal to M;
- a presentation unit for presenting the recommended image.
- the candidate image comprising a first candidate image; the device further comprising a positioning unit,
- the candidate image further includes a second candidate image; the positioning unit is further used to
- the recommended image is presented in at least one of a map annotation manner and an image mode.
- an apparatus comprising:
- One or more processors are One or more processors;
- One or more programs the one or more programs being stored in the memory, when executed by the one or more processors:
- N candidate images are obtained as the recommended image
- M is an integer greater than or equal to 1
- N is greater than or equal to 1, according to the shooting position of each of the M candidate images and the position of the target object.
- a nonvolatile computer storage medium storing one or more programs when the one or more programs are executed by a device causes The device:
- N candidate images are obtained as the recommended image
- M is an integer greater than or equal to 1
- N is greater than or equal to 1, according to the shooting position of each of the M candidate images and the position of the target object.
- the embodiment of the present invention obtains N candidate images according to the location where the target object is located, and then according to the shooting position of each candidate image in the M candidate images and the location of the target object, as a recommendation.
- An image, M is an integer greater than or equal to 1
- N is an integer greater than or equal to 1, and less than or equal to M, such that the recommended image can be presented, since the text data of the POI is no longer displayed, but the POI is also presented.
- the image data is such that the displayed POI data substantially satisfies the true positioning intention of the user. Therefore, the problem of increasing the data interaction between the application and the query engine caused by the user repeatedly querying through the application in the prior art can be avoided, thereby reducing the image data.
- the processing load of the query engine is such that the problem of increasing the data interaction between the application and the query engine caused by the user repeatedly querying through the application in the prior art.
- the text data of the POI is not only displayed, but the image data of the POI is also displayed, the displayed POI data substantially satisfies the true positioning intention of the user, and the positioning result can be effectively improved. Sex.
- the text data of the POI is not only displayed, but the image data of the POI is also displayed, the displayed POI data substantially satisfies the true positioning intention of the user, and the positioning efficiency can be effectively improved.
- FIG. 1 is a schematic flowchart diagram of an image display method according to an embodiment of the present invention
- FIG. 2 is a schematic diagram showing a distribution of candidate images in the embodiment corresponding to FIG. 1;
- FIG. 3 is a schematic diagram of a recommended image of a specified position in the embodiment corresponding to FIG. 1;
- FIG. 4 is a schematic structural diagram of an image display apparatus according to another embodiment of the present invention.
- FIG. 5 is a schematic structural diagram of an image display apparatus according to another embodiment of the present invention.
- the terminals involved in the embodiments of the present invention may include, but are not limited to, a mobile phone, a personal digital assistant (PDA), a wireless handheld device, a wireless netbook, a personal computer, a portable computer, a tablet computer, and an MP3 player. , MP4 players, wearable devices (for example, smart glasses, smart watches, smart bracelets, etc.).
- PDA personal digital assistant
- MP4 players wearable devices (for example, smart glasses, smart watches, smart bracelets, etc.).
- FIG. 1 is a schematic flowchart of an image display method according to an embodiment of the present invention, as shown in FIG. 1 .
- N candidate images as the recommended image according to the shooting position of each candidate image in the M candidate images and the location of the target object, where M is an integer greater than or equal to 1, and N is greater than or equal to 1. And an integer less than or equal to M.
- the execution body of 101 to 103 may be an application located at a local terminal, or may be a plug-in or a software development kit (SDK) or the like provided in an application located in the local terminal, or It can also be a query engine located in the network side server, which is not specifically limited in this embodiment.
- SDK software development kit
- the application may be a local application installed on the terminal (nativeApp), or may be a web application (webApp) of a browser on the terminal. This embodiment does not limit this.
- the so-called candidate image may refer to an image including a specified object, wherein the specified object may be understood as a designated POI or an iconic building thereof.
- the specified object may be understood as a designated POI or an iconic building thereof.
- attractions such as Tiananmen Square, the gates of scenic spots such as the gates of the Summer Palace, and other landmarks in the sights such as the White Tower in the North Sea.
- M is greater than or equal to 1
- N is an integer greater than or equal to 1, and less than or equal to M, such that the recommended image can be presented, since the text data of the POI is no longer only displayed, but the image data of the POI is also presented, so that the displayed POI
- the data substantially satisfies the user's true positioning intention. Therefore, the problem of increasing the data interaction between the application and the query engine caused by the user repeatedly querying through the application in the prior art can be avoided, thereby reducing the processing load of the query engine.
- various existing positioning technologies may be used to obtain a positioning result of the target object, that is, geographical location information of a location where the target object is located, for example, The longitude, the latitude, and the like are not particularly limited in this embodiment.
- positioning technologies such as Global Positioning System (GPS) technology, Wireless Fidelity (Wi-Fi) positioning technology, or base station positioning technology.
- GPS Global Positioning System
- Wi-Fi Wireless Fidelity
- a target object can be understood as a user whose current location is intended to be a nearby POI.
- the M candidate images that are involved in the foregoing may be obtained in multiple manners, which is not specifically limited in this embodiment.
- Tiananmen Take Tiananmen as an example. You can use the search keyword "Tiananmen" to make an inquiry. An image matching the search keyword is obtained as a candidate image. Alternatively, an image including the entity of Tiananmen sent by another terminal may be directly received as a candidate image.
- the geographic location information of the location of each candidate image in the M candidate images may be specifically determined according to the geographic location information of the location where the target object is located.
- the distance between the position and the photographing position is calculated, and further, N candidate images can be determined as the recommended image based on the distance.
- the corresponding candidate image may be determined as the recommended image;
- the distance threshold indicates that the position is farther from the POI displayed by the corresponding candidate image, and the corresponding candidate image may be ignored, that is, the corresponding candidate image is not determined as the recommended image.
- the candidate image may include a first candidate image; and correspondingly, before 102, a first candidate image where the specified object is located may be specifically obtained, and according to the The Exchangeable Image File Format (EXIF) information of the first candidate image obtains a shooting position of the first candidate image.
- EXIF The Exchangeable Image File Format
- the so-called designated object is all or part of a POI.
- the shooting position of the candidate image that is, the geographical position information of the shooting position can be directly obtained by using the EXIF information of the candidate image.
- the geographical position information of the obtained shooting position of the candidate image can be associated with the candidate image, and the association relationship can be recorded.
- the shooting position of each candidate image can be obtained based on the association relationship.
- EXIF is an image file format, and its data storage is exactly the same as the Joint Photographic Experts Group (JPEG) format.
- EXIF inserts a set of shooting parameters in the head of the JPEG format, which can be called EXIF information.
- the EXIF information can selectively include various apertures, shutters, white balance, sensitivity (ISO), focal length, date and time, and other information related to the current shooting conditions, as well as the brand, model, color coding of the shooting tool. Other information such as the sound recorded during shooting, the thumbnail, and the GPS parameters of the shooting position. Therefore, the EXIF format image can be browsed by any viewing software capable of viewing images in JPEG format, but not all graphics programs can process EXIF information.
- Some candidate images have EXIF information, and the EXIF information may also include GPS parameters of the shooting position. Therefore, such candidate images can directly obtain the shooting position of the candidate images by using the EXIF information of the candidate images.
- the candidate image may further include a second candidate image in addition to the first candidate image.
- a second candidate image in which the specified object is located may be specifically obtained, and then three-dimensional reconstruction processing is performed according to the first candidate image and the second candidate image to obtain the first candidate image.
- the relative positioning information of the photographing tool and the relative positioning information of the photographing tool of the second candidate image enable enabling according to the photographing position of the first candidate image, the relative positioning information of the photographing tool of the first candidate image, and the The relative positioning information of the photographing tool of the second candidate image is obtained, and the photographing position of the second candidate image is obtained.
- the number of the first candidate images may be one, or may be multiple.
- the number of the second candidate images may be one, or may be plural. This embodiment is not particularly limited.
- the three-dimensional reconstruction process is performed according to the first candidate image and the second candidate image, and any method in the prior art may be used, which is not specifically limited in this embodiment.
- the first candidate image may be subjected to feature extraction processing to obtain feature information of the first candidate image, and feature extraction processing on the second candidate image to obtain the second candidate image.
- Feature information “the feature extraction process of the first candidate image” and the “feature extraction process of the second candidate image” are performed in a non-fixed execution order, and the feature extraction process may be performed on the first candidate image.
- the feature extraction process may be performed on the second candidate image, and then the feature extraction process may be performed on the first candidate image.
- This embodiment is not particularly limited.
- the feature matching values between the two candidate images may be respectively calculated for all the candidate images, that is, all the first candidate images and all the second candidate images, and then the pixels on each candidate image are determined according to the feature matching values. Correspondence between them.
- the two two here are Refers to any two candidate images, which may be one first candidate image and another first candidate image, or may also be one first candidate image and one second candidate image, or may also be one second candidate image and another
- the second candidate image is not particularly limited in this embodiment.
- the basic matrix between the two candidate images can be separately calculated for all the candidate images, that is, all the first candidate images and all the second candidate images, and then the basic matrix is used to filter the incorrect candidate images.
- the two-two refers to any two candidate images, which may be one first candidate image and another first candidate image, or may also be a first candidate image and a second candidate image, or may also be one
- the second candidate image and the other second candidate image are not particularly limited in this embodiment.
- the initial internal parameters of the shooting tool may include, but are not limited to, a focal length and coordinate information of the primary point.
- the focal length can be directly read from the EXIF information; the principal point refers to the intersection of the main optical axis and the image plane, and can be approximated by using the center of the candidate image.
- the relative positioning information is obtained by reference to a shooting tool of one of the candidate images.
- a photographing tool of a candidate image as a reference may be referred to as a reference photographing tool. That is to say, the relative positioning information of the photographing tool of the candidate image refers to the positioning information of the photographing tool of the candidate image with respect to the reference photographing tool.
- the depth of the pixel point can be obtained according to the relative positioning information of the shooting tools of the two candidate images, and then a set of three-dimensional information of the specified object and a shooting tool of the two candidate images are obtained according to the depth of the pixel point. Calculate the internal parameters.
- the relative positioning information of the new candidate image refers to the positioning information of the shooting tool of the new candidate image with respect to the reference shooting tool.
- another set of three-dimensionality of the designated object is obtained by the foregoing method.
- the internal parameters of the calculation tool for the information and the new candidate image is performed cyclically until relative positioning information of all new candidate images is obtained.
- the geographic location information may include, but is not limited to, longitude and dimensions, it may further include altitude. Since the altitude at which the photographer takes the POI is generally the same as the altitude of the POI, the altitude can be ignored during the calculation of the shooting position, and the longitude and latitude can be used as the geographical location information.
- the geographical position information of the shooting position of any two first candidate images that is, the geographical position information of the shooting position, the relative positioning information of the corresponding shooting tool, and the relative positioning information of the shooting tool of the second candidate image to be positioned.
- the location of the specified object can be obtained, the location of the specified object, the photographing position of the first candidate image, the first azimuth and the second may be further determined. Azimuth angle, the shooting position of the second candidate image is obtained.
- the geographical position information of the obtained shooting position of the candidate image can be associated with the candidate image, and the association relationship can be recorded.
- the shooting position of each candidate image can be obtained based on the association relationship.
- FIG. 2 a schematic diagram of a shooting position distribution of the candidate images, wherein the darkest central region is a hot spot region A in which the shooting position of the candidate image is concentrated, and the lightest edge region is the shooting position of the candidate image. Sparse non-hot spot area B.
- the recommended image may be displayed in at least one of a map labeling manner and an image mode, which is not specifically limited in this embodiment. .
- the recommended image may be presented to the user in a map annotation manner on an electronic map.
- the recommended image may be directly presented to the user in an image manner on an electronic map or other interface, as shown in FIG. 3 .
- M is greater than Or an integer equal to 1, N being an integer greater than or equal to 1, and less than or equal to M, such that the recommended image can be presented, since the text data of the POI is no longer displayed, but the image data of the POI is also presented.
- the displayed POI data substantially satisfies the user's true positioning intention. Therefore, the problem of increasing the data interaction between the application and the query engine caused by the user repeatedly querying through the application in the prior art can be avoided, thereby reducing the processing of the query engine. burden.
- the text data of the POI is not only displayed, but the image data of the POI is also displayed, the displayed POI data substantially satisfies the user.
- the true positioning intention can effectively improve the effectiveness of the positioning result.
- the text data of the POI is not only displayed, but the image data of the POI is also displayed, the displayed POI data substantially satisfies the true positioning intention of the user, and the positioning efficiency can be effectively improved.
- FIG. 4 is a schematic structural diagram of an image display apparatus according to another embodiment of the present invention, as shown in FIG. 5.
- the image presentation device of the present embodiment may include a position obtaining unit 41, an image obtaining unit 42, and a presentation unit 43.
- the location obtaining unit 41 is configured to obtain a location where the target object is located
- the image obtaining unit 42 is configured to obtain N candidate images according to the shooting position of each of the M candidate images and the location of the target object.
- M is an integer greater than or equal to 1
- N is an integer greater than or equal to 1, and less than or equal to M
- a presentation unit 43 for presenting the recommended image.
- the image display apparatus provided in this embodiment may be an application located in a local terminal, or may be a plug-in or a software development kit (SDK) installed in an application located in a local terminal.
- SDK software development kit
- the unit, or the query engine located in the network side server, is not specifically limited in this embodiment.
- the application may be a local application (nativeApp) installed on the terminal, or may be a web application (webApp) of the browser on the terminal, which is not limited in this embodiment.
- the candidate image includes a first candidate image; correspondingly, as shown in FIG. 5, the image display apparatus provided in this embodiment may further include a positioning unit. 51. Specifically, it may be used to obtain a first candidate image where the specified object is located; and obtain a shooting position of the first candidate image according to the EXIF information of the first candidate image.
- the candidate image further includes a second candidate image, in addition to the first candidate image, and the positioning unit 51 may further be used to obtain the location. Determining a second candidate image in which the specified object is located; performing three-dimensional reconstruction processing according to the first candidate image and the second candidate image to obtain relative positioning information of the shooting tool of the first candidate image and the second Relative positioning information of the photographing tool of the candidate image; and relative positioning information of the photographing tool of the first candidate image and relative positioning information of the photographing tool of the second candidate image according to the photographing position of the first candidate image, the relative positioning information of the photographing tool of the first candidate image, A photographing position of the second candidate image is obtained.
- the positioning unit may be configured to perform feature extraction processing on the first candidate image to obtain feature information of the first candidate image, and perform feature extraction processing on the second candidate image to obtain Feature information of the second candidate image; and feature information according to the first candidate image, an internal parameter of a photographing tool of the first candidate image, feature information of the second candidate image, and the second candidate An internal parameter of the photographing tool of the image obtains relative positioning information of the photographing tool of the first candidate image and relative positioning information of the photographing tool of the second candidate image.
- the presentation unit 43 may be specifically configured to display the recommended image in at least one of a map annotation manner and an image manner.
- the position of the target object is obtained by the position obtaining unit, and the image obtaining unit obtains N candidate images according to the shooting position of each of the M candidate images and the position of the target object.
- M is an integer greater than or equal to 1
- N is an integer greater than or equal to 1, and less than or equal to M, so that the presentation unit can present the recommended image, since the text data of the POI is no longer only displayed, but The image data of the POI is also displayed, so that the displayed POI data substantially satisfies the true positioning intention of the user, and therefore, the data interaction between the application and the query engine caused by the repeated query by the user in the prior art can be avoided in the prior art.
- the problem which reduces the processing load of the query engine.
- the text data of the POI is not only displayed, but the image data of the POI is also displayed, the displayed POI data substantially satisfies the true positioning intention of the user, and the positioning result can be effectively improved. Sex.
- the text data of the POI is not only displayed, but the image data of the POI is also displayed, the displayed POI data substantially satisfies the true positioning intention of the user, and the positioning efficiency can be effectively improved.
- the disclosed system, apparatus, and method may be implemented in other manners.
- the device embodiments described above are merely illustrative.
- the division of the unit is only a logical function division.
- there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
- the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
- the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
- each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
- the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
- the above-described integrated unit implemented in the form of a software functional unit can be stored in a computer readable storage medium.
- the above software functional unit is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform the methods of the various embodiments of the present invention. Part of the steps.
- the foregoing storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (ROM), and a random access memory (Random Access).
- ROM read-only memory
- Random Access random access memory
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
本发明提供一种图像展现方法、装置、设备及非易失性计算机存储介质。本发明实施例通过获得目标对象所在的位置,进而根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数,使得能够展现所述推荐图像,由于不再只展现POI的文本数据,而是还展现POI的图像数据,使得所展现的POI数据基本满足用户真正的定位意图,因此,能够避免现有技术中由于用户通过应用反复进行查询而导致的增加应用与查询引擎之间的数据交互的问题,从而降低了查询引擎的处理负担。
Description
本申请要求了申请日为2014年07月24日,申请号为201410355933.2发明名称为“图像展现方法及装置”的中国专利申请的优先权。
本发明涉及定位服务(Location Based Service,LBS)技术,特别涉及一种图像展现方法、装置、设备及非易失性计算机存储介质。
随着通信技术的发展,终端集成了越来越多的功能,从而使得终端的系统功能列表中包含了越来越多相应的应用(Application,APP)。有些应用中会涉及一些定位服务(Location Based Service,LBS),又称位置服务,例如,百度地图等。在LBS中,应用所对应的服务端存储了大量的兴趣点(Point of Interest,POI)数据,以向应用即客户端提供基于LBS查询的查询结果。其中,兴趣点数据可以包括名称信息、类别信息、地理位置信息(即经度和纬度等)等这几个方面的文本数据。
然而,在一些情况下,例如,实际的POI并没有标志性的名称指示牌,以明确指示该POI等,当用户到达一个POI的附近时,向用户所展现的文本数据可能无法满足用户真正的定位意图,使得用户需要通过应用反复进行定位操作,这样,会增加应用与查询引擎之间的数据交互,从而导致了查询引擎的处理负担的增加。
发明内容
本发明的多个方面提供一种图像展现方法、装置、设备及非易失性计算机存储介质,用以降低查询引擎的处理负担。
本发明的一方面,提供一种图像展现方法,包括:
获得目标对象所在的位置;
根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数;
展现所述推荐图像。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述候选图像包括第一候选图像;所述根据M个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像之前,还包括:
获得指定物体所在的第一候选图像;
根据所述第一候选图像的EXIF信息,获得所述第一候选图像的拍摄位置。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述候选图像还包括第二候选图像;所述根据M个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像之前,
还包括:
获得所述指定物体所在的第二候选图像;
根据所述第一候选图像和所述第二候选图像,进行三维重建处理,以获得所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息;
根据所述第一候选图像的拍摄位置、所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息,获得所述第二候选图像的拍摄位置。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述根据所述第一候选图像和所述第二候选图像,进行三维重建处理,以获得所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息,包括:
对所述第一候选图像进行特征提取处理,以获得所述第一候选图像的特征信息;
对所述第二候选图像进行特征提取处理,以获得所述第二候选图像的特征信息;
根据所述第一候选图像的特征信息、所述第一候选图像的拍摄工具的内参数、所述第二候选图像的特征信息和所述第二候选图像的拍摄工具的内参数,获得所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,
所述展现所述推荐图像,包括:
以地图标注方式和图像方式中的至少一项,展现所述推荐图像。
本发明的另一方面,提供一种图像展现装置,包括:
位置获得单元,用于获得目标对象所在的位置;
图像获得单元,用于根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数;
展现单元,用于展现所述推荐图像。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述候选图像包括第一候选图像;所述装置还包括定位单元,用于
获得指定物体所在的第一候选图像;以及
根据所述第一候选图像的EXIF信息,获得所述第一候选图像的拍摄位置。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述候选图像还包括第二候选图像;所述定位单元,还用于
获得所述指定物体所在的第二候选图像;
根据所述第一候选图像和所述第二候选图像,进行三维重建处理,以获得所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息;以及
根据所述第一候选图像的拍摄位置、所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息,获得
所述第二候选图像的拍摄位置。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述定位单元,具体用于
对所述第一候选图像进行特征提取处理,以获得所述第一候选图像的特征信息;
对所述第二候选图像进行特征提取处理,以获得所述第二候选图像的特征信息;以及
根据所述第一候选图像的特征信息、所述第一候选图像的拍摄工具的内参数、所述第二候选图像的特征信息和所述第二候选图像的拍摄工具的内参数,获得所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述展现单元,具体用于
以地图标注方式和图像方式中的至少一项,展现所述推荐图像。
本发明的另一方面,提供一种设备,包括:
一个或者多个处理器;
存储器;
一个或者多个程序,所述一个或者多个程序存储在所述存储器中,当被所述一个或者多个处理器执行时:
获得目标对象所在的位置;
根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数;
展现所述推荐图像。
本发明的另一方面,提供一种非易失性计算机存储介质,所述非易失性计算机存储介质存储有一个或者多个程序,当所述一个或者多个程序被一个设备执行时,使得所述设备:
获得目标对象所在的位置;
根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数;
展现所述推荐图像。
由上述技术方案可知,本发明实施例通过获得目标对象所在的位置,进而根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数,使得能够展现所述推荐图像,由于不再只展现POI的文本数据,而是还展现POI的图像数据,使得所展现的POI数据基本满足用户真正的定位意图,因此,能够避免现有技术中由于用户通过应用反复进行查询而导致的增加应用与查询引擎之间的数据交互的问题,从而降低了查询引擎的处理负担。
另外,采用本发明提供的技术方案,由于不再只展现POI的文本数据,而是还展现POI的图像数据,使得所展现的POI数据基本满足用户真正的定位意图,能够有效提高定位结果的有效性。
另外,采用本发明提供的技术方案,由于不再只展现POI的文本数据,而是还展现POI的图像数据,使得所展现的POI数据基本满足用户真正的定位意图,能够有效提高定位的效率。
为了更清楚地说明本发明实施例中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为本发明一实施例提供的图像展现方法的流程示意图;
图2为图1对应的实施例中候选图像的分布示意图;
图3为图1对应的实施例中指定位置的推荐图像示意图;
图4为本发明另一实施例提供的图像展现装置的结构示意图;
图5为本发明另一实施例提供的图像展现装置的结构示意图。
为使本发明实施例的目的、技术方案和优点更加清楚,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本发明一部分实施例,而不是全部的
实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的全部其他实施例,都属于本发明保护的范围。
需要说明的是,本发明实施例中所涉及的终端可以包括但不限于手机、个人数字助理(Personal Digital Assistant,PDA)、无线手持装置、无线上网本、个人电脑、便携电脑、平板电脑、MP3播放器、MP4播放器、可穿戴设备(例如,智能眼镜、智能手表、智能手环等)等。
另外,本文中术语“和/或”,仅仅是一种描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。另外,本文中字符“/”,一般表示前后关联对象是一种“或”的关系。
图1为本发明一实施例提供的图像展现方法的流程示意图,如图1所示。
101、获得目标对象所在的位置。
102、根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数。
103、展现所述推荐图像。
需要说明的是,101~103的执行主体可以为位于本地终端的应用,或者还可以为设置在位于本地终端的应用中的插件或软件开发工具包(Software Development Kit,SDK)等功能单元,或者还可以为位于网络侧服务器中的查询引擎,本实施例对此不进行特别限定。
可以理解的是,所述应用可以是安装在终端上的本地程序(nativeApp),或者还可以是终端上的浏览器的一个网页程序(webApp),
本实施例对此不进行限定。
其中,所谓的候选图像,可以是指包含指定物体的图像,其中,指定物体可以理解为指定POI或者其标志性建筑。例如,景点如天安门等、景点的大门如颐和园的大门等、景点中的标志性地点如北海的白塔等。
这样,通过获得目标对象所在的位置,进而根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数,使得能够展现所述推荐图像,由于不再只展现POI的文本数据,而是还展现POI的图像数据,使得所展现的POI数据基本满足用户真正的定位意图,因此,能够避免现有技术中由于用户通过应用反复进行查询而导致的增加应用与查询引擎之间的数据交互的问题,从而降低了查询引擎的处理负担。
可选地,在本实施例的一个可能的实现方式中,在101中,具体可以采用现有的各种定位技术,获得目标对象的定位结果,即目标对象所在的位置的地理位置信息例如,经度和纬度等,本实施例对此不进行特别限定。例如,全球定位系统(Global Positioning System,GPS)技术、无线相容性认证(Wireless Fidelity,Wi-Fi)定位技术或基站定位技术等定位技术。目标对象可以理解为一个用户,该用户当前的定位意图为附近的POI。
可选地,在本实施例的一个可能的实现方式中,在102中所涉及的M个候选图像,具体可以通过多种方式获取,本实施例对此不进行特别限定。
以天安门为例,具体可以利用搜索关键词“天安门”,进行查询,
以获得与该搜索关键词匹配的图像,以作为候选图像。或者,还可以直接接收其他终端所发送的包含天安门这一实体的图像,以作为候选图像。
可选地,在本实施例的一个可能的实现方式中,在102中,具体可以根据目标对象所在的位置的地理位置信息,与M个候选图像中每个候选图像的拍摄位置的地理位置信息,计算该位置与拍摄位置之间的距离,进而,则可以根据所述距离,确定N个候选图像,以作为推荐图像。
具体地,若所述距离小于或等于预先设置的距离阈值,说明该位置距离对应的候选图像所展现的POI较近,则可以将对应的候选图像确定为推荐图像;若所述距离大于所述距离阈值,说明该位置距离对应的候选图像所展现的POI较远,则可以忽略对应的候选图像,即不将对应的候选图像确定为推荐图像。
可选地,在本实施例的一个可能的实现方式中,所述候选图像可以包括第一候选图像;相应地,在102之前,具体可以获得指定物体所在的第一候选图像,进而根据所述第一候选图像的可交换图像文件格式(Exchangeable Image File Format,EXIF)信息,获得所述第一候选图像的拍摄位置。所谓的指定物体,就是一个POI的全部或者部分。
这样,对于这种候选图像,能够利用候选图像的EXIF信息,直接获得候选图像的拍摄位置,即拍摄位置的地理位置信息。
至此,可以将所获得的候选图像的拍摄位置的地理位置信息与该候选图像进行关联,并记录该关联关系。这样,在执行102时,则可以根据该关联关系,获得每个候选图像的拍摄位置。
其中,EXIF是一种图像文件格式,它的数据存储与联合图像专家小组(Joint Photographic Experts Group,JPEG)格式是完全相同的。
实际上EXIF就是在JPEG格式的头部插入了一组拍摄参数,该信息可以称为EXIF信息。其中,EXIF信息可以有选择性地包括拍摄时的光圈、快门、白平衡、感光度(ISO)、焦距、日期时间等各种与当时拍摄条件相关的信息,以及拍摄工具品牌、型号、色彩编码、拍摄时录制的声音、缩略图、拍摄位置的GPS参数等其他信息。因此,具体可以利用任何能够查看JPEG格式图像的看图软件浏览EXIF格式图像,但并不是所有的图形程序都能处理EXIF信息。
有些候选图像是具有EXIF信息的,该EXIF信息中也可以包括拍摄位置的GPS参数,因此,这种候选图像,能够利用候选图像的EXIF信息,直接获得候选图像的拍摄位置。
然而,并不是所有的候选图像都具有EXIF信息,也不是所有的候选图像的EXIF信息均包括拍摄位置的GPS参数,因此,这种候选图像,并不能够利用候选图像的EXIF信息,直接获得候选图像的拍摄位置。
可选地,在本实施例的一个可能的实现方式中,所述候选图像除了包括第一候选图像之外,还可以进一步包括第二候选图像。
相应地,在102之前,具体可以获得所述指定物体所在的第二候选图像,进而根据所述第一候选图像和所述第二候选图像,进行三维重建处理,以获得所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息,使得能够根据所述第一候选图像的拍摄位置、所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息,获得所述第二候选图像的拍摄位置。
其中,所述第一候选图像的数量可以为一个,或者还可以为多个,
本实施例对此不进行特别限定;同理,所述第二候选图像的数量可以为一个,或者还可以为多个,本实施例对此不进行特别限定。
具体地,根据所述第一候选图像和所述第二候选图像,进行三维重建处理,具体可以采用现有技术中的任何方法,本实施例对此不进行特别限定。
例如,具体可以对所述第一候选图像进行特征提取处理,以获得所述第一候选图像的特征信息,以及对所述第二候选图像进行特征提取处理,以获得所述第二候选图像的特征信息。“对所述第一候选图像进行特征提取处理”与“对所述第二候选图像进行特征提取处理”的没有固定的执行顺序,可以先执行“对所述第一候选图像进行特征提取处理”,再执行“对所述第二候选图像进行特征提取处理”,或者还可以执行“对所述第一候选图像进行特征提取处理”的同时,执行“对所述第二候选图像进行特征提取处理”,或者还可以先执行“对所述第二候选图像进行特征提取处理”,再执行“对所述第一候选图像进行特征提取处理”,本实施例对此不进行特别限定。然后,则可以根据所述第一候选图像的特征信息、所述第一候选图像的拍摄工具的内参数、所述第二候选图像的特征信息和所述第二候选图像的拍摄工具的内参数,获得所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息。
下面以现有的一种三维重建方法举例说明一下。
首先,可以针对全部的候选图像即全部的第一候选图像和全部的第二候选图像,分别计算两两候选图像之间的特征匹配值,进而根据特征匹配值,确定每个候选图像上的像素之间的对应关系。此处的两两,是
指任意两个候选图像,可以为一个第一候选图像与另一个第一候选图像,或者还可以为一个第一候选图像与一个第二候选图像,或者还可以为一个第二候选图像与另一个第二候选图像,本实施例对此不进行特别限定。
然后,可以针对全部的候选图像即全部的第一候选图像和全部的第二候选图像,分别计算两两候选图像之间的基本矩阵,进而利用基本矩阵,过滤不正确的每个候选图像上的像素之间的对应关系。此处的两两,是指任意两个候选图像,可以为一个第一候选图像与另一个第一候选图像,或者还可以为一个第一候选图像与一个第二候选图像,或者还可以为一个第二候选图像与另一个第二候选图像,本实施例对此不进行特别限定。
接着,利用两个候选图像的拍摄工具的初始内参数,利用两个候选图像的基本矩阵,进行运动估计,以获得这两个候选图像的拍摄工具的相对定位信息如旋转参数和平移参数。其中,拍摄工具的初始内参数可以包括但不限于焦距和主点的坐标信息。焦距,具体可以从EXIF信息中直接读取;主点,是指主光轴与像平面的交点,具体可以利用候选图像的中心来近似获得。其中,所述相对定位信息是以其中的一个候选图像的拍摄工具为参考获得。作为参考的候选图像的拍摄工具,可以称为参考拍摄工具。也就是说,候选图像的拍摄工具的相对定位信息,是指候选图像的拍摄工具相对于参考拍摄工具的定位信息。
进而,则可以根据这两个候选图像的拍摄工具的相对定位信息,获得像素点的深度,再根据像素点的深度,获得所述指定物体的一组三维信息和这两个候选图像的拍摄工具的计算内参数。
然后,根据所获得的一组三维信息,利用N点透视方法,获得另一
个新的候选图像的相对定位信息。其中,所述新的候选图像的相对定位信息,是指新的候选图像的拍摄工具相对于参考拍摄工具的定位信息。接着,再利用新的候选图像的拍摄工具的初始内参数与之前的两个候选图像中的任意一个候选图像的拍摄工具的计算内参数,采用前述方法,获得所述指定物体的另一组三维信息和新的候选图像的拍摄工具的计算内参数。这样,循环执行本步骤,直到获得全部新的候选图像的相对定位信息为止。
由于地理位置信息可以包括但不限于经度和维度,还可以进一步包括海拔。由于拍摄者拍摄POI的位置的海拔一般与POI的海拔相同,因此,在拍摄位置的计算过程中,可以忽略海拔,以经度和纬度作为地理位置信息即可。
最后,则可以根据任意两个第一候选图像的拍摄位置即拍摄位置的地理位置信息、及其对应的拍摄工具的相对定位信息和一个待定位的第二候选图像的拍摄工具的相对定位信息,利用放射变换原理,获得该第二候选图像的拍摄位置即拍摄位置的地理位置信息。
可以理解的是,如果可以能够获得指定物体的位置的地理位置信息,还可以进一步根据所述指定物体的位置、所述第一候选图像的拍摄位置、所述第一方位角和所述第二方位角,获得所述第二候选图像的拍摄位置。
详细描述可以参见现有技术中的相关内容,此处不再赘述。
至此,可以将所获得的候选图像的拍摄位置的地理位置信息与该候选图像进行关联,并记录该关联关系。这样,在执行102时,则可以根据该关联关系,获得每个候选图像的拍摄位置。
以天安门为例,具体可以利用搜索关键词“天安门”,进行查询,
以获得与该搜索关键词匹配的图像,以作为候选图像。采用上述方法,计算出这些候选图像中无法直接利用其EXIF信息获得拍摄位置的候选图像,的拍摄位置。如图2所示,这些候选图像的拍摄位置分布示意图,其中,颜色最深的中心区域,为候选图像的拍摄位置较为集中的热点区域A,颜色最浅的边缘区域,为候选图像的拍摄位置较为稀疏的非热点区域B。
可选地,在本实施例的一个可能的实现方式中,在103中,具体可以以地图标注方式和图像方式中的至少一项,展现所述推荐图像,本实施例对此不进行特别限定。
例如,具体可以在电子地图上,以地图标注方式,向用户展现所述推荐图像。
或者,再例如,具体可以在电子地图上或其他界面上,以图像方式,直接向用户展现所述推荐图像,如图3所示。
本实施例中,通过获得目标对象所在的位置,进而根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数,使得能够展现所述推荐图像,由于不再只展现POI的文本数据,而是还展现POI的图像数据,使得所展现的POI数据基本满足用户真正的定位意图,因此,能够避免现有技术中由于用户通过应用反复进行查询而导致的增加应用与查询引擎之间的数据交互的问题,从而降低了查询引擎的处理负担。
另外,采用本发明提供的技术方案,由于不再只展现POI的文本数据,而是还展现POI的图像数据,使得所展现的POI数据基本满足用户
真正的定位意图,能够有效提高定位结果的有效性。
另外,采用本发明提供的技术方案,由于不再只展现POI的文本数据,而是还展现POI的图像数据,使得所展现的POI数据基本满足用户真正的定位意图,能够有效提高定位的效率。
需要说明的是,对于前述的各方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本发明并不受所描述的动作顺序的限制,因为依据本发明,某些步骤可以采用其他顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于优选实施例,所涉及的动作和模块并不一定是本发明所必须的。
在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述的部分,可以参见其他实施例的相关描述。
图4为本发明另一实施例提供的图像展现装置的结构示意图,如图5所示。本实施例的图像展现装置可以包括位置获得单元41、图像获得单元42和展现单元43。其中,位置获得单元41,用于获得目标对象所在的位置;图像获得单元42,用于根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数;展现单元43,用于展现所述推荐图像。
需要说明的是,本实施例所提供的图像展现装置可以为位于本地终端的应用,或者还可以为设置在位于本地终端的应用中的插件或软件开发工具包(Software Development Kit,SDK)等功能单元,或者还可以为位于网络侧服务器中的查询引擎,本实施例对此不进行特别限定。
可以理解的是,所述应用可以是安装在终端上的本地程序(nativeApp),或者还可以是终端上的浏览器的一个网页程序(webApp),本实施例对此不进行限定。
可选地,在本实施例的一个可能的实现方式中,所述候选图像包括第一候选图像;相应地,如图5所示,本实施例所提供的图像展现装置还可以进一步包括定位单元51,具体可以用于获得指定物体所在的第一候选图像;以及根据所述第一候选图像的EXIF信息,获得所述第一候选图像的拍摄位置。
可选地,在本实施例的一个可能的实现方式中,所述候选图像除了包括第一候选图像之外,还进一步包括第二候选图像;所述定位单元51,还可以进一步用于获得所述指定物体所在的第二候选图像;根据所述第一候选图像和所述第二候选图像,进行三维重建处理,以获得所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息;以及根据所述第一候选图像的拍摄位置、所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息,获得所述第二候选图像的拍摄位置。
具体地,所述定位单元,具体可以用于对所述第一候选图像进行特征提取处理,以获得所述第一候选图像的特征信息;对所述第二候选图像进行特征提取处理,以获得所述第二候选图像的特征信息;以及根据所述第一候选图像的特征信息、所述第一候选图像的拍摄工具的内参数、所述第二候选图像的特征信息和所述第二候选图像的拍摄工具的内参数,获得所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息。
可选地,在本实施例的一个可能的实现方式中,所述展现单元43,具体可以用于以地图标注方式和图像方式中的至少一项,展现所述推荐图像。
需要说明的是,图1对应的实施例中方法,可以由本实施例提供的图像展现装置实现。详细描述可以参见图1对应的实施例中的相关内容,此处不再赘述。
本实施例中,通过位置获得单元获得目标对象所在的位置,进而由图像获得单元根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数,使得展现单元能够展现所述推荐图像,由于不再只展现POI的文本数据,而是还展现POI的图像数据,使得所展现的POI数据基本满足用户真正的定位意图,因此,能够避免现有技术中由于用户通过应用反复进行查询而导致的增加应用与查询引擎之间的数据交互的问题,从而降低了查询引擎的处理负担。
另外,采用本发明提供的技术方案,由于不再只展现POI的文本数据,而是还展现POI的图像数据,使得所展现的POI数据基本满足用户真正的定位意图,能够有效提高定位结果的有效性。
另外,采用本发明提供的技术方案,由于不再只展现POI的文本数据,而是还展现POI的图像数据,使得所展现的POI数据基本满足用户真正的定位意图,能够有效提高定位的效率。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统,装置和单元的具体工作过程,可以参考前述方法实施例
中的对应过程,在此不再赘述。
在本发明所提供的几个实施例中,应该理解到,所揭露的系统,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本发明各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元,可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)或处理器(processor)执行本发明各个实施例所述方法的部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access
Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是:以上实施例仅用以说明本发明的技术方案,而非对其限制;尽管参照前述实施例对本发明进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。
Claims (12)
- 一种图像展现方法,其特征在于,包括:获得目标对象所在的位置;根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数;展现所述推荐图像。
- 根据权利要求1所述的方法,其特征在于,所述候选图像包括第一候选图像;所述根据M个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像之前,还包括:获得指定物体所在的第一候选图像;根据所述第一候选图像的EXIF信息,获得所述第一候选图像的拍摄位置。
- 根据权利要求2所述的方法,其特征在于,所述候选图像还包括第二候选图像;所述根据M个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像之前,还包括:获得所述指定物体所在的第二候选图像;根据所述第一候选图像和所述第二候选图像,进行三维重建处理,以获得所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息;根据所述第一候选图像的拍摄位置、所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息,获得所述第二候选图像的拍摄位置。
- 根据权利要求3所述的方法,其特征在于,所述根据所述第一候选图像和所述第二候选图像,进行三维重建处理,以获得所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息,包括:对所述第一候选图像进行特征提取处理,以获得所述第一候选图像的特征信息;对所述第二候选图像进行特征提取处理,以获得所述第二候选图像的特征信息;根据所述第一候选图像的特征信息、所述第一候选图像的拍摄工具的内参数、所述第二候选图像的特征信息和所述第二候选图像的拍摄工具的内参数,获得所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息。
- 根据权利要求1~4任一权利要求所述的方法,其特征在于,所述展现所述推荐图像,包括:以地图标注方式和图像方式中的至少一项,展现所述推荐图像。
- 一种图像展现装置,其特征在于,包括:位置获得单元,用于获得目标对象所在的位置;图像获得单元,用于根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数;展现单元,用于展现所述推荐图像。
- 根据权利要求6所述的装置,其特征在于,所述候选图像包括第一候选图像;所述装置还包括定位单元,用于获得指定物体所在的第一候选图像;以及根据所述第一候选图像的EXIF信息,获得所述第一候选图像的拍摄位置。
- 根据权利要求7所述的装置,其特征在于,所述候选图像还包括第二候选图像;所述定位单元,还用于获得所述指定物体所在的第二候选图像;根据所述第一候选图像和所述第二候选图像,进行三维重建处理,以获得所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息;以及根据所述第一候选图像的拍摄位置、所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息,获得所述第二候选图像的拍摄位置。
- 根据权利要求8所述的装置,其特征在于,所述定位单元,具体用于对所述第一候选图像进行特征提取处理,以获得所述第一候选图像的特征信息;对所述第二候选图像进行特征提取处理,以获得所述第二候选图像的特征信息;以及根据所述第一候选图像的特征信息、所述第一候选图像的拍摄工具的内参数、所述第二候选图像的特征信息和所述第二候选图像的拍摄工具的内参数,获得所述第一候选图像的拍摄工具的相对定位信息和所述第二候选图像的拍摄工具的相对定位信息。
- 根据权利要求6~9任一权利要求所述的装置,其特征在于,所 述展现单元,具体用于以地图标注方式和图像方式中的至少一项,展现所述推荐图像。
- 一种设备,包括:一个或者多个处理器;存储器;一个或者多个程序,所述一个或者多个程序存储在所述存储器中,当被所述一个或者多个处理器执行时:获得目标对象所在的位置;根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数;展现所述推荐图像。
- 一种非易失性计算机存储介质,所述非易失性计算机存储介质存储有一个或者多个程序,当所述一个或者多个程序被一个设备执行时,使得所述设备:获得目标对象所在的位置;根据M个候选图像中每个候选图像的拍摄位置和所述目标对象所在的位置,获得N个候选图像,以作为推荐图像,M为大于或等于1的整数,N为大于或等于1,且小于或等于M的整数;展现所述推荐图像。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410355933.2 | 2014-07-24 | ||
CN201410355933.2A CN104102732B (zh) | 2014-07-24 | 2014-07-24 | 图像展现方法及装置 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2016011763A1 true WO2016011763A1 (zh) | 2016-01-28 |
Family
ID=51670885
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2014/093382 WO2016011763A1 (zh) | 2014-07-24 | 2014-12-09 | 图像展现方法、装置、设备及非易失性计算机存储介质 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN104102732B (zh) |
WO (1) | WO2016011763A1 (zh) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104102732B (zh) * | 2014-07-24 | 2017-03-08 | 百度在线网络技术(北京)有限公司 | 图像展现方法及装置 |
CN105868223A (zh) * | 2015-11-09 | 2016-08-17 | 乐视致新电子科技(天津)有限公司 | 壁纸信息提供方法、装置、用户设备及服务器 |
CN106570195A (zh) * | 2016-11-18 | 2017-04-19 | 广东小天才科技有限公司 | 一种基于位置的照片搜索方法及装置、用户设备 |
CN111415410B (zh) * | 2019-01-08 | 2023-06-20 | 阿里巴巴集团控股有限公司 | Poi位置标注方法及装置 |
CN110413719A (zh) * | 2019-07-25 | 2019-11-05 | Oppo广东移动通信有限公司 | 信息处理方法及装置、设备、存储介质 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102542523A (zh) * | 2011-12-28 | 2012-07-04 | 天津大学 | 一种基于街景的城市图片信息认证方法 |
CN102946476A (zh) * | 2012-10-30 | 2013-02-27 | 北京小米科技有限责任公司 | 一种快速定位的方法及装置 |
CN103577400A (zh) * | 2012-07-18 | 2014-02-12 | 三星电子(中国)研发中心 | 一种提供地点信息的方法及系统 |
CN104102732A (zh) * | 2014-07-24 | 2014-10-15 | 百度在线网络技术(北京)有限公司 | 图像展现方法及装置 |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8131118B1 (en) * | 2008-01-31 | 2012-03-06 | Google Inc. | Inferring locations from an image |
CN103164480A (zh) * | 2011-12-13 | 2013-06-19 | 北京千橡网景科技发展有限公司 | 用于在社交网络中推荐兴趣点的方法和设备 |
-
2014
- 2014-07-24 CN CN201410355933.2A patent/CN104102732B/zh active Active
- 2014-12-09 WO PCT/CN2014/093382 patent/WO2016011763A1/zh active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102542523A (zh) * | 2011-12-28 | 2012-07-04 | 天津大学 | 一种基于街景的城市图片信息认证方法 |
CN103577400A (zh) * | 2012-07-18 | 2014-02-12 | 三星电子(中国)研发中心 | 一种提供地点信息的方法及系统 |
CN102946476A (zh) * | 2012-10-30 | 2013-02-27 | 北京小米科技有限责任公司 | 一种快速定位的方法及装置 |
CN104102732A (zh) * | 2014-07-24 | 2014-10-15 | 百度在线网络技术(北京)有限公司 | 图像展现方法及装置 |
Also Published As
Publication number | Publication date |
---|---|
CN104102732A (zh) | 2014-10-15 |
CN104102732B (zh) | 2017-03-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI546519B (zh) | 興趣點的展現方法及裝置 | |
US10032302B2 (en) | Rebuilding images based on historical image data | |
US9716827B2 (en) | Location aware photograph recommendation notification | |
US9646406B2 (en) | Position searching method and apparatus based on electronic map | |
US9584694B2 (en) | Predetermined-area management system, communication method, and computer program product | |
WO2016011763A1 (zh) | 图像展现方法、装置、设备及非易失性计算机存储介质 | |
WO2016058456A1 (zh) | 拍照方法及智能终端、云端服务器 | |
WO2015124082A1 (en) | Electronic travel album generating method and system | |
US20110292221A1 (en) | Automatic camera | |
US20150187139A1 (en) | Apparatus and method of providing augmented reality | |
WO2015172359A1 (zh) | 一种对象搜索方法及装置 | |
EP4221242A2 (en) | System and method for selecting scenes for browsing histories in augmented reality interfaces | |
JP2010039583A (ja) | 電子地図上での写真表示方法及びシステム、並びにその電子地図 | |
US9070345B2 (en) | Integrating street view with live video data | |
WO2017024684A1 (zh) | 用户行为意图的获取方法、装置、设备及非易失性计算机存储介质 | |
CN104572830A (zh) | 推荐拍摄信息的处理方法及装置 | |
WO2020068241A1 (en) | Fashion by trend user interfaces | |
JP2010276364A (ja) | ナビ情報作成装置、ナビゲーションシステム、ナビゲーション情報作成方法、およびナビゲーション方法 | |
WO2018000299A1 (en) | Method for assisting acquisition of picture by device | |
JP5708868B1 (ja) | プログラム、情報処理装置及び方法 | |
WO2017120767A1 (zh) | 一种头部姿态预测方法和装置 | |
JP2024525132A (ja) | 共有仮想空間内で電子装置を位置決め及び方向付けするためのコンピュータ実装方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14897964 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 14897964 Country of ref document: EP Kind code of ref document: A1 |