CN112100407A - Information inheriting and superposing method of multimedia image system - Google Patents
Information inheriting and superposing method of multimedia image system Download PDFInfo
- Publication number
- CN112100407A CN112100407A CN202011027136.3A CN202011027136A CN112100407A CN 112100407 A CN112100407 A CN 112100407A CN 202011027136 A CN202011027136 A CN 202011027136A CN 112100407 A CN112100407 A CN 112100407A
- Authority
- CN
- China
- Prior art keywords
- image
- multimedia
- user
- information
- basic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/41—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/432—Query formulation
- G06F16/434—Query formulation using image data, e.g. images, photos, pictures taken by a user
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/44—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/48—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/483—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Abstract
The information inheriting and superposing method of the multimedia image system is characterized in that: the multimedia image is characterized in that one or more information points are arranged on the image, multimedia data are adopted to describe each information point, and then the image and the multimedia data corresponding to each information point are merged and stored; the multimedia image system comprises a multimedia image basic database and a user self-made multimedia image; processing by adopting an automatic retrieval processing method or/and a manual retrieval processing method; by reinforcing the hierarchy of the multimedia function of the image and utilizing the technical means of information inheritance and superposition, the user can quickly construct or discover the required data and information through the multimedia image.
Description
Technical Field
The invention relates to an information inheritance and superposition method of a multimedia image system, which can enable a user to quickly construct or discover data and information required by the user through a multimedia image by reinforcing the hierarchy of multimedia functions of the image and utilizing the technical means of information inheritance and superposition, and belongs to the technical field of multimedia image processing and application.
Background
In the prior art, there are many automatic recognition systems and software for "seeing the picture to know the object", which are usually based on the application of deep learning image recognition algorithm, and can give the recognition result of the scenery in the image according to the image taken by the user; however, the objects identified in the prior art are mainly scene-independent objects with obvious general characteristics, such as daily necessities, plants, animals, landmark buildings and the like, and there is a certain difficulty in identifying scene-related objects and providing specific information related to the scene.
Scene-related scenery features that the scenery has strong relevance with the scene, but general features or marks are not obvious or have high repeatability; for example, a scene without obvious mark features, a building, or a temporarily built scene or a movable scene with strong timeliness is difficult to determine the accurate position and related information of the scene quickly and timely through a photo image taken by a user; at this time, if the related images are limited in the current scene range for cross comparison, the probability of successful matching is greatly improved.
On the other hand, a large number of sights or items are contained in each public scene; if each particular attraction or item is to be described in detail, aspects, having many specific details, are typically involved. If the description is carried out through the text of long-text or a large amount of multimedia data, the user can hardly find out the interest points; if the introduction content is simplified, the personalized requirements of exploration and knowledge of the user cannot be met. Therefore, how to guide the user to know the scene more comprehensively and stereoscopically and realize self-service personalized tourism is a problem which needs to be solved for improving the human-computer interaction effect and arousing the interest of the user.
Disclosure of Invention
The technical scheme of the invention is that the hierarchy of the multimedia function of the image is strengthened, and the user can quickly construct or discover the required data and information through the multimedia image by using the technical means of information inheritance and superposition.
The technical scheme of the invention is as follows: the information inheriting and superposing method of the multimedia image system is characterized in that: the multimedia image is characterized in that one or more information points are arranged on the image, multimedia data are adopted to describe each information point, and then the image and the multimedia data corresponding to each information point are merged and stored; the multimedia data is one or any combination of more of characters, audio, images and videos; wherein, the information points are corresponding to the characteristic images of specific point positions or local areas in the images; when a user browses a multimedia image, the user firstly sees the image, and then selects the local area position corresponding to each information point in the image, namely the multimedia data corresponding to the information point can be played;
the multimedia image system comprises a multimedia image basic database and a user self-made multimedia image; processing by adopting an automatic retrieval and processing method or/and a manual retrieval and processing method;
the automatic retrieval and processing method comprises the steps of extracting scenes, objects and people in user images, automatically matching the scenes, the objects and the people with basic images in a multimedia image basic database, and identifying image characteristics, namely automatically searching whether the basic images containing the same scenes, the objects and the people exist or not; the automatic retrieval and processing method at least comprises the following steps:
s101, collecting basic images, preparing multimedia materials, then associating the basic images with the multimedia materials, and manufacturing a multimedia image basic database;
it should be noted that the basic images are collected and the multimedia materials are prepared in a targeted manner according to the established target of the basic database; the multimedia image basic database can be manufactured, maintained and upgraded continuously through the means of collection, sorting, editing, superposition, summarization and the like; the basic image should be clear in detail and reasonable in composition, and can be made by professional photographers and editors;
s102, carrying out image segmentation and identification on the common image of the user through an image identification algorithm, and extracting a plurality of relatively independent image local areas; or a user manually selects a plurality of image local areas; then, cross comparison is carried out on each image local area and basic image data in a multimedia image basic database respectively, and image features are matched;
usually, each image local area contains relatively independent scenes, objects and people;
s103, setting the image local area successfully matched with the common image as an information point, sequentially superposing and copying the multimedia data of the matched information point or the whole multimedia image contained in the multimedia image basic data into the common image provided by the user, and associating the multimedia data with the corresponding information point, so that the common image of the user is upgraded into the multimedia image of the user;
s104, the user carries out personalized browsing and editing on the multimedia image of the user, namely, the information point and the multimedia data in the multimedia image are operated, and the specific operation is one or any combination of more of addition, modification and deletion;
s105, finally, forming a user self-made multimedia image which corresponds to the situation of the user image and is recorded with the user personalized multimedia information points;
the manual retrieval and processing method comprises the steps that the manual retrieval refers to the steps of extracting scenes, objects and people in images of a user, inputting keywords related to the scenes by the user, searching basic images containing keyword descriptions in a multimedia image basic database, and completing matching after the basic images are confirmed by the user; the manual retrieval and processing method at least comprises the following steps:
s201, collecting basic images, preparing multimedia materials, then associating the basic images with the multimedia materials, and manufacturing a multimedia image basic database;
s202, a user prepares a common image for expressing a certain theme idea, marks specific point positions or local areas in the image and forms a plurality of information points;
s203, the user carries out personalized retrieval on the multimedia image basic database according to the meaning to be expressed by each information point, finds out a multimedia data material meeting the requirement, and then superposes and copies the selected multimedia data or the whole multimedia image into a common image provided by the user and associates the selected multimedia data or the whole multimedia image with the corresponding information point; and operating each information point, wherein the specific operation is one or any combination of more of addition, modification and deletion;
and S204, finally, forming the user self-made multimedia image which is based on the multimedia image basic database and highlights the theme idea which the user wants to express and is recorded with the personalized multimedia information point.
Further, when the information point of the user-made multimedia image is associated with a multimedia image, the associated multimedia image is first displayed when the information point is referred to, and then the information point in the associated multimedia image can be continuously selected for further browsing, and so on.
Furthermore, when a multimedia image basic database is manufactured, image acquisition is respectively carried out on the same scene from a plurality of angles, or/and a plurality of positions, or/and a plurality of local areas, or/and a plurality of time nodes, so that a group of basic images are formed, or 3D modeling is carried out on the scene, and then association with information points is completed; in the matching process of step S102, not only one-to-one matching between the user image and the base image is supported, but also one-to-many or many-to-many matching between the user image and the base image is supported; therefore, the user image and the basic image are quickly matched; the matching process adopts a deep learning image recognition algorithm, and if the matching result is wrong, the user can check the matching result and then carry out re-matching.
Because the direction and the angle of the image shot by the user in real time are random and the shooting effect is influenced by different shooting time, more image data pre-stored in the multimedia image basic database can show the characteristics of the scenery from more aspects, and the success rate of image matching is improved.
Furthermore, when a user browses the multimedia image, a prompt signal is set on the image while the image is displayed, so that the user can intuitively find each information point, and the user can conveniently select and browse the interested information points; or, through the function of displaying the information point list, each information point and the content abstract are directly listed, so that the user can conveniently select and browse each information point.
Furthermore, a category label is set for the multimedia data describing each information point, so that a user can quickly select interested information; and moreover, the user can set own preference, and the system performs comparative analysis and preferentially displays information points interested by the user according to the user preference and the category labels, so that the user can browse conveniently.
Further, when the establishment of the multimedia image basic database is based on a public scene, respectively shooting scenes in the public scene to form basic images on the basis of the scope governed by the public scene; then, the shot basic images are sorted and edited, and all the information points are respectively superposed into all the basic images, so that a multimedia image basic database is formed, and multi-angle and three-dimensional description of the public scene is realized;
when the user is in the public scene, the live image shot by the user can be matched with the multimedia image basic database of the public scene; the user can browse and move in a fixed public scene within a certain time interval; therefore, by taking the public scene as a limit, the data size of comparison can be reduced, and more accurate matching effect and faster matching efficiency can be achieved.
Further, when a multimedia image basic database is manufactured, the basic image is associated with position data in an electronic map of a public scene; the function is as follows:
firstly, after a user shoots an image and matches the image with a basic image in a multimedia image basic database, the position of the user in a public scene can be determined, and further, the service of navigation in the scene is provided for the user;
secondly, performing context correlation analysis on images continuously shot by the user within a certain time period so as to determine the position and the travel route of the user in the public scene, and further reducing the image matching range of the step S102 by taking the recent user position data and the travel route of the user as the basis, thereby improving the matching efficiency.
The invention has the beneficial effects that:
1. the multimedia image basic database is made professionally and is used for comprehensively expressing a certain scene or professional materials in a certain field; the method is characterized by large data volume and comprehensive information;
2. the user takes the image as an entry point, and rapidly extracts personalized basic materials for the user to use through automatic retrieval or/and manual retrieval, so that the interactive communication between the user and the basic database is realized, and the function of the multimedia image basic database is exerted to the maximum extent;
3. the multimedia images of the basic library and the self-made multimedia images can support multilayer nesting, namely, the information points of the multimedia images still contain the multimedia images, so that the multimedia images have richer layers; the personalized events related to the image shooting time are convenient to store and record, or the good memories are stored, and the quick sharing can be realized;
4. whether the producer himself or herself is present or not, the content which the multimedia image wants to express can be conveniently known through the self-made multimedia image; and can use the multimedia image to make new modification and creation (i.e. inherit and superpose again);
5. based on the abundant multimedia image basic database, the method can form quick association with the user image shot by the user in real time, timely and accurately provide the information concerned by the user, and achieve the effect of showing pictures and texts; the method can be applied to application scenes such as self-service guidance, interesting teaching, field skill training and guidance in large scenes.
Drawings
FIG. 1: the invention relates to a flow chart of an information inheritance and superposition method of a multimedia image system;
FIG. 2: the invention is a multimedia image basic database diagram;
FIG. 3: the invention discloses a multimedia image schematic diagram prepared by a user to be edited;
FIG. 4: the edited user self-made multimedia image schematic diagram of the invention.
Detailed Description
Example 1:
hereinafter, the information inheriting and superimposing method of the multimedia image system according to the present invention will be described in detail with reference to the accompanying drawings.
Fig. 1 is a flowchart of an information inheriting and superimposing method of a multimedia image system according to the present invention, and the specific process is as follows:
firstly, collecting basic images, preparing multimedia materials and manufacturing a multimedia image basic database;
on the basis, a user prepares a common image, divides the user image to set a plurality of image areas, and the division can adopt (algorithm) automatic division or (user) manual selection;
then, if an automatic retrieval method is adopted, the local areas of each image are respectively crossed and compared with basic image data in a multimedia image basic database, image characteristics are matched, and association is established; at the moment, the image matching is based on matching the same scene, object and person according to the image characteristics, and particularly, the matching difficulty is reduced by taking a specific scene as a range;
if the manual retrieval method is adopted, information points are set according to local areas of each image, a multimedia image basic database is directly retrieved, multimedia data materials meeting requirements are searched for, and the multimedia data materials are associated with the information points; when a manual retrieval method is adopted, the target information point and the data in the basic database are not necessarily the same scene, object and person; only the relevance that the producer wants to express is needed;
then, each information point is subjected to personalized processing, the content required by the user is reserved through adding, modifying and deleting operations, and personalized expression is added; the accuracy and the specialty of the information are ensured by utilizing a basic database; then, through personalized editing processing, the multimedia image has a unique visual angle, and personalized expression of a user is realized;
finally, merging and storing the sorted data to form a user-made multimedia image; personalized information can be rapidly shared and transmitted; or more three-dimensional personalized data can be stored, and browsing at any time is convenient. And can be used for editing again by other people.
As shown in fig. 2, which is an example of a multimedia image base database; the method comprises five images which are respectively as follows:
base image A: contains 4 information points, A1, A2, A3, A4;
the A1 comprises three items of multimedia data, A11, A12 and A13;
the A2 comprises two items of multimedia data, A21, A22;
the A3 comprises four items of multimedia data, A31, A32, A33, A34;
the A4 comprises three items of multimedia data, A41, A42 and A43;
base image B: contains 1 information point, B1;
the B1 comprises six items of multimedia data, B11, B12, B13, B14, B15 and B16;
a base image C: contains 1 information point, C1;
c1 includes four items of multimedia data, C11, C12, C13, C14;
a basic image D: contains 1 information point, D1;
the D1 includes three items of multimedia data, D11, D12, D13;
a basic image E: contains 3 information points, E1, E2, E3;
e1 includes four items of multimedia data, E11, E12, E13, E14;
e2 includes three items of multimedia data, E21, E22, E23;
e3 includes two items of multimedia data, E31, E32.
As shown in fig. 3, which is a schematic diagram of a user-customized multimedia image U to be edited, an original image of the user is first divided into a plurality of image regions, and the division process can be automatically completed by an image segmentation algorithm, or manually selected by the user, or the two means are combined with each other; taking fig. 3 as an example, five regions are divided, namely, U1, U2, U3, U4 and U5; and after the five regions are subjected to image matching with a multimedia image basic database, the following results are obtained:
u1 is matched with base image B, associating with multimedia data B11, B12, B13, B14, B15, B16;
u2 is matched with the base image C, thereby being associated with the multimedia data C11, C12, C13, C14;
u3 is matched with the base image a as a whole, thereby being associated with information points a1, a2, A3, a 4;
u4 is matched with the information point E3 in the base image E, thereby being associated with the multimedia data E31, E32;
u5 does not match the base image and is temporarily empty.
Then, as shown in fig. 4, on the basis of fig. 3, the user processes the image to form a schematic diagram of an edited user-made multimedia image Ue, which specifically includes:
for U1, partial data is deleted, and only three multimedia data B11, B13, B15 are retained;
for U2, adding one user-defined data, namely U21, to form five multimedia data, C11, C12, C13, C14 and U21;
for U3, partial data is deleted, only three information points a1, a2, A3 are reserved, where:
the A1 comprises three items of multimedia data, A11, A12 and A13;
the A2 comprises two items of multimedia data, A21, A22;
the A3 comprises four items of multimedia data, A31, A32, A33, A34;
for U4, adding two items of user-defined data, namely U41 and U42, to form four items of multimedia data, E31, E32, U41 and U42;
for U5, add one item of user-defined data, U51;
the deleted multimedia data is data that the user feels are not interested in, while the added data is personalized data that the user wants to express the user's own feelings, and the existing data can be edited and modified. And finally, merging and storing the data to form a user-made multimedia image Ue with the user-customized multimedia information points as shown in fig. 3.
In the above, the implementation method of the present invention is introduced, and the application effect of the method is described below by combining with a plurality of specific application scenarios.
Scene one, tourist attraction: the personalized tour guide function is realized, and the experience of the tour process can be enriched;
when a tourist (user) arrives at a certain sight spot, such as a certain building, the tourist only needs to shoot an appearance image of the building outside, and data in the basic database can be called, wherein the data comprise detailed introduction of the tourism content in the building; through the information prompt of each part, the tourist can quickly decide whether the tourist is interested in browsing carefully or not; or ignore the sight spot and allocate the saved time to the sight spot which is more interested in the sight spot;
the existing self-service voice guide system provides voice explanation for each tourist with a complete rule; after the system is adopted, richer explanation contents can be prepared for each scenic spot; firstly, the tourists can take the interesting scenes preferentially, and on the basis, the system can more accurately provide the explanation contents needed by the tourists to be freely selected and played by the tourists, so that personalized tour guide is realized; the guest can select data desired to be saved for a long period of time and viewed again to be saved together with the captured image.
During the process of visiting, some interesting things often happen accidentally, and the visitors can increase the current feeling of voice description recording while using the images to record the things; for example, if a tourist finds that a certain piece of cloud is very characteristic, the image area of the cloud can be used as an information point, and then the information point is described and stored through voice or characters and the like.
Further, when the user shares the user-made multimedia image and applies for adding the user-made multimedia image into the multimedia image basic database, the user-shared data is checked and screened, and then the qualified data is merged into the multimedia image basic database; the method comprises the steps of adding the user-made multimedia images into a multimedia image basic database or superposing effective information points in the user-made multimedia images on the corresponding images of the existing multimedia image basic database.
By the method, a user can participate in the making and updating of the multimedia image basic database, and the scene is described more stereoscopically from more angles; for example, a guest or professional tour guide may make and upload sight point tour guide voice, video, etc.
Scene two, museum:
due to the fact that the exhibits shown by the museum are numerous, many exhibits contain a large amount of detailed information, and the exhibits can be continuously and alternately shown or updated; based on the complete and detailed basic database of the exhibit, better visiting experience can be provided for the user.
In addition, the user can quickly obtain the high-definition image of the exhibit through simple shooting, so that the time and the energy consumed for shooting the complete and clear image are saved, and meanwhile, a certain protection effect on the exhibit can be realized. For example, a user may take profile images of a group of exhibits at a time, and then select only those exhibits in which the user is interested to browse through, and selectively save them.
Scene three, interesting teaching:
the number of basic knowledge points used for teaching is huge, but standardization can be realized to a certain extent; the teaching style and habits of each teacher are different, and the individual teaching tools can be quickly made by each teacher by the following method under the condition of utilizing a standardized teaching library; specifically, the method comprises the following steps:
firstly, establishing a teaching project basic information base which contains rich teaching content information;
secondly, when the teacher prepares for lessons, selecting a plurality of proper images according to the teaching contents, and then associating the information points of the teaching contents with the images; the teacher edits and makes a personalized teaching multimedia image according to the respective style;
thirdly, in the teaching process, firstly displaying the image, then freely searching interest points related to the teaching theme in the image by students, if the interest points coincide with the hidden information points, activating corresponding teaching contents, and explaining by teachers; therefore, the teaching process has good interaction effect and is full of interestingness;
of course, the students can also save the multimedia images produced by the teachers, edit the multimedia images, add personal learning notes on the basis of the multimedia images, and the like, so that the students can review the multimedia images conveniently.
Scene four, mall, supermarket, shop:
firstly, a customer can quickly know various data of the commodity, including price, performance parameters, characteristics, preferential activities, evaluation of other customers and the like, by shooting the image of the commodity, so that a self-service shopping guide process is realized. Of course, the images taken by the customers may contain various commodities, and only the commodities in which the customers are interested can be selected for further understanding.
If the customer can not quickly decide to buy, the user can remember the alternative commodities in more detail through the self-made multimedia images and can compare and select the commodities at the later stage without omission.
Further, when similar attributes exist among a plurality of information points of the user-made multimedia image, the user can select a plurality of information points at the same time, the system automatically compares and analyzes the multimedia data in the information points, searches data which can be compared with each other, and displays the comparison result.
For example, customers often wish to perform a comparative analysis of several similar items; similar commodities in a supermarket are usually placed at adjacent positions, and quick comparison and analysis can be completed by shooting an image of a certain shelf and then selecting a specified commodity in the image according to a basic database, so that customers can be helped to select the favorite commodities.
And a fifth scenario, skill training and field fault diagnosis:
when a complex large-scale equipment facility is faced, the staff is usually trained in the post skill, and the training efficiency can be improved by adopting the following methods:
firstly, subdividing the structure of complex equipment and facilities, and shooting images of various details or directly importing drawing data to form images; then, making basic information for each subdivision structure, and associating the basic information with the image to form a multimedia image basic database;
secondly, when the staff contact the equipment and facilities, if the staff encounters an unknown part, the staff can shoot the image and match the image with the multimedia image basic database, and then can learn at any time;
the training process, through shoot live picture, through comparing and studying, when meeting the technical data that must record and study repeatedly, can edit and store the professional data that need keep to the picture, and can add personalized label, such as some questions or thinking, etc..
Further, when the equipment and facilities are located in different places and the technical level of the field maintenance engineer is low, the efficiency of finding and solving the problem is low, and the following method can be adopted:
firstly, a series of standard flow multimedia images for troubleshooting can be manufactured according to experience, and field personnel can perform troubleshooting according to the guidance of the multimedia images;
secondly, shooting an image of a specific position by a field worker according to the instruction, and marking an information point on the image and explaining the further operation after the image is analyzed by a remote technician; gradually guiding field personnel to carry out troubleshooting;
thirdly, the field personnel can carry the camera equipment and use wearable equipment as the best, the camera equipment continuously shoots and is matched with the multimedia image basic database in the process of field operation, and when the field personnel enter a specific area, the multimedia information is played, and the field personnel are prompted to carry out related routine operation or risk prompt.
In addition, after the scene is electronized, if an emergency or accident occurs, only images need to be shot, the positions where problems occur are marked, and descriptions of the problems are added; then the multimedia image is sent to an alarm system, so that the position of the accident and the key information of the accident can be quickly confirmed; the alarm efficiency is improved; the problem that the alarm personnel can not accurately express the key information of the accident when being unfamiliar with the surrounding environment is avoided.
The invention is not limited to the above embodiments, and those skilled in the art can make equivalent modifications or substitutions without departing from the spirit of the invention, and such equivalent modifications or substitutions are included in the scope defined by the claims of the present application.
Claims (8)
1. The information inheriting and superposing method of the multimedia image system is characterized in that: the multimedia image is characterized in that one or more information points are arranged on the image, multimedia data are adopted to describe each information point, and then the image and the multimedia data corresponding to each information point are merged and stored; the multimedia data is one or any combination of more of characters, audio, images and videos; wherein, the information points are corresponding to the characteristic images of specific point positions or local areas in the images; when a user browses a multimedia image, the user firstly sees the image, and then selects the local area position corresponding to each information point in the image, namely the multimedia data corresponding to the information point can be played;
the multimedia image system comprises a multimedia image basic database and a user self-made multimedia image; processing by adopting an automatic retrieval and processing method or/and a manual retrieval and processing method;
the automatic retrieval and processing method comprises the steps of extracting scenes, objects and people in user images, automatically matching the scenes, the objects and the people with basic images in a multimedia image basic database, and identifying image characteristics, namely automatically searching whether the basic images containing the same scenes, the objects and the people exist or not; the automatic retrieval and processing method at least comprises the following steps:
s101, collecting basic images, preparing multimedia materials, then associating the basic images with the multimedia materials, and manufacturing a multimedia image basic database;
s102, carrying out image segmentation and identification on the common image of the user through an image identification algorithm, and extracting a plurality of relatively independent image local areas; or a user manually selects a plurality of image local areas; then, cross comparison is carried out on each image local area and basic image data in a multimedia image basic database respectively, and image features are matched;
s103, setting the image local area successfully matched with the common image as an information point, sequentially superposing and copying the multimedia data of the matched information point or the whole multimedia image contained in the multimedia image basic data into the common image provided by the user, and associating the multimedia data with the corresponding information point, so that the common image of the user is upgraded into the multimedia image of the user;
s104, the user carries out personalized browsing and editing on the multimedia image of the user, namely, the information point and the multimedia data in the multimedia image are operated, and the specific operation is one or any combination of more of addition, modification and deletion;
s105, finally, forming a user self-made multimedia image which corresponds to the situation of the user image and is recorded with the user personalized multimedia information points;
the manual retrieval and processing method comprises the steps that the manual retrieval refers to the steps of extracting scenes, objects and people in images of a user, inputting keywords related to the scenes by the user, searching basic images containing keyword descriptions in a multimedia image basic database, and completing matching after the basic images are confirmed by the user; the manual retrieval and processing method at least comprises the following steps:
s201, collecting basic images, preparing multimedia materials, then associating the basic images with the multimedia materials, and manufacturing a multimedia image basic database;
s202, a user prepares a common image for expressing a certain theme idea, marks specific point positions or local areas in the image and forms a plurality of information points;
s203, the user carries out personalized retrieval on the multimedia image basic database according to the meaning to be expressed by each information point, finds out a multimedia data material meeting the requirement, and then superposes and copies the selected multimedia data or the whole multimedia image into a common image provided by the user and associates the selected multimedia data or the whole multimedia image with the corresponding information point; and operating each information point, wherein the specific operation is one or any combination of more of addition, modification and deletion;
and S204, finally, forming the user self-made multimedia image which is based on the multimedia image basic database and highlights the theme idea which the user wants to express and is recorded with the personalized multimedia information point.
2. The information inheriting and superimposing method for a multimedia image system according to claim 1, wherein: when the information point of the user-made multimedia image is related to the multimedia image, the related multimedia image is firstly displayed when the information point is consulted, then the information point in the related multimedia image can be continuously selected for further browsing, and so on.
3. The information inheriting and superimposing method for a multimedia image system according to claim 1, wherein: when a multimedia image basic database is manufactured, image acquisition is respectively carried out on the same scene from a plurality of angles, or/and a plurality of positions, or/and a plurality of local areas, or/and a plurality of time nodes, so that a group of basic images are formed, or 3D modeling is carried out on the scene, and then association with information points is completed; in the matching process of step S102, not only one-to-one matching between the user image and the base image is supported, but also one-to-many or many-to-many matching between the user image and the base image is supported; therefore, the user image and the basic image are quickly matched; the matching process adopts a deep learning image recognition algorithm, and if the matching result is wrong, the user can check the matching result and then carry out re-matching.
4. The information inheriting and superimposing method for a multimedia image system according to claim 1, wherein: setting category labels for multimedia data describing each information point, so that a user can quickly select interested information; and moreover, the user can set own preference, and the system performs comparative analysis and preferentially displays information points interested by the user according to the user preference and the category labels, so that the user can browse conveniently.
5. The information inheriting and superimposing method for a multimedia image system according to claim 1, wherein: when a user shares a user self-made multimedia image and applies for adding the user self-made multimedia image into a multimedia image basic database, after checking and screening user shared data, merging qualified data into the multimedia image basic database; the method comprises the steps of adding the user-made multimedia images into a multimedia image basic database or superposing effective information points in the user-made multimedia images on the corresponding images of the existing multimedia image basic database.
6. The information inheriting and superimposing method for a multimedia image system according to claim 1, wherein: when the similar attributes exist among a plurality of information points of the user-made multimedia image, the user can simultaneously select a plurality of information points, the system automatically compares and analyzes the multimedia data in the information points, searches data which can be mutually compared, and displays the comparison result.
7. The information inheriting and superimposing method for a multimedia image system according to claim 1, wherein: when the establishment of the multimedia image basic database is based on a public scene, respectively shooting scenes in the public scene to form basic images on the basis of the scope governed by the public scene; then, the shot basic images are sorted and edited, and all the information points are respectively superposed into all the basic images, so that a multimedia image basic database is formed, and multi-angle and three-dimensional description of the public scene is realized.
8. The information inheriting and superimposing method for a multimedia image system according to claim 7, wherein: when a multimedia image basic database is manufactured, correlating basic images with position data in an electronic map of a public scene; the function is as follows:
firstly, after a user shoots an image and matches the image with a basic image in a multimedia image basic database, the position of the user in a public scene can be determined, and further, the service of navigation in the scene is provided for the user;
secondly, performing context correlation analysis on images continuously shot by the user within a certain time period so as to determine the position and the travel route of the user in the public scene, and further reducing the image matching range of the step S102 by taking the recent user position data and the travel route of the user as the basis, thereby improving the matching efficiency.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011027136.3A CN112100407B (en) | 2020-09-25 | 2020-09-25 | Information inheriting and superposing method of multimedia image system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011027136.3A CN112100407B (en) | 2020-09-25 | 2020-09-25 | Information inheriting and superposing method of multimedia image system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112100407A true CN112100407A (en) | 2020-12-18 |
| CN112100407B CN112100407B (en) | 2021-05-21 |
Family
ID=73756508
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011027136.3A Active CN112100407B (en) | 2020-09-25 | 2020-09-25 | Information inheriting and superposing method of multimedia image system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112100407B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112651656A (en) * | 2020-12-31 | 2021-04-13 | 四川弘和通讯有限公司 | Method and system for detecting dynamic trend of fire condition based on timeline mode |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334796A (en) * | 2008-02-29 | 2008-12-31 | 浙江师范大学 | Personalized and synergistic integration network multimedia search and enquiry method |
| CN102708355A (en) * | 2011-02-15 | 2012-10-03 | 索尼公司 | Information processing device, authoring method, and program |
| US20130086277A1 (en) * | 2003-02-05 | 2013-04-04 | Silver Screen Tele-Reality, Inc. | System, method, and computer readable medium for creating a video clip |
| CN106713840A (en) * | 2016-06-28 | 2017-05-24 | 腾讯科技（深圳）有限公司 | Virtual information display method and device |
| CN107193904A (en) * | 2017-05-11 | 2017-09-22 | 浙江唯见科技有限公司 | A kind of books VR and AR experience interactive system |
| CN107633241A (en) * | 2017-10-23 | 2018-01-26 | 三星电子（中国）研发中心 | A kind of method and apparatus of panoramic video automatic marking and tracking object |
-
2020
- 2020-09-25 CN CN202011027136.3A patent/CN112100407B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130086277A1 (en) * | 2003-02-05 | 2013-04-04 | Silver Screen Tele-Reality, Inc. | System, method, and computer readable medium for creating a video clip |
| CN101334796A (en) * | 2008-02-29 | 2008-12-31 | 浙江师范大学 | Personalized and synergistic integration network multimedia search and enquiry method |
| CN102708355A (en) * | 2011-02-15 | 2012-10-03 | 索尼公司 | Information processing device, authoring method, and program |
| CN106713840A (en) * | 2016-06-28 | 2017-05-24 | 腾讯科技（深圳）有限公司 | Virtual information display method and device |
| CN107193904A (en) * | 2017-05-11 | 2017-09-22 | 浙江唯见科技有限公司 | A kind of books VR and AR experience interactive system |
| CN107633241A (en) * | 2017-10-23 | 2018-01-26 | 三星电子（中国）研发中心 | A kind of method and apparatus of panoramic video automatic marking and tracking object |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112651656A (en) * | 2020-12-31 | 2021-04-13 | 四川弘和通讯有限公司 | Method and system for detecting dynamic trend of fire condition based on timeline mode |
| CN112651656B (en) * | 2020-12-31 | 2023-11-07 | 四川弘和通讯有限公司 | Method and system for detecting dynamic trend of fire based on time line mode |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112100407B (en) | 2021-05-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019214453A1 (en) | Content sharing system, method, labeling method, server and terminal device | |
| US20080147325A1 (en) | Method and system for providing augmented reality | |
| CN106255968A (en) | Natural language picture search | |
| US20050216464A1 (en) | Automated authoring tool and method to facilitate inclusion of maps and other geographical data into travelogues | |
| CN102257492A (en) | System and method for generating a context enhanced work of communication | |
| CN103605706A (en) | Knowledge map based resource retrieval method | |
| US10223430B2 (en) | Intelligent playbook application | |
| MX2010008950A (en) | System and method for global historical database. | |
| CN116050429B (en) | Geographic environment entity construction system and method based on multi-mode data association | |
| CN103399870A (en) | Visual word bag feature weighting method and system based on classification drive | |
| CN108205566B (en) | Method and device for managing point cloud based on track and navigation equipment | |
| CN107004023A (en) | The semantic expansion of track data | |
| Maybury | Multimedia information extraction: Advances in video, audio, and imagery analysis for search, data mining, surveillance and authoring | |
| CN108509567B (en) | Method and device for building digital culture content library | |
| CN112100407B (en) | Information inheriting and superposing method of multimedia image system | |
| KR20190107252A (en) | A System of Providing Theme Travel AI Curation Based on AR through Customization Learning of Virtual Character | |
| CN110414001A (en) | Sentence generation method and device, storage medium and electronic device | |
| CN105845020A (en) | Real-scene map making method and device | |
| Sheehan et al. | Learning to interpret satellite images using wikipedia | |
| Caquard et al. | Mapping memories of exile | |
| CN114967914A (en) | Virtual display method, device, equipment and storage medium | |
| Münster et al. | Where are we now on the Road to 4d Urban History Research and Discovery? | |
| CN105095443A (en) | Information value-addition method and device based on super sketchpad | |
| CN111258409B (en) | Feature point identification method and device for man-machine interaction | |
| Li et al. | Social-aware visualized exploration of tourist behaviours |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |