KR20100029725A - System and method for managing image information using object extracted from image - Google Patents

Abstract

PURPOSE: An image information managing system using a photographed object extracted from a photographed image and a method thereof are provided to efficiently manage and search a photographed image using photographing object information and attributes of photographed objects. CONSTITUTION: An information input unit(130) inputs a photographing image and input information. A 3D model unit(140) generates a virtual image in a virtual space realized by objects. An object extracting unit(121) compares the virtual image with the photographing image. The object extracting unit extracts each object constituting the photographing image as photographing objects. The object extracting unit generates photographing object information.

Description

System and method for managing image information using object extracted from photographed image

The present invention relates to an image information management system and a method thereof, and more particularly, extracting photographing objects included in a photographing image using vector information related to the photographing image, and managing image information using the extracted photographing object. The present invention relates to an image information management system using a photographing object extracted from retrievable photographed images, and a method thereof.

In general, images generated by video cameras such as cameras and camcorders in a variety of business fields, including construction projects are used for recording because they contain a large amount of integrated information.

In particular, with the recent spread of digital cameras and digital camcorders, thousands and tens of thousands of photos and videos are generated in various places including construction sites and factories. However, pictures and videos, which are image-oriented information delivery media, do not contain information on who, when, where, what, how, and why.

1 is a diagram illustrating a general photographed image. For example, FIG. 1 (a) is a photographed image of a building, and it is difficult to know where and why a certain building was photographed. On the other hand, Figure 1 (b) is a photographed image of the interior of the building, as in Figure 1 (a) it is also difficult to know what floor of which building and what was taken. Therefore, there is a problem of recording the shooting object and the shooting purpose of the shooting image one by one, and if there are a lot of similar buildings, it is difficult to know which building is the building.

Therefore, the photographer and videographer had to separately record the shooting location, the subject of the shooting, and the purpose of the shooting in the photo and video. On the other hand, if there is no such complicated recording process, for example, if similar pictures occur in repeated floors at the construction site, it is difficult to determine where each picture was taken, so that many pictures containing important construction information are lost or obsolete. There is a problem.

On the other hand, a lot of money and time is required to record a subject and a place to shoot a lot of photos and videos, and even if recorded, there is a problem that it takes a great time and money to manage and search photos and videos.

There is a growing need for a management system that automatically extracts and saves the shooting object and the shooting object of the taken shooting image, and effectively manages the shooting image by using the extracted shooting object and shooting purpose.

The problem to be solved by the present invention is extracted from the photographed image, which can easily obtain the shooting object information about what was photographed using the photographed image, vector information and the 3D model and the purpose of photographing why. The present invention provides an image information management system using a photographing object and a method thereof.

In order to solve the above problems, the present invention receives a recording image including the shooting time information on the time of shooting and the shooting angle of view information on the angle of view at the time of shooting and input information including the vector information of the shooting image. An information input unit; A 3D model unit which stores objects having real world coordinate information and an object property including a name of the object, and generates a virtual image based on photographing angle information and the vector information in a virtual space formed of the objects; An object extracting unit for extracting each object constituting the captured image by comparing the virtual image with the captured image as a photographing object, and generating photographing object information including the name of the extracted photographing object; And an image information database for storing photographing object information for each photographing object and photographing object, wherein the vector information of the photographing image is information about the position and the photographing direction of the photographing apparatus at the time of photographing. Image including position information, shooting orientation information on the azimuth angle of the lens axis of the camera, vertical tilt information of which the lens axis of the camera is tilted with respect to the gravity direction, and horizontal tilt information of which the horizontal axis of the photographed image is tilted with respect to the horizon To provide an information management system.

Preferably, the 3D model unit further stores the event information, including the event name and the event duration associated with the object for each object, the management system compares the shooting time information and the event information of the shooting object, and shooting The apparatus may further include an object extracting unit for extracting a photographing object whose time information exists within an event period of the photographing object and storing the event name in the image information database as a photographing purpose.

According to the present invention, by using the captured image, the vector information and the 3D model, it is possible to easily obtain the shooting object information on what the captured image is taken and the shooting purpose of why the captured image, and the shooting object information and shooting The attributes of objects can be used to efficiently manage and search captured images.

First, the terms used in the present invention will be summarized first.

The photographed image refers to an image photographed by a photographing apparatus including a camera and a camcorder, and includes photographing time information which is information on a time at the time of photographing and photographing angle of view information on an angle of view at the time of photographing.

In recent years, in addition to the photographed image in the image file containing the photographed image, meta information (exif) related to the device control information of the photographing device, for example, the manufacturer and model of the photographing device, photographing time, image recording time, shutter speed, lens focal length (View angle), aperture value, exposure compensation value, shooting program, metering mode, white balance setting, B / W reference point, pixel compression / sampling / positioning (Y: Cb: Cr), component setting and compression ratio (Y to C), Color space, x resolution, y resolution, x size, y size, unit, orientation, file compression method, image name, etc. can be additionally recorded. In the present invention, the photographed image may further include all or part of the device control information in addition to the photographed image information and the photographing time information of the time at the photographing time.

The vector information of the photographed image is information for identifying a photographing subject, that is, a subject photographed by the photographing apparatus, photographing position information about the three-dimensional position of the photographing apparatus, photographing azimuth information about the azimuth angle toward the photographic lens axis, photographing lens The vertical tilt information in which the axis is inclined with respect to the gravity direction and the horizontal tilt information in which the horizontal axis of the captured image is inclined with respect to the horizon may further include shooting distance information that is a distance from the camera to the shooting object. The vector information is information about the position and the direction of photographing the camera when the shutter is pressed, that is, when the photographed image is generated.

The recording position information of the three-dimensional position of the camera indicates the shooting position in three-dimensional coordinates, the GPS position information (latitude, longitude, altitude) by the GPS system, or the coordinate concept using other similar techniques. to be.

2A to 2C are diagrams illustrating vector information of a photographed image, wherein a dotted line indicates a lens axis (shooting direction) of the photographing unit 110, a dashed dotted line indicates a horizon line, a dashed dotted line indicates a gravity direction, and a solid line indicates an image Each means a horizontal axis.

Referring to FIG. 2A, the azimuth angle α denotes a horizontal angle formed by the lens axis toward the subject 7 of the photographing unit 110 with the north, that is, a direction toward the photographing subject from the photographing unit 110 as the north. It means the horizontal angle and is expressed clockwise with respect to true north. Therefore, the azimuth angle may have a range of 0 to 360 degrees.

Referring to FIG. 2B, the vertical tilt refers to an angle β of the lens axis toward the subject 7 of the photographing unit 110 in the direction of gravity in the vector information generating apparatus 100. For example, when photographing a subject in a direction perpendicular to the ground in the air, the vertical tilt is 0 degrees, and when photographing the air in a direction perpendicular to the ground, the vertical tilt is 180 degrees. On the other hand, the photographing distance information means the distance l from the lens of the camera to the subject.

Referring to FIG. 2C, the horizontal tilt means an angle γ formed between the horizontal axis of the captured image and the horizon direction. For example, the vector information generating apparatus 100 that is photographing the subject 7 in FIG. 2C is inclined by γ ° in the counterclockwise direction.

Analyzing the vector information of the photographed image can be estimated the three-dimensional position of the object to be photographed, to be precise, the three-dimensional position of the object located in the center of the image in the photographed image can be estimated. Therefore, if the object to be photographed is a fixed position on the earth, knowing the vector information of the subject to know the three-dimensional position of the object to be photographed on the earth, it is possible to estimate exactly what the subject.

Meanwhile, as described above, the image information may include device control information of the image photographing apparatus. Device control information of the imager includes information on the focal length, which is closely related to the angle of view of the imager. Therefore, when the focal length is known, photographing angle information of the angle of view of the camera can also be known. When the angle of view information of the image camera is added to the above-described vector information, the imager can more accurately estimate the captured image.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Like reference numerals in the drawings denote like elements.

3 is a block diagram showing a video information management system according to the present invention.

Referring to FIG. 3, the image information management system 100 includes an information input unit 130, an information management unit 130, a 3D model unit 140, and an image information database (DB, 150). In addition, the information retrieval unit 110 may be further included.

The information input unit 120 serves to receive various input information through wired / wireless communication or an interface with an external device, and the input information includes a captured image and vector information of the captured image.

The photographed image refers to an image photographed by a photographing apparatus including a camera and a camcorder, and includes photographing time information, which is information on time at the time of photographing, and photographing angle of view information on an angle of view at the time of photographing. The photographed image may further include the device control information when the photographed image is a photographed image generated by a photographing apparatus that generates an image file including device control information (meta information).

The vector information of the photographed image is information for identifying a photographing subject, that is, a subject photographed by the photographing apparatus, photographing position information on the three-dimensional position of the photographing apparatus, photographing azimuth information about the azimuth angle toward the photographic lens axis, photographing lens The vertical tilt information in which the axis is inclined with respect to the gravity direction and the horizontal tilt information in which the horizontal axis of the captured image is inclined with respect to the horizon may further include shooting distance information that is a distance from the camera to the shooting object. The vector information is information about the position and the direction of photographing the camera when the shutter is pressed, that is, when the photographed image is generated.

Since the vector information may be substituted into the real world, when the photographer photographs a photographing target fixed on the earth, it may be determined which photographic subject the photographer photographed.

The input information input through the information input unit 120 is provided to the object extractor 121 and the 3D model unit 140 of the information manager 120.

The 3D model unit 140 stores an object having real world coordinate information and an object attribute including the name of the object, and a virtual space 141 implemented with the objects. The virtual 3D model has unique names and properties for each object (object, point, line, face, and solid) constituting the virtual space.

The objects constituting the 3D model unit 140 have coordinate information corresponding to the real world, and the (unique) names and attributes of these objects are stored in the object DB 142 in the 3D model DB 142. Objects have various properties, including various properties, for example their location, manufacturer, price, event name, event duration.

In many industries, including the construction business field, a computer-based design method can be used, and the 3D model unit 140 has a virtual model composed of each object in a virtual space to be used in each industrial field.

For example, in the construction business field, the 3D model unit 140 has a virtual space in which a building is modeled by combining points, lines, faces, and three-dimensional objects, and the objects have attributes (location information, material information, price). Information) and event information (construction information, process information, process schedule information) are integrated.

The 3D model unit 140 may have real world coordinate information so that the 3D model unit 140 may mimic the real world, and change the screen to various viewpoints such as an image camera of the real world through a virtual camera in a virtual space. Therefore, the virtual world can be expressed immediately similar to the real world. Therefore, the captured image taken in the real world includes the same information as the virtual image generated through the virtual camera of the 3D model unit 140.

As described above, the 3D model unit 140 generates a virtual image based on the photographing angle information and the vector information in the virtual space, and provides the generated virtual image to the object extractor 121.

The information manager 120 includes an object extractor 121, a representative extractor 122, and an object extractor 123.

The object extracting unit 121 compares the virtual image with the captured image, extracts each object constituting the captured image as a photographing object, and generates photographing object information including the name of the extracted photographing object.

If the vector information and the moving picture angle information are present, a virtual image almost similar to the actual photographed image may be generated in the virtual space of the 3D model unit 140. On the other hand, since the virtual image is an image composed of each object in the virtual space, when comparing the virtual image and the captured image, it is possible to extract the names and properties of the objects included in the captured image. In the present invention, the object included in the photographed image is a photographing object, and information including the name of the photographing object is determined as photographing object information.

The image information database 150 is a database (database, DB) for storing photographing object information and attribute information of each photographing object for each photographing image and photographing object, and various information such as photographing purpose, representative object, and representative object to be described later will be described. Can be stored.

Meanwhile, the 3D model DB 142 may further store event information including the event name and the event duration associated with the object for each object. An event refers to an event associated with each object. Each event has a unique name and a schedule in which the event is performed. For example, in the case of building construction, an event may be an individual process in a building construction, and an event period may be a period in which the individual process is performed.

The object extracting unit 123 compares the shooting time information with the event period of the shooting object, extracts the shooting object in which the shooting time information exists within the event period of the shooting object, and stores the event name in the image information database as the shooting purpose. .

That is, the purpose of shooting corresponds to the purpose of generating the photographed image (the answer is to the purpose of taking the picture ... "Why did you take it?") . Meanwhile, since a plurality of photographing objects may exist in one photographed image, a plurality of photographing objects may have a photographing purpose in one photographed image according to the characteristics of the event.

Meanwhile, the object extraction unit 123 compares the shooting time information with the event information of the shooting object, extracts the shooting object whose shooting time information exists within a predetermined period before and after the event period of the shooting object, and captures the event name in the image information database. It can also be stored as a purpose. The predetermined period can be freely set. For example, if the event period is February 15, 2009 to February 25, 2009, and the predetermined period is 2 days, the shooting time information of the captured image is between February 13, 2009 and February 27, 2009. The event name of the object can be extracted for shooting purposes.

The representative extracting unit 122 extracts a photographing object that is closest to the center of the photographing image among the photographing objects, and stores the photographing object as a representative object in the image information database. Since the photographed image may include a plurality of photographing objects, it is important to select a representative object representing the photographed image. In general, since the most important object is taken in the center of the image and the image is taken, it is preferable to select the photographing object closest to the center of the photographed image as the representative object.

On the other hand, the conditions for selecting the representative object can be freely changed and set, for example, the shooting object occupying the largest area in the captured image can be selected as the representative object, or the shooting of the captured image determined by the shooting time information A photographing object whose time exists within the event period of the photographing object, the entire image of the object is included in the photographing image, or the photographing distance is within a certain distance may be selected as the representative object.

Meanwhile, as described above, the plurality of photographing objects included in one photographed image may have a photographing purpose according to the characteristics of the event. Therefore, the representative extracting unit 122 may extract the photographing object closest to the center of the photographing object among the photographing objects in which the photographing purpose exists and store the representative object in the image information database. If a representative object does not have a shooting purpose, the representative object has representation as an object but does not represent an object for shooting purpose. The object to be selected and stored as the representative object is selected as the object closest to the center of the captured image among the objects having the object of photographing.

Meanwhile, the information manager 130 may generate a new type of object image information including information on a photographing object in order to communicate with other external devices and share the generated information with other systems. Here, the object image information includes the photographed image, the vector information of the photographed image, the photographed object constituting the photographed image, the representative object among the photographed objects constituting the photographed image, and the representative purpose of the photographed image. It may also include all or part of the shooting purpose and the attributes of each shooting object. On the other hand, the photographed image includes photographing time information of the time at the time of photographing and photographing angle of view of the angle of view at the time of photographing in addition to the photographed image image, and may further include all or part of the device control information (meta information). It may be.

Meanwhile, the information input unit 130 may receive a search condition, which is provided to the information search unit 110 to be described later.

The search conditions are combined using at least one of a name of a photographed image, a name of a photographing object, an event name and an event period, a photographing time, a unique name of a photographing device, a photographing position, and a photographing distance.

On the other hand, the search conditions can be combined with various other search conditions in addition to the above search conditions in order to perform various methods of searching the image information database 150, and representative objects (event name of the representative object, event period of the representative object) ), The purpose of the photographing, and the information about the representative object can be optionally combined.

The information search unit 110 includes a search condition unit 111, a search unit 112, and a result provider 113.

The search conditioner 111 serves to provide a search condition provided by the information inputter 130 to the searcher 112 to be described later. The search condition may be provided to the search unit to be described later. The search condition may be input through the information input unit 130 or the search condition stored in the search condition unit 111 may be provided to the search unit 112.

The search unit 112 serves to search and sort the image information database using the search conditions. That is, the search unit 112 searches the image information database 150 by using the search condition, and outputs the captured image included in the image information database according to a given sorting method or makes the corresponding captured image hyperlinked. Give results.

The result provider 113 serves to provide the user with the search results by the searcher 112.

4 is a diagram illustrating an object existing in the virtual space of the 3D model unit, and FIG. 5 is a diagram illustrating an attribute of each object of the 3D model unit.

FIG. 4 (a) illustrates a building modeled in a virtual space such as BIM (building information modeling), and FIGS. 4 (b) to 4 (d) illustrate each object constituting the building. .

As can be seen in Figures 4 (a) to 4 (d), the building modeled in the virtual space of the 3D model unit 140 is composed of three floors, and each floor has a floor and a roof and It consists of a wall, and each wall consists of a copper wall, a west wall, a south wall, and a north wall.

As described above, the 3D model unit may have not only an integrated view but also an individually separated view in the virtual space as shown in each figure of FIG. 4. Accordingly, the 3D model unit may distinguish each object from each other, and thus, even when many objects are included in the captured image, the 3D model unit may extract each object. Attribute and event information for each such object is stored in a DB form, and when each object is extracted, the attribute and event information for the object may also be obtained.

FIG. 5 is a diagram illustrating an object database that stores information about each object, and illustrates an object DB of the building of FIG. 4.

In the object database of FIG. 5, names of objects (which may be object IDs as unique names) and attributes are stored for each object name, and the attributes include the positions of the parts of the building, which are objects. The manufacturer, person in charge, price, event (process name in construction) and event period (process period) are stored.

6 is a diagram illustrating extracting a photographing object, a photographing purpose, and a representative object according to the present invention.

6 (a) illustrates input information input through the information input unit, and an upper image means a captured image, and a lower portion indicates information input together with the captured image. 6 (b) is a diagram illustrating a virtual image generated in a virtual space by the 3D model unit, and FIGS. 6 (c) and 6 (d) show a list of extracted photographing objects and a photographing purpose of each photographing object. , And is a diagram illustrating the representativeness.

The input information input through the information input unit includes the photographed image and the vector information of the photographed image, and the photographed image includes photographing time information regarding the time at the photographing time and photographing angle of view information about the angle of view at the photographing time. The photographing angle information may be input in the form of device control information of the camera at the bottom of FIG.

When the virtual image is generated, the object extractor 121 extracts each object constituting the photographed image as a photographing object by comparing the photographed image of FIG. 6 (a) with the virtual image of FIG. 6 (b). 6 (a) and 6 (b), the objects 1,2,3,4,5,6,7 in the captured image are respectively a, b, c, d, e, f, Corresponding to g, 1,2,3,4,5,6,7, which are objects matching the object of the virtual image, are extracted as the photographing object. 1,2,3,4,5,6,7 extracted as the photographing objects are the same objects as a, b, c, d, e, f, g in the virtual image, and thus, a, b, c, d, e The names and attributes of, f, g are used as the names and attributes of the photographing object. Meanwhile, 8 objects in the captured image are not extracted as the photographing object because they are objects that do not exist in the virtual image.

On the other hand, if each shooting object has a shooting purpose, the shooting purpose can be extracted, Figure 6 (d) is an example of the shooting purpose extracted and stored for each shooting object of Figure 6 (c).

The object extracting unit stores the event name in the image information database when the photographing time information indicating the time at which the photographed image is taken exists within a predetermined period before and after the event period of the photographing object.

FIG. 6 (d) illustrates whether each photographing object of FIG. 6 (c) is representative or not, and the representative extracting unit extracts a photographing object closest to the center of the photographing image and stores the photographing object as a representative object in the image information database. Meanwhile, as described above, the representative object may be determined by various conditions among the photographing objects.

7 and 8 are diagrams illustrating an application example of the image information management system according to the present invention.

FIG. 7 is a diagram illustrating a process schedule table during building construction, and FIG. 8 is a diagram illustrating photographed images photographed at each process period.

There will be a process schedule for the entire building, but for the sake of convenience, only the process for the 3rd floor of the building will be described.

According to the process schedule, the 3rd floor of the building is planned to be completed in 7 weeks, and the process period is determined for each object of the 3rd floor of the building. Each process is an event meaning an event, and 'Week 1' to 'Week 7' mean each event name (name of the process). Each of these events and event periods are stored in the object database and the event database of the 3D model unit.

FIG. 8 refers to a photographing image of a construction in progress during each event on the third floor of a building under construction. Each photographed image of FIG. 8 is a photographed image from which a photographing purpose has already been extracted through the object extracting unit. During the construction, a lot of images are taken, and the captured images are shots of various views, various locations, and various objects.

According to the present invention, a photographing object is extracted from a photographed image, and a photographing purpose of the extracted photographing object may also be extracted. Each photographed image of FIG. 8 uses a search unit for photographed images including a photographing object from which photographing objects are extracted. Search results.

FIG. 8 (a) means a photographed image of a floor taken at Week 1, which is an event period, and 8 (c) means a photographed image taken of a western wall at Week 3, with shaded portions within each event period. Means the object under construction. As shown in FIG. 8, according to the present invention, the captured image photographed within each event period may be searched for and output.

According to the present invention, by using the captured image, the vector information and the 3D model to extract the shooting object information and the shooting object for each shooting object included in the shooting image, the shooting object information and why shooting of what the shooting image is taken It is possible to easily obtain the shooting purpose for the one, and to manage and retrieve the captured image efficiently by using the shooting object information and the shooting purpose.

Hereinafter will be described the image information management method according to the present invention. Since the image information management method according to the embodiment of the present invention is essentially the same as the function of the image information management system, redundant description thereof will be omitted.

9 is a flowchart illustrating a method of managing image information according to the present invention.

The image information management method according to the present invention includes a step (S10) of extracting a photographing object to generate photographing object information, further extracting a representative object (S20), extracting a photographing purpose (S30), At least one of the step S40 of extracting the representative object and the search step S50 using the search condition may be selectively included.

10 is a flowchart for explaining a step of generating photographing object information.

First, the information input unit receives a photographing image including photographing time information about a time at the time of photographing and photographing angle of view information about an angle of view at the time of photographing, and input information including vector information of the photographed image (S11).

The 3D model unit implements a virtual space with an object having real world coordinate information, and generates a virtual image using photographing angle information and vector information in the virtual space.

The object extracting unit extracts a photographing object using the generated virtual image, and generates and stores photographing object information on the photographing object (S12 and S13).

That is, the object extracting unit compares the virtual image and the captured image, extracts each object constituting the captured image as a photographing object (S12), generates photographing object information including the name of the extracted photographing object, and generates the photographed image. The object information is stored in the image information database for each of the captured image and the captured object (S13).

11 is a flowchart for explaining a step of extracting a representative object.

In the representative object extraction step, the representative extracting unit extracts a photographing object that is closest to the center of the photographed image from among the photographing objects, and stores the photographing object as a representative object in the image information database, and stores the event information of the representative object in the image information database.

Referring to the representative object extraction step in detail, first, the representative extracting unit determines, for each photographing object, whether the photographing object is the photographing object closest to the center of the photographing image (S21).

The representative extracting unit stores the irradiated photographing object as a representative object in the image information database if the photographing object to be investigated is the closest to the center of the photographed image (S22), and extracts event information of the representative object. Store in video information database.

Meanwhile, when the photographing object to be examined is not the photographing object closest to the center of the photographed image, the representative object unit determines the representativeness of the next photographing object by examining the next photographing object of the photographed image (S22).

Meanwhile, the method of extracting the representative object may be various in addition to the method of extracting the object closest to the center of the captured image. For example, it occupies the largest area in the photographed image among the photographed objects, or the photographing time information is present within the event period of the photographing object, or the photographed image includes the whole view of the object, or from the photographed position. A photographing object having a distance (= distance from the photographing device to the photographing object) within a certain distance can be extracted as the representative object. The predetermined distance may be set in various ways.

12 is a flowchart for explaining a step of extracting a photographing object.

The object extracting unit compares the shooting time information with the event information of the shooting object and determines whether the shooting time information exists within the event period of the shooting object (S31).

When the shooting time information exists within the event period of the shooting object, the object extracting unit stores the event name of the shooting object in the image information database as the shooting object (S32).

After extracting the shooting time information does not exist within the event period of the shooting object or after performing step S32, the object extracting unit checks whether all the shooting objects have been determined (S33).

If the object extraction unit does not judge all the photographing objects, it selects the next photographing object of the surveyed object (S32) to perform the extraction object extraction step (S31). do.

13 is a flowchart for explaining a step of extracting a representative object.

The object extracting unit compares the shooting time information with the event information of the shooting object and determines whether the shooting time information exists within the event period of the shooting object (S41).

The representative extracting unit determines whether the photographing time information is the photographing object that is closest to the center of the photographing image with respect to the photographing object existing within the event period (S42).

If the photographing object is closest to the center of the photographed image, the representative extracting unit stores the event name of the photographing object in the image information database (S43).

On the other hand, in the step S41, the target extractor selects the next photographing object for the next investigation when the photographing time information does not exist within the event period, and in step S42, the representative extracting unit selects the photographing object closest to the center of the photographed image. If not, the next photographing object is selected for the next survey (S44). The next photographing object selected performs steps S41 and S43.

14 is a flowchart showing a search step using a search condition.

First, the information input unit receives a search condition combined with a captured image, photographed object information, event information, and photographed time information. Meanwhile, as described above, various search conditions may be input for various types of search, name of the photographed image, name of the photographing object, event name and event duration, photographing time, unique name of the photographing apparatus, photographing position, and photographing distance. The combined search condition may be input using at least one of the information about.

The search unit searches the image information database according to the input search condition (S52), and the result provider provides the user with the search result by the search unit.

The method of the present invention can also be embodied as computer readable code on a computer readable recording medium. The computer-readable recording medium includes all kinds of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like, and may also be implemented in the form of a carrier wave (for example, transmission over the Internet). Include. The computer readable recording medium can also be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion.

In the above described the present invention with reference to the specific embodiment shown in the drawings, but this is only an example, those of ordinary skill in the art to which the present invention pertains various modifications and variations therefrom. Therefore, the protection scope of the present invention should be interpreted by the claims to be described later, and all the technical ideas within the equivalent and equivalent ranges should be construed as being included in the protection scope of the present invention.

1 is a diagram illustrating a general photographed image.

2A to 2C are diagrams illustrating vector information of a captured image.

3 is a block diagram showing a video information management system according to the present invention.

4 is a view for explaining an object existing in the virtual space of the 3D model unit.

5 is a diagram illustrating an attribute of each object of the 3D model unit.

6 is a diagram illustrating extracting a photographing object, a photographing purpose, and a representative object according to the present invention;

7 and 8 are each a view for explaining an example of the use of the image information management system according to the present invention.

9 is a flowchart illustrating a method of managing image information according to the present invention.

10 is a flowchart for explaining a step of generating photographing object information.

11 is a flowchart for explaining a step of extracting a representative object.

12 is a flowchart for explaining a step of extracting a photographing purpose;

Fig. 13 is a flowchart for explaining a step of extracting a representative object.

14 is a flowchart showing a search step using a search condition;

Claims (14)

An information input unit for receiving a photographing image including photographing time information on a photographing time and photographing angle of view information on an angle of view at the time of photographing, and input information including vector information of the photographing image; 3D model that stores objects having real world coordinate information and object properties including names of the objects, and generates virtual images based on the photographing angle information and the vector information in a virtual space implemented with the objects. part; An object extracting unit which compares the virtual image with the photographed image, extracts each object constituting the photographed image as a photographing object, and generates photographing object information including a name of the extracted photographing object; And And a video information database for storing the photographing object information for each photographed image and photographing object. The vector information of the photographed image is information on the position and the direction of the camera at the time of shooting, the shooting position information on the three-dimensional position of the camera, the shooting azimuth information on the azimuth angle to the lens axis of the camera, the lens axis of the camera And a vertical tilt information inclined with respect to the gravity direction, and a horizontal tilt information in which the horizontal axis of the captured image is inclined with respect to the horizon. The method of claim 1, wherein the 3D model unit For each object, it further stores event information including the event name and its duration. The management system Compare the shooting time information with the event information of the shooting object, extract the shooting object in which the shooting time information exists within a predetermined period before and after the event period of the shooting object, and record the event name in the image information database. The image information management system further comprises an object extraction unit for storing. The method of claim 1, wherein the 3D model unit For each object, it further stores event information including the event name and its duration. The management system And a representative extracting unit extracting a photographing object closest to the center of the photographing object from the photographing object and storing the photographing object as a representative object in the image information database, and storing event information of the representative object in the image information database. Information management system. The method of claim 1, wherein the 3D model unit For each object, it further stores event information including the event name and its duration. The management system Among the photographing objects, occupies the largest area in the photographed image, or the photographing time information exists within the event period of the photographing object, or the entire image of the object is included in the photographing object, or from the photographing position. And a representative extracting unit for extracting a photographing object having a distance within a predetermined distance, and storing the photographing object as the representative object in the image information database, and storing the event information of the representative object in the image information database. The system of claim 2, wherein the management system is And a representative extracting unit extracting a photographing object closest to the center of the photographing image from among photographing objects having the photographing purpose and storing the photographing object as a representative object in the image information database. The method of claim 2, wherein the information input unit Further receiving a combined search condition using at least one of information on a photographed image, a name of a photographing object, an event name and an event period, a photographing time, a photographic name, a photographing location, and a photographing distance; The management system And a search unit which searches and sorts photographed images of the photographed image database according to the search condition, and provides searched sorted search results. The method of claim 2, wherein the information input unit Receiving a search condition combined with the photographed image, the photographed object information, the event information, and the photographing time information; The management system And a search unit which searches and sorts representative objects of the photographed image database according to the search condition, and provides searched sorted search results. (a) receiving a photographing image including photographing time information on a photographing time and photographing angle of view information on an angle of view at the time of photographing, and input information including vector information of the photographing image; (b) realizing a virtual space with an object having real world coordinate information, and generating a virtual image using the photographing angle information and the vector information in the virtual space; (c) extracting each object constituting the captured image as a photographing object by comparing the virtual image with the photographed image, and generating photographing object information including a name of the extracted photographing object; And (d) storing the photographing object information in an image information database for each photographed image and photographing object; The vector information of the photographing image is information about the position and the direction of the photographing device at the time of photographing. And vertical tilt information inclined with respect to the gravity direction, and horizontal tilt information in which the horizontal axis of the captured image is inclined with respect to the horizon. The method of claim 8, wherein the method is (e) providing event information including an event name and an event duration associated with the object for each object; And (f) extracting a photographing object closest to the center of the photographing image from the photographing object, storing the photographing object as a representative object in the image information database, and storing event information of the representative object in the image information database; How to manage video information. The method of claim 8, wherein the method is (e) providing event information including an event name and an event duration associated with the object for each object; And (f) occupies the largest area in the photographed image among the photographed objects, or the photographing time information is present in the event period of the photographing object, or the photographed image includes the whole view of the object, or photographed And extracting a photographing object having a distance from a location within a predetermined distance and storing the photographing object as a representative object in the image information database, and storing event information of the representative object in the image information database. The method of claim 8, wherein the method is (e) providing event information including an event name and an event duration associated with the object for each object; And (f) extracting a photographing object in which the photographing time information exists within a predetermined period before and after the event period of the photographing object, and storing the event name in the image information database as a photographing purpose. . The method of claim 11, wherein the method is (g) extracting a photographing object closest to the center of the photographing image from among photographing objects in which the photographing purpose exists and storing the representative object in the image information database as a representative object. The method of claim 10, wherein the method is (h) receiving a combination of search conditions using at least one of information about a photographed image, a name of a photographing object, an event name and event duration, a photographing time, a photographic name, a photographing location, and a photographing distance; ; And (i) providing search results of searching and sorting the photographed images of the photographed image database according to the search condition. The system of claim 3 or 5, wherein the system is An image for generating object image information including the photographed image, the vector information of the photographed image, a photographed object constituting the photographed image, a representative object among photographed objects constituting a photographed image, and a representative purpose of the photographed image. Information management system.

Images