JP2021196675A - Computer system and program - Google Patents

Abstract

To properly correct distortion of a captured image.SOLUTION: A computer system includes a processor. The processor acquires an original image including a feature to be captured, accesses a map database storing map data of multiple generations, selects map data of a generation corresponding to an imaging time of the original image, specifies a reference feature corresponding to an imaging spot of the original image by using the selected map data, and corrects distortion of the original image on the basis of the reference feature and the feature to be captured, to generate a corrected image.SELECTED DRAWING: Figure 1

Description

One aspect of the disclosure relates to computer systems, processing methods, programs, and / or data structures.

Patent Document 1 describes an image recognition method for converting either image data or map data into data viewed from the viewpoint of the other data based on the amount of distortion between the image data and the map data. ing. Patent Document 2 describes an image processing system that generates reference data used when recognizing a landscape image based on a photographed image of a landscape.

Japanese Unexamined Patent Publication No. 2010-176645 Japanese Unexamined Patent Publication No. 2011-227888

It is desired to appropriately correct the distortion of the captured image.

The computer system according to one aspect of the present disclosure comprises a processor. The processor acquires the original image including the object to be photographed, accesses the map database that stores the map data of multiple generations, selects the map data of the generation corresponding to the shooting time of the original image, and shoots the original image. The reference feature corresponding to the point is identified using the selected map data, and the distortion of the original image is corrected based on the reference feature and the projected feature to generate a corrected image.

It is a figure which shows an example of application and functional structure of the image processing system which concerns on embodiment. It is a figure which shows an example of the hardware composition of the computer used for the image processing system which concerns on embodiment. It is a flowchart which shows an example of the operation of the image processing system which concerns on embodiment. It is a figure which shows an example of image correction. It is a figure which shows the change between the corrected images.

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or equivalent elements are designated by the same reference numerals, and duplicate description is omitted.

[System overview]
In the present embodiment, as an example, the computer system according to the present disclosure is applied to the image processing system 1. The image processing system 1 according to the embodiment is a computer system that corrects distortion of an image that captures a feature.

An image is information expressed on a predetermined medium so that a person can recognize an event through vision. The image may be an image generated by an image pickup device such as a camera, or may be an image subjected to any other image processing after shooting. Electronic data indicating an image, that is, image data is processed by a computer to visualize the image, and as a result, a person can recognize the image through vision. In one example, the image is a still image, i.e. a photograph.

The image may be taken by a camera held by a person, or may be taken by a camera mounted on a moving body such as a car or a drone. The image may be distorted due to factors such as the type of camera used for shooting (360-degree camera, wide-angle lens, fisheye lens), shooting technology, and the like. The image processing system 1 corrects such distortion.

Image distortion means that the subject appearing in an image is deformed so as to be different from the case where a person visually recognizes the subject. Examples of image distortion include, but are not limited to, stretching or shrinking in at least a portion of the image. "Correcting image distortion" means processing an image so that the subject appearing in the image is the same as or close to the subject recognized by a person through vision. In the present disclosure, correcting image distortion is also simply referred to as "image correction" or "image correction". Even if the degree of distortion differs between two images that capture a common shooting range, the image processing system 1 corrects these images so that the two corrected images are almost the same, and both images are used. Can be made comparable. The correction for enabling comparison between images in this way is also called "normalization".

In the present disclosure, an image processed by the image processing system 1 to correct distortion (that is, an image in which the subject is distorted) is referred to as an "original image", and an image in which distortion is corrected is referred to as a "corrected image".

A feature is any tangible object that exists on the ground. The feature may be a natural object or an artificial object. For example, features include mountains, farmlands, residential areas, vacant lots, rivers, lakes, seas, tourist areas, roads, railroads, buildings, parks, towers, traffic lights, railroad crossings, sidewalks, pedestrian bridges, floating signs, traffic signs, road surfaces. It may include markings and the like.

[System configuration]
FIG. 1 is a diagram showing an example of application of the image processing system 1. The image processing system 1 includes a server 10 that executes the main functions of the system. In one example, the server 10 connects to the map database 20 and one or more user terminals 30 via a communication network.

The server 10 is a computer that corrects the distortion of the original image. In one example, the server 10 corrects the distortion of the original image based on the request from the user terminal 30, and transmits the corrected image to the user terminal 30.

FIG. 1 also shows an example of the functional configuration of the server 10. The server 10 includes a communication unit 11, a specific unit 12, a correction unit 13, and a change extraction unit 14 as functional modules. The communication unit 11 is a functional module for transmitting and receiving data to and from the user terminal 30. The specifying unit 12 is a functional module that specifies various information necessary for correcting the original image. The correction unit 13 is a functional module that corrects the original image based on the specified information. The change extraction unit 14 is a functional module that compares two corrected images and extracts changes in features over time.

The computer that functions as the server 10 is not limited. In one example, the server 10 is composed of a large computer such as a business server. FIG. 2 is a diagram showing an example of the hardware configuration of the server 10. For example, the server 10 has a control circuit 100. In one example, the control circuit 100 has one or more processors 101, a memory 102, a storage 103, a communication port 104, and an input / output port 105. Processor 101 executes operating system and application programs. The storage 103 is composed of a hard disk, a non-volatile semiconductor memory, or a storage medium of a removable medium (for example, a magnetic disk, an optical disk, etc.), and stores an operating system and an application program. The memory 102 temporarily stores the program loaded from the storage 103 or the calculation result by the processor 101. In one example, the processor 101 functions as each functional module of the server 10 by executing a program in cooperation with the memory 102. The communication port 104 performs data communication with another device via the communication network NW according to a command from the processor 101. The input / output port 105 executes input / output of an electric signal to / from an input / output device (user interface) such as a keyboard, a mouse, and a monitor according to a command from the processor 101.

The storage 103 stores a program 120 for making the computer function as the server 10. The program 120 includes program code for making the computer function as each of the above functional modules. The program 120 may be provided after being fixedly recorded on a non-temporary recording medium such as a CD-ROM, a DVD-ROM, or a semiconductor memory. Alternatively, program 120 may be provided via a communication network as a data signal superimposed on a carrier wave.

The server 10 may be configured by one or more computers. When a plurality of computers are used, one server 10 is logically configured by connecting these computers to each other via a communication network.

The map database 20 is a non-temporary storage medium or storage device that permanently stores map data indicating map elements constituting a map. Map data shows information on individual features. In one example, a record showing an individual feature includes a feature ID, geographic location, and attributes (referred to in the present disclosure as "feature attributes"). The feature ID is an identifier that uniquely identifies the feature. Geographical location refers to a place in the real world. Geographical location is expressed, for example, in latitude and longitude, but may be expressed by other indicators. A feature attribute is a feature or property of a feature, represented by any data item. Examples of feature attributes include, but are not limited to, feature types, names, locations, structures, construction dates, and occupants, but feature attributes may be represented by any data item.

In this embodiment, the map database 20 stores map data of a plurality of generations. The "generation" of map data is a concept indicating an update of the contents of a map, and can be paraphrased as a "version" of map data. Generally, over time, new features are installed, features are repositioned, and features are removed. In order to reflect such changes in features on the map, the map data is updated at a certain timing (for example, once a year, once every few years, etc.). It can be said that "multi-generational map data" is a set of past and present map data accumulated by the update. For example, when the map data Ma is changed to the map data Mb by the update, it can be said that the map data Mb is the next generation (version) of the map data Ma. If the map data Ma is the nth generation, the map data Mb is the (n + 1) generation. In this disclosure, the generation of map data is represented by a natural number.

The map database 20 stores map data from the first generation to the nth generation (n> 1). The map data of each generation is associated with time information indicating the time of that generation. For example, the time information may indicate the date (date) when the map data was created. For example, assuming that the map database 20 stores the map data of the third generation, the time information of the map data of the first generation, the second generation, and the third generation is "December 1, 2017" and "2018, respectively." "December 15, 2019" and "December 1, 2019" may be indicated. Alternatively, the time information may indicate the validity period of the map data. For example, the timing information of the 1st generation, 2nd generation, and 3rd generation map data is "December 1, 2017-December 14, 2018" and "December 15, 2018-11, 2019, respectively". May indicate "30th of the month" and "after December 1, 2019". In this way, the method of expressing the timing information is not limited. In any case, by referring to the time information, it is possible to identify the map data that is valid at a certain point in time.

The structure of the map data is not limited, and the data structure may be designed by any policy. For example, the record indicating the above-mentioned feature may be normalized or denormalized by an arbitrary policy and stored in one or more data tables.

The individual data items of the map data may be set statically or dynamically. "Statically set" means that the value is preset and the setting is not changed unless there is manual intervention. On the other hand, "dynamically set" means that the value can be changed in response to any event without manual intervention. Dynamic configuration is achieved by running a program that controls a given data item on a given computer. The dynamic settings may be performed by the image processing system 1 or by another computer system.

The installation location of the map database 20 is not limited. For example, the map database 20 may be built as a part of the image processing system 1 and built in the server 10, or may be provided in a computer system different from the image processing system 1.

In one example, the server 10 refers to a reference step that refers to the map database 20 (map data) in response to an instruction from the first control unit (more specifically, the specific unit 12). Execute a program to be executed by a different second control unit. For example, this program is implemented as an application programming interface (API). Both the first control unit and the second control unit are functional modules and are realized on the processor. The processor on which the first control unit is executed and the processor on which the second control unit is executed may be the same or different. For example, at least one of the first control unit and the second control unit is realized on the processor 101.

The user terminal 30 is a computer (client terminal) operated by the user. The user terminal 30 may be a fixed terminal or a mobile terminal. Examples of the user terminal 30 include, but are not limited to, mobile phones, smartphones, tablet terminals, wearable terminals, and personal computers. Although FIG. 1 shows only one user terminal 30, the number of user terminals 30 accessing the image processing system 1 is not limited.

[Processing procedure in the system]
(Image correction)
The operation of the image processing system 1 will be described with reference to FIG. 3, and the image correction method according to the present embodiment will be described. FIG. 3 is a flowchart showing an example of the operation of the image processing system 1 as a processing flow S1.

In step S11, the communication unit 11 receives the original image data indicating the original image including the object to be photographed from the user terminal 30. The object to be photographed is the object reflected in the image. The original image data may indicate at least one of the shooting time and the shooting point. The shooting time is the time when the original image was taken. The shooting time may be represented by a date (year / month / day), or may be represented by a date and a time. For example, the shooting time is represented by the date and time obtained by the timer of the image pickup apparatus. The shooting point is the place where the original image was taken. The method of expressing the shooting point is not limited, and may be represented by, for example, latitude and longitude, or may be represented by a city, ward, town, village name, block name, number, or the like. For example, the imaging point is represented by the latitude and longitude obtained by the GPS (Global Positioning System) function of the image pickup device and the imaging direction (for example, east, west, south, north). The original image data may include other data items.

In step S12, the specifying unit 12 specifies a shooting time and a shooting point of the original image. When the original image data indicates a shooting time and a shooting point, the specific unit 12 can specify the shooting time and the shooting point as they are. When the original image data indicates the shooting time but does not indicate the shooting point, the specific unit 12 selects the map data of the generation corresponding to the shooting time (map data effective at the shooting time). In one example, when the shooting time of the original image data is "June 1, 2018", the specific unit 12 includes the time information "December 1, 2017" as the map data of the generation corresponding to the shooting time. Select the map data and the map data including the time information "December 15, 2018". In another example, when the shooting time of the original image data is "August 1, 2018", the specific unit 12 is "December 1, 2017-2018" as the map data of the generation corresponding to the shooting time. Select the map data that includes the time information "December 14th". also. The identification unit 12 executes image analysis to estimate a plurality of objects to be photographed and their positional relationships. In one example, the specific unit 12 compares the latitude / longitude of the shooting point with the geographical position (latitude / longitude) included in the map data, and selects the map data including the latitude / longitude of the shooting point. Then, the specifying unit 12 refers to the selected map data and identifies a geographical position that matches the estimation result as a photographing point.

When the original image data indicates a shooting point but does not indicate a shooting time, the specific unit 12 executes image analysis to estimate a plurality of objects to be photographed and their positional relationships. In one example, the specific unit 12 compares the latitude / longitude of the shooting point with the geographical position (latitude / longitude) included in the map data, and selects the map data including the latitude / longitude of the shooting point. Then, the specifying unit 12 refers to each of the map data of the plurality of generations, and specifies the time of the map data having a shooting point that matches the positional relationship of the object to be photographed as the shooting time.

When the original image data does not indicate the shooting time and the shooting point, the specific unit 12 estimates a plurality of objects to be photographed and their positional relationships, refers to the map data of a plurality of generations, and matches the estimation result. Specify the geographical location as the shooting point. In one example, the specifying unit 12 refers to map data from the first generation to the nth generation (n> 1) in sequence, and identifies a geographical position that matches the estimation result as a photographing point. Alternatively, the specifying unit 12 refers to the map data from the nth generation to the first generation in sequence, and specifies a geographical position that matches the estimation result as a photographing point. Then, the specifying unit 12 specifies the time of the map data used for specifying the shooting point as the shooting time.

In step S13, the specific unit 12 specifies the geographical range corresponding to the shooting point by using the map data corresponding to the shooting time. In one example, the specific unit 12 refers to the map database 20 and selects the map data of the generation corresponding to the shooting time (map data effective at the shooting time). In one example, when the shooting time of the original image data is "June 1, 2018", the specific unit 12 includes the time information "December 1, 2017" as the map data of the generation corresponding to the shooting time. Select the map data and the map data including the time information "December 15, 2018". In another example, when the shooting time of the original image data is "August 1, 2018", the specific unit 12 uses "December 1, 2017 to 12/2018" as the map data of the generation corresponding to the shooting time. Select the map data that includes the time information "Month 14th". Subsequently, the specifying unit 12 refers to the map data to specify the geographical range corresponding to the shooting point. The geographical range corresponding to the shooting point may be a geographical range including the shooting point or a geographical range located in the vicinity of the shooting point. The shape of the specified geographical range is not limited and may be, for example, a rectangle or a circle. The dimensions of the specified geographical range are not limited, and may be, for example, several meters square or several tens of meters square.

In step S14, the specifying unit 12 identifies a feature included in the specified geographical range as a reference feature. Specifically, the specifying unit 12 refers to the selected map data and identifies one or more features located within the geographical range as reference features. In one example, the specifying unit 12 specifies a feature whose position does not change in map data of a plurality of generations as a reference feature. That is, the specific unit 12 specifies a feature whose position does not change for a relatively long period of time as a reference feature. Examples of reference features include manholes and buildings, but the features specified as reference features are not limited to these.

In step S15, the correction unit 13 corrects the distortion of the original image indicated by the original image data based on the reference feature and the object to be photographed. The correction method is not limited, and the correction unit 13 may correct the original image by using an arbitrary algorithm. In one example, the correction unit 13 corrects the original image based on the position or shape of the reference feature and the position or shape of the object to be photographed. For example, the correction unit 13 analyzes the original image to associate each object with the reference feature, and then the positional relationship between the plurality of object objects in the original image is between the plurality of reference objects. The distortion of the original image may be corrected so as to match the positional relationship of. The position of each place for defining the positional relationship may be the geographical position of the feature or the coordinates defining the outer edge of the feature. The degree to which the distortion is corrected, that is, the degree to which the distortion is corrected, may depend on the number of the target object or the reference feature as a reference in the correction process. For example, the degree of correction can be higher as the number of objects to be photographed or reference objects increases. The correction unit 13 may determine the degree of the correction.

FIG. 4 is a diagram showing an example of correction of the original image, and specifically, shows an example of correcting the distortion of the original image 210 to generate the corrected image 220. The original image 210 includes a subject such as a manhole 211 and buildings 212 to 215. The plurality of points 213p attached to the corners of the building 213 are examples of the coordinates defining the outer edge of the building 213. For example, the correction unit 13 corrects the distortion of the original image 210 and generates the corrected image 220 based on the geographical position of each object and the position of two or more of the coordinates of the outer edge of each building. do.

Returning to FIG. 3, in step S16, the correction unit 13 generates corrected image data indicating the corrected image. The correction unit 13 may generate corrected image data including additional information regarding the object to be corrected in the corrected image. For example, the correction unit 13 may acquire the feature attribute of the object to be photographed from the map database 20 and include the feature attribute as additional information in the corrected image data. When the original image data does not indicate the shooting time, the correction unit 13 may set the shooting time based on the time information of the selected map data and include the shooting time as additional information in the corrected image data. When the original image data does not indicate the shooting point, the correction unit 13 may set the shooting point based on the specified geographical range and include the shooting point as additional information in the corrected image data. The correction unit 13 may include an index indicating the degree of correction in the corrected image data.

In step S17, the communication unit 11 transmits the corrected image data indicating the corrected image to the user terminal 30. In one example, the user terminal 30 receives and displays the corrected image data, whereby the user can visually recognize the corrected image. When the corrected image data includes additional information, the user terminal 30 displays the additional information, whereby the user can obtain information about the object to be photographed or the original image. When the corrected image data indicates the degree of correction, the user can see the index to know how much the distortion of the image has been corrected.

[Use of corrected image]
The corrected image may be used for any purpose. As described above, by normalizing two original images that capture a common shooting range but differ in shooting time, it is possible to compare images, for example, features existing in that shooting range. Temporal changes can be extracted. In one example, the image processing system 1 executes the processing flow S1 for each of the first and second original images taken at a common shooting point to generate the first corrected image and the second corrected image. After that, in the image processing system 1, the change extraction unit 14 extracts the temporal change of the feature based on the difference between the two corrected images. Examples of temporal changes in features include the installation of new features, the repositioning of features, and the removal of features. For example, the communication unit 11 receives the first corrected image and the second corrected image from the user terminal 30, the change extraction unit 14 obtains the difference between the two images, and the change with time of the feature is calculated based on the difference. Extract. The communication unit 11 transmits the extraction result to the user terminal.

FIG. 5 is a diagram showing changes between corrected images. In this example, the first corrected image 310 and the second corrected image 320 capture a common shooting range including the road 311 and the manhole 312. The first corrected image 310 further captures the road sign 313 located behind the manhole 312 in the image. The second corrected image 320 further captures the road sign 321 located behind the manhole 312 in the image. In this example, the change extraction unit 14 extracts a change in the position of the road sign based on the difference between the first corrected image 310 and the second corrected image 320, and provides an extraction result indicating the change.

By confirming the extraction result, the user can grasp the temporal change of the feature. In addition, the user can grasp the approximate time when the change of the feature occurs in consideration of the shooting time of the first corrected image and the second corrected image. If the user is a map researcher, he / she can go to a field survey to update the map information of the map database 20 based on the change of the feature. Therefore, by using the image processing system 1, it is possible to automatically inform the investigator of the timing when the field survey is necessary. If the temporal change of the feature grasped by the image processing system 1 is reliable, the map database 20 can be automatically updated by omitting the field survey by the investigator.

Alternatively, the corrected image may be used as an image to be displayed on the display for virtual reality (VR) or augmented reality (AR). For example, when the original image received from the user terminal 30 is a copy of the current state of the feature, the specifying unit 12 of the server 10 specifies the shooting point with reference to the map data of the latest generation. Subsequently, the specific unit 12 goes back to the map data of the past generation and acquires the past object to be photographed at the same shooting point. Subsequently, the correction unit 13 generates a correction image based on the acquired object to be photographed. Then, the communication unit 11 transmits the corrected image of the past landscape (projected object) to the user terminal 30. By displaying the corrected image, the user terminal 30 can convey to the user the state of the object to be photographed at that time. In this case, the information transmitted from the communication unit 11 is not limited to the corrected image, but may be past feature attributes of the object to be photographed (for example, information representing the type and name of the feature). Further, the information transmitted from the communication unit 11 may be both the corrected image and the past feature attributes of the object to be photographed.

As another example, when the original image acquired from the user terminal 30 shows the state of the past features, the specifying unit 12 specifies the shooting point with reference to the map data of the past generation. Subsequently, the specific unit 12 traces the map data of the latest generation and acquires the current object to be photographed at the same shooting point. Subsequently, the correction unit 13 generates a correction image based on the acquired object to be photographed. Then, the communication unit 11 transmits the corrected image of the current landscape (projected object) to the user terminal 30. The user terminal 30 can convey the current state to the user by displaying the corrected image. In this case, the information transmitted from the communication unit 11 is not limited to the corrected image, but may be the current feature attribute of the object to be photographed (for example, information representing the type and name of the feature). Further, the information transmitted from the communication unit 11 may be both the corrected image and the current feature attribute of the object to be photographed.

[effect]
As described above, the computer system according to one aspect of the present disclosure includes a processor. The processor acquires the original image including the object to be photographed, accesses the map database that stores the map data of multiple generations, selects the map data of the generation corresponding to the shooting time of the original image, and shoots the original image. The reference feature corresponding to the point is identified using the selected map data, and the distortion of the original image is corrected based on the reference feature and the projected feature to generate a corrected image.

The program according to one aspect of the present disclosure is to access the step of acquiring the original image including the object to be photographed and the map database that stores the map data of multiple generations, and to access the map of the generation corresponding to the time when the original image was taken. The steps of selecting data and identifying the reference feature corresponding to the shooting point of the original image using the selected map data, and correcting the distortion of the original image based on the reference feature and the object to be photographed. And let the computer perform the steps to generate the corrected image.

In such an aspect, the map data of the time corresponding to the original image is selected, and the distortion of the original image is corrected based on the reference feature and the projected feature obtained from the map data. By using the information of the feature at the time corresponding to the original image, the distortion of the captured image can be appropriately corrected.

In computer systems of other aspects, map data may indicate the attributes of individual features. The processor may refer to the map data, acquire the attribute of the object to be photographed as the feature attribute, and output the corrected image data including the corrected image and the feature attribute. By this processing, it is possible to provide information on the features shown in the image.

In a computer system according to another aspect, the processor estimates the time corresponding to the selected generation of map data as the shooting time of the original image, and outputs the corrected image data including the corrected image and the estimated shooting time. You may. By this process, even if the shooting time of the original image is unknown, the shooting time can be estimated and the information of the shooting time can be embedded in the corrected image data.

In a computer system according to another aspect, the processor may output corrected image data including a corrected image and a degree of correction. This process can provide information indicating how much the distortion has been corrected.

In the computer system according to the other aspect, the processor corrects the distortions of the first and second original images that capture a common shooting range to generate the first corrected image and the second corrected image, and first. Changes in features may be extracted based on the difference between the corrected image and the second corrected image. This process makes it possible to automatically grasp changes in features.

[Modification example]
The present disclosure has been described in detail above based on the embodiment. However, the present disclosure is not limited to the above embodiment. This disclosure can be modified in various ways without departing from its gist.

In the above embodiment, the specific unit 12 specifies a geographical range corresponding to the photographing point, and specifies a reference feature included in the geographical range. However, the specifying unit 12 may specify the reference feature directly from the shooting point using the map data corresponding to the shooting time without specifying the geographical range.

In the above embodiment, the server 10 includes the change extraction unit 14, but this functional module is not an essential component. Therefore, the image processing system 1 does not have to have a function of comparing two corrected images and extracting changes in features.

In the above embodiment, the computer system according to the present disclosure is applied to the client-server system, but the computer system according to the present disclosure may be applied to a stand-alone computer.

In the present disclosure, the expression "at least one processor executes the first process, executes the second process, ... executes the nth process", or the expression corresponding thereto is the first. The concept including the case where the execution subject (that is, the processor) of n processes from the process 1 to the process n changes in the middle is shown. That is, this expression shows a concept including both a case where all n processes are executed by the same processor and a case where the processor changes according to an arbitrary policy in the n processes.

When comparing the magnitude relations of two numbers in a computer system, either of the two criteria "greater than or equal to" and "greater than or equal to" may be used, and the two criteria of "less than or equal to" and "less than" Either of them may be used. The selection of such criteria does not change the technical significance of the process of comparing the magnitude relations of two numbers.

The processing procedure of the method executed by at least one processor is not limited to the example in the above embodiment. For example, some of the steps (processes) described above may be omitted, or the steps may be executed in a different order. Further, any two or more steps among the above-mentioned steps may be combined, or a part of the steps may be modified or deleted. Alternatively, other steps may be performed in addition to each of the above steps.

The embodiments described in all or part of the above embodiments include appropriate correction of images, improvement of processing speed, improvement of processing accuracy, improvement of usability, improvement of functions using data, provision of appropriate functions, and the like. Providing appropriate data, programs, recording media, equipment and / or systems, and data, such as improving or providing appropriate functions, reducing the capacity of data and / or programs, and downsizing equipment and / or systems. Any of the optimization of production / manufacturing of data, programs, recording media, equipment and / or systems such as reduction of production / manufacturing cost of programs, equipment or systems, facilitation of production / manufacturing, shortening of production / manufacturing time, etc. Solve one problem.

1 ... image processing system, 10 ... server, 11 ... communication unit, 12 ... specific unit, 13 ... correction unit, 14 ... change extraction unit, 20 ... map database, 30 ... user terminal, 120 ... program, 210 ... original image, 220 ... Corrected image, 310 ... First corrected image, 320 ... Second corrected image.

Claims (6)

Equipped with a processor
The processor
Acquire the original image including the object to be photographed,
The map database that stores the map data of multiple generations was accessed, the map data of the generation corresponding to the shooting time of the original image was selected, and the reference feature corresponding to the shooting point of the original image was selected. Identify using map data,
A corrected image is generated by correcting the distortion of the original image based on the reference feature and the projected feature.
Computer system. The map data shows the attributes of individual features.
The processor
With reference to the map data, the attribute of the object to be photographed is acquired as a feature attribute.
Outputs corrected image data including the corrected image and the feature attribute.
The computer system according to claim 1. The processor
The time corresponding to the generation of the selected map data is estimated as the shooting time of the original image.
Outputs corrected image data including the corrected image and the estimated shooting time.
The computer system according to claim 1 or 2. The processor outputs corrected image data including the corrected image and the degree of the correction.
The computer system according to any one of claims 1 to 3. The processor
The distortions of the first original image and the second original image that capture the common shooting range are corrected to generate the first corrected image and the second corrected image.
The change of the feature is extracted based on the difference between the first corrected image and the second corrected image.
The computer system according to any one of claims 1 to 4. Steps to get the original image including the object to be shot,
The map database that stores the map data of multiple generations was accessed, the map data of the generation corresponding to the shooting time of the original image was selected, and the reference feature corresponding to the shooting point of the original image was selected. Steps to identify using map data and
A step of correcting the distortion of the original image based on the reference feature and the projected feature to generate a corrected image, and
A program that causes a computer to run.

Images