Method, computer device, and computer program for automatic detection of POI changes

Abstract

A method, a computer device, and a computer program for automatic detection of POI change are provided. The POI change detection method includes the steps of detecting a first signboard region from a given reference image, detecting a plurality of second signboard regions from a plurality of past images corresponding to the reference image, and comparing the first signboard region with the plurality of second signboard regions to detect a POI change.

Description

Technical Field

[0001] The following description relates to a technique for detecting changes in points of interest (POIs) existing in real space.

Background Art

[0002] POI (point of interest) information means information regarding main places such as shopping streets, government offices, and schools around roads.

[0003] In order to provide accurate information in maps, augmented reality (AR), etc., it is necessary to always maintain the latest POI information.

[0004] As an example of related technology, Korean Registered Patent No. 10-1183519 (registration date: September 11, 2012) discloses a technique for generating POI information, which is main location information, using a geographic information panorama produced by making a panorama of photographs of actual terrain and features.

[0005] Although a technique for utilizing signboard information included in an image to automatically generate POI information has been used, since the sizes and shapes of signboards are diverse and the fonts, positions, directions, etc. of the characters on the signboards are different, it has been difficult to recognize them.

Summary of the Invention

Problems to be Solved by the Invention

[0006] Provided are a method and an apparatus for detecting POI changes using a plurality of street view images.

[0007] Provided are a method and an apparatus for defining a new POI using one latest image and a plurality of past images.

Means for Solving the Problems

[0008] A method for detecting POI changes, performed on a computer device, wherein the computer device includes at least one processor configured to execute computer-readable instructions contained in memory, and the POI change detection method includes the steps of: detecting a first sign region from a given reference image using at least one processor; detecting a plurality of second sign regions from a plurality of past images corresponding to the reference image using at least one processor; and sensing a POI change by comparing the first sign region with the plurality of second sign regions using at least one processor.

[0009] In one aspect, the step of detecting the POI change may include defining the first sign area as an open POI if there is no sign area among the plurality of second sign areas that has a similarity of a certain level or higher to the first sign area.

[0010] In other words, the step of defining the opening POI may include the step of applying a weighted value that takes into account the difference in the time of capture between the reference image and the plurality of past images when determining the similarity between the first sign area and the plurality of second sign areas.

[0011] In other respects, the step of detecting the POI change may further include the step of defining the third sign area as a closed POI if the third sign area detected from any one of the multiple past images has a similarity to the first sign area below a certain level.

[0012] In other respects, the step defined as the closed POI may include the step of detecting the closed POI using past images taken at the time the reference image was taken and the most recent time among the multiple past images.

[0013] In other respects, the POI change detection method may further include the steps of extracting information regarding the opening POI by analyzing the first sign area using the at least one processor, and registering the information regarding the opening POI in a database using the at least one processor.

[0014] In other respects, the POI change detection method may further include the steps of extracting information regarding the closed POI by analyzing the third sign area using the at least one processor, and deleting the information regarding the closed POI from the database or changing it to a different management format using the at least one processor.

[0015] In other respects, the POI change detection method may further include the step of collecting a plurality of past images taken at a time prior to the reference image, in which the position and orientation information is the same as or similar to that of the reference image, using at least one processor.

[0016] From another perspective, the collection step may involve collecting Street View images taken at past points in time at regular intervals as the plurality of past images.

[0017] In another aspect, the collection step may involve collecting Street View images taken at consecutive past time points immediately preceding the time the reference image was taken, as the plurality of past images.

[0018] The present invention provides a computer program, recorded on a computer-readable recording medium, for causing a computer to execute the aforementioned POI change detection method.

[0019] A computer device includes at least one processor configured to execute computer-readable instructions included in a memory. The at least one processor processes a process of detecting a first sign area from a given reference image, a process of detecting a plurality of second sign areas from a plurality of past images corresponding to the reference image, and a process of comparing the first sign area with the plurality of second sign areas to detect a POI change, and provides a computer device.

Advantages of the Invention

[0020] According to an embodiment of the present invention, by defining a new POI using one recent image and a plurality of past images, a POI change can be detected more accurately, and thus the latest POI information can always be maintained.

Brief Description of the Drawings

[0021] [Figure 1] It is a diagram showing an example of a network environment in one embodiment of the present invention. [Figure 2] It is a block diagram showing an example of a computer device in one embodiment of the present invention. [Figure 3] It is a flowchart showing an example of a method that can be executed by a computer device in one embodiment of the present invention. [Figure 4] It is a diagram showing an example of a POI information management process in one embodiment of the present invention. [Figure 5] It is an illustrative diagram for explaining a process of defining an opening POI in one embodiment of the present invention. [Figure 6] It is an illustrative diagram for explaining a process of defining an opening POI in one embodiment of the present invention. [Figure 7] It is an illustrative diagram for explaining a process of defining a closing POI in one embodiment of the present invention. [Figure 8] It is an illustrative diagram for explaining a process of defining a closing POI in one embodiment of the present invention.

Best Mode for Carrying Out the Invention

[0022] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0023] Embodiments of the present invention relate to a technique for detecting POI changes existing in the real space.

[0024] Embodiments including the matters specifically disclosed in this specification can minimize misrecognition and accurately detect POI changes by overlapping comparison using a plurality of past street view images for one most recent street view image.

[0025] The POI change detection system according to an embodiment of the present invention may be realized by at least one computer device, and the POI change detection method according to an embodiment of the present invention may be executed by at least one computer device included in the POI change detection system. At this time, in the computer device, a computer program in an embodiment of the present invention may be installed and executed, and the computer device may execute the POI change detection method according to an embodiment of the present invention according to the control of the executed computer program. The above-described computer program may be recorded on a computer-readable recording medium in order to be combined with the computer device and cause the computer to execute the POI change detection method.

[0026] FIG. 1 is a diagram showing an example of a network environment in an embodiment of the present invention. The network environment of FIG. 1 shows an example including a plurality of electronic devices 110, 120, 130, 140, a plurality of servers 150, 160, and a network 170. Such FIG. 1 is merely an example for explaining the invention, and the number of electronic devices and the number of servers are not limited as in FIG. 1. Further, the network environment of FIG. 1 is merely an example of the environments applicable to the present embodiment, and the environments applicable to the present embodiment are not limited to the network environment of FIG. 1.

[0027] The multiple electronic devices 110, 120, 130, and 140 may be fixed terminals or mobile terminals implemented by computer devices. Examples of the multiple electronic devices 110, 120, 130, and 140 include smartphones, mobile phones, navigation systems, PCs (personal computers), notebook PCs, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), and tablets. As an example, Figure 1 shows a smartphone as an example of electronic device 110, but in embodiments of the present invention, electronic device 110 may mean one of a variety of physical computer devices that can communicate with other electronic devices 120, 130, 140 and / or servers 150, 160 via the network 170 using substantially wireless or wired communication methods.

[0028] The communication method is not limited, and may include not only communication methods that utilize communication networks that can be included in network 170 (for example, mobile communication networks, wired internet, wireless internet, broadcasting networks), but also short-range wireless communication between devices. For example, network 170 may include one or more arbitrary networks such as PAN (personal area network), LAN (local area network), CAN (campus area network), MAN (metropolitan area network), WAN (wide area network), BBN (broadband network), and the Internet. Furthermore, network 170 may include, but is not limited to, one or more network topologies, including bus networks, star networks, ring networks, mesh networks, star-bus networks, tree or hierarchical networks.

[0029] Servers 150 and 160 may each be implemented by one or more computer devices that communicate with multiple electronic devices 110, 120, 130, and 140 via a network 170 to provide commands, code, files, content, services, etc. For example, server 150 may be a system that provides services to multiple electronic devices 110, 120, 130, and 140 connected via a network 170.

[0030] Figure 2 is a block diagram showing an example of a computer device in one embodiment of the present invention. Each of the aforementioned electronic devices 110, 120, 130, and 140, as well as each of the servers 150 and 160, may be implemented by the computer device 200 shown in Figure 2.

[0031] Such a computer device 200 may include a memory 210, a processor 220, a communication interface 230, and an input / output interface 240, as shown in Figure 2. The memory 210 is a computer-readable recording medium and may include RAM (random access memory), ROM (read-only memory), and persistent mass storage devices such as disk drives. Here, persistent mass storage devices such as ROM and disk drives may be included in the computer device 200 as separate persistent storage devices distinct from the memory 210. The memory 210 may also store an operating system and at least one program code. Such software components may be loaded into the memory 210 from a computer-readable recording medium separate from the memory 210. Such a separate computer-readable recording medium may include computer-readable recording media such as floppy disks, disks, tapes, DVD / CD-ROM drives, and memory cards. In other embodiments, the software components may be loaded into the memory 210 through a communication interface 230 which is not a computer-readable recording medium. For example, software components may be loaded into the memory 210 of the computer device 200 based on a computer program installed by a file received via the network 170.

[0032] The processor 220 may be configured to process computer program instructions by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor 220 by memory 210 or a communication interface 230. For example, the processor 220 may be configured to execute instructions received according to program code stored in a recording device such as memory 210.

[0033] The communication interface 230 may provide a function for the computer device 200 to communicate with other devices (for example, the recording device described above) via the network 170. For example, requests, instructions, data, files, etc., generated by the processor 220 of the computer device 200 according to program code recorded in a recording device such as memory 210 may be transmitted to other devices via the network 170 under the control of the communication interface 230. Conversely, signals, instructions, data, files, etc., from other devices may be received by the computer device 200 via the network 170 through the communication interface 230 of the computer device 200. Signals, instructions, data, etc., received via the communication interface 230 may be transmitted to the processor 220 or memory 210, and files, etc., may be recorded on a recording medium (the persistent recording device described above) that the computer device 200 may further include.

[0034] The input / output interface 240 may be a means for interface with the input / output device 250. For example, the input device may include a microphone, keyboard, or mouse, and the output device may include a display or speaker. In another example, the input / output interface 240 may be a means for interface with a device that integrates input and output functions into one, such as a touchscreen. The input / output device 250 may consist of the computer device 200 and one other device.

[0035] In other embodiments, the computer device 200 may include fewer or more components than those shown in Figure 2. However, it is not necessary to explicitly show most of the conventional components in the figure. For example, the computer device 200 may be implemented to include at least some of the input / output devices 250 described above, and may further include other components such as transceivers and databases.

[0036] The following describes specific embodiments of methods and apparatus for automatically detecting changes in points of interest (POIs).

[0037] Maintaining up-to-date Point of Interest (POI) information is crucial for providing accurate information about real-world spaces in various services such as maps and augmented reality.

[0038] This embodiment automatically detects changes in Points of Interest (POIs) using sign information contained in Street View images, and utilizes multiple past Street View images to minimize misrecognition of POI changes.

[0039] The computer device 200 according to this embodiment may be configured with a computer-implemented POI change detection system. For example, the POI change detection system may be implemented as an independently operating program, or it may be configured as an in-app (in-app) system for a specific application, so as to be able to operate on the specific application.

[0040] The processor 220 of the computer device 200 may be implemented with components for performing the following POI change detection method. Depending on the embodiment, the components of the processor 220 may be selectively included in the processor 220 or excluded from the processor 220. Also, depending on the embodiment, the components of the processor 220 may be separated or merged for the expression of the functions of the processor 220.

[0041] Such a processor 220 and its components may control the computer device 200 to perform steps included in the following POI change detection method. For example, the processor 220 and its components may be implemented to execute instructions from the operating system code contained in the memory 210 and the code of at least one program.

[0042] Here, the components of the processor 220 may be representations of different functions that are executed by the processor according to instructions provided by the program code stored in the computer device 200.

[0043] The processor 220 may read necessary instructions from the memory 210, which is loaded with instructions related to the control of the computer device 200. In this case, the instructions read may include instructions for controlling the processor 220 to perform the steps described below.

[0044] The steps included in the POI change detection method described below may be performed in a different order than shown in the diagram, some steps may be omitted, or additional processes may be included.

[0045] The steps included in the POI change detection method may be performed on the server 150, and in some embodiments, at least a portion of the steps may be performed on one of the electronic devices 110, 120, 130, and 140.

[0046] Figure 3 is a flowchart showing an example of a method that a computer device can perform in one embodiment of the present invention.

[0047] Referring to Figure 3, in step 310, if the processor 220 is given an image taken in Street View format for the target location (hereinafter referred to as the "reference image"), it may collect multiple past images corresponding to the reference image. In this case, the reference image may mean a Street View image taken most recently for the target location, and may include shooting information for that image (location information (latitude / longitude), direction information, etc.). The processor 220 may obtain past Street View images that match the reference image from a map database in which Street View images of the target location are stored in chronological order, using the shooting information for each image. In other words, the processor 220 may select a Street View image from among the Street View images stored in the map database that is the same as or similar to the location and direction information of the reference image. In this case, the processor 220 may collect at least two or more past Street View images for the reference image. The processor 220 may select a past image taken earlier than the reference image from among the Street View images of the target location in the map database. For example, the processor 220 may select Street View images from past points in time at regular intervals, for instance, images taken one week ago, two weeks ago, three weeks ago, etc., as past images for the reference image. As another example, the processor 220 may select a series of Street View images from past points in time, including the Street View image taken immediately before the reference image, as past images for the reference image. The criteria and methods for selecting past images corresponding to the reference image can be changed at will.

[0048] In step 320, the processor 220 may detect POI changes using a reference image and multiple past images. For example, the processor 220 may detect POI changes by comparing the sign area in the reference image with the sign area in the past images. In this embodiment, the processor may detect POI changes by detecting the sign area of ​​a store that can best sense new openings, closures, name changes, etc. When the processor 220 is given a reference image and multiple past images, it may apply a sign detector to each image to detect polygonal sign areas. The processor 220 may detect sign areas from the reference image and past images using a machine learning model trained on a deep learning platform using a previously collected set of sign images. The processor 220 may build a machine learning model by training it with images of various shapes and types of signs as training data, thereby detecting sign areas in images. At this time, the processor 220 may obtain detection results at multiple scales of the image in order to detect signs of various sizes present in the image, merge them to generate a saliency map, and then detect the sign regions, which are the final detection results, from the saliency map. After this, the processor 220 may compare each sign region detected from the reference image (hereinafter referred to as "reference sign") with sign regions detected from multiple past images (hereinafter referred to as "past sign") to detect POI changes. At this time, if there are no past sign that have a similarity level of a certain level or higher to the reference sign, the processor 220 may determine that there is a POI change and define that reference sign as an open POI. Alternatively, the processor 220 may compare a sign region detected from any one of the multiple past images (past sign) with a sign region detected from the reference image (reference sign), and if the reference sign has a similarity level below a certain level to the past sign, the processor may determine that there is a POI change and define that past sign as a closed POI.Therefore, the processor 220 can detect changes in POIs due to store openings by comparing a reference sign detected from a reference image with past sign detected from multiple past images, and can detect changes due to store closings by comparing a past sign detected from a past image at a specific point in time with a reference sign detected from a reference image.

[0049] In step 330, the processor 220 may extract POI information from the reference image based on the POI change detection results. If a store opening POI is detected as one of the POI changes, the processor 220 may use OCR (optical character recognition) or the like to extract information about the store opening POI from the reference image. In other words, the processor 220 may apply character recognition technology such as OCR to the sign area detected as a POI change area among the sign areas detected from the reference image to generate POI information (e.g., company name). As an example, the processor 220 may recognize the company name included in the sign area corresponding to the POI change area and use it as information about the POI. Furthermore, the processor 220 may obtain information about the POI by searching the internet for the POI using the location information of the reference image in which the sign area corresponding to the POI change area was detected and the company name recognized in the sign area. Similarly, for store closing POIs, character recognition technology such as OCR may be used to extract information about the store closing POI from past images.

[0050] In step 340, the processor 220 may register the POI information extracted in step 330 as a result of POI change into a database for services provided by the server 150 (for example, a map service, an augmented reality service, etc.). The processor 220 may also register information about newly opened POIs in the database as a result of a POI change due to a store opening, and in the case of a POI change due to a store closing, it may delete the closed POI information in the database or change it to a different management format. Thus, by reflecting the POI change results in the database, the processor 220 can maintain up-to-date POI information about the target location.

[0051] Figure 4 shows an example of a POI information management process in one embodiment of the present invention. Figure 4 summarizes a POI information management process that maintains POI information with the latest information through automatic detection of POI changes.

[0052] Referring to Figure 4, if the processor 220 is given a reference image, which is a recent Street View image obtained by capturing Street View images of a target location, it may use the capture information (location and direction information) of the reference image to read a certain number (K) of past Street View images from the map database 401 that have the same or similar location and direction information as the reference image.

[0053] Next, the processor 220 may perform POI change detection by comparing K past Street View images with a reference image, which is a recent Street View image. In this case, if no sign area similar to the sign area in the reference image exists in any of the K past Street View images, the processor 220 may define it as a new POI (open POI). Also, if no sign area similar to the sign area in any one of the K past Street View images exists in the reference image, the processor 220 may define it as a deleted POI (closed POI).

[0054] Next, the processor 220 may analyze the changing POI information to extract information about an open POI from the sign area in the reference image, and extract information about a closed POI from the sign area in the past image.

[0055] Finally, the processor 220 may reflect the changed POI information in the POI database 402. The processor 220 may update the POI information registered in the POI database 402 to newly register information about open POIs, and in the case of closed POIs, it may delete the relevant POI information in the POI database or change it to a different management format.

[0056] Figures 5-6 are illustrative diagrams illustrating the process of defining an opening POI in one embodiment of the present invention.

[0057] Referring to Figure 5, when the processor 220 is given a recently captured image I of a target location, it may use the location (latitude / longitude) and direction information of the recently captured image I to collect past captured images II, III, and IV that have the same or similar location and direction information as the recently captured image I. In this case, past captured images II, III, and IV may be taken at different times, and Street View images taken at a time earlier than the recently captured image I may be selected.

[0058] The processor 220 may extract a sign feature vector I from the sign region detected in the most recently captured image I. Similarly, the processor 220 may extract sign feature vectors II, III, and IV from the sign regions detected in the previously captured images II, III, and IV, respectively.

[0059] The processor 220 may perform a similarity comparison between the sign feature vector I of the most recently captured image I and the sign feature vectors II, III, and IV of previously captured images II, III, and IV.

[0060] For example, processor 220 may extract image descriptors using the DIR (Deep Image Retrieval) algorithm and compare the extracted descriptors to determine their similarity. A descriptor is a vector representation of image features and is widely used in image search and image analysis technologies. For deep learning-based image search, a global image representation is learned. In the case of a global descriptor, when an input image is received, 2048-dimensional features are extracted through a feature extraction process (convolution, pooling, etc.). At this time, cosine similarity may be used to compare the extracted 2048-dimensional descriptors. In addition, it is also possible to compare signature feature vectors using known algorithms such as SIFT (Scale Invariant Feature Transform) and SURF (Speeded Up Robust Features).

[0061] When performing a similarity comparison, a weighted value that takes into account the difference in the time of capture between previously captured images may be applied to the similarity with past images. For example, the similarity between a recently captured image and an image taken one week ago may be weighted higher than the similarity between an image taken two weeks ago.

[0062] The processor 220 may determine that a sign region detected from the most recently captured image I is an existing POI if at least one of the sign feature vectors III, III, and IV of the previously captured images II, III, and IV has a similarity of a certain level or higher to the sign feature vector I of the most recently captured image I.

[0063] On the other hand, if the similarity between the sign feature vectors II, III, and IV of past captured images II, III, and IV and the sign feature vector I of the most recently captured image I is below a certain level, the processor 220 may define the sign region detected from the most recently captured image I as a new POI due to the store opening.

[0064] For example, as shown in Figure 6, the processor 220 may collect multiple past images 602 taken at a previous point in time for a recently captured image 601 that includes signs AAA, BBB, EEE, and DDD, and compare the signs in the recently captured image 601 with the signs in the multiple past images 602.

[0065] The processor 220 defines signs AAA, BBB, and DDD in the recently captured image 601 that match at least once with signs in multiple past captured images 602 as existing POIs, while EEE, which does not match with any of the signs in the multiple past captured images 602, may be defined as a newly opened POI.

[0066] The processor 220 utilizes multiple past Street View images to detect changes in points of interest (POIs) due to store openings, thereby achieving the effect of performing overlapping sign similarity matching and minimizing misrecognition of POI changes.

[0067] Figures 7-8 are illustrative diagrams illustrating the process of defining a closed POI in one embodiment of the present invention.

[0068] Referring to Figure 7, the processor 220 may use past images II, III, and IV, which correspond to the most recent image I, to detect changes in the point of interest (POI) due to the closing of the store.

[0069] The processor 220 compares the sign feature vector II of the previously captured image II with the sign feature vector I of the most recently captured image I. If the similarity between the sign feature vector I and the sign feature vector II is below a certain level, the sign region detected from the previously captured image II may be defined as a POI that has been deleted due to the store closing.

[0070] For example, as shown in Figure 8, the processor 220 may compare the signs in the most recently captured image 601 with the signs in the previously captured image 802, which include signs AAA, BBB, CCC, and DDD.

[0071] The processor 220 may define signs AAA, BBB, and DDD in the past captured image 802 that match signs in the most recent captured image 601 as existing POIs, and CCC that does not match signs in the most recent captured image 601 as closed POIs.

[0072] The processor 220 can provide accurate POI information by detecting not only changes in POI due to opening but also changes in POI due to closing.

[0073] Thus, according to the embodiment of the present invention, by defining a new POI using one recent image and multiple past images, POI changes can be detected more accurately, thereby maintaining the latest POI information at all times. This embodiment minimizes misrecognition of POI changes by detecting signs from multiple past images and comparing them with sign information in the recent image, thereby improving POI change detection performance.

[0074] The above-described apparatus may be implemented by hardware components, software components, and / or combinations of hardware and software components. For example, the apparatus and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as processors, controllers, ALUs (arithmetic logic units), digital signal processors, microcomputers, FPGAs (field programmable gate arrays), PLUs (programmable logic units), microprocessors, or various devices capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications running on the OS. The processing unit may also respond to software execution, access data, record, manipulate, process, and generate data. For convenience of understanding, it may be described as if a single processing unit is used, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Other processing configurations, such as a parallel processor, are also possible.

[0075] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired, or to instruct the processing unit independently or collectively. Software and / or data may be embodied in any kind of machine, component, physical device, computer recording medium, or device in order to be interpreted based on the processing unit or to provide instructions or data to the processing unit. Software may be distributed across a networked computer system, and may be recorded or executed in a distributed manner. Software and data may be recorded on one or more computer-readable recording media.

[0076] The methods according to the embodiment may be implemented in the form of program instructions executable by various computer means and recorded on a computer-readable medium. In this case, the medium may continuously record computer-executable programs or may temporarily record them for execution or download. Furthermore, the medium may be various recording or storage means in the form of a combination of one or more hardware components, and may be a medium directly connected to a computer system or distributed on a network. Examples of mediums include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and devices configured to record program instructions such as ROM, RAM, and flash memory. Other examples of mediums include recording media and storage media managed by app stores that distribute applications, and sites and servers that supply and distribute various other software.

[0077] As described above, embodiments have been explained based on limited embodiments and drawings, but those skilled in the art will be able to make various modifications and variations from the above description. For example, the described technique may be performed in a different order than described, and / or the components of the described system, structure, apparatus, circuit, etc. may be combined or assembled in a different manner than described, or opposed or replaced by other components or equivalents, and still achieve suitable results.

[0078] Therefore, even if the embodiment is different, it falls within the scope of the attached claims if it is equivalent to the claims.

Claims

1. A method for detecting changes in a point of interest (POI) that is performed using a computer device, The computer device includes at least one processor configured to execute computer-readable instructions contained in memory, The aforementioned POI change detection method is: The steps include: detecting a first sign region from a given reference image using at least one of the aforementioned processors; The steps include: detecting a plurality of second sign regions from a plurality of past images corresponding to the reference image using at least one of the processors, and The step of using at least one processor to determine the similarity between the first sign region and the plurality of second sign regions by applying a weighted value that takes into account the difference in the time of capture between the reference image and the plurality of past images, and to detect a change in POI based on the similarity. A method for detecting changes in point of interest (POI), including the method described above.

2. The step of detecting the POI change is: If none of the aforementioned multiple second sign areas have a similarity to the first sign area above a certain level, the first sign area is defined as a store opening POI. A method for detecting changes in a POI according to claim 1, including the following:

3. The step of detecting the POI change is: If a third sign region detected from any one of the aforementioned multiple past images has a similarity to the first sign region below a certain level, the third sign region is defined as a closed POI. The method for detecting changes in a POI according to claim 2, further comprising:

4. The step of defining the aforementioned closing POI is: The step of detecting the closed POI using past images taken at the time the reference image was taken and the most recent time from among the multiple past images. A method for detecting changes in a POI according to claim 3, including the following:

5. The aforementioned POI change detection method is: The steps include: extracting information regarding the opening POI by analyzing the first sign area using at least one processor, and The step of registering information regarding the opening of a store POI in a database using at least one of the processors. The method for detecting changes in a POI according to claim 2, further comprising:

6. The aforementioned POI change detection method is: The steps include: extracting information regarding the closed POI by analyzing the third sign area using at least one of the processors, and The step of using at least one processor to delete the information regarding the closing POI from the database or change it to a different management format. The method for detecting changes in a POI according to claim 3, further comprising:

7. The aforementioned POI change detection method is: The step of collecting a plurality of past images taken at a time prior to the reference image using at least one processor, wherein the position and orientation information is the same as or similar to that of the reference image. The method for detecting changes in a POI according to claim 1, further comprising:

8. The aforementioned step of collecting data is: Collecting Street View images taken at regular intervals in the past as the aforementioned multiple past images. A method for detecting changes in a POI according to claim 7, characterized by the above.

9. The aforementioned step of collecting data is: The process involves collecting Street View images taken at consecutive past points in time, starting immediately before the time the aforementioned reference image was taken, as the aforementioned multiple past images. A method for detecting changes in a POI according to claim 7, characterized by the above.

10. A computer program recorded on a computer-readable recording medium for causing a computer to execute the POI change detection method described in any one of claims 1 to 9.

11. A computer device, At least one processor configured to execute computer-readable instructions contained in memory Includes, The aforementioned at least one processor is The first sign region is detected from the given reference image. Multiple second sign regions are detected from multiple past images corresponding to the aforementioned reference image, and The similarity between the first sign area and the multiple second sign areas is determined by applying a weighted value that takes into account the difference in the time of capture between the reference image and the multiple past images, and a change in the point of interest (POI) is detected based on the similarity. A computer device characterized by the following:

12. The aforementioned at least one processor is If none of the aforementioned multiple second sign areas have a similarity to the first sign area above a certain level, the first sign area is defined as a store opening POI. The computer device according to claim 11, characterized by the above.

13. The aforementioned at least one processor is If a third sign area detected from any one of the aforementioned multiple past images has a similarity to the first sign area below a certain level, the third sign area is defined as a closed POI. The computer device according to claim 12, characterized by the above.

14. The aforementioned at least one processor is The closing point of interest (POI) is detected using past images taken at the time the reference image was taken and the most recent time from among the multiple past images. The computer device according to claim 13, characterized by the above.

15. The aforementioned at least one processor is By analyzing the first sign area, information regarding the opening POI is extracted. Register the aforementioned information regarding the opening of a store in the database. The computer device according to claim 12, characterized by the above.

16. The aforementioned at least one processor is By analyzing the third sign area, information regarding the closing POI is extracted. Delete the aforementioned information regarding store closures from the database or change it to a different management system. The computer device according to claim 13, characterized by the above.

17. The aforementioned at least one processor is Collecting multiple past images taken at a point in time prior to the aforementioned reference image, whose position and orientation information is the same as or similar to that of the aforementioned reference image. The computer device according to claim 11, characterized by the above.

18. The aforementioned at least one processor is Collecting Street View images taken at regular intervals in the past, or Street View images taken at consecutive past points in time immediately preceding the time the reference image was taken, as the multiple past images. The computer device according to claim 17, characterized by the above.

Images