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) present in real space. [Background technology]

[0002] POI (point of interest) information refers to information about major locations such as shopping districts, government offices, and schools around roads.

[0003] In order to provide accurate information on maps, augmented reality (AR), etc., it is necessary to constantly maintain up-to-date POI information.

[0004] As an example of related technology, Korean Patent Registration No. 10-1183519 (registered on September 11, 2012) discloses a technology for generating POI information, which is information on key locations, using geographic information panoramas created from panoramic photographs of actual terrain and features.

[0005] Technology is used to automatically generate POI information by utilizing signboard information contained in images, but it has been difficult to recognize signs because they come in a variety of sizes and shapes, and the font, position, and direction of the text on the signs vary. Summary of the Invention [Problem to be solved by the invention]

[0006] A method and apparatus for detecting POI changes using multiple road view images is provided.

[0007] A method and apparatus for defining a new POI using one recent image and multiple past images is provided. [Means for solving the problem]

[0008] Provided is a POI change detection method executed on a computer device, the computer device including at least one processor configured to execute computer-readable instructions contained in a memory, the POI change detection method including the steps of: detecting, by the at least one processor, a first signboard region from a given reference image; detecting, by the at least one processor, a plurality of second signboard regions from a plurality of past images corresponding to the reference image; and detecting, by the at least one processor, the first signboard region with the plurality of second signboard regions to detect a POI change.

[0009] According to one aspect, the step of detecting a POI change may include a step of defining the first signboard area as an opening POI if there is no signboard area among the plurality of second signboard areas that has a similarity to the first signboard area above a certain level.

[0010] According to another aspect, the step of defining the POI as an opening POI may include a step of applying a weighting factor that takes into account a difference in the time points of capture between the reference image and the plurality of past images when determining the similarity between the first signboard area and the plurality of second signboard areas.

[0011] According to another aspect, the step of detecting a POI change may further include a step of defining a third signboard area detected from any one of the plurality of past images as a closed POI if the third signboard area has a similarity to the first signboard area below a certain level.

[0012] According to another aspect, the step of defining the POI as a closed POI may include a step of detecting the closed POI using past images taken at the time of shooting the reference image and the most recent time among the plurality of past images.

[0013] According to another aspect, the POI change detection method may further include a step of extracting information about the opening POI by analyzing the first signboard area by the at least one processor, and a step of registering information about the opening POI in a database by the at least one processor.

[0014] According to another aspect, the POI change detection method may further include a step of extracting information about the closed POI by analyzing the third signboard area by the at least one processor, and a step of deleting the information about the closed POI from a database or changing it to another management form by the at least one processor.

[0015] According to another aspect, the POI change detection method may further include a step of collecting, by the at least one processor, a plurality of past images taken at a time earlier than the reference image, the past images having position and direction information identical to or similar to that of the reference image.

[0016] According to another aspect, the collecting step may collect street view images captured at past times with a fixed interval as the plurality of past images.

[0017] According to still another aspect, the collecting step may collect, as the plurality of past images, street view images captured at successive past points in time starting immediately before the capture point in time of the reference image.

[0018] A computer program is provided that is recorded on a computer-readable recording medium to cause a computer to execute the POI change detection method.

[0019] A computer device is provided, the computer device including at least one processor configured to execute computer-readable instructions contained in a memory, the at least one processor processing a process of detecting a first signboard region from a given reference image, a process of detecting a plurality of second signboard regions from a plurality of past images corresponding to the reference image, and a process of comparing the first signboard region with the plurality of second signboard regions to detect a POI change. [Effects of the Invention]

[0020] According to an 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 always maintaining up-to-date POI information. [Brief explanation of the drawings]

[0021] [Figure 1] FIG. 1 illustrates an example of a network environment in accordance with an embodiment of the present invention. [Figure 2] FIG. 1 is a block diagram illustrating an example of a computing device according to an embodiment of the present invention. [Figure 3] 1 is a flowchart illustrating an example of a method that can be performed by a computer device in accordance with an embodiment of the present invention. [Figure 4] FIG. 10 is a diagram illustrating an example of a POI information management process in an embodiment of the present invention. [Figure 5] FIG. 10 is an exemplary diagram illustrating a process for defining an opening POI in accordance with an embodiment of the present invention. [Figure 6] FIG. 10 is an exemplary diagram illustrating a process for defining an opening POI in accordance with an embodiment of the present invention. [Figure 7] FIG. 10 is an exemplary diagram illustrating a process for defining a closed POI in accordance with an embodiment of the present invention. [Figure 8] FIG. 10 is an exemplary diagram illustrating a process for defining a closed POI in accordance with an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

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

[0023] An embodiment of the present invention relates to a technology for detecting changes in POIs that exist in real space.

[0024] Embodiments including those specifically disclosed in this specification can minimize false positives and accurately detect POI changes by overlapping multiple past Street View images with a single 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. In this case, a computer program according to an embodiment of the present invention may be installed and executed in the computer device, and the computer device may execute the POI change detection method according to an embodiment of the present invention under the control of the executed computer program. The computer program may be recorded on a computer-readable recording medium so as to be combined with the computer device to cause the computer to execute the POI change detection method.

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

[0027] The electronic devices 110, 120, 130, and 140 may be fixed or mobile terminals implemented by computers. Examples of the electronic devices 110, 120, 130, and 140 include smartphones, mobile phones, navigation systems, personal computers (PCs), notebook PCs, digital broadcasting terminals, personal digital assistants (PDAs), portable multimedia players (PMPs), and tablets. While FIG. 1 illustrates a smartphone as an example of the electronic device 110, in embodiments of the present invention, the electronic device 110 may represent one of a variety of physical computer devices capable of communicating with the other electronic devices 120, 130, and 140 and / or the servers 150 and 160 via the network 170 using a substantially wireless or wired communication method.

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

[0029] Each of the servers 150, 160 may be implemented by one or more computing devices that communicate with the multiple electronic devices 110, 120, 130, 140 via the network 170 to provide instructions, code, files, content, services, etc. For example, the server 150 may be a system that provides services to the multiple electronic devices 110, 120, 130, 140 connected via the network 170.

[0030] 2 is a block diagram showing an example of a computer device according to an embodiment of the present invention. Each of the electronic devices 110, 120, 130, and 140 and each of the servers 150 and 160 described above may be realized by a computer device 200 shown in FIG.

[0031] As shown in FIG. 2 , such a computer device 200 may include a memory 210, a processor 220, a communication interface 230, and an input / output interface 240. The memory 210 is a computer-readable recording medium and may include random access memory (RAM), read-only memory (ROM), and a persistent mass storage device such as a disk drive. Here, a persistent mass storage device such as a ROM or a disk drive may be included in the computer device 200 as a separate persistent storage device 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 separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, or a memory card. In another embodiment, 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, the software components may be loaded into the memory 210 of the computing device 200 based on a computer program installed by a file received over the network 170 .

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

[0033] The communication interface 230 may provide a function for the computer device 200 to communicate with other devices (e.g., the above-mentioned storage device) via the network 170. For example, requests, instructions, data, files, etc. generated by the processor 220 of the computer device 200 in accordance with program code stored in a storage device such as the 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 communication interface 230 of the computer device 200 via the network 170. The signals, instructions, data, etc. received via the communication interface 230 may be transmitted to the processor 220 or the memory 210, and files, etc. may be recorded on a storage medium (e.g., the above-mentioned permanent storage device) that the computer device 200 may further include.

[0034] The input / output interface 240 may be a means for interfacing with the input / output device 250. For example, the input device may include a device such as a microphone, keyboard, or mouse, and the output device may include a device such as a display or speaker. As another example, the input / output interface 240 may be a means for interfacing with a device that integrates input and output functions into one, such as a touch screen. The input / output device 250 may be configured as a single device together with the computer device 200.

[0035] Also, in other embodiments, computing device 200 may include fewer or more components than those shown in Figure 2. However, most prior art components need not be explicitly shown in the figures. For example, computing 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 a transceiver, a database, etc.

[0036] Specific embodiments of a method and apparatus for automatically detecting POI changes are described below.

[0037] In order to provide accurate information about real spaces in various services such as maps and augmented reality, it is important to maintain up-to-date POI information.

[0038] This embodiment automatically detects POI changes using signboard information contained in street view images, and uses multiple past street view images to minimize erroneous recognition of POI changes.

[0039] A computer-implemented POI change detection system may be configured in the computer device 200 according to this embodiment. For example, the POI change detection system may be implemented in the form of an independently operating program, or may be implemented in the form of an in-app for a specific application so as to be operable on the specific application.

[0040] The processor 220 of the computing 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 or excluded from the processor 220. Also, depending on the embodiment, the components of the processor 220 may be separated or combined to represent the functionality of the processor 220.

[0041] Such processor 220 and its components may control the computing device 200 to perform the 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 and the code of at least one program contained in the memory 210.

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

[0043] The processor 220 may read the necessary instructions from the memory 210, which has been loaded with instructions related to the control of the computing device 200. In this case, the read instructions 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 that shown in the figures, some steps may be omitted, or additional processes may be included.

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

[0046] FIG. 3 is a flowchart illustrating an example method that may be performed by a computing device in accordance with an embodiment of the present invention.

[0047] Referring to FIG. 3 , in step 310, when an image captured in Street View format of a target location (hereinafter referred to as a “reference image”) is given, processor 220 may collect multiple past images corresponding to the reference image. In this case, the reference image may refer to a Street View image captured most recently of the target location, and may include capture information for the image (e.g., location information (latitude / longitude), direction information, etc.). Processor 220 may retrieve past Street View images matching the reference image from a map database in which Street View images of the target location are stored in chronological order, using the capture information for each image. In other words, processor 220 may select, from among the Street View images stored in the map database, a Street View image captured at a previous time point that has the same or similar location and direction information as the reference image. In this case, processor 220 may collect at least two or more past Street View images for the reference image. Processor 220 may select, from among the Street View images of the target location in the map database, a past image captured at an earlier time point than the reference image. As one example, processor 220 may select Street View images from a certain interval of time in the past, for example, images taken one week ago, two weeks ago, three weeks ago, etc., at weekly intervals, as previous images relative to the reference image. As another example, processor 220 may select Street View images from consecutive previous times, including a Street View image taken immediately before the reference image was taken, as previous images relative to the reference image. The criteria and method for selecting previous images corresponding to the reference image can be changed as many times as necessary.

[0048] In step 320, the processor 220 may detect a POI change using a reference image and multiple past images. For example, the processor 220 may detect a POI change by comparing a signboard area included in the reference image with a signboard area included in the past images. In this embodiment, a POI change may be detected by detecting a store sign portion that best indicates a new opening, closing, or name change. When the reference image and multiple past images are provided, the processor 220 may apply a signboard detector to each image to detect a polygon-shaped signboard area. The processor 220 may detect signboard areas from each of the reference image and the past images using a machine learning model trained based on deep learning using a set of signboard images collected in advance. The processor 220 may build a machine learning model by learning images of signboards of various shapes and types as training data, and may use the model to detect signboard areas within the images. In this case, processor 220 may acquire detection results at multiple scales of the image to detect signs of various sizes present in the image, merge the detection results to generate a saliency map, and then detect signboard regions, which are the final detection results, from the saliency map. Then, processor 220 may compare each signboard region detected from the reference image (hereinafter referred to as a "reference signboard") with signboard regions detected from multiple past images (hereinafter referred to as "past signboards") to detect a POI change. If there is no past signboard with a similarity level to the reference signboard above a certain level, processor 220 may determine that a POI change has occurred and define the reference signboard as an opening POI. Furthermore, processor 220 may compare a signboard region detected from one of multiple past images (past signboard) with a signboard region detected from the reference image (reference signboard). If the reference signboard has a similarity level to the past signboard below a certain level, processor 220 may determine that a POI change has occurred and define the past signboard as a closing POI.Therefore, processor 220 can detect POI changes due to opening POIs by comparing a reference sign detected from a reference image with past signboards detected from multiple past images, and can detect changes due to closing POIs by comparing past signboards detected from past images at a specific time point with a reference signboard detected from a reference image.

[0049] In step 330, processor 220 may extract POI information from the reference image based on the POI change detection result. If a store opening POI is detected as one of the POI changes, processor 220 may extract information about the store opening POI from the reference image using optical character recognition (OCR) or the like. In other words, processor 220 may generate POI information (e.g., a business name) by applying character recognition technology such as OCR to a signboard area detected as a POI change area among signboard areas detected in the reference image. As an example, processor 220 may recognize a business name included in a signboard area corresponding to a POI change area and use it as information about the POI. Furthermore, processor 220 may acquire location information of the reference image in which a signboard area corresponding to a POI change area was detected and online information about the POI obtained by searching using the business name recognized in the signboard area, as information about the POI. Similarly, for a closed store POI, information about the closed store POI may be extracted from a past image using character recognition technology such as OCR.

[0050] In step 340, processor 220 may register the POI information resulting from the POI change extracted in step 330 in a database for services (such as a map service or an augmented reality service, for example) provided by server 150. Processor 220 may newly register information about the opening POI in the database as a result of the POI change due to the opening POI, and in the case of a POI change due to a closing POI, may delete the closing POI information in the database or change it to a different management format. Thus, processor 220 can maintain the latest POI information about the target location by reflecting the POI change result in the database.

[0051] Figure 4 is a diagram illustrating an example of a POI information management process in one embodiment of the present invention, which summarizes the POI information management process for maintaining up-to-date POI information through automatic POI change detection.

[0052] Referring to Figure 4, when processor 220 is given a reference image, which is the most recent street view image obtained by street view photography of a target location, it may use the photography information (position and direction information) of the reference image to read from map database 401 a certain number (K) of past street view images whose position and direction information are the same as or similar to that of the reference image.

[0053] Next, processor 220 may perform POI change detection by comparing the K past street view images with a reference image, which is the most recent street view image. At this time, if a signboard area similar to a signboard area in the reference image is not present in the K past street view images, processor 220 may define the POI as a new POI (a newly opened store POI). Furthermore, if a signboard area similar to a signboard area in any one of the K past street view images is not present in the reference image, processor 220 may define the POI as a deleted POI (a closed store POI).

[0054] Next, processor 220 may analyze the changed POI information to extract information about the POI from the sign area in the reference image for the opening POI, and extract information about the POI from the sign area in the past image for the closing POI.

[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 an opening POI in the POI database 402, and in the case of a closing POI, may delete the POI information in the POI database or change it to a different management format.

[0056] 5 and 6 are exemplary diagrams illustrating a process for defining an opening POI in one embodiment of the present invention.

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

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

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

[0060] For example, the processor 220 may extract image descriptors using a deep image retrieval (DIR) algorithm and compare the extracted descriptors to determine their similarity. Descriptors, which represent image features as vectors, are widely used in image search and image analysis. Deep learning-based image search involves learning a global image representation. In the case of a global descriptor, when an input video is received, 2048-dimensional features are extracted through a feature extraction process (e.g., convolution, pooling, etc.). Cosine similarity may be used to compare the extracted 2048-dimensional descriptors. Additionally, well-known algorithms such as Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF) may be used to compare sign feature vectors.

[0061] When performing similarity comparison, a weighting factor may be applied to the similarity with a previously captured image, taking into account the difference in the time at which the images were captured. For example, a similarity factor comparing a recent image with an image captured one week ago may be weighted higher than a similarity factor comparing an image captured two weeks ago.

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

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

[0064] For example, as shown in FIG. 6, the processor 220 may collect a plurality of previous images 602 taken at a previous point in time for a recent image 601 including signs AAA, BBB, EEE, and DDD, and compare the signs in the recent image 601 with the signs in the plurality of previous images 602.

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

[0066] By using multiple past street view images to detect POI changes due to store openings, processor 220 can achieve the effect of performing sign similarity matching redundantly, thereby minimizing false recognition of POI changes.

[0067] 7 and 8 are exemplary diagrams illustrating a process for defining a closed POI in one embodiment of the present invention.

[0068] Referring to FIG. 7, the processor 220 may detect a change in POI due to a closed POI by using the previous image II, which was taken most recently, among the previous images II, III, and IV corresponding to the latest image I.

[0069] The processor 220 may compare the sign feature vector II of the previously captured image II with the sign feature vector I of the most recently captured image I, and if the similarity between the sign feature vector I and the sign feature vector II is less than a certain level, define the sign area detected from the previously captured image II as a POI that has been deleted due to closure.

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

[0071] The processor 220 may define signs AAA, BBB, and DDD in the previously captured image 802 that match signs in the most recently captured image 601 as existing POIs, and may define signs CCC that do not match signs in the most recently captured image 601 as a closed POI.

[0072] The processor 220 can provide accurate POI information by detecting not only POI changes due to store openings but also POI changes due to store closings.

[0073] As described above, according to an 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, and the latest POI information can be always maintained. This embodiment detects signs from all of the multiple past images and compares them with the sign information in the recent image, thereby minimizing false recognition of POI changes and improving POI change detection performance.

[0074] The above-described devices may be realized using hardware components, software components, and / or a combination of hardware and software components. For example, the devices and components described in the embodiments may be realized using one or more general-purpose or special-purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or various devices capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the OS. The processing device may also access, record, manipulate, process, and generate data in response to the execution of the software. For convenience of understanding, a single processing device may be described. However, those skilled in the art will understand that a processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing device may include multiple processors or one processor and one controller. Other processing configurations, such as parallel processors, are also possible.

[0075] Software may include a computer program, code, instructions, or a combination of one or more of these, and may configure a processing device to operate as desired or instruct the processing device, either individually or collectively. The software and / or data may be embodied in any type of machine, component, physical device, computer storage medium, or device to be interpreted by or to provide instructions or data to a processing device. The software may be distributed, stored, and executed in a distributed manner across computer systems connected by a network. The software and data may be stored on one or more computer-readable storage media.

[0076] Methods according to embodiments 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 a computer-executable program or may temporarily record the program for execution or download. The medium may be various recording or storage means in the form of a single piece of hardware or multiple pieces of hardware combined together. It may be a medium directly connected to a computer system or distributed over a network. Examples of media 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 media configured to record program instructions, such as ROMs, RAMs, and flash memories. Other examples of media include recording media or storage media managed by app stores that distribute applications, or by websites or servers that provide or distribute various software.

[0077] Although the embodiments have been described above based on limited examples and drawings, those skilled in the art will appreciate that various modifications and variations may be made from the above description. For example, the described techniques may be performed in an order different from that described, and / or the described system, structure, device, circuit, or other element may be coupled or combined in a manner different from that described, or may be substituted or replaced by other elements or equivalents, and still achieve suitable results.

[0078] Therefore, different embodiments are within the scope of the appended claims, provided that they are equivalent to the claims.

Claims

1. A method for detecting changes in a point of interest (POI) executed on a computer device, comprising: the computing device includes at least one processor configured to execute computer-readable instructions contained in a memory; The POI change detection method includes: detecting, by the at least one processor, a first signage region from a given reference image; detecting, by the at least one processor, a plurality of second sign regions from a plurality of past images corresponding to the reference image; and comparing, by the at least one processor, the first signboard region with the plurality of second signboard regions to detect POI changes. A POI change detection method, comprising:

2. The step of detecting a change in POI includes: If there is no signboard area among the plurality of second signboard areas that has a similarity to the first signboard area of ​​a certain level or more, defining the first signboard area as an opening POI. The POI change detection method according to claim 1 , comprising:

3. The step of defining the POI as an opening POI includes: applying a weighting factor that takes into account a difference in the time points at which the reference image and the plurality of previous images were captured when determining the similarity between the first signboard region and the plurality of second signboard regions; The POI change detection method according to claim 2 , comprising:

4. The step of detecting a change in POI includes: If a third signboard area detected from any one of the plurality of past images has a similarity to the first signboard area below a certain level, the third signboard area is defined as a closed POI. The POI change detection method according to claim 2 , further comprising:

5. The step of defining the POI as a closed POI includes: detecting the closed POI using past images taken at the time of taking the reference image and the immediately preceding time among the plurality of past images; The POI change detection method according to claim 4, comprising:

6. The POI change detection method includes: extracting, by the at least one processor, information about the open POI through analysis of the first sign area; and registering information about the opening POI in a database by the at least one processor; The POI change detection method according to claim 2 , further comprising:

7. The POI change detection method includes: extracting, by the at least one processor, information about the closed POIs through analysis of the third sign area; and and deleting the information about the closed POI from the database or changing it to another management format by the at least one processor. The POI change detection method according to claim 4 , further comprising:

8. The POI change detection method includes: collecting, by the at least one processor, the plurality of past images captured at a time prior to the reference image, the past images having position and orientation information identical to or similar to that of the reference image; The POI change detection method according to claim 1 , further comprising:

9. The collecting step includes: Collecting street view images taken at regular intervals in the past as the plurality of past images.

9. The method for detecting a change in a POI according to claim 8.

10. The collecting step includes: Collecting, as the plurality of past images, street view images taken at successive past points in time starting immediately before the point in time at which the reference image was taken.

9. The method for detecting a change in a POI according to claim 8.

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

12. 1. A computer device comprising: at least one processor configured to execute computer-readable instructions contained in the memory; Including, The at least one processor 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 POI changes; A computer device comprising:

13. The at least one processor If there is no signboard area among the plurality of second signboard areas that has a similarity to the first signboard area of ​​a certain level or more, the first signboard area is defined as an opening POI.

13. The computer device of claim 12.

14. The at least one processor When determining the similarity between the first signboard region and the plurality of second signboard regions, a weighted value is applied that takes into account the difference in the time points of photographing the reference image and the plurality of past images.

14. The computer device of claim 13.

15. The at least one processor If a third signboard area detected from any one of the plurality of past images has a similarity with the first signboard area below a certain level, the third signboard area is defined as a closed POI.

14. The computer device of claim 13.

16. The at least one processor Detecting the closed POI using past images taken at the time of taking the reference image and the immediately preceding time among the plurality of past images.

16. The computer device of claim 15.

17. The at least one processor extracting information about the opening POI by analyzing the first signboard area; Registering information about the opening POI in a database 14. The computer device of claim 13.

18. The at least one processor extracting information about the closed POI by analyzing the third signboard area; Delete the information about the closed POI from the database or change it to another management format.

16. The computer device of claim 15.

19. The at least one processor Collecting the plurality of past images, which are taken at a time before the reference image and have the same or similar position and direction information as the reference image, from among the past images taken at a time before the reference image.

13. The computer device of claim 12.

20. The at least one processor Collecting, as the plurality of past images, Street View images taken at past times with a fixed interval between them, or Street View images taken at past times consecutively from immediately before the time when the reference image was taken.

20. The computer device of claim 19.

Images