Method for determining a guide point of a point of interest, related apparatus and computer program product

Abstract

The disclosure provides a method, device, electronic equipment, computer readable storage medium and computer program product for determining a guide point of a point of interest, and relates to the technical field of artificial intelligence such as computer vision, intelligent transportation and electronic map. A specific embodiment of the method comprises: acquiring a plurality of initial selection images within a preset distance range of a point of interest and corresponding shooting coordinates and shooting angles, then determining an orientation angle of the point of interest, and determining an initial selection image with the highest voting score as a first target image and an initial selection image closest to the point of interest in the orientation angle as a second target image, in response to the similarity between the first target image and the second target image exceeding a similarity threshold, determining a guide point of the point of interest based on the projection point coordinates of a fusion image of the first target image and the second target image. The embodiment can accurately determine the guide point of the point of interest based on the scene image around the point of interest.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, in particular to the technical field of computer vision, intelligent transportation, electronic map and other artificial intelligence, and especially relates to a method and device for determining a guide point of a point of interest, an electronic device, a computer readable storage medium and a computer program product. BACKGROUND

[0002] A point of interest (POI) is a kind of information point with geographical space characteristics. In an electronic map, each residential area, park, school, company, shopping mall and the like is a POI.

[0003] In a real scene, in order to facilitate the user to visit a real building corresponding to a POI smoothly, a guide point corresponding to a real entrance of the real building of the POI is usually set, so as to take the guide point as a navigation terminal in an actual navigation process, to provide a navigation service for the user pointing to the POI, and to solve the problem of being unable to reach directly due to inaccurate navigation, such as detouring by driving and needing to cross a separation belt. SUMMARY

[0004] Embodiments of the present disclosure provide a method, device, electronic device, computer readable storage medium and computer program product for determining a guide point of a point of interest.

[0005] In a first aspect, a method for determining a guide point of a point of interest is provided, including: obtaining a plurality of preliminary images located within a preset distance range of the point of interest and shooting coordinates and shooting angles of the preliminary images; obtaining an orientation angle of the point of interest, and generating voting scores of the preliminary images based on a voting mechanism algorithm; determining a first target image as the preliminary image with the highest voting score and a second target image as the preliminary image closest to the point of interest in the orientation angle; and in response to a similarity between the first target image and the second target image exceeding a similarity threshold, determining the guide point of the point of interest based on a projection point coordinate of a fusion image of the first target image and the second target image.

[0006] In a second aspect, the embodiments of the present disclosure provide a device for determining a guide point of a point of interest, comprising: a preliminary image acquisition unit configured to acquire a plurality of preliminary images located within a preset distance range of the point of interest, and shooting coordinates and a shooting angle of the preliminary images; an orientation angle and a voting score acquisition unit, comprising an orientation angle acquisition subunit configured to acquire an orientation angle of the point of interest, and a voting score acquisition subunit configured to generate a voting score of each preliminary image based on a voting mechanism algorithm; a target image determination unit configured to determine a preliminary image with the highest voting score as a first target image, and a preliminary image closest to the point of interest in the orientation angle as a second target image; and a guide point determination unit configured to, in response to a similarity between the first target image and the second target image exceeding a similarity threshold, determine a guide point of the point of interest based on a projection point coordinate of a fusion image of the first target image and the second target image.

[0007] In a third aspect, the embodiments of the present disclosure provide an electronic device, comprising: at least one processor; and a memory communicatively connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to implement the method for determining a guide point of a point of interest as described in any implementation manner of the first aspect.

[0008] In a fourth aspect, the embodiments of the present disclosure provide a non-transitory computer-readable storage medium storing computer instructions, and the computer instructions are used to enable a computer to implement the method for determining a guide point of a point of interest as described in any implementation manner of the first aspect.

[0009] In a fifth aspect, the embodiments of the present disclosure provide a computer program product comprising a computer program, and the computer program is executable by a processor to implement the method for determining a guide point of a point of interest as described in any implementation manner of the first aspect.

[0010] The method, device, electronic device, computer-readable storage medium and computer program product for determining a guide point of a point of interest provided by the embodiments of the present disclosure acquire a plurality of preliminary images located within a preset distance range of the point of interest, and shooting coordinates and a shooting angle of the preliminary images, then acquire an orientation angle of the point of interest, and generate a voting score of each preliminary image based on a voting mechanism algorithm, next, determine a preliminary image with the highest voting score as a first target image, and a preliminary image closest to the point of interest in the orientation angle as a second target image, and finally, in response to a similarity between the first target image and the second target image exceeding a similarity threshold, determine a guide point of the point of interest based on a projection point coordinate of a fusion image of the first target image and the second target image.

[0011] After the scene images within the preset range of the interest point are determined as the initial selected images, the content, the shooting coordinates and the shooting angle of the multiple scene images are mined to determine the guide point position of the interest point. The guide point position of the interest point can be accurately determined in a relatively complex real scene.

[0012] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0013] Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments made with reference to the drawings:

[0014] Figure 1 is an exemplary system architecture to which the present disclosure can be applied;

[0015] Figure 2 A flowchart of a method for determining a guide point of an interest point provided by an embodiment of the present disclosure;

[0016] Figure 3 A flowchart of another method for determining a guide point of an interest point provided by an embodiment of the present disclosure;

[0017] Figure 4-1 、 4-2 , 4-3 is an effect schematic diagram of a method for determining a guide point of an interest point in an application scenario provided by an embodiment of the present disclosure;

[0018] Figure 5 A structural block diagram of a device for determining a guide point of an interest point provided by an embodiment of the present disclosure;

[0019] Figure 6 A structural schematic diagram of an electronic device suitable for executing a method for determining a guide point of an interest point provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to help understanding. They should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and structures are omitted in the following description for clarity and conciseness. It should be noted that the embodiments in the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0021] In addition, the technical solutions involved in the present disclosure involve the acquisition, storage, use, processing, transportation, provision and disclosure of user personal information, which comply with relevant laws and regulations and do not violate public order and good customs.

[0022] Figure 1 An exemplary system architecture 100 is shown to illustrate embodiments of the method, device, electronic device and computer readable storage medium for determining a guide point of a point of interest to which the present disclosure can be applied.

[0023] As shown in Figure 1 The system architecture 100 can include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0024] The user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. The terminal devices 101, 102, 103 and the server 105 can be installed with various applications for realizing information communication between them, such as map construction applications, navigation applications, instant messaging applications, etc.

[0025] The terminal devices 101, 102, 103 and the server 105 can be hardware or software. When the terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens, including but not limited to smart phones, tablet computers, laptop computers and desktop computers, etc. When the terminal devices 101, 102, 103 are software, they can be installed in the above-mentioned electronic devices, which can be implemented as multiple software or software modules, or as a single software or software module, which is not specifically limited here. When the server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server. When the server 105 is software, it can be implemented as multiple software or software modules, or as a single software or software module, which is not specifically limited here.

[0026] The server 105 can provide various services through various applications built-in, to provide image collection of scene images, and take the map construction application which uses the collected images including real scenes to construct electronic maps as an example, the server 105 can achieve the following effects when running the image collection application: first, through the network 104, the server 105 obtains multiple primary images within a preset distance range of a point of interest, and the shooting coordinates and shooting angles of the primary images from the terminal devices 101, 102 and 103; then, the server 105 obtains the orientation angle of the point of interest, and generates the voting scores of the primary images based on the voting mechanism algorithm; next, the server 105 determines the primary image with the highest voting score as the first target image, and determines the primary image closest to the point of interest on the orientation angle as the second target image; finally, the server 105 responds when the similarity between the first target image and the second target image exceeds the similarity threshold, and determines the guide point of the point of interest based on the projection point coordinates of the fusion image of the first target image and the second target image.

[0027] It should be noted that the primary images and the shooting coordinates and shooting angles corresponding to the primary images can be obtained from the terminal devices 101, 102 and 103 through the network 104, or can be pre-stored in the server 105 locally through various ways. Therefore, when the server 105 detects that the local has already stored these data (for example, before starting the guide point determination task of the point of interest left over), the server 105 can choose to obtain these data directly from the local, and in this case, the exemplary system architecture 100 can also not include the terminal devices 101, 102 and 103 and the network 104.

[0028] Since collecting and processing initial images requires significant computing resources and power, the methods for determining guide points of interest provided in subsequent embodiments of this disclosure are generally executed by a server 105 with strong computing power and abundant computing resources. Correspondingly, the device for determining guide points of interest is also generally located in the server 105. However, it should also be noted that when terminal devices 101, 102, and 103 also possess sufficient computing power and resources, they can also perform the aforementioned calculations performed by the server 105 through map-building applications installed on them, thereby outputting the same results as the server 105. Especially when multiple terminal devices with different computing capabilities exist simultaneously, but the map-building application determines that the terminal device has strong computing power and abundant remaining computing resources, it can allow the terminal device to perform the aforementioned calculations, thereby appropriately reducing the computing pressure on the server 105. Accordingly, the device for determining guide points of interest can also be located in terminal devices 101, 102, and 103. In this case, the exemplary system architecture 100 may also exclude the server 105 and the network 104.

[0029] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0030] Please refer to Figure 2 , Figure 2 A flowchart of a method for determining guide points of interest according to an embodiment of this disclosure is provided, wherein process 200 includes the following steps:

[0031] Step 201: Obtain multiple preliminary images located within a preset distance range of the point of interest, along with the shooting coordinates and shooting angle of each preliminary image.

[0032] In this embodiment, the execution body of the method for determining the guide point of interest (e.g., Figure 1 The server 105 shown acquires multiple preliminary images located within a preset distance range of the point of interest, as well as the shooting coordinates and shooting angles of the preliminary images. The preliminary images are real scene images that include the content pointed to by the point of interest. For example, when the point of interest is a shopping mall, the preliminary images are real scene images of the corresponding buildings of the shopping mall taken from various angles. The preset distance range can be determined in combination with actual needs. It can usually be determined based on the shooting capabilities of the shooting terminal device used by the user who took the preliminary images. For example, when the shooting terminal device is a mobile phone or other terminal device, the preset distance range can be determined to be 150 meters based on the shooting capabilities of the mobile phone.

[0033] It should be understood that the shooting coordinates of the preliminary images can be determined based on the location of the user when shooting the preliminary images. In practice, the above execution subject can generally construct a coordinate map in advance to facilitate identification of the geographic coordinates of the interest point and the shooting coordinates of each preliminary image using the coordinate map.

[0034] It should be noted that the preliminary images, the shooting coordinates and the shooting angles of the preliminary images can be obtained directly from a local storage device by the above execution subject, or can be obtained from a non-local storage device (for example Figure 1 The local storage device can be a data storage module provided in the above execution subject, such as a server hard disk, in which case the preliminary images, the shooting coordinates and the shooting angles of the preliminary images can be read locally quickly. The non-local storage device can also be any other electronic device provided for storing data, such as some user terminal, etc., in which case the above execution subject can obtain the required preliminary images, the shooting coordinates and the shooting angles of the preliminary images by sending an acquisition command to the electronic device.

[0035] Step 202, obtaining the orientation angle of the interest point, and generating the voting score of each preliminary image based on a voting mechanism algorithm.

[0036] In this embodiment, the orientation angle of the interest point is obtained, which can generally be determined based on the included angle information between the interest point in the preliminary image and the pre-known target object, road, and the voting score of each preliminary image is generated using a voting mechanism algorithm. Voting is a combination strategy for classification problems in ensemble learning, which is an ensemble learning model following the principle of majority over minority. By integrating multiple models, the variance is reduced, thereby improving the robustness of the model (how high the algorithm tolerates data changes). Among all ensemble learning methods, the most intuitive is majority voting, because its purpose is to output the most popular (or most popular) prediction among the predictions of the base learners. Majority voting is the simplest ensemble learning technique, which allows the predictions of multiple base learners to be combined, similar to the way elections work. This algorithm assumes that each base learner is a voter and each class is a competitor. In order to select the competitor as the winner, the algorithm will consider the votes. In practice, there are two main methods for combining multiple predictions with voting: one is hard voting, and the other is soft voting.

[0037] The scoring standard of the bidding mechanism algorithm can be determined according to the different types of interest points and actual needs, for example, when the interest point is a "shopping mall" and the desired guide point is the "shopping mall entrance position", the scoring standard of the voting mechanism algorithm can be determined according to the completeness and clarity of the "shopping mall entrance" related information content included in the preliminary image.

[0038] Step 203, determining the first target image as the preliminary image with the highest voting score, and determining the second target image as the preliminary image closest to the interest point in the orientation angle.

[0039] In the embodiment, after the orientation angle and the voting scores of the preliminary images are obtained based on step 202, the first target image is determined as the preliminary image with the highest voting score, and the second target image is determined as the preliminary image closest to the interest point in the orientation angle.

[0040] In practice, when there is no preliminary image in the orientation angle of the interest point, the shooting coordinate of the preliminary image with the smallest orientation angle value can be obtained, and then the direction pointing to the shooting coordinate is determined as the direction of the interest point based on the geographic coordinates of the interest point as the origin. The orientation of the interest point is determined based on the fabricated representation of the orientation, and the second target image is determined based on the fabricated representation of the orientation.

[0041] Step 204, in response to the similarity between the first target image and the second target image exceeding a similarity threshold, determining the guide point of the interest point based on the projection point coordinates of the fusion image of the first target image and the second target image.

[0042] In the embodiment, the similarity between the first target image and the second target image is generated, and in response to the similarity exceeding a pre-configured similarity threshold, the first target image and the second target image are fused to generate a fusion image, the predicted shooting coordinates of the fusion image are projected, and the projection coordinates are taken as the guide coordinates of the interest point, wherein the predicted shooting coordinates of the fusion image are usually the guide point of the interest point.

[0043] In practice, the projection coordinates corresponding to the fusion image and the coordinates of the interest point can also be connected, and then the interest point is extended to the roadside in the direction of the projection point coordinates of the fusion image, and the target point intersecting with the roadside after the extension is determined as the guide point of the interest point, or the point with the shortest straight-line distance to the roadside is determined as the guide point of the interest point based on the projection point coordinates of the fusion image, so as to place the guide point on the roadside, and provide a guide point that is more convenient for users to use and determine the position.

[0044] The method for determining the guide point of the interest point provided by the embodiment of the disclosure can use the content, shooting coordinates, and shooting angles of the multiple scene images in the preset range of the interest point to determine the guide point position of the interest point, and can accurately determine the guide point of the interest point in a relatively complex real scene.

[0045] In some optional implementations of the embodiment, the method further includes: determining the orientation angle of the interest point based on an average of the shooting angles of the preliminary images.

[0046] Specifically, after the shooting angles of the preliminary images are aggregated, an average of the shooting angles is determined based on the aggregated shooting angles and the number of the preliminary images, and the orientation angle of the interest point is determined based on the mirror symmetry angle of the average (i.e., the orientation angle is determined after the angle value of the average is increased by 180°), so as to directly determine the orientation angle of the interest point by using the preliminary images corresponding to the interest point, and improve the determination efficiency of the orientation angle.

[0047] Correspondingly, in the case where the orientation angle of the interest point determined based on the average does not directly exist in the preliminary images, the orientation angle can be adjusted based on the method of determining the orientation angle described in step 203, and the same part of the content can be referred to the description of the corresponding part in step 203, which will not be described here.

[0048] Please refer to Figure 3 , Figure 3 A flowchart of another method for determining a guide point of an interest point provided by the embodiment of the disclosure is shown in FIG. 3, wherein the flow 300 includes the following steps:

[0049] In step 301, an image collection task is generated based on the interest points included in the interest point database, and the image collection task is published to a user.

[0050] In the embodiment, the interest points used for constructing an electronic map can be determined and collected in advance, the determined and collected interest points are constructed into an interest point database, and the corresponding image collection task is generated based on each interest point in the interest point database, the image collection task is used to instruct a user to collect a real scene image around the corresponding interest point, and then the image collection task is published to the user.

[0051] In practice, the image collection task can be pushed to the user by publishing the image collection task to a task sending platform or directly pushing the image collection task to each user, and in practice, when the user completes the image collection task, the operator of the above-mentioned execution subject can also adaptively provide a feedback mechanism for the user, so as to form a good interaction between the users.

[0052] Further, the image collection task can also propose corresponding collection requirements for different types of interest points, for example, when the interest point is a shopping mall, the corresponding collection requirement can be “shooting the entrance of the shopping mall”.

[0053] In step 302, the collection image returned by the user for the image collection task and the shooting parameter of the collection image are obtained.

[0054] In this embodiment, after issuing an image acquisition task to the user based on step 302 above, the acquired image returned by each user for the image acquisition task and the shooting parameters of the acquired image are obtained. The shooting parameters include at least the shooting coordinates and the shooting angle. It should be understood that the shooting parameters are usually obtained by requiring the user to actively provide or authorize the above-mentioned execution entity to collect the user's position information when the user completes the image acquisition task (i.e. when the acquired image is taken) in order to determine the shooting coordinates and shooting angle corresponding to the acquired image.

[0055] In some embodiments, a reasonable acquisition range can be configured for each point of interest (image acquisition task), and after determining the shooting coordinates of the acquired image, the acquired image can be filtered based on the acquisition range and shooting coordinates, so as to filter the acquired image with a large deviation in shooting positioning accuracy.

[0056] In addition, in practice, after the acquisition of images is completed, outlier mining algorithms can be used to filter noisy data to further improve the quality of the acquired images.

[0057] Step 303: The acquired images belonging to the same point of interest and their corresponding shooting parameters are stored in the initial image set of the corresponding point of interest.

[0058] In this embodiment, a preliminary image set is configured in advance for different points of interest. After receiving the acquired image (and the corresponding shooting parameters) pointing to the point of interest, the acquired image and the corresponding shooting parameters are stored in the preliminary image set of the point of interest. In practice, the point of interest corresponding to the acquired image can be determined by the point of interest pointed to in the image acquisition task pointed to by the returned acquired image, and the acquired images belonging to the same point of interest and the corresponding shooting parameters are stored in the preliminary image set of the corresponding point of interest.

[0059] Step 304: From the initial image set corresponding to the point of interest, obtain multiple initial images located within a preset distance range of the point of interest, as well as the shooting coordinates and shooting angle of the initial images.

[0060] In this embodiment, when acquiring the initial images corresponding to the points of interest, the initial image set generated and obtained based on the above steps can be used to extract each initial image, along with its corresponding shooting coordinates and shooting angle, from the initial image set by setting a preset distance range.

[0061] Step 305: Obtain the orientation angle of the point of interest and generate the voting score for each preliminary image based on the voting mechanism algorithm.

[0062] Step 306: The preliminary image with the highest voting score is determined as the first target image, and the preliminary image that is closest to the point of interest in terms of orientation angle is determined as the second target image.

[0063] Step 307: In response to the similarity between the first target image and the second target image exceeding a similarity threshold, the guide point of the interest point is determined based on the projection point coordinates of the fused image of the first target image and the second target image.

[0064] Steps 305-307 above and as follows Figure 2 Steps 202-204 shown are the same. For the same parts, please refer to the corresponding parts of the previous embodiment. They will not be repeated here. This embodiment is based on the above. Figure 2 Based on the illustrated embodiment, further, image acquisition tasks can be generated based on points of interest and sent to users to obtain images that can be selected as preliminary images. This can enrich the image sources of real scene images around points of interest, thereby enriching the source of materials used to recreate real scenes and determine guide points for points of interest, and further improving the quality of determining guide points for points of interest.

[0065] In some optional implementations of this embodiment, storing the acquired images belonging to the same point of interest and their corresponding shooting parameters into the initial image set of the corresponding point of interest includes: performing a clustering algorithm on each acquired image based on the shooting parameters of each acquired image to generate a shooting category for each acquired image; performing unsupervised clustering processing on the acquired images in each shooting category to obtain the cluster center of each shooting category; and, in response to the existence of a target point of interest corresponding to the cluster center, storing the acquired images under the shooting category corresponding to the cluster center into the initial image set of the target point of interest.

[0066] Specifically, the clustering algorithm is performed on each of the collected images based on the shooting parameters of the collected images to generate a shooting category of each of the collected images, that is, each of the collected images of an image collection task that can belong to a same interest point is clustered to obtain a plurality of shooting categories (each shooting category corresponds to an image collection task of a same interest point), and then an unsupervised clustering algorithm such as a density-based clustering algorithm (Density-Based Spatial Clustering of Applications with Noise, referred to as DBSCAN) is used to perform unsupervised clustering on the collected images in each shooting category to obtain a clustering center of each shooting category, and then each clustering center is matched with each target interest point, and when there is a target interest point matched with the clustering center, a response is performed, and the collected images in the shooting category corresponding to the clustering center are stored in an initial image set of the target interest point. In this way, the user does not need to accurately feed back the pointed interest point, and the same collected image can be used to determine the guide points of multiple interest points, which not only reduces the above data requirement of the user, but also further improves the utilization rate of the collected images.

[0067] In some optional implementations of the embodiment, the shooting parameters further include a shooting time, and the method for determining the guide point of the interest point further includes: determining a collected image with a shooting time not exceeding a preset time threshold as a qualified collected image; and storing the collected images belonging to a same interest point and the corresponding shooting parameters in the initial image set of the corresponding interest point includes: storing the qualified collected images belonging to a same interest point and the corresponding shooting parameters in the initial image set of the corresponding interest point.

[0068] Specifically, when the shooting parameters further include a shooting time, a time threshold can also be preset according to actual needs, so as to screen the collected images by using the time threshold. The time threshold is a time distance of the shooting time from the current time (for example, the time threshold is one year from the shooting time to the current time). After the collected image with a shooting time not exceeding the preset time threshold is determined as a qualified collected image, only the qualified collected image is stored in the initial image set, so as to eliminate the historical data with low timeliness by using the time threshold, and further improve the practical quality of the collected images and the initial images.

[0069] In some optional implementations of the embodiment, the method further includes: obtaining standard text information of each of the interest points and collected text information included in each of the collected images; establishing an association between the interest point and the collected image based on a similarity between the standard text information and the collected text information; and removing the collected image that is not associated with the interest point.

[0070] Specifically, standard text information (such as sign information, trademark information, etc.) of each point of interest can be obtained, as well as the collected text information included in each collected image. After obtaining the similarity between the standard text information and the collected text information, the association between each point of interest and each collected image is established based on the similarity. The association can usually be divided into multiple levels (for example, when the similarity is <30%, there is no association between the point of interest and the collected image; when the similarity is 30% ≤ 70%, the point of interest and the collected image have a normal association; when the similarity is 70% ≤ 100%, the point of interest and the collected image have a strong association). Furthermore, after determining the association between the point of interest and the collected image, the collected images that do not have an association with the point of interest are cleared. This is to determine the use value of the collected images for the point of interest, while sorting out and clearing the unusable or irrelevant collected images to improve the use quality of the collected images.

[0071] In some optional implementations of this embodiment, the method further includes: obtaining the coordinate information of the point of interest, and determining the road network information within the preset distance range of the point of interest based on the coordinate information; and clearing the preliminary images in the preliminary image set corresponding to the point of interest whose coordinates are not located on the road network information.

[0072] Specifically, after obtaining the coordinate information of each point of interest, the road network information of each point of interest within a preset distance range can be determined based on the coordinate information. The initial images in the initial image set corresponding to each point of interest whose coordinates are not located on the corresponding road network information can be cleared. This is to clean up the collected images that cannot be used for road binding operations, and to avoid the shooting coordinates (positions) that cannot be bound to the road interfering with the determination of the guide point of interest, or the determination of the guide point being unreachable, thereby improving the practical quality of the guide point.

[0073] To enhance understanding, this disclosure also provides a specific implementation scheme based on a particular application scenario, in which the guide point is determined for the "A Department Store" point of interest, as detailed below:

[0074] Obtain images located within a preset distance range from the point of interest, such as... Figure 4-1 The image shows preliminary selected images a, b, and c, along with their shooting coordinates and angles. For example, ... Figure 4-2 As shown, in the coordinate system constructed with the point of interest as the origin, the shooting coordinates of the initial selected image a are (-1, 2), the shooting coordinates of the initial selected image b are (0, -15), the shooting coordinates of the initial selected image c are (12, -15), and the shooting angles of the initial selected image a are -26.6°, the shooting angles of the initial selected image b are 0°, and the shooting angles of the initial selected image c are 51°.

[0075] After obtaining the orientation angle of the "A Department Store", the voting mechanism algorithm is used to generate the voting scores of the preliminary images according to the clarity and completeness of the "store entrance" mark included in the preliminary images, and the scores of the preliminary image a, the preliminary image b, and the preliminary image c are determined as 90, 80, and 50 respectively.

[0076] The preliminary image a with the highest voting score is determined as the first target image, and the preliminary image b closest to the interest point in the orientation angle is determined as the second target image.

[0077] After obtaining the similarity (91%) between the first target image and the second target image, it is determined that the similarity exceeds the similarity threshold (80%) in response, a fusion image is generated based on the first target image and the second target image, and the guide point of the interest point is determined based on the projection point coordinates (0, -2) of the fusion image. Referring to Figure 4-3 , the guide point is the "store entrance" of the "A Department Store".

[0078] Further referring to Figure 5 , as an implementation of the method shown in the above figures, the present disclosure provides an embodiment of a device for determining the guide point of an interest point. The device embodiment corresponds to the method embodiment shown in Figure 2 , and the device can be applied to various electronic devices.

[0079] As shown in Figure 5 , the device 500 for determining the guide point of an interest point of the present embodiment can include a preliminary image acquisition unit 501, an orientation angle and voting score acquisition unit 502, a target image determination unit 503, and a guide point determination unit 504. The preliminary image acquisition unit 501 is configured to acquire a plurality of preliminary images within a preset distance range of an interest point and the shooting coordinates and shooting angles of the preliminary images. The orientation angle and voting score acquisition unit 502 includes an orientation angle acquisition subunit configured to obtain the orientation angle of the interest point, and a voting score acquisition subunit configured to generate the voting scores of the preliminary images based on a voting mechanism algorithm. The target image determination unit 503 is configured to determine the preliminary image with the highest voting score as the first target image, and the preliminary image closest to the interest point in the orientation angle as the second target image. The guide point determination unit 504 is configured to determine the guide point of the interest point based on the projection point coordinates of the fusion image of the first target image and the second target image in response to the similarity between the first target image and the second target image exceeding the similarity threshold.

[0080] In the embodiment, the specific processing of the initial image acquisition unit 501, the orientation angle and voting score acquisition unit 502, the target image determination unit 503 and the guide point determination unit 504 in the device 500 for determining the guide point of the interest point and the technical effects brought by the specific processing can be referred to the corresponding description of steps 201-204 in the embodiment. Figure 2 The related description of steps 201-204 in the corresponding embodiment will not be repeated here.

[0081] In some optional implementation manners of the embodiment, the device 500 for determining the guide point of the interest point further comprises: an acquisition task distribution unit configured to generate an image acquisition task based on the interest points included in the interest point database, and distribute the image acquisition task to a user; an acquisition image collection unit configured to acquire an acquisition image returned by the user for the image acquisition task, and a shooting parameter of the acquisition image, the shooting parameter at least comprising a shooting coordinate and a shooting angle; an initial image storage unit configured to store the acquisition images belonging to the same interest point and the corresponding shooting parameters in the initial image set of the corresponding interest point; and the initial image acquisition unit is further configured to acquire a plurality of initial images located within a preset distance range of the interest point and the shooting coordinate and the shooting angle of the initial images from the initial image set corresponding to the interest point.

[0082] In some optional implementation manners of the embodiment, the initial image storage unit comprises: a shooting category generation subunit configured to perform a clustering algorithm on each acquisition image based on the shooting parameter of each acquisition image to generate a shooting category of each acquisition image; a clustering center generation subunit configured to perform unsupervised clustering processing on the acquisition images in each shooting category to obtain a clustering center of each shooting category; and an initial image set storage subunit configured to store the acquisition images under the shooting category corresponding to the clustering center in the initial image set of the target interest point in response to the existence of the target interest point corresponding to the clustering center.

[0083] In some optional implementation manners of the embodiment, the shooting parameter further comprises a shooting time, and the device 500 for determining the guide point of the interest point further comprises: a first acquisition image screening unit configured to determine the acquisition image whose shooting time does not exceed a preset time threshold as a qualified acquisition image; and the initial image storage unit is further configured to store the qualified acquisition images belonging to the same interest point and the corresponding shooting parameters in the initial image set of the corresponding interest point.

[0084] In some optional implementation of the embodiment, the device 500 for determining the guide point of the interest point further comprises: a text information acquisition unit configured to acquire standard text information of each of the interest points and acquisition text information included in each of the acquisition images; an acquisition image association unit configured to establish an association between the interest point and the acquisition image based on similarity of the standard text information and the acquisition text information; and a second acquisition image screening unit configured to remove the acquisition image that is not associated with the interest point.

[0085] In some optional implementation of the embodiment, the device 500 for determining the guide point of the interest point further comprises: a road network information acquisition unit configured to acquire coordinate information of the interest point and determine road network information within the preset distance range of the interest point based on the coordinate information; and a preliminary image screening unit configured to remove the preliminary image whose shooting coordinate is not located on the road network information in the preliminary image set corresponding to the interest point.

[0086] In some optional implementation of the embodiment, the device 500 for determining the guide point of the interest point further comprises: a direction angle determination unit configured to determine a direction angle of the interest point based on an average value of shooting angles of each of the preliminary images.

[0087] The embodiment provides the device for determining the guide point of the interest point, which can use the content, the shooting coordinate and the shooting angle in the multiple scene images to determine the guide point position of the interest point after taking the scene images within the preset range of the interest point as the preliminary images, and can accurately determine the guide point of the interest point in a relatively complex real scene.

[0088] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0089] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0090] As Figure 6As shown, the device 600 includes a computing unit 601 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 602 or a computer program loaded into a random access memory (RAM) 603 from a storage unit 608. Various programs and data required for the operation of the device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0091] Various components in the device 600 are connected to the I / O interface 605, including an input unit 606, such as a keyboard, a mouse, etc., an output unit 607, such as various types of displays, speakers, etc., a storage unit 608, such as a magnetic disk, an optical disk, etc., and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0092] The computing unit 601 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 601 performs various methods and processes described above, such as the method of determining a guide point of a point of interest. For example, in some embodiments, the method of determining a guide point of a point of interest can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method of determining a guide point of a point of interest described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the method of determining a guide point of a point of interest by any other appropriate means, such as by means of firmware.

[0093] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0094] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, or entirely on a remote machine or server.

[0095] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0096] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0097] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0098] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of large management difficulty and weak business scalability in traditional physical host and virtual private server (VPS, Virtual Private Server) services. The server can also be a server of a distributed system, or a server combined with a blockchain.

[0099] According to the technical scheme of the embodiment of the present disclosure, the scene images within the preset range of the interest point can be used as the initial selected images, and the content, shooting coordinates and shooting angle of the multiple scene images are mined to determine the guide point position of the interest point. The guide point of the interest point can be accurately determined in a relatively complex real scene.

[0100] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions provided by the present disclosure can be achieved, which is not limited herein.

[0101] The above detailed description does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for determining guide points of interest, comprising: Acquire multiple preliminary images located within a preset distance range of the point of interest, along with the shooting coordinates and shooting angles of the preliminary images; The orientation angle of the point of interest is obtained, and a voting score is generated for each of the preliminary images based on a voting mechanism algorithm. The scoring criteria for the voting score are determined based on the completeness and / or clarity of the content related to the guide point of the point of interest in the preliminary image. The preliminary image with the highest voting score is determined as the first target image, and the preliminary image that is closest to the point of interest in terms of orientation angle is determined as the second target image; In response to the similarity between the first target image and the second target image exceeding a similarity threshold, the guiding point of the interest point is determined based on the projection point coordinates of the fused image of the first target image and the second target image.

2. The method according to claim 1, further comprising: An image acquisition task is generated based on the points of interest included in the point of interest database, and the image acquisition task is published to the user. The system obtains the captured image returned by the user for the image acquisition task and the shooting parameters of the captured image, wherein the shooting parameters include at least: shooting coordinates and shooting angle; Images belonging to the same point of interest, along with their corresponding shooting parameters, are stored in the initial image set for that point of interest; and The acquisition of multiple preliminary images located within a preset distance range of the point of interest, along with the shooting coordinates and shooting angles of the preliminary images, includes: From the initial set of images corresponding to the point of interest, obtain multiple initial images located within a preset distance range of the point of interest, along with the shooting coordinates and shooting angles of the initial images.

3. The method according to claim 2, wherein, The step of storing the acquired images belonging to the same point of interest and their corresponding shooting parameters into the initial image set of the corresponding point of interest includes: Based on the shooting parameters of each of the acquired images, a clustering algorithm is performed on each of the acquired images to generate the shooting category of each of the acquired images; Unsupervised clustering is performed on the captured images in each of the aforementioned shooting categories to obtain the cluster centers for each shooting category; In response to the existence of a target interest point corresponding to the cluster center, the acquired images under the shooting category corresponding to the cluster center are stored in the initial image set of the target interest point.

4. The method according to claim 2, wherein the shooting parameters further include shooting time, and further include: Images whose capture time does not exceed a preset time threshold are identified as qualified images. as well as The step of storing the acquired images belonging to the same point of interest and their corresponding shooting parameters into the initial image set of the corresponding point of interest includes: Qualified images belonging to the same point of interest, along with their corresponding shooting parameters, are stored in the initial image set for that point of interest.

5. The method according to claim 2, further comprising: Obtain standard text information for each of the points of interest, as well as the text information included in each of the acquired images; The association between the points of interest and the acquired images is established based on the similarity between the standard text information and the acquired text information; Remove any images that do not have the associated points of interest.

6. The method according to any one of claims 2-5, further comprising: Obtain the coordinate information of the point of interest, and determine the road network information within the preset distance range of the point of interest based on the coordinate information; Remove the initial images from the initial image set corresponding to the point of interest whose coordinates are not located on the road network information.

7. The method according to claim 1, further comprising: The orientation angle of the point of interest is determined based on the average shooting angle of each of the initial selected images.

8. A device for determining a guide point of interest, comprising: The initial image acquisition unit is configured to acquire multiple initial images located within a preset distance range of the point of interest, as well as the shooting coordinates and shooting angle of the initial images; The orientation angle and voting score acquisition unit includes an orientation angle acquisition subunit configured to acquire the orientation angle of the point of interest, and a voting score acquisition subunit configured to generate voting scores for each of the preliminary selection images based on a voting mechanism algorithm, wherein the scoring criteria for the voting score are determined based on the completeness and / or clarity of the content related to the guide point of the point of interest in the preliminary selection image; The target image determination unit is configured to determine the preliminary image with the highest voting score as the first target image and the preliminary image that is closest to the point of interest in terms of orientation angle as the second target image; The guide point determination unit is configured to determine the guide point of the interest point based on the projection point coordinates of the fused image of the first target image and the second target image in response to the similarity between the first target image and the second target image exceeding a similarity threshold.

9. The apparatus according to claim 8, further comprising: The image acquisition task distribution unit is configured to generate an image acquisition task based on the points of interest included in the point of interest database, and to publish the image acquisition task to the user. An image acquisition unit is configured to acquire the acquired image returned by the user for the image acquisition task and the shooting parameters of the acquired image, wherein the shooting parameters include at least: shooting coordinates and shooting angle; The initial image storage unit is configured to store acquired images belonging to the same point of interest, along with their corresponding shooting parameters, into the corresponding initial image set for that point of interest; and The preliminary image acquisition unit is further configured to acquire multiple preliminary images located within a preset distance range of the point of interest, as well as the shooting coordinates and shooting angles of the preliminary images, from the preliminary image set corresponding to the point of interest.

10. The apparatus according to claim 9, wherein, The initial image storage unit includes: The shooting category generation subunit is configured to perform a clustering algorithm on each of the captured images based on the shooting parameters of each captured image to generate the shooting category of each captured image; Cluster center generation subunits are configured to perform unsupervised clustering processing on the acquired images in each of the shooting categories to obtain the cluster centers for each shooting category; The initial image set is stored in the sub-unit, which is configured to, in response to the existence of a target interest point corresponding to the cluster center, store the acquired images under the shooting category corresponding to the cluster center into the initial image set of the target interest point.

11. The apparatus according to claim 9, wherein the shooting parameters further include shooting time, and further include: The first image acquisition filtering unit is configured to determine the acquired images whose shooting time does not exceed a preset time threshold as qualified acquired images. as well as The initial image storage unit is further configured to store qualified acquired images belonging to the same point of interest and their corresponding shooting parameters into the initial image set of the corresponding point of interest.

12. The apparatus according to claim 9, further comprising: The text information acquisition unit is configured to acquire standard text information of each of the points of interest, as well as the acquired text information included in each of the acquired images; The image association unit is configured to establish an association between the point of interest and the acquired image based on the similarity between the standard text information and the acquired text information; The second image filtering unit is configured to remove images that do not have an association with the point of interest.

13. The apparatus according to any one of claims 9-12, further comprising: The road network information acquisition unit is configured to acquire the coordinate information of the point of interest and determine the road network information within the preset distance range of the point of interest based on the coordinate information. The initial image filtering unit is configured to remove initial images from the initial image set corresponding to the point of interest whose captured coordinates are not located on the road network information.

14. The apparatus according to claim 8, further comprising: The orientation angle determination unit is configured to determine the orientation angle of the point of interest based on the average of the shooting angles of each of the initial selected images.

15. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for determining a guide point of interest according to any one of claims 1-7.

16. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of determining a guide point of interest according to any one of claims 1-7.

17. A computer program product comprising a computer program that, when executed by a processor, implements a method for determining a guide point of interest according to any one of claims 1-7.

Images