Image information verification method, system and computer readable storage medium

Abstract

The present invention provides a method, system and computer-readable storage medium for verifying image information, wherein the method for verifying image information includes receiving image information, and obtaining preset vehicle information and preset building information; obtaining corresponding vehicle information to be detected according to the image information, and obtaining at least one building information to be detected; if the vehicle information to be detected matches the preset vehicle information, and any building information to be detected matches the preset building information, it is determined that the image information has passed the verification. By applying the technical solution provided by the present invention, when verifying the identity of an online car-hailing vehicle, the vehicle information and building information in the image information are verified at the same time. While ensuring the correct identity of the online car-hailing vehicle, by introducing the synchronous detection of random landmark buildings, the occurrence of cheating in "off-site" verification of vehicles is avoided, thereby improving the accuracy and reliability of vehicle image detection.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and in particular to an image information verification method, an image information verification system and a computer-readable storage medium. Background Art

[0002] In related technologies, online ride-hailing platforms operate tens of thousands of vehicles every day, and a small number of them are not registered vehicles. In order to supervise such vehicles, it is necessary to verify online whether the operating vehicles are consistent with the registered ones. However, the current verification method only verifies the vehicle image, not the area where the vehicle is located, so there is a loophole of "off-site" verification. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art or related art.

[0004] To this end, a first aspect of the present invention provides a method for verifying image information.

[0005] A second aspect of the present invention provides a system for verifying image information.

[0006] A third aspect of the present invention provides a computer-readable storage medium.

[0007] In view of this, the first aspect of the present invention provides a method for verifying image information, including: receiving image information, and obtaining preset vehicle information and preset building information; obtaining corresponding vehicle information to be detected according to the image information, and obtaining at least one building information to be detected; if the vehicle information to be detected matches the preset vehicle information, and any building information to be detected matches the preset building information, it is determined that the image information has passed the verification.

[0008] In this technical solution, when verifying the image information, the image information is first received. The image information is used to verify the identity of the online car-hailing vehicle, which includes the vehicle information to be detected and the building information to be detected. Among them, the vehicle information to be detected is the vehicle image of the online car-hailing vehicle, which may include the vehicle appearance, vehicle color and license plate information. The building information to be detected is the registration place of the online car-hailing vehicle, that is, the landmark building where the vehicle to be detected is registered, such as railway stations, monuments, skyscrapers and other "unique" buildings, which can all be used as landmark buildings.

[0009] When verifying the image information, the image information is obtained by image recognition to obtain the information of the vehicle to be detected and the information of the building to be detected that is located in the same image as the vehicle to be detected. If and only if the vehicle to be detected matches the preset vehicle information filed with the online car-hailing platform, and any of the information of the building to be detected included in the image information matches the preset building information, the image information is determined to have passed the verification, otherwise it fails. Among them, the preset building information is the building information corresponding to a randomly designated building among the landmark buildings where the vehicle to be detected is registered.

[0010] By applying the technical solution provided by the present invention, when verifying the identity of an online car-hailing vehicle, the vehicle information and building information in the picture information are verified at the same time. While ensuring the correct identity of the online car-hailing vehicle, by introducing synchronous detection of random landmark buildings, cheating in "off-site" vehicle verification is avoided, thereby improving the accuracy and reliability of vehicle image detection.

[0011] In addition, the image information verification method in the above technical solution provided by the present invention may also have the following additional technical features:

[0012] In the above technical solution, the step of obtaining information of at least one building to be detected specifically includes: parsing image information through a building detection model to obtain a feature image containing one or more buildings; determining coordinate information corresponding to one or more buildings according to the feature image, and determining feature information corresponding to any building; generating a representation vector corresponding to any building according to the coordinate information and the feature information, and generating the information of the building to be detected according to the representation vector.

[0013] In this technical solution, the original image information is parsed by the building detection model, and a feature image containing one or more buildings is obtained. Specifically, the building detection model integrates the target detection model and the feature similarity matching model, and extracts basic features through the common backbone network of the model. Specifically, a target detection branch is added to the backbone network, and the positions of different buildings are detected by the target detection branch to determine the coordinate information. Next, the local feature information corresponding to each building is extracted from the basic feature map extracted by the backbone network, that is, the above-mentioned feature image, through the coordinate information of different buildings.

[0014] The feature information of different buildings is respectively connected to the pixel row recognition head to output the characterization vector corresponding to any building. The information of the building to be detected is generated according to the characterization vector. Whether the building is the target building is determined according to the information of the building to be detected. There is no need to repeatedly match and verify the similarity between the feature images of multiple buildings and the designated building one by one, which effectively saves computing resources and improves detection efficiency.

[0015] In any of the above technical solutions, the preset building information includes a preset characterization vector corresponding to the preset building; the similarity between any characterization vector in the building information to be detected and the preset characterization vector is determined; if the similarity between any characterization vector and the preset characterization vector is less than a preset threshold, it is determined that the building information to be detected matches the preset building information.

[0016] In this technical solution, by comparing the characterization vector in the information of the building to be detected with the preset characterization vector, the similarity between the characterization vector of the building to be detected and the preset characterization vector can be determined. If the similarity is higher than the preset threshold, it is determined that the building to be detected and the preset building are the same building, and the building information in the image information matches the preset building information. When any building included in the image information is identified as a preset building, it can be determined that the shooting location of the current image information is consistent with the registration location of the vehicle to be detected on the online car-hailing platform, which effectively prevents the cheating method of "shooting in a different place" and improves the accuracy of image verification of online car-hailing.

[0017] In any of the above technical solutions, the step of obtaining the corresponding vehicle information to be detected based on the image information specifically includes: parsing the image information to obtain a vehicle image; detecting the vehicle image through a license plate recognition model to determine the license plate number information corresponding to the vehicle image; and determining the vehicle information based on the license plate number information.

[0018] In this technical solution, when performing vehicle verification, the target recognition model detects and captures the image of the vehicle to be detected in the image information. The vehicle image should include the overall image of one side of the vehicle and the license plate image. After the vehicle image is captured, the license plate recognition model (OCR, Optical Character Recognition) is used to determine the corresponding license plate number information, and the vehicle information is determined based on the license plate number information to ensure the integrity and accuracy of the vehicle information.

[0019] In some implementations, the vehicle information also includes vehicle appearance information, specifically including vehicle color, vehicle size, vehicle type, etc., and may also include vehicle brand information, etc.

[0020] In any of the above technical solutions, the preset vehicle information includes preset license plate number information; if the license plate number information matches the preset license plate number information, it is determined that the vehicle information to be detected matches the preset vehicle information.

[0021] In this technical solution, when determining whether the vehicle to be detected is a preset vehicle registered on the platform, the matching of the license plate number is the minimum requirement. Therefore, when the detected license plate number information matches the preset license plate number information registered on the platform, it can be determined that the information of the vehicle to be detected matches the preset vehicle information, that is, the vehicle in the image information is a vehicle registered on the platform.

[0022] In any of the above technical solutions, before the step of receiving image information, the image information verification method also includes: receiving a verification request, and obtaining the first position information of the corresponding vehicle to be detected according to the verification request; obtaining a preset building set, and determining the landmark building closest to the vehicle to be detected in the preset building set according to the first position information, and determining it as the preset building; and sending the second position information of the preset building to the terminal corresponding to the vehicle to be detected.

[0023] In this technical solution, when performing image verification on an online car-hailing vehicle, the online car-hailing platform can first initiate a verification request. The verification request can also be initiated by a terminal held by the driver, or by a terminal held by a subscriber of the online car-hailing service. After receiving the verification request, the first position information of the vehicle to be detected, that is, the target online car-hailing vehicle of the verification request, is obtained. The first position information can be obtained by the GPS (Global Positioning System) installed on the online car-hailing vehicle and uploaded by the vehicle end.

[0024] After obtaining the first location information of the vehicle to be detected, obtain the preset building set pre-stored on the platform. The preset building set contains all the landmark buildings in cities or regions where online car-hailing services are available, and their feature information from various perspectives. Select a landmark building closest to the vehicle to be detected from the preset building set and determine it as the preset building. Send the second location information of the preset building to the terminal corresponding to the vehicle to be detected, so that the driver can drive to the vicinity of the landmark building to take photos.

[0025] Among them, when determining the preset buildings, you can also first determine multiple landmark buildings within a certain range from the vehicle to be detected, and randomly select a landmark building from multiple landmark buildings that are relatively close as the preset building, so as to further improve the randomness and diversity of the preset building selection and avoid cheating.

[0026] In any of the above technical solutions, the step of receiving image information specifically includes: receiving image information sent by the terminal, the image information simultaneously including an image corresponding to the vehicle to be detected and an image corresponding to the preset building.

[0027] In this technical solution, the terminal corresponding to the vehicle to be detected, that is, the terminal held by the online car-hailing driver who is currently receiving verification, uploads image information for verification to ensure the driver's identity. At the same time, the image information needs to include the direction corresponding to the vehicle to be detected and the image corresponding to the preset building, on the one hand to ensure the accuracy of the vehicle, on the other hand to ensure the accuracy of the vehicle position, so as to improve the accuracy of verification.

[0028] In any of the above technical solutions, before the step of receiving image information, the image information verification method also includes: obtaining a preset detection model and obtaining building sample data, the building sample data including coordinate information and feature information corresponding to multiple buildings; generating a training set based on the building sample data, and training the preset detection model through the training set to obtain a building detection model.

[0029] In this technical solution, firstly, pictures of landmark buildings from the east, south, west and north are collected, and the characteristic information of each building is calibrated by image recognition technology, and the location information is calibrated. Building sample data is generated by the annotated pictures of multiple buildings, and finally a training set for training the preset detection model is generated. By training the preset detection model with the training set, a highly efficient building detection model can be obtained.

[0030] The second aspect of the present invention provides an image information verification system, including a processor configured to store a computer program; the processor is configured to execute the computer program to implement the image information verification method provided in any of the above-mentioned technical solutions. Therefore, the image information verification system includes all the beneficial effects of the image information verification method provided in any of the above-mentioned technical solutions, which will not be repeated here.

[0031] The third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the image information verification method provided in any of the above-mentioned technical solutions is implemented. Therefore, the computer-readable storage medium includes all the beneficial effects of the image information verification method provided in any of the above-mentioned technical solutions, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0033] Figure 1 A flowchart showing a method for verifying image information according to an embodiment of the present invention is shown;

[0034] Figure 2 Another flow chart showing a method for verifying image information according to an embodiment of the present invention;

[0035] Figure 3 Another flow chart of a method for verifying image information according to an embodiment of the present invention is shown;

[0036] Figure 4 Another flow chart of a method for verifying image information according to an embodiment of the present invention is shown;

[0037] Figure 5Another flow chart of a method for verifying image information according to an embodiment of the present invention is shown;

[0038] Figure 6 Another flow chart of a method for verifying image information according to an embodiment of the present invention is shown;

[0039] Figure 7 A schematic diagram of the architecture of a building detection model according to an embodiment of the present invention is shown;

[0040] Figure 8 A schematic diagram of the online car-hailing verification process according to an embodiment of the present invention is shown;

[0041] Fig. 9 A structural block diagram of an image information verification system according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0042] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0043] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0044] Refer to the following Figures 1 to 9 The image information verification method, image information verification system and computer-readable storage medium according to some embodiments of the present invention are described.

[0045] Embodiment 1

[0046] like Figure 1 As shown, in an embodiment of the first aspect of the present invention, a method for verifying image information is provided, comprising:

[0047] Step S102, receiving image information, and obtaining preset vehicle information and preset building information;

[0048] Step S104, obtaining corresponding information of a vehicle to be detected according to the image information, and obtaining information of at least one building to be detected;

[0049] Step S106: if the vehicle information to be detected matches the preset vehicle information, and any building information to be detected matches the preset building information, it is determined that the image information passes the verification.

[0050] In this embodiment, when verifying the image information, the image information is first received. The image information is used to verify the identity of the online car-hailing vehicle, which includes the vehicle information to be detected and the building information to be detected. Among them, the vehicle information to be detected is the vehicle image of the online car-hailing vehicle, which may include the vehicle appearance, vehicle color and license plate information. The building information to be detected is the registration place of the online car-hailing vehicle, that is, the landmark building where the vehicle to be detected is registered, such as railway stations, monuments, skyscrapers and other "unique" buildings, which can all be used as landmark buildings.

[0051] When verifying the image information, the image information is obtained by image recognition to obtain the information of the vehicle to be detected and the information of the building to be detected that is located in the same image as the vehicle to be detected. If and only if the vehicle to be detected matches the preset vehicle information filed with the online car-hailing platform, and any of the information of the building to be detected included in the image information matches the preset building information, the image information is determined to have passed the verification, otherwise it fails. Among them, the preset building information is the building information corresponding to a randomly designated building among the landmark buildings where the vehicle to be detected is registered.

[0052] The embodiment provided by the present invention, when verifying the identity of the online-hailing car, simultaneously verifies the vehicle information and building information in the picture information. While ensuring the correct identity of the online-hailing car, by introducing synchronous detection of random landmark buildings, it avoids the occurrence of "off-site" vehicle verification cheating, thereby improving the accuracy and reliability of vehicle image detection.

[0053] In one embodiment of the present invention, Figure 2 As shown, the step of obtaining at least one building information to be detected specifically includes:

[0054] Step S202, parsing the image information through a building detection model to obtain a feature image containing one or more buildings;

[0055] Step S204, determining coordinate information corresponding to one or more buildings according to the feature image, and determining feature information corresponding to any building;

[0056] Step S206: Generate a characterization vector corresponding to any building according to the coordinate information and the feature information, and generate information of the building to be detected according to the characterization vector.

[0057] In this embodiment, the original image information is parsed by the building detection model, and a feature image containing one or more buildings is obtained. Specifically, the building detection model integrates the target detection model and the feature similarity matching model, and extracts basic features through the common backbone network of the models. Specifically, a target detection branch is added to the backbone network, and the positions of different buildings are detected by the target detection branch to determine the coordinate information. Next, the local feature information corresponding to each building is extracted from the basic feature map extracted from the backbone network, that is, the above-mentioned feature image, through the coordinate information of different buildings, that is, the above-mentioned feature information.

[0058] The feature information of different buildings is respectively connected to the pixel row recognition head to output the characterization vector corresponding to any building. The information of the building to be detected is generated according to the characterization vector. Whether the building is the target building is determined according to the information of the building to be detected. There is no need to repeatedly match and verify the similarity between the feature images of multiple buildings and the designated building one by one, which effectively saves computing resources and improves detection efficiency.

[0059] In one embodiment of the present invention, Figure 3 As shown, the preset building information includes a preset characterization vector corresponding to the preset building, and the method for verifying the image information further includes:

[0060] Step S302, determining the similarity between any characterization vector in the building information to be detected and a preset characterization vector;

[0061] Step S304: if the similarity between any characterization vector and the preset characterization vector is less than a preset threshold, it is determined that the building information to be detected matches the preset building information.

[0062] In this embodiment, by comparing the characterization vector in the information of the building to be detected with the preset characterization vector, the similarity between the characterization vector of the building to be detected and the preset characterization vector can be determined. If the similarity is higher than the preset threshold, it is determined that the building to be detected and the preset building are the same building, and the building information in the image information matches the preset building information. When any building included in the image information is identified as a preset building, it can be determined that the shooting location of the current image information is consistent with the registration location of the vehicle to be detected on the online car-hailing platform, which effectively prevents the cheating method of "shooting in a different place" and improves the accuracy of image verification of online car-hailing.

[0063] In one embodiment of the present invention, Figure 4 As shown, the step of obtaining the corresponding vehicle information to be detected according to the image information specifically includes:

[0064] Step S402, parsing the image information to obtain a vehicle image;

[0065] Step S404, detecting the vehicle image through the license plate recognition model to determine the license plate number information corresponding to the vehicle image;

[0066] Step S406, determining vehicle information according to the license plate number information.

[0067] In this embodiment, when performing vehicle verification, the target recognition model detects and captures the image of the vehicle to be detected in the image information. The vehicle image should include the overall image of a certain side of the vehicle and the license plate image. After the vehicle image is captured, the corresponding license plate number information is determined by the license plate recognition model (OCR, Optical Character Recognition, optical character recognition), and the vehicle information is determined based on the license plate number information to ensure the integrity and accuracy of the vehicle information.

[0068] In some implementations, the vehicle information also includes vehicle appearance information, specifically including vehicle color, vehicle size, vehicle type, etc., and may also include vehicle brand information, etc.

[0069] In one embodiment of the present invention, the preset vehicle information includes preset license plate number information; if the license plate number information matches the preset license plate number information, it is determined that the vehicle information to be detected matches the preset vehicle information.

[0070] In this embodiment, when determining whether the vehicle to be detected is a preset vehicle registered on the platform, the matching of the license plate number is the minimum requirement. Therefore, when the detected license plate number information matches the preset license plate number information registered on the platform, it can be determined that the information of the vehicle to be detected matches the preset vehicle information, that is, the vehicle in the image information is a vehicle registered on the platform.

[0071] In one embodiment of the present invention, Figure 5 As shown, before the step of receiving the image information, the method for verifying the image information further includes:

[0072] Step S502, receiving a verification request, and obtaining first position information of a corresponding vehicle to be detected according to the verification request;

[0073] Step S504, obtaining a preset building set, determining a landmark building closest to the vehicle to be detected in the preset building set according to the first position information, and determining it as the preset building;

[0074] Step S506: Send the second location information of the preset building to the terminal corresponding to the vehicle to be detected.

[0075] In this embodiment, when performing image verification on an online car-hailing vehicle, the online car-hailing platform may first initiate a verification request. The verification request may also be initiated by a terminal held by a driver, or by a terminal held by a subscriber of the online car-hailing service. After receiving the verification request, the first position information of the vehicle to be detected, i.e., the target online car-hailing vehicle of the verification request, is obtained. The first position information may be obtained by a GPS (Global Positioning System) installed on the online car-hailing vehicle and uploaded by the vehicle end.

[0076] After obtaining the first location information of the vehicle to be detected, obtain the preset building set pre-stored on the platform. The preset building set contains all the landmark buildings in cities or regions where online car-hailing services are available, and their feature information from various perspectives. Select a landmark building closest to the vehicle to be detected from the preset building set and determine it as the preset building. Send the second location information of the preset building to the terminal corresponding to the vehicle to be detected, so that the driver can drive to the vicinity of the landmark building to take photos.

[0077] Among them, when determining the preset buildings, you can also first determine multiple landmark buildings within a certain range from the vehicle to be detected, and randomly select a landmark building from multiple landmark buildings that are relatively close as the preset building, so as to further improve the randomness and diversity of the preset building selection and avoid cheating.

[0078] In one embodiment of the present invention, the step of receiving image information specifically includes: receiving image information sent by a terminal, wherein the image information includes an image corresponding to the vehicle to be detected and an image corresponding to a preset building.

[0079] In this embodiment, the terminal corresponding to the vehicle to be detected, that is, the terminal held by the online car-hailing driver who is currently receiving verification, uploads image information for verification to ensure the driver's identity. At the same time, the image information needs to include the direction corresponding to the vehicle to be detected and the image corresponding to the preset building, on the one hand to ensure the accuracy of the vehicle, on the other hand to ensure the accuracy of the vehicle position, so as to improve the accuracy of verification.

[0080] In one embodiment of the present invention, Figure 6 As shown, before the step of receiving the image information, the method for verifying the image information further includes:

[0081] Step S602, obtaining a preset detection model and obtaining building sample data, where the building sample data includes coordinate information and feature information corresponding to a plurality of buildings;

[0082] Step S604, generating a training set according to the building sample data, and training a preset detection model through the training set to obtain a building detection model.

[0083] In this embodiment, firstly, pictures of each landmark building from the east, south, west and north perspectives are collected, and the characteristic information of each building is calibrated by image recognition technology, and the location information is calibrated. Building sample data is generated by the annotated pictures of multiple buildings, and finally a training set for training a preset detection model is generated. By training the preset detection model with the training set, a highly efficient building detection model can be obtained.

[0084] Embodiment 2

[0085] In a complete embodiment of the present invention, the embodiment of the present invention is described in detail by taking the process of verifying whether an online car-hailing vehicle is a registered vehicle during the online car-hailing service as an example.

[0086] Specifically, when the driver completes an order during a certain period of time, he specifies a nearby landmark building and asks the vehicle to take a photo with the landmark to complete vehicle verification. After taking the photo, the photo is uploaded to check whether the specified landmark building exists in the photo. Usually, there are multiple buildings in the background of the vehicle photo, so each building needs to be compared with the target landmark building. If each comparison is done independently from the beginning, it will take a long time. Therefore, the present invention proposes a new target building matching model, which can complete the matching of multiple buildings with only one detection.

[0087] The architecture diagram of the building detection model is as follows Figure 7 As shown, and has the following characteristics:

[0088] 1. The target detection model and the feature similarity matching model are integrated, and the common backbone network of the model of the present invention is used to extract basic features. A target detection branch is added to the backbone network to detect different building locations, and then the locations of different buildings are used to extract the local features corresponding to the buildings on the basic feature map extracted by the backbone network. The local features of different buildings are then connected to the similarity recognition head to output the characterization vector of the building. The characterization vector is compared with the characterization vector of the target building respectively, and the distance between the features is less than a threshold and is considered to be the same building.

[0089] 2. After extracting the local features of different buildings, we connect a recognition head for the east, south, west, and north directions of the building to reinforce that the representation vectors of the same building in different directions must be consistent.

[0090] When a driver completes an order, the system automatically determines whether there are any recognizable landmark buildings near the driver. If so, the location of the landmark will be sent to the driver, and the driver will be required to take a photo of the vehicle and the landmark at the designated landmark and upload it to the system for real-time authentication.

[0091] The implementation process has the following steps:

[0092] Step 1: Collect pictures of each landmark building from the southeast, northwest and north angles and mark their locations.

[0093] Step 2: Offline training of the model of the present invention is performed using the collected images until the representation vectors output from different viewing angles of the same landmark building are similar.

[0094] Step 3: During online verification, send the location of the landmark building closest to the driver, ask the driver to drive to the designated landmark, take a photo of the vehicle and the landmark and upload it for verification.

[0095] Step 4: Identify the license plate number through the license plate OCR recognition model and compare it with the registered license plate number. If the license plate numbers are consistent, the vehicle is confirmed successfully.

[0096] Step 5: Firstly extract the basic feature map using the model of the present invention.

[0097] Step 6: Detect the coordinates of different buildings in the group photo on the basic feature map in step 5.

[0098] Step 7: Extract local features of different buildings based on steps 5 and 6.

[0099] Step 8: Based on step 7, output the representation vectors of different buildings.

[0100] Step 9: Use the representation vectors of the designated landmark buildings to compare with the representation vectors of the buildings in the group photo one by one.

[0101] Step 10: When the similarity between a certain building representation vector and a designated landmark representation vector in the group photo is higher than a threshold, the landmark is confirmed to be successful.

[0102] Step 11: If both step 4 and step 10 are successful, the verification is considered successful; otherwise, it is considered a failure.

[0103] The specific online car-hailing verification process is as follows: Figure 8 As shown, including:

[0104] Verification starts;

[0105] Step S802, sending a location of a landmark building that is closest to the driver and has a comparison picture;

[0106] Step S804, the driver takes a photo of the vehicle and the designated landmark location and uploads it;

[0107] Step S806, extracting a basic feature map through the building detection model;

[0108] Step S808, the target detection branch detects the coordinates of different buildings;

[0109] Step S810, extracting local features according to different building coordinates;

[0110] Step S812, outputting representation vectors of different buildings;

[0111] Step S814, identifying the license plate number;

[0112] Step S816, determine whether the license plate number is consistent with the registered one, and whether there is a landmark building in the photo; if so, the verification is successful, otherwise the verification fails.

[0113] Embodiment 3

[0114] like Fig. 9 As shown, in one embodiment of the present invention, an image information verification system 900 is provided, including a memory 902, configured to store a computer program; a processor 904, configured to execute the computer program to implement the image information verification method provided in any of the above embodiments. Therefore, the image information verification system 900 includes all the beneficial effects of the image information verification method provided in any of the above embodiments, which will not be repeated here.

[0115] Embodiment 4

[0116] In one embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the image information verification method provided in any of the above embodiments is implemented. Therefore, the computer-readable storage medium includes all the beneficial effects of the image information verification method provided in any of the above embodiments, which will not be repeated here.

[0117] In the description of the present invention, the term "plurality" refers to two or more than two. Unless otherwise clearly defined, the orientation or positional relationship indicated by the terms "upper" and "lower" is based on the orientation or positional relationship described in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention. The terms "connection", "installation", "fixation", etc. should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be directly connected or indirectly connected through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0118] In the description of the present invention, the description of the terms "one embodiment", "some embodiments", "specific embodiments", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In the present invention, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0119] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for verifying image information, characterized in that: include: Receive image information, and obtain preset vehicle information and preset building information, wherein the preset building information is building information corresponding to a randomly designated building among landmark buildings at the registration location of the to-be-detected vehicle, wherein the preset building information includes a preset representation vector corresponding to the preset building; Acquire corresponding information of a vehicle to be detected according to the image information, and acquire information of at least one building to be detected that is located in the same image as the vehicle to be detected, wherein the at least one building to be detected information includes a characterization vector corresponding to at least one building; The vehicle information to be detected matches the preset vehicle information, and any of the building information to be detected matches the preset building information, and it is determined that the image information has passed the verification; wherein, the matching of any of the building information to be detected with the preset building information is determined based on the similarity between the characterization vector of any of the buildings and the preset characterization vector being less than a preset threshold.

2. The method for verifying image information according to claim 1, characterized in that: The step of obtaining information of at least one building to be detected that is located in the same image as the vehicle to be detected specifically includes: Parsing the image information by a building detection model to obtain a feature image containing one or more buildings; Determine coordinate information corresponding to one or more of the buildings according to the feature image, and determine feature information corresponding to any of the buildings; A characterization vector corresponding to any one of the buildings is generated according to the coordinate information and the feature information, and the information of the building to be detected is generated according to the characterization vector.

3. The image information verification method according to claim 1, characterized in that: The step of acquiring corresponding information of the vehicle to be detected according to the image information specifically includes: parsing the image information to obtain a vehicle image; Detecting the vehicle image through a license plate recognition model to determine the license plate number information corresponding to the vehicle image; The vehicle information is determined according to the license plate number information.

4. The method for verifying image information according to claim 3, characterized in that: The preset vehicle information includes preset license plate number information; If the license plate number information matches the preset license plate number information, it is determined that the to-be-detected vehicle information matches the preset vehicle information.

5. The method for verifying image information according to claim 3 or claim 4, characterized in that: Before the step of receiving the image information, the method for verifying the image information further includes: Receiving a verification request, and acquiring first position information of a corresponding vehicle to be detected according to the verification request; Acquire a preset building set, and determine a landmark building closest to the vehicle to be detected in the preset building set according to the first position information, and determine it as the preset building; The second location information of the preset building is sent to a terminal corresponding to the vehicle to be detected.

6. The method for verifying image information according to claim 5, characterized in that: The step of receiving image information specifically includes: The image information sent by the terminal is received, where the image information includes an image corresponding to the vehicle to be detected and an image corresponding to the preset building.

7. The method for verifying image information according to any one of claims 2 to 4, characterized in that: Before the step of receiving the image information, the method for verifying the image information further includes: Obtaining a preset detection model and obtaining building sample data, wherein the building sample data includes coordinate information and feature information corresponding to a plurality of buildings; A training set is generated according to the building sample data, and the preset detection model is trained by the training set to obtain the building detection model.

8. A system for verifying image information, characterized in that: include: a memory configured to store a computer program; A processor is configured to execute the computer program to implement the image information verification method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the image information verification method according to any one of claims 1 to 7 is implemented.

Images