Advertising board content safety monitoring method and system for expressway

Abstract

The invention relates to the technical field of advertising board content safety monitoring, in particular to an advertising board content safety monitoring method and system for an expressway. An advertisement violation event analysis module in the system controls a cloud recognition platform to receive an advertising board image uploaded by a camera; and carrying out image feature extraction on the billboard image through an image identification technology, carrying out content compliance analysis on the billboard image, identifying a violation event set corresponding to the billboard image, binding the identified violation event with the corresponding billboard image, and feeding back to a display end. The influence of the change of the surrounding environment of the advertising board on the photovoltaic power supply state of the camera is considered, and the problem of power supply endurance of the camera in a continuous atrocious weather environment is solved; the dynamic regulation and control of the shooting period of the camera is realized according to the residual electric quantity and the future weather change condition around the billboard, and the safety monitoring time of the camera on the content of the billboard is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of billboard content security monitoring, and in particular to a billboard content security monitoring method and system for highways. Background Art

[0002] Expressways are important transportation arteries, and billboards along them (including high-pillar billboards, overpass billboards, and service area billboards) are important vehicles for commercial promotion and public welfare information release. They have a wide audience and a huge influence. However, the compliance and safety of billboard content are of paramount importance. The content may involve risks such as false propaganda, illegal and irregular information, vulgar and negative information, and misleading content due to damage or detachment. Therefore, it is necessary to monitor the content of billboards on expressways.

[0003] Traditional methods of regulating billboard content mainly rely on regular manual inspections and passive reporting. This method is inefficient and has poor timeliness. Faced with a large number of scattered highway billboards, manual inspections cannot achieve real-time and comprehensive monitoring.

[0004] With the development of Internet of Things technology, some sections of roads use a method of fixing photovoltaic-powered cameras around billboards and transmitting images taken by the billboards back to a monitoring center. However, this method does not take into account the photovoltaic power supply of the cameras. As a result, in continuous severe weather environments, the cameras often suffer from insufficient power supply and are unable to monitor and transmit the content of the billboards in a timely manner. There is no way to dynamically adjust the camera shooting cycle according to the remaining power and future weather changes around the billboards to ensure the camera's battery life. Therefore, the existing technology has major defects. Summary of the Invention

[0005] The object of the present invention is to provide a method and system for monitoring the content security of billboards on highways, so as to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solution: a method for monitoring the content security of billboards on highways, the method comprising the following steps: S1. Obtaining the location information of billboards installed on the highway; using a photovoltaic-powered camera to periodically capture images of billboards installed on the highway. The camera communicates with a cloud recognition platform via a 5G network and uploads the location information of the corresponding camera and the image of the billboard each time. S2. The cloud-based recognition platform receives billboard images uploaded by the camera, extracts image features from the billboard images using image recognition technology, performs content compliance analysis on the billboard images, identifies the set of violation events corresponding to the billboard images, and binds the identified violation events to the corresponding billboard images, feeding back the information to the display end. S3. Obtain the current shooting environment information and remaining power value of the photovoltaic-powered cameras deployed on the highway; evaluate the corresponding endurance crisis coefficient of each photovoltaic-powered camera deployed on the highway based on the current weather forecast information for each photovoltaic-powered camera deployed on the highway; and calculate the feedback demand evaluation value of each deployed billboard based on the set of violation events corresponding to the images captured by each deployed billboard in historical data; S4. Based on the endurance crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway and the feedback demand evaluation value of each deployed billboard, generate a shooting cycle adjustment coefficient corresponding to each photovoltaic-powered camera deployed on the highway, and update the shooting cycle corresponding to each photovoltaic-powered camera deployed on the highway in real time.

[0007] Furthermore, the shooting time period for each photovoltaic-powered camera deployed in S1 to shoot the image of the billboard set on the corresponding highway is obtained by querying the database; different cameras have different corresponding shooting time periods; When the camera communicates with the cloud recognition platform through the 5G network, the uploaded data also includes the time of each shooting of the corresponding camera, and the billboard image taken each time is bound to the corresponding shooting time and the corresponding camera location information.

[0008] Furthermore, the S2 includes: S21, the cloud recognition platform receives the billboard image uploaded by the camera and numbers each uploaded billboard image; the number corresponding to the i-th uploaded billboard image is recorded as Bi; S22, extracting text information from the billboard image corresponding to Bi using OCR technology, summarizing keywords in the extracted text information, and obtaining an image semantic feature set of the billboard image corresponding to Bi; S23. Obtain the average grayscale value of each pixel in the billboard image corresponding to Bi as the image grayscale value of the corresponding billboard image, denoted as HBi; obtain a set of billboard images uploaded by the camera to which Bi belongs within the most recent preset time, denoted as Bi's reference set; obtain a billboard image in Bi's reference set, the absolute value of the difference between the image grayscale value corresponding to Bi and HBi is less than a preset grayscale threshold, and the billboard image that is closest to the shooting time corresponding to Bi is denoted as Bi's comparison image; S24. Obtain the grayscale value differences between the pixels at the same position between the comparison image corresponding to Bi and the billboard image corresponding to Bi, and mark the positions of the pixels where the grayscale value differences are greater than a preset value in the billboard image corresponding to Bi. The pixel marking results in the billboard image corresponding to Bi are used as the image feature set of the billboard image corresponding to Bi. S25, comparing keywords in the image semantic feature set of the billboard image corresponding to Bi with a preset keyword library corresponding to semantic violation behaviors one by one, and summarizing the keyword set in the preset keyword library corresponding to the semantic violation behaviors in the comparison results as a semantic violation judgment set; when the semantic violation judgment set is an empty set, it is determined that there is no semantic violation event in the billboard image corresponding to Bi; otherwise, it is determined that there is a semantic violation event in the billboard image corresponding to Bi; S26, dividing the image feature set of the billboard image corresponding to Bi into groups whose pixel distances are less than a preset pixel distance, and removing groups whose number of pixels is less than a preset number, recording the image feature set of the billboard image corresponding to Bi after the group removal operation as a picture violation judgment set; when the picture violation judgment set is an empty set, it is determined that there is no picture violation event in the billboard image corresponding to Bi; otherwise, it is determined that there is a picture violation event in the billboard image corresponding to Bi; S27 , record the summary set of the image violation event determination results and the semantic violation event determination results of the billboard image corresponding to Bi as the violation event set of the billboard image corresponding to Bi .

[0009] The present invention recognizes the status of content violation events on highway billboards from the perspectives of semantics and images, and recognizes risks such as false propaganda, illegal information, vulgar and bad information, and misleading risks caused by damaged or detached content on billboards. The set of violation events on billboard images not only provides auxiliary reference for corresponding administrators in rectifying billboard violations, but also provides reference suggestions and data support for the maintenance of highway billboards.

[0010] Furthermore, the shooting environment information in S3 includes the effective visibility of the environment at the time of shooting; the weather forecast information includes the effective visibility prediction value, solar irradiance prediction value and wind speed corresponding to each time point in a subsequent preset time period based on the current time; The calculation formula for evaluating the endurance crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway in S3 is as follows: ; Among them, EL j represents the evaluation value of the cruising risk coefficient corresponding to the j-th photovoltaic power supply camera deployed on the highway; TG j represents the length of the interval corresponding to the shooting working time interval of the j-th photovoltaic power supply camera deployed on the highway based on the current weather forecast information; TG j At any time point in the corresponding time interval, the effective visibility prediction value corresponding to the j-th photovoltaic power supply camera deployed on the highway based on the weather forecast information at the current time is greater than the first visibility threshold; BP jrepresents the remaining power value of the jth photovoltaic-powered camera deployed on the highway at the current time; H j represents the power consumption of each shot by the j-th photovoltaic-powered camera deployed on the highway at the current time; TP j represents the shooting cycle of the jth photovoltaic-powered camera deployed on the highway at the current time; TB j G represents the length of the time interval corresponding to the solar irradiance prediction value greater than the preset solar irradiance threshold value in the weather forecast information of the j-th photovoltaic power supply camera deployed on the highway; （j，t） Indicates TB j The predicted value of solar irradiance at time point t in the corresponding time interval; β （j，t） Indicates TB j The solar irradiance loss coefficient bound to the effective visibility prediction value at time point t in the corresponding time interval in the database preset table; F{} represents the operation of querying the solar power generation speed corresponding to different solar irradiances in the database preset table; Indicates that the solar irradiance in the database preset table is Time corresponds to the speed of light power generation; BC j represents the upper limit of the battery capacity of the jth photovoltaic-powered camera deployed on the highway.

[0011] Furthermore, the calculation formula involved in calculating the feedback demand evaluation value of each deployed billboard in S3 is as follows: ; Among them, FR j represents the feedback demand evaluation value of the deployed j-th billboard; the maximum wind speed of the deployed j-th billboard based on the current weather forecast information is recorded as W j ; Obtain the maximum wind speed value corresponding to two consecutive shootings of the same billboard image by the deployed photovoltaic camera. When there is no violation event in the previous billboard image and there is a violation event in the next billboard image, bind the violation event corresponding to the next billboard image to the maximum wind speed value corresponding to the two shooting periods; SP j Indicates that the bound wind speed is less than or equal to W in the set of violation events corresponding to the captured images of the j-th billboard deployed in the historical data j The summary set of billboard images to which each screen violation event belongs; SE j Indicates that the bound wind speed is less than or equal to W in the set of violation events corresponding to the captured images of the j-th billboard deployed in the historical data j The summary set of billboard images to which each semantic violation event belongs; Len{} represents the function of counting the number of elements in the set; Num jIndicates that the maximum wind speed corresponding to the time interval between the image of the j-th billboard deployed in the historical data and the time of the previous image shooting is less than or equal to W j The total number of captured images.

[0012] When analyzing the feedback demand evaluation value of each deployed billboard, the present invention obtains the analysis by analyzing the proportion of images involving violation events on the billboard; during the analysis process, the maximum wind speed value corresponding to two consecutive times when the photovoltaic camera takes the same billboard image is used as the screening condition. The reason is that the wind speed on the highway may carry surrounding objects or damage the billboard itself, resulting in the risk of damage (involving image violation events); at the same time, it is also taken into account that in the process of analyzing violation events on the billboard image, for the same image, not only the image violation event risk but also the semantic violation event risk will be analyzed. Therefore, when using wind speed as the screening condition, it is necessary to first obtain SP j and SE j The number of billboard images contained in the union of ; and then accurately calculate the feedback demand evaluation value of each deployed billboard.

[0013] Furthermore, in the process of obtaining the shooting cycle adjustment coefficient corresponding to each photovoltaic power supply camera deployed on the highway in S4, the shooting cycle adjustment coefficient corresponding to the j-th photovoltaic power supply camera deployed on the highway is recorded as g j , ; Among them, Sigmoid() represents the Sigmoid function; ξ represents the preset weight coefficient; EL j represents the evaluation value of the cruising risk coefficient corresponding to the j-th photovoltaic power supply camera deployed on the highway; FR j represents the feedback demand evaluation value of the deployed j-th billboard; the g j The value range is (-1,1); The updated result of the shooting cycle corresponding to each photovoltaic-powered camera deployed on the highway is equal to the product of the shooting cycle corresponding to the corresponding photovoltaic-powered camera at the current time multiplied by 1 and the difference between the shooting cycle adjustment coefficient corresponding to the corresponding photovoltaic-powered camera; the shooting cycle corresponding to the photovoltaic-powered camera is updated once every preset time period.

[0014] A billboard content security monitoring system for highways, comprising an advertising image acquisition module, an advertising violation event analysis module, a battery life crisis and demand assessment and analysis module, and a shooting cycle adjustment and management module; The advertising image acquisition module obtains the location information of billboards installed on the highway; the photovoltaic-powered camera deployed periodically captures images of billboards installed on the highway. The camera communicates with the cloud recognition platform via the 5G network and uploads the location information of the corresponding camera and the billboard image captured each time; The advertising violation event analysis module controls the cloud recognition platform to receive billboard images uploaded by the camera, extracts image features from the billboard images through image recognition technology, performs content compliance analysis on the billboard images, identifies the set of violation events corresponding to the billboard images, and binds the identified violation events with the corresponding billboard images, and feeds them back to the display end; The battery life crisis and demand assessment and analysis module obtains the current shooting environment information and remaining power value of the photovoltaic-powered cameras deployed on the highway; combines the weather forecast information of each photovoltaic-powered camera deployed on the highway based on the current time, and evaluates the battery life crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway; combines the set of violation events corresponding to the captured images of each deployed billboard in the historical data, and calculates the feedback demand assessment value of each deployed billboard; The shooting cycle adjustment management module generates a shooting cycle adjustment coefficient corresponding to each photovoltaic-powered camera deployed on the highway based on the endurance crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway and the feedback demand evaluation value of each deployed billboard, and updates the shooting cycle corresponding to each photovoltaic-powered camera deployed on the highway in real time.

[0015] Furthermore, the endurance crisis and demand evaluation and analysis module includes an endurance crisis coefficient calculation unit and a feedback demand evaluation and analysis unit. The endurance crisis coefficient calculation unit obtains the shooting environment information and the remaining power value of the photovoltaic-powered cameras deployed on the highway at the current time; combines the weather forecast information of each photovoltaic-powered camera deployed on the highway based on the current time, and evaluates the endurance crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway; The feedback demand evaluation analysis unit calculates a feedback demand evaluation value of each deployed billboard based on a set of violation events corresponding to captured images of each deployed billboard in historical data.

[0016] Furthermore, the shooting cycle adjustment management module includes a shooting cycle adjustment coefficient calculation unit and a shooting cycle dynamic control unit. The shooting cycle adjustment coefficient calculation unit generates a shooting cycle adjustment coefficient corresponding to each photovoltaic-powered camera deployed on the highway based on the endurance crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway and the feedback demand evaluation value of each deployed billboard; The shooting cycle dynamic control unit updates the shooting cycle corresponding to each photovoltaic-powered camera deployed on the highway in real time according to the shooting cycle adjustment coefficient corresponding to each photovoltaic-powered camera deployed on the highway.

[0017] Compared with the existing technology, the beneficial effects achieved by the present invention are: the present invention takes into account the impact of changes in the surrounding environment of the billboard on the photovoltaic power supply status of the camera, and solves the problem of camera power supply endurance in continuous harsh weather environments; and realizes dynamic regulation of the camera shooting cycle according to the remaining power and future weather changes around the billboard, effectively extending the camera's security monitoring time of the billboard content on the highway, and realizing effective supervision of the safety of the billboard content on the highway. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a schematic structural diagram of the billboard content security monitoring system for highways according to the present invention; Figure 2 The figure is a flow chart of the method for monitoring the content security of billboards on highways according to the present invention. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0020] See also Figure 1-Figure 2 , the present invention provides a technical solution: Figure 1 As shown, this embodiment provides a billboard content security monitoring system for highways, the system includes an advertising image acquisition module, an advertising violation event analysis module, a battery life crisis and demand assessment analysis module, and a shooting cycle adjustment management module; The advertising image acquisition module obtains the location information of billboards installed on the highway; the photovoltaic-powered camera deployed periodically captures images of billboards installed on the highway. The camera communicates with the cloud recognition platform via the 5G network and uploads the location information of the corresponding camera and the billboard image captured each time; The advertising violation event analysis module controls the cloud recognition platform to receive billboard images uploaded by the camera, extracts image features from the billboard images through image recognition technology, performs content compliance analysis on the billboard images, identifies the set of violation events corresponding to the billboard images, and binds the identified violation events with the corresponding billboard images, and feeds them back to the display end; The endurance crisis and demand assessment and analysis module includes an endurance crisis coefficient calculation unit and a feedback demand assessment and analysis unit. The endurance crisis coefficient calculation unit obtains the shooting environment information and the remaining power value of the photovoltaic-powered cameras deployed on the highway at the current time; combines the weather forecast information of each photovoltaic-powered camera deployed on the highway based on the current time, and evaluates the endurance crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway; The feedback demand evaluation and analysis unit calculates a feedback demand evaluation value for each deployed billboard based on a set of violation events corresponding to captured images of each deployed billboard in historical data; The shooting cycle adjustment management module includes a shooting cycle adjustment coefficient calculation unit and a shooting cycle dynamic control unit. The shooting cycle adjustment coefficient calculation unit generates a shooting cycle adjustment coefficient corresponding to each photovoltaic-powered camera deployed on the highway based on the endurance crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway and the feedback demand evaluation value of each deployed billboard; The shooting cycle dynamic control unit updates the shooting cycle corresponding to each photovoltaic-powered camera deployed on the highway in real time according to the shooting cycle adjustment coefficient corresponding to each photovoltaic-powered camera deployed on the highway.

[0021] like Figure 2 As shown, this embodiment provides a method for monitoring billboard content security on a highway, the method comprising the following steps: S1. Obtaining the location information of billboards installed on the highway; using a photovoltaic-powered camera to periodically capture images of billboards installed on the highway. The camera communicates with a cloud recognition platform via a 5G network and uploads the location information of the corresponding camera and the image of the billboard each time. The shooting time period for each photovoltaic-powered camera deployed in S1 to shoot an image of a billboard set on a corresponding highway is obtained by querying a database; different cameras have different corresponding shooting time periods; When the camera communicates with the cloud recognition platform through the 5G network, the uploaded data also includes the time of each shooting of the corresponding camera, and the billboard image taken each time is bound to the corresponding shooting time and the corresponding camera location information.

[0022] S2. The cloud-based recognition platform receives billboard images uploaded by the camera, extracts image features from the billboard images using image recognition technology, performs content compliance analysis on the billboard images, identifies the set of violation events corresponding to the billboard images, and binds the identified violation events to the corresponding billboard images, feeding back the information to the display end. The S2 includes: S21, the cloud recognition platform receives the billboard image uploaded by the camera and numbers each uploaded billboard image; the number corresponding to the i-th uploaded billboard image is recorded as Bi; S22, extracting text information from the billboard image corresponding to Bi using OCR technology, summarizing keywords in the extracted text information, and obtaining an image semantic feature set of the billboard image corresponding to Bi; S23. Obtain the average grayscale value of each pixel in the billboard image corresponding to Bi as the image grayscale value of the corresponding billboard image, denoted as HBi; obtain a set of billboard images uploaded by the camera to which Bi belongs within the most recent preset time, denoted as Bi's reference set; obtain a billboard image in Bi's reference set, the absolute value of the difference between the image grayscale value corresponding to Bi and HBi is less than a preset grayscale threshold, and the billboard image that is closest to the shooting time corresponding to Bi is denoted as Bi's comparison image; S24. Obtain the grayscale value differences between the pixels at the same position between the comparison image corresponding to Bi and the billboard image corresponding to Bi, and mark the positions of the pixels where the grayscale value differences are greater than a preset value in the billboard image corresponding to Bi. The pixel marking results in the billboard image corresponding to Bi are used as the image feature set of the billboard image corresponding to Bi. S25, comparing keywords in the image semantic feature set of the billboard image corresponding to Bi with a preset keyword library corresponding to semantic violation behaviors one by one, and summarizing the keyword set in the preset keyword library corresponding to the semantic violation behaviors in the comparison results as a semantic violation judgment set; when the semantic violation judgment set is an empty set, it is determined that there is no semantic violation event in the billboard image corresponding to Bi; otherwise, it is determined that there is a semantic violation event in the billboard image corresponding to Bi; S26, dividing the image feature set of the billboard image corresponding to Bi into groups whose pixel distances are less than a preset pixel distance, and removing groups whose number of pixels is less than a preset number, recording the image feature set of the billboard image corresponding to Bi after the group removal operation as a picture violation judgment set; when the picture violation judgment set is an empty set, it is determined that there is no picture violation event in the billboard image corresponding to Bi; otherwise, it is determined that there is a picture violation event in the billboard image corresponding to Bi; S27 , record the summary set of the image violation event determination results and the semantic violation event determination results of the billboard image corresponding to Bi as the violation event set of the billboard image corresponding to Bi .

[0023] S3. Obtain the current shooting environment information and remaining power value of the photovoltaic-powered cameras deployed on the highway; evaluate the corresponding endurance crisis coefficient of each photovoltaic-powered camera deployed on the highway based on the current weather forecast information for each photovoltaic-powered camera deployed on the highway; and calculate the feedback demand evaluation value of each deployed billboard based on the set of violation events corresponding to the images captured by each deployed billboard in historical data; The shooting environment information in S3 includes the effective visibility of the environment at the time of shooting; the weather forecast information includes the effective visibility prediction value, solar irradiance prediction value and wind speed corresponding to each time point in the subsequent preset time period based on the current time; The calculation formula for evaluating the endurance crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway in S3 is as follows: ; Among them, EL j represents the evaluation value of the cruising risk coefficient corresponding to the j-th photovoltaic power supply camera deployed on the highway; TG j represents the length of the interval corresponding to the shooting working time interval of the j-th photovoltaic power supply camera deployed on the highway based on the current weather forecast information; TG j At any time point in the corresponding time interval, the effective visibility prediction value corresponding to the j-th photovoltaic power supply camera deployed on the highway based on the weather forecast information at the current time is greater than the first visibility threshold; In this embodiment, the time interval in which the corresponding effective visibility prediction value in the current weather forecast information of the j-th photovoltaic-powered camera deployed on the highway is less than or equal to the first visibility threshold is used as the shooting sleep time interval of the corresponding photovoltaic-powered camera; during the shooting sleep time interval, the photovoltaic-powered camera provides work; BP j represents the remaining power value of the jth photovoltaic-powered camera deployed on the highway at the current time; H j represents the power consumption of each shot by the j-th photovoltaic-powered camera deployed on the highway at the current time; TP j represents the shooting cycle of the jth photovoltaic-powered camera deployed on the highway at the current time; TB j G represents the length of the time interval corresponding to the solar irradiance prediction value greater than the preset solar irradiance threshold value in the weather forecast information of the j-th photovoltaic power supply camera deployed on the highway; （j，t） Indicates TBj The predicted value of solar irradiance at time point t in the corresponding time interval; β （j，t） Indicates TB j The solar irradiance loss coefficient bound to the effective visibility prediction value at time point t in the corresponding time interval in the database preset table; F{} represents the operation of querying the solar power generation speed corresponding to different solar irradiances in the database preset table; Indicates that the solar irradiance in the database preset table is Time corresponds to the speed of light power generation; BC j represents the upper limit of the battery capacity of the jth photovoltaic-powered camera deployed on the highway.

[0024] The calculation formula involved in calculating the feedback demand evaluation value of each deployed billboard in S3 is as follows: ; Among them, FR j represents the feedback demand evaluation value of the deployed j-th billboard; the maximum wind speed of the deployed j-th billboard based on the current weather forecast information is recorded as W j ; Obtain the maximum wind speed value corresponding to two consecutive shootings of the same billboard image by the deployed photovoltaic camera. When there is no violation event in the previous billboard image and there is a violation event in the next billboard image, bind the violation event corresponding to the next billboard image to the maximum wind speed value corresponding to the two shooting periods; SP j Indicates that the bound wind speed is less than or equal to W in the set of violation events corresponding to the captured images of the j-th billboard deployed in the historical data j The summary set of billboard images to which each screen violation event belongs; SE j Indicates that the bound wind speed is less than or equal to W in the set of violation events corresponding to the captured images of the j-th billboard deployed in the historical data j The summary set of billboard images to which each semantic violation event belongs; Len{} represents the function of counting the number of elements in the set; Num j Indicates that the maximum wind speed corresponding to the time interval between the image of the j-th billboard deployed in the historical data and the time of the previous image shooting is less than or equal to W j The total number of captured images.

[0025] S4. Based on the endurance crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway and the feedback demand evaluation value of each deployed billboard, generate a shooting cycle adjustment coefficient corresponding to each photovoltaic-powered camera deployed on the highway, and update the shooting cycle corresponding to each photovoltaic-powered camera deployed on the highway in real time.

[0026] In the process of obtaining the shooting cycle adjustment coefficient corresponding to each photovoltaic power supply camera deployed on the highway in S4, the shooting cycle adjustment coefficient corresponding to the j-th photovoltaic power supply camera deployed on the highway is recorded as g j , ; Among them, Sigmoid() represents the Sigmoid function; ξ represents the preset weight coefficient; EL j represents the evaluation value of the cruising risk coefficient corresponding to the j-th photovoltaic power supply camera deployed on the highway; FR j represents the feedback demand evaluation value of the deployed j-th billboard; the g j The value range is (-1,1); The updated result of the shooting cycle corresponding to each photovoltaic-powered camera deployed on the highway is equal to the product of the shooting cycle corresponding to the corresponding photovoltaic-powered camera at the current time multiplied by 1 and the difference between the shooting cycle adjustment coefficient corresponding to the corresponding photovoltaic-powered camera; the shooting cycle corresponding to the photovoltaic-powered camera is updated once every preset time period.

[0027] In this embodiment, the update and adjustment of the shooting period corresponding to the photovoltaic-powered camera is a continuous process. The update result of the shooting period corresponding to the photovoltaic-powered camera may become smaller, may remain unchanged, or may become larger. The updated shooting period is a multiple of the shooting period before the update (0, 2).

[0028] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0029] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for monitoring the content security of billboards on highways, characterized in that: The method comprises the following steps: S1. Obtaining the location information of billboards installed on the highway; using a photovoltaic-powered camera to periodically capture images of billboards installed on the highway. The camera communicates with a cloud recognition platform via a 5G network and uploads the location information of the corresponding camera and the image of the billboard each time. S2. The cloud-based recognition platform receives billboard images uploaded by the camera, extracts image features from the billboard images using image recognition technology, performs content compliance analysis on the billboard images, identifies the set of violation events corresponding to the billboard images, and binds the identified violation events to the corresponding billboard images, feeding back the information to the display end. S3. Obtain the current shooting environment information and remaining power value of the photovoltaic-powered cameras deployed on the highway; evaluate the corresponding endurance crisis coefficient of each photovoltaic-powered camera deployed on the highway based on the current weather forecast information for each photovoltaic-powered camera deployed on the highway; and calculate the feedback demand evaluation value of each deployed billboard based on the set of violation events corresponding to the images captured by each deployed billboard in historical data; S4. Based on the endurance crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway and the feedback demand evaluation value of each deployed billboard, generate a shooting cycle adjustment coefficient corresponding to each photovoltaic-powered camera deployed on the highway, and update the shooting cycle corresponding to each photovoltaic-powered camera deployed on the highway in real time.

2. The method for monitoring the content security of billboards on highways according to claim 1, characterized in that: The shooting time period for each photovoltaic-powered camera deployed in S1 to shoot an image of a billboard set on a corresponding highway is obtained by querying a database; different cameras have different corresponding shooting time periods; When the camera communicates with the cloud recognition platform through the 5G network, the uploaded data also includes the time of each shooting of the corresponding camera, and the billboard image taken each time is bound to the corresponding shooting time and the corresponding camera location information.

3. The method for monitoring the content security of billboards on highways according to claim 1, wherein: The S2 includes: S21, the cloud recognition platform receives the billboard image uploaded by the camera and numbers each uploaded billboard image; the number corresponding to the i-th uploaded billboard image is recorded as Bi; S22, extracting text information from the billboard image corresponding to Bi using OCR technology, summarizing keywords in the extracted text information, and obtaining an image semantic feature set of the billboard image corresponding to Bi; S23. Obtain the average grayscale value of each pixel in the billboard image corresponding to Bi as the image grayscale value of the corresponding billboard image, denoted as HBi; obtain a set of billboard images uploaded by the camera to which Bi belongs within the most recent preset time, denoted as Bi's reference set; obtain a billboard image in Bi's reference set, the absolute value of the difference between the image grayscale value corresponding to Bi and HBi is less than a preset grayscale threshold, and the billboard image that is closest to the shooting time corresponding to Bi is denoted as Bi's comparison image; S24. Obtain the grayscale value differences between the pixels at the same position between the comparison image corresponding to Bi and the billboard image corresponding to Bi, and mark the positions of the pixels where the grayscale value differences are greater than a preset value in the billboard image corresponding to Bi. The pixel marking results in the billboard image corresponding to Bi are used as the image feature set of the billboard image corresponding to Bi. S25, comparing keywords in the image semantic feature set of the billboard image corresponding to Bi with a preset keyword library corresponding to semantic violation behaviors one by one, and summarizing the keyword set in the preset keyword library corresponding to the semantic violation behaviors in the comparison results as a semantic violation judgment set; when the semantic violation judgment set is an empty set, it is determined that there is no semantic violation event in the billboard image corresponding to Bi; otherwise, it is determined that there is a semantic violation event in the billboard image corresponding to Bi; S26, dividing the image feature set of the billboard image corresponding to Bi into groups whose pixel distances are less than a preset pixel distance, and removing groups whose number of pixels is less than a preset number, recording the image feature set of the billboard image corresponding to Bi after the group removal operation as a picture violation judgment set; when the picture violation judgment set is an empty set, it is determined that there is no picture violation event in the billboard image corresponding to Bi; otherwise, it is determined that there is a picture violation event in the billboard image corresponding to Bi; S27 , record the summary set of the image violation event determination results and the semantic violation event determination results of the billboard image corresponding to Bi as the violation event set of the billboard image corresponding to Bi .

4. The method for monitoring content security of billboards on highways according to claim 1, wherein: The shooting environment information in S3 includes the effective visibility of the environment at the time of shooting; the weather forecast information includes the effective visibility prediction value, solar irradiance prediction value and wind speed corresponding to each time point in the subsequent preset time period based on the current time; The calculation formula for evaluating the endurance crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway in S3 is as follows: ； Among them, EL j represents the evaluation value of the cruising risk coefficient corresponding to the j-th photovoltaic power supply camera deployed on the highway; TG j represents the length of the interval corresponding to the shooting working time interval of the j-th photovoltaic power supply camera deployed on the highway based on the current weather forecast information; TG j At any time point in the corresponding time interval, the effective visibility prediction value corresponding to the j-th photovoltaic power supply camera deployed on the highway based on the weather forecast information at the current time is greater than the first visibility threshold; BP j represents the remaining power value of the jth photovoltaic-powered camera deployed on the highway at the current time; H j represents the power consumption of each shot by the j-th photovoltaic-powered camera deployed on the highway at the current time; TP j represents the shooting cycle of the jth photovoltaic-powered camera deployed on the highway at the current time; TB j G represents the length of the time interval corresponding to the solar irradiance prediction value greater than the preset solar irradiance threshold value in the weather forecast information of the j-th photovoltaic power supply camera deployed on the highway; （j，t） Indicates TB j The predicted value of solar irradiance at time point t in the corresponding time interval; β （j，t） Indicates TB j The solar irradiance loss coefficient bound to the effective visibility prediction value at time point t in the corresponding time interval in the database preset table; F{} represents the operation of querying the solar power generation speed corresponding to different solar irradiances in the database preset table; Indicates that the solar irradiance in the database preset table is Time corresponds to the speed of light power generation; BC j represents the upper limit of the battery capacity of the jth photovoltaic-powered camera deployed on the highway.

5. The method for monitoring content security of billboards on highways according to claim 4, characterized in that: The calculation formula involved in calculating the feedback demand evaluation value of each deployed billboard in S3 is as follows: ； Among them, FR j represents the feedback demand evaluation value of the deployed j-th billboard; the maximum wind speed of the deployed j-th billboard based on the current weather forecast information is recorded as W j ; Obtain the maximum wind speed value corresponding to two consecutive shootings of the same billboard image by the deployed photovoltaic camera. When there is no violation event in the previous billboard image and there is a violation event in the next billboard image, bind the violation event corresponding to the next billboard image to the maximum wind speed value corresponding to the two shooting periods; SP j Indicates that the bound wind speed is less than or equal to W in the set of violation events corresponding to the captured images of the j-th billboard deployed in the historical data j The summary set of billboard images to which each screen violation event belongs; SE j Indicates that the bound wind speed is less than or equal to W in the set of violation events corresponding to the captured images of the j-th billboard deployed in the historical data j The summary set of billboard images to which each semantic violation event belongs; Len{} represents the function of counting the number of elements in the set; Num j Indicates that the maximum wind speed corresponding to the time interval between the image of the j-th billboard deployed in the historical data and the time of the previous image shooting is less than or equal to W j The total number of captured images.

6. The method for monitoring the content security of billboards on highways according to claim 1, characterized in that: In the process of obtaining the shooting cycle adjustment coefficient corresponding to each photovoltaic power supply camera deployed on the highway in S4, the shooting cycle adjustment coefficient corresponding to the j-th photovoltaic power supply camera deployed on the highway is recorded as g j , ； Among them, Sigmoid() represents the Sigmoid function; ξ represents the preset weight coefficient; EL j represents the evaluation value of the cruising risk coefficient corresponding to the j-th photovoltaic power supply camera deployed on the highway; FR j represents the feedback demand evaluation value of the deployed j-th billboard; the g j The value range is (-1,1); The updated result of the shooting cycle corresponding to each photovoltaic-powered camera deployed on the highway is equal to the product of the shooting cycle corresponding to the corresponding photovoltaic-powered camera at the current time multiplied by 1 and the difference between the shooting cycle adjustment coefficient corresponding to the corresponding photovoltaic-powered camera; the shooting cycle corresponding to the photovoltaic-powered camera is updated once every preset time period.

7. A billboard content security monitoring system for highways, applying the billboard content security monitoring method for highways according to any one of claims 1 to 6, characterized in that: The system includes an advertising image acquisition module, an advertising violation event analysis module, a battery life crisis and demand assessment analysis module, and a shooting cycle adjustment management module; The advertising image acquisition module obtains the location information of billboards installed on the highway; the photovoltaic-powered camera deployed periodically captures images of billboards installed on the highway. The camera communicates with the cloud recognition platform via the 5G network and uploads the location information of the corresponding camera and the billboard image captured each time; The advertising violation event analysis module controls the cloud recognition platform to receive billboard images uploaded by the camera, extracts image features from the billboard images through image recognition technology, performs content compliance analysis on the billboard images, identifies the set of violation events corresponding to the billboard images, and binds the identified violation events with the corresponding billboard images, and feeds them back to the display end; The battery life crisis and demand assessment and analysis module obtains the current shooting environment information and remaining power value of the photovoltaic-powered cameras deployed on the highway; combines the weather forecast information of each photovoltaic-powered camera deployed on the highway based on the current time, and evaluates the battery life crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway; combines the set of violation events corresponding to the captured images of each deployed billboard in the historical data, and calculates the feedback demand assessment value of each deployed billboard; The shooting cycle adjustment management module generates a shooting cycle adjustment coefficient corresponding to each photovoltaic-powered camera deployed on the highway based on the endurance crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway and the feedback demand evaluation value of each deployed billboard, and updates the shooting cycle corresponding to each photovoltaic-powered camera deployed on the highway in real time.

8. The billboard content security monitoring system for highways according to claim 7, characterized in that: The endurance crisis and demand assessment and analysis module includes an endurance crisis coefficient calculation unit and a feedback demand assessment and analysis unit. The endurance crisis coefficient calculation unit obtains the shooting environment information and the remaining power value of the photovoltaic-powered cameras deployed on the highway at the current time; combines the weather forecast information of each photovoltaic-powered camera deployed on the highway based on the current time, and evaluates the endurance crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway; The feedback demand evaluation analysis unit calculates a feedback demand evaluation value of each deployed billboard based on a set of violation events corresponding to captured images of each deployed billboard in historical data.

9. The billboard content security monitoring system for highways according to claim 7, characterized in that: The shooting cycle adjustment management module includes a shooting cycle adjustment coefficient calculation unit and a shooting cycle dynamic control unit. The shooting cycle adjustment coefficient calculation unit generates a shooting cycle adjustment coefficient corresponding to each photovoltaic-powered camera deployed on the highway based on the endurance crisis coefficient corresponding to each photovoltaic-powered camera deployed on the highway and the feedback demand evaluation value of each deployed billboard; The shooting cycle dynamic control unit updates the shooting cycle corresponding to each photovoltaic-powered camera deployed on the highway in real time according to the shooting cycle adjustment coefficient corresponding to each photovoltaic-powered camera deployed on the highway.

Images