An intelligent monitoring method, device, equipment and medium based on the Internet of Things

Abstract

The present application relates to the field of Internet of Things technology, and in particular to an intelligent monitoring method, device, equipment and medium based on the Internet of Things. The method includes: obtaining multiple images of a target area, and the load-bearing information of the target area with a time series; extracting features from multiple images, judging whether a vehicle has entered the target area based on the extracted features, and if a vehicle exists, determining whether the features include the target feature; if the target feature is included, determining the position information of the target feature and the target load-bearing information corresponding to the position information; if the target feature is not included, determining the load-bearing difference of the target area before and after the vehicle enters the target area, and determining the estimated weight of the vehicle based on the load-bearing difference; if the target load-bearing information or the estimated weight of the vehicle is greater than the preset weight threshold, controlling the alarm device to issue an alarm message, which can improve the recognition accuracy of electric vehicles and the safety of the target area.

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to an intelligent monitoring method, device, equipment and medium based on the Internet of Things. Background Art

[0002] As people pursue longer distances on electric vehicles, electric vehicle batteries have gradually upgraded from stable lead-acid batteries to lithium batteries with higher energy density but more active performance. The risk of battery fire has greatly increased, especially in public areas with high traffic volume, such as elevators. Electric vehicles entering such areas will occupy a large amount of public space and affect the normal lives of other people. Therefore, the supervision of electric vehicles is very important.

[0003] The related technology installs a camera above the area where electric vehicles are prohibited from entering, and compares the pictures captured by the camera with sample pictures of electric vehicles. If the shapes of the two are similar, an alarm is triggered. However, the electric vehicles may be obscured by the human body in the captured pictures, which makes it easy to identify objects with similar shapes to electric vehicles, such as bicycles and children's cars, as electric vehicles, and the recognition accuracy is low. Summary of the invention

[0004] In order to solve the problem of low electric vehicle identification accuracy in the prior art, the present application provides an intelligent monitoring method, device, equipment and medium based on the Internet of Things.

[0005] In the first aspect, the present application provides an intelligent monitoring method based on the Internet of Things, which adopts the following technical solutions:

[0006] An intelligent monitoring method based on the Internet of Things, comprising:

[0007] Acquire multiple images of a target area and load-bearing information of the target area in a time series;

[0008] Extracting features from the multiple images, judging whether a vehicle has entered the target area according to the extracted features, and if it is judged that a vehicle has entered the target area, determining whether the extracted features include target features;

[0009] If the extracted features include the target feature, determining the position information of the target feature in the target area, and determining the target load-bearing information corresponding to the position information according to the load-bearing information corresponding to the target area;

[0010] If the extracted features do not include the target features, determining the weight difference of the target area before and after the vehicle enters the target area according to the weight information corresponding to the target area, and determining the estimated weight of the vehicle according to the weight difference;

[0011] It is determined whether the target load-bearing information or the estimated vehicle weight is greater than a preset weight threshold. If the target load-bearing information or the estimated vehicle weight is greater than the preset weight threshold, the alarm device is controlled to issue an alarm message.

[0012] By adopting the above technical solution, feature extraction is performed on multiple images, so as to accurately determine whether there is a vehicle entering the target area; if so, it is further determined whether the extracted features contain the target features; if so, the position information of the target features in the target area is determined, and according to the position information, the target load-bearing information corresponding to the position information can be accurately determined from the load-bearing information with a time series corresponding to the target area, and the target load-bearing information can represent the weight of the vehicle entering the target area; if not contained, the estimated weight of the vehicle is determined according to the load-bearing difference of the target area before and after the vehicle enters the target area; the obtained target load-bearing information or the estimated weight of the vehicle is compared with the preset weight threshold, so as to determine whether the vehicle entering the target area is an electric vehicle, thereby improving the recognition accuracy of the electric vehicle, and in response to the illegal behavior of pushing the electric vehicle into the target area, the alarm device is controlled to send an alarm message to prompt the owner to push the electric vehicle out of the target area, thereby improving the safety of the target area.

[0013] In a preferred example, the present application may be further configured as follows: determining the weight difference of the target area before and after the vehicle enters the target area according to the weight information corresponding to the target area, and determining the estimated weight of the vehicle according to the weight difference, including:

[0014] Determine, from the multiple images, a first image before the vehicle enters the target area, a first time corresponding to the first image, a second image after the vehicle enters the target area, and a second time corresponding to the second image;

[0015] determining, based on the first image and the second image, a change in weight of a person before and after the vehicle enters the target area;

[0016] Determining a weight difference between the target area at the first moment and the target area at the second moment according to the weight information corresponding to the target area;

[0017] The estimated vehicle weight is determined based on the change in the weight of the person and the load-bearing difference.

[0018] By adopting the above technical solution, the weight of the changed person is estimated according to the first image and the second image of the changed person, and the weight change of the changed person corresponding to the changed person before and after the vehicle enters the target area can be accurately determined. The load-bearing difference of the target area includes the vehicle weight and the weight change of the changed person corresponding to the changed person. The estimated weight of the vehicle can be obtained through the weight change of the person and the load-bearing difference, which improves the accuracy of determining the weight change of the changed person and the estimated weight of the vehicle.

[0019] In a preferred example, the present application may be further configured to: determine the weight change of the person before and after the vehicle enters the target area according to the first image and the second image, including:

[0020] determining, based on the first image and the second image, a changed person before and after the vehicle enters the target area;

[0021] Acquire historical data corresponding to the target area, the historical data including historical images of people entering and leaving the target area, and historical load-bearing information corresponding to the people entering and leaving the target area;

[0022] If the historical data corresponding to the target area includes the target historical data corresponding to the changed person, then determining the weight change of the person before and after the vehicle enters the target area according to the target historical data;

[0023] If the target historical data corresponding to the changed person does not exist in the historical data corresponding to the target area, the contour information of the changed person is determined based on the first image and the second image, and the weight change of the person before and after the vehicle enters the target area is determined based on the contour information of the changed person.

[0024] By adopting the above technical scheme, the target historical data of the changed personnel entering and exiting the target area can be determined based on the historical data, the historical images of the changed personnel entering and exiting the target area and the corresponding historical load-bearing information of the target area can be determined based on the target historical data, and the weight change of the changed personnel can be determined based on the target historical data, thereby improving the accuracy of determining the weight change of the personnel.

[0025] In a preferred example, the present application may be further configured to: extract features from the multiple images, and determine whether a vehicle has entered the target area based on the extracted features, including:

[0026] According to the edge features of the target area, each of the multiple images is divided into an area within the target area and an area outside the target area, and features are extracted from the areas within the target area corresponding to each of the multiple images;

[0027] If the preset vehicle features can be extracted from the target area of ​​any image, it is determined that a vehicle has entered the target area.

[0028] By adopting the above technical solution, each of the multiple images is divided into an area within the target area and an area outside the target area according to the edge features of the target area, and features are extracted for the areas within the target areas corresponding to each of the multiple images. Based on the extracted features, it is determined whether a vehicle enters the elevator, thereby eliminating the influence of vehicles outside the target area on the determination result, and improving the accuracy of determining whether a vehicle enters the target area.

[0029] In a preferred example, the present application may be further configured to: determine whether the target load-bearing information or the estimated vehicle weight exceeds a preset weight threshold, including:

[0030] Filter out the image with the largest vehicle area from the multiple images;

[0031] When the vehicle in the image with the largest vehicle area is incomplete, repairing the missing area of ​​the vehicle to obtain a complete vehicle;

[0032] Determine a plurality of initial regions from the complete vehicle according to the extracted features, obtain temperatures corresponding to the plurality of initial regions, and determine an initial region with the highest temperature from the plurality of initial regions as a first region;

[0033] Taking the area other than the first area in the complete vehicle as the second area, and obtaining the temperature difference between the first area and the second area;

[0034] Determining whether the temperature difference exceeds a preset temperature threshold;

[0035] If the temperature difference exceeds the preset temperature threshold, it is determined whether the target load-bearing information or the estimated vehicle weight exceeds a preset weight threshold.

[0036] By adopting the above technical solution, when the vehicle in the image with the largest vehicle area is incomplete, the missing area of ​​the vehicle is repaired, which can improve the integrity of the vehicle image, determine the temperature difference between the first area and the second area of ​​the complete vehicle, and compare the temperature difference with the preset temperature threshold. It is possible to determine whether the vehicle is an electric vehicle based on the temperature difference, thereby improving the accuracy of determining whether an electric vehicle has entered the target area.

[0037] In a preferred example, the present application may be further configured as follows: before determining whether the extracted features include the target features, the method further includes:

[0038] determining a vehicle profile based on the plurality of images;

[0039] Determine the vehicle owner's profile according to the vehicle profile, and perform face recognition on the vehicle owner based on the vehicle owner's profile to obtain the vehicle owner's identity information;

[0040] Determining the vehicle characteristic information corresponding to the vehicle owner identity information based on a preset corresponding relationship, where the preset corresponding relationship is a corresponding relationship between the vehicle owner identity information and compliant vehicle characteristic information;

[0041] matching the features extracted from the plurality of images with the vehicle feature information;

[0042] If the matching fails, it is determined whether the extracted features include the target features.

[0043] By adopting the above technical solution, before determining whether the extracted features contain the target features, the vehicle outline and the owner's identity information are determined, and the compliant vehicle feature information corresponding to the owner's identity information can be determined according to the preset correspondence. If the extracted features can be successfully matched with the compliant vehicle feature information, it indicates that the vehicle entering the target area is compliant, which can simplify the detection process and improve the efficiency of vehicle detection.

[0044] In a preferred example, the present application may be further configured as follows: determining the target load-bearing information corresponding to the position information according to the load-bearing information corresponding to the target area, including:

[0045] Determine the sub-load-bearing information corresponding to each of the plurality of sub-areas in the target area;

[0046] Determine a target sub-area corresponding to the location information;

[0047] The target load-bearing information corresponding to the target sub-region is determined from the sub-load-bearing information corresponding to each of the plurality of sub-regions.

[0048] By adopting the above technical solution, the target area is divided into multiple sub-areas, and the load-bearing information corresponding to each sub-area can be determined, the target sub-area corresponding to the vehicle's position information can be determined, and then the target load-bearing information corresponding to the target sub-area can be determined. The target load-bearing information is the estimated weight of the vehicle entering the target area, which improves the accuracy of determining the estimated weight of the vehicle.

[0049] In the second aspect, the present application provides an intelligent monitoring device based on the Internet of Things, which adopts the following technical solutions:

[0050] An intelligent monitoring device based on the Internet of Things, comprising:

[0051] An acquisition module, used for acquiring a plurality of images of a target area and load-bearing information of the target area in a time series;

[0052] An extraction module, configured to extract features from the plurality of images, determine whether a vehicle has entered the target area based on the extracted features, and if it is determined that a vehicle has entered the target area, determine whether the extracted features include target features;

[0053] A first determination module is used to determine the position information of the target feature in the target area if the extracted features include the target feature, and determine the target load-bearing information corresponding to the position information according to the load-bearing information corresponding to the target area;

[0054] A second determination module is used to determine the weight difference of the target area before and after the vehicle enters the target area according to the weight information corresponding to the target area if the extracted features do not include the target feature, and determine the estimated weight of the vehicle according to the weight difference;

[0055] The control module is used to determine whether the target load-bearing information or the estimated weight of the vehicle is greater than a preset weight threshold. If the target load-bearing information or the estimated weight of the vehicle is greater than the preset weight threshold, the alarm device is controlled to issue an alarm message.

[0056] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0057] one or more processors;

[0058] Memory;

[0059] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to: execute the intelligent monitoring method based on the Internet of Things as described in any one of the first aspects.

[0060] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0061] A computer-readable storage medium stores a computer program, which, when executed in a computer, causes the computer to execute the intelligent monitoring method based on the Internet of Things as described in any one of the first aspects.

[0062] In summary, this application includes the following beneficial technical effects:

[0063] The present application performs feature extraction on multiple images, and can accurately determine whether there is a vehicle entering the target area; if so, further determine whether the extracted features contain the target features; if contained, determine the position information of the target features in the target area, and based on the position information, accurately determine the target load-bearing information corresponding to the position information from the load-bearing information with a time series corresponding to the target area, and the target load-bearing information can represent the weight of the vehicle entering the target area; if not contained, determine the estimated weight of the vehicle based on the load-bearing difference of the target area before and after the vehicle enters the target area; compare the obtained target load-bearing information or the estimated weight of the vehicle with a preset weight threshold, and determine whether the vehicle entering the target area is an electric vehicle, thereby improving the recognition accuracy of electric vehicles, and controlling the alarm device to send an alarm message for the illegal behavior of pushing the electric vehicle into the target area, so as to prompt the owner to push the electric vehicle out of the target area, thereby improving the safety of the target area. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a flow chart of an intelligent monitoring method based on the Internet of Things provided in an embodiment of the present application;

[0065] Figure 2 is a schematic diagram of dividing a target area into sub-areas provided in an embodiment of the present application;

[0066] Figure 3 It is a structural diagram of an intelligent monitoring device based on the Internet of Things provided in an embodiment of the present application;

[0067] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0068] The following is combined with Figure 1-4 This application is described in further detail.

[0069] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make modifications to the present embodiment without any creative contribution as needed, but such modifications are protected by the patent law as long as they are within the scope of the claims of the present application.

[0070] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0071] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0072] The present application embodiment provides an intelligent monitoring method based on the Internet of Things, such as Figure 1 As shown, the method provided in the embodiment of the present application can be executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes steps S101 to S105, wherein:

[0073] S101, acquiring multiple images of a target area and load-bearing information of the target area in a time series.

[0074] In this embodiment, the target area can be an elevator, a public lobby entrance, a medical area entrance, etc. A camera device can be set above the target area, and the camera device acquires an image in the target area once every preset acquisition time, thereby obtaining multiple images of the target area and the image acquisition time corresponding to each of the multiple images. Among them, the preset acquisition time can be set according to actual needs. Optionally, the preset acquisition time is set to 1s. A weighing sensor can be set at the bottom of the target area to monitor the load-bearing information of the target area in real time, so as to obtain the load-bearing information with a time series corresponding to the target area.

[0075] S102, extracting features from the multiple images, judging whether a vehicle has entered a target area based on the extracted features, and if it is judged that a vehicle has entered the target area, determining whether the extracted features include target features.

[0076] In this embodiment, the extracted features may include license plates, wheels, lights, handlebars, and pedals. When a preset number of features can be identified in any image, it is determined that the vehicle has entered the target area. The preset number can be set according to actual needs. Optionally, the preset number is set to 2. The target feature can be used to indicate the position of the vehicle in the target area. The vehicle contacts the target area through the wheels, so the target feature can be a wheel.

[0077] S103: If the extracted features include target features, determine the position information of the target features in the target area, and determine the target load-bearing information corresponding to the position information according to the load-bearing information corresponding to the target area.

[0078] When the extracted features include wheels, an image including wheels is selected from multiple images as a target image, and the target image is preprocessed, including noise removal, image smoothing, contrast enhancement and other operations to improve the quality and readability of the target image; edge detection algorithms such as Sobel and Canny are used to detect the edge of the wheel; based on edge detection, morphological operations such as dilation and erosion are used to fill the internal blank area of ​​the wheel and further enhance the contour information of the wheel; contour tracking or regional growing algorithms are used to find the outer contour of the wheel, and the position of the lowest point of the wheel contour is determined according to the outer contour of the wheel, that is, the position information of the target feature in the target area.

[0079] The target area includes multiple target sub-areas, and each sub-area can be provided with a weighing sensor for detecting the load-bearing information of the sub-area. The load-bearing information with a time series corresponding to each sub-area constitutes the load-bearing information with a time series of the target area. According to the position information of the target feature in the target area, the target sub-area corresponding to the position information can be determined, and the load-bearing information with a time series corresponding to the target sub-area can be obtained, from which the target load-bearing information corresponding to the image acquisition moment of the target image can be determined. Among them, the identified wheel can be used as the target feature, and the target sub-load-bearing information corresponding to the wheel in the target sub-area can be determined according to the position information of the wheel in the target area.

[0080] S104: If the extracted features do not include the target features, determine the weight difference of the target area before and after the vehicle enters the target area according to the weight information corresponding to the target area, and determine the estimated weight of the vehicle according to the weight difference.

[0081] Before and after the vehicle enters the target area, there is a change in the personnel in the target area. The load-bearing difference of the target area includes the vehicle weight and the weight change of the personnel corresponding to the changed personnel. The contour information of each changed person can be determined through the image, and the weight of each changed person can be estimated based on the contour information. Then, the weight change of the personnel in the target area corresponding to the changed personnel before and after the vehicle enters the target area can be determined. The load-bearing difference of the target area is subtracted from the weight change of the personnel to obtain the estimated weight of the vehicle.

[0082] S105. Determine whether the target load-bearing information or the estimated vehicle weight is greater than a preset weight threshold. If the target load-bearing information or the estimated vehicle weight is greater than the preset weight threshold, control the alarm device to issue an alarm message.

[0083] In this embodiment, the preset vehicle weight threshold can be determined by obtaining the weights of several bicycles, children's bicycles, and electric vehicles with the highest sales volume on the market. Specifically, the average weights of several bicycles, children's bicycles, and electric vehicles with the highest sales volume on the market can be calculated respectively to obtain the first average weight of several bicycles, the second average weight of several children's bicycles, and the third average weight of several electric vehicles, and the larger value of the first average weight and the second average weight is determined, and the average value of the larger value and the third average weight is calculated as the preset vehicle weight threshold.

[0084] The target load-bearing information and the estimated vehicle weight are the estimated vehicle weights under the two detection methods. Since the weight of electric vehicles is greater than that of other vehicles (bicycles, strollers, etc.), if the weight of the vehicle entering the target area is lower than the preset vehicle weight threshold, it is determined that the vehicle entering the target area is a bicycle or a stroller. Bicycles and strollers are legally allowed to enter the target area. When the weight of the vehicle entering the elevator exceeds the preset vehicle weight threshold, the vehicle is determined to be an electric vehicle, and the alarm device in the target area is controlled to send out an alarm message.

[0085] The embodiment of the present application can accurately determine whether there is a vehicle entering the target area by extracting features from multiple images; if so, further determine whether the extracted features include the target features; if included, determine the position information of the target features in the target area, and based on the position information, accurately determine the target load-bearing information corresponding to the position information from the load-bearing information with a time series corresponding to the target area, and the target load-bearing information can represent the weight of the vehicle entering the target area; if not included, determine the estimated weight of the vehicle based on the load-bearing difference in the target area before and after the vehicle enters the target area; compare the obtained target load-bearing information or the estimated weight of the vehicle with a preset weight threshold, and determine whether the vehicle entering the target area is an electric vehicle, thereby improving the recognition accuracy of electric vehicles, and controlling the alarm device to issue an alarm message for the illegal behavior of pushing the electric vehicle into the target area to prompt the owner to push the electric vehicle out of the target area, thereby improving the safety of the target area.

[0086] A possible implementation of the embodiment of the present application is to determine the weight difference of the target area before and after the vehicle enters the target area according to the weight-bearing information corresponding to the target area, and determine the estimated weight of the vehicle according to the weight-bearing difference, including:

[0087] Determine, from the plurality of images, a first image before the vehicle enters the target area, a first time corresponding to the first image, a second image after the vehicle enters the target area, and a second time corresponding to the second image;

[0088] Determine, based on the first image and the second image, a change in weight of the person before and after the vehicle enters the target area;

[0089] Determine the weight difference between the target area at the first moment and the target area at the second moment according to the weight information corresponding to the target area;

[0090] Determine the estimated vehicle weight based on the change in occupant weight and the load-bearing difference.

[0091] In this embodiment, the vehicle's motion phases are divided into three, namely: the vehicle has not entered the target area, the vehicle is entering the target area, and the vehicle has completely entered the target area. By performing edge recognition on the image, the positional relationship between the vehicle's outline and the target area outline can be divided, and the vehicle's motion phase can be determined based on the positional relationship. Multiple images of the vehicle not entering the target area and multiple images of the vehicle completely entering the target area are acquired, and the image with the latest image acquisition time is determined from the multiple images of the vehicle not entering the target area as the first image, and the image with the earliest image acquisition time is determined from the multiple images of the vehicle completely entering the target area as the second image, and the image acquisition time corresponding to the first image is used as the first moment, and the image acquisition time corresponding to the second image is used as the second moment.

[0092] The first image indicates that the vehicle has not entered the target area, and the second image indicates that the vehicle has completely entered the target area. By comparing the people in the first image and the second image through image recognition, the changed people in the target area from the first moment to the second moment can be determined. Exemplarily, the people in the target area in the first image are A, B, C, and D, and the people in the target area in the second image are A, C, and E. Then the changed people in the target area from the first moment to the second moment are B, D, and E, among which the change information corresponding to B and D is leaving the target area, and the change information corresponding to E is entering the target area.

[0093] Based on the first image and the second image, the contour of each changed person can be recognized. For any of the changed persons, key points can be identified and measured based on the contour information of the person to obtain the corresponding human morphological information of the person. The human morphological information includes information such as the height, posture, and body shape of the person. A virtual model of the person is constructed based on the human morphological information, and the obtained virtual model is input into the preset weight prediction model to obtain the estimated weight of the person.

[0094] Among them, the preset weight prediction model is pre-set, and the construction process of the preset weight prediction model can be: collecting a large number of personnel images and weight data corresponding to the personnel images, the personnel images include human bodies in different postures; posture-related features can be extracted from each human body image through a deep learning model, the features include bone structure, reminders, muscle distribution, etc., and the deep learning model can use a convolutional neural network or a generative adversarial network; a regression model is trained by extracting posture features and corresponding weight data, and the regression model can learn how to convert posture features corresponding to human morphological information into weight values.

[0095] According to the estimated weight of each changed person, the weight change of the person before and after the vehicle enters the target area can be determined. The first estimated weight sum of the persons added in the second image compared with the first image and the second estimated weight sum of the persons reduced in the second image compared with the first image are calculated, and the difference between the first estimated weight sum and the second estimated weight sum is taken as the weight change of the person before and after the vehicle enters the target area, that is, the weight change of the person corresponding to the target area at the first time and the second time.

[0096] Calculate the weight difference between the weight information of the target area at the second moment and the first moment. Since a vehicle enters the target area between the first moment and the second moment, the weight difference includes the change in personnel weight and the weight of the vehicle. Calculate the difference between the weight difference and the change in personnel weight to get the estimated weight of the vehicle.

[0097] The embodiment of the present application estimates the weight of the changed person through the first image and the second image where the changed person is located, and can accurately determine the weight change corresponding to the changed person before and after the vehicle enters the target area. The load-bearing difference of the target area includes the vehicle weight and the weight change corresponding to the changed person. The estimated weight of the vehicle can be obtained through the weight change of the person and the load-bearing difference, which improves the accuracy of determining the weight change corresponding to the changed person and the estimated weight of the vehicle.

[0098] A possible implementation of the embodiment of the present application is to determine the weight change of a person before and after the vehicle enters the target area according to the first image and the second image, including:

[0099] Determining, based on the first image and the second image, the changed persons before and after the vehicle enters the target area;

[0100] Obtaining historical data corresponding to the target area, the historical data including historical images of people entering and leaving the target area, and historical load-bearing information corresponding to people entering and leaving the target area;

[0101] If the historical data corresponding to the target area includes target historical data corresponding to the changed personnel, the weight change of the personnel before and after the vehicle enters the target area is determined according to the target historical data;

[0102] If there is no target historical data corresponding to the changed person in the historical data corresponding to the target area, the contour information of the changed person is determined based on the first image and the second image, and the weight change of the person before and after the vehicle enters the target area is determined based on the contour information of the changed person.

[0103] In this embodiment, the historical data of the target area is stored in the historical database, and the historical data includes the historical images of the target area and the historical load-bearing information corresponding to the target area. By performing contour recognition on the people in the historical images, the entry and exit of the people in the target area can be determined, and the entry and exit of the people includes entering and exiting at the same time as others or entering and exiting alone. When a person enters and exits the target area alone through image recognition, the corresponding load-bearing change of the target area at the time when the person enters and exits the target area can be obtained, and the load-bearing change is used as the historical weight of the person. The face recognition of the person is performed on the image to determine the identity of the person, and the identity of the person and the corresponding historical weight are stored in the historical database.

[0104] According to the first image and the second image, the changed personnel before and after the vehicle enters the target area can be determined, and the identity of each changed person can be determined by performing face recognition on each changed person based on the image. According to the identity of each changed person, whether there is target historical data corresponding to the identity is found from the historical database, and the target historical data includes the identity of the person and the corresponding historical weight. From the changed personnel, the first target person whose corresponding target historical data can be determined from the historical database is determined, and the historical weight in the target historical data corresponding to the first target person is used as the estimated weight of the target person. For the second target person whose corresponding target historical data cannot be determined from the historical database among the changed personnel, the contour information of the second target person can be identified through the first image and the second image, and the estimated weight of the second target person can be obtained according to the contour information and the preset weight prediction model. According to the estimated weight of each changed person, the weight change of the person before and after the vehicle enters the target area can be determined.

[0105] The embodiment of the present application can determine the target historical data of the changed personnel entering and exiting the target area based on historical data, can determine the historical images of the changed personnel entering and exiting the target area and the corresponding historical load-bearing information of the target area based on the target historical data, and can determine the personnel weight changes corresponding to the changed personnel based on the target historical data, thereby improving the accuracy of determining the personnel weight changes.

[0106] A possible implementation of the embodiment of the present application is to extract features from multiple images and determine whether a vehicle has entered a target area based on the extracted features, including:

[0107] According to the edge features of the target area, each of the multiple images is divided into an area within the target area and an area outside the target area, and features are extracted from the areas within the target area corresponding to each of the multiple images;

[0108] If the preset vehicle features can be extracted from the target area of ​​any image, it is determined that a vehicle has entered the target area.

[0109] In this embodiment, the target area can be an elevator, a public lobby entrance and exit, or a medical area entrance and exit. When the target area is an elevator, the edge feature of the target area is the elevator door frame. When the target area is a public lobby entrance and exit, the edge feature of the target area is the public lobby door frame. When the target area is a medical area entrance and exit, the edge feature of the target area is the medical area entrance and exit door frame.

[0110] Specifically, the target area can be processed by edge detection algorithms, such as Sobel, Canny, Prewitt, etc. The edge detection algorithm can detect the edge features of the target area in the image, and the image can be divided into the target inner area and the target outer area according to the detected edge features. For example, assuming that the target area is an elevator, when the elevator door is opened, the image captured by the camera in the elevator includes both the area inside the elevator and the area outside the elevator. If it is to be detected whether there is a vehicle in the elevator, it is necessary to eliminate the interference of the vehicles parked outside the elevator.

[0111] The embodiment of the present application divides each of the multiple images into an area within the target area and an area outside the target area according to the edge features of the target area, and extracts features from the areas within the target areas corresponding to each of the multiple images. It determines whether a vehicle enters the elevator based on the extracted features, thereby eliminating the influence of vehicles outside the target area on the determination result, and improving the accuracy of determining whether a vehicle enters the target area.

[0112] A possible implementation of the embodiment of the present application is to determine whether the target load-bearing information or the estimated weight of the vehicle exceeds a preset weight threshold, including:

[0113] Filter out the image with the largest vehicle area from multiple images;

[0114] When the vehicle in the image with the largest vehicle area is incomplete, the missing area of ​​the vehicle is repaired to obtain a complete vehicle;

[0115] Determine a plurality of initial regions from the complete vehicle according to the extracted features, obtain temperatures corresponding to the plurality of initial regions, and determine the initial region with the highest temperature from the plurality of initial regions as the first region;

[0116] Taking the area other than the first area in the complete vehicle as the second area, and obtaining the temperature difference between the first area and the second area;

[0117] Determine whether the temperature difference exceeds a preset temperature threshold;

[0118] If the temperature difference exceeds a preset temperature threshold, it is determined whether the target load-bearing information or the estimated vehicle weight exceeds a preset weight threshold.

[0119] In this embodiment, multiple images can be preprocessed to enhance image quality and reduce noise. The preprocessing steps include contrast enhancement, filtering, denoising, etc. Then, a target detection algorithm is used to mark and divide the vehicle in each image. The target detection algorithm will output the bounding box of the detected vehicle. Optionally, the target detection algorithm includes YOLO, SSD, Faster R-CNN, etc.; the number of pixels in each bounding box is calculated through an image processing library (such as OpenCV) to estimate the vehicle area through the number of pixels; from the number of pixels corresponding to each of the multiple images, an image with the largest number of pixels is selected to obtain the image with the largest vehicle area.

[0120] For the image with the largest vehicle area, the vehicle shape is determined based on the divided vehicle boundary box, and the determined vehicle shape is compared with the preset vehicles in the preset vehicle library, and then the preset vehicle with the highest similarity to the vehicle shape is determined from the preset vehicle library. The shape of the preset vehicle can be used to determine whether the vehicle in the image is complete. The preset vehicle library stores a variety of vehicle images on the market whose sales exceed the preset sales threshold, where the preset sales threshold can be set according to actual needs. If the vehicle is incomplete, the missing part of the vehicle is predicted based on the preset vehicle with the highest similarity to the vehicle through a morphological processing method. Based on the predicted missing area, a filling algorithm or a deep learning model is used to repair the missing area to obtain a complete vehicle. Optionally, texture synthesis, interpolation, deep learning and other algorithms can be used to fill the missing area.

[0121] When an electric vehicle is running, the battery discharges and generates heat, causing the battery area to be hotter than other areas of the electric vehicle. A thermal imager can capture the infrared radiation emitted by the vehicle and convert it into a visible image (thermal imaging image). Through the visible image, the temperature distribution of the entire vehicle can be understood. When the temperature of a part of the vehicle is too high, it can be determined that the vehicle entering the target area is an electric vehicle.

[0122] In actual situations, there are two situations for setting the position of the battery in an electric vehicle. One is to set it under the pedal (between the two wheels), and the other is to set it under the seat. By identifying the image corresponding to the complete vehicle, the position of the pedal and the seat can be determined, and an area is divided under the pedal and under the seat respectively to obtain two initial areas. The size and shape of the initial area can be set according to actual experience. The initial area represents the possible location and size of the battery. According to the thermal imaging image obtained by the thermal imager, the average temperature of each initial area can be determined respectively, and the initial area corresponding to the higher of the two average temperatures is taken as the first area, which is the possible location of the battery, and the area of ​​the complete vehicle except the first area is taken as the second area.

[0123] The average temperature of the first area is taken as the first temperature, and the average temperature of the second area is taken as the second temperature. The difference between the first temperature and the second temperature is calculated to obtain the temperature difference between the first area and the second area. The preset temperature threshold can be set according to actual experience. The preset temperature threshold represents the temperature difference between the battery temperature and other areas of the electric vehicle. If the temperature difference between the first area and the second area exceeds the preset temperature threshold, it means that the vehicle in the image is an electric vehicle. According to the comparison of the target load-bearing information or the estimated weight of the vehicle with the preset weight threshold, a secondary detection can be completed to improve the accuracy of judging whether the vehicle is an electric vehicle.

[0124] In an embodiment of the present application, when the vehicle in the image with the largest vehicle area is incomplete, the missing area of ​​the vehicle is repaired, which can improve the completeness of the vehicle image, determine the temperature difference between the first area and the second area of ​​the complete vehicle, and compare the temperature difference with a preset temperature threshold. It is possible to determine whether the vehicle is an electric vehicle based on the temperature difference, thereby improving the accuracy of determining whether an electric vehicle has entered the target area.

[0125] In a possible implementation manner of the embodiment of the present application, before determining whether the extracted features include the target features, the method further includes:

[0126] determining a vehicle contour based on the plurality of images;

[0127] Determine the outline of the owner according to the outline of the vehicle, perform face recognition on the owner based on the outline of the owner, and obtain the identity information of the owner;

[0128] Determine the vehicle characteristic information corresponding to the vehicle owner's identity information based on a preset corresponding relationship, where the preset corresponding relationship is the corresponding relationship between the vehicle owner's identity information and the compliant vehicle characteristic information;

[0129] Matching features extracted from multiple images with vehicle feature information;

[0130] If the matching fails, it is performed to determine whether the extracted features include the target features.

[0131] In this embodiment, a plurality of correspondences are stored in the preset vehicle database, and the correspondences are the correspondences between the vehicle owner's identity information and the compliant vehicle feature information. For some non-electric vehicles, such as bicycles and children's cars, the vehicle owner's identity information and vehicle feature information can be stored in the preset vehicle database in advance, indicating that the vehicles in the preset vehicle database are compliant vehicles and can enter and exit the target area.

[0132] Before determining whether the extracted features include the target features, the image in which the handlebars are identified can be determined from multiple images, and the vehicle outline including the handlebars can be determined through an edge detection algorithm. The owner pushes the vehicle into the target area by grasping the handlebars. The outline of the owner connected to the handlebars can be determined through the position of the handlebars in the vehicle outline. The owner's face can be recognized based on the owner's outline to obtain the owner's identity information.

[0133] If the vehicle feature information corresponding to the vehicle owner's identity information can be retrieved from the preset vehicle database based on the vehicle owner's identity information, the features extracted from the multiple images corresponding to the target area will be matched with the vehicle feature information. If the match is successful, it means that the vehicle entering the target area is a compliant vehicle and no subsequent detection steps are required. If the vehicle feature information corresponding to the vehicle owner's identity information cannot be retrieved from the preset vehicle database based on the vehicle owner's identity information, it means that the preset corresponding relationship corresponding to the vehicle owner's identity information is not stored in the preset vehicle database, and it cannot be determined whether the vehicle entering the target area is compliant, and re-detection is required to determine whether the vehicle is an electric vehicle.

[0134] In an embodiment of the present application, before determining whether the extracted features include target features, the vehicle outline and the owner's identity information are determined, and the compliant vehicle feature information corresponding to the owner's identity information can be determined based on a preset correspondence. If the extracted features can be successfully matched with the compliant vehicle feature information, it indicates that the vehicle entering the target area is compliant, which can simplify the detection process and improve the efficiency of vehicle detection.

[0135] A possible implementation of the embodiment of the present application is to determine the target load-bearing information corresponding to the position information according to the load-bearing information corresponding to the target area, including:

[0136] Determine the sub-load bearing information corresponding to each of the multiple sub-areas in the target area;

[0137] Determine a target sub-region corresponding to the position information;

[0138] The target load-bearing information corresponding to the target sub-region is determined from the sub-load-bearing information corresponding to each of the plurality of sub-regions.

[0139] In this embodiment, see Figure 2, the target area can be divided into multiple sub-areas, and a weighing sensor is set in each sub-area to detect the sub-bearing information of the corresponding sub-area. Among them, the size of the sub-area is larger than the contact area between the wheel and the target area. The contact area between the wheel and the target area can be determined according to actual experience. Optionally, the size of the sub-area can be set to 15cm×15cm. According to the position of the wheel in the image, the target sub-area corresponding to the contact position between the wheel and the target area can be determined. When the contact position between the wheel and the target area is completely located in a sub-area, the sub-area is the target sub-area. When the contact position between the wheel and the target area is located on the boundary line of multiple sub-areas, the wheel is in contact with multiple sub-areas in the target area at the same time, and these multiple sub-areas are taken as target sub-areas. When the target sub-area corresponds to one sub-area, the bearing information of the sub-area is taken as the target bearing information. When the target sub-area corresponds to multiple sub-areas, the sum of the bearing information of multiple sub-areas is taken as the target bearing information.

[0140] The embodiment of the present application divides the target area into multiple sub-areas, and is able to determine the load-bearing information corresponding to each sub-area, determine the target sub-area corresponding to the vehicle's position information, and then determine the target load-bearing information corresponding to the target sub-area. The target load-bearing information is the estimated weight of the vehicle entering the target area, which improves the accuracy of determining the estimated weight of the vehicle.

[0141] In one achievable manner, when the target area is an elevator, controlling the alarm device to issue an alarm message includes:

[0142] Control the elevator door to remain open and control the alarm device in the elevator to issue a voice reminder until the vehicle is detected to be pushed out of the elevator;

[0143] Monitor the movement trajectory of the vehicle after it is pushed out of the elevator to determine whether the parking point of the vehicle meets the preset parking range;

[0144] If the vehicle is not pushed out of the elevator within the preset time, or the parking spot of the vehicle does not conform to the preset parking range, an alarm signal is sent to the property terminal.

[0145] In this embodiment, the movement trajectory of the vehicle after being pushed out of the elevator can be monitored by cameras arranged at different positions outside the elevator door, and the preset parking range and preset duration can be manually set according to actual needs.

[0146] In another achievable manner, when the target area is an elevator, the method further includes:

[0147] When the alarm device sends out an alarm message, the corresponding owner in the elevator is identified by face recognition, the owner's identity is confirmed, and the number of violations is recorded for the owner;

[0148] When the number of violations of the car owner reaches the preset number threshold, the car owner is controlled, and the control includes stopping the car owner's elevator card usage rights. Among them, the preset number threshold can be set according to actual needs, and optionally, the preset number threshold can be set to 3.

[0149] The above embodiment introduces an intelligent monitoring method based on the Internet of Things from the perspective of method flow, and the following embodiment introduces an intelligent monitoring device based on the Internet of Things from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiment.

[0150] The present application embodiment provides an intelligent monitoring device based on the Internet of Things, such as Figure 3 As shown, the device may include:

[0151] An acquisition module 301 is used to acquire multiple images of a target area and load-bearing information of the target area in a time series;

[0152] An extraction module 302 is used to extract features from multiple images, determine whether a vehicle has entered a target area based on the extracted features, and if it is determined that a vehicle has entered the target area, determine whether the extracted features include target features;

[0153] The first determination module 303 is used to determine the position information of the target feature in the target area if the extracted features include the target feature, and determine the target load-bearing information corresponding to the position information according to the load-bearing information corresponding to the target area;

[0154] The second determination module 304 is used to determine the weight difference of the target area before and after the vehicle enters the target area according to the weight information corresponding to the target area if the extracted features do not include the target feature, and determine the estimated weight of the vehicle according to the weight difference;

[0155] The control module 305 is used to determine whether the target load-bearing information or the estimated vehicle weight is greater than a preset weight threshold. If the target load-bearing information or the estimated vehicle weight is greater than the preset weight threshold, the alarm device is controlled to issue an alarm message.

[0156] In a preferred example, the present application may be further configured as follows: when the second determination module 304 determines the weight difference of the target area before and after the vehicle enters the target area according to the weight information corresponding to the target area, and determines the estimated weight of the vehicle according to the weight difference, it is specifically used to:

[0157] Determine, from the plurality of images, a first image before the vehicle enters the target area, a first time corresponding to the first image, a second image after the vehicle enters the target area, and a second time corresponding to the second image;

[0158] Determine, based on the first image and the second image, a change in weight of the person before and after the vehicle enters the target area;

[0159] Determine the weight difference between the target area at the first moment and the target area at the second moment according to the weight information corresponding to the target area;

[0160] Determine the estimated vehicle weight based on the change in occupant weight and the load-bearing difference.

[0161] In a preferred example, the present application may be further configured as follows: when the second determination module 304 determines the weight change of the person before and after the vehicle enters the target area according to the first image and the second image, it is specifically used to:

[0162] Determining, based on the first image and the second image, the changed persons before and after the vehicle enters the target area;

[0163] Obtaining historical data corresponding to the target area, the historical data including historical images of people entering and leaving the target area, and historical load-bearing information corresponding to people entering and leaving the target area;

[0164] If the historical data corresponding to the target area includes target historical data corresponding to the changed personnel, the weight change of the personnel before and after the vehicle enters the target area is determined according to the target historical data;

[0165] If there is no target historical data corresponding to the changed person in the historical data corresponding to the target area, the contour information of the changed person is determined based on the first image and the second image, and the weight change of the person before and after the vehicle enters the target area is determined based on the contour information of the changed person.

[0166] In a preferred example, the present application can be further configured as follows: when the extraction module 302 performs feature extraction on multiple images and determines whether a vehicle enters the target area according to the extracted features, it is specifically used to:

[0167] According to the edge features of the target area, each of the multiple images is divided into an area within the target area and an area outside the target area, and features are extracted from the areas within the target area corresponding to each of the multiple images;

[0168] If the preset vehicle features can be extracted from the target area of ​​any image, it is determined that a vehicle has entered the target area.

[0169] In a preferred example, the present application may be further configured as follows: when the control module 305 determines whether the target load-bearing information or the estimated vehicle weight exceeds a preset weight threshold, it is specifically configured to:

[0170] Filter out the image with the largest vehicle area from multiple images;

[0171] When the vehicle in the image with the largest vehicle area is incomplete, the missing area of ​​the vehicle is repaired to obtain a complete vehicle;

[0172] Determine a plurality of initial regions from the complete vehicle according to the extracted features, obtain temperatures corresponding to the plurality of initial regions, and determine the initial region with the highest temperature from the plurality of initial regions as the first region;

[0173] Taking the area other than the first area in the complete vehicle as the second area, and obtaining the temperature difference between the first area and the second area;

[0174] Determine whether the temperature difference exceeds a preset temperature threshold;

[0175] If the temperature difference exceeds a preset temperature threshold, it is determined whether the target load-bearing information or the estimated vehicle weight exceeds a preset weight threshold.

[0176] In a preferred example, the present application may be further configured as follows: further comprising a matching module, specifically used for:

[0177] determining a vehicle contour based on the plurality of images;

[0178] Determine the outline of the owner according to the outline of the vehicle, perform face recognition on the owner based on the outline of the owner, and obtain the identity information of the owner;

[0179] Determine the vehicle characteristic information corresponding to the vehicle owner's identity information based on a preset corresponding relationship, where the preset corresponding relationship is the corresponding relationship between the vehicle owner's identity information and the compliant vehicle characteristic information;

[0180] Matching features extracted from multiple images with vehicle feature information;

[0181] If the matching fails, it is performed to determine whether the extracted features include the target features.

[0182] In a preferred example, the present application may be further configured as follows: when the first determination module 303 determines the target load-bearing information corresponding to the position information according to the load-bearing information corresponding to the target area, it is specifically used to:

[0183] Determine the sub-load bearing information corresponding to each of the multiple sub-areas in the target area;

[0184] Determine the target sub-region corresponding to the position information;

[0185] The target load-bearing information corresponding to the target sub-region is determined from the sub-load-bearing information corresponding to each of the plurality of sub-regions.

[0186] An intelligent monitoring device based on the Internet of Things provided in an embodiment of the present application is applicable to the above method embodiment and will not be described in detail here.

[0187] An electronic device is provided in an embodiment of the present application, such as Figure 4 As shown, Figure 4The electronic device 400 shown includes: a processor 401 and a memory 403. The processor 401 and the memory 403 are connected, such as through a bus 402. Optionally, the electronic device 400 may also include a transceiver 404. It should be noted that in actual applications, the transceiver 404 is not limited to one, and the structure of the electronic device 400 does not constitute a limitation on the embodiments of the present application.

[0188] Processor 401 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 401 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0189] The bus 402 may include a path to transmit information between the above components. The bus 402 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 402 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0190] The memory 403 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0191] The memory 403 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 401. The processor 401 is used to execute the application code stored in the memory 403 to implement the contents shown in the above-mentioned embodiment of the intelligent monitoring method based on the Internet of Things.

[0192] Figure 4 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0193] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0194] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0195] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An intelligent monitoring method based on the Internet of Things, characterized in that: include: Acquire multiple images of a target area and load-bearing information of the target area in a time series; Extracting features from the multiple images, judging whether a vehicle has entered the target area according to the extracted features, and if it is judged that a vehicle has entered the target area, determining whether the extracted features include target features; If the extracted features include the target feature, determining the position information of the target feature in the target area, and determining the target load-bearing information corresponding to the position information according to the load-bearing information corresponding to the target area; If the extracted features do not include the target features, determining the weight difference of the target area before and after the vehicle enters the target area according to the weight information corresponding to the target area, and determining the estimated weight of the vehicle according to the weight difference; Determining whether the target load-bearing information or the estimated weight of the vehicle is greater than a preset weight threshold, and if the target load-bearing information or the estimated weight of the vehicle is greater than the preset weight threshold, controlling the alarm device to issue an alarm message; Wherein, judging whether the target load-bearing information or the estimated vehicle weight exceeds a preset weight threshold includes: Filter out the image with the largest vehicle area from the multiple images; When the vehicle in the image with the largest vehicle area is incomplete, repairing the missing area of ​​the vehicle to obtain a complete vehicle; Determine a plurality of initial regions from the complete vehicle according to the extracted features, obtain temperatures corresponding to the plurality of initial regions, and determine an initial region with the highest temperature from the plurality of initial regions as a first region; Taking the area other than the first area in the complete vehicle as the second area, and obtaining the temperature difference between the first area and the second area; Determining whether the temperature difference exceeds a preset temperature threshold; If the temperature difference exceeds the preset temperature threshold, it is determined whether the target load-bearing information or the estimated vehicle weight exceeds a preset weight threshold.

2. The intelligent monitoring method based on the Internet of Things according to claim 1 is characterized in that: Determining the load-bearing difference of the target area before and after the vehicle enters the target area according to the load-bearing information corresponding to the target area, and determining the estimated weight of the vehicle according to the load-bearing difference, including: Determine, from the multiple images, a first image before the vehicle enters the target area, a first time corresponding to the first image, a second image after the vehicle enters the target area, and a second time corresponding to the second image; determining, based on the first image and the second image, a change in weight of a person before and after the vehicle enters the target area; Determining a weight difference between the target area at the first moment and the target area at the second moment according to the weight information corresponding to the target area; The estimated vehicle weight is determined based on the change in the weight of the person and the load-bearing difference.

3. The intelligent monitoring method based on the Internet of Things according to claim 2 is characterized in that: Determining, according to the first image and the second image, a change in weight of a person before and after the vehicle enters the target area, includes: determining, based on the first image and the second image, a changed person before and after the vehicle enters the target area; Acquire historical data corresponding to the target area, the historical data including historical images of people entering and leaving the target area, and historical load-bearing information corresponding to the people entering and leaving the target area; If the historical data corresponding to the target area includes the target historical data corresponding to the changed person, then determining the weight change of the person before and after the vehicle enters the target area according to the target historical data; If the target historical data corresponding to the changed person does not exist in the historical data corresponding to the target area, the contour information of the changed person is determined based on the first image and the second image, and the weight change of the person before and after the vehicle enters the target area is determined based on the contour information of the changed person.

4. The intelligent monitoring method based on the Internet of Things according to claim 1 is characterized in that: Extracting features from the multiple images and determining whether a vehicle has entered the target area according to the extracted features include: According to the edge features of the target area, each of the multiple images is divided into an area within the target area and an area outside the target area, and features are extracted from the areas within the target area corresponding to each of the multiple images; If the preset vehicle features can be extracted from the target area of ​​any image, it is determined that a vehicle has entered the target area.

5. The intelligent monitoring method based on the Internet of Things according to claim 1 is characterized in that: Before determining whether the extracted features include target features, the method further includes: determining a vehicle profile based on the plurality of images; Determine the vehicle owner's profile according to the vehicle profile, and perform face recognition on the vehicle owner based on the vehicle owner's profile to obtain the vehicle owner's identity information; Determining the vehicle characteristic information corresponding to the vehicle owner identity information based on a preset corresponding relationship, where the preset corresponding relationship is a corresponding relationship between the vehicle owner identity information and compliant vehicle characteristic information; matching the features extracted from the plurality of images with the vehicle feature information; If the matching fails, it is determined whether the extracted features include the target features.

6. The intelligent monitoring method based on the Internet of Things according to claim 1 is characterized in that: Determining target load-bearing information corresponding to the position information according to the load-bearing information corresponding to the target area includes: Determine the sub-load-bearing information corresponding to each of the plurality of sub-areas in the target area; Determine a target sub-area corresponding to the location information; The target load-bearing information corresponding to the target sub-region is determined from the sub-load-bearing information corresponding to each of the plurality of sub-regions.

7. An intelligent monitoring device based on the Internet of Things, characterized in that: include: An acquisition module, used for acquiring a plurality of images of a target area and load-bearing information of the target area in a time series; An extraction module, configured to extract features from the plurality of images, determine whether a vehicle has entered the target area based on the extracted features, and if it is determined that a vehicle has entered the target area, determine whether the extracted features include target features; A first determination module is used to determine the position information of the target feature in the target area if the extracted features include the target feature, and determine the target load-bearing information corresponding to the position information according to the load-bearing information corresponding to the target area; A second determination module is used to determine the weight difference of the target area before and after the vehicle enters the target area according to the weight information corresponding to the target area if the extracted features do not include the target feature, and determine the estimated weight of the vehicle according to the weight difference; A control module, used to determine whether the target load-bearing information or the estimated weight of the vehicle is greater than a preset weight threshold, and if the target load-bearing information or the estimated weight of the vehicle is greater than the preset weight threshold, control the alarm device to issue an alarm message; Wherein, when the control module is executing the judgment whether the target load-bearing information or the estimated vehicle weight exceeds the preset weight threshold, it is specifically used to: Filter out the image with the largest vehicle area from the multiple images; When the vehicle in the image with the largest vehicle area is incomplete, repairing the missing area of ​​the vehicle to obtain a complete vehicle; Determine a plurality of initial regions from the complete vehicle according to the extracted features, obtain temperatures corresponding to the plurality of initial regions, and determine an initial region with the highest temperature from the plurality of initial regions as a first region; Taking the area other than the first area in the complete vehicle as the second area, and obtaining the temperature difference between the first area and the second area; Determining whether the temperature difference exceeds a preset temperature threshold; If the temperature difference exceeds the preset temperature threshold, it is determined whether the target load-bearing information or the estimated vehicle weight exceeds a preset weight threshold.

8. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the intelligent monitoring method based on the Internet of Things as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the intelligent monitoring method based on the Internet of Things as described in any one of claims 1 to 6.

Images