Gas engine safety personnel behavior monitoring method, device and equipment and storage medium

Abstract

The invention discloses a gas engine safety personnel behavior monitoring method, device and equipment and a storage medium, and relates to the technical field of behavior monitoring, and the method comprises the steps: obtaining the identity recognition information of safety personnel, determining the identity information of the safety personnel according to the identity recognition information, and sending the determined identity information to a server; the method comprises the steps of obtaining identity information of a security person, determining action feature information of the security person according to the identity information, obtaining a first behavior feature of the security person according to the action feature information, determining image feature information of the security person according to the identity information, and obtaining a second behavior feature of the security person according to the image feature information, analyzing the first behavior characteristics and the second behavior characteristics based on a behavior monitoring model to obtain behavior characteristics of the safety personnel, outputting dangerous behavior alarm information when the behavior characteristics are preset behavior characteristics, and determining behaviors of the safety personnel by combining action characteristics and image characteristics. And the accuracy of behavior monitoring is improved.

Description

Technical Field

[0001] The present application relates to the field of behavior monitoring technology, and in particular to a method, device, equipment and storage medium for monitoring the behavior of gas engine safety personnel. Background Art

[0002] Gas engines involve dangerous factors such as high temperature, high pressure, and flammable gases during operation. If improper operation or behavioral errors occur during the operation of safety personnel, serious accidents such as explosions, fires, poisoning, etc. will occur, threatening life safety. In order to reduce the probability of accidents, the current method is to monitor the operating behavior of safety personnel to promptly discover and correct unsafe behaviors. The current behavior monitoring of safety personnel is usually based on visual methods to determine the behavioral operations of safety personnel. However, visual detection often has visual blind spots and environments with low light, which will seriously affect the accuracy of monitoring behavioral operations. Therefore, the current monitoring accuracy of safety personnel behavior monitoring is not high, which reduces the timeliness of discovering dangerous operating behaviors.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a method, device, equipment and storage medium for monitoring the behavior of gas engine safety personnel, aiming to solve the technical problem of low accuracy in monitoring the behavior of gas engine safety personnel in the prior art.

[0005] To achieve the above objectives, the present application proposes a method for monitoring the behavior of gas engine safety personnel, the method comprising:

[0006] Obtaining identity information of a security personnel, and determining the identity information of the security personnel according to the identity information;

[0007] Determine action feature information of the security personnel according to the identity information, and obtain a first behavior feature of the security personnel according to the action feature information;

[0008] Determine the image feature information of the security personnel according to the identity information, and obtain the second behavior feature of the security personnel according to the image feature information;

[0009] The first behavior feature and the second behavior feature are analyzed based on a behavior monitoring model to obtain the behavior feature of the security personnel, and when the behavior feature is a preset behavior feature, dangerous behavior alarm information is output.

[0010] In one embodiment, the step of determining the action feature information of the security personnel according to the identity information and obtaining the first behavior feature of the security personnel according to the action feature information includes:

[0011] Determine an identity tag according to the identity information, traverse the action feature list based on the identity tag, and obtain action feature information corresponding to the identity information;

[0012] Determine a sequence of action feature points according to the action feature information, and determine an action trajectory according to a time sequence corresponding to the sequence of action feature points;

[0013] Determining the maintenance time of the action trajectory according to the timestamps corresponding to the first and last action feature points of the action feature point sequence;

[0014] A first behavior feature of the security personnel is obtained based on the maintenance time and the action trajectory.

[0015] In one embodiment, the step of determining a sequence of action feature points according to the action feature information, and determining a motion trajectory according to a time sequence corresponding to the sequence of action feature points comprises:

[0016] Determine an action feature point sequence according to the action feature information, and analyze the action feature point sequence to obtain a timestamp and a spatial coordinate of each action feature point in the action feature point sequence;

[0017] Determining the time sequence of the action feature points according to the timestamps, and rearranging the action feature point sequence according to the time sequence to obtain a time-series action feature point sequence;

[0018] Determine a trajectory vector according to the spatial coordinates of two adjacent temporal action feature points in the temporal action feature point sequence;

[0019] The trajectory vector is transformed into an action trajectory according to the time sequence information of each time sequence action feature point.

[0020] In one embodiment, the step of determining the image feature information of the security personnel according to the identity information and obtaining the second behavior feature of the security personnel according to the image feature information includes:

[0021] Determine an image identity feature according to the identity information, and determine a monitoring area corresponding to the image identity feature from the monitoring image based on the image identity feature;

[0022] Determining a behavior monitoring area within the monitoring area based on the image identity feature;

[0023] Obtaining image feature information of the security personnel based on the image information in the behavior monitoring area;

[0024] Perform image recognition on the image feature information to obtain a second behavior feature of the security personnel.

[0025] In one embodiment, the step of determining the behavior monitoring area within the monitoring area based on the image identity feature includes:

[0026] Determine a feature sequence based on the image identity feature, the feature sequence being a set of identification marks of the security personnel;

[0027] Determine the identification mark according to the feature sequence, and traverse the identification mark in the monitoring area to obtain the identification feature;

[0028] Determine an identification area according to the identification feature;

[0029] Matching the identification feature with the identification mark to determine the degree of match between the identification feature and the identification mark;

[0030] Repeat the steps of matching the identification feature with the identification mark and determining the matching degree between the identification feature and the identification mark until the identification mark is the last identification mark of the feature sequence, and combine the matching degrees into a regional matching degree;

[0031] The region matching degrees are sorted to obtain a region matching degree sequence, and the recognition region corresponding to the maximum region recognition degree in the region matching degree sequence is output as the behavior monitoring region.

[0032] In one embodiment, the step of analyzing the first behavior feature and the second behavior feature based on the behavior monitoring model to obtain the behavior feature of the security personnel, and outputting dangerous behavior alarm information when the behavior feature is a preset behavior feature, includes:

[0033] Analyze the first behavior feature and the second behavior feature based on a behavior monitoring model to determine the behavior type of the security personnel;

[0034] Matching a behavior monitoring strategy and a preset behavior feature according to the behavior type, wherein the behavior monitoring strategy and the preset behavior feature are in a one-to-one correspondence;

[0035] Analyze the first behavior feature and the second behavior feature based on the behavior monitoring strategy to obtain the behavior feature of the security personnel;

[0036] When the behavior feature is a preset behavior feature, dangerous behavior alarm information is output.

[0037] In one embodiment, the step of analyzing the first behavior feature and the second behavior feature based on the behavior monitoring model to obtain the behavior feature of the security personnel, and outputting the dangerous behavior alarm information when the behavior feature is a preset behavior feature, further includes:

[0038] Analyze the dangerous behavior alarm information to determine the urgency of the dangerous behavior alarm information;

[0039] When the emergency level is a first emergency level, sending the dangerous behavior alarm information to the security personnel who performs the dangerous behavior;

[0040] When the urgency level is the second urgency level, the occurrence location and the type of the dangerous behavior are determined according to the dangerous behavior alarm information, and the occurrence location and the type of dangerous behavior are sent to a preset target person, wherein the first urgency level is less than the second urgency level.

[0041] In addition, to achieve the above purpose, the present application also proposes a gas engine safety personnel behavior monitoring device, the gas engine safety personnel behavior monitoring device comprising:

[0042] An identity authentication module is used to obtain the identity information of the security personnel and determine the identity information of the security personnel according to the identity information;

[0043] An action feature extraction module, used to determine the action feature information of the security personnel according to the identity information, and obtain the first behavior feature of the security personnel according to the action feature information;

[0044] An image feature extraction module, used to determine the image feature information of the security personnel according to the identity information, and obtain the second behavior feature of the security personnel according to the image feature information;

[0045] The behavior monitoring module is used to analyze the first behavior feature and the second behavior feature based on a behavior monitoring model to obtain the behavior feature of the security personnel, and output dangerous behavior alarm information when the behavior feature is a preset behavior feature.

[0046] In addition, to achieve the above-mentioned purpose, the present application also proposes a gas engine safety personnel behavior monitoring device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the gas engine safety personnel behavior monitoring method as described above.

[0047] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the gas engine safety personnel behavior monitoring method as described above are implemented.

[0048] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the gas engine safety personnel behavior monitoring method as described above are implemented.

[0049] One or more technical solutions proposed in the present application have at least the following technical effects: obtaining the identity recognition information of the security personnel, determining the identity information of the security personnel based on the identity recognition information, determining the action feature information of the security personnel based on the identity information, obtaining the first behavior feature of the security personnel based on the action feature information, determining the image feature information of the security personnel based on the identity information, obtaining the second behavior feature of the security personnel based on the image feature information, analyzing the first behavior feature and the second behavior feature based on a behavior monitoring model to obtain the behavior feature of the security personnel, and outputting dangerous behavior alarm information when the behavior feature is a preset behavior feature, determining the behavior of the security personnel by combining the action feature and the image feature, and improving the accuracy of behavior monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0052] Figure 1 A flow chart of the first embodiment of the method for monitoring the behavior of gas engine safety personnel provided in this application;

[0053] Figure 2 A schematic diagram of a process for determining action characteristic information provided in an embodiment of a method for monitoring the behavior of gas engine safety personnel in this application;

[0054] Figure 3 A schematic diagram of an image feature determination process provided for an embodiment of a method for monitoring the behavior of gas engine safety personnel in this application;

[0055] Figure 4This is a schematic diagram of the module structure of the gas engine safety personnel behavior monitoring device according to an embodiment of the present application;

[0056] Figure 5 Schematic diagram of the equipment structure of the hardware operating environment involved in the gas engine safety personnel behavior monitoring method in the embodiment of the present application.

[0057] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0059] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0060] The main solution of the embodiment of the present application is: obtaining the identity recognition information of the security personnel, determining the identity information of the security personnel based on the identity recognition information, determining the action characteristic information of the security personnel based on the identity information, obtaining the first behavior characteristic of the security personnel based on the action characteristic information, determining the image characteristic information of the security personnel based on the identity information, obtaining the second behavior characteristic of the security personnel based on the image characteristic information, analyzing the first behavior characteristic and the second behavior characteristic based on a behavior monitoring model to obtain the behavior characteristic of the security personnel, and outputting dangerous behavior alarm information when the behavior characteristic is a preset behavior characteristic.

[0061] In this embodiment, for the convenience of description, the following description is made by taking the gas engine safety personnel behavior monitoring device as the execution subject.

[0062] Since the existing technology for monitoring the behavior of security personnel is usually based on visual methods to determine the behavioral operations of security personnel, but visual detection often has visual blind spots and environments with low light, which will seriously affect the accuracy of monitoring the behavioral operations. Therefore, the current monitoring accuracy of the behavior of security personnel is not high, which reduces the timeliness of discovering dangerous operational behaviors.

[0063] The present application provides a solution, which monitors the operational behavior of security personnel based on action features and image features when monitoring the behavior of security personnel, and can judge the behavior of security personnel from multiple dimensions to improve the accuracy of behavior monitoring.

[0064] It can be seen from the above embodiments that the present application obtains the identity recognition information of the security personnel, determines the identity information of the security personnel based on the identity recognition information, determines the motion feature information of the security personnel based on the identity information, obtains the first behavior feature of the security personnel based on the motion feature information, determines the image feature information of the security personnel based on the identity information, obtains the second behavior feature of the security personnel based on the image feature information, analyzes the first behavior feature and the second behavior feature based on a behavior monitoring model to obtain the behavior feature of the security personnel, and outputs dangerous behavior alarm information when the behavior feature is a preset behavior feature, determines the behavior of the security personnel by combining the motion feature and the image feature, and improves the accuracy of behavior monitoring.

[0065] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a gas engine safety personnel behavior monitoring device, etc. The following takes the gas engine safety personnel behavior monitoring device as an example to illustrate this embodiment and the following embodiments.

[0066] Based on this, the embodiment of the present application provides a method for monitoring the behavior of gas engine safety personnel, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the gas engine safety personnel behavior monitoring method of the present application.

[0067] In this embodiment, the gas engine safety personnel behavior monitoring method includes steps S10 to S40:

[0068] Step S10, obtaining the identity information of the security personnel, and determining the identity information of the security personnel according to the identity information.

[0069] It should be noted that identity recognition information is used to distinguish gas engine safety personnel, which may be facial information, fingerprint information, iris information, etc., which can be used to uniquely identify safety personnel. Regardless of the type of identity recognition information, it corresponds to the identity characteristics of the safety personnel, such as facial features, position information, division of work responsibilities, exclusive sensor identification codes and other information.

[0070] In the specific implementation, in order to ensure that the working environment of the gas engine safety personnel is a safe working environment, when entering the working environment, the safety personnel information can be entered and obtained first. According to the actual workplace layout, one of the identification methods such as facial recognition, fingerprint recognition, and iris recognition can be selected as the identity authentication information, and the obtained identity authentication information can be matched with the identity information of the safety personnel, so that the safety personnel entering the gas engine working environment can be safely registered. When the safety personnel needs to enter the work scene, the obtained identity authentication information can be matched with the identity authentication information recorded in the database. After the identity authentication of the safety personnel is successful, the identity information of the safety personnel can be added to the work pool to obtain the identity information of the safety personnel.

[0071] Step S20, determining the action feature information of the security personnel according to the identity information, and obtaining the first behavior feature of the security personnel according to the action feature information.

[0072] It should be noted that the action feature information is the key action information that can describe the movement of the security personnel's operating behavior, which is obtained through a series of processing based on the sensor signal generated by the sensor monitoring the security personnel's operating behavior. The first behavioral feature refers to the action feature of the security personnel in the behavioral operation.

[0073] In a specific implementation, when the security personnel performs a behavioral operation, the sensor worn by the security personnel will feedback a sensor signal based on the security personnel's behavioral operation, wherein the motion information of the security personnel when performing the current behavioral operation is returned, including at least the spatial coordinates of key points, duration and other information, and these data will be bound to the security personnel's identity information. Therefore, after determining the security personnel's identity information, the motion feature information of the security personnel's behavioral operation corresponding to the identity information can be obtained based on the identity information, and then the motion feature fitting is performed based on the spatial coordinate information, duration and other information in the motion feature information to determine the security personnel's behavioral operation, and then obtain the first behavioral feature of the security personnel. The first behavioral feature can reflect whether the security personnel operates in accordance with the specifications.

[0074] In a feasible implementation, step S20 may include steps S21 to S24:

[0075] Step S21: determining an identity tag according to the identity information, traversing an action feature list based on the identity tag, and obtaining action feature information corresponding to the identity information;

[0076] Step S22: determining a sequence of action feature points according to the action feature information, and determining an action trajectory according to a time sequence corresponding to the sequence of action feature points;

[0077] Step S23: determining the maintenance time of the action trajectory according to the timestamps corresponding to the first and last action feature points of the action feature point sequence;

[0078] Step S24: obtaining a first behavior feature of the security personnel based on the maintenance time and the action trajectory.

[0079] In the specific implementation, refer to Figure 2 , Figure 2 The figure is a flow chart for determining action feature information. The identity tag is determined according to the identity information, and the action feature list is traversed based on the identity tag to obtain the action feature information corresponding to the identity information, and then the action feature information is analyzed to obtain the action feature point sequence. Due to the time delay that may exist when the sensor data is transmitted, the sensor signal generated first may be received later, so the time sequence of the action feature points in the action feature point sequence may be chaotic. Therefore, the action feature points can be rearranged according to the time sequence, and the action trajectory can be determined according to the time sequence corresponding to the action feature point sequence, and the maintenance time of the action trajectory can be determined according to the timestamps corresponding to the first and last action feature points in the action feature point sequence, and the first behavior feature of the security personnel can be obtained according to the duration and the action trajectory.

[0080] Exemplarily, the step of determining a sequence of action feature points according to the action feature information, and determining a motion trajectory according to a time sequence corresponding to the sequence of action feature points includes:

[0081] Determine an action feature point sequence according to the action feature information, and analyze the action feature point sequence to obtain a timestamp and a spatial coordinate of each action feature point in the action feature point sequence;

[0082] Determining the time sequence of the action feature points according to the timestamps, and rearranging the action feature point sequence according to the time sequence to obtain a time-series action feature point sequence;

[0083] Determine a trajectory vector according to the spatial coordinates of two adjacent temporal action feature points in the temporal action feature point sequence;

[0084] The trajectory vector is transformed into an action trajectory according to the time sequence information of each time sequence action feature point.

[0085] In a specific implementation, the action feature point sequence is determined according to the action feature information, and the action feature point sequence is analyzed to obtain the timestamp and spatial coordinates of each feature point in the action feature point. The action feature point sequence can be expressed as D{D1, D2...D n}, where D i is a single feature point. For any feature point D i For D i{t i ,s i (x i ,y i ,z i )}Wherein, t is the timestamp, s is the spatial coordinate of the action feature point, the time sequence of the action feature points is determined according to the timestamp, and the action feature point sequence is rearranged according to the time data to obtain a temporal action feature point sequence, the trajectory vector is determined according to the spatial coordinates of two adjacent temporal action feature points in the temporal action feature point sequence, and the obtained trajectory vectors are used to obtain the action trajectory according to the temporal information of the temporal action feature points.

[0086] Step S30, determining the image feature information of the security personnel according to the identity information, and obtaining the second behavior feature of the security personnel according to the image feature information.

[0087] It should be noted that the image feature information is the image feature obtained by the image acquisition device, wherein the image feature is used to determine the security personnel from the monitoring image, and then determine the monitoring area in the monitoring image. The second behavioral feature refers to the action behavior feature of the security personnel obtained from the monitoring image. In addition, the second behavioral feature also includes the security personnel's clothing and the wearing characteristics of the safety protection equipment.

[0088] In a specific implementation, after obtaining the identity information of the security personnel, the image feature information of the security personnel can be determined from the database according to the identity information, and then the identity of the security personnel appearing in the image can be determined in the monitoring image according to the image feature information, and the monitoring area of ​​the current security personnel can be determined. It can be clearly seen that when the security personnel is detected to appear in the monitoring image, a monitoring identification area will be generated in the area where the security personnel is located in the monitoring image. The security personnel can be circled in the form of a rectangular frame, and can move with the corresponding area of ​​the security personnel in the monitoring image until it disappears in the current monitoring image. In this process, the wearing of the safety protection equipment of the security personnel can be monitored, for example, by monitoring the image, it can be determined whether the security personnel are wearing safety helmets, protective clothing, etc. correctly, and illegal items can also be detected. In addition, when the image monitoring of the security personnel is performed, the behavior of the security personnel can also be detected to determine whether the security personnel are in the correct operation area, and the operation behavior of the security personnel can be recorded in the form of an image to obtain the second behavior characteristics of the security personnel. The second behavior characteristics can not only judge the operation specifications of the security personnel, but also judge the correctness of the area where the security personnel perform the operation.

[0089] In a feasible implementation, step S30 may include steps S31 to S34:

[0090] Step S31: determining an image identity feature according to the identity information, and determining a monitoring area corresponding to the image identity feature from a monitoring image based on the image identity feature.

[0091] Step S32: Determine a behavior monitoring area within the monitoring area based on the image identity feature.

[0092] Step S33: Obtaining image feature information of the security personnel based on the image information in the behavior monitoring area.

[0093] Step S34: performing image recognition on the image feature information to obtain the second behavior feature of the security personnel.

[0094] In the specific implementation, refer to Figure 3 , Figure 3 The figure is a flow chart for determining image features. When determining the image identity features according to the identity information, the monitoring area corresponding to the image identity features can be determined from the monitoring image based on the image identity features. At this time, the monitoring area where the current security personnel is located is determined by comparing the identity features of the security personnel with the portrait in the monitoring image, and then confirming the identity. The behavior monitoring area is determined in the monitoring area according to the image identity features. The behavior monitoring area is a part of the monitoring area, that is, a monitoring area may include at least one behavior monitoring area, and each security personnel corresponds to a behavior monitoring area. There may be an intersection and overlap between the behavior monitoring areas. And then feature extraction is performed based on the image information in the behavior monitoring area, image recognition is performed on the security personnel in the area, the behavior of the security personnel is determined, and the image feature information of the security personnel is obtained, including the interactive relationship between the security personnel and the operating parts, the interactive mode and other information, and then the image feature information is image recognized to obtain the second behavior feature of the security personnel. In addition, the wearing safety behavior of the security personnel can also be detected to determine whether the protective measures of the security personnel are complete.

[0095] Exemplarily, the step of determining the behavior monitoring area within the monitoring area based on the image identity feature includes:

[0096] Determine a feature sequence based on the image identity feature, the feature sequence being a set of identification marks of the security personnel;

[0097] Determine the identification mark according to the feature sequence, and traverse the identification mark in the monitoring area to obtain the identification feature;

[0098] Determine an identification area according to the identification feature;

[0099] Matching the identification feature with the identification mark to determine the degree of match between the identification feature and the identification mark;

[0100] Repeat the steps of matching the identification feature with the identification mark and determining the matching degree between the identification feature and the identification mark until the identification mark is the last identification mark of the feature sequence, and combine the matching degrees into a regional matching degree;

[0101] The region matching degrees are sorted to obtain a region matching degree sequence, and the recognition region corresponding to the maximum region recognition degree in the region matching degree sequence is output as the behavior monitoring region.

[0102] In a specific implementation, a feature sequence is determined based on the image identity feature. The feature sequence is a set of identification marks of the security personnel, for example, including identifiable information such as the facial features of the security personnel. The identification mark is determined based on the feature sequence, and the identification mark is traversed in the monitoring area to obtain the identification feature, and the identification area is determined based on the identification feature. That is to say, the identity features corresponding to the identity information of the security personnel can be matched with the recognition features in the portrait in the monitoring image to determine the identity information of the personnel in the monitoring image. At this time, the recognition features can be matched with the recognition marks to determine the matching degree between each feature. A person has multiple recognition features, and the features of different persons may have similarities. Therefore, when determining the identity of the person, all the features of the person can be comprehensively judged. At the same time, some features of the person image in the detection image may be blocked, so this feature can be skipped and not matched. Only the features that can be determined are matched. After matching all the recognition features with the recognition marks, the regional matching degree can be determined based on the obtained total matching degree, that is, the degree of similarity between the person selected in the behavior monitoring area in the monitoring image and the security personnel corresponding to the current identity information as the same person. This action will perform the same operation on all behavior monitoring areas whose identities have not been confirmed, and arrange the obtained total regional matching degrees in order of size, so as to determine the maximum regional matching degree, and output the recognition area corresponding to the maximum regional recognition degree as the behavior monitoring area.

[0103] Step S40: Analyze the first behavior feature and the second behavior feature based on a behavior monitoring model to obtain the behavior feature of the security personnel, and output dangerous behavior alarm information when the behavior feature is a preset behavior feature.

[0104] It should be noted that the behavior monitoring model is used to make a comprehensive judgment on the first behavior feature and the second behavior feature, combine the two feature information to judge the behavioral operations of the security personnel, and determine the behavioral characteristics of the security personnel. The alarm information can specifically include the specific content of the dangerous behavior, such as the place of occurrence, relevant personnel, degree of danger, etc.

[0105] In the specific implementation, the behavior monitoring model can comprehensively process the first behavior feature and the second behavior feature. In the first behavior feature, the feature information is obtained by processing the sensor signal, so it can only include the behavior operation of the security personnel, such as pushing, pulling, rotating and other operations, and is also limited to the standardization of the operation behavior. The feature information in the second behavior feature is obtained by the image acquisition device, including the contact position of the security personnel with the operating member in the actual operation, and the operation method of performing the behavior operation. Take the rotation of the gas valve as an example. When the security personnel rotates the gas valve, the first behavior feature can only record the interval between the hands of the security personnel and the rotation operation in the same direction. In the second behavior feature, it can determine the contact position of the hands of the security personnel with the gas valve, as well as the behavior operation when the gas valve is rotated. By combining the first behavior feature and the second behavior feature, the behavior operation of the security personnel can be obtained. The behavior feature is compared with the preset behavior feature to determine whether it is a dangerous behavior. When the current behavior operation is a dangerous behavior, the current dangerous behavior alarm information is output.

[0106] Exemplarily, the step of analyzing the first behavior feature and the second behavior feature based on the behavior monitoring model to obtain the behavior feature of the security personnel, and outputting dangerous behavior alarm information when the behavior feature is a preset behavior feature includes:

[0107] Analyze the first behavior feature and the second behavior feature based on a behavior monitoring model to determine the behavior type of the security personnel;

[0108] Matching a behavior monitoring strategy and a preset behavior feature according to the behavior type, wherein the behavior monitoring strategy and the preset behavior feature are in a one-to-one correspondence;

[0109] Analyze the first behavior feature and the second behavior feature based on the behavior monitoring strategy to obtain the behavior feature of the security personnel;

[0110] When the behavior feature is a preset behavior feature, dangerous behavior alarm information is output.

[0111] In a specific implementation, when the first behavior feature and the second behavior feature are analyzed based on the behavior monitoring model to determine the behavior type of the security personnel, the first behavior feature and the second behavior feature can be time-aligned through the timestamps of the first behavior feature and the second behavior feature to determine that the current operation feature remains consistent in time, and then the behavior monitoring strategy and the preset behavior feature are matched according to the behavior type, specifically the standardized operation behavior of each behavior, wherein the monitoring strategy and the preset behavior feature are in a one-to-one correspondence, and the first behavior feature and the second behavior feature are analyzed based on the behavior monitoring strategy to obtain the behavior characteristics of the security personnel, and the behavior characteristics are judged to determine the relationship with the preset behavior characteristics, and when the behavior characteristics are the preset behavior characteristics, the dangerous behavior alarm information is output.

[0112] Exemplarily, after the step of analyzing the first behavior feature and the second behavior feature based on the behavior monitoring model to obtain the behavior feature of the security personnel and outputting dangerous behavior alarm information when the behavior feature is a preset behavior feature, the method further includes:

[0113] Analyze the dangerous behavior alarm information to determine the urgency of the dangerous behavior alarm information;

[0114] When the emergency level is a first emergency level, sending the dangerous behavior alarm information to the security personnel who performs the dangerous behavior;

[0115] When the urgency level is the second urgency level, the occurrence location and the type of the dangerous behavior are determined according to the dangerous behavior alarm information, and the occurrence location and the type of dangerous behavior are sent to a preset target person, wherein the first urgency level is less than the second urgency level.

[0116] In a specific implementation, the dangerous behavior alarm information is analyzed to determine the urgency of the dangerous behavior alarm information, wherein the first urgency is less than the second urgency. When the urgency is the first urgency, the current dangerous behavior alarm information can be sent to the security personnel who perform the dangerous behavior to remind the security personnel to change the behavior operation, and the current alarm information can also be recorded for personnel training; when the urgency is the second urgency, the location of the danger and the type of dangerous behavior can be determined based on the dangerous behavior alarm information, and the location and type of dangerous behavior can be sent to the preset target personnel, wherein the preset target personnel can be the superior management personnel of the current security personnel and / or other security personnel in the area where the current security personnel is located.

[0117] The present embodiment provides a method for monitoring the behavior of gas engine safety personnel, which obtains identity recognition information of the safety personnel, determines the identity information of the safety personnel based on the identity recognition information, determines the action feature information of the safety personnel based on the identity information, obtains the first behavior feature of the safety personnel based on the action feature information, determines the image feature information of the safety personnel based on the identity information, obtains the second behavior feature of the safety personnel based on the image feature information, analyzes the first behavior feature and the second behavior feature based on a behavior monitoring model to obtain the behavior feature of the safety personnel, and outputs dangerous behavior alarm information when the behavior feature is a preset behavior feature, determines the behavior of the safety personnel by combining the action feature and the image feature, and improves the accuracy of behavior monitoring.

[0118] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the gas engine safety personnel behavior monitoring method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0119] This application also provides a gas engine safety personnel behavior monitoring device, please refer to Figure 4 , the gas engine safety personnel behavior monitoring device comprises:

[0120] The identity authentication module 10 is used to obtain the identity information of the security personnel and determine the identity information of the security personnel according to the identity information;

[0121] An action feature extraction module 20, configured to determine the action feature information of the security personnel according to the identity information, and obtain a first behavior feature of the security personnel according to the action feature information;

[0122] An image feature extraction module 30, configured to determine image feature information of the security personnel according to the identity information, and obtain a second behavior feature of the security personnel according to the image feature information;

[0123] The behavior monitoring module 40 is used to analyze the first behavior feature and the second behavior feature based on a behavior monitoring model to obtain the behavior feature of the security personnel, and output dangerous behavior alarm information when the behavior feature is a preset behavior feature.

[0124] The gas engine safety personnel behavior monitoring device provided by the present application adopts the gas engine safety personnel behavior monitoring method in the above embodiment, which can solve the technical problem of low accuracy of gas engine safety personnel behavior monitoring in the prior art. Compared with the prior art, the beneficial effects of the gas engine safety personnel behavior monitoring device provided by the present application are the same as the beneficial effects of the gas engine safety personnel behavior monitoring method provided by the above embodiment, and the other technical features of the gas engine safety personnel behavior monitoring device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0125] The present application provides a gas engine safety personnel behavior monitoring device, the gas engine safety personnel behavior monitoring device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the gas engine safety personnel behavior monitoring method in the above-mentioned embodiment one.

[0126] Reference below Figure 5 , which shows a schematic diagram of the structure of a gas engine safety personnel behavior monitoring device suitable for implementing the embodiment of the present application. The gas engine safety personnel behavior monitoring device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The gas engine safety personnel behavior monitoring 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.

[0127] like Figure 5As shown, the gas engine safety personnel behavior monitoring device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the gas engine safety personnel behavior monitoring device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the gas engine safety personnel behavior monitoring device to communicate wirelessly or wired with other devices to exchange data. Although the gas engine safety personnel behavior monitoring device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0128] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0129] The gas engine safety personnel behavior monitoring device provided by the present application adopts the gas engine safety personnel behavior monitoring method in the above embodiment, which can solve the technical problem of low accuracy of gas engine safety personnel behavior monitoring in the prior art. Compared with the prior art, the beneficial effects of the gas engine safety personnel behavior monitoring device provided by the present application are the same as the beneficial effects of the gas engine safety personnel behavior monitoring method provided by the above embodiment, and the other technical features of the gas engine safety personnel behavior monitoring device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0130] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0131] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0132] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the gas engine safety personnel behavior monitoring method in the above-mentioned embodiment.

[0133] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0134] The computer-readable storage medium may be included in the gas engine safety personnel behavior monitoring device; or may exist independently without being assembled into the gas engine safety personnel behavior monitoring device.

[0135] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the gas engine safety personnel behavior monitoring device, the gas engine safety personnel behavior monitoring device:

[0136] Obtain the identity information of the security personnel, and determine the identity information of the security personnel based on the identity information; determine the action feature information of the security personnel based on the identity information, and obtain the first behavior feature of the security personnel based on the action feature information; determine the image feature information of the security personnel based on the identity information, and obtain the second behavior feature of the security personnel based on the image feature information; analyze the first behavior feature and the second behavior feature based on a behavior monitoring model to obtain the behavior feature of the security personnel, and output dangerous behavior alarm information when the behavior feature is a preset behavior feature.

[0137] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the security personnel computer, partially on the security personnel computer, as a separate software package, partially on the security personnel computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the security personnel computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0138] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0139] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0140] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned gas engine safety personnel behavior monitoring method, and can solve the technical problem of low accuracy of gas engine safety personnel behavior monitoring in the prior art. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the gas engine safety personnel behavior monitoring method provided in the above-mentioned embodiment, and will not be repeated here.

[0141] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned gas engine safety personnel behavior monitoring method when executed by a processor.

[0142] The computer program product provided by the present application can solve the technical problem of low accuracy in monitoring the behavior of gas engine safety personnel in the prior art. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the gas engine safety personnel behavior monitoring method provided by the above embodiment, and will not be repeated here.

[0143] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for monitoring the behavior of gas engine safety personnel, characterized in that: The gas engine safety personnel behavior monitoring method comprises: Obtaining identity information of a security personnel, and determining the identity information of the security personnel according to the identity information; Determine action feature information of the security personnel according to the identity information, and obtain a first behavior feature of the security personnel according to the action feature information; Determine the image feature information of the security personnel according to the identity information, and obtain the second behavior feature of the security personnel according to the image feature information; The first behavior feature and the second behavior feature are analyzed based on a behavior monitoring model to obtain the behavior feature of the security personnel, and when the behavior feature is a preset behavior feature, dangerous behavior alarm information is output.

2. The method according to claim 1, characterized in that The step of determining the action feature information of the security personnel according to the identity information and obtaining the first behavior feature of the security personnel according to the action feature information comprises: Determine an identity tag according to the identity information, traverse the action feature list based on the identity tag, and obtain action feature information corresponding to the identity information; Determine a sequence of action feature points according to the action feature information, and determine an action trajectory according to a time sequence corresponding to the sequence of action feature points; Determining the maintenance time of the action trajectory according to the timestamps corresponding to the first and last action feature points of the action feature point sequence; A first behavior feature of the security personnel is obtained based on the maintenance time and the action trajectory.

3. The method according to claim 2, characterized in that The step of determining a sequence of action feature points according to the action feature information, and determining an action trajectory according to a time sequence corresponding to the sequence of action feature points comprises: Determine an action feature point sequence according to the action feature information, and analyze the action feature point sequence to obtain a timestamp and a spatial coordinate of each action feature point in the action feature point sequence; Determining the time sequence of the action feature points according to the timestamps, and rearranging the action feature point sequence according to the time sequence to obtain a time-series action feature point sequence; Determine a trajectory vector according to the spatial coordinates of two adjacent temporal action feature points in the temporal action feature point sequence; The trajectory vector is transformed into an action trajectory according to the time sequence information of each time sequence action feature point.

4. The method according to claim 1, characterized in that The step of determining the image feature information of the security personnel according to the identity information and obtaining the second behavior feature of the security personnel according to the image feature information comprises: Determine an image identity feature according to the identity information, and determine a monitoring area corresponding to the image identity feature from the monitoring image based on the image identity feature; Determining a behavior monitoring area within the monitoring area based on the image identity feature; Obtaining image feature information of the security personnel based on the image information in the behavior monitoring area; Perform image recognition on the image feature information to obtain a second behavior feature of the security personnel.

5. The method according to claim 4, characterized in that The step of determining the behavior monitoring area within the monitoring area based on the image identity feature comprises: Determine a feature sequence based on the image identity feature, the feature sequence being a set of identification marks of the security personnel; Determine the identification mark according to the feature sequence, and traverse the identification mark in the monitoring area to obtain the identification feature; Determine an identification area according to the identification feature; Matching the identification feature with the identification mark to determine the degree of match between the identification feature and the identification mark; Repeat the steps of matching the identification feature with the identification mark and determining the matching degree between the identification feature and the identification mark until the identification mark is the last identification mark of the feature sequence, and combine the matching degrees into a regional matching degree; The region matching degrees are sorted to obtain a region matching degree sequence, and the recognition region corresponding to the maximum region recognition degree in the region matching degree sequence is output as the behavior monitoring region.

6. The method according to claim 1, characterized in that The step of analyzing the first behavior feature and the second behavior feature based on the behavior monitoring model to obtain the behavior feature of the security personnel, and outputting dangerous behavior alarm information when the behavior feature is a preset behavior feature, comprises: Analyze the first behavior feature and the second behavior feature based on a behavior monitoring model to determine the behavior type of the security personnel; Matching a behavior monitoring strategy and a preset behavior feature according to the behavior type, wherein the behavior monitoring strategy and the preset behavior feature are in a one-to-one correspondence; Analyze the first behavior feature and the second behavior feature based on the behavior monitoring strategy to obtain the behavior feature of the security personnel; When the behavior feature is a preset behavior feature, dangerous behavior alarm information is output.

7. The method according to any one of claims 1 to 6, characterized in that After the step of analyzing the first behavior feature and the second behavior feature based on the behavior monitoring model to obtain the behavior feature of the security personnel and outputting dangerous behavior alarm information when the behavior feature is a preset behavior feature, the method further includes: Analyze the dangerous behavior alarm information to determine the urgency of the dangerous behavior alarm information; When the emergency level is a first emergency level, sending the dangerous behavior alarm information to the security personnel who performs the dangerous behavior; When the urgency level is the second urgency level, the occurrence location and the type of the dangerous behavior are determined according to the dangerous behavior alarm information, and the occurrence location and the type of dangerous behavior are sent to a preset target person, wherein the first urgency level is less than the second urgency level.

8. A gas engine safety personnel behavior monitoring device, characterized in that: The device comprises: An identity authentication module is used to obtain the identity information of the security personnel and determine the identity information of the security personnel according to the identity information; An action feature extraction module, used to determine the action feature information of the security personnel according to the identity information, and obtain the first behavior feature of the security personnel according to the action feature information; An image feature extraction module, used to determine the image feature information of the security personnel according to the identity information, and obtain the second behavior feature of the security personnel according to the image feature information; The behavior monitoring module is used to analyze the first behavior feature and the second behavior feature based on a behavior monitoring model to obtain the behavior feature of the security personnel, and output dangerous behavior alarm information when the behavior feature is a preset behavior feature.

9. A gas engine safety personnel behavior monitoring device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the gas engine safety personnel behavior monitoring method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the gas engine safety personnel behavior monitoring method according to any one of claims 1 to 7 are implemented.

Images