CN118053261B - Anti-spoofing early warning method, device, equipment and medium for smart campus - Google Patents
Anti-spoofing early warning method, device, equipment and medium for smart campus Download PDFInfo
- Publication number
- CN118053261B CN118053261B CN202410452397.1A CN202410452397A CN118053261B CN 118053261 B CN118053261 B CN 118053261B CN 202410452397 A CN202410452397 A CN 202410452397A CN 118053261 B CN118053261 B CN 118053261B
- Authority
- CN
- China
- Prior art keywords
- height
- value list
- tracking target
- maximum value
- data points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000003780 insertion Methods 0.000 claims abstract description 27
- 230000037431 insertion Effects 0.000 claims abstract description 27
- 230000008859 change Effects 0.000 claims description 26
- 238000005259 measurement Methods 0.000 claims description 24
- 230000006399 behavior Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000009434 installation Methods 0.000 claims description 17
- 230000015654 memory Effects 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 16
- 230000002776 aggregation Effects 0.000 claims description 14
- 238000004220 aggregation Methods 0.000 claims description 14
- 238000012544 monitoring process Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000012935 Averaging Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000003491 array Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 230000008447 perception Effects 0.000 abstract 1
- 230000008569 process Effects 0.000 description 12
- 238000001514 detection method Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000035772 mutation Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 230000009897 systematic effect Effects 0.000 description 3
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 230000002411 adverse Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 206010016173 Fall Diseases 0.000 description 1
- 206010017577 Gait disturbance Diseases 0.000 description 1
- 206010039740 Screaming Diseases 0.000 description 1
- 238000010009 beating Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0407—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
- G08B21/043—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis detecting an emergency event, e.g. a fall
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/66—Radar-tracking systems; Analogous systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/886—Radar or analogous systems specially adapted for specific applications for alarm systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0469—Presence detectors to detect unsafe condition, e.g. infrared sensor, microphone
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Health & Medical Sciences (AREA)
- Gerontology & Geriatric Medicine (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Human Computer Interaction (AREA)
- Electromagnetism (AREA)
- Psychiatry (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Alarm Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The application is suitable for the technical field of Internet, and particularly relates to an anti-spoofing early warning method, device, equipment and medium for intelligent campus. The method comprises the steps of identifying all point cloud data of a target scene to obtain each tracking target, determining a maximum value list and a minimum value list corresponding to the heights of data points, obtaining new data points at the current moment, determining the insertion position of each new data point in the maximum value list, inserting the new data points in the maximum value list based on the insertion position to obtain an updated maximum value list, calculating the current height based on the updated maximum value list, obtaining the historical heights of each tracking target at the historical moment, judging the falling state of the tracking target based on the historical heights and the current height, accurately updating the maximum value list corresponding to the tracking target in an interpolation mode of the new data points, and further accurately identifying the falling state, so that a supervision system can conveniently supervise, and the safety perception capability is improved under the premise of protecting privacy.
Description
Technical Field
The application is suitable for the technical field of Internet, and particularly relates to an anti-spoofing early warning method, device, equipment and medium for intelligent campus.
Background
At present, campus safety is a subject of important attention in society, and the campus safety not only relates to personal and property safety of teachers and students, but also relates to happiness and stability of thousands of families and harmony and stability of society. The current situation of safety management of a kindergarten in middle and primary schools is not ideal, the foundation of the safety management is weak, effective scientific guidance is lacked, the safety management level is uneven, and the unstable risk of campus safety continuously brings new challenges to the safety management of schools. The safety management belongs to a system engineering, and the core problem of the safety system engineering is that scientific mechanisms for preventing, avoiding and processing are effectively established for various benefit conflicts and disaster accidents which lead to the safety problem in a social system, and systematic factors which bring the safety problem are dealt with by highly systematic safety measures. Based on the problems of multiple dimensions, high management difficulty and the like of campus safety, various safety-related object-associated sensing systems are online in the campus. In the activity of campus safety management, multidimensional operation data are collected, analysis is carried out on the data, early warning is carried out on risk events, targeted auxiliary decision-making suggestions are provided according to different types and different values of the early warning, and systematic consideration of campus safety management problems is possible, so that a decision is made for on-site treatment.
Most of the current campus sensing systems need to use cameras to collect images and process the images to generate early warning events so as to facilitate timely supervision, however, some specific scenes in the campus need to protect privacy of students, teachers and other personnel, so that the cameras cannot be used for image collection, for example, when supervising dormitories, the cameras are naturally unsuitable, and therefore sensing devices such as sound and radar can be used for data sensing. Because the sound does not necessarily represent a real scene in the automated analysis process, and the radar has a false recognition condition, false alarm conditions often occur when such data are used for judging.
Therefore, how to effectively process the radar measurement data to accurately judge the falling event of personnel, so that the monitoring system can intervene in time to monitor the falling event becomes a problem to be solved.
Disclosure of Invention
In view of the above, the embodiments of the present application provide an anti-fraud early warning method, apparatus, device, and medium for smart campuses, so as to solve the problem of how to effectively process radar measurement data, accurately determine events such as personnel falling, and facilitate timely intervention and supervision by a supervision system.
In a first aspect, an embodiment of the present application provides an anti-spoofing early warning method for smart campuses, where the anti-spoofing early warning method includes:
Performing target recognition on all point cloud data obtained by radar measurement in an acquired target scene to obtain each tracking target, and determining a maximum value list and a minimum value list corresponding to the height of the data points from an array formed by the data points of each tracking target;
Acquiring new data points at the current moment, and determining the insertion position of each new data point in the maximum value list according to the height of the new data point, the maximum value list and the minimum value list;
Inserting the new data points into the maximum value list based on the insertion positions to obtain an updated maximum value list, and calculating to obtain the current height of the corresponding tracking target at the current moment based on the updated maximum value list;
Acquiring the historical height of each tracking target at the historical moment, calculating the change rate of the current height compared with the historical height according to the historical height and the current height, detecting whether the change rate is larger than a threshold value, and if the change rate is larger than the threshold value, determining that the corresponding tracking target is in a falling state so as to generate a falling event for anti-theft early warning.
In a second aspect, an embodiment of the present application provides an anti-fraud early warning device for smart campus, where the anti-fraud early warning device includes:
The data preprocessing module is used for carrying out target recognition on all point cloud data obtained by radar measurement in an acquired target scene to obtain each tracking target, and determining a maximum value list and a minimum value list corresponding to the height of the data points from an array formed by the data points of each tracking target;
The data insertion module is used for acquiring new data points at the current moment and determining the insertion position of each new data point in the maximum value list according to the height of the new data points, the maximum value list and the minimum value list;
The data calculation module is used for inserting the new data points into the maximum value list based on the insertion position to obtain an updated maximum value list, and calculating the current height of the corresponding tracking target at the current moment based on the updated maximum value list;
the first supervision module is used for acquiring the historical height of each tracking target at the historical moment, calculating the change rate of the current height compared with the historical height according to the historical height and the current height, detecting whether the change rate is larger than a threshold value, and if the change rate is larger than the threshold value, determining that the corresponding tracking target is in a falling state so as to generate a falling event for anti-ice early warning.
In a third aspect, an embodiment of the present application provides a computer device, where the computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, where the processor implements the anti-spoofing method according to the first aspect when the processor executes the computer program.
In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, where a computer program is stored, where the computer program is executed by a processor to implement the anti-spoofing early warning method according to the first aspect.
Compared with the prior art, the embodiment of the application has the beneficial effects that: the method comprises the steps of carrying out target identification on all point cloud data obtained by radar measurement in an obtained target scene to obtain each tracking target, determining a maximum value list and a minimum value list corresponding to the height of the data points from an array formed by the data points of each tracking target, obtaining new data points at the current moment, determining the insertion position of each new data point in the maximum value list according to the height of the new data points and the maximum value list and the minimum value list, inserting the new data points in the maximum value list based on the insertion position to obtain an updated maximum value list, calculating to obtain the current height of the corresponding tracking target at the current moment based on the updated maximum value list, obtaining the historical height of each tracking target at the current moment, calculating to obtain the change rate of the current height compared with the historical height according to the historical height and the current height, detecting whether the change rate is larger than a threshold value, if the change rate of the current height is larger than the threshold value, determining that the corresponding tracking target is in a falling state, generating an event, carrying out a falling prevention alarm, accurately updating the maximum value list corresponding to the tracking target in the maximum value list based on the interpolation mode of the new data points, thereby realizing falling judgment of the height, further improving the falling state of the monitoring and accurately, monitoring and protecting the system, and protecting the falling state.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of an application environment of an anti-spoofing early warning method for smart campus according to an embodiment of the present application;
Fig. 2 is a flow chart of a method for anti-spoofing early warning for smart campus according to a second embodiment of the present application;
fig. 3 is a flowchart of a method for anti-spoofing early warning for smart campus according to a third embodiment of the present application;
Fig. 4 is a flowchart of a method for anti-spoofing early warning for smart campus according to a fourth embodiment of the present application;
Fig. 5 is a flowchart of a method for anti-spoofing early warning for smart campus according to a fifth embodiment of the present application;
fig. 6 is a schematic structural diagram of an anti-fraud early warning device for smart campus according to a sixth embodiment of the present application;
fig. 7 is a schematic structural diagram of a computer device according to a seventh embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As used in the present description and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".
Furthermore, the terms "first," "second," "third," and the like in the description of the present specification and in the appended claims, are used for distinguishing between descriptions and not necessarily for indicating or implying a relative importance.
Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
It should be understood that the sequence numbers of the steps in the following embodiments do not mean the order of execution, and the execution order of the processes should be determined by the functions and the internal logic, and should not be construed as limiting the implementation process of the embodiments of the present application.
In order to illustrate the technical scheme of the application, the following description is made by specific examples.
The method for preventing the anti-spoofing of the smart campus provided by the embodiment of the application can be applied to an application environment as shown in fig. 1, wherein the sensing device is a device installed in a target scene and used for collecting corresponding data in the target scene, for example, the sensing device can be a radar, and particularly can be a millimeter wave radar and the like. The sensing equipment is connected with the server through a network and the like, so that the server can acquire corresponding data and process the data. The computer device corresponding to the server may be implemented by an independent server or a server cluster formed by a plurality of servers. Correspondingly, the server communicates with the client, the client A is a mobile client, a user can view the mobile client on mobile equipment such as a mobile phone, the client B is a computer, and the worker and the user view the mobile equipment in a fixed place. The client includes, but is not limited to, palm top computers, desktop computers, notebook computers, ultra-Mobile Personal Computer (UMPC), netbooks, cloud computer devices, personal digital assistants (Personal DIGITAL ASSISTANT, PDA), and the like. The server side, all the clients and the like form a whole supervision system, and the server side is used for collecting data and analyzing and processing the data so as to realize supervision. Of course, the anti-spoofing early warning method of the application can also be applied to the sensing equipment, provided that the sensing equipment is provided with a processing chip capable of carrying out analysis and operation, and at the moment, the sensing equipment can realize supervision only by sending the processing result to the server.
Referring to fig. 2, a flow chart of an anti-spoofing early warning method for a smart campus according to a second embodiment of the present application is provided, where the anti-spoofing early warning method for a smart campus is applied to a server or a sensing device in fig. 1, where the sensing device may integrate sensors for sensing such as a radar, a sound collector, a temperature sensor, a smoke sensor, etc. to implement sensing of multidimensional data, so as to implement multidimensional supervision. As shown in fig. 2, the anti-spoofing early warning method for smart campus may include the following steps:
step S201, performing target recognition on all point cloud data obtained by radar measurement in the acquired target scene to obtain each tracking target, and determining a maximum value list and a minimum value list corresponding to the height of the data points from an array formed by the data points of each tracking target.
In this embodiment, the target scene may refer to an installation scene of a sensing device, where the sensing device is a device including a millimeter wave radar, and the millimeter wave radar can measure objects in the installation scene, for example, the target scene may be a classroom, a dormitory, and the like, and especially in the dormitory scene, image acquisition is inconvenient, so that in-scene sensing performed by using the millimeter wave radar can effectively protect privacy.
The radar is used for carrying out real-time scanning on the target scene, the real-time scanning is formed by continuously combining single scanning, namely each sampling moment corresponds to one single scanning, information such as the distance, the angle and the like of all objects in the target scene at the corresponding moment can be obtained in one single scanning, the information can be described as point cloud data, namely each object is characterized as a continuous point, and each point corresponds to one information such as the distance, the angle and the like.
And analyzing all point cloud data acquired from the target scene, specifically, identifying the target, wherein the target is a human body, an object and the like in the target scene, and the same target is required to be used for the same human body, so that the clustered point cloud data can be used for clustering, then the shape of the clustered point cloud is identified to judge the target type corresponding to the clustered point cloud, if the clustered point cloud is a human body, a person target is positioned, and along with the point cloud data acquired in real time, similarity comparison is performed on the clustered results obtained after every two continuous measurements to obtain two similar clustered results, and therefore, the two similar clustered results are determined to be the same target, and target tracking can be realized. Therefore, all the power supply data are subjected to target recognition, and each tracking target can be obtained, wherein the tracking targets are set to be human bodies, namely, the recognition of personnel is realized.
For any tracking target, the array of data points corresponding to the tracking target (i.e. the data group of data points) can represent the height, width and other information of the tracking target, and for this purpose, the data point height analysis can be performed on the array of the tracking target, i.e. the maximum value and the minimum value of the height can be obtained.
The maximum value list stores at least one maximum value, that is, the maximum value list can store the maximum value of the height of the same tracking target in the point cloud data obtained by multiple measurements, and correspondingly, the minimum value list stores at least one minimum value, that is, the minimum value list can store the minimum value of the height of the same tracking target in the point cloud data obtained by multiple measurements.
Optionally, determining a maximum value list and a minimum value list corresponding to the height of the data points from the array formed by the data points of each tracking target includes:
extracting angle information and distance information of any data point aiming at an array formed by the data points of any tracking target;
Acquiring the installation height of the radar, calculating to obtain the height of a corresponding data point according to the installation height, the angle information and the distance information, and traversing all the data points to obtain the height of each data point;
Carrying out validity judgment on the heights of all data points to obtain a judgment result, and calculating to obtain the maximum value and the minimum value of the corresponding array according to the data points with the valid heights as the judgment result;
and respectively sequencing the maximum values and the minimum values corresponding to the arrays of radar measurement in the continuous first preset time period to obtain a maximum value list and a minimum value list.
For an array of data points of a tracking target, angle information, distance information and the like of each data point are extracted, and the height of the data point under a world coordinate system (with the ground of the target scene as a horizontal plane) is calculated by combining the installation height of the radar.
When each data point is calculated, abnormal data points need to be removed, for example, data points with the height obviously exceeding the reasonable height of the human body are abnormal data points, and for example, data points with the height being negative values can also be judged to be abnormal data points. For abnormal data points, the effectiveness is doubtful, so that the data obtained after the data points are removed is a more accurate maximum value and a more accurate minimum value.
In this embodiment, the maximum value list and the minimum value list are constructed by using the maximum values and the minimum values corresponding to the array of radar measurements in the continuous first preset time period, for example, the first preset time is 1 second, so as to reduce the measurement error in turn and improve the accuracy of the height determination.
Step S202, obtaining new data points at the current moment, and determining the insertion position of each new data point in the maximum value list according to the height of the new data point, the maximum value list and the minimum value list.
In this embodiment, the current time may refer to any time when the method of the present application is executed, and the new data point is a data point obtained after the radar is used to measure at the current time, where the new data point may refer to all data points measured by the radar during the current measurement. The current time is required to be within the time period for which the corresponding maximum value list is constructed, for example, within 1 second as described above.
Based on the same way as the calculation of the height of the data point in the above step S201, the height of the new data point is calculated, and according to the height of the new data point, the corresponding insertion position is searched in the maximum value list and the minimum value list, wherein the height of the new data point is compared with any minimum value in the minimum value list, if the height of the new data point is greater than all the minimum values, the height of the new data point is compared with any maximum value in the maximum value list, if the height of the new data point is greater than any maximum value, the maximum value list is a list with the maximum values arranged in sequence, so that the next maximum value can be searched until a proper insertion position is found, and if the height of the new data point is less than any minimum value, the loop can be directly jumped out, that is, the insertion position of the new data point in the maximum value list is empty, that is, and no insertion is required.
For example, the maximum value list is H1, H2, H3, H4, and the height H of the new data point is greater than H3 and less than H4, then the insertion position may be between H3 and H4, or H4 may be eliminated, and H is used instead of H4.
Step S203, new data points are inserted into the maximum value list based on the insertion position, an updated maximum value list is obtained, and the current height of the corresponding tracking target at the current moment is calculated and obtained based on the updated maximum value list.
In this embodiment, after determining the insertion position, the height corresponding to the new data point may be inserted into the maximum value list, so as to obtain an updated maximum value list, where, of course, if the insertion position is empty, the data in the maximum value list is not changed, and the updated maximum value list is the same as the previous maximum value list.
The average value obtained by averaging all the maxima in the updated maximum list is recorded as the current height at the current time, and in an embodiment, a value may be selected from the updated maximum list as the current height. Of course, in the process of determining the current height, maximum value data smoothing processing may be additionally performed on the updated maximum value list, and the current height may be calculated according to the result after the smoothing processing.
Optionally, calculating, based on the updated maximum value list, a current height of the tracking target corresponding to the characterization at the current moment includes:
Averaging all maximum values in the updated maximum value list to obtain an averaging result;
and determining an average result as a current height of the corresponding tracking target at the current moment.
The average value can effectively express the height of the tracking target in the time period corresponding to the whole maximum value list, and accuracy of height calculation is improved.
Step S204, the historical height of each tracking target at the historical moment is obtained, the change rate of the current height compared with the historical height is calculated according to the historical height and the current height, whether the change rate is larger than a threshold value is detected, if the change rate is larger than the threshold value is detected, the corresponding tracking target is determined to be in a falling state, and therefore falling events are generated to perform anti-theft early warning.
In this embodiment, the historical time is a time before the current time, where the historical time may be a time period, that is, the historical time corresponds to a historical maximum value list, the height corresponding to the historical maximum value list is the historical height, the current height is compared with the historical height, if a mutation occurs (that is, the change rate is greater than the threshold value), it may be indicated that the tracking target has a high mutation, and of course, the mutation is a mutation towards a low value, that is, from a high value to a low value, at this time, the tracking target is considered to fall, that is, the tracking target is updated to be in a falling state. The change rate may refer to a ratio of two or more measurements to the current height, and may specifically refer to a falling ratio of the height, where after the falling ratio exceeds a threshold, a person may be determined to be a falling behavior state.
The updated tracking target may be generated as a fall event, which can be sent to the supervision system to enable supervision. In this embodiment, the sensing device may further include a voice module, and after the fall event is generated, the voice module may be controlled to output a preset first voice, for example, to use the first voice for driving away, warning, and the like.
Of course, for campus spoofing, there may be many possibilities that the behavior determination cannot be accurately achieved by detecting the height at one time, so the embodiment of the present application uses a high interpolation insertion mode to perform calculation, for example, for the behaviors of being embraced, being lifted to fall, falling by oneself, and the like, the falling determination can be performed by the above-mentioned high calculation mode, so that the determination accuracy of the falling behavior is improved.
According to the embodiment of the application, all point cloud data obtained by radar measurement in an acquired target scene are subjected to target identification to obtain each tracking target, a maximum value list and a minimum value list corresponding to the height of the data points are determined from an array formed by the data points of each tracking target, new data points at the current moment are acquired, the insertion position of each new data point in the maximum value list is determined according to the height of the new data points and the maximum value list and the minimum value list, new data points are inserted in the maximum value list based on the insertion position, an updated maximum value list is obtained, the current height of the corresponding tracking target at the current moment is calculated and obtained based on the updated maximum value list, the historical height of each tracking target at the historical moment is obtained, the change rate of the current height is calculated and obtained according to the historical height and the current height, if the change rate of the current height is larger than the historical height is larger than a threshold value, the corresponding tracking target is determined to be in a falling state if the change rate of the current height is larger than the threshold value, so that a falling-down prevention early warning event is generated, the maximum value corresponding to the tracking target is accurately updated in the maximum value list in an interpolation mode of the maximum value list, the falling-prevention early warning mode is realized, accordingly, the falling state is accurately identified, the falling state is accurately is monitored, the system is monitored, and the safety is monitored, and the situation is more accurately is monitored, and the situation is more is monitored.
Referring to fig. 3, a flow chart of a method for anti-fraud early warning for smart campus according to a third embodiment of the present application is provided. As shown in fig. 3, the anti-spoofing method may further include the following steps:
Step S301, acquiring sound data collected in a prediction time interval before and after the current time.
The above-mentioned sound collector is used to collect sound data in the installation environment of the sensing device, and of course, the sound collector is used to collect sound data in real time, and for the current moment, only the sound data in a certain period of time before and after the current moment is needed, for example, if the preset time interval is 30 seconds, the sound data corresponding to 30 seconds before and after the current moment is at least 1 minute of sound data.
The current time in the application is not the world time of the running of the device, but the time corresponding to the processed data, for example, if the preset time interval is 30 seconds, if the device is running normally, the current time is different from the world time corresponding to the data of the current time by at least 30 seconds.
After determining that the corresponding tracking target is in the falling state in step S204, the method further includes the steps of:
In step S302, it is detected whether a preset keyword exists in the sound data.
The step of detecting whether the preset keyword exists in the sound data should be set to be started after the radar detects that the tracking target is in a falling state, so as to start pushing of a subsequent falling event to prevent false alarm, and meanwhile, data operation can be reduced to a certain extent, for example, if the radar cannot monitor people, steps such as keyword detection are not needed even if the radar detects people, the occupied space of the data operation is reduced, and the loss of equipment is reduced.
The preset keywords are sensitive words, such as alarming, rescuing and the like, and words formed by more than two words are adopted as much as possible, so that the keyword detection accuracy can be improved to a certain extent. If preset keywords exist, the condition that the data at the current moment reaches the condition of starting event pushing is indicated, namely, the condition that a deceptive falling event is indicated to appear in the environment where the sensing equipment is located is primarily considered.
Step S303, if it is detected that the preset keyword exists in the sound data, the duration of each tracking target in the falling state is counted, and whether the duration is greater than a first time threshold is detected.
In this embodiment, the duration may be a duration set according to the requirement, and after detecting that the tracking target is in a falling state, the continuous height detection is performed on the tracking target, and the height detection process may use the height calculation method described in the second embodiment.
Whether the height is suddenly changed from a low value to a high value is detected, if the height is not suddenly changed, the tracking target is always in a falling state, if the height is suddenly changed, the tracking target is changed from falling to standing, and the like, namely the falling state is ended.
Step S304, for any tracking target, if the duration is detected to be greater than the first time threshold, a falling event for the tracking target is generated, and the falling event is sent to a supervision system for supervision.
In this embodiment, in order to distinguish different specific behaviors, so that the fall determination is more accurate, the detection of different states is performed by taking time as a threshold value, if the tracking target is in the fall state for a long time, the possibility of falling and danger is high, if the tracking target is in the fall state for a short time, the tracking target may possibly have the behaviors of stumbling or squatting, for example, the long time may be more than one minute, the short time may be less than 30 seconds, and the like.
The embodiment of the application can better distinguish the detailed falling behaviors, so that the reliability is improved for falling judgment, the falling event is generated on the basis of reliability, the falling event can be pushed more accurately by combining the use of sound data, the occurrence rate of false recognition is reduced, and finally, a supervision system is provided to pay attention to and respond to the corresponding dangerous situation in time, so that the campus safety is improved.
Optionally, after acquiring the sound data acquired in the predicted time interval before and after the current time, the method further includes:
Inputting sound data into a pre-trained voice analysis model, and outputting a first result and the confidence coefficient thereof for representing the occurrence of the spoofing semanteme, a second result and the confidence coefficient thereof for representing the occurrence of the sharp sound, and a third result and the confidence coefficient thereof for representing the occurrence of the inverted sound;
After generating the fall event for the tracking target, further comprising:
normalizing the confidence coefficient of the first result, the confidence coefficient of the second result and the confidence coefficient of the third result to obtain a weight for representing the first result, a weight for representing the second result and a weight for representing the third result;
And calculating the score of the spoofing state of the sound data according to the first result and the weight thereof, the second result and the weight thereof, and the third result and the weight thereof, and transmitting the score of the spoofing state to a monitoring system when the falling event is transmitted to the monitoring system for monitoring.
The pre-trained speech analysis model may adopt a natural language processing (Natural Language Processing, NLP) technology, specifically may include, but is not limited to, semantic analysis, lexical analysis, syntactic analysis, named entity recognition, and the like, for example, a neural network adopting a combination of speech recognition and semantic recognition may use a continuous language model, a network structure may adopt a cyclic neural network (Recurrent Neural Network, RNN), a long-short-term memory network (Long Short Term Memory, LSTM), a gated loop unit (Gate Recurrent Unit, GRU) network, a fransformer, and the like, and semantic recognition may use a full convolutional neural network (Fully Convolutional Networks, FCN), deepLab series model, and the like.
The pre-trained voice analysis model can identify the deceptive semantics, the sharp sounds and the falling sounds, wherein the functions of the three parts can be trained by using three types of data when training, the deceptive semantics are generally cursory people, offensive language and the like, the deceptive semantics can be analyzed by using the semantic recognition, the sharp sounds are generally expressed as screaming, shouting, alarming and the like, the falling sounds can be expressed as beating, kicking, falling to the ground and the like, and the voice recognition can be used for analysis, so that the corresponding characterization result and the confidence thereof can be obtained.
The confidence level can be used to obtain a weight corresponding to each result, so that the result is expressed in the form of a visual number (i.e. a score of a status of the spoofing is obtained), wherein the score of the status of the spoofing can follow a fall event to form associated data, so that when the fall event is received by the monitoring system, the score of the status of the spoofing corresponding to the fall event is displayed. Further, the spoofing status score may be matched to alarms of different phases and treatment plans of different phases.
In this embodiment, the collected sound data is analyzed by using the model to obtain the score of the condition of the spoofing for evaluating the spoofing, and the radar data can only analyze the behavior, so that the defect that the radar data cannot evaluate the spoofing can be made up by combining the sound data, and meanwhile, the accuracy of the spoofing alarm can be effectively improved by combining the sound data and the radar data.
Referring to fig. 4, a flow chart of a method for anti-fraud early warning for smart campus according to a fourth embodiment of the present application is provided. As shown in fig. 4, in the step S201, the target recognition is performed on the point cloud data obtained by using radar measurement in the acquired target scene, and after each tracking target is obtained, the following steps may be further included:
Step S401, detecting whether N or more tracking targets exist in a preset range.
The preset range may refer to a specified range in the target scene, if the target scene is segmented, the segmented space may be used as a preset range, and if a plurality of tracking targets appear in the preset range, the corresponding space may be described as having more people.
Step S402, if N or more tracking targets are detected to exist in the preset range, determining that a person aggregation state exists in the target scene.
The preset range and N are set relatively, so that the main purpose is to highlight the density of the tracking target in the preset range, if the density is higher, that is, the higher N is, the higher the possibility of personnel gathering is, and in the case of personnel gathering, adverse events may occur, at this time, if the judgment is performed by combining the falling behaviors of the personnel described in the second embodiment, it may be stated that serious adverse conditions occur, and in this case, important attention is required.
Step S403, when the duration of the personnel aggregation state in the target scene is greater than the second time threshold, executing to determine a maximum value list and a minimum value list corresponding to the height of the data points from the array formed by the data points of each tracking target, generating personnel aggregation events, and sending the personnel aggregation events to the supervision system for supervision.
In this embodiment, if the supervisory system receives the personnel gathering event, the supervisory system may individually perform corresponding management, for example, broadcast by using a preset second voice to drive the gathering personnel, and if the supervisory system receives the personnel gathering event and the falling event at the same time, this indicates that the situation is more serious than the aforementioned individual personnel gathering event, so a more urgent management manner may be adopted.
For an individual people gathering event, the event can be pushed to a supervision terminal, and the supervision terminal can query other supervision devices to perform joint analysis so as to determine the accurate people gathering property.
In an embodiment, if the supervision system receives the personnel aggregation event and the falling event, the two events are fused to generate an early warning event, and the early warning event is sent to the supervision terminal and the mobile terminal. The anti-deception early warning method further comprises the following steps:
acquiring the installation location of a radar, and searching a mobile terminal connected with a monitoring system in a preset range according to the installation location;
If the existence of the mobile terminal in the preset range is detected, pushing the early warning event and the installation positioning to the mobile terminal so that a user of the mobile terminal perceives the early warning event.
The user can find a corresponding target scene based on the installation positioning, so as to solve the security event as soon as possible, wherein the installation positioning can be GPS positioning coordinates, or can be information set according to a preset rule, such as a house number and the like.
Referring to fig. 5, a flow chart of an anti-spoofing early warning method for smart campus provided by a fifth embodiment of the present application is shown in fig. 5, and after determining that the corresponding tracking target is in a falling state in the step S204, the method may further include the following steps:
in step S501, local point cloud data in a preset space around the tracking target in a second preset time period is extracted, and a start time of the second preset time period is a time corresponding to when the corresponding tracking target is determined to be in a falling state.
In this embodiment, the local point cloud data is a data point in a preset space around the tracking target based on the falling state, and the second preset time period may be a shorter time, for example, the sampling period is 10 seconds, and the second preset time period may be 2 minutes. The local point cloud data can be used to analyze the surroundings of the tracking target to enhance subsequent use of the data.
Step S502, performing behavior recognition on the local point cloud data to obtain a behavior recognition result, and if the behavior recognition result indicates that there is limb contact with the tracking target in the falling state, updating the falling event in the monitoring system into an abnormal falling event.
In this embodiment, the local point cloud data is processed, so that whether other tracking targets exist around the corresponding tracking target, that is, whether other resident people exist around the falling person, can be analyzed, and if so, the situation that further injury or danger exists to the resident people is possibly indicated.
The behavior is identified based on the local point cloud data to determine whether surrounding people have limb contact with the falling tracking target, if there is a possibility that the falling tracking target is continuously injured, the emergency of the event needs to be improved, namely, the falling event is updated to be an abnormal falling event, so that the important attention of a supervision system is brought to. At this time, a preset third voice may be outputted using the voice model shown in the above embodiment to warn the person who is doing injury.
Corresponding to the anti-spoofing early warning method for the smart campus in the above embodiment, fig. 6 shows a block diagram of a structure of the anti-spoofing early warning device for the smart campus provided in the sixth embodiment of the present application, where the anti-spoofing early warning device is applied to the server or the sensing device in fig. 1, where the sensing device may integrate sensors for sensing such as radar, sound collector, temperature sensor, smoke sensor, etc. to implement sensing of multidimensional data, so as to implement multidimensional supervision. For convenience of explanation, only portions relevant to the embodiments of the present application are shown.
Referring to fig. 6, the anti-spoofing early warning device includes:
the data preprocessing module 61 is configured to perform target recognition on all point cloud data obtained by using radar measurement in the acquired target scene, obtain each tracking target, and determine a maximum value list and a minimum value list corresponding to the height of the data points from an array formed by the data points of each tracking target;
The data inserting module 62 is configured to acquire new data points at the current time, and determine an inserting position of each new data point in the maximum value list according to the height of the new data point and the maximum value list and the minimum value list;
a data calculation module 63, configured to insert a new data point into the maximum value list based on the insertion position, obtain an updated maximum value list, and calculate, based on the updated maximum value list, a current height of the tracking target at the current time;
The first supervision module 64 is configured to obtain a historical height of each tracking target at a historical moment, calculate a change rate of the current height compared with the historical height according to the historical height and the current height, detect whether the change rate is greater than a threshold, and if the change rate is greater than the threshold, determine that the corresponding tracking target is in a falling state, so as to generate a falling event for anti-theft early warning.
Optionally, the anti-spoofing early warning device further includes:
the sound data acquisition module is used for acquiring sound data acquired in a predicted time interval before and after the current moment;
the keyword detection module is used for detecting whether preset keywords exist in the sound data;
The duration detection module is used for counting the duration of each tracking target in the falling state if the preset keyword exists in the sound data after the corresponding tracking target is determined to be in the falling state, and detecting whether the duration is larger than a first time threshold;
The falling event generation module is used for generating a falling event aiming at any tracking target if the duration is detected to be larger than a first time threshold value, and sending the falling event to the supervision system for supervision.
Optionally, the anti-spoofing early warning device further includes:
the model analysis module is used for inputting the sound data into a pre-trained voice analysis model after acquiring the sound data acquired in the prediction time interval before and after the current moment, and outputting a first result and the confidence coefficient thereof for representing the occurrence of the deception semantics, a second result and the confidence coefficient thereof for representing the occurrence of the sharp sounds, and a third result and the confidence coefficient thereof for representing the occurrence of the falling ground sounds;
The weight analysis module is used for carrying out normalization processing on the confidence coefficient of the first result, the confidence coefficient of the second result and the confidence coefficient of the third result after generating a falling event aiming at the tracking target, so as to obtain the weight for representing the first result, the weight for representing the second result and the weight for representing the third result;
and the spoofing state evaluation module is used for calculating and obtaining a spoofing state score of the sound data according to the first result and the weight thereof, the second result and the weight thereof, and the third result and the weight thereof, and transmitting the spoofing state score to the supervision system when the falling event is transmitted to the supervision system for supervision.
Optionally, the data preprocessing module 61 includes:
The information extraction unit is used for extracting angle information and distance information of any data point aiming at an array formed by the data points of any tracking target;
The height calculation unit is used for acquiring the installation height of the radar, calculating the height of the corresponding data point according to the installation height, the angle information and the distance information, traversing all the data points and obtaining the height of each data point;
The effective value judging unit is used for judging the effectiveness of the heights of all the data points to obtain a judging result, and calculating the maximum value and the minimum value of the corresponding array according to the data points with the effective heights as the judging result;
And the list generation unit is used for respectively sequencing the maximum value and the minimum value corresponding to the array of radar measurement in the continuous first preset time period to obtain a maximum value list and a minimum value list.
Optionally, the data calculation module 63 includes:
the average calculation unit is used for carrying out average calculation on all maximum values in the updated maximum value list to obtain an average calculation result;
And the current height determining unit is used for determining the average result as the current height of the corresponding tracking target at the current moment.
Optionally, the anti-spoofing early warning device further includes:
The fine detection module is used for carrying out target recognition on point cloud data obtained by radar measurement in an acquired target scene to obtain each tracking target, and detecting whether N or more tracking targets exist in a preset range;
The aggregation state determining module is used for determining that the personnel aggregation state exists in the target scene if N or more tracking targets exist in the preset range;
And the second supervision module is used for executing the maximum value list and the minimum value list which are corresponding to the height of the data points and are determined from the array formed by the data points of each tracking target when the duration of the personnel aggregation state in the target scene is greater than a second time threshold, generating personnel aggregation events, and sending the personnel aggregation events to the supervision system for supervision.
Optionally, the anti-spoofing early warning device further includes:
The local data extraction module is used for extracting local point cloud data in a preset space around the tracking target in a second preset time period after determining that the corresponding tracking target is in a falling state, wherein the starting time of the second preset time period is the corresponding time when the corresponding tracking target is determined to be in the falling state;
The abnormal judgment module is used for carrying out behavior recognition on the local point cloud data to obtain a behavior recognition result, and if the behavior recognition result indicates that limb contact exists between the local point cloud data and a tracking target in a falling state, the falling event in the monitoring system is updated to be an abnormal falling event.
It should be noted that, because the content of information interaction and execution process between the modules and the embodiment of the method of the present application are based on the same concept, specific functions and technical effects thereof may be referred to in the method embodiment section, and details thereof are not repeated herein.
Fig. 7 is a schematic structural diagram of a computer device according to a seventh embodiment of the present application. As shown in fig. 7, the computer device of this embodiment includes: at least one processor (only one shown in fig. 7), a memory, and a computer program stored in the memory and executable on the at least one processor, the processor executing the computer program implementing the steps of any of the various embodiments of the anti-spoofing early warning method for smart campus described above.
The computer device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that fig. 7 is merely an example of a computer device and is not intended to be limiting, and that a computer device may include more or fewer components than shown, or may combine certain components, or different components, such as may also include a network interface, a display screen, an input device, and the like.
The Processor may be a CPU, but may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL processors, DSPs), application SPECIFIC INTEGRATED Circuits (ASICs), off-the-shelf Programmable gate arrays (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory includes a readable storage medium, an internal memory, etc., where the internal memory may be the memory of the computer device, the internal memory providing an environment for the execution of an operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be a hard disk of a computer device, and in other embodiments may be an external storage device of a computer device, for example, a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), etc. that are provided on a computer device. Further, the memory may also include both internal storage units and external storage devices of the computer device. The memory is used to store an operating system, application programs, boot loader (BootLoader), data, and other programs such as program codes of computer programs, and the like. The memory may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above device may refer to the corresponding process in the foregoing method embodiment, which is not described herein again. The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the method of the above-described embodiment, and may be implemented by a computer program to instruct related hardware, and the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of the method embodiment described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code, a recording medium, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. Such as a U-disk, removable hard disk, magnetic or optical disk, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The present application may also be implemented as a computer program product for implementing all or part of the steps of the method embodiments described above, when the computer program product is run on a computer device, causing the computer device to execute the steps of the method embodiments described above.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided by the present application, it should be understood that the disclosed apparatus/computer device and method may be implemented in other manners. For example, the apparatus/computer device embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (8)
1. The anti-spoofing early warning method for the intelligent campus is characterized by comprising the following steps of:
Performing target recognition on all point cloud data obtained by radar measurement in an acquired target scene to obtain each tracking target, and determining a maximum value list and a minimum value list corresponding to the height of the data points from an array formed by the data points of each tracking target;
Acquiring new data points at the current moment, and determining the insertion position of each new data point in the maximum value list according to the height of the new data point, the maximum value list and the minimum value list;
Inserting the new data points into the maximum value list based on the insertion positions to obtain an updated maximum value list, and calculating to obtain the current height of the corresponding tracking target at the current moment based on the updated maximum value list;
Acquiring the historical height of each tracking target at the historical moment, calculating the change rate of the current height compared with the historical height according to the historical height and the current height, detecting whether the change rate is larger than a threshold value, and if the change rate is larger than the threshold value, determining that the corresponding tracking target is in a falling state so as to generate a falling event for anti-theft early warning;
The determining a maximum value list and a minimum value list corresponding to the height of the data points from the array formed by the data points of each tracking target comprises the following steps:
extracting angle information and distance information of any data point aiming at an array formed by the data points of any tracking target;
Acquiring the installation height of the radar, calculating to obtain the height of a corresponding data point according to the installation height, the angle information and the distance information, and traversing all the data points to obtain the height of each data point;
Carrying out validity judgment on the heights of all data points to obtain a judgment result, and calculating to obtain a maximum value and a minimum value corresponding to the array according to the data points with the valid heights of the judgment result;
Respectively sequencing maximum values and minimum values corresponding to the arrays of radar measurement in a continuous first preset time period to obtain a maximum value list and a minimum value list;
The step of calculating the current height of the corresponding tracking target at the current moment based on the updated maximum value list, including:
Averaging all maximum values in the updated maximum value list to obtain an averaging result;
and determining the average result as the current height of the corresponding tracking target at the current moment.
2. The method of claim 1, further comprising:
acquiring sound data acquired in a predicted time interval before and after the current moment;
After the determining that the corresponding tracking target is in the falling state, the method further comprises:
detecting whether a preset keyword exists in the sound data;
if the preset keywords exist in the sound data, counting the duration time of each tracking target in a falling state, and detecting whether the duration time is larger than a first time threshold;
and for any tracking target, if the duration is detected to be greater than the first time threshold, generating a falling event for the tracking target, and sending the falling event to a supervision system for supervision.
3. The method of claim 2, further comprising, after said acquiring sound data collected during a predicted time interval before and after said current time, the steps of:
Inputting the sound data into a pre-trained voice analysis model, and outputting a first result and the confidence coefficient thereof for representing the occurrence of the spoofing semanteme, a second result and the confidence coefficient thereof for representing the occurrence of the sharp sound, and a third result and the confidence coefficient thereof for representing the occurrence of the inverted sound;
After the generating a fall event for the tracking target, further comprising:
Normalizing the confidence coefficient of the first result, the confidence coefficient of the second result and the confidence coefficient of the third result to obtain a weight for representing the first result, a weight for representing the second result and a weight for representing the third result;
And calculating according to the first result and the weight thereof, the second result and the weight thereof, and the third result and the weight thereof, obtaining the score of the sound data in the condition of the deception, and sending the score of the deception to a supervision system when the falling event is sent to the supervision system for supervision.
4. The method for anti-spoofing and early warning according to claim 1, wherein, after performing target recognition on the point cloud data obtained by radar measurement in the obtained target scene to obtain each tracking target, further comprising:
Detecting whether N or more tracking targets exist in a preset range, wherein N is an integer greater than 1;
If N or more tracking targets are detected to exist in the preset range, determining that a person aggregation state exists in the target scene;
And when the duration time of the personnel aggregation state in the target scene is greater than a second time threshold value, executing the maximum value list and the minimum value list which are determined from the array formed by the data points of each tracking target and correspond to the height of the data points, generating personnel aggregation events, and sending the personnel aggregation events to a supervision system for supervision.
5. The method for anti-spoofing alert according to any one of claims 1 to 4, further comprising, after the determining that the corresponding tracking target is in a fall state:
Extracting local point cloud data in a preset space around the tracking target in a second preset time period, wherein the starting time of the second preset time period is the corresponding time when the corresponding tracking target is determined to be in a falling state;
And carrying out behavior recognition on the local point cloud data to obtain a behavior recognition result, and if the behavior recognition result indicates that limb contact exists with the falling state tracking target, updating the falling event in the monitoring system into an abnormal falling event.
6. A prevent anti-spoofing early warning device for wisdom campus, its characterized in that, prevent that anti-spoofing early warning device includes:
The data preprocessing module is used for carrying out target recognition on all point cloud data obtained by radar measurement in an acquired target scene to obtain each tracking target, and determining a maximum value list and a minimum value list corresponding to the height of the data points from an array formed by the data points of each tracking target;
The data insertion module is used for acquiring new data points at the current moment and determining the insertion position of each new data point in the maximum value list according to the height of the new data points, the maximum value list and the minimum value list;
The data calculation module is used for inserting the new data points into the maximum value list based on the insertion position to obtain an updated maximum value list, and calculating the current height of the corresponding tracking target at the current moment based on the updated maximum value list;
The first supervision module is used for acquiring the historical height of each tracking target at the historical moment, calculating the change rate of the current height compared with the historical height according to the historical height and the current height, detecting whether the change rate is greater than a threshold value, and if the change rate is greater than the threshold value, determining that the corresponding tracking target is in a falling state so as to generate a falling event for anti-slushing early warning;
the data preprocessing module comprises:
The information extraction unit is used for extracting angle information and distance information of any data point aiming at an array formed by the data points of any tracking target;
The height calculation unit is used for acquiring the installation height of the radar, calculating the height of the corresponding data point according to the installation height, the angle information and the distance information, traversing all the data points and obtaining the height of each data point;
The effective value judging unit is used for judging the effectiveness of the heights of all the data points to obtain a judging result, and calculating the maximum value and the minimum value of the corresponding array according to the data points with the effective heights as the judging result;
The list generation unit is used for respectively sequencing the maximum value and the minimum value corresponding to the array of radar measurement in the continuous first preset time period to obtain a maximum value list and a minimum value list;
the data calculation module includes:
the average calculation unit is used for carrying out average calculation on all maximum values in the updated maximum value list to obtain an average calculation result;
And the current height determining unit is used for determining the average result as the current height of the corresponding tracking target at the current moment.
7. A computer device comprising a processor, a memory and a computer program stored in the memory and executable on the processor, the processor implementing the anti-spoofing method as claimed in any one of claims 1 to 5 when the computer program is executed by the processor.
8. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the anti-spoofing method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410452397.1A CN118053261B (en) | 2024-04-16 | 2024-04-16 | Anti-spoofing early warning method, device, equipment and medium for smart campus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410452397.1A CN118053261B (en) | 2024-04-16 | 2024-04-16 | Anti-spoofing early warning method, device, equipment and medium for smart campus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118053261A CN118053261A (en) | 2024-05-17 |
| CN118053261B true CN118053261B (en) | 2024-06-25 |
Family
ID=91053848
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410452397.1A Active CN118053261B (en) | 2024-04-16 | 2024-04-16 | Anti-spoofing early warning method, device, equipment and medium for smart campus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118053261B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118262475B (en) * | 2024-05-30 | 2024-08-27 | 河北雄安亿晶云科技有限公司 | AI intelligent sound wave auxiliary campus anti-cheating system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205661A (en) * | 2021-04-30 | 2021-08-03 | 广东艾檬电子科技有限公司 | Anti-cheating implementation method and system, intelligent wearable device and storage medium |
| CN114821422A (en) * | 2022-04-24 | 2022-07-29 | 橙安(广东)信息技术有限公司 | Intelligent campus monitoring system and method for prejudging campus overlord |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20240093846A (en) * | 2021-10-24 | 2024-06-24 | 로직마크, 인크. | System and method for fall detection using multiple sensors including barometric or barometric pressure sensors |
| CN115273845A (en) * | 2022-07-27 | 2022-11-01 | 西安西古光通信有限公司 | Visual anti-cheating system, system operation method, device and medium |
-
2024
- 2024-04-16 CN CN202410452397.1A patent/CN118053261B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205661A (en) * | 2021-04-30 | 2021-08-03 | 广东艾檬电子科技有限公司 | Anti-cheating implementation method and system, intelligent wearable device and storage medium |
| CN114821422A (en) * | 2022-04-24 | 2022-07-29 | 橙安(广东)信息技术有限公司 | Intelligent campus monitoring system and method for prejudging campus overlord |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118053261A (en) | 2024-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2010141117A2 (en) | System and method for predicting abnormal behavior | |
| CN111126153B (en) | Safety monitoring method, system, server and storage medium based on deep learning | |
| CN118053261B (en) | Anti-spoofing early warning method, device, equipment and medium for smart campus | |
| CN114235050A (en) | Marine environment monitoring and early warning method, device and system | |
| CN117671887B (en) | Intelligent security early warning management method and system based on big data | |
| CN111291596A (en) | Early warning method and device based on face recognition | |
| CN112464951A (en) | Fishery safety emergency disposal system and method based on Internet of things | |
| CN113314230A (en) | Intelligent epidemic prevention method, device, equipment and storage medium based on big data | |
| US11449567B2 (en) | Method and apparatus for detecting regional event based on search engine, and storage medium | |
| CN117784124A (en) | Millimeter wave radar falling monitoring method and device in multi-person scene | |
| CN116778657A (en) | Method and system for intelligently identifying intrusion behavior | |
| CN110852517B (en) | Abnormal behavior early warning method and device, data processing equipment and storage medium | |
| CN118747607B (en) | AI-based campus student risk early warning method and system | |
| CN114758457B (en) | Intelligent monitoring method and device for illegal operation among banknote adding | |
| CN118262475B (en) | AI intelligent sound wave auxiliary campus anti-cheating system | |
| CN118298384B (en) | Intelligent security monitoring method and system based on 5G network | |
| CN118042418B (en) | Intelligent supervision processing system for safe travel of old people based on mobile terminal | |
| CN114694848B (en) | Electronic information acquisition system for epidemic situation prevention and control | |
| CN118887725A (en) | Behavior monitoring method and device, electronic equipment and storage medium | |
| CN115378738A (en) | Alarm filtering method, system and equipment based on classification algorithm | |
| CN116137038A (en) | Method, device, computer equipment and medium for detecting oil leakage | |
| CN116807455A (en) | Bathroom falling detection method and device based on Doppler and radar | |
| CN116652396A (en) | Safety early warning method and system for laser inner carving machine | |
| CN117082217A (en) | Intelligent video monitoring system based on Jetson platform | |
| CN118886699A (en) | Model system for carrying out dynamic risk assessment on public safety based on algorithm model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |