Disclosure of Invention
The utility model provides a people flow alarming method, device, electronic equipment and storage medium, it can be through periodically detecting the people flow of camera monitoring area to when the people flow of every moment all satisfies the preset condition in the preset alarm period, push the warning suggestion, improved the accuracy of detection.
In order to achieve the above object, the technical scheme adopted by the embodiment of the invention is as follows:
In a first aspect, an embodiment of the present invention provides a traffic alert method, which is applied to an electronic device, where the electronic device communicates with a camera; the method comprises the following steps:
receiving people flow data sent by the camera in real time, wherein the people flow data represents the people flow of a monitoring area of the camera at the current moment;
according to the people flow data sent in real time, carrying out people flow detection and alarm on a preset alarm area according to a preset alarm period;
determining a first starting time and a first ending time of the ith preset alarm period aiming at the ith preset alarm period; the difference value between the first ending time and the first starting time is the alarm duration of the preset alarm period;
judging whether the people flow in the preset alarm area meets preset alarm conditions from the first starting time to the first ending time, and pushing alarm prompts when the preset alarm conditions are met, wherein the preset alarm conditions represent that the people flow at each time in the ith preset alarm period meets preset conditions.
In a possible implementation manner, the electronic device stores the traffic of each historical moment in advance, and the traffic of each historical moment is generated according to traffic data sent by the camera in real time before a preset detection moment, wherein the preset detection moment is the moment when a detection instruction of a user is received;
The step of determining the first starting time and the first ending time of the ith preset alarm period comprises the following steps:
if i is equal to 1, acquiring the people flow at each historical moment in the preset alarm period before the preset detection moment to obtain a plurality of initial people flows;
judging whether each initial people flow meets the preset conditions or not;
if yes, taking the preset detection time as the first starting time;
if not, obtaining each target people flow which does not meet the preset conditions, determining the maximum moment from the historical moment corresponding to each target people flow, and taking the maximum moment as the first starting moment;
if i is greater than 1, taking the first ending moment of the i-1 th preset alarm period as the first starting moment;
and superposing the alarm time length of the preset alarm period on the basis of the first starting time to obtain the first ending time.
In one possible implementation manner, the step of determining whether the people flow in the preset alarm area meets a preset alarm condition from the first starting time to the first ending time, and pushing an alarm prompt when the preset alarm condition is met, includes:
Detecting the people flow of the monitoring area according to a preset detection period from the first starting time to the first ending time, wherein the detection duration of the preset detection period is smaller than or equal to the alarm duration;
determining the detection starting time and the detection ending time of the mth preset detection period; if i is equal to 1 and m is equal to 1, the detection starting time is the preset detection time; if i is greater than 1 and m is equal to 1, the detection starting time is the pushing time of the alarm prompt of the i-1 th preset alarm period; if i is greater than or equal to 1 and m is greater than 1, the detection starting time is the detection ending time of the m-1 th preset detection period;
when the detection end time is reached, determining the people flow at each time in the preset detection period according to the people flow data sent by each camera in real time, wherein the people flow represents the people flow of the preset alarm area at the current time;
judging whether the people flow at each moment in the mth preset detection period meets the preset conditions or not;
if yes, acquiring the detection ending time of the mth preset detection period;
And determining the pushing moment of the alarm prompt according to the detection ending moment of the mth preset detection period and the first ending moment, and pushing the alarm prompt at the pushing moment.
In one possible implementation manner, after the step of determining whether the traffic of people at each moment in the preset detection period meets the preset condition, the method further includes:
if the people flow in at least one moment in the mth preset detection period does not meet the preset condition, determining the maximum moment from all the moments corresponding to the people flow which does not meet the preset condition, taking the maximum moment as a second starting moment, and superposing the alarm duration on the basis of the second starting moment to obtain a second ending moment;
and taking the second starting time as a first starting time after the i-th preset alarm period is updated, taking the second ending time as a first ending time after the i-th preset alarm period is updated, taking the detection ending time as a detection starting time after the m-th preset detection period is updated, and returning to the step of executing the step of judging whether the people flow at each time in the m-th preset detection period meets the preset condition or not until the people flow at each time in the m-th preset detection period meets the preset condition, and acquiring the detection ending time of the m-th preset detection period.
In a possible implementation manner, the step of determining the pushing time of the alarm prompt according to the detection ending time and the first ending time includes:
comparing the detection ending time of the mth preset detection period with the first ending time;
if the detection ending time of the mth preset detection period is greater than or equal to the first ending time, the detection ending time is used as the pushing time of the alarm prompt;
if the detection ending time of the mth preset detection period is smaller than the first ending time, assigning m+1 to m, and returning to the step of determining the detection starting time of the mth preset detection period until the detection ending time of the mth preset detection period is larger than or equal to the first ending time, and taking the detection ending time as the pushing time of the alarm prompt.
In one possible embodiment, the number of the cameras is at least one, and the monitoring areas of each camera do not overlap; the step of determining the people flow at each moment in the preset detection period according to the people flow data sent by each camera in real time comprises the following steps:
Judging whether each camera sends the people flow data at the current moment or not according to each moment in the preset detection period;
if yes, summing the people flow data to obtain the people flow at the current moment;
if not, determining each target camera which does not send the people flow data, and taking the people flow data sent at the previous moment as the people flow data at the current moment for each target camera; summing the people flow data of each camera at the current moment to obtain the people flow at the current moment;
and obtaining the people flow at each moment in the preset detection period.
In one possible embodiment, the preset alert condition includes at least one of the following;
the people flow at each moment in the ith preset alarm period is a first preset value;
and the flow rate of people at each moment in the ith preset alarm period is not the second preset value;
and the people flow at each moment in the ith preset alarm period is smaller than a preset upper limit value;
and the people flow at each moment in the ith preset alarm period is larger than a preset lower limit value.
In a second aspect, the embodiment of the invention also provides a people flow alarming device, which is applied to electronic equipment, wherein the electronic equipment is communicated with a camera; the device comprises:
the receiving module is used for receiving the people flow data sent by the camera in real time and generating the people flow at the current moment in real time, wherein the people flow data represents the people flow of the monitoring area of the camera at the current moment, and the people flow represents the people flow of the preset alarm area at the current moment;
the detection module is used for:
according to the real-time generated people flow, carrying out people flow detection and alarm on the preset alarm area according to a preset alarm period;
determining a first starting time and a first ending time of the ith preset alarm period aiming at the ith preset alarm period; the difference value between the first ending time and the first starting time is the alarm duration of the preset alarm period;
and the alarm module is used for judging whether the people flow in the preset alarm area meets the preset alarm condition from the first starting moment to the first ending moment, and pushing an alarm prompt when the preset alarm condition is met, wherein the preset alarm condition characterizes that the people flow at each moment in the ith preset alarm period meets the preset condition.
In a third aspect, an embodiment of the present invention further provides an electronic device, including:
one or more processors;
and a memory for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the people flow alerting method described above.
In a fourth aspect, an embodiment of the present invention further provides a computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the above-mentioned people flow alert method.
Compared with the prior art, the embodiment of the invention provides a people flow alarming method, a device, electronic equipment and a storage medium. Firstly, receiving people flow data sent by a camera in real time; then, according to the traffic data sent in real time, detecting and alarming the traffic of the preset alarming area according to the preset alarming period; determining a first starting time and a first ending time of the ith preset alarm period according to the ith preset alarm period; and finally, judging whether the flow of people in the preset alarm area meets the preset alarm condition or not at each moment from the first starting moment to the first ending moment, and pushing an alarm prompt when the flow of people in the preset alarm area meets the preset alarm condition. According to the method, the people flow in the monitoring area of the camera is detected periodically, and when the people flow at each moment in the preset alarm period meets the preset condition, the alarm prompt is pushed, so that the detection accuracy is improved.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
Furthermore, the terms "first," "second," and the like, if any, are used merely for distinguishing between descriptions and not for indicating or implying a relative importance.
It should be noted that the features of the embodiments of the present invention may be combined with each other without conflict.
In order to ensure public safety in production and life, for some specific places, the flow of people in the places is often required to be limited.
In the prior art, the position information can be acquired based on the data of the mobile device of the user, so that the real-time statistics of the people flow is realized, and whether the increasing speed of the people flow in the preset time period exceeds a preset threshold value is judged to determine whether to perform people flow alarming.
However, although the method for acquiring the traffic based on the data of the mobile device of the user has high real-time performance, more or less statistical errors exist, and the errors are mainly caused by factors such as the lack of the mobile device, the disappearance of signals, the shortage of the electric quantity of the mobile device and the like. Moreover, the method is only suitable for alarming the upper limit and the lower limit of the people flow, and is not suitable for the situation that the number of people is required to have higher accuracy.
Aiming at the problems, the implementation provides a people flow alarming method, which generates people flow at each moment according to people flow data sent by a camera in real time, detects whether the people flow in each preset alarming period of the people flow meets alarming conditions, pushes alarming prompts when the people flow at each moment in the preset alarming period meets the preset conditions, and further improves the accuracy of people flow alarming.
Referring to fig. 1, fig. 1 shows an application scenario schematic diagram of a traffic alert method provided in this embodiment. At least one camera is arranged in the area A, each camera has a corresponding monitoring area, and each monitoring area is not overlapped.
The cameras are used to collect traffic data of the monitored area and may include statistical snapshot cameras and in-out mode snapshot cameras. The statistical snapshot camera can directly analyze the traffic of people in the monitoring range of the current moment through a target detection algorithm deployed in the camera, and the in-out mode snapshot camera can calculate the traffic of people in the monitoring range of the current moment according to the traffic of people entering the monitoring range and the traffic of people leaving the monitoring range of the current moment, which are acquired at each moment.
Because the monitoring range of each camera is different, the people flow obtained by each camera at the current moment can be summed to approximately obtain the people flow at the current moment of the area A.
Although a plurality of cameras are installed in the area a, the area to be monitored of each camera has a small coverage area ratio for the whole area a, and the acquired traffic flow of the monitored area has a certain error compared with the actual traffic flow of the area a. In order to reduce errors, when the cameras are controlled, some important monitoring areas, such as an operation table of a factory, a waiting table of a station, a square, a scenic spot viewing table and the like, have certain requirements on the flow of people, and no monitoring points are needed for common pedestrian roads and the like.
The cameras in fig. 1 all communicate with the electronic device 100, and the electronic device 100 receives the traffic data sent by each camera in real time and carries out alarm prompt according to the traffic data.
Referring to fig. 2, fig. 2 is a block diagram illustrating an electronic device 100 according to the present embodiment, and the electronic device 100 may be, but is not limited to, a mobile phone, a tablet computer, a notebook computer, a server, or other electronic devices with processing capability. The electronic device 100 includes a memory 101, a processor 102, and a bus 103. The memory 101 and the processor 102 are connected via a bus 103, such as a disk, ROM, or RAM, or any combination thereof. By way of example, the computer platform may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The method of the present invention may be implemented in accordance with these program instructions.
The memory 101 is used to store programs such as the people flow alert device 200. The traffic alert device 200 includes at least one software function module stored in the memory 101 in the form of software or firmware (firmware), and the processor 102 executes the program to implement the traffic alert method in this embodiment after receiving the execution instruction.
The Memory 101 may be, but is not limited to, a random access Memory (Random Access Memory, RAM), a Read Only Memory (ROM), a programmable Read Only Memory (Programmable Read-OnlyMemory, PROM), an erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), an electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.
The processor 102 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the traffic alert method in this embodiment may be performed by hardware integrated logic or software instructions in the processor 102. The processor 102 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a micro control unit (Microcontroller Unit, MCU), a complex programmable logic device (Complex Programmable Logic Device, CPLD), a field programmable gate array (Field Programmable Gate Array, FPGA), an embedded ARM, and the like.
For ease of illustration, only one processor is depicted in the electronic device 100. It should be noted, however, that the electronic device 100 of the present invention may also include a plurality of processors, and thus steps performed by one processor described in the present invention may also be performed jointly by a plurality of processors or separately. For example, if the processor of the electronic device 100 performs step a and step B, it should be understood that step a and step B may also be performed by two different processors together or performed separately in one processor. For example, the first processor performs step a, the second processor performs step B, or the first processor and the second processor together perform steps a and B.
On the basis of the above, the people flow alarming method provided by the embodiment is described, and the method is applied to the electronic device 100, and the electronic device 100 and the camera communicate. Referring to fig. 3, fig. 3 shows a flow chart of a traffic alert method according to the present embodiment, and the method includes the following steps S110 to S140.
S110, receiving the people flow data sent by the camera in real time, wherein the people flow data represents the people flow of the monitoring area of the camera at the current moment.
In this embodiment, there are a plurality of cameras, and the traffic data sent by each camera characterizes the traffic of the monitored area of the camera at the current moment, for example, the monitored area of the camera 2 in fig. 1 is a sector area in the figure, and the corresponding traffic data is 3.
S120, detecting and alarming the traffic of the people in the preset alarming area according to the traffic of the people generated in real time and the preset alarming period.
In this embodiment, the preset alarm period refers to an interval for detecting and alarming the traffic of the preset alarm area, the preset alarm period has a corresponding alarm duration, the alarm duration refers to a duration for detecting the traffic of the preset alarm area, for example, from the current moment, the traffic of the preset alarm area in 10 seconds is detected every 10 seconds, then the nth 10 seconds is the nth preset alarm period, and the 10 seconds is the alarm duration.
The preset alarm area is an area where people flow needs to be alarmed, for example, an area a in fig. 1.
S130, determining a first starting time and a first ending time of an ith preset alarm period aiming at the ith preset alarm period; the difference between the first ending time and the first starting time is the alarm duration of the preset alarm period.
In this embodiment, if i is equal to 1, determining a first starting time according to a preset detection time, where the preset detection time is a time when a detection instruction of a user is received; if i is greater than 1, the first ending time of the i-1 th preset alarm period is used as the first starting time of the i-1 th preset alarm period.
When a detection instruction of a user is received, since there is a traffic volume at a historical time before a preset detection time, a first starting time of a first preset alarm period needs to be determined according to the traffic volume at the historical time.
S140, judging whether the people flow in the preset alarm area meets the preset alarm condition from the first starting time to the first ending time, and pushing an alarm prompt when the preset alarm condition is met, wherein the preset alarm condition represents that the people flow in each moment in the ith preset alarm period meets the preset condition.
In this embodiment, if the traffic of people at least at one time in the ith preset alarm period does not meet the preset condition, the first starting time and the first ending time of the ith preset alarm period are determined again, and until the traffic of people at each time in the ith preset alarm period meets the preset condition, the alarm prompt is pushed.
For example, the alarm time length is 10 seconds, the number of people in the preset alarm area is required to be fixed to 2 people, the preset condition is that the number of people at each moment in the ith preset alarm period is 2 people, and if the alarm prompt can be received by the user every 10 seconds, the number of people in the preset alarm area is required to meet the requirement.
Compared with the prior art, the people flow alarming method provided by the embodiment periodically detects the people flow of the camera monitoring area according to the people flow data sent by the camera in real time, and pushes alarming prompt when the people flow at each moment in the preset alarming period meets the preset condition. Because the people flow data are acquired in real time through the camera, the real-time performance is higher and the error is smaller; and moreover, detection is carried out at each moment in a preset alarm period, and when the flow of people at each moment meets preset conditions, alarm prompts are pushed, so that the detection accuracy is improved.
Optionally, the preset alert condition may include at least one of the following;
the people flow at each moment in the ith preset alarm period is a first preset value;
and the flow of people at each moment in the ith preset alarm period is not a second preset value;
and the people flow at each moment in the ith preset alarm period is smaller than a preset upper limit value;
and the people flow at each moment in the ith preset alarm period is larger than a preset lower limit value.
In this embodiment, the alarm that the first preset value is the fixed number of people is set as the people flow at each moment in the ith preset alarm period can be applied to some factories, whether the number of people in workshops or operation tables always meets the specified number of people is monitored through a camera, if yes, an alarm prompt is pushed, and adjustment can be made according to the time interval of pushing the alarm prompt so as to avoid risks.
If the first preset value is 0, the alarm is unmanned, the alarm can be generated when the monitoring center is not in security guard, and for some large-scale electric field areas, the push alarm is detected by no person, so that the power utilization can be controlled to be started or closed, and energy conservation is realized.
The fact that the flow of people at each moment in the ith preset alarm period is not the second preset value is not the planned inconsistent alarm, the method can be used for bank vault scenes, the number of people is appointed during money transportation, and the alarm is carried out if the number of people does not accord with the second preset value.
The people flow at each moment in the ith preset alarm period is smaller than the preset upper limit value and is equal to the number of people exceeding the upper limit value, so that the alarm device can be used in scenes such as squares, scenic spots and the like, and the trampling event caused by crowd gathering is avoided.
The alarm when the people flow is larger than the preset lower limit value and is lower than the lower limit value in the ith preset alarm period can be used in high-safety or high-risk areas such as vaults, prisons and the like.
The above alarm types can be combined for use, for example, a certain operation platform needs to ensure that two people are present at the same time, a first preset value can be set to 2, a second preset value is set to 2, the alarm duration is set to 10 seconds, if the push of the alarm of the number of people with fixed alarms can be received every 10 seconds, but no push of the alarm which is not coincident is planned, the operation is normally performed.
Optionally, before receiving the detection instruction of the user, that is, before the preset detection time, the electronic device 100 is in a state of receiving the traffic data sent by the camera in real time, and generating the traffic at each historical time according to the traffic data, so that the electronic device stores the traffic at each historical time in advance.
Accordingly, the first start time and the first end time of the first preset detection period may be determined as follows.
The method comprises the steps of firstly, obtaining the people flow at each historical moment in a preset alarm period before a preset detection moment, and obtaining a plurality of initial people flows.
And secondly, judging whether each initial people flow meets the preset condition.
And thirdly, if yes, taking the preset detection time as a first starting time.
And step four, if not, obtaining each target people flow which does not meet the preset condition, determining the maximum moment from the historical moment corresponding to each target people flow, and taking the maximum moment as the first starting moment.
In this embodiment, for ease of understanding, please refer to fig. 4, fig. 4 shows a detection timing chart of nodes at each time, where one node corresponds to one time, dura is an alarm duration, node 1 is a history initial time, i.e. a history time corresponding to the traffic volume obtained by the electronic device earliest, and it is assumed that node 1 is smaller than node 2.
Assuming that the node 4 is a preset detection time, the previous preset alarm period is from the node 2 to the node 4, and the people flow at each historical time in the nodes 2 to 4 is obtained to obtain a plurality of initial people flows. Judging whether each initial people flow meets a preset condition or not; if yes, the previous preset alarm period is indicated to meet the preset alarm condition, and then the alarm prompt is pushed at the node 4, and the node 4 is taken as the first starting moment of the first preset alarm period.
If at least one node does not meet the preset condition, the fact that the previous preset alarm period does not meet the preset alarm condition is indicated, the alarm prompt cannot be pushed at the node 4 is indicated, the first starting moment of the first preset alarm period needs to be determined, and the moment of pushing the alarm prompt is determined according to the people flow data of each moment generated in real time after the node 4. For example, if it is detected that the traffic of the node 3 does not meet the preset condition, the node 3 is taken as the first starting time of the first preset alarm period.
Because each alarm period after the first preset alarm period is judged according to the current time of people flow generated in real time, if i is greater than 1, the first ending time of the i-1 th preset alarm period is taken as the first starting time.
It should be noted that, the first start time and the first end time of each preset alarm period are not predetermined at one time, but are determined after the completion of the detection of the previous preset alarm period and the pushing of the alarm prompt.
And finally, superposing the alarm time length of the preset alarm period on the basis of the first starting time to obtain the first ending time.
Optionally, for the ith preset alarm period, after the first starting time and the first ending time are determined, ideally, the people flow at the current time is detected in real time, and when the detected people flow at each time meets the preset condition at the first ending time, the method for pushing the alarm is highest in instantaneity and accuracy. However, this algorithm places high demands on the performance of the electronic device and does not require detection every second since the camera does not send traffic data every second.
Therefore, the people flow at each moment in the preset alarm period can be periodically detected, so that the detection efficiency is high, and the detection accuracy is also high.
Thus, referring to fig. 5 on the basis of fig. 3, step S140 may include the following sub-steps S1401-S1406.
S1401, detecting the flow of people in the monitoring area according to a preset detection period from the first starting time to the first ending time, wherein the detection duration of the preset detection period is smaller than or equal to the alarm duration.
In this embodiment, in order to reduce the time delay of pushing the alarm prompt, the detection duration of the preset detection period may be obtained according to the following formula.
Freq＝min(median(fCam1 ,fCam2 ,…,fCam),Dura)
Wherein Freq is the detection duration, fCap1 ,fCam2 … fCamn is the period of sender traffic data of n cameras, media is the operation of taking the median, dura is the alarm duration of the preset alarm period.
From the above, it can be seen that the detection duration is less than or equal to the alarm duration, because if the detection duration is greater than the alarm duration, a situation that the traffic in the preset alarm period already meets the preset alarm condition, but the traffic at each moment in the preset alarm period is not detected yet, the time delay of pushing the alarm prompt will become large.
S1402, determining the detection start time and the detection end time of the mth preset detection period.
In this embodiment, if i is equal to 1 and m is equal to 1, the detection start time is a preset detection time; if i is greater than 1 and m is equal to 1, detecting the pushing moment of the alarm prompt of the i-1 th preset alarm period as the starting moment; if i is greater than or equal to 1 and m is greater than 1, the detection starting time is the detection ending time of the (m-1) th preset detection period; the detection end time is obtained by superposing the detection duration on the basis of the detection start time.
With continued reference to fig. 4, the first preset alarm period in fig. 4 is from node 4 to node 10, and since the traffic data between nodes 4 is the traffic data at the existing historical time, no real-time acquisition is required, and the traffic data after node 4 is the traffic at the current time generated in real time, the traffic detection of the previous preset detection period is performed when the node 4 reaches the node 7 with the detection start time. If the preset condition is met, taking the node 7 as the detection starting time of the 2 nd preset detection period, and continuing the people flow detection of the next preset detection period.
If i is greater than 1, for the ith preset alarm period, since the ith-1 preset alarm period has completed detection of at least one preset detection period, the end time of the last preset detection period in the ith-1 preset alarm period is taken as the detection start time of the ith preset alarm period.
S1403, when the detection end time is reached, determining the people flow at each time in a preset detection period according to the people flow data sent by each camera in real time, wherein the people flow represents the people flow of a preset alarm area.
In this embodiment, the electronic device 100 determines the traffic flow at each moment in the preset detection period according to the traffic flow data sent in real time by each camera.
For example, please continue to refer to fig. 1, if the traffic data sent by the camera 1 is 1, the traffic data sent by the camera 2 is 3, the traffic data sent by the camera 3 is 4, the traffic data sent by the camera 4 is 2, and the traffic data sent by the camera 5 is 1 in a preset detection period, the generated traffic is 11, which indicates that the traffic of the area a at the time is 11.
It should be noted that, although there is a certain error between the traffic volume at a certain time generated by the electronic device 100 and the actual traffic volume at the time of the area a, the area where the camera is disposed is the key area of the area a, and the remaining areas not monitored may be areas with low requirements for traffic volume, such as entrances and exits, pedestrian roads, and the like, so the error is within an acceptable range.
S1404, judging whether the people flow at each moment in the mth preset detection period meets the preset condition.
In this embodiment, the traffic at each time in the mth preset detection period is generated in real time and stored in the electronic device, and when the end time of the mth preset detection period is reached, the traffic at each time in the mth preset detection period is detected.
S1405, if the people flow at each moment in the mth preset detection period meets the preset condition, acquiring the detection ending moment of the mth preset detection period.
S1406, determining the pushing time of the alarm prompt according to the detection end time and the first end time of the mth preset detection period, and pushing the alarm prompt at the pushing time.
With continued reference to fig. 5, following sub-step S1404, sub-steps S1407-S1408 are also included in juxtaposition with S1405-S1406.
S1407, if the traffic of people in at least one moment in the mth preset detection period does not meet the preset condition, determining the maximum moment from the corresponding moment of all the traffic of people which do not meet the preset condition, taking the maximum moment as a second starting moment, and superposing the alarm duration on the basis of the second starting moment to obtain a second ending moment.
S1408, taking the second starting time as the first starting time after the i-th preset alarm period is updated, taking the second ending time as the first ending time after the i-th preset alarm period is updated, and taking the detection ending time as the detection starting time after the m-th preset detection period is updated, and returning to the executing substep S1404 until the flow of people at each time in the m-th preset detection period meets the preset condition, and obtaining the detection ending time of the m-th preset detection period.
In this embodiment, if it is detected that the traffic of people at least at one moment does not meet the preset condition in the mth preset detection period, it is indicated that the traffic of people in the ith preset alarm period cannot meet the preset alarm condition, and the first start moment and the first end moment of the ith preset alarm period need to be determined again, and then a new round of detection is performed.
For example, please continue to refer to fig. 4, if it is detected that the traffic of the node 5 does not meet the preset condition in the 1 st preset detection period, the node 5 is taken as a second starting time, and the alarm duration is superimposed on the basis of the second starting time to obtain a second ending time. And returning to the executing substep S1404 to perform a new round of detection, wherein the second starting time is used as the first starting time of the ith preset alarm period, the second ending time is used as the first ending time of the ith preset alarm period, and the detection ending time node 7 is used as the detection starting time after the 1 st preset detection period is updated.
After finishing the detection of the traffic of the person in the mth preset detection period, it is necessary to determine whether the detection of the traffic of the person at each moment in the preset alarm period has been detected.
Thus, referring to fig. 6 on the basis of fig. 5, sub-step S1406 may include the following detailed steps S14061-S14063.
S14061, comparing the detection end time of the mth preset detection period with the first end time.
S14062, if the detection end time of the mth preset detection period is greater than or equal to the first end time, the detection end time is taken as the pushing time of the alarm prompt.
S14063, if the detection end time of the mth preset detection period is smaller than the first end time, assigning m+1 to m, and returning to the executing substep S1402 until the detection end time of the mth preset detection period is greater than or equal to the first end time, and taking the detection end time as the pushing time of the alarm prompt.
In this embodiment, when the detection of the traffic of the person in the mth preset detection period is completed and the traffic of each time in the preset detection period meets the preset condition, whether the detection end time of the preset detection period is greater than or equal to the first termination time is determined, if yes, it is indicated that the detection of the traffic of each time in the ith preset alarm period is completed and the traffic of the person reaches the preset alarm condition, and the detection end time is taken as the pushing time of the alarm prompt; if not, the detection of the people flow at each moment in the ith preset alarm period is not finished, and the detection of the next detection period is needed.
Optionally, because there are multiple cameras, each camera sends people flow data to the electronic device 100 in real time, ideally, the sending frequency of each camera is optimal for sending people flow data once per second, so that not only is the real-time performance high, but also the people flow data synchronization rate of each camera is high, and the accuracy of people flow generated by the electronic device 100 at the current moment is high.
However, due to the difference between the hardware of the different cameras and the algorithm deployed by the different cameras, the sending frequency of each camera may be different, for example, the camera 1 sends the traffic data at the current moment once every 10 seconds, and the camera 2 sends the traffic data at the current moment once every 15 seconds, so that the traffic data received by the electronic device 100 may have an asynchronous problem, and the traffic data sent by the received cameras at different moments needs to be processed to obtain the traffic at each moment.
Thus, step S1403 may include the following detailed steps.
The first step is to judge whether each camera sends the people flow data at the current moment or not according to each moment in the preset detection period.
In this embodiment, the cameras may include a statistics snapshot camera and an in-out mode snapshot camera, and for the statistics snapshot camera, the number of people in the monitoring area may be analyzed in real time through a deployed target detection algorithm to obtain people flow data at the current moment.
For the in-out mode snapshot camera, people flow data at the current moment can be obtained according to the number of people entering the monitoring area and leaving the monitoring area at each moment in a certain period.
cama ＝{[a,(Pin1 ,Pin2 ,…,Pinn ),(Pout1 ,Pout2 ,…,Poutn ),(t1 ,t2 ,…,tn )]}
cama For the data sequence acquired by the access mode snapshot camera a, pin1 ,Pin2 ,…,Pinn Respectively t1 ,t2 ,…,tn The number of persons entering the monitoring area at any time, pout1 ,Pout2 ,…,Poutn Respectively t1 ,t2 ,…,tn The number of people who walk out of the monitoring area at any time, then tn The people flow data at the moment is
And secondly, if each camera sends the people flow data at the current moment, summing the people flow data to obtain the people flow at the current moment.
Thirdly, if at least one camera does not send people flow data at the current moment, determining each target camera which does not send people flow data, and regarding the people flow data sent at the previous moment as the people flow data at the current moment for each target camera; and summing the people flow data of each camera at the current moment to obtain the people flow at the current moment.
Fourth, the people flow rate at each moment in the preset detection period is obtained.
In this embodiment, the above-described process is described below with a specific example for the sake of understanding.
If there are 2 cameras in the area a, the camera 1 transmits traffic data once every 5 seconds, and the camera 2 transmits traffic data once every 10 seconds. The preset detection period is 0 th to 10 th seconds, the people flow of each historical moment before the preset detection moment is prestored in the electronic equipment, the people flow of the second before the preset detection moment is 5, wherein the people flow data of the camera 1 in the second before the preset detection moment is 2, and the people flow data of the camera 2 in the second before the preset detection moment is 3.
When no issuing data exists in the two cameras at the 0 th second, the traffic 5 of the previous second of the preset detection time is taken as the traffic of the 0 th second, similarly, the traffic of the 1 st second to the 4 th second is 5, the traffic data sent by the camera 1 is 2, the traffic data not sent by the camera 2 is taken as the traffic data of the camera 2 at the previous time, namely, the traffic data of the camera 2 at the 5 th second is 3, and then the traffic of the area A is 6 at the 5 th second, similarly, the traffic of the area A is 6 at the 6 th second to the 9 th second.
At 10 seconds, the traffic data sent by the camera 1 is 3, and the traffic data sent by the camera 2 is 5, and the traffic of the zone a at 10 seconds is 8.
It should be noted that, in some special cases, the camera may not send people flow data until it is time to send people flow data, for example, in the above example, camera 1 does not send people flow data in any of the 0 th to 10 th seconds, at this time, if all the people flow data after the 5 th second are determined to be the people flow data of the previous second, the error may be large, a receiving time threshold e_range may be set, if people flow data of a certain camera is not received within the duration of e_range, the camera device is considered to be abnormal, restoration processing may be performed on the camera, and if still abnormal, the camera is replaced.
The receive time threshold e_range may be determined as follows:
if there are n cameras, and the time interval of the x-th camera is deltatx (x E (1, n)), then e_range=max (Δt)x )+1(x∈(1,n))。
Compared with the prior art, the embodiment has the following beneficial effects:
firstly, according to the people flow alarming method provided by the embodiment, according to people flow data sent by a camera in real time, people flow in a monitoring area of the camera is periodically detected, and alarming prompts are pushed when people flow at each moment in a preset alarming period meets preset conditions. Because the people flow data are acquired in real time through the camera, the real-time performance is higher and the error is smaller; and moreover, detection is carried out at each moment in a preset alarm period, and when the flow of people at each moment meets preset conditions, alarm prompts are pushed, so that the detection accuracy is improved.
Secondly, for the ith preset alarm period, a preset detection period is set, and the pushing delay of alarm prompt is reduced by periodically detecting the people flow at each moment in the preset detection period.
Then, aiming at the situation that the sending frequencies of the people flow are inconsistent, a second-by-second forward method is adopted to obtain the people flow at each moment, so that the error of the acquired people flow at each moment is reduced, and the instantaneity can be ensured.
Finally, according to the people flow alarming method provided by the embodiment, corresponding preset alarming conditions can be set according to different application conditions, and the application scene is wider.
Referring to fig. 7, fig. 7 is a block diagram illustrating a traffic alarm device 200 according to the present embodiment. The traffic alert device 200 is applied to the electronic apparatus 100, and the electronic apparatus 100 communicates with a camera. The device comprises: a receiving module 201, a detecting module 202 and an alarming module 203.
The receiving module 201 is configured to receive traffic data sent in real time by the camera, where the traffic data characterizes traffic of a monitoring area of the camera at a current moment.
A detection module 202 for:
according to the real-time generated traffic, detecting the traffic and alarming the preset alarming area according to the preset alarming period;
Determining a first starting time and a first ending time of the ith preset alarm period aiming at the ith preset alarm period; the difference between the first ending time and the first starting time is the alarm duration of the preset alarm period.
And the alarm module 203 is configured to determine whether the traffic of the preset alarm area satisfies a preset alarm condition from the first start time to the first end time, and push an alarm prompt when the preset alarm condition is satisfied, where the preset alarm condition indicates that the traffic of each time in the ith preset alarm period satisfies the preset condition.
Optionally, the electronic device 100 stores the traffic of people at each historical moment in advance, where the traffic of people at each historical moment is generated according to traffic data sent by the camera in real time before a preset detection moment, and the preset detection moment is a moment when a detection instruction of a user is received.
The detection module 202 is further configured to:
if i is equal to 1, acquiring the people flow at each historical moment in a preset alarm period before a preset detection moment to obtain a plurality of initial people flows;
judging whether each initial people flow meets a preset condition or not;
if yes, taking the preset detection time as a first starting time;
If not, acquiring each target person flow which does not meet the preset condition, determining the maximum moment from the historical moment corresponding to each target person flow, and taking the maximum moment as the first starting moment;
if i is greater than 1, taking the first ending moment of the i-1 th preset alarm period as the first starting moment;
and superposing the alarm time length of the preset alarm period on the basis of the first starting time to obtain a first ending time.
Optionally, the alarm module 203 is further configured to:
detecting the people flow in the monitoring area according to a preset detection period from the first starting time to the first ending time, wherein the detection duration of the preset detection period is smaller than or equal to the alarm duration;
determining the detection starting time and the detection ending time of an mth preset detection period; if i is equal to 1 and m is equal to 1, the detection starting time is a preset detection time; if i is greater than 1 and m is equal to 1, detecting the pushing moment of the alarm prompt of the i-1 th preset alarm period as the starting moment; if i is greater than or equal to 1 and m is greater than 1, the detection starting time is the detection ending time of the (m-1) th preset detection period;
when the detection end time is reached, according to the people flow data sent by each camera in real time, determining the people flow at each time in a preset detection period, wherein the people flow represents the people flow in a preset alarm area;
Judging whether the people flow at each moment in the mth preset detection period meets preset conditions or not;
if yes, acquiring the detection ending time of the mth preset detection period;
and determining the pushing moment of the alarm prompt according to the detection ending moment and the first ending moment of the mth preset detection period, and pushing the alarm prompt at the pushing moment.
Optionally, the alarm module 203 is further configured to:
if the people flow in at least one moment in the mth preset detection period does not meet the preset condition, determining the maximum moment from all the moments corresponding to the people flow which does not meet the preset condition, taking the maximum moment as a second starting moment, and superposing alarm duration on the basis of the second starting moment to obtain a second ending moment;
the second starting time is used as the first starting time after the i-th preset alarm period is updated, the second ending time is used as the first ending time after the i-th preset alarm period is updated, the detection ending time is used as the detection starting time after the m-th preset detection period is updated, and the step of judging whether the people flow at each time in the m-th preset detection period meets the preset condition is performed again until the people flow at each time in the m-th preset detection period meets the preset condition, and the detection ending time of the m-th preset detection period is obtained.
Optionally, the alarm module 203 is further configured to:
comparing the detection end time of the mth preset detection period with the first termination time;
if the detection end time of the mth preset detection period is greater than or equal to the first termination time, the detection end time is used as the pushing time of the alarm prompt;
if the detection ending time of the mth preset detection period is smaller than the first ending time, assigning m+1 to m, and returning to the step of determining the detection starting time of the mth preset detection period until the detection ending time of the mth preset detection period is larger than or equal to the first ending time, and taking the detection ending time as the pushing time of the alarm prompt.
Optionally, the cameras are at least one, and the monitoring areas of each camera do not overlap.
The alarm module 203 is further configured to:
judging whether each camera transmits the traffic data at the current moment or not according to each moment in a preset detection period;
if yes, summing the data of each person flow to obtain the person flow at the current moment;
if not, determining each target camera which does not send the people flow data, and taking the people flow data sent at the previous moment as the people flow data at the current moment for each target camera; summing the people flow data of each camera at the current moment to obtain the people flow at the current moment;
And obtaining the people flow at each moment in a preset detection period.
It will be apparent to those skilled in the art that the specific operation of the traffic alert device 200 has been described above for convenience and brevity. Reference may be made to the corresponding procedure in the foregoing method embodiments, and no further description is given here.
The present embodiment also provides a computer readable storage medium having a computer program stored thereon, which when executed by the processor 102 implements the people flow alert method disclosed in the above embodiment.
In summary, the embodiment of the invention provides a people flow alarming method, a device, electronic equipment and a storage medium, which are characterized in that firstly, people flow data sent by a camera in real time are received; then, according to the traffic data sent in real time, detecting and alarming the traffic of the preset alarming area according to the preset alarming period; determining a first starting time and a first ending time of the ith preset alarm period according to the ith preset alarm period; and finally, judging whether the flow of people in the preset alarm area meets the preset alarm condition or not at each moment from the first starting moment to the first ending moment, and pushing an alarm prompt when the flow of people in the preset alarm area meets the preset alarm condition. According to the method, the people flow in the monitoring area of the camera is detected periodically, and when the people flow at each moment in the preset alarm period meets the preset condition, the alarm prompt is pushed, so that the detection accuracy is improved.
The present invention is not limited to the above embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.