CN114743365A - Prison intelligent monitoring system and method based on edge calculation - Google Patents
Prison intelligent monitoring system and method based on edge calculation Download PDFInfo
- Publication number
- CN114743365A CN114743365A CN202210228295.2A CN202210228295A CN114743365A CN 114743365 A CN114743365 A CN 114743365A CN 202210228295 A CN202210228295 A CN 202210228295A CN 114743365 A CN114743365 A CN 114743365A
- Authority
- CN
- China
- Prior art keywords
- prisoner
- edge computing
- prison
- video data
- dangerous
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/002—Generating a prealarm to the central station
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/009—Signalling of the alarm condition to a substation whose identity is signalled to a central station, e.g. relaying alarm signals in order to extend communication range
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B3/00—Audible signalling systems; Audible personal calling systems
- G08B3/10—Audible signalling systems; Audible personal calling systems using electric transmission; using electromagnetic transmission
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Electromagnetism (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
Abstract
The application provides a prison intelligent monitoring system and method based on edge calculation, and relates to the technical field of monitoring. The intelligent prison monitoring method based on edge calculation comprises the steps of obtaining monitoring video data in the whole prison room, and identifying dangerous behaviors of prisoners according to the obtained monitoring video data; if the dangerous behaviors of the prisoner are identified, prompt information indicating that the prisoner has the dangerous behaviors is generated; and sending the prompt information to the appointed terminal equipment, so that the prompt information is notified to a prison police carrying the appointed terminal equipment. The method and the system for monitoring the prison condition can monitor the condition in the prison without carelessness, prevent prisoners from crossing the prison or other illegal behaviors, and can well assist prisons to manage the prison.
Description
Technical Field
The application relates to the technical field of monitoring, in particular to an intelligent monitoring system and method for prisons based on edge calculation.
Background
Prisons or detention houses are mainly monitored by video monitoring, and real behavior judgment still needs to be carried out after prison policemen actually view. The response time of the prison police is slow, the best opportunity may be missed in case of emergency, and the prison police sometimes neglect some potential illegal behaviors due to disguise of the behavior of a prison, so that the technical problem needs to be solved.
Disclosure of Invention
In view of the above problems, the present application is made to provide an intelligent monitoring system and method for prison based on edge computing, which overcome or at least partially solve the above problems, can monitor the situation in the prison without carelessness, prevent prisoners from breaking the prison or having other illegal activities, and can well assist the prisons in managing the prisons. The technical scheme is as follows:
in a first aspect, an intelligent prison monitoring system based on edge calculation is provided, which includes:
the edge calculation unit is used for acquiring monitoring video data in the whole prison room and identifying dangerous behaviors of prisoners according to the acquired monitoring video data;
the prompt information generating unit is used for generating prompt information which indicates that the prisoner has dangerous behaviors if the dangerous behaviors of the prisoner are identified;
and the alarm unit is used for sending the prompt information to the specified terminal equipment so as to inform the prison police carrying the specified terminal equipment of the prompt information.
In one possible implementation, the edge calculation unit is further configured to:
determining an edge computing node in a working state in a plurality of edge computing nodes;
sending the acquired monitoring video data to the determined edge computing node in the working state in real time;
and receiving dangerous behaviors of the prisoner in the monitoring video data, which are returned by the edge computing nodes and identified through edge computing.
In one possible implementation, the edge calculation unit is further configured to:
acquiring a feature identifier of an edge computing node to be bound;
binding the obtained feature identifier with an edge computing node to be bound;
and sending the acquired monitoring video data to the bound edge computing node in real time.
In one possible implementation manner, the feature identifier of the edge computing node includes one or more of an ID, a two-dimensional code, a barcode, and a uniform resource identifier URL of the edge computing node.
In one possible implementation, the edge calculation unit is further configured to:
converting each frame in the acquired monitoring video data into a corresponding frame image;
for each frame image, intercepting n rectangular images in each frame image according to the predetermined rectangular area coordinates of n selected areas, wherein n is a positive integer greater than 1;
processing the n rectangular images, converting the n rectangular images into n square images with specified side length, and combining the n square images into an integral square image according to a preset arrangement sequence;
inputting the whole square image into a pre-trained dangerous behavior action recognition model, and predicting dangerous behavior actions corresponding to the whole square image by using the trained dangerous behavior action recognition model to obtain a prediction result;
and identifying dangerous behaviors of the prisoner according to the prediction result.
In one possible implementation, the edge calculation unit is further configured to:
before intercepting n rectangular images in each frame image according to the predetermined rectangular area coordinates of the n selected areas for each frame image, judging whether a monitoring camera acquires monitoring video data currently and acquires a sample video when the rectangular area coordinates of the n selected areas are determined, and whether position change occurs;
if the position changes, determining an affine transformation matrix of the position changes;
and converting the determined rectangular area coordinates of the n selected areas by using an affine transformation matrix to obtain the converted rectangular area coordinates of the n selected areas, and accordingly, for each frame image, intercepting the n rectangular images in each frame image according to the converted rectangular area coordinates of the n selected areas.
In a second aspect, an intelligent prison monitoring method based on edge calculation is provided, and comprises the following steps:
acquiring monitoring video data in the whole prison room, and identifying dangerous behaviors of prisoners according to the acquired monitoring video data;
if the dangerous behaviors of the prisoner are identified, prompt information indicating that the prisoner has the dangerous behaviors is generated;
and sending the prompt information to the appointed terminal equipment, so that the prompt information is notified to a prison police carrying the appointed terminal equipment.
In a possible implementation manner, the identifying dangerous behaviors of the prisoner according to the acquired monitoring video data includes:
determining an edge computing node in a working state in a plurality of edge computing nodes;
sending the acquired monitoring video data to the determined edge computing node in the working state in real time;
and receiving dangerous behaviors of the prisoner in the monitoring video data, which are returned by the edge computing nodes and identified through edge computing.
In a possible implementation manner, the sending the acquired monitoring video data to the edge computing node in real time includes:
acquiring a feature identifier of an edge computing node to be bound;
binding the obtained feature identifier with an edge computing node to be bound;
and sending the acquired monitoring video data to the bound edge computing node in real time.
In one possible implementation manner, the feature identifier of the edge computing node includes one or more of an ID, a two-dimensional code, a barcode, and a uniform resource identifier URL of the edge computing node.
In a possible implementation manner, the identifying dangerous behaviors of the prisoner according to the acquired monitoring video data includes:
converting each frame in the acquired monitoring video data into a corresponding frame image;
for each frame image, intercepting n rectangular images in each frame image according to the predetermined rectangular area coordinates of n selected areas, wherein n is a positive integer greater than 1;
processing the n rectangular images, converting the n rectangular images into n square images with specified side length, and combining the n square images into an integral square image according to a preset arrangement sequence;
inputting the whole square image into a pre-trained dangerous behavior action recognition model, and predicting dangerous behavior actions corresponding to the whole square image by using the trained dangerous behavior action recognition model to obtain a prediction result;
and identifying dangerous behaviors of the prisoner according to the prediction result.
In a possible implementation manner, before, for each frame image, truncating n rectangular images in each frame image according to predetermined rectangular region coordinates of n selected regions, the method further includes:
judging whether the position changes or not when the monitoring camera collects monitoring video data currently and samples videos are collected when the coordinates of the rectangular areas of the n selected areas are determined;
if the position changes, determining an affine transformation matrix of the position changes;
and converting the determined rectangular area coordinates of the n selected areas by using an affine transformation matrix to obtain the converted rectangular area coordinates of the n selected areas, and accordingly, for each frame image, intercepting the n rectangular images in each frame image according to the converted rectangular area coordinates of the n selected areas.
In a possible implementation manner, sending the prompt message to a designated terminal device further includes:
the prisoner is provided with a GPS positioning device, a voice warning device, a sole is provided with a pressure sensor, and a mechanical control device is arranged at a joint of clothes of the prisoner, the mechanical control device can lock the joint of the prisoner so that the joint of the prisoner cannot bend, firstly, the prompt message is sent to a prison police carrying the appointed terminal equipment, then the prompt message is sent to the voice warning device on the prisoner, the GPS of the prisoner is started so that the positioning of the prisoner can be sent to the prison police carrying the appointed terminal equipment, the voice device can play 5 times of voice which enables the prisoner to stop dangerous behaviors and observe whether the prisoner still has the dangerous behaviors, if the dangerous behaviors exist, the mechanical control device is firstly controlled to lock the upper half joint of the prisoner, then the pressure sensor arranged at the sole of the prisoner is used for judging whether the two feet of the current prisoner stably touch the ground, then when the feet of the prisoner touch the ground, the mechanical control device is controlled to lock the joints of the knee part of the prisoner so as to control the prisoner again under the condition of stable body and prevent the prisoner from falling down, and the specific steps comprise,
step a 1: upper body locking enable of mechanical control device controlled by formula (1) according to existence of dangerous behavior of criminal in 5 times of voice broadcast
Wherein E (t)0) An upper body lock enable control value representing the mechanical control device at the present time; t is t0Represents the current time; w (t) represents the existence value of the dangerous behavior of the prisoner detected at time t (if the dangerous behavior of the prisoner is detected, w (t) is 1, otherwise w (t) is 0); t represents the voice station for one-time voice broadcasting to stop dangerous behaviors of a criminalThe time taken; t represents an integer variable (in milliseconds);
if E (t)0) 1, indicating that the upper body of the mechanical control device needs to be controlled to be locked at the current moment;
if E (t)0) 0, indicating that the mechanical control device is not controlled at the current moment, continuously detecting whether the prisoner has dangerous behaviors, and then performing the calculation and control of the step a1 again;
step a 2: whether the current prisoner stably lands on both feet is judged by using the formula (2) according to the pressure sensor arranged at the sole of the prisoner
Wherein Q (t)0) An output value representing that the two feet of the prisoner stably land at the current moment; f (t)0I) represents the value collected by the pressure sensor at the ith part of the two feet of the prisoner at the current moment (wherein F (t)01) represents the value collected by the pressure sensor at the tiptoe part of the left foot of the prisoner, F (t)0_2) The value F (t) which is acquired by the pressure sensor at the heel part of the left foot of the prisoner03) represents the value collected by the pressure sensor at the tiptoe part of the right foot of the prisoner, F (t)04) represents the value collected by the pressure sensor at the heel part of the right foot of the prisoner); 0.5N represents a force of 0.5 newtons; Λ represents a logical relationship and; v represents a logical relationship or; | | represents the absolute value;
if Q (t)0) 1, representing that the two feet of the prisoner are in a stable landing state at the current moment;
if Q (t)0) 0, which indicates that the two feet of the prisoner are not stably landed at the current moment;
step a 3: controlling the joint locking enable of the knee part of the mechanical control device according to the current stable output value of the feet of the prisoner and the upper body locking enable of the mechanical control device by using the formula (3)
Wherein K (t)0) A joint lock enable control value indicating a knee portion of the mechanical control device at a current time;
if K (t)0) 1, the joint of the knee part of the mechanical control device needs to be controlled to be locked at the current moment, and then the joint of the prisoner is locked in a state that the two feet of the prisoner are stable, so that the prisoner cannot move;
if K (t)0) And 0 indicates that the mechanical control device is not controlled at the current moment.
By means of the technical scheme, the intelligent prison monitoring system and method based on edge calculation, provided by the embodiment of the application, are used for acquiring monitoring video data in the whole prison room and identifying dangerous behaviors of prisoners according to the acquired monitoring video data; if the dangerous behaviors of the prisoner are identified, prompt information indicating that the prisoner has the dangerous behaviors is generated; and sending the prompt information to the appointed terminal equipment, so that the prompt information is notified to a prison police carrying the appointed terminal equipment. The prison monitoring method and the prison monitoring system can monitor the conditions in the prisons without carelessness, prevent prisoners from crossing the prisons or other illegal behaviors, and can well assist prisoners in managing the prisons.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments of the present application will be briefly described below.
FIG. 1 shows a flow diagram of a prison intelligent monitoring method based on edge computing according to an embodiment of the application;
FIG. 2 illustrates a flow diagram of a method for intelligent prison surveillance based on edge computing according to another embodiment of the present application;
fig. 3 shows a block diagram of an edge computing based intelligent prison monitoring device according to an embodiment of the application.
Detailed Description
Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that such uses are interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the term "include" and its variants are to be read as open-ended terms meaning "including, but not limited to".
The embodiment of the application provides an intelligent prison monitoring method based on edge calculation, which can be applied to prison monitoring equipment. As shown in fig. 1, the intelligent prison monitoring method based on edge calculation may include the following steps S101 to S103:
step S101, acquiring monitoring video data in the whole prison room, and identifying dangerous behaviors of prisoners according to the acquired monitoring video data;
step S102, if the dangerous behaviors of the prisoner are identified, prompt information indicating that the prisoner has the dangerous behaviors is generated;
and step S103, sending the prompt information to the specified terminal equipment, and informing the prison police carrying the specified terminal equipment of the prompt information.
The method comprises the steps of acquiring monitoring video data in the whole prison room, and identifying dangerous behaviors of prisoners according to the acquired monitoring video data; if the dangerous behaviors of the prisoner are identified, prompt information indicating that the prisoner has the dangerous behaviors is generated; and sending the prompt information to the specified terminal equipment, thereby informing the prison police carrying the specified terminal equipment of the prompt information. The prison monitoring method and the prison monitoring system can monitor the conditions in the prisons without carelessness, prevent prisoners from crossing the prisons or other illegal behaviors, and can well assist prisoners in managing the prisons.
A possible implementation manner is provided in the embodiment of the present application, where the identifying of the dangerous behaviors of the prisoner according to the obtained monitoring video data in step S101 may specifically include the following steps a1 to A3:
step A1, determining the edge computing node in working state in a plurality of edge computing nodes;
step A2, sending the acquired monitoring video data to the determined edge computing node in the working state in real time;
and step A3, receiving dangerous behaviors of the prisoner in the monitoring video data identified by the edge calculation returned by the edge calculation node.
According to the embodiment of the application, the resolution accuracy is improved through edge calculation, and the recognition efficiency is improved.
The embodiment of the present application provides a possible implementation manner, where the step a2 sends the acquired monitoring video data to the determined edge computing node in the working state in real time, and the method specifically includes the following steps a2-1 to a 2-3:
a2-1, acquiring a feature identifier of an edge computing node to be bound;
step A2-2, binding the obtained feature identifier with an edge computing node to be bound;
and step A2-3, sending the acquired monitoring video data to the bound edge computing node in real time.
According to the method and the device, the proper edge computing node can be found for binding, and the identification efficiency of subsequent dangerous behavior actions is improved.
The characteristic identifier of the edge computing node mentioned in the above step a1-1 may include one or more of an ID (Identity Document), a two-dimensional code, a barcode, and a URL (Uniform Resource identifier) of the edge computing node.
A possible implementation manner is provided in the embodiment of the present application, where the identifying of the dangerous behaviors of the prisoner according to the obtained monitoring video data in step S101 may specifically include the following steps B1 to B5:
step B1, converting each frame in the acquired monitoring video data into a corresponding frame image;
step B2, for each frame image, intercepting n rectangular images in each frame image according to the predetermined rectangular area coordinates of n selected areas, wherein n is a positive integer greater than 1;
step B3, processing the n rectangular images, converting the n rectangular images into n square images with specified side length, and combining the n square images into an integral square image according to a preset arrangement sequence;
step B4, inputting the whole square image into a pre-trained dangerous behavior action recognition model, and predicting the dangerous behavior action corresponding to the whole square image by using the trained dangerous behavior action recognition model to obtain a prediction result;
and step B5, identifying the dangerous behaviors of the prisoner according to the prediction result.
According to the embodiment of the application, the video data frame image is processed through edge calculation, so that the dangerous behaviors of prisoners can be accurately and efficiently identified, and prisons can be well assisted to manage the prisons.
In this embodiment, a possible implementation manner is provided, before the step B2, for each frame image, truncating n rectangular images in each frame image according to the predetermined rectangular area coordinates of the n selected regions, the following steps C1 to C3 may be further included:
step C1, judging whether the position changes or not when the monitoring camera collects the monitoring video data currently and the sample video is collected when the rectangular area coordinates of the n selected areas are determined;
step C2, if the position changes, determining an affine transformation matrix of the position change;
and step C3, converting the determined rectangular region coordinates of the n selected regions by using an affine transformation matrix to obtain the converted rectangular region coordinates of the n selected regions, and accordingly, for each frame image, intercepting the n rectangular images in each frame image according to the converted rectangular region coordinates of the n selected regions.
In the embodiment, if the position of the camera is not changed, the camera does not need to be calibrated, the purpose of calibration is to adjust the change of the position of the camera or the change of the angle of the camera to bring the change of the position of the pre-selection frame in the image, so that the accuracy of image selection can be improved, and the accuracy of identification is further improved.
A possible implementation manner is provided in the embodiment of the present application, where step S103 sends the prompt information to the specified terminal device, further includes:
the method comprises the steps that a GPS (Global Positioning System) Positioning device, a voice warning device and a sole of a prisoner are installed on the prisoner, a pressure sensor is installed on the prisoner, a mechanical control device is installed on the joint of clothes of the prisoner, the mechanical control device can lock the joint of the prisoner to enable the joint of the prisoner to be incapable of bending, prompt information is sent to a prison police carrying a specified terminal device firstly, then the prompt information is sent to the voice warning device on the prisoner, the GPS on the prisoner is started to enable the Positioning of the prisoner to be sent to the prisoner carrying the specified terminal device, the voice device plays 5 times of voice enabling the prisoner to stop dangerous behaviors and observes whether the prisoner still has the dangerous behaviors, if the dangerous behaviors exist, the mechanical control device is controlled to lock the upper half joint of the prisoner firstly, then whether the current prisoner stably lands on both feet is judged through the pressure sensor arranged on the sole of the prisoner, then when the feet of the prisoner touch the ground, the mechanical control device is controlled to lock the joints of the knee part of the prisoner so as to control the prisoner again under the condition of stable body and prevent the prisoner from falling down, and the specific steps comprise,
step a 1: upper body locking enable of mechanical control device controlled by formula (1) according to existence of dangerous behavior of criminal in 5 times of voice broadcast
Wherein E (t)0) An upper body lock enable control value representing a mechanical control device at a current time; t is t0Represents the current time; w (t) represents the existence value of dangerous behavior of the prisoner detected at the time t (if dangerous behavior of the prisoner is detected, W (t)) 1, whereas w (t) is 0); t represents the time taken for voice broadcasting to stop the voice of the dangerous behavior for one time by a criminal; t represents an integer variable (in milliseconds);
if E (t)0) 1, indicating that the upper half body of the mechanical control device needs to be controlled to be locked at the current moment;
if E (t)0) When the current time is 0, the mechanical control device is not controlled, the criminal is continuously detected whether the criminal has dangerous behaviors, and then the calculation and the control of the step a1 are carried out again;
step a 2: whether the current prisoner stably lands on both feet is judged by using the formula (2) according to the pressure sensor arranged at the sole of the prisoner
Wherein Q (t)0) An output value representing that the two feet of the prisoner stably land at the current moment; f (t)0I) represents the value collected by the pressure sensor at the ith part of each foot of the prisoner at the current moment (wherein F (t)01) represents the value collected by the pressure sensor at the tiptoe of the left foot of the prisoner, F (t)02) represents the value collected by the pressure sensor at the heel of the left foot of the prisoner, F (t)03) represents the value collected by the pressure sensor at the tiptoe part of the right foot of the prisoner, F (t)04) represents the value collected by the pressure sensor at the heel part of the right foot of the prisoner); 0.5N represents a force of 0.5 newtons; Λ represents a logical relationship and; the V-shaped represents a logical relationship or; | | represents the absolute value;
if Q (t)0) 1, representing that the two feet of the prisoner are in a stable landing state at the current moment;
if Q (t)0) 0, representing that the two feet of the prisoner are not in a stable landing state at the current moment;
step a 3: controlling the joint locking enable of the knee part of the mechanical control device according to the current stable output value of the feet of the prisoner and the upper body locking enable of the mechanical control device by using the formula (3)
Wherein K (t)0) A joint lock enable control value indicating a knee portion of the mechanical control device at a current time;
if K (t)0) 1, the joint of the knee part of the mechanical control device needs to be controlled to be locked at the current moment, and then the joint of the prisoner is locked under the state that the two feet of the prisoner are stable so as to be incapable of moving;
if K (t)0) When the current time is 0, the mechanical control device is not controlled.
The beneficial effects of the above technical scheme are: controlling the upper body locking enable of the mechanical control device according to the existence condition of the dangerous behaviors of the prisoner within 5 times of voice broadcast by using the formula (1) of the step a1, so that the upper body of the prisoner who does not listen to the supervised education is limited at first, and the actions of the dangerous behaviors of the prisoner are reduced; then, judging whether the current prisoner stably lands on the ground or not according to the pressure sensor arranged at the sole of the prisoner by using the formula (2) of the step a2, and aiming at judging whether the current prisoner is stable in the double-foot state or not so as to facilitate subsequent safety control; and finally, controlling the joint locking enabling of the knee part of the mechanical control device according to the current stable output value of the feet of the prisoner and the upper body locking enabling of the mechanical control device by using the formula (3) of the step a3, and further controlling and locking the joint of the knee part of the prisoner under the condition of ensuring the safety of the prisoner so as to prevent the prisoner from moving and continuing dangerous behaviors.
In the above, various implementation manners of each link of the embodiment shown in fig. 1 are introduced, and an implementation process of the intelligent prison monitoring method based on edge calculation will be described in detail below by using a specific embodiment.
Another embodiment of the present application provides an edge-computing-based intelligent prison monitoring method, as shown in fig. 2, which may include the following steps S201 to S205:
step S201, acquiring monitoring video data in the whole prison room;
step S202, sending the acquired monitoring video data to an edge computing node in real time;
it can be understood that, here, the obtained monitoring video data is sent to the edge computing node in real time, specifically, the feature identifier of the edge computing node to be bound is obtained, then the obtained feature identifier is bound with the edge computing node to be bound, and then the obtained monitoring video data is sent to the bound edge computing node in real time. The characteristic identification of the edge computing node mentioned here may include one or more of ID, two-dimensional code, barcode, URL of the edge computing node.
Step S203, receiving dangerous behaviors of the prisoner in the monitoring video data, which are returned by the edge computing nodes and identified through edge computing;
it is understood that the edge computing nodes may use the steps B1 through B5 as described above to identify the dangerous behavior of the prisoner based on the surveillance video data, and will not be described in detail herein.
Step S204, if the dangerous behaviors of the prisoner are identified, prompt information indicating that the prisoner has the dangerous behaviors is generated;
it is understood that if the dangerous behavior of the prisoner is not identified, no prompt information indicating that the prisoner has dangerous behavior is generated.
And step S205, sending the prompt information to the specified terminal equipment, so as to inform the prison police carrying the specified terminal equipment of the prompt information.
According to the embodiment of the application, the video data frame images are processed through edge calculation, so that dangerous behaviors of prisoners can be accurately and efficiently identified, the conditions in the prisons can be monitored without carelessness, the prisoners are prevented from breaking the prisons or other illegal behaviors are prevented, and the prisoners can be well assisted to manage the prisons.
It should be noted that, in practical applications, all the possible embodiments described above may be combined in a combined manner at will to form possible embodiments of the present application, and details are not described here again.
Based on the intelligent prison monitoring method based on edge calculation provided by the embodiments, the embodiment of the application also provides an intelligent prison monitoring device based on edge calculation based on the same inventive concept.
Fig. 3 shows a block diagram of an edge computing based intelligent prison monitoring device according to an embodiment of the application. As shown in fig. 3, the intelligent prison monitoring device based on edge calculation may include an edge calculation unit 310, a prompt information generation unit 320, and an alarm unit 330.
The edge calculation unit 310 is used for acquiring monitoring video data in the whole prison room and identifying dangerous behaviors of a prison according to the acquired monitoring video data;
a prompt information generating unit 320, configured to generate prompt information indicating that a criminal has a dangerous behavior if the dangerous behavior of the criminal is identified;
and the alarm unit 330 is configured to send the prompt message to the specified terminal device, so as to notify the prison police carrying the specified terminal device of the prompt message.
In an embodiment of the present application, a possible implementation manner is provided, and the edge calculating unit 310 shown in fig. 3 is further configured to:
sending the acquired monitoring video data to an edge computing node in real time;
and receiving dangerous behaviors of the prisoner in the monitoring video data, which are returned by the edge computing nodes and identified through edge computing.
In an embodiment of the present application, a possible implementation manner is provided, and the edge calculating unit 310 shown in fig. 3 is further configured to:
acquiring a feature identifier of an edge computing node to be bound;
binding the obtained feature identifier with an edge computing node to be bound;
and sending the acquired monitoring video data to the bound edge computing node in real time.
The embodiment of the application provides a possible implementation manner, and the feature identifier of the edge computing node includes one or more of an ID, a two-dimensional code, a barcode, and a uniform resource identifier URL of the edge computing node.
In an embodiment of the present application, a possible implementation manner is provided, and the edge calculating unit 310 shown in fig. 3 is further configured to:
converting each frame in the acquired monitoring video data into a corresponding frame image;
for each frame image, intercepting n rectangular images in each frame image according to the predetermined rectangular area coordinates of n selected areas, wherein n is a positive integer greater than 1;
processing the n rectangular images, converting the n rectangular images into n square images with specified side length, and combining the n square images into an integral square image according to a preset arrangement sequence;
inputting the whole square image into a pre-trained dangerous behavior action recognition model, and predicting the dangerous behavior action corresponding to the whole square image by using the trained dangerous behavior action recognition model to obtain a prediction result;
and identifying dangerous behaviors of the prisoner according to the prediction result.
In an embodiment of the present application, a possible implementation manner is provided, and the edge calculating unit 310 shown in fig. 3 is further configured to:
before intercepting n rectangular images in each frame image according to the predetermined rectangular area coordinates of the n selected areas for each frame image, judging whether a monitoring camera acquires monitoring video data currently and acquires a sample video when the rectangular area coordinates of the n selected areas are determined, and whether position change occurs;
if the position changes, determining an affine transformation matrix of the position changes;
and converting the determined rectangular area coordinates of the n selected areas by using an affine transformation matrix to obtain the converted rectangular area coordinates of the n selected areas, and accordingly, for each frame image, intercepting the n rectangular images in each frame image according to the converted rectangular area coordinates of the n selected areas.
In the embodiment of the present application, a possible implementation manner is provided, and the alarm unit 330 shown in fig. 3 is further configured to:
the prisoner is provided with a positioning device, a voice warning device, a sole is provided with a pressure sensor, a mechanical control device is arranged at the joint of clothes of the prisoner, the mechanical control device can lock the joint of the prisoner to prevent the joint of the prisoner from bending, prompt information is sent to a prison police carrying a specified terminal device, then the prompt information is sent to the voice warning device on the prisoner, GPS on the prisoner is started to enable the positioning of the prisoner to be sent to a prison police carrying the specified terminal device, the voice device plays 5 times of voice enabling the prisoner to stop dangerous behaviors and observes whether the prisoner still has dangerous behaviors, if the prisoner still has dangerous behaviors, the mechanical control device is controlled to lock the upper half body joint of the prisoner, then the pressure sensor arranged at the sole of the prisoner judges whether the current prisoner stably lands on feet, and then the mechanical control device is controlled to lock the joint of the knee part of the prisoner when the prisoner lands on feet, so that the prisoner can be controlled under the condition of stable body to prevent the prisoner from falling down, the concrete steps comprise,
step a 1: upper body locking enable of mechanical control device controlled by formula (1) according to existence of dangerous behavior of criminal in 5 times of voice broadcast
Wherein E (t)0) An upper body lock enable control value representing a mechanical control device at a current time; t is t0Represents the current time; w (t) represents the existence value of the dangerous behavior of the prisoner detected at the time t (if the dangerous behavior of the prisoner is detected, w (t) is 1, otherwise w (t) is 0); t represents the time taken for voice broadcasting to stop the voice of the dangerous behavior for one time by a criminal; t represents an integer variable (in milliseconds);
if E (t)0) 1, indicating that the upper body of the mechanical control device needs to be controlled to be locked at the current moment;
if E (t)0) When the current time is 0, the mechanical control device is not controlled, the criminal is continuously detected whether the criminal has dangerous behaviors, and then the calculation and the control of the step a1 are carried out again;
step a 2: whether the current prisoner stably lands on both feet is judged by using the formula (2) according to the pressure sensor arranged at the sole of the prisoner
Wherein Q (t)0) An output value representing that the two feet of a prisoner stably land at the current moment; f (t)0I) represents the value collected by the pressure sensor at the ith part of each foot of the prisoner at the current moment (wherein F (t)01) represents the value collected by the pressure sensor at the tiptoe of the left foot of the prisoner, F (t)0-2) The value F (t) which is acquired by the pressure sensor at the heel part of the left foot of the prisoner03) represents the value collected by the pressure sensor at the tiptoe part of the right foot of the prisoner, F (t)04) represents the value collected by the pressure sensor at the heel part of the right foot of the prisoner); 0.5N represents a force of 0.5 newtons; Λ represents a logical relationship and; the V-shaped represents a logical relationship or; | | represents the absolute value;
if Q (t)0) 1, representing that the two feet of the prisoner are in a stable landing state at the current moment;
if Q (t)0) 0, representing that the two feet of the prisoner are not in a stable landing state at the current moment;
step a 3: controlling the joint locking enable of the knee part of the mechanical control device according to the current stable output value of the feet of the prisoner and the upper body locking enable of the mechanical control device by using the formula (3)
Wherein K (t)0) A joint lock enable control value indicating a knee portion of the mechanical control device at a current time;
if K (t)0) 1, the joint of the knee part of the mechanical control device needs to be controlled to be locked at the current moment, and then the joint of the prisoner is locked under the state that the two feet of the prisoner are stable so as to be incapable of moving;
if K (t)0) When the current time is 0, it means that the machine control device is not controlled.
The intelligent prison monitoring system based on edge calculation obtains monitoring video data in the whole prison room, and identifies dangerous behaviors of prisoners according to the obtained monitoring video data; if the dangerous behaviors of the prisoner are identified, prompt information indicating that the prisoner has the dangerous behaviors is generated; and sending the prompt information to the appointed terminal equipment, so that the prompt information is notified to a prison police carrying the appointed terminal equipment. The prisoner monitoring method and the prisoner monitoring system can monitor the conditions in the prisons without carelessness, prevent prisoners from crossing the prisons or other illegal behaviors, and can well assist prisoners in managing the prisons.
It can be clearly understood by those skilled in the art that the specific working processes of the system, the apparatus, and the module described above may refer to the corresponding processes in the foregoing method embodiments, and for the sake of brevity, the detailed description is omitted here.
Those of ordinary skill in the art will understand that: the technical solution of the present application may be essentially or wholly or partially embodied in the form of a software product, where the computer software product is stored in a storage medium and includes program instructions for enabling an electronic device (e.g., a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application when the program instructions are executed. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Alternatively, all or part of the steps of implementing the foregoing method embodiments may be implemented by hardware (an electronic device such as a personal computer, a server, or a network device) associated with program instructions, which may be stored in a computer-readable storage medium, and when the program instructions are executed by a processor of the electronic device, the electronic device executes all or part of the steps of the method described in the embodiments of the present application.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments can be modified or some or all of the technical features can be replaced with equivalents within the spirit and principle of the present application; such modifications or substitutions do not depart from the scope of the present application.
Claims (10)
1. An intelligent prison monitoring system based on edge calculation is characterized by comprising the following components:
the edge calculation unit is used for acquiring monitoring video data in the whole prison room and identifying dangerous behaviors of prisoners according to the acquired monitoring video data;
the prompt information generating unit is used for generating prompt information which indicates that the criminal has dangerous behaviors if the dangerous behaviors of the criminal are identified;
and the alarm unit is used for sending the prompt information to the specified terminal equipment so as to inform the prison police carrying the specified terminal equipment of the prompt information.
2. An edge computing based prison intelligent supervision system according to claim 1 characterized in that the edge computing unit is also used to:
determining an edge computing node in a working state in a plurality of edge computing nodes;
sending the acquired monitoring video data to the determined edge computing node in the working state in real time;
and receiving dangerous behaviors of the prisoner in the monitoring video data, which are returned by the edge computing nodes and identified through edge computing.
3. An edge computing based prison intelligent supervision system according to claim 2 characterized in that the edge computing unit is also used to:
acquiring a feature identifier of an edge computing node to be bound;
binding the obtained feature identifier with an edge computing node to be bound;
and sending the acquired monitoring video data to the bound edge computing node in real time.
4. An edge computing based prison intelligent monitoring system as claimed in claim 3 wherein the characteristic identification of the edge computing node comprises one or more of an ID, a two-dimensional code, a barcode, a uniform resource identifier (URL) of the edge computing node.
5. An edge computing based prison intelligent supervision system according to claim 1 characterized in that the edge computing unit is also used to:
converting each frame in the acquired monitoring video data into a corresponding frame image;
for each frame image, intercepting n rectangular images in each frame image according to the predetermined rectangular area coordinates of n selected areas, wherein n is a positive integer greater than 1;
processing the n rectangular images, converting the n rectangular images into n square images with specified side length, and combining the n square images into an integral square image according to a preset arrangement sequence;
inputting the whole square image into a pre-trained dangerous behavior action recognition model, and predicting dangerous behavior actions corresponding to the whole square image by using the trained dangerous behavior action recognition model to obtain a prediction result;
and identifying dangerous behaviors of the prisoner according to the prediction result.
6. An edge computing based prison intelligent supervision system according to claim 5 characterized in that the edge computing unit is also used to:
before intercepting n rectangular images in each frame image according to the predetermined rectangular area coordinates of the n selected areas for each frame image, judging whether the position change occurs when a monitoring camera acquires monitoring video data currently and acquires a sample video when the rectangular area coordinates of the n selected areas are determined;
if the position changes, determining an affine transformation matrix of the position changes;
and converting the determined rectangular area coordinates of the n selected areas by using an affine transformation matrix to obtain the converted rectangular area coordinates of the n selected areas, and accordingly, for each frame image, intercepting the n rectangular images in each frame image according to the converted rectangular area coordinates of the n selected areas.
7. An intelligent prison monitoring method based on edge calculation is characterized by comprising the following steps:
acquiring monitoring video data in the whole prison room, and identifying dangerous behaviors of prisoners according to the acquired monitoring video data;
if the dangerous behaviors of the prisoner are identified, prompt information indicating that the prisoner has the dangerous behaviors is generated;
and sending the prompt information to the appointed terminal equipment, so that the prompt information is notified to a prison police carrying the appointed terminal equipment.
8. An edge computing based prison intelligent prison monitoring method as claimed in claim 7, wherein the identification of the dangerous behavior of a prison according to the acquired monitoring video data comprises:
determining an edge computing node in a working state in a plurality of edge computing nodes;
sending the acquired monitoring video data to the determined edge computing node in the working state in real time;
and receiving dangerous behaviors of the prisoner in the monitoring video data, which are returned by the edge computing nodes and identified through edge computing.
9. The intelligent prison monitoring method based on edge computing as claimed in claim 8, wherein the step of sending the obtained monitoring video data to the determined edge computing nodes in working state in real time comprises:
acquiring a feature identifier of an edge computing node to be bound;
binding the obtained feature identifier with an edge computing node to be bound;
and sending the acquired monitoring video data to the bound edge computing node in real time.
10. The intelligent prison monitoring method based on edge calculation as claimed in claim 7, wherein the prompt message is sent to a designated terminal device, further comprising:
the prisoner is provided with a GPS positioning device, a voice warning device, a sole is provided with a pressure sensor, and a mechanical control device is arranged at a joint of clothes of the prisoner, the mechanical control device can lock the joint of the prisoner so that the joint of the prisoner cannot bend, firstly, the prompt message is sent to a prison police carrying the appointed terminal equipment, then the prompt message is sent to the voice warning device on the prisoner, the GPS of the prisoner is started so that the positioning of the prisoner can be sent to the prison police carrying the appointed terminal equipment, the voice device can play 5 times of voice which enables the prisoner to stop dangerous behaviors and observe whether the prisoner still has the dangerous behaviors, if the dangerous behaviors exist, the mechanical control device is firstly controlled to lock the upper half joint of the prisoner, then the pressure sensor arranged at the sole of the prisoner is used for judging whether the two feet of the current prisoner stably touch the ground, then when the feet of the prisoner touch the ground, the mechanical control device is controlled to lock the joints of the knee part of the prisoner so as to control the prisoner again under the condition of stable body and prevent the prisoner from falling down, and the specific steps comprise,
step a 1: upper body locking enable of mechanical control device controlled by formula (1) according to existence of dangerous behavior of criminal in 5 times of voice broadcast
Wherein E (t)0) An upper body lock enable control value representing the mechanical control device at the present time; t is t0Represents the current time; w (t) denotes time tThe detected existence value of the dangerous behavior of the prisoner (if the dangerous behavior of the prisoner is detected, W (t) is 1, otherwise W (t) is 0); t represents the time taken for the voice broadcast to stop the voice of the dangerous behavior of the criminal once; t represents an integer variable (in milliseconds);
if E (t)0) 1, indicating that the upper body of the mechanical control device needs to be controlled to be locked at the current moment;
if E (t)0) 0, indicating that the mechanical control device is not controlled at the current moment, continuously detecting whether the prisoner has dangerous behaviors, and then performing the calculation and control of the step a1 again;
step a 2: whether the current prisoner stably lands on both feet or not is judged according to the pressure sensor arranged on the sole of the prisoner by using the formula (2)
Wherein Q (t)0) An output value representing that the two feet of the prisoner stably land at the current moment; f (t)0I) represents the value collected by the pressure sensor at the ith part of the two feet of the prisoner at the current moment (wherein F (t)01) represents the value collected by the pressure sensor at the tiptoe of the left foot of the prisoner, F (t)02) represents the value collected by the pressure sensor at the heel of the left foot of the prisoner, F (t)03) represents the value collected by the pressure sensor at the tiptoe part of the right foot of the prisoner, F (t)04) represents the value collected by the pressure sensor at the heel part of the right foot of the prisoner); 0.5N represents a force of 0.5 newtons; Λ represents a logical relationship and; the V-shaped represents a logical relationship or; | | represents the absolute value;
if Q (t)0) 1, representing that the two feet of the prisoner are in a stable landing state at the current moment;
if Q (t)0) 0, which indicates that the two feet of the prisoner are not stably landed at the current moment;
step a 3: controlling the joint locking enable of the knee portion of the mechanical control device according to the current prisoner's bipedal stable output value and the upper body locking enable of the mechanical control device using formula (3)
Wherein K (t)0) A joint lock enable control value representing a knee portion of the mechanical control device at a current time;
if K (t)0) 1, the joint of the knee part of the mechanical control device needs to be controlled to be locked at the current moment, and then the joint of the prisoner is locked in a state that the two feet of the prisoner are stable, so that the prisoner cannot move;
if K (t)0) And 0 indicates that the mechanical control device is not controlled at the current moment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210228295.2A CN114743365A (en) | 2022-03-10 | 2022-03-10 | Prison intelligent monitoring system and method based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210228295.2A CN114743365A (en) | 2022-03-10 | 2022-03-10 | Prison intelligent monitoring system and method based on edge calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114743365A true CN114743365A (en) | 2022-07-12 |
Family
ID=82274994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210228295.2A Pending CN114743365A (en) | 2022-03-10 | 2022-03-10 | Prison intelligent monitoring system and method based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114743365A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110070155A (en) * | 2019-04-08 | 2019-07-30 | 山东瀚岳智能科技股份有限公司 | A kind of comprehensive Activity recognition method and system of the inmate based on wearable device |
| CN111695549A (en) * | 2020-08-04 | 2020-09-22 | 图为信息科技(深圳)有限公司 | Safety helmet wearing detection and identification method based on edge calculation and alarm system |
| CN112241673A (en) * | 2019-07-19 | 2021-01-19 | 浙江商汤科技开发有限公司 | Video method and device, electronic equipment and storage medium |
| CN112950400A (en) * | 2021-03-30 | 2021-06-11 | 煤炭科学研究总院 | Data processing platform |
| CN113296903A (en) * | 2021-02-01 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Edge cloud system, edge control method, control node and storage medium |
| CN114092865A (en) * | 2022-01-21 | 2022-02-25 | 北京清鹤科技有限公司 | Prisoner supervision method and system based on neural network |
-
2022
- 2022-03-10 CN CN202210228295.2A patent/CN114743365A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110070155A (en) * | 2019-04-08 | 2019-07-30 | 山东瀚岳智能科技股份有限公司 | A kind of comprehensive Activity recognition method and system of the inmate based on wearable device |
| CN112241673A (en) * | 2019-07-19 | 2021-01-19 | 浙江商汤科技开发有限公司 | Video method and device, electronic equipment and storage medium |
| CN111695549A (en) * | 2020-08-04 | 2020-09-22 | 图为信息科技(深圳)有限公司 | Safety helmet wearing detection and identification method based on edge calculation and alarm system |
| CN113296903A (en) * | 2021-02-01 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Edge cloud system, edge control method, control node and storage medium |
| CN112950400A (en) * | 2021-03-30 | 2021-06-11 | 煤炭科学研究总院 | Data processing platform |
| CN114092865A (en) * | 2022-01-21 | 2022-02-25 | 北京清鹤科技有限公司 | Prisoner supervision method and system based on neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110490078B (en) | Monitoring video processing method, device, computer equipment and storage medium | |
| US9870470B2 (en) | Method and apparatus for detecting a multi-stage event | |
| CN101207803B (en) | Camera tampering detection method, module and apparatus | |
| US20130188031A1 (en) | Risk recognition method for use in video surveillance system based on human identification | |
| CN103443823B (en) | Shooting pattern recognition device, shooting image identification system and shooting image-recognizing method | |
| US20150078618A1 (en) | System for tracking dangerous situation in cooperation with mobile device and method thereof | |
| CN110751116B (en) | Target identification method and device | |
| CN113095132A (en) | Neural network-based gas field target detection and behavior identification method, system, terminal and storage medium | |
| CN108629310B (en) | Engineering management supervision method and device | |
| CN111814776B (en) | Image processing method, device, server and storage medium | |
| KR20220077404A (en) | Method and System for Implementation of Multi-level On-site Safety Control of Worker Safety | |
| JP2012128877A (en) | Suspicious behavior detection system and method | |
| CN111008621A (en) | Object tracking method and device, computer equipment and storage medium | |
| CN111914673A (en) | Target behavior detection method and device and computer readable storage medium | |
| KR102346204B1 (en) | Method, device and system for processing cctv image installed in public place based on artificial intelligence | |
| KR102077632B1 (en) | Hybrid intellgent monitoring system suing local image analysis and cloud service | |
| CN114743365A (en) | Prison intelligent monitoring system and method based on edge calculation | |
| KR20210053718A (en) | Animal tracking monitoring server and operation method thereof | |
| CN113469137A (en) | Abnormal behavior recognition method and device, storage medium and electronic device | |
| CN111695404B (en) | Pedestrian falling detection method and device, electronic equipment and storage medium | |
| RU2017128108A (en) | PLANNING INTERACTION WITH SUBJECT | |
| Vivek Anand et al. | Image validation with virtualization in blockchain based internet of things | |
| CN117151675B (en) | Remote operation and maintenance method and system based on video monitoring and encryption | |
| CN112329499B (en) | Image processing method, device and equipment | |
| CN115909215B (en) | Edge intrusion early warning method and system based on target detection |
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 |