CN110164074A - A kind of method for early warning, prior-warning device and computer storage medium - Google Patents
A kind of method for early warning, prior-warning device and computer storage medium Download PDFInfo
- Publication number
- CN110164074A CN110164074A CN201910461434.4A CN201910461434A CN110164074A CN 110164074 A CN110164074 A CN 110164074A CN 201910461434 A CN201910461434 A CN 201910461434A CN 110164074 A CN110164074 A CN 110164074A
- Authority
- CN
- China
- Prior art keywords
- person
- photo
- size
- suspicious
- determining
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000004590 computer program Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000013459 approach Methods 0.000 description 6
- 230000001960 triggered effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 241000282326 Felis catus Species 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
- G08B13/19615—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion wherein said pattern is defined by the user
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Studio Devices (AREA)
Abstract
The present embodiments relate to field of security technologies, disclose a kind of method for early warning, using infrared sensor detection preset range in whether someone；When detecting someone, triggering camera is opened and captures portrait photographs；The proportionality coefficient of portrait photographs is determined according to the size of the portrait photographs of candid photograph and pre-set dimension, and determines whether the personage in the portrait photographs captured is suspicious figure according to proportionality coefficient；If it is determined that personage is suspicious figure, then early warning is carried out.Method for early warning, prior-warning device and the computer storage medium provided in embodiment of the present invention is avoided using failing to report alert problem brought by range sensor and can realize long range early warning.
Description
Technical Field
The embodiment of the invention relates to the technical field of security and protection, in particular to an early warning method, an early warning device and a computer storage medium.
Background
In the technical field of security and protection, in order to accurately identify a person passing through a doorway as a suspicious person approaching the doorway instead of only a passerby passing through the doorway, a distance sensor is usually arranged at the doorway, and the distance sensor judges whether the person is the suspicious person by detecting the distance between the distance sensor and the person so as to realize security and protection alarm.
However, the inventors found that at least the following problems exist in the prior art: because the distance sensor is arranged in the equipment, glass or an equipment panel is used for isolating the distance sensor from the detected person, the sensitivity of the distance sensor is reduced, and sometimes people cannot be sensed to approach the distance sensor, so that the missed alarm is caused; and because the existing distance sensor is limited in sensing distance, long-distance early warning cannot be achieved.
Disclosure of Invention
The embodiment of the invention aims to provide an early warning method, an early warning device and a computer storage medium, which avoid the problem of alarm missing caused by using a distance sensor and can realize long-distance early warning.
In order to solve the technical problem, an embodiment of the invention provides an early warning method, which detects whether a person is in a preset range by using an infrared sensor; when a person is detected, triggering a camera to start and snapshotting a picture of the person; determining a proportionality coefficient of the figure photo according to the size of the captured figure photo and a preset size, and determining whether a figure in the captured figure photo is a suspicious figure according to the proportionality coefficient; and if the person is determined to be a suspicious person, early warning is carried out.
The embodiment of the invention also provides an early warning device, which comprises: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the warning method.
The embodiment of the invention also provides a computer readable storage medium, which stores a computer program, and the computer program realizes the early warning method when being executed by a processor.
Compared with the prior art, the embodiment of the invention provides an early warning method, which is characterized in that an infrared sensor is utilized to detect whether a person exists in a preset range; when a person is detected, triggering a camera to start and snapshotting a picture of the person; determining a proportionality coefficient of the figure photo according to the size of the captured figure photo and a preset size, and determining whether a figure in the captured figure photo is a suspicious figure according to the proportionality coefficient; and if the person is determined to be a suspicious person, early warning is carried out. According to the embodiment of the invention, an infrared sensor is used for detecting whether a person exists in a preset range, when the person is detected, a camera is triggered to start and capture a figure photo, the figure distance in the captured photo is determined directly according to the size of the figure photo captured by the camera and the proportional coefficient of the preset size, and then whether the figure is a suspicious figure is determined according to the figure distance, so that the problem of alarm missing caused when a distance sensor is used for detecting whether the figure is the suspicious figure is avoided; compared with a distance sensor, the camera is not limited by the distance when the camera captures the picture, so that the early warning method in the scheme can be used for capturing and detecting people in a large range, and long-distance early warning is realized.
In addition, the personal photograph includes: a first photograph taken at a first time; determining a proportionality coefficient of the figure photo according to the size of the captured figure photo and a preset size, and determining whether a figure in the captured figure photo is a suspicious figure according to the proportionality coefficient, wherein the method specifically comprises the following steps: identifying a size of a first target area in the captured first photograph; determining a first proportional coefficient of the size of the first target area and a preset size; and if the first scale factor is larger than 1, determining that the person in the captured person photo is a suspicious person.
In addition, the personal photograph includes: the method comprises the following steps of taking a first photo at a first moment and taking a second photo at a second moment at a preset time interval; determining a proportionality coefficient of the figure photo according to the size of the captured figure photo and a preset size, and determining whether a figure in the captured figure photo is a suspicious figure according to the proportionality coefficient, wherein the method specifically comprises the following steps: identifying a size of a first target area in the first photograph and a size of a second target area in the second photograph; determining a first proportionality coefficient of the size of the first target area and a preset size and a second proportionality coefficient of the size of the second target area and the preset size; judging whether the first scale factor is larger than 1; if the first scale coefficient is larger than 1, judging whether the second scale coefficient is larger than the first scale coefficient; and if the second scale coefficient is larger than the first scale coefficient, determining that the person in the person photo is a suspicious person. According to the scheme, under the condition that the first proportionality coefficient is larger than 1 and the second proportionality coefficient is larger than the first proportionality coefficient, namely when people in the captured people photos are closer to the camera, the people in the people photos are determined to be suspicious people and early warning is carried out, and therefore the accuracy of suspicious people identification and early warning is improved.
In addition, after determining whether the second scaling factor is greater than the first scaling factor, the method further includes: and if the second scale factor is not larger than the first scale factor, determining that the person in the person photo is not the suspicious person. In the scheme, when the second proportionality coefficient is not larger than the first proportionality coefficient, the people in the captured people photo are far away from the camera, so that the people in the captured people photo are determined to be passers-by which are about to be far away from the doorway instead of suspicious people, and the accuracy of suspicious people identification and early warning is further improved.
In addition, after determining whether the first scale factor is greater than 1, the method further includes: if the first scaling factor is not more than 1, judging whether the second scaling factor is more than 1; if the second scaling factor is greater than 1, it is determined that the person in the person photograph is a suspicious person. According to the scheme, after the first scale coefficient is judged to be not more than 1, whether the second scale coefficient is larger than 1 is also judged, if the second scale coefficient is larger than 1, the fact that people in the captured people photo do not approach the doorway at the first moment but approach the doorway at the second moment is shown, the people in the people photo can be determined to be suspicious people, and therefore the accuracy of suspicious people recognition and early warning is further improved.
In addition, if the person is determined to be a suspicious person, performing early warning, specifically comprising: and if the person is determined to be a suspicious person, determining an alarm strategy corresponding to the second proportionality coefficient according to the corresponding relation between the preset alarm strategy and the proportionality coefficient, and alarming according to the alarm strategy. According to the scheme, flexible alarming is achieved through the preset corresponding relation between the alarming strategy and the proportional coefficient.
In addition, if the person is determined to be a suspicious person, performing early warning, specifically comprising: and if the person is determined to be a suspicious person, determining an alarm strategy corresponding to the first scale coefficient according to the corresponding relation between the preset alarm strategy and the scale coefficient, and alarming according to the alarm strategy. According to the scheme, flexible alarming is achieved through the preset corresponding relation between the alarming strategy and the proportional coefficient.
In addition, still include: and when the alarm is given, the captured character photo is sent to the background server so that the background server can send the captured character photo to the mobile terminal of the householder. Should put and place, send the people photo of taking a candid photograph to householder's mobile terminal, be favorable to the householder in time to learn gate situation and suspicious people.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.
Fig. 1 is a schematic flow chart of an early warning method according to a first embodiment of the present invention;
fig. 2 is a schematic flow chart of a warning method according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an early warning device according to a third embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in order to provide a better understanding of the present application in various embodiments of the present invention. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments.
The first embodiment of the invention relates to an early warning method, and the core of the embodiment lies in that an infrared sensor is used for detecting whether a person exists in a preset range; when a person is detected, triggering a camera to start and snapshotting a picture of the person; determining a proportionality coefficient of the figure photo according to the size of the captured figure photo and a preset size, and determining whether a figure in the captured figure photo is a suspicious figure according to the proportionality coefficient; and if the person is determined to be a suspicious person, early warning is carried out. According to the embodiment of the invention, an infrared sensor is used for detecting whether a person exists in a preset range, when the person is detected, a camera is triggered to start and capture a figure photo, the figure distance in the captured photo is determined directly according to the size of the figure photo captured by the camera and the proportional coefficient of the preset size, and then whether the figure is a suspicious figure is determined according to the figure distance, so that the problem of alarm missing caused when a distance sensor is used for detecting whether the figure is the suspicious figure is avoided; compared with a distance sensor, the camera is not limited by the distance when the camera captures the picture, so that the early warning method in the scheme can be used for capturing and detecting people in a large range, and long-distance early warning is realized.
The implementation details of the early warning method of the present embodiment are specifically described below, and the following description is only provided for the convenience of understanding, and is not necessary to implement the present embodiment.
The flow diagram of the early warning method in this embodiment is shown in fig. 1:
step 101: and detecting whether a person exists in a preset range by using an infrared sensor. If a person is detected, entering step 102; if no person is detected, the step 101 is continued.
Specifically, an infrared sensor is arranged at the doorway, and the infrared sensor is used for detecting whether a person is in a preset range, wherein the preset range is the detection range of the infrared sensor, and the preset range can be set by a user. When a person is detected, the person is proved to enter the detection range of the infrared sensor, and then the step 102 is carried out; when the person is not detected, the fact that the person does not enter the detection range of the infrared sensor is proved for a while, and at the moment, the infrared sensor is continuously utilized to detect whether the person exists in the detection range. It should be noted that the infrared sensor is usually in an on state, so as to detect whether a person is in a preset range in real time.
Step 102: triggering the camera and opening and snapshotting the figure photo, wherein the figure photo includes: a first photograph taken at a first time.
Specifically speaking, when the infrared sensor detects that there is a person in the preset range, trigger the camera to open and take a candid photograph of the person at the first moment, the camera here is the domestic security protection camera of fixed focus. The first time may be a time when the camera is triggered to be turned on.
Step 103: the size of the first target area in the captured first photograph is identified.
Specifically, the first target area refers to an area where a person is located in the first picture, the size of the first target area represents the size of the area where the person is located in the whole first picture, and the larger the size of the first target area (i.e., the area where the person is located) in the first picture is, the closer the person is to the camera is. In this embodiment, the area of the person in the first photograph is specifically identified by an image identification technology, and the size of the area of the person is calculated. When a plurality of persons appear in the first photograph, the region in which the person closest to the camera, that is, the person with the largest size, is located is used as the first target region of the photograph.
Step 104: a first scaling factor of the size of the first target area to a preset size is determined.
Specifically, the preset size is the size of a person in the whole picture when the person shot by the user in advance by using the camera is away from the camera by a preset distance, and when the shot distance between the person and the camera is smaller than the preset distance, the person is close to the doorway. In this embodiment, a first scale coefficient of the size of the first target area and the preset size is determined, and whether the distance between the person in the first picture and the camera is smaller than the preset distance is represented by the size of the first scale coefficient.
Compared with the mode of determining the distance between the person and the camera by using the distance sensor in the prior art, the method and the device for determining the distance between the person and the camera have the advantages that the camera with the fixed focal length is used for obtaining the person picture, the distance between the person and the camera is judged by determining the proportional coefficient of the size of the person area in the person picture and the preset size, the problem of alarm missing caused by insensitivity of the distance sensor is avoided, in addition, the camera does not have distance limitation compared with the distance sensor, and long-distance early warning can be realized.
It should be noted that, since the average heights of men, women and children are different, a plurality of preset sizes may be set, the size of the men, women and children with the average height in the whole screen at the preset position is selected and used as the corresponding preset size, before the first scale factor of the size of the first target area and the preset size is determined, it may be determined by a face recognition technology that the person in the first target area is a man, a woman or a child, so as to select the corresponding preset size and then determine the first scale factor.
Step 105: and judging whether the first scale factor is larger than 1. If the first scaling factor is greater than 1, go to step 106; if the first scaling factor is not greater than 1, proceed to step 107.
Step 106: and determining that the person in the captured person photo is a suspicious person.
Step 107: it is determined that the person in the captured photograph of the person is not a suspect person.
With reference to the foregoing steps 105 to 107, specifically, if the first scaling factor of the size of the first target area to the preset size is not greater than 1, it indicates that the size of the first target area is smaller than or equal to the preset size, that is, the distance between the person in the first picture and the camera is greater than or equal to the preset distance, and at this time, it may be determined that the person in the first picture does not approach the doorway, and the person in the first picture is determined as a non-suspicious person. If the first scale factor is greater than 1, it is indicated that the size of the first target area is greater than a preset size, that is, the distance between the person in the first picture and the camera is smaller than the preset distance, at this time, it may be determined that the person in the first picture captured approaches the doorway, and at this time, the person in the first picture may be determined as a suspicious person.
Step 108: and determining an alarm strategy corresponding to the first scale coefficient according to the corresponding relation between the preset alarm strategy and the scale coefficient, and alarming according to the alarm strategy.
Specifically, different scale coefficients reflect different distances between people, the larger the scale coefficient is, the closer the people are to the camera, and in the embodiment, different alarm strategies are adopted according to different distances between people, so that flexible alarm is realized. Presetting a corresponding relation between an alarm strategy and a proportionality coefficient, for example: when the proportionality coefficient is more than 1 and less than 2, the corresponding alarm strategy is to ring an alarm bell or broadcast a voice alarm bell to the householder so as to prompt the householder that a suspicious person approaches the doorway; when the proportionality coefficient is larger than 2 and smaller than 3, the visible doorbell or cat eye in the door can be opened at the moment, and the voice alarm bell is broadcasted to the user, so that the user can conveniently check suspicious people close to the door from the door; when the proportionality coefficient is larger than 3, the visible doorbell and the cat eye in the door can be started, and the alarm information can be sent to the mobile terminal of the householder, so that the user can know that a suspicious person is close to the door in time. And after the first proportion coefficient is determined, determining an alarm strategy according to the first proportion coefficient and the corresponding relation and alarming. In this embodiment, the corresponding relationship between the alarm policy and the scaling factor may be set by the user according to actual needs, and is not limited to the above example.
Further, when alarming is conducted, the captured people photos are sent to the background server, so that the background server can send the captured people photos to the mobile terminal of the householder, and the householder can know the door state and suspicious people in time.
Compared with the prior art, the embodiment of the invention provides an early warning method, an infrared sensor is utilized to detect whether a person exists in a preset range, when the person is detected, a camera is triggered to start and capture a figure photo, the figure distance in the captured photo is determined directly according to the size of the figure photo captured by the camera and the proportional coefficient of the preset size, and then whether the figure is a suspicious figure is determined according to the figure distance, so that the problem of alarm missing caused when the distance sensor is used for detecting whether the figure is the suspicious figure is avoided; compared with a distance sensor, the camera is not limited by the distance when the camera captures the picture, so that the early warning method in the scheme can be used for capturing and detecting people in a large range, and long-distance early warning is realized.
A second embodiment of the present invention relates to an early warning method. The second embodiment is substantially the same as the first embodiment, except that when the distance between the person in the first photo captured at the first moment and the camera is less than the preset distance, which is probably caused by passerby passing through the camera due to some reasons such as rain, in the embodiment, the first photo captured at the first moment and the second photo captured at the preset time interval are used for determining the first proportionality coefficient and the second proportionality coefficient according to the two photos, when the first proportionality coefficient is greater than 1 and the second proportionality coefficient is greater than the first proportionality coefficient, it is indicated that the person in the captured person photo is closer to the camera, and at this time, the captured person is determined to be a suspicious person and is subjected to early warning, so that the accuracy of suspicious person identification and early warning is improved.
A schematic flow diagram of a second embodiment in this embodiment is shown in fig. 2, and specifically includes:
step 201: and detecting whether a person exists in a preset range by using an infrared sensor. If a person is detected, entering step 102; if no person is detected, step 201 is continued.
Step 201 is substantially the same as step 101 in the first embodiment, and is not described herein again.
Step 202: triggering the camera and opening and snapshotting the figure photo, wherein the figure photo includes: the method comprises the steps of taking a first photo at a first moment in time and taking a second photo at a second moment in time separated by a preset duration in time.
Specifically, since the person is generally in a moving state, the position of the person in the photo captured by the camera at the previous time and the position of the person at the next time are likely to be different, so in the embodiment, after the camera is triggered to turn on and capture the first photo at the first time, the second photo is captured at the second time spaced by the first time by the preset time length, so that whether the person is a suspicious person can be better determined according to the captured photo of the person.
Step 203: the size of a first target area in the first photograph and the size of a second target area in the second photograph are identified.
Specifically, the specific manner of "recognizing the size of the first target area of the first photograph" in this embodiment is the same as the specific implementation manner of step 103 in the first embodiment, and details thereof are not repeated in this embodiment. The second target area is a human body area of a person in the first photo in the second photo, so when the size of the second target area is recognized, firstly, the position of the person in the second photo needs to be recognized by using a face recognition technology, the area of the person in the second photo is used as the second target area, and then the size of the second target area is determined.
Step 204: and determining a first proportionality coefficient of the size of the first target area and the preset size and a second proportionality coefficient of the size of the second target area and the preset size.
Specifically, the specific implementation of "determining the first scaling factor of the size of the first target region and the preset size" in the present embodiment is substantially the same as step 104 in the first embodiment, and the manner of determining the second scaling factor of the size of the second target region and the preset size is similar to the method of determining the first scaling factor, and will not be described in detail in the present embodiment.
Step 205: and judging whether the first scale factor is larger than 1. If the first scaling factor is greater than 1, go to step 206; if the first scaling factor is not greater than 1, proceed to step 209.
Specifically, since the person is usually in motion, after determining the scaling factor of the person at two moments, it is necessary to first determine whether the first scaling factor corresponding to the first picture at the first moment is greater than 1, so as to determine whether the distance between the person and the camera at the first moment is less than the preset distance. If the first scale factor is larger than 1, determining that the distance between the person and the camera at the first moment is smaller than a preset distance, and then entering step 206; if the first scaling factor is not greater than 1, it is determined that the distance between the person and the camera at the first time is greater than the preset distance, and then the process proceeds to step 209.
Step 206: and judging whether the second proportionality coefficient is larger than the first proportionality coefficient. If the second scaling factor is greater than the first scaling factor, go to step 207; if the second scaling factor is not greater than the first scaling factor, proceed to step 208.
Step 207: the person in the person picture is determined to be a suspicious person.
Step 208: it is determined that the person in the person photograph is not a suspect person.
With respect to the above steps 206 to 208, specifically, although the first scale factor obtained at the first time is greater than 1, it indicates that the distance between the person in the first picture and the camera is less than the preset distance, but may be caused when the passerby passes through the camera due to some reason such as rain. In order to improve the accuracy of suspicious character recognition and early warning, in this embodiment, after the first scaling factor is judged to be greater than 1, it is also judged whether the second scaling factor is greater than the first scaling factor, and when the second scaling factor is greater than the first scaling factor, it is indicated that the characters in the captured character picture are closer to the camera, then step 207 may be performed to determine that the characters in the captured character picture are not passersby, but suspicious characters to be close to the doorway; when the second scaling factor is not greater than the first scaling factor, indicating that the person in the captured photo of the person is further away from the camera, then step 208 may be performed to determine that the person in the captured photo of the person is a passerby about to get away from the doorway rather than a suspicious person.
Step 209: and judging whether the second proportionality coefficient is larger than 1. If the second proportionality coefficient is greater than 1, go to step 207; if the second scaling factor is not greater than 1, proceed to step 208.
Specifically, since the first scale factor obtained at the first moment is not greater than 1, it indicates that the person in the first picture is located at a distance from the camera greater than the preset distance, but it may be that the person does not come close to the camera within the time interval of capturing the first picture and the second picture. In order to improve the accuracy of suspicious character recognition and early warning, in this embodiment, after the first scaling factor is determined to be not greater than 1, it is further determined whether the second scaling factor is greater than 1, if the second scaling factor is greater than 1, it is indicated that a character in the captured character picture is close to the doorway at the second moment, and then the step 207 is entered, so that the character can also be determined as a suspicious character; if the second scaling factor is not greater than 1, it indicates that the person in the captured photo of the person is not approaching the doorway at the second time, and then step 208 is entered to determine that the person is not a suspicious person.
Step 210: and determining an alarm strategy corresponding to the second proportionality coefficient according to the corresponding relation between the preset alarm strategy and the proportionality coefficient, and alarming according to the alarm strategy.
Specifically, in this embodiment, after the person in the captured photo of the person is determined to be a suspicious person, when the second scaling factor is determined, the alarm policy may be determined according to the second scaling factor and the corresponding relationship in the first embodiment, and an alarm may be performed.
Compared with the prior art, the early warning method is provided in the embodiment of the invention, when the distance between the person in the first photo captured at the first moment and the camera is less than the preset distance and is probably caused by the fact that passerby passes through the camera due to some reasons such as rain and the like, in the embodiment, the first photo captured at the first moment and the second photo captured at the preset time interval are used for determining the first proportionality coefficient and the second proportionality coefficient according to the two photos, when the first proportionality coefficient is greater than 1 and the second proportionality coefficient is greater than the first proportionality coefficient, the person in the captured person photo is closer to the camera, and the captured person is determined to be a suspicious person and early warning is carried out, so that the accuracy of suspicious person identification and early warning is improved.
The steps of the above methods are divided for clarity, and the implementation may be combined into one step or split some steps, and the steps are divided into multiple steps, so long as the same logical relationship is included, which are all within the protection scope of the present patent; it is within the scope of the patent to add insignificant modifications to the algorithms or processes or to introduce insignificant design changes to the core design without changing the algorithms or processes.
A third embodiment of the present invention relates to an early warning apparatus, as shown in fig. 3, including at least one processor 301; and a memory 302 communicatively coupled to the at least one processor 301; the memory 302 stores instructions executable by the at least one processor 301, and the instructions are executed by the at least one processor 301, so that the at least one processor 301 can execute the above-mentioned warning method.
Where the memory 302 and the processor 301 are coupled in a bus, the bus may comprise any number of interconnected buses and bridges, the buses coupling one or more of the various circuits of the processor 301 and the memory 302. The bus may also connect various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor 301 is transmitted over a wireless medium through an antenna, which further receives the data and transmits the data to the processor 301.
The processor 301 is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And memory 302 may be used to store data used by processor 301 in performing operations.
The embodiment of the invention also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the early warning method of the embodiment.
That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the invention, and that various changes in form and details may be made therein without departing from the spirit and scope of the invention in practice.
Claims (10)
1. An early warning method, comprising:
detecting whether a person exists in a preset range by using an infrared sensor;
when a person is detected, triggering a camera to start and snapshotting a picture of the person;
determining a proportionality coefficient of the figure photo according to the size of the captured figure photo and a preset size, and determining whether a figure in the captured figure photo is a suspicious figure according to the proportionality coefficient;
and if the person is determined to be a suspicious person, early warning is carried out.
2. The warning method of claim 1, wherein the photo of the person comprises: a first photograph taken at a first time;
the method for determining the proportion coefficient of the figure photo according to the size of the figure photo captured by the snap shot and the preset size and determining whether the figure in the captured figure photo is a suspicious figure according to the proportion coefficient specifically comprises the following steps:
identifying a size of a first target area in the first photograph taken;
determining a first proportional coefficient of the size of the first target area and the preset size;
and if the first proportion coefficient is larger than 1, determining that the people in the captured people photo are suspicious people.
3. The warning method of claim 1, wherein the photo of the person comprises: the method comprises the following steps of taking a first photo at a first moment and taking a second photo at a second moment at a preset time interval;
the method for determining the proportion coefficient of the figure photo according to the size of the figure photo captured by the snap shot and the preset size and determining whether the figure in the captured figure photo is a suspicious figure according to the proportion coefficient specifically comprises the following steps:
identifying a size of a first target region in the first photograph and a size of a second target region of the second photograph;
determining a first proportionality coefficient of the size of the first target area and the preset size and a second proportionality coefficient of the size of the second target area and the preset size;
judging whether the first proportional coefficient is larger than 1;
if the first scaling factor is larger than 1, judging whether the second scaling factor is larger than the first scaling factor;
and if the second proportion coefficient is larger than the first proportion coefficient, determining that the person in the person photo is a suspicious person.
4. The warning method according to claim 3, wherein after the determining whether the second scaling factor is greater than the first scaling factor, the method further comprises:
and if the second scaling factor is not larger than the first scaling factor, determining that the person in the person photo is not a suspicious person.
5. The warning method according to claim 3, further comprising, after the determining whether the first scale factor is greater than 1:
if the first proportionality coefficient is not larger than 1, judging whether the second proportionality coefficient is larger than 1;
and if the second proportionality coefficient is larger than 1, determining that the person in the person photo is a suspicious person.
6. The warning method according to claim 3, wherein if the person is determined to be a suspicious person, the warning is performed, specifically comprising:
and if the person is determined to be a suspicious person, determining an alarm strategy corresponding to the second proportional coefficient according to the corresponding relation between a preset alarm strategy and the proportional coefficient, and alarming according to the alarm strategy.
7. The warning method according to claim 2, wherein if the person is determined to be a suspicious person, the warning is performed, specifically comprising:
and if the person is determined to be a suspicious person, determining an alarm strategy corresponding to the first proportional coefficient according to the corresponding relation between a preset alarm strategy and the proportional coefficient, and alarming according to the alarm strategy.
8. The warning method of claim 1, further comprising: and when the alarm is given, the captured figure photo is sent to a background server, so that the background server can send the captured figure photo to a mobile terminal of a user.
9. An early warning device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the warning method of any one of claims 1 to 8.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the warning method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910461434.4A CN110164074A (en) | 2019-05-30 | 2019-05-30 | A kind of method for early warning, prior-warning device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910461434.4A CN110164074A (en) | 2019-05-30 | 2019-05-30 | A kind of method for early warning, prior-warning device and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110164074A true CN110164074A (en) | 2019-08-23 |
Family
ID=67630394
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910461434.4A Withdrawn CN110164074A (en) | 2019-05-30 | 2019-05-30 | A kind of method for early warning, prior-warning device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110164074A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110807393A (en) * | 2019-10-25 | 2020-02-18 | 深圳市商汤科技有限公司 | Early warning method and device based on video analysis, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708643A (en) * | 2011-03-28 | 2012-10-03 | 无锡国科微纳传感网科技有限公司 | Invasion detection method and system |
| CN103218889A (en) * | 2012-01-18 | 2013-07-24 | 联想(北京)有限公司 | Body-separating alarm terminal and realization method thereof |
| CN107895450A (en) * | 2017-12-01 | 2018-04-10 | 何嘉艺 | A kind of alarm method, apparatus and system |
| WO2019060066A1 (en) * | 2017-09-20 | 2019-03-28 | Google Llc | Systems and methods of detecting and responding to a visitor to a smart home environment |
| CN109618130A (en) * | 2018-11-21 | 2019-04-12 | 移康智能科技（上海）股份有限公司 | A kind of alarm method, intelligent peephole and warning system |
-
2019
- 2019-05-30 CN CN201910461434.4A patent/CN110164074A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708643A (en) * | 2011-03-28 | 2012-10-03 | 无锡国科微纳传感网科技有限公司 | Invasion detection method and system |
| CN103218889A (en) * | 2012-01-18 | 2013-07-24 | 联想(北京)有限公司 | Body-separating alarm terminal and realization method thereof |
| WO2019060066A1 (en) * | 2017-09-20 | 2019-03-28 | Google Llc | Systems and methods of detecting and responding to a visitor to a smart home environment |
| CN107895450A (en) * | 2017-12-01 | 2018-04-10 | 何嘉艺 | A kind of alarm method, apparatus and system |
| CN109618130A (en) * | 2018-11-21 | 2019-04-12 | 移康智能科技（上海）股份有限公司 | A kind of alarm method, intelligent peephole and warning system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110807393A (en) * | 2019-10-25 | 2020-02-18 | 深圳市商汤科技有限公司 | Early warning method and device based on video analysis, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020125406A1 (en) | Safety guardianship method, apparatus, terminal and computer readable storage medium | |
| KR101858396B1 (en) | Intelligent intrusion detection system | |
| US20090195382A1 (en) | Video sensor and alarm system and method with object and event classification | |
| CN111656411B (en) | Recording control device, recording control system, recording control method, and storage medium | |
| CN103839346A (en) | Intelligent door and window anti-intrusion device and system and intelligent door control system | |
| CN112606796A (en) | Automatic opening and closing control method and system for vehicle trunk and vehicle | |
| KR101104656B1 (en) | Pet image detection system and method for controlling operation thereof | |
| CN105844209A (en) | Visitor identification based on infrared radiation detection | |
| CN113033521A (en) | Perimeter dynamic early warning method and system based on target analysis | |
| KR20190108218A (en) | Emergency Analysis Device and Method Using Digital Image | |
| KR102233679B1 (en) | Apparatus and method for detecting invader and fire for energy storage system | |
| CN115346060A (en) | Picture abnormity identification method and device, electronic equipment and storage medium | |
| CN110164074A (en) | A kind of method for early warning, prior-warning device and computer storage medium | |
| JP5865584B2 (en) | Specific person detection system and detection method | |
| TWI631480B (en) | Entry access system having facil recognition | |
| JP2012212217A (en) | Image monitoring device | |
| JP2010177936A (en) | Intercom device | |
| JP3088880B2 (en) | Person recognition device | |
| CN110134565A (en) | Environment light detection method and device | |
| CN106251545B (en) | A kind of intelligent family monitoring system | |
| KR101770586B1 (en) | Pedestrian detecting system and control method thereof | |
| JP5757708B2 (en) | Reporting device | |
| JP2001148843A (en) | Image pickup device and criminal prevention system using the image pickup device | |
| KR20180111150A (en) | Apparatus for extracting foreground from video and method for the same | |
| EP4343718A1 (en) | An image sensor device, method and computer program |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190823 |