CN111178239A - Intelligent community-based personnel loitering early warning method and system - Google Patents
Intelligent community-based personnel loitering early warning method and system Download PDFInfo
- Publication number
- CN111178239A CN111178239A CN201911374326.XA CN201911374326A CN111178239A CN 111178239 A CN111178239 A CN 111178239A CN 201911374326 A CN201911374326 A CN 201911374326A CN 111178239 A CN111178239 A CN 111178239A
- Authority
- CN
- China
- Prior art keywords
- personnel
- loitering
- candidate
- monitoring
- preset
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012544 monitoring process Methods 0.000 claims abstract description 60
- 238000004458 analytical method Methods 0.000 claims abstract description 40
- 230000008859 change Effects 0.000 claims abstract description 35
- 239000011159 matrix material Substances 0.000 claims description 36
- 238000000605 extraction Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 8
- 238000011176 pooling Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a smart community-based personnel loitering early warning method, which comprises the following steps: the method comprises the steps that a server periodically obtains monitoring images from a monitoring network, wherein the monitoring network comprises at least one camera, and the camera is arranged in any area of a community; the server inputs the monitoring image into a first analysis network, and the first analysis network outputs a selection result of the candidate persons in the monitoring image and the position frame bodies selected as the candidate persons; the server calculates the position information change of the position frame corresponding to the candidate personnel in real time, periodically judges whether the change total amount of the position information change accords with the characteristics of a preset loitering personnel, if so, defines the candidate personnel as the loitering personnel, and sends the position information and the corresponding image corresponding to the loitering personnel to a preset property management center. Compared with the existing loitering person identification technical scheme, the loitering person identification method is higher in identification accuracy.
Description
Technical Field
The embodiment of the invention relates to the field of image detection, in particular to a method, a system, computer equipment and a storage medium for early warning of wandering of people based on an intelligent community.
Background
Along with social development and development of smart cities, the intelligent video monitoring system receives more and more attention from people. The safety requirements of people on living environment are getting stronger, and the intelligent video monitoring system becomes an important tool and means of a safety guarantee and defense system.
The existing intelligent video monitoring system can only monitor and analyze some basic enclosure crossing functions, but cannot identify the parts of wandering personnel outside the community enclosure, so that the early warning capability is low.
Disclosure of Invention
In order to solve the above problem, an embodiment of the present invention provides a method for warning wandering of people based on an intelligent community, including the following steps:
the method comprises the steps that a server periodically obtains monitoring images from a monitoring network, wherein the monitoring network comprises at least one camera, and the camera is arranged in any area of a community;
the server inputs the monitoring image into a first analysis network, the first analysis network is formed by connecting a preset convolution feature extraction structure and a full connection layer, and the first analysis network outputs a selection result of a candidate person in the monitoring image and a position frame body corresponding to the candidate person selected;
the server calculates the position information change of the position frame corresponding to the candidate personnel in real time, periodically judges whether the change total amount of the position information change accords with the characteristics of a preset loitering personnel, if so, defines the candidate personnel as the loitering personnel, and sends the position information and the corresponding image corresponding to the loitering personnel to a preset property management center.
Preferably, the convolution feature extraction structure is formed by interleaving fifteen convolution layers and five pooling layers, wherein the convolution kernel used by the convolution layer is 3 × 3.
Preferably, the full connection layer is set to be of a two-classification structure.
Preferably, the step of inputting the monitoring image into a first analysis network by the server, where the first analysis network is formed by connecting a preset convolution feature extraction structure and a full connection layer, and the step of outputting the selection result of the candidate person in the monitoring image and the position frame selected as the candidate person to correspond to by the first analysis network includes:
the server forms a pixel value matrix according to pixel values corresponding to the arranged pixel points of the monitoring image and inputs the pixel value matrix to the first analysis network;
the pixel value matrix is firstly input into a convolution feature extraction structure in the first analysis network, the pixel value matrix and the convolution kernel perform product-sum operation to generate a second matrix, the second matrix is processed through a pooling layer to form a third matrix, and the third matrix is output to the full connection layer by the convolution feature extraction structure;
and after receiving the third matrix, the full-connection layer performs summation operation on the third matrix and a preset weight coefficient to obtain the final score, judges whether the final score is greater than a preset threshold value, if so, the source input image contains human body features, and outputs the candidate personnel image selected as the human body in the image and the position frame body corresponding to the candidate personnel image by using a regression function.
Preferably, the position frame corresponding to the selected candidate person is a rectangle, the corner points are w, x, y, and z, the position frame is characterized by the corner points, and the coordinates of the position frame are (w, x, y, and z).
Preferably, the step of calculating, by the server, a change in the position information of the position frame corresponding to the candidate person in real time includes:
the server calculates the coordinate of a central point B of the position frame body in real time to obtain a numerical array of the coordinate of the central point B, and the numerical array correspondingly represents the position information change of the position frame body.
Preferably, the step of periodically determining whether the total change amount of the position information change meets a characteristic of a loitering person of a threshold, if so, defining the candidate person as the loitering person, and sending the position information and the corresponding image corresponding to the loitering person to a preset property management center includes:
the server performs subtraction operation on adjacent elements of the numerical array to obtain a second numerical array, adds all elements in the second numerical array to obtain an element sum, judges whether the element sum is larger than a preset threshold value, defines the candidate as the loitering person if the element sum is larger than the preset threshold value, and sends position information and a corresponding image corresponding to the loitering person to a preset property management center.
The embodiment of the invention also provides a system for early warning of wandering of people, which comprises:
the system comprises an acquisition module, a monitoring module and a monitoring module, wherein the acquisition module is used for periodically acquiring a monitoring image from a monitoring network, the monitoring network comprises at least one camera, and the camera is arranged in any area of a community;
the analysis module is used for inputting the monitoring image into a first analysis network, the first analysis network is formed by connecting a preset convolution feature extraction structure and a full connection layer, and the first analysis network outputs a selection result of a candidate person in the monitoring image and a position frame body corresponding to the candidate person selected;
and the early warning module is used for calculating the position information change of the position frame corresponding to the candidate personnel in real time, periodically judging whether the change total amount of the position information change accords with the characteristics of a preset loitering personnel, if so, defining the candidate personnel as the loitering personnel, and sending the position information and the corresponding image corresponding to the loitering personnel to a preset property management center.
An embodiment of the present invention further provides a computer device, where the computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the computer program, when executed by the processor, implements the method for early warning of wandering of people based on smart community as described above.
An embodiment of the present invention further provides a computer storage medium, which stores a computer program, where the computer program is capable of being executed by at least one processor to perform the method for warning that a person loitering based on a smart community as described above.
The intelligent community-based personnel loitering early warning method can effectively identify loitering personnel inside and outside the community, and has higher identification accuracy compared with the existing loitering personnel identification technical scheme.
Drawings
FIG. 1 is a flowchart illustrating steps of a method for warning wandering of a person in an intelligent community;
FIG. 2 is a schematic diagram illustrating the process modules of an intelligent community-based system for warning wandering;
fig. 3 is a schematic diagram of a hardware structure of the computer device of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
It should be understood that although the terms first, second, etc. may be used to describe the designated key in embodiments of the present invention, the designated key should not be limited to these terms. These terms are only used to distinguish specified keywords from each other. For example, the first specified keyword may also be referred to as the second specified keyword, and similarly, the second specified keyword may also be referred to as the first specified keyword, without departing from the scope of embodiments of the present invention.
The word "if" as used herein may be interpreted as referring to "at … …" or "when … …" or "corresponding to a determination" or "in response to a detection", depending on the context. Similarly, the phrase "if determined" or "if detected (a stated condition or time)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
Referring to fig. 1, an embodiment of the present invention provides a method for warning wandering of people based on an intelligent community, including:
step S100, a server periodically acquires a monitoring image from a monitoring network, wherein the monitoring network comprises at least one camera, and the camera is arranged in any area of a community.
Specifically, a server acquires a monitoring image from a monitoring network at a preset frequency, wherein the setting of the acquisition frequency is set according to an actual scene, the existing popular third-generation network monitoring system is preferred by the monitoring network, the server sends a call request to a reserved interface of the monitoring network, and the monitoring network directly returns the monitoring image to which the request points.
Step S200, the server inputs the monitoring image into a first analysis network, the first analysis network is formed by connecting a preset convolution feature extraction structure and a full connection layer, and the first analysis network outputs a selection result of the candidate persons in the monitoring image and a position frame body corresponding to the selected candidate persons.
Specifically, the first analysis network is formed by a convolution feature extraction structure and a full connection layer, the convolution feature extraction structure is connected with the full connection layer in data transmission, and the convolution feature extraction structure sends an output result to the full connection layer to perform scoring and rating operation.
And then, the full-connection layer judges the judged category of the source input image according to the calculated category score, and outputs the category with the highest score.
Step S300, the server calculates the position information change of the position frame corresponding to the candidate in real time, periodically judges whether the total change amount of the position information change accords with the characteristics of a preset loitering person, defines the candidate as the loitering person if the change amount accords with the characteristics of the preset loitering person, and sends the position information and the corresponding image corresponding to the loitering person to a preset property management center.
Specifically, the server calculates the position of the region image corresponding to the candidate person on the parallel route of the full connection layer by using a preset regression function, and gives a rectangular frame to the region for calibration and characterization after the calculation is completed.
Then, the overall identification step does not identify a single frame image, but identifies multiple frame images or continuous frame images, so that after a period of time, the output candidate personnel data is also an array comprising multiple position data, each position data corresponds to the position information of a position frame, the array comprising the multiple position data corresponds to the change of the position information of the candidate personnel as a whole, the overall length of the route of the candidate personnel is calculated by the array data, whether the overall length of the route is greater than a preset threshold value or not is judged, if the overall length of the route is greater than the preset threshold value, the candidate personnel meet the characteristics of the loitering personnel, the candidate personnel are redefined and named as loitering personnel, and the instant position information corresponding to the loitering personnel and the corresponding screenshot of the monitoring image comprising the content of the loitering personnel are sent to a property management center.
The intelligent community-based personnel loitering early warning method can effectively identify loitering personnel inside and outside the community, and has higher identification accuracy compared with the existing loitering personnel identification technical scheme.
Optionally, the convolution feature extraction structure is formed by interleaving fifteen convolution layers and five pooling layers, where a convolution kernel used by a convolution layer is 3 × 3.
Optionally, the full connection layer is set to be a two-classification structure.
Specifically, the full connection layer is set to be a two-classification structure, namely two categories of a human body or a non-human body, data output by the convolution feature extraction structure is matrix data with each row being an element and extending in a column shape, each column is designed with a preset weight value for judging each category, and a value in an interval of 0 to 1 is obtained through a normalization formula to represent the probability that an input image belongs to the human body or the non-human body.
Optionally, in step S200, the server inputs the monitored image into a first analysis network, where the first analysis network is formed by connecting a preset convolution feature extraction structure and a full connection layer, and the step of outputting the selected result of the candidate person in the monitored image and the position frame selected as the candidate person corresponding to the first analysis network includes:
step S210, the server forms a pixel value matrix according to pixel values corresponding to arranged pixel points of the monitoring image, and inputs the pixel value matrix to the first analysis network.
Specifically, the input first analysis network is not the monitoring image itself, but is used for displaying the bottom layer pixel value of the monitoring image, and forms a pixel value matrix according to the arrangement position of the pixel points and the numerical value arrangement sequence of the corresponding matrix, and then inputs the pixel value matrix to the first analysis network.
Step S220, the pixel value matrix is first input to a convolution feature extraction structure in the first analysis network, the pixel value matrix and the convolution kernel perform product-sum operation to generate a second matrix, the second matrix is processed by a pooling layer to form a third matrix, and the third matrix is output by the convolution feature extraction structure to the full connection layer.
Specifically, in the convolution characteristic structure, the pixel value matrix needs to perform product-sum operation with convolution kernels in the convolution characteristic structure due to excessive information content of the pixel value matrix, so that pixel dimensionality is reduced, then a pooling layer is used for sampling, that is, pixel point information with the highest pixel value is selected from every 4 × 4 area for retention, and the rest 3 pixel point information is discarded.
Step S230, after receiving the third matrix, the full connection layer performs summation operation on the third matrix and a preset weight coefficient to obtain the final score, determines whether the final score is greater than a preset threshold, if so, the source input image includes human body features, and outputs a candidate person image selected as a human body in the image and a position frame corresponding to the candidate person image by using a regression function.
Optionally, the position frame corresponding to the selected candidate person is a rectangle, corner points of the position frame are w, x, y, and z, the position frame is characterized by the corner points, and coordinates of the position frame are (w, x, y, and z).
Optionally, the step of calculating, by the server, the change of the position information of the position frame corresponding to the candidate person in real time includes:
the server calculates the coordinate of a central point B of the position frame body in real time to obtain a numerical array of the coordinate of the central point B, and the numerical array correspondingly represents the position information change of the position frame body.
Illustratively, the four corner points a of the frame body are (1,2), B is (3,2), C (3,6), and D (1,6), then the coordinates of the center point are ((3+1) ÷ 2, (6+2) ÷ 2), the calculation is completed, that is, (2,4), and then the coordinates of the center point B of the frame body are (2, 4). After image recognition is performed for a period of time, the coordinates of the center point B obtained are (3,4), (3,4), (3,5), (3,6), (3,7), (3,8),
(3,9),(3,10). The numerical array B of the center point B ═ [ (3,4), (3,4), (3,5), (3,6), (3,7), (3,8), (3,9), (3,10) ].
Optionally, the step S300 of periodically determining whether the total change amount of the change of the position information meets a feature of a loitering person of a threshold, if so, defining the candidate person as the loitering person, and sending the position information and the corresponding image corresponding to the loitering person to a preset property management center includes:
the server performs subtraction operation on adjacent elements of the numerical array to obtain a second numerical array, adds all elements in the second numerical array to obtain an element sum, judges whether the element sum is larger than a preset threshold value, defines the candidate as the loitering person if the element sum is larger than the preset threshold value, and sends position information and a corresponding image corresponding to the loitering person to a preset property management center.
Continuing with the above exemplary contents, if the numerical array B of the center point B is [ (3,4), (3,4), (3,5), (3,6), (3,7), (3,8), (3,9), (3,10) ], and the distance array C converted by the basic distance calculation is [0,1,1,1,1, 1], the element sum is 6, the preset distance threshold is 28, the value of the element sum is only 6, and is much smaller than the set threshold, it is determined that the candidate is not a loiter person.
The embodiment of the invention also provides a system for early warning of wandering of people, which comprises:
the system comprises an acquisition module 100, a monitoring module and a display module, wherein the acquisition module is used for periodically acquiring a monitoring image from a monitoring network, the monitoring network comprises at least one camera, and the camera is arranged in any area of a community;
an analysis module 200, configured to input the monitoring image into a first analysis network, where the first analysis network is formed by connecting a preset convolution feature extraction structure and a full connection layer, and the first analysis network outputs a selection result of a candidate person in the monitoring image and a position frame corresponding to the selected candidate person;
the early warning module 300 is configured to calculate a change in position information of a position frame corresponding to the candidate person in real time, periodically determine whether a total change amount of the change in position information meets a feature of a preset loitering person, define the candidate person as the loitering person if the change amount meets the feature of the preset loitering person, and send position information and a corresponding image corresponding to the loitering person to a preset property management center.
Please refer to fig. 3, which is a schematic diagram of a hardware architecture of a computer device according to an embodiment of the present invention. In the present embodiment, the computer device 2 is a device capable of automatically performing numerical calculation and/or information processing in accordance with a preset or stored instruction. The computer device 2 may be a personal computer, a tablet computer, a mobile phone, a smart phone, or a rack server, a blade server, a tower server, or a cabinet server (including an independent server or a server cluster composed of a plurality of servers) for providing a virtual client. As shown, the computer device 2 at least includes, but is not limited to, a memory 21, a processor 22, a network interface 23, and a smart community-based personnel loitering warning system 20, which are communicatively connected to each other through a system bus, wherein:
in this embodiment, the memory 21 includes at least one type of computer-readable storage medium including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a secure digital (secure digital) SD card, a flash card (FlashCard) or the like provided on the computer device 20, and of course, the memory 21 may also include both an internal storage unit and an external storage device of the computer device 2. In this embodiment, the memory 21 is used for storing an operating system installed on the computer device 2 and various application software, such as program codes of the intelligent community-based personnel loitering the early warning system 20. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.
the network interface 23 may comprise a wireless network interface or a limited network interface, and the network interface 23 is typically used for establishing a communication connection between the computer device 2 and other electronic apparatuses. For example, the network interface 23 is used to connect the computer device 2 with an external terminal necklace, establish a data transmission channel and a communication connection between the computer device 2 and an external interrupt, and the like via a network. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a global system for mobile communications (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth (Bluetooth), or Wi-Fi.
In this embodiment, the article reminder system 20 stored in the memory 21 can also be divided into one or more program modules, and the one or more program modules are stored in the memory 21 and executed by one or more processors (in this embodiment, the processor 22) to complete the present invention.
In addition, the present embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by a processor implements a corresponding function. The computer-readable storage medium of the embodiment is used for the intelligent community-based personnel loitering early warning system 20, and when being executed by the processor, the intelligent community-based personnel loitering early warning method of the invention is realized.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A people loitering early warning method based on an intelligent community is characterized by comprising the following steps:
the method comprises the steps that a server periodically obtains monitoring images from a monitoring network, wherein the monitoring network comprises at least one camera, and the camera is arranged in any area of a community;
the server inputs the monitoring image into a first analysis network, the first analysis network is formed by connecting a preset convolution feature extraction structure and a full connection layer, and the first analysis network outputs a selection result of a candidate person in the monitoring image and a position frame body corresponding to the candidate person selected;
the server calculates the position information change of the position frame corresponding to the candidate personnel in real time, periodically judges whether the change total amount of the position information change accords with the characteristics of a preset loitering personnel, if so, defines the candidate personnel as the loitering personnel, and sends the position information and the corresponding image corresponding to the loitering personnel to a preset property management center.
2. The intelligent community-based personnel loitering early warning method according to claim 1, wherein the convolution feature extraction structure is formed by interweaving fifteen convolution layers and five pooling layers, wherein a convolution kernel used by a convolution layer is 3 x 3 structure.
3. The intelligent community-based personnel loitering early warning method according to claim 1, wherein the full connection layer is set to be of a two-classification structure.
4. The intelligent community-based personnel loitering early warning method according to claim 2, wherein the server inputs the monitoring image into a first analysis network, the first analysis network is formed by connecting a preset convolution feature extraction structure and a full connection layer, and the step of outputting the selected result of the candidate personnel in the monitoring image and the position frame body selected as the candidate personnel comprises the following steps:
the server forms a pixel value matrix according to pixel values corresponding to the arranged pixel points of the monitoring image and inputs the pixel value matrix to the first analysis network;
the pixel value matrix is firstly input into a convolution feature extraction structure in the first analysis network, the pixel value matrix and the convolution kernel perform product-sum operation to generate a second matrix, the second matrix is processed through a pooling layer to form a third matrix, and the third matrix is output to the full connection layer by the convolution feature extraction structure;
and after receiving the third matrix, the full-connection layer performs summation operation on the third matrix and a preset weight coefficient to obtain the final score, judges whether the final score is greater than a preset threshold value, if so, the source input image contains human body features, and outputs the candidate personnel image selected as the human body in the image and the position frame body corresponding to the candidate personnel image by using a regression function.
5. The intelligent community-based personnel loitering early warning method according to claim 4, wherein the position frame body corresponding to the selected candidate personnel is a rectangle with corner points w, x, y, z, the position frame body is characterized by the corner points, and the position frame body coordinates are (w, x, y, z).
6. The intelligent community-based personnel loitering early warning method according to claim 5, wherein the step of calculating the position information change of the position frame corresponding to the candidate personnel in real time by the server comprises:
the server calculates the coordinate of a central point B of the position frame body in real time to obtain a numerical array of the coordinate of the central point B, and the numerical array correspondingly represents the position information change of the position frame body.
7. The intelligent community-based personnel loitering warning method according to claim 6, wherein the step of periodically determining whether the total change amount of the position information changes meets the characteristic of loitering personnel of a threshold value, if so, defining the candidate personnel as the loitering personnel, and sending the position information and the corresponding image corresponding to the loitering personnel to a preset property management center comprises the steps of:
the server performs subtraction operation on adjacent elements of the numerical array to obtain a second numerical array, adds all elements in the second numerical array to obtain an element sum, judges whether the element sum is larger than a preset threshold value, defines the candidate as the loitering person if the element sum is larger than the preset threshold value, and sends position information and a corresponding image corresponding to the loitering person to a preset property management center.
8. A person loitering warning system, comprising:
the system comprises an acquisition module, a monitoring module and a monitoring module, wherein the acquisition module is used for periodically acquiring a monitoring image from a monitoring network, the monitoring network comprises at least one camera, and the camera is arranged in any area of a community;
the analysis module is used for inputting the monitoring image into a first analysis network, the first analysis network is formed by connecting a preset convolution feature extraction structure and a full connection layer, and the first analysis network outputs a selection result of a candidate person in the monitoring image and a position frame body corresponding to the candidate person selected;
and the early warning module is used for calculating the position information change of the position frame corresponding to the candidate personnel in real time, periodically judging whether the change total amount of the position information change accords with the characteristics of a preset loitering personnel, if so, defining the candidate personnel as the loitering personnel, and sending the position information and the corresponding image corresponding to the loitering personnel to a preset property management center.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the computer program when executed by the processor implements the intelligent community based personnel loitering warning method as claimed in any one of claims 1 to 7.
10. A computer storage medium storing a computer program executable by at least one processor to perform the intelligent community-based method of loitering people forewarning as claimed in claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911374326.XA CN111178239A (en) | 2019-12-27 | 2019-12-27 | Intelligent community-based personnel loitering early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911374326.XA CN111178239A (en) | 2019-12-27 | 2019-12-27 | Intelligent community-based personnel loitering early warning method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111178239A true CN111178239A (en) | 2020-05-19 |
Family
ID=70657511
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911374326.XA Pending CN111178239A (en) | 2019-12-27 | 2019-12-27 | Intelligent community-based personnel loitering early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111178239A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106454253A (en) * | 2016-11-02 | 2017-02-22 | 北京弘恒科技有限公司 | Method and system for detecting area wandering |
| CN108961339A (en) * | 2018-07-20 | 2018-12-07 | 深圳辰视智能科技有限公司 | A kind of point cloud gestures of object estimation method, device and its equipment based on deep learning |
-
2019
- 2019-12-27 CN CN201911374326.XA patent/CN111178239A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106454253A (en) * | 2016-11-02 | 2017-02-22 | 北京弘恒科技有限公司 | Method and system for detecting area wandering |
| CN108961339A (en) * | 2018-07-20 | 2018-12-07 | 深圳辰视智能科技有限公司 | A kind of point cloud gestures of object estimation method, device and its equipment based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 周佳怡: "《基于卷积神经网络的图像目标检测方法研究》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112071425B (en) | Data processing method and device, computer equipment and storage medium | |
| CN111860140B (en) | Target event detection method, device, computer equipment and storage medium | |
| CN111860430B (en) | Identification method and device of fighting behavior, storage medium and electronic device | |
| CN113159147A (en) | Image identification method and device based on neural network and electronic equipment | |
| WO2021051547A1 (en) | Violent behavior detection method and system | |
| CN112132265B (en) | Model training method, cup-disk ratio determining method, device, equipment and storage medium | |
| CN110956122A (en) | Image processing method and device, processor, electronic device and storage medium | |
| US20180005022A1 (en) | Method and device for obtaining similar face images and face image information | |
| CN111489290A (en) | Face image super-resolution reconstruction method and device and terminal equipment | |
| CN108628442B (en) | Information prompting method and device and electronic equipment | |
| CN112149570B (en) | Multi-person living body detection method, device, electronic equipment and storage medium | |
| CN113392681A (en) | Human body falling detection method and device and terminal equipment | |
| CN111159452A (en) | Method and system for reminding forgetful article, computer equipment and storage medium | |
| CN111340213A (en) | Neural network training method, electronic device, and storage medium | |
| CN111126049B (en) | Object relation prediction method, device, terminal equipment and readable storage medium | |
| CN111767867A (en) | Text detection method, model training method and corresponding devices | |
| CN111476144B (en) | Pedestrian attribute identification model determining method and device and computer readable storage medium | |
| CN110796068A (en) | Drowning detection method and system for community swimming pool | |
| CN111178239A (en) | Intelligent community-based personnel loitering early warning method and system | |
| CN111814653A (en) | Method, device, equipment and storage medium for detecting abnormal behaviors in video | |
| CN110705420A (en) | Elevator car advertisement accurate pushing method and device and storage medium | |
| CN113807413B (en) | Object identification method and device and electronic equipment | |
| CN115171192A (en) | Face key point detection method and device | |
| CN114330885A (en) | Method, device and equipment for determining target state and storage medium | |
| CN114202804A (en) | Behavior action recognition method and device, processing equipment and storage medium |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200519 |