CN110807886A - Community security early warning method and system - Google Patents
Community security early warning method and system Download PDFInfo
- Publication number
- CN110807886A CN110807886A CN201911027521.5A CN201911027521A CN110807886A CN 110807886 A CN110807886 A CN 110807886A CN 201911027521 A CN201911027521 A CN 201911027521A CN 110807886 A CN110807886 A CN 110807886A
- Authority
- CN
- China
- Prior art keywords
- human body
- early warning
- preset
- variable
- video stream
- 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 34
- 230000002159 abnormal effect Effects 0.000 claims abstract description 39
- 238000001514 detection method Methods 0.000 claims abstract description 23
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000012544 monitoring process Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 5
- 230000009191 jumping Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 abstract description 2
- 238000010191 image analysis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000010304 firing Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000010365 information processing 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
- 238000011176 pooling Methods 0.000 description 1
- OLBCVFGFOZPWHH-UHFFFAOYSA-N propofol Chemical compound CC(C)C1=CC=CC(C(C)C)=C1O OLBCVFGFOZPWHH-UHFFFAOYSA-N 0.000 description 1
- 229960004134 propofol Drugs 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
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
- G08B13/19—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 infrared-radiation detection systems
-
- 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
-
- 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
- G08B13/19695—Arrangements wherein non-video detectors start video recording or forwarding but do not generate an alarm themselves
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a community safety early warning method, which comprises the following steps: the method comprises the steps that a server monitors an abnormal signal uploaded by an enclosure infrared sensing device, wherein the abnormal signal is generated by an enclosure crossing event, and if the server monitors the uploaded abnormal signal, a preset first variable is assigned to be true; the server pulls the video stream collected by the camera, extracts a single-frame picture and sends the single-frame picture to the human body recognition module to recognize a human body target in the picture; the human body identification module outputs a human body target identification result, the human body target identification result is input to the early warning detection module for early warning detection, and if the output result is that an abnormal condition occurs, the preset second variable is true; and performing AND gate operation on the first variable and the second variable, and if the result is true, sending early warning information to a monitoring center. The community safety early warning method, the community safety early warning system, the computer equipment and the storage medium can reduce the false alarm rate.
Description
Technical Field
The embodiment of the invention relates to the field of image processing, in particular to a community safety early warning method and a community safety early warning system.
Background
At present, a plurality of communities are surrounded by enclosing walls or guardrails, and the silence and the safety of the communities are ensured. However, people often climb over the enclosing wall in the cell to facilitate the drawing, or thieves climb over the enclosing wall to illegally enter the cell. If the intention of people around the enclosure can be monitored and an alarm can be given in time, the above events can be greatly reduced.
At present, an enclosure crossing early warning system mainly adopts an infrared sensor form and gives an alarm when sensing an infrared signal above an enclosure; and the other cells adopt a traditional video monitoring algorithm, a line is drawn on the enclosing wall, and an alarm is given when a person touches the line. Even some of the cells simply add sharp objects such as glass frit to the top of the enclosure to prevent unauthorized enclosure surging.
The infrared sensor is adopted, firstly, the cost is high, a large number of infrared sensors are needed, and the requirement on the performance of equipment is high. Second, false alarms are more serious because of the possibility of outdoor temperatures, fallen leaves, etc. causing false alarms.
Disclosure of Invention
In order to solve the above problems, an embodiment of the present invention provides a community security early warning method, including the following steps:
the method comprises the steps that a server monitors an abnormal signal uploaded by an enclosure infrared sensing device, wherein the abnormal signal is generated by an enclosure crossing event, and if the server monitors the uploaded abnormal signal, a preset first variable is assigned to be true;
the server pulls a video stream collected by the camera, the high-definition video stream is coded through a preset format, the server receives the high-definition video stream, and the uploaded compressed video stream is decoded through a preset video decoding library, wherein the video stream is a collected image around a community enclosure;
after the server finishes the decoding of the video stream, extracting a single-frame picture and sending the single-frame picture into a human body recognition module for human body target recognition in the picture;
the human body identification module outputs a human body target identification result, the human body target identification result is input to the early warning detection module for early warning detection, and if the output result is that an abnormal condition occurs, the preset second variable is true;
and performing AND gate operation on the first variable and the second variable, and if the result is true, sending early warning information to a monitoring center.
Preferably, the preset encoding format of the high-definition video stream is an h.264/h.265 format.
Preferably, the step of extracting the single-frame picture and sending the single-frame picture to the human body recognition module for human body target recognition in the picture comprises:
extracting the single frame picture;
converting the image information carried by the single frame of picture into a matrix, and generating a plurality of characteristic layers through a preset convolution kernel;
and further determining whether each characteristic layer contains human body characteristics or not through a softmax function for the characteristic layers.
Preferably, the human body recognition module outputs a human body target recognition result, the human body target recognition result is input to the early warning detection module for early warning detection, and if the output result indicates that an abnormal condition occurs, the step of assigning a preset second variable to be true comprises the following steps:
the human body identification module outputs the human body target identification result to the early warning monitoring module;
and the early warning monitoring module calculates the weight sum of each characteristic layer in the human body target recognition result through a preset weight ratio, and if the weight sum is greater than a preset threshold value, the occurrence of an abnormal condition is judged and a preset second variable is assigned to be true.
Preferably, the training process of the preset weight ratio is performed around a two-class cross-entropy loss function, which is of the form:
log(yt|yp)＝-(yt*log(yp)+(1-yt)*log(1-yp))
preferably, the step of generating a plurality of feature layers by using a preset convolution kernel includes:
and selecting an image feature matrix with the same size for the single-frame picture according to the set size of the output matrix, and performing dot product operation on the image feature matrix and the convolution kernel to obtain a plurality of output matrices, wherein each numerical value in the output matrices is used for representing image information carried by the feature layer.
Preferably, after the step of performing the click operation on the image feature matrix and the convolution kernel, the method further includes:
and moving the convolution kernel on the input matrix along the horizontal step length, performing click operation, and jumping to the next horizontal position after circulating twice.
The embodiment of the invention also provides a community safety early warning system, which comprises:
the first variable module is used for monitoring an abnormal signal uploaded by the enclosure infrared sensing device by the server, wherein the abnormal signal is generated by an enclosure crossing event, and if the server monitors the uploaded abnormal signal, the preset first variable is assigned as true;
the video acquisition module is used for the server to pull the video stream acquired by the camera, the high-definition video stream is encoded through a preset format, the server receives the high-definition video stream, and the uploaded compressed video stream is decoded through a preset video decoding library, wherein the video stream is an acquired image around a community enclosure;
the human body recognition module is used for extracting a single-frame picture and sending the single-frame picture into the human body recognition module for recognizing a human body target in the picture after the server finishes decoding the video stream;
the second variable module is used for outputting a human target recognition result by the human body recognition module, inputting the human target recognition result to the early warning detection module for early warning detection, and if the output result is that an abnormal condition occurs, determining that the preset second variable is true;
and the logic operation module is used for carrying out AND gate operation on the first variable and the second variable, and sending early warning information to a monitoring center if the result is true.
The 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 capable of running on the processor, and the computer program is implemented by the processor to implement the above-mentioned community security early warning method when executed by the processor.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and the computer program is executable by at least one processor, so that the at least one processor executes the steps of the above-mentioned community security early warning method.
According to the community safety early warning method, the community safety early warning system, the computer equipment and the storage medium, after the sensor detects that abnormal condition signals such as wall turning and the like occur, the server pulls the monitoring image of the relevant position to perform image analysis, and then the results of the sensor and the image analysis are combined, so that whether the abnormal condition occurs or not is finally judged, the false alarm rate can be reduced, and the accuracy of safety early warning monitoring is improved.
Drawings
FIG. 1 is a flowchart illustrating steps of a community security early warning method according to the present invention;
FIG. 2 is a schematic diagram of a program module of the community security early warning system provided in the present invention;
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 community security early warning method, including:
step S100, a server monitors an abnormal signal uploaded by an enclosure infrared sensing device, wherein the abnormal signal is generated by an enclosure crossing event, and if the server monitors the uploaded abnormal signal, a preset first variable is assigned to be true.
Specifically, be provided with infrared sensor on the enclosure, in case take place someone and cross the enclosure action, the light beam that infrared sensor emitted is sheltered from, and the low level that the sensor normally exported will change into the high level, generally speaking, the server will be received through the transmission line the high level signal that the sensor sent sets for to cross the enclosure incident, in case receive the high level signal that the sensor sent, then judge to produce and cross the enclosure incident, in fact, the drop of leaf and the sheltering from of sensor light beam all can be caused to other animals climb the wall head, and the action trigger frequency of misreporting is higher.
In addition, in order to complete subsequent combination judgment, the server judges that a first variable is set for the wall turning triggered by the sensor, and when a high-level signal is transmitted by the sensor, the value of the first variable is assigned and updated to true, namely true.
Step S200, the server pulls the video stream collected by the camera, the high-definition video stream is coded through a preset format, the server receives the high-definition video stream, the uploaded compressed video stream is decoded through a preset video decoding library, and the video stream is the collected image around the community fence.
Step S300, after the server finishes the video stream decoding, extracting a single frame picture and sending the single frame picture into a human body recognition module to carry out human body target recognition in the picture.
Specifically, after the server completes video stream decoding again, a single frame of picture is extracted by an SVM vector machine and sent to a human body recognition module for human body target recognition in the picture, wherein the human body recognition module is recognized by a fast-RCNN network, the fast-RCNN network is composed of 4 layer structures and is used as a CNN network target detection method, the fast-RCNN firstly uses a group of basic conv + relu + firing layers to extract feature maps of input image, and the feature maps are used for subsequent RPN layers and full connection layers
2)、RPN(Region Proposal Networks):
The RPN is mainly used for generating region explosals, firstly, a stack of Anchor boxes is generated, after the Anchor boxes are cut and filtered, the Anchor boxes are judged to belong to a foreground (forkround) or a background (background) through softmax, namely, an object or is not an object, so that the two-classification is realized; at the same time, the other branch bounding box regression correction anchor box forms a more accurate propofol (note: more accurate here with respect to the next box regression of the following full link layer)
3)、Roi Pooling：
The layer obtains a proseal feature map with a fixed size by utilizing the prosals generated by the RPN and the feature map obtained by the last layer of the VGG16, and the target can be identified and positioned by utilizing the full-connection operation after the layer enters the layer
4)、Classifier：
The Roi poolling layer is formed into a feature map with a fixed size to perform full connection operation, Softmax is used to perform classification of specific categories, and meanwhile, L1 Loss is used to complete bounding box regression operation to obtain the accurate position of the object.
In step S400, the human body recognition module outputs a human body target recognition result, and inputs the human body target recognition result to the early warning detection module for early warning detection, and if the output result is that an abnormal condition occurs, the preset second variable is true.
Specifically, the class output in step S300 is subjected to a second classification determination, the existing output is a plurality of classes, but the present invention changes the class into the second classification, that is, the two classes are classified into two classes, that is, "someone turns over the wall" and "nobody turns over the wall", if the classification result is "someone turns over the wall", the output result is that an abnormal condition occurs, and a value "true", that is, true, is given to the preset second variable.
And S500, performing AND gate operation on the first variable and the second variable, and if the result is true, sending early warning information to a monitoring center.
Specifically, an AND gate operation is performed on a first variable and a second variable, if the first variable is true and the second variable is true, the true AND gate calculation result is true, the occurrence of a wall turning event is finally determined, and preset early warning information is sent to a monitoring center along a preset path.
According to the community safety early warning method provided by the embodiment of the invention, after the sensor detects the occurrence of abnormal condition signals such as wall turning and the like, the server pulls the monitoring image of the relevant position to perform image analysis, and then the results of the sensor and the image analysis are combined, so that whether the abnormal condition occurs is finally judged, the false alarm rate can be reduced, and the accuracy of safety early warning monitoring is improved.
Optionally, the preset encoding format of the high-definition video stream is h.264/h.265 format.
Specifically, the coding structure of h.265/HEVC is similar to that of h.264/AVC, and mainly includes intra prediction (intra prediction), inter prediction (inter prediction), transform (transform), quantization (quantization), deblocking filter (deblocking filter), entropy coding (entropy coding), but in the HEVC coding structure, the whole is divided into three basic units, namely, Coding Unit (CU), Prediction Unit (PU), and Transform Unit (TU).
h.265/HEVC provides more different tools to reduce the code rate than h.264/AVC, where the size of each macroblock (macroblock/MB) in h.264 is a fixed 16 × 16 pixels in coding units, and the coding unit of h.265 can be selected from the smallest 8 × 8 to the largest 64 × 64.
Optionally, the step S300 of extracting a single frame of picture and sending the single frame of picture to the human body recognition module for human body target recognition in the picture includes:
step S310 extracts the single frame picture.
Step S320 converts the image information carried by the single frame image into a matrix, and generates a plurality of feature layers by a preset convolution kernel.
Step S330, determining whether each characteristic layer contains human body characteristics or not through a softmax function for the characteristic layers.
Optionally, the human body recognition module outputs a human body target recognition result, the human body target recognition result is input to the early warning detection module for early warning detection, and if the output result indicates that an abnormal condition occurs, the step of assigning a preset second variable to be true includes:
the human body identification module outputs the human body target identification result to the early warning monitoring module;
and the early warning monitoring module calculates the weight sum of each characteristic layer in the human body target recognition result through a preset weight ratio, and if the weight sum is greater than a preset threshold value, the occurrence of an abnormal condition is judged and a preset second variable is assigned to be true.
Optionally, the training process of the preset weight ratio is performed around a two-class cross entropy loss function, which is in the form of:
log(yt|yp)＝-(yt*log(yp)+(1-yt)*log(1-yp))
optionally, the step of generating a plurality of feature layers by using a preset convolution kernel includes:
and selecting an image feature matrix with the same size for the single-frame picture according to the set size of the output matrix, and performing dot product operation on the image feature matrix and the convolution kernel to obtain a plurality of output matrices, wherein each numerical value in the output matrices is used for representing image information carried by the feature layer.
Optionally, after the step of performing the click operation on the image feature matrix and the convolution kernel, the method further includes:
and moving the convolution kernel on the input matrix along the horizontal step length, performing click operation, and jumping to the next horizontal position after circulating twice.
The embodiment of the invention also provides a community safety early warning system, which comprises:
the first variable module 100 is used for monitoring an abnormal signal uploaded by the enclosure infrared sensing device by a server, wherein the abnormal signal is generated by an enclosure crossing event, and if the server monitors the uploaded abnormal signal, the preset first variable is assigned as true;
the video acquisition module 200 is configured to pull a video stream acquired by a camera by the server, encode the high-definition video stream in a preset format, receive the high-definition video stream by the server, and decode the uploaded compressed video stream through a preset video decoding library, where the video stream is an acquired image around a community enclosure;
the human body recognition module 300 is used for extracting a single frame picture and sending the single frame picture into the human body recognition module for human body target recognition in the picture after the server finishes the video stream decoding;
a second variable module 400, configured to output a human target recognition result by the human body recognition module, and input the human target recognition result to the early warning detection module for early warning detection, where if the output result is that an abnormal condition occurs, the preset second variable is true;
and the logic operation module 500 is configured to perform an and gate operation on the first variable and the second variable, and send early warning information to the monitoring center if the result is true.
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 smartphone, 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), and the like, and is configured to provide 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 community security pre-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 memory Card (Flash Card), etc. 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 in the computer device 2 and various application software, such as a program code of the community security 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.
Processor 22 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data Processing chip in some embodiments. The processor 22 is typically used to control the overall operation of the computer device 2. In this embodiment, the processor 22 is configured to execute the program code stored in the memory 21 or process data, for example, execute the community security early warning system 20, so as to implement the community security early warning method.
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 of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth (Bluetooth), Wi-Fi, and the like.
In this embodiment, the community security early warning system 20 stored in the memory 21 may be further 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 community security early warning system 20, and when being executed by a processor, the computer readable storage medium implements the community security early warning method of the present invention.
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 community safety early warning method is characterized by comprising the following steps:
the method comprises the steps that a server monitors an abnormal signal uploaded by an enclosure infrared sensing device, wherein the abnormal signal is generated by an enclosure crossing event, and if the server monitors the uploaded abnormal signal, a preset first variable is assigned to be true;
the server pulls a video stream collected by the camera, the high-definition video stream is coded through a preset format, the server receives the high-definition video stream, and the uploaded compressed video stream is decoded through a preset video decoding library, wherein the video stream is a collected image around a community enclosure;
after the server finishes the decoding of the video stream, extracting a single-frame picture and sending the single-frame picture into a human body recognition module for human body target recognition in the picture;
the human body identification module outputs a human body target identification result, the human body target identification result is input to the early warning detection module for early warning detection, and if the output result is that an abnormal condition occurs, the preset second variable is true;
and performing AND gate operation on the first variable and the second variable, and if the result is true, sending early warning information to a monitoring center.
2. The community safety precaution method according to claim 1, wherein the high definition video stream preset encoding format is h.264/h.265 format.
3. The community safety early warning method according to claim 1, wherein the step of extracting the single frame picture and sending the single frame picture to the human body recognition module for human body target recognition in the picture comprises the following steps:
extracting the single frame picture;
converting the image information carried by the single frame of picture into a matrix, and generating a plurality of characteristic layers through a preset convolution kernel;
and further determining whether each characteristic layer contains human body characteristics or not through a softmax function for the characteristic layers.
4. The community safety early warning method according to claim 1, wherein the human body recognition module outputs a human body target recognition result, the human body target recognition result is input to an early warning detection module for early warning detection, and if the output result indicates that an abnormal condition occurs, the step of assigning a preset second variable as true comprises the following steps:
the human body identification module outputs the human body target identification result to the early warning monitoring module;
and the early warning monitoring module calculates the weight sum of each characteristic layer in the human body target recognition result through a preset weight ratio, and if the weight sum is greater than a preset threshold value, the occurrence of an abnormal condition is judged and a preset second variable is assigned to be true.
5. The community safety precaution method according to claim 4, wherein the training process of the preset weight ratio is performed around a two-class cross entropy loss function, which is of the form:
log(yt|yp)＝-(yt*log(yp)+(1-yt)*log(1-yp))。
6. the community safety precaution method according to claim 3, wherein the step of generating a plurality of feature layers by a preset convolution kernel includes:
and selecting an image feature matrix with the same size for the single-frame picture according to the set size of the output matrix, and performing dot product operation on the image feature matrix and the convolution kernel to obtain a plurality of output matrices, wherein each numerical value in the output matrices is used for representing image information carried by the feature layer.
7. The community safety precaution method according to claim 6, wherein the step of performing a click operation on the image feature matrix and the convolution kernel further comprises:
and moving the convolution kernel on the input matrix along the horizontal step length, performing click operation, and jumping to the next horizontal position after circulating twice.
8. A community safety precaution system, comprising:
the first variable module is used for monitoring an abnormal signal uploaded by the enclosure infrared sensing device by the server, wherein the abnormal signal is generated by an enclosure crossing event, and if the server monitors the uploaded abnormal signal, the preset first variable is assigned as true;
the video acquisition module is used for the server to pull the video stream acquired by the camera, the high-definition video stream is encoded through a preset format, the server receives the high-definition video stream, and the uploaded compressed video stream is decoded through a preset video decoding library, wherein the video stream is an acquired image around a community enclosure;
the human body recognition module is used for extracting a single-frame picture and sending the single-frame picture into the human body recognition module for recognizing a human body target in the picture after the server finishes decoding the video stream;
the second variable module is used for outputting a human target recognition result by the human body recognition module, inputting the human target recognition result to the early warning detection module for early warning detection, and if the output result is that an abnormal condition occurs, determining that the preset second variable is true;
and the logic operation module is used for carrying out AND gate operation on the first variable and the second variable, and sending early warning information to a monitoring center if the result is true.
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 community security pre-warning method as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, having stored therein a computer program, the computer program being executable by at least one processor to cause the at least one processor to perform the steps of the community safety precaution method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911027521.5A CN110807886A (en) | 2019-10-28 | 2019-10-28 | Community security early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911027521.5A CN110807886A (en) | 2019-10-28 | 2019-10-28 | Community security early warning method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110807886A true CN110807886A (en) | 2020-02-18 |
Family
ID=69489224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911027521.5A Pending CN110807886A (en) | 2019-10-28 | 2019-10-28 | Community security early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110807886A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112184520A (en) * | 2020-08-28 | 2021-01-05 | 恒大智慧科技有限公司 | Community security evaluation method, server and computer readable storage medium |
| CN114038144A (en) * | 2021-10-12 | 2022-02-11 | 中国通信建设第三工程局有限公司 | AI-based community security monitoring system and method |
| CN114913663A (en) * | 2021-02-08 | 2022-08-16 | 腾讯科技（深圳）有限公司 | Anomaly detection method and device, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001034856A (en) * | 1999-07-15 | 2001-02-09 | Matsushita Electric Ind Co Ltd | Security system |
| CN101976489A (en) * | 2010-10-15 | 2011-02-16 | 李原 | Laser-vision linked night invasion detection device |
| CN107729799A (en) * | 2017-06-13 | 2018-02-23 | 银江股份有限公司 | Crowd's abnormal behaviour vision-based detection and analyzing and alarming system based on depth convolutional neural networks |
| CN109117794A (en) * | 2018-08-16 | 2019-01-01 | 广东工业大学 | A kind of moving target behavior tracking method, apparatus, equipment and readable storage medium storing program for executing |
| CN208922419U (en) * | 2018-04-25 | 2019-05-31 | 四川通服智能科技有限公司 | A kind of intelligent safety defense monitoring system |
-
2019
- 2019-10-28 CN CN201911027521.5A patent/CN110807886A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001034856A (en) * | 1999-07-15 | 2001-02-09 | Matsushita Electric Ind Co Ltd | Security system |
| CN101976489A (en) * | 2010-10-15 | 2011-02-16 | 李原 | Laser-vision linked night invasion detection device |
| CN107729799A (en) * | 2017-06-13 | 2018-02-23 | 银江股份有限公司 | Crowd's abnormal behaviour vision-based detection and analyzing and alarming system based on depth convolutional neural networks |
| CN208922419U (en) * | 2018-04-25 | 2019-05-31 | 四川通服智能科技有限公司 | A kind of intelligent safety defense monitoring system |
| CN109117794A (en) * | 2018-08-16 | 2019-01-01 | 广东工业大学 | A kind of moving target behavior tracking method, apparatus, equipment and readable storage medium storing program for executing |
Non-Patent Citations (4)
| Title |
|---|
| KK123K: "Faster R-CNN详解", 《CSDN，HTTPS://BLOG.CSDN.NET/KK123K/ARTICLE/DETAILS/86554226》 * |
| 张传雷 等: "《基于图像分析的植物及其病虫害识别方法研究》", 31 October 2018 * |
| 文常保 等: "《人工神经网络理论及应用》", 31 March 2019 * |
| 风间悠香: "计算机视觉基础-2——图像分类与卷积网络介绍", 《HTTPS://WWW.CNBLOGS.COM/LEOKALE-ZZ/ARCHIVE/2004/01/13/11157364.HTML》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112184520A (en) * | 2020-08-28 | 2021-01-05 | 恒大智慧科技有限公司 | Community security evaluation method, server and computer readable storage medium |
| CN114913663A (en) * | 2021-02-08 | 2022-08-16 | 腾讯科技（深圳）有限公司 | Anomaly detection method and device, computer equipment and storage medium |
| CN114038144A (en) * | 2021-10-12 | 2022-02-11 | 中国通信建设第三工程局有限公司 | AI-based community security monitoring system and method |
| CN114038144B (en) * | 2021-10-12 | 2023-04-14 | 中国通信建设第三工程局有限公司 | AI-based community security monitoring system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110807886A (en) | Community security early warning method and system | |
| CN112287816B (en) | Dangerous work area accident automatic detection and alarm method based on deep learning | |
| US20150078444A1 (en) | Method and system for coding or recognizing of surveillance videos | |
| CN110390340B (en) | Feature coding model, training method and detection method of visual relation detection model | |
| CN109544870B (en) | Alarm judgment method for intelligent monitoring system and intelligent monitoring system | |
| CN113628404A (en) | Method and device for reducing invalid alarm | |
| CN115909260A (en) | Method and system for early warning of workplace intrusion based on machine vision | |
| CN113869205A (en) | Object detection method and device, electronic equipment and storage medium | |
| KR20200119372A (en) | Artificial Neural Network Based Object Region Detection Method, Device and Computer Program Thereof | |
| CN113139428A (en) | Target identification method, edge device, frontier defense monitoring system and readable storage medium | |
| Sefat et al. | Implementation of vision based intelligent home automation and security system | |
| CN111507342A (en) | Image processing method, device and system and storage medium | |
| CN113673311A (en) | Traffic abnormal event detection method, equipment and computer storage medium | |
| CN115103157A (en) | Video analysis method and device based on edge cloud cooperation, electronic equipment and medium | |
| CN110853272A (en) | Bus safety monitoring method, device, equipment and storage medium | |
| CN110648499A (en) | Safety early warning method for community old people and computer storage medium | |
| CN110659997A (en) | Data cluster identification method and device, computer system and readable storage medium | |
| CN114445663A (en) | Method, apparatus and computer program product for detecting challenge samples | |
| CN114120172A (en) | Video-based target detection method and device, electronic equipment and storage medium | |
| CN116246287B (en) | Target object recognition method, training device and storage medium | |
| Negri | Estimating the queue length at street intersections by using a movement feature space approach | |
| CN114973224A (en) | Character recognition method and device, electronic equipment and storage medium | |
| CN114842411A (en) | Group behavior identification method based on complementary space-time information modeling | |
| CN111225178A (en) | Video monitoring method and system based on object detection | |
| KR102530635B1 (en) | Object Region Detection Method, Device and Computer Program For Traffic Information and Pedestrian Information Thereof |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200218 |