CN111179583A - Community electronic fence system for artificial intelligence target recognition and configuration method thereof - Google Patents
Community electronic fence system for artificial intelligence target recognition and configuration method thereof Download PDFInfo
- Publication number
- CN111179583A CN111179583A CN202010006466.8A CN202010006466A CN111179583A CN 111179583 A CN111179583 A CN 111179583A CN 202010006466 A CN202010006466 A CN 202010006466A CN 111179583 A CN111179583 A CN 111179583A
- Authority
- CN
- China
- Prior art keywords
- electronic fence
- community
- electronic
- target
- artificial intelligence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19608—Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a community electronic fence system for artificial intelligent target recognition and a configuration method thereof, wherein the community electronic fence system is constructed based on an intelligent camera, sensing equipment and a community electronic fence management server, and is used for sensing, analyzing and responding to an civilized behavior in a community; the method comprises the steps of establishing a space area of the electronic fence by applying a target identification principle, and automatically configuring the electronic fence so as to simplify the configuration process of the electronic fence and improve the configuration efficiency of the electronic fence, so that the electronic fence technology is applied to various types of community management.
Description
Technical Field
The invention relates to the technical field of electronic fences, in particular to a community electronic fence system for artificial intelligence target recognition and a configuration method thereof.
Background
At present, electronic fence technology is applied to many occasions, such as standardization of flight of unmanned aerial vehicles, sharing of single-vehicle parking areas and the like, electronic fences are not real fences, but a virtual space area is planned and set, the electronic fences comprehensively use the Internet of things technologies such as positioning and sensing to sense a specific target object entering the virtual space area and further perform necessary control and response on the specific target object, for example, when an unmanned aerial vehicle enters the space area defined by the electronic fences, the unmanned aerial vehicle can be sensed, if the space area is a no-fly area, the sensing is responded, a limiting instruction is issued to a flight control chip of the unmanned aerial vehicle, and further the unmanned aerial vehicle cannot take off or forcibly land; or pushing the sharing bicycle into a space area defined by the electronic fence, if the space area is sensed to be a parking area, responding to the sensing, the sharing bicycle can be locked and the charging can be stopped, otherwise, the vehicle can not be locked or the charging can not be stopped, and the parking is standardized.
The electronic fence technology is not popularized in communities, and the phenomena of immobility such as parking in a mess, blocking a fire fighting channel, randomly trampling a lawn, walking a pet in a prohibited area and the like in community management are more, so that a community fence Internet of things system needs to be established, and the immobility behaviors are sensed, analyzed and responded by utilizing an intrusion sensing function; however, in a larger-scale community, a large number of different types of electronic fences need to be established, the establishment process is very complicated, firstly, a field survey needs to be performed to determine an area where the electronic fence is established in the community and the type of each electronic fence, secondly, a mapping relation between an actual space area of the electronic fence and a picture area of a video picture of an intelligent camera needs to be determined, thirdly, a configuration form needs to be established for each electronic fence by consuming a large amount of time and workload, and parameters in the form are defined and filled in.
Therefore, how to simplify the configuration process of the electronic fence and improve the configuration efficiency, so that the electronic fence can be applied to various types of community management, is a problem to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, the invention provides a community electronic fence system for artificial intelligence target identification and a configuration method thereof, wherein the community electronic fence system is constructed based on an intelligent camera, sensing equipment and a community electronic fence management server, and is used for sensing, analyzing and responding to an civilized behavior in a community; the method comprises the steps of establishing a space area of the electronic fence by applying a target identification principle, and automatically configuring the electronic fence so as to simplify the configuration process of the electronic fence and improve the configuration efficiency of the electronic fence, so that the electronic fence technology is applied to various types of community management.
To achieve the above object, the present invention generates the following electronic fence system:
an artificial intelligence target recognition community electronic fence system, comprising: the system comprises a plurality of intelligent cameras and a community electronic fence management server; wherein the content of the first and second substances,
the intelligent camera is used for shooting video pictures of a space area corresponding to the electronic fence;
the community electronic fence management server is used for acquiring video pictures shot by the intelligent camera, extracting and identifying target types and behavior types of target objects entering a space area corresponding to the electronic fence in the video pictures based on a neural network, judging compliance of the target types and the behavior types, and registering, reminding and warning property of the target types and the behavior types which are not in compliance.
Specifically, after receiving a video picture, the community electronic fence management server extracts a plurality of picture areas which are contained in continuous frame video pictures and used for establishing the electronic fence, and obtains a plurality of candidate area pictures in the extracted plurality of picture areas by using a selective search algorithm, wherein the candidate areas are areas containing target objects, and the candidate areas are extracted by using the algorithm, so that the number of unnecessary candidate areas generated in the traditional target identification algorithm is reduced, and the screening efficiency is improved; and the target type and the behavior type of the target object in the candidate area are extracted by using the convolutional neural network, so that the accuracy and the efficiency of type extraction are improved.
Preferably, the intelligent camera further comprises a sensing device, the sensing device is used for assisting the intelligent camera to sense the target type and the behavior type of the target object, specifically, different types of sensing devices can be deployed according to the monitoring requirement, and the monitoring accuracy and the monitoring efficiency of the target object are improved.
Preferably, the field of view shot by the smart camera generally covers the spatial regions corresponding to all electronic fences established in the community; each video picture shot by the intelligent cameras comprises picture areas of a plurality of electronic fences, each picture area corresponds to different types of electronic fences, a plurality of intelligent cameras are arranged to cover space areas corresponding to all the electronic fences, and monitoring holes caused by visual field limitation are effectively avoided.
Preferably, the community electronic fence management server is further configured to establish a configuration form database, and each electronic fence corresponds to one configuration form; wherein, the configuration form comprises: the ID number, the spatial position, the type and the compliance judgment rule of each electronic fence, the number of the intelligent camera corresponding to the electronic fence, the definition rule of the picture area corresponding to the intelligent camera corresponding to the electronic fence and the number of the perception equipment corresponding to the electronic fence. And the community electronic fence management server judges the target type and the behavior type according to the shooting time of the configuration form database and the video picture and by combining the duration of the behavior.
A community electronic fence configuration method for artificial intelligence target recognition comprises the following steps:
s1, establishing a signboard with a specific mark at the boundary vertex of all the space areas for establishing the electronic fence;
s2, shooting video pictures corresponding to spatial areas of all electronic fences in the community by an intelligent camera, and identifying and extracting the signboards and the positions of the video pictures where the signboards are located;
and S3, generating a configuration form corresponding to the electronic fence according to the specific identification of the signboard.
Preferably, the specific marks comprise specific color block patterns or symbols, and different specific marks represent different types of electronic fences and position coordinates of the signboard, so that all electronic fences in a community range can be conveniently and uniformly shot, the types can be acquired, and the configuration efficiency can be improved.
Preferably, the S2 includes the following specific steps: determining the type of the electronic fence and a corresponding compliance judgment rule according to the specific identifier of the electronic fence, and automatically allocating the ID number of the electronic fence and the number of the intelligent camera corresponding to the electronic fence; and connecting the positions of the signboards in the video picture, and determining the corresponding picture area of the electronic fence in the video picture.
Preferably, the method further comprises the following steps: and sending the configuration form of the electronic fence to a mobile terminal of a worker, and perfecting the configuration form of the electronic fence by the worker, wherein the configuration form comprises the serial number of the sensing equipment corresponding to the electronic fence, so that the configuration form is conveniently supplemented manually, and the perfection of the configuration form is facilitated.
Preferably, the community electronic fence management server stores all the generated configuration forms of the electronic fences in a database, and generates a configuration form database of the community electronic fences.
The invention has the following beneficial effects:
according to the technical scheme, based on the prior art, the artificial intelligence target identification community electronic fence system is designed, the civilization phenomenon is sensed, analyzed and responded, the community management is favorably strengthened, the behavior of people is normalized, the artificial intelligence target identification community electronic fence configuration method is further provided, the configuration process of the electronic fence is simplified, the configuration efficiency of the electronic fence is improved, the time length and the workload consumed in the configuration process are reduced, the electronic fence technology is favorably applied to various types of community management, and the popularization degree of the electronic fence is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a block diagram of a community electronic fence system for artificial intelligent target identification;
FIG. 2 is a schematic diagram of a community electronic fence management server;
FIG. 3 is a flow chart of a community non-civilized behavior alerting method for artificial intelligent target identification;
FIG. 4 is a flow chart of a configuration method for artificial intelligence target recognition.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. 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.
As shown in fig. 1 and 2, the present invention provides the following system:
an artificial intelligence target recognition community electronic fence system, comprising: the system comprises a plurality of intelligent cameras 1, sensing equipment 2 and a community electronic fence management server 3; wherein, community's fence management server includes: a perception module 31, an analysis module 32, a response module 33 and a database establishing module 34;
specifically, a plurality of intelligent cameras 1 are deployed in a space area where electronic fences need to be established in a community, the visual field range shot by the intelligent cameras 1 generally covers the space area corresponding to all the electronic fences in the community, and each intelligent camera 1 has a larger visual field range, so that a video picture shot by each intelligent camera 1 comprises a plurality of picture areas, each picture area corresponds to different types of electronic fences, for example, a video picture shot by one intelligent camera 1 comprises two picture areas, namely a lawn and a road, the lawn picture area corresponds to an electronic fence which prevents the lawn from being trampled, and the road picture area corresponds to an electronic fence which prohibits parking; in addition, the video picture uploaded by the smart camera 1 includes shooting time.
According to the types of electronic fences corresponding to different spatial areas, different types of sensing equipment 2 are deployed as required, the sensing equipment 2 is used for performing auxiliary judgment on the target type and the behavior type of a target object, for example, infrared temperature measuring equipment is deployed as the sensing equipment 2 in a lawn spatial area corresponding to the lawn electronic fence which is trampling-resistant, whether the target object entering the lawn is a human being, an animal or a non-biological object is distinguished through infrared remote temperature measurement, if the target object is a non-biological object, the target object may be a weeding machine or a weeding robot and the like, and then the target type and the behavior type of the target object are further analyzed through a community electronic fence management server according to a video picture shot by an intelligent camera 1; the method comprises the steps that a geomagnetic sensor is deployed in a road space area corresponding to the electronic fence which is forbidden to park, whether vehicles exist in the road space area or not is measured in an auxiliary mode through geomagnetic induction, and if the vehicles exist, the behavior types of the vehicles are further analyzed through a community electronic fence management server according to video pictures shot by the intelligent camera 1.
Specifically, the database establishing module 34 establishes a configuration form database in advance, each electronic fence corresponds to one configuration form, and the configuration form records the ID number, spatial position, type, and compliance judgment rule of each electronic fence, the number of the smart camera including the picture area corresponding to the electronic fence, the picture area definition rule corresponding to the smart camera, and the number of the sensing device corresponding to the electronic fence. For example, in an electronic fence for preventing random parking on a public road, the configuration form records the ID number of the electronic fence, the spatial position in the community (defined by the link name), the type (electronic fence prohibited from parking), the compliance determination rule (when the target type extracted from the screen area corresponding to the electronic fence is a vehicle and the behavior type is still and the stationary time exceeds a predetermined time, it is determined that the electronic fence is not compliant), the ID number (CAMERA ID) of the smart CAMERA including the screen area corresponding to the electronic fence, and the screen area definition rule (defined by the position coordinates of the boundary vertices of the screen area corresponding to the electronic fence in the video screen taken by the smart CAMERA, that is, the position coordinates of the head and end points of the link < X ≦ X1，Y1＞,＜X2,Y2>) aiming at the ID number of the geomagnetic sensor of the space area corresponding to the picture area; for another example, for an electronic fence that prevents humans and animals from trampling and destroying a lawn, the configuration form records the ID number of the electronic fence, the spatial position in the community (defined by the lawn name), the type (the electronic fence against the trampling of the lawn), the rule for compliance determination (the electronic fence is determined to be not compliant when the type of the target extracted from the area of the screen corresponding to the electronic fence is human or animal and the type of the behavior is movement), and the screen corresponding to the electronic fenceThe ID number of the intelligent CAMERA (CAMERA ID) of the region, and the picture region definition rule (defined by the position coordinates of the boundary vertex of the picture region corresponding to the electronic fence in the video picture shot by the intelligent CAMERA, namely, the position coordinates of the four vertices of the lawn space region < X1,Y1＞,＜X2,Y2＞,＜X3,Y3＞,＜X4,Y4>) the ID number of the infrared temperature measuring device aimed at the spatial region.
After the community electronic fence management server 3 acquires the shot video picture from the intelligent camera 1, the sensing module 31 extracts the target object entering the space area corresponding to the electronic fence, and identifies the target type and the behavior type of the target object, wherein the specific extraction and identification processes are as follows:
firstly, extracting a plurality of picture areas which are contained in continuous frame video pictures and establish electronic fences from video pictures shot by an intelligent camera 1, and acquiring a plurality of candidate area pictures in the extracted plurality of picture areas by using a selective search algorithm, wherein the candidate areas are areas containing target objects;
secondly, identifying a target object contained in the candidate area picture by utilizing a convolutional neural network algorithm, specifically, receiving the sample candidate area picture by each neuron of an input layer, transmitting the sample candidate area picture to each neuron of an intermediate layer, wherein the intermediate layer is an internal information processing layer, processing and transforming the sample candidate area picture to obtain target type information of the target object in the sample candidate area picture, outputting the target type information by each neuron of an output layer, comparing the output target type information with the target type information expected to be output by the sample, if the actual output is not consistent with the expected output, entering an error back propagation stage, correcting weight values of each layer according to an error gradient reduction mode by an error passing through the output layer, reversing the layers of the intermediate layer and the input layer until the error between the actual output target type information and the target type information expected to be output is reduced to an acceptable degree, stopping the learning process, obtaining a trained convolutional neural network, further inputting any clear and real candidate area picture to each neuron of an input layer of the convolutional neural network, performing processing transformation through an intermediate layer, obtaining target type information of a target object in the candidate area picture, and outputting the target type information by each neuron of an output layer;
and simultaneously, identifying the behavior type of the target object by using a convolutional neural network algorithm, obtaining a trained convolutional neural network for identifying the behavior type of the target object after the training of the process, respectively inputting a plurality of picture area pictures extracted from continuous frame video pictures to each neuron of an input layer of the convolutional neural network, processing and transforming the pictures through an intermediate layer to obtain the behavior type of the target object in the picture area pictures, and outputting behavior type information by each neuron of an output layer.
The analysis module 32 analyzes the recognized target type and behavior type according to the shooting time of the configuration form database and the video picture and by combining the duration of the behavior, and judges whether the target type and the behavior type are in compliance; if the target type and the behavior type are judged to be not in compliance, the response module 33 registers, reminds and gives a property alarm to the target type and the behavior type, so as to realize the standard of the non-civilized phenomenon, for example, recording the license plate number of the illegal parking, sending prompt information to the mobile phone of the owner registered with the license plate number, and sending alarm prompt information to the mobile phone of the property patrol security guard.
Based on the above system, the present invention proposes the following method, as shown in fig. 3:
an artificial intelligence target recognition community non-civilized behavior alarm method comprises the following steps:
the method comprises the following steps: shooting a video picture of a space area corresponding to the electronic fence by the intelligent camera;
in order to further optimize the technical characteristics, sensing equipment is also deployed to assist the intelligent camera in judging the target type and the behavior type of the target object in an auxiliary manner, for example, infrared temperature measuring equipment is deployed in a lawn space area corresponding to a trampling-proof lawn electronic fence as the sensing equipment, whether the target object entering the lawn is a person, an animal or a non-living object is distinguished through infrared remote temperature measurement, if the target object is a non-living object, the target object may be a weeding machine or a weeding robot, and the like, and then the target type and the behavior type of the target object are further analyzed through a community electronic fence management server according to a video picture shot by the intelligent camera; the method comprises the steps that a geomagnetic sensor is deployed in a road space area corresponding to the electronic fence for prohibiting parking, whether vehicles exist in the road space area or not is measured in an auxiliary mode through geomagnetic induction, and if the vehicles exist, the behavior types of the vehicles are further analyzed through a community electronic fence management server according to video pictures shot by an intelligent camera.
Step two: acquiring a video picture shot by an intelligent camera, and extracting and identifying the target type and the behavior type of a target object entering a space area corresponding to the electronic fence in the video picture based on a neural network;
specifically, a plurality of intelligent cameras are deployed in a space area where electronic fences need to be established in a community, the visual field range shot by the intelligent cameras generally covers the space area corresponding to all the electronic fences in the community, and each intelligent camera has a larger visual field range, so that a video picture shot by each intelligent camera comprises a plurality of picture areas, each picture area corresponds to different types of electronic fences, for example, a video picture shot by one intelligent camera comprises two picture areas, namely a lawn and a road, the corresponding type of the lawn picture area is an electronic fence for preventing the lawn from being trampled, and the corresponding type of the road picture area is an electronic fence for prohibiting parking; in addition, the video picture uploaded by the smart camera 1 includes shooting time.
In addition, the specific steps of extracting and identifying the target type and the behavior type of the target object are as follows:
firstly, extracting a plurality of picture areas which are contained in continuous frame video pictures and establish electronic fences from video pictures shot by an intelligent camera, and acquiring a plurality of candidate area pictures in the extracted plurality of picture areas by using a selective search algorithm, wherein the candidate areas are areas containing target objects;
secondly, training a convolutional neural network by using the sample candidate area pictures to obtain a trained convolutional neural network, further inputting any clear and real candidate area picture to each neuron of an input layer of the convolutional neural network, performing processing transformation through an intermediate layer to obtain target type information of a target object in the candidate area picture, and outputting the target type information by each neuron of an output layer;
and simultaneously, identifying the behavior type of the target object by using a convolutional neural network algorithm, specifically, respectively inputting a plurality of picture area pictures extracted from continuous frame video pictures to each neuron of an input layer of the convolutional neural network for identifying the behavior type after training, processing and transforming the pictures through an intermediate layer to obtain the behavior type of the target object in the picture area pictures, and outputting behavior type information by each neuron of the output layer.
Step three: performing compliance judgment on the target type and the behavior type;
specifically, the recognized target type and behavior type are analyzed according to the configuration form database and the shooting time of the video picture and by combining the duration of the behavior, and whether the target type and the behavior type are in compliance is judged.
Step four: and registering, reminding and alarming the property of the non-compliant target type and the behavior type.
Specifically, after judging that the target type and the behavior type are not in compliance, the target type and the behavior type are registered, reminded and alarmed for property, so as to realize the standard of the non-civilized phenomenon, for example, recording the license plate number of the illegal parking, sending prompt information to the mobile phone of the owner registered by the license plate number, and sending alarm prompt information to the mobile phone of the property patrol security guard.
As shown in figure 4 of the drawings,
a community electronic fence configuration method for artificial intelligence target recognition comprises the following steps:
s1, establishing a signboard with a specific mark at the boundary vertex of all the space areas for establishing the electronic fence;
specifically, the specific mark includes a specific color block pattern or symbol, such as a two-dimensional code, and a staff sets up or holds a signboard having the specific color block pattern or symbol at four vertices of a space area, such as a rectangular space area, where the electric fence is to be set up; different specific identifiers represent different types of electronic fences and the position coordinates of the signboard.
S2, shooting video pictures corresponding to spatial areas of all electronic fences in the community by an intelligent camera, and identifying and extracting the signboards and the positions of the video pictures where the signboards are located;
specifically, the S2 includes the following specific steps: determining the type of the electronic fence and a corresponding compliance judgment rule according to the specific identifier of the electronic fence, and automatically allocating the ID number of the electronic fence and the number of the intelligent camera corresponding to the electronic fence; and connecting the positions of the signboards in the video picture, and determining the corresponding picture area of the electronic fence in the video picture.
And S3, generating a configuration form corresponding to the electronic fence according to the specific identification of the signboard.
In order to further optimize the technical characteristics, the method further comprises the following steps: and sending the configuration form of the electronic fence to a mobile terminal of a worker, and perfecting the configuration form of the electronic fence by the worker, wherein the configuration form comprises the number of the sensing equipment corresponding to the electronic fence.
In order to further optimize the technical characteristics, the community electronic fence management server stores all the generated configuration forms of the electronic fences in a database, and generates a configuration form database of the community electronic fences.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An artificial intelligence target recognition's community electronic fence system, its characterized in that includes: the system comprises a plurality of intelligent cameras (1) and a community electronic fence management server (3); wherein the content of the first and second substances,
the community electronic fence management server comprises: a sensing module (31), an analysis module (32) and a response module (33);
the intelligent camera (1) is used for shooting video pictures of a space area corresponding to the electronic fence;
the perception module (31) is used for acquiring a video picture shot by the intelligent camera (1), and extracting and identifying the target type and the behavior type of a target object entering a space area corresponding to the electronic fence in the video picture based on a neural network;
the analysis module (32) is used for carrying out compliance judgment on the target type and the behavior type;
the response module (33) is used for registering, reminding and warning property for non-compliant object types and behavior types.
2. An artificial intelligence target recognition community electronic fence system as claimed in claim 1, further comprising a perception device (2), wherein said perception device (2) is used for assisting said intelligent camera (1) to perceive the target type and behavior type of the target object.
3. An artificial intelligence target recognition community electronic fence system as claimed in claim 1, wherein the field of view shot by the intelligent camera (1) covers the space area corresponding to all electronic fences established in the community as a whole; the video pictures shot by each intelligent camera (1) comprise picture areas of a plurality of electronic fences, and each picture area corresponds to different types of electronic fences.
4. An artificial intelligence target recognition community electronic fence system as claimed in claim 1, wherein said community electronic fence management server (3) further comprises a database building module (34); the database establishing module (34) is used for establishing a configuration form database, and each electronic fence corresponds to one configuration form; wherein, the configuration form comprises: the ID number, the spatial position, the type and the compliance judgment rule of each electronic fence, the number of the intelligent camera corresponding to the electronic fence, the definition rule of the picture area corresponding to the intelligent camera corresponding to the electronic fence and the number of the perception equipment corresponding to the electronic fence.
5. The community electronic fence system for artificial intelligence target recognition as claimed in claim 1, wherein the analysis module (32) performs compliance judgment on the target type and the behavior type according to the configuration form database and the shooting time of the video picture and the duration of the behavior.
6. A community electronic fence configuration method for artificial intelligence target identification is characterized by comprising the following steps:
s1, establishing a signboard with a specific mark at the boundary vertex of all the space areas for establishing the electronic fence;
s2, shooting video pictures corresponding to spatial areas of all electronic fences in the community by an intelligent camera, and identifying and extracting the signboards and the positions of the video pictures where the signboards are located;
and S3, generating a configuration form corresponding to the electronic fence according to the specific identification of the signboard.
7. The method as claimed in claim 6, wherein the specific mark comprises a specific color block pattern or symbol, and different specific marks represent different types of electronic fences and the position coordinates of the signboard.
8. The method for configuring community electronic fence for artificial intelligence object recognition according to claim 6, wherein the step S2 includes the following specific steps: determining the type of the electronic fence and a corresponding compliance judgment rule according to the specific identifier of the electronic fence, and automatically allocating the ID number of the electronic fence and the number of the intelligent camera corresponding to the electronic fence; and connecting the positions of the signboards in the video picture, and determining the corresponding picture area of the electronic fence in the video picture.
9. The method for configuring community electronic fence for artificial intelligence object recognition according to claim 6, further comprising the following steps: and sending the configuration form of the electronic fence to a mobile terminal of a worker, and perfecting the configuration form of the electronic fence by the worker, wherein the configuration form comprises the number of the sensing equipment corresponding to the electronic fence.
10. The method for configuring community electronic fences for artificial intelligence target identification of claim 6, wherein the community electronic fence management server stores all the generated configuration forms of the electronic fences in a database, and generates a configuration form database of the community electronic fences.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010006466.8A CN111179583A (en) | 2020-01-03 | 2020-01-03 | Community electronic fence system for artificial intelligence target recognition and configuration method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010006466.8A CN111179583A (en) | 2020-01-03 | 2020-01-03 | Community electronic fence system for artificial intelligence target recognition and configuration method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111179583A true CN111179583A (en) | 2020-05-19 |
Family
ID=70656129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010006466.8A Pending CN111179583A (en) | 2020-01-03 | 2020-01-03 | Community electronic fence system for artificial intelligence target recognition and configuration method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111179583A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111681382A (en) * | 2020-05-28 | 2020-09-18 | 天津市三源电力设备制造有限公司 | Method for detecting temporary fence crossing in construction site based on visual analysis |
| CN112465552A (en) * | 2020-11-30 | 2021-03-09 | 北京云创生活科技有限公司 | Community point counting method, device and equipment and readable storage medium |
| CN112465551A (en) * | 2020-11-30 | 2021-03-09 | 北京云创生活科技有限公司 | Community integral acquisition method and device based on block chain |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102542707A (en) * | 2010-12-09 | 2012-07-04 | 北京航天长峰科技工业集团有限公司 | Land electronic fence monitoring system |
| CN104349127A (en) * | 2013-08-05 | 2015-02-11 | 郑州学生宝电子科技有限公司 | Campus intelligent video monitoring system |
| CN104574726A (en) * | 2014-12-19 | 2015-04-29 | 欧阳秋娜 | Monitoring system and monitoring method of electronic fence |
| CN105448017A (en) * | 2015-12-22 | 2016-03-30 | 德胜（苏州）洋楼有限公司 | Community rail alarming system |
| CN107452171A (en) * | 2017-07-20 | 2017-12-08 | 中国三冶集团有限公司 | Intelligent high-end residential cell perimeter security system |
| CN107516390A (en) * | 2016-06-15 | 2017-12-26 | 重庆文客巴科技有限公司 | A kind of fence monitoring system |
| CN108206932A (en) * | 2016-12-16 | 2018-06-26 | 北京迪科达科技有限公司 | A kind of campus intelligent monitoring management system |
| US20180211117A1 (en) * | 2016-12-20 | 2018-07-26 | Jayant Ratti | On-demand artificial intelligence and roadway stewardship system |
| CN108846335A (en) * | 2018-05-31 | 2018-11-20 | 武汉市蓝领英才科技有限公司 | Wisdom building site district management and intrusion detection method, system based on video image |
| CN109670431A (en) * | 2018-12-11 | 2019-04-23 | 北京小马智行科技有限公司 | A kind of behavioral value method and device |
-
2020
- 2020-01-03 CN CN202010006466.8A patent/CN111179583A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102542707A (en) * | 2010-12-09 | 2012-07-04 | 北京航天长峰科技工业集团有限公司 | Land electronic fence monitoring system |
| CN104349127A (en) * | 2013-08-05 | 2015-02-11 | 郑州学生宝电子科技有限公司 | Campus intelligent video monitoring system |
| CN104574726A (en) * | 2014-12-19 | 2015-04-29 | 欧阳秋娜 | Monitoring system and monitoring method of electronic fence |
| CN105448017A (en) * | 2015-12-22 | 2016-03-30 | 德胜（苏州）洋楼有限公司 | Community rail alarming system |
| CN107516390A (en) * | 2016-06-15 | 2017-12-26 | 重庆文客巴科技有限公司 | A kind of fence monitoring system |
| CN108206932A (en) * | 2016-12-16 | 2018-06-26 | 北京迪科达科技有限公司 | A kind of campus intelligent monitoring management system |
| US20180211117A1 (en) * | 2016-12-20 | 2018-07-26 | Jayant Ratti | On-demand artificial intelligence and roadway stewardship system |
| CN107452171A (en) * | 2017-07-20 | 2017-12-08 | 中国三冶集团有限公司 | Intelligent high-end residential cell perimeter security system |
| CN108846335A (en) * | 2018-05-31 | 2018-11-20 | 武汉市蓝领英才科技有限公司 | Wisdom building site district management and intrusion detection method, system based on video image |
| CN109670431A (en) * | 2018-12-11 | 2019-04-23 | 北京小马智行科技有限公司 | A kind of behavioral value method and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111681382A (en) * | 2020-05-28 | 2020-09-18 | 天津市三源电力设备制造有限公司 | Method for detecting temporary fence crossing in construction site based on visual analysis |
| CN112465552A (en) * | 2020-11-30 | 2021-03-09 | 北京云创生活科技有限公司 | Community point counting method, device and equipment and readable storage medium |
| CN112465551A (en) * | 2020-11-30 | 2021-03-09 | 北京云创生活科技有限公司 | Community integral acquisition method and device based on block chain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111179583A (en) | Community electronic fence system for artificial intelligence target recognition and configuration method thereof | |
| CN110569772B (en) | Method for detecting state of personnel in swimming pool | |
| KR102122859B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| WO2010099470A1 (en) | Image processing sensor systems | |
| CN110619277A (en) | Multi-community intelligent deployment and control method and system | |
| Zin et al. | A Markov random walk model for loitering people detection | |
| CN110809248A (en) | Community fence Internet of things system with intrusion sensing function | |
| CN111163294A (en) | Building safety channel monitoring system and method for artificial intelligence target recognition | |
| JP4975801B2 (en) | Monitoring method and monitoring apparatus using hierarchical appearance model | |
| CN112084892B (en) | Road abnormal event detection management device and method thereof | |
| CN108805184B (en) | Image recognition method and system for fixed space and vehicle | |
| CN114358980A (en) | Intelligent community property management system and method based on Internet of things | |
| CN114612813A (en) | Identity recognition method, model training method, device, equipment and storage medium | |
| KR102309106B1 (en) | Situation linkage type image analysis device | |
| CN114817991A (en) | Internet of vehicles image desensitization method and system | |
| CN113486885A (en) | License plate recognition method and device, electronic equipment and storage medium | |
| GB2499449A (en) | Surveillance by face recognition using colour display of images | |
| KR20210158037A (en) | Method for tracking multi target in traffic image-monitoring-system | |
| CN111914704B (en) | Tricycle manned identification method and device, electronic equipment and storage medium | |
| KR102141781B1 (en) | Object Re-IdentificatioApparatus Using Locally Matching Method and Its Method | |
| CN112861711A (en) | Regional intrusion detection method and device, electronic equipment and storage medium | |
| Mekni et al. | Real-time smart parking integration in intelligent transportation systems (its) | |
| CN113536847A (en) | Industrial scene video analysis system and method based on deep learning | |
| CN111914844A (en) | Image identification method and device, electronic equipment and storage medium | |
| JP7479535B1 (en) | Person detection system and person detection method |
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 |