CN207164939U - Periphery intrusion preventing device based on target position information fusion - Google Patents
Periphery intrusion preventing device based on target position information fusion Download PDFInfo
- Publication number
- CN207164939U CN207164939U CN201720950736.4U CN201720950736U CN207164939U CN 207164939 U CN207164939 U CN 207164939U CN 201720950736 U CN201720950736 U CN 201720950736U CN 207164939 U CN207164939 U CN 207164939U
- Authority
- CN
- China
- Prior art keywords
- intrusion
- circumference
- periphery
- target
- intrusion alarm
- 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.)
- Active
Links
Abstract
The utility model proposes the periphery intrusion preventing device merged based on target position information, periphery intrusion preventing equipment is communicated with circumference intrusion alarm server, periphery intrusion preventing equipment is by circumference intrusion alarm unit, main control unit forms with CCTV camera, circumference intrusion alarm unit detects and positions intrusion target, warning message is sent to main control unit, main control unit is according to intrusion target quantity and positional information in warning message, CCTV camera focal length is set dynamically, determine target classification region, and judge target type, uploading warning message gives circumference intrusion alarm server simultaneously, circumference intrusion alarm server is according to the timestamp for receiving warning message, the video monitoring data of storage corresponding period;The target position information that the present apparatus is exported based on circumference intrusion alarm unit, dynamic adjust CCTV camera focal length, determine video object specification area, add object space resolution ratio, improve target classification accuracy rate, reduce the rate of false alarm of periphery intrusion preventing.
Description
Technical field
It the utility model is related to a kind of periphery intrusion preventing device, especially a kind of circumference based on target position information fusion
Anti-intrusion device, belong to intelligent security guard technical field.
Background technology
Periphery intrusion preventing is the important skill that the non-permitted target such as protection important area, prevention personnel, vehicle enters the region
Art means.By years development, occur infrared emission, microwave to penetrating, tension fence, vibration optical fiber, intelligent video analysis,
(It is buried)A variety of periphery intrusion preventing technologies such as leaky cable, discrete MEMS vibrating sensors, CW with frequency modulation FMCW radars.
When rate of false alarm refers to that no target occurs, due to external interference, to cause periphery intrusion preventing system to be mistakenly considered target illegal
Invasion produces alarm, is a core technology parameter for weighing periphery intrusion preventing system practical application effect.Due to outdoor environment
Complexity, weather condition is changeable, uncontrollable disturbing factor is more, and existing periphery intrusion preventing system all suffers from how reducing system
The technological challenge of rate of false alarm.
With the development of periphery intrusion preventing technology, new periphery intrusion preventing system such as ultra-wideband leakage cable, discrete
MEMS vibrating sensors, FMCW radars etc. are respectively provided with target positioning and multiple target detection ability, target location accuracy are general
Within 10 meters.But due to being disturbed by various factors under complex environment, however it remains higher rate of false alarm.
On the other hand, the intelligent video analysis technology for being conventionally used to periphery intrusion preventing is based primarily upon moving-target and background separation
Technology and artificial setting virtual perimeter domain mode realize target acquisition, and target classification ability is low, easily by illumination condition, target
The factor such as posture and the movement of non-targets of interest influences.
Develop with the technology of artificial intelligence, can have in automatic identification frame out which object and they be located at respectively
Picture target detection where turns into the study hotspot of computer vision field, R-CNN, Faster R- successively occurs
The many algorithms such as CNN, R-FCN, YOLO, SSD.But the accuracy rate of relative image classification up to more than 96%, because target detection relates to
And multiple links such as more candidate region search, feature extraction and territorial classifications, algorithm complex is high, poor real, and detection is accurate
Rate is relatively low, and the Average Accuracy for being currently based on VOC standard testing collection reaches as high as 88%.In addition, the detection of small size target is industry
The generally acknowledged problem in boundary, the Average Accuracy of the test set COCO comprising many Small objects are less than 40% at present.
The content of the invention
The problem of the utility model influences practical application effect for existing periphery intrusion preventing rate of false alarm height, with target
The circumference intrusion alarm technology of stationkeeping ability(Such as FMCW radars)On the basis of, combine sensation target detection technique, based on week
The target position information of boundary's intrusion alarm equipment output, dynamic adjusts the focal length of video camera, and determines video object classification analysis
The candidate region of processing, while increase the resolution ratio of object space, the accuracy rate of target classification is improved, filters out non-targeted object
Caused false alarm, reduce the rate of false alarm of periphery intrusion preventing.
To realize above technical purpose, the technical solution of the utility model is:Circumference based on target position information fusion
Anti-intrusion device, including circumference intrusion alarm server and the periphery intrusion preventing equipment for being deployed in zone of protection, it is characterised in that:
The periphery intrusion preventing equipment is communicated by communication link with circumference intrusion alarm server, the periphery intrusion preventing equipment
Including circumference intrusion alarm unit, main control unit, CCTV camera, communication unit and power supply unit, the main control unit difference
It is connected, and is connected by communication unit with circumference intrusion alarm server, institute with circumference intrusion alarm unit and CCTV camera
State CCTV camera to be connected with circumference intrusion alarm server by communication unit, said supply unit is invaded with circumference report respectively
Alert unit, main control unit, CCTV camera connect with communication unit, and said supply unit provides direct current for periphery intrusion preventing equipment
Working power;
The circumference intrusion alarm unit is used for automatic Detection location intrusion target, concurrently send warning message to give master control list
Member, the main control unit are Built-in Image processing unit GPU mobile processor, and the mobile processor is responsible for processing circumference and entered
The warning message of alarm unit is invaded, intrusion target quantity and positional information in warning message, monitoring camera is set dynamically
The lens focus of machine and the visual zone for determining target classification, and run the embedded target sorting algorithm based on depth network and sentence
Disconnected target type, while upload warning message and give circumference intrusion alarm server, the CCTV camera is used to monitor invasion mesh
Simultaneously uploaded videos monitoring data gives circumference intrusion alarm server, the circumference intrusion alarm server root in mark position region
According to the timestamp for receiving warning message, the video monitoring data for corresponding to the period is stored.
Further, the communication unit is fiber optic communication or ethernet communication, when periphery intrusion preventing equipment enters with circumference
When invading the distance between Alarm Server more than the farthest transmission range of Ethernet, communication link uses fiber optic communication mode;Otherwise,
Communication link uses more inexpensive ethernet communication mode.
Further, the circumference intrusion alarm server be responsible for whole circumference deployment one or more circumferences prevent
Equipment, storage, the monitor video data and circumference intrusion alarm message of retrieval circumference are invaded, and are carried out with other security protection subsystems
Data interaction and linkage;
Management of the circumference intrusion alarm server to periphery intrusion preventing equipment includes:Multiple periphery intrusion preventing equipment
Time synchronized, for target classification depth network model storage and maintenance, periphery intrusion preventing equipment state collection and work
Parameter configuration.
Further, the Content of Communication bag between the periphery intrusion preventing equipment and the circumference intrusion alarm server
Include:The monitor video encoding stream of CCTV camera is uploaded to circumference intrusion alarm server, with target type and target location
Warning message etc. data reports to circumference intrusion alarm server, periphery intrusion preventing equipment on circumference intrusion alarm server
Oneself state, periphery intrusion preventing equipment is reported to download depth network training model, the circumference of renewal from circumference intrusion alarm server
Intrusion alarm server(1)Setting to periphery intrusion preventing equipment parameters.
Further, when circumferential length is more than the monitoring range of single periphery intrusion preventing equipment, by disposing multiple weeks
Boundary's anti-intrusion set realizes the covering of whole circumference.
Preferably, the circumference intrusion alarm unit is FMCW radars, it is not small to the detection range of personnel targets
In 100m, target location error is no more than 5m, and the destination number that can be detected simultaneously is not less than 10.
Further, the CCTV camera is low-light (level) high-definition camera, built-in red equipped with power zoom optical lens
Outer supplementary lighting module, light filling can be carried out at night.
Preferably, the video resolution of the CCTV camera be not less than 1920 × 1080, frame per second not less than 30 frames/
Second, built in video compressed encoding function, video flowing that can be after output squeezing;The night of infrared supplementary lighting module under the conditions of normal meteorological
Between irradiation distance be not less than 100m, the maximum focal length of optical lens can ensure human body target at distance 100m in various postures
Under pixel count be not less than 50000.
In order to further realize above technical purpose, the utility model also proposes a kind of based on target position information fusion
Periphery intrusion preventing method, it is characterised in that comprise the following steps:
Step 1: periphery intrusion preventing equipment is started shooting with circumference intrusion alarm server, and network is established by communication unit
Communication, the periphery intrusion preventing equipment complete the time synchronized with circumference intrusion alarm server;
Step 2: according to the scope of monitor area, circumference intrusion alarm server sets the focal length of CCTV camera, it is ensured that
Monitored picture is clear and covers whole monitor area, and the CCTV camera is to the continuous uploaded videos of circumference intrusion alarm server
Monitoring data stream, circumference intrusion alarm server storage video monitoring data;
The alarm of circumference intrusion alarm unit is set dynamically according to weather conditions, circumference intrusion alarm server in step 3
Threshold value, circumference intrusion alarm unit are detected based on current alarm threshold value to the circumference intrusion behavior in surveillance area;
Step 4: when circumference intrusion alarm unit detects intrusion behavior, the master control list into periphery intrusion preventing equipment
Member reports the warning message comprising intrusion target quantity and positional information;
Step 5: positional information of the main control unit according to destination number and each target, the focal length of CCTV camera is adjusted,
Ensure that all targets are both present in monitor video picture, while ensure that each target has higher spatial resolution;
Step 6: positional information of the main control unit according to destination number and each target, the visual area of target classification is determined
Domain, the embedded target sorting algorithm based on depth network is run, judges target type;
Step 7: if target is intrusion target, reported by communication unit comprising target type and positional information, report
The warning message of alert time;If target is non-intrusive target, this warning message is filtered out, and upload comprising time of origin
False alarm message;
Step 8: after circumference intrusion alarm server receives warning message or false alarm message, based on the time in message
Stamp, video and the storage of corresponding period are searched for, is recorded as alarm logging or false alarm.
Further, the main control unit in the step 6 uses different insertions according to destination number and target location
Formula target classification algorithm:If target is multiple, the position based on each target determines the candidate region of target classification respectively, adopts
Target detection is carried out with Faster R-CNN algorithms;If target is 1, the position based on the target determines object classification process
Region, using the region as a width complete image, target classification is carried out using the image classification algorithms based on depth network model.
The beneficial effects of the utility model are:
1)Based on the target position information of circumference intrusion alarm unit detection, the focal length of CCTV camera is set dynamically, carries
The spatial resolution of high target(Increase size of the target in picture), small size target detection problem is avoided, lifts target
Classification accuracy, reduce circumference invasion rate of false alarm;The various sizes of training set of all kinds of targets need not be established simultaneously, reduces training
Data set scale;
3)Based on the target position information of circumference intrusion alarm unit detection, the candidate region of sets target detection, reduce
Region quantity and search arithmetic amount, reduce the complexity of algorithm of target detection, improve algorithm real-time.
Brief description of the drawings
Fig. 1 is the overall structure diagram of the utility model periphery intrusion preventing device.
Fig. 2 is the structured flowchart of the utility model periphery intrusion preventing equipment.
Fig. 3 is the schematic flow sheet of the utility model periphery intrusion preventing method.
Brief description of the drawings:1- circumference intrusion alarms server, 2- periphery intrusion preventings equipment, 21- circumference intrusion alarms unit,
22- main control units, 23- CCTV cameras, 24- communication units and 25- power supply units.
Embodiment
With reference to specific drawings and examples, the utility model is described in further detail.
With reference to the accompanying drawings shown in 1, based on the periphery intrusion preventing device of target position information fusion, including circumference intrusion alarm clothes
Business device 1 and the periphery intrusion preventing equipment 2 for being deployed in zone of protection, it is characterised in that:The periphery intrusion preventing equipment 2 passes through communication
Link is communicated with circumference intrusion alarm server 1, when circumferential length is more than the monitoring range of single periphery intrusion preventing equipment 2
When, the covering of whole circumference is realized by disposing multiple periphery intrusion preventing equipment 2;
The circumference intrusion alarm server 1 is responsible for one or more periphery intrusion preventing equipment of whole circumference deployment
2, storage, the monitor video data and circumference intrusion alarm message of retrieval circumference, and carry out data friendship with other security protection subsystems
Mutually with linkage;
1 management to periphery intrusion preventing equipment 2 of the circumference intrusion alarm server includes:Multiple periphery intrusion preventing equipment
2 time synchronized, for target classification depth network model storage and maintenance, the state acquisition of periphery intrusion preventing equipment 2 with
Running parameter configures.
With reference to the accompanying drawings shown in 2, the periphery intrusion preventing equipment 2 realize to the detection of the extremely low rate of false alarm of intrusion behavior with it is upper
Report, including circumference intrusion alarm unit 21, main control unit 22, CCTV camera 23, communication unit 24 and power supply unit 25, it is described
Main control unit 22 is connected with circumference intrusion alarm unit 21 and CCTV camera 23 respectively, and is entered by communication unit 24 with circumference
Invade Alarm Server 1 to connect, the CCTV camera 23 is connected by communication unit 24 with circumference intrusion alarm server 1, institute
Power supply unit 25 is stated to be connected with circumference intrusion alarm unit 21, main control unit 22, CCTV camera 23 and communication unit 24 respectively,
Said supply unit 25 is that periphery intrusion preventing equipment 2 provides DC supply.
Optionally, the supply voltage of circumference intrusion alarm unit 21 and CCTV camera 23 is direct current 12V, main control unit 22
Supply voltage be direct current 5V, the supply voltage of communication unit 24 is direct current 9V;
The circumference intrusion alarm unit 21 is used for automatic Detection location intrusion target, concurrently send warning message to give master control list
Member 22, the main control unit 22 are Built-in Image processing unit GPU mobile processor, and the mobile processor is responsible for processing week
The warning message of boundary's intrusion alarm unit 21, intrusion target quantity and positional information in warning message, dynamic setting prison
Control the lens focus of video camera 23 and determine the visual zone of target classification, and run the embedded target based on depth network point
Class algorithm judges target type, while uploads warning message and be used for circumference intrusion alarm server 1, the CCTV camera 23
Monitor intrusion target position region and uploaded videos monitoring data is to circumference intrusion alarm server 1, the circumference invasion
Alarm Server 1 stores the video monitoring data for corresponding to the period according to the timestamp for receiving warning message.
The circumference intrusion alarm unit 21 has automatic detection and the stationkeeping ability of multiple intrusion targets, being capable of whole day
When, round-the-clock detection intrusion target, and provide the quantity and positional information of intrusion target, the circumference intrusion alarm unit 21 is
FMCW radars, 100m is not less than to the detection range of personnel targets, target location error is no more than 5m, can detected simultaneously
Destination number is not less than 10;
The communication unit 24 is fiber optic communication or ethernet communication, when periphery intrusion preventing equipment 2 and circumference intrusion alarm
When the distance between server 1 exceedes Ethernet farthest transmission range, communication link uses fiber optic communication mode;Otherwise, communicate
Link uses more inexpensive ethernet communication mode;
Content of Communication between the periphery intrusion preventing equipment 2 and the circumference intrusion alarm server 1 includes:Monitoring is taken the photograph
The monitor video encoding stream of camera 23 is uploaded to circumference intrusion alarm server 1, with the data such as target type and target location
Warning message report to circumference intrusion alarm server 1, periphery intrusion preventing equipment 2 reports to circumference intrusion alarm server 1
Oneself state, periphery intrusion preventing equipment 2 download depth network training model, the circumference of renewal from circumference intrusion alarm server 1
Setting of the intrusion alarm server 1 to the running parameter of periphery intrusion preventing equipment 2.
The CCTV camera 23 is low-light (level) high-definition camera, equipped with power zoom optical lens, built-in infrared light filling
Module, light filling can be carried out at night, lift night video monitoring quality;
The video resolution of the CCTV camera 23 is not less than 1920 × 1080, and frame per second is not less than 30 frames/second, built-in to regard
Frequency compressed encoding function, video flowing that can be after output squeezing;Under the conditions of normal meteorological infrared supplementary lighting module night irradiation away from
Pixel of the human body target under various postures at distance 100m can be ensured from the maximum focal length not less than 100m, optical lens
Number is not less than 50000.
The main control unit 22 is Built-in Image processing unit GPU mobile processor, is responsible for processing circumference intrusion alarm
The warning message of unit 21, and according to target position information in warning message, the optical lens of dynamic setting CCTV camera 23
Focal length, target in video image is of moderate size, avoid the target classification error under Small object size, lifting target classification is accurate
True rate, while the various sizes of training set of various targets need not be established, reduce training dataset scale;Invaded and reported based on circumference
Target position information in the alert warning message of unit 21, determines video analysis region, reduces candidate region quantity and selection calculates, drop
The low complexity of algorithm of target detection, boosting algorithm real-time;Run and target is carried out based on the good depth network of training in advance
Classification.
According to Fig. 3, a kind of periphery intrusion preventing method based on target position information fusion, it is characterised in that including
Following steps:
Step 1: periphery intrusion preventing equipment 2 is started shooting with circumference intrusion alarm server 1, and established by communication unit 24
Network service, the periphery intrusion preventing equipment 2 complete the time synchronized with circumference intrusion alarm server 1, the work of time synchronized
With being to ensure that timestamp skew is smaller in intrusion alarm message that each periphery intrusion preventing equipment 2 reports;
Periphery intrusion preventing equipment 2 is carried out with circumference intrusion alarm server 1 using NTP NTP in the present embodiment
Time synchronized, using the time of circumference intrusion alarm server 1 as reference data, precision is up to Millisecond;
Step 2: according to the scope of monitor area, circumference intrusion alarm server 1 sets the focal length of CCTV camera 23,
Ensure that monitored picture is clear and covers whole monitor area, and there is no blind spot, during night built in opening CCTV camera 23
Infrared supplementary lighting module, there is provided floor light, the CCTV camera 23 are supervised to 1 continuous uploaded videos of circumference intrusion alarm server
Data flow is controlled, circumference intrusion alarm server 1 stores video monitoring data;
Circumference intrusion alarm unit 21 is set dynamically according to weather conditions, circumference intrusion alarm server 1 in step 3
Alarm threshold value, circumference intrusion alarm unit 21 are carried out based on current alarm threshold value to the circumference intrusion behavior in surveillance area
Detection;
Under the conditions of Different climate, the rate of false alarm difference of circumference intrusion alarm unit 21 is larger, such as wind blows circumference
Neighbouring trees, the false alarm of FMCW radars may be caused, it is necessary to be directed to DIFFERENT METEOROLOGICAL CONDITIONS, optimal warning level is set
Value, filters out incidents of false alarm as far as possible;
Step 4: when circumference intrusion alarm unit 21 detects intrusion behavior, the master control into periphery intrusion preventing equipment 2
Unit 22 reports the warning message comprising intrusion target quantity and positional information, and the warning message also includes intrusion target classification
Information;
Step 5: main control unit 22 adjusts CCTV camera 23 according to destination number and the positional information of each target
Focal length, ensure that all targets are both present in monitor video picture, while ensure that each target has higher spatial resolution
(That is target effective area in monitored picture is larger);
The principle of focal length for adjusting CCTV camera 23 is:Ensureing that all targets integrally appear in monitor video as far as possible
On the basis of in picture, the physics size based on datum target and its distance with periphery intrusion preventing equipment 2, according to optical imagery
Model calculates the focal length of the optical lens substantially required when object pixel points reach 50000;
Step 6: positional information of the main control unit 22 according to destination number and each target, the vision of target classification is determined
Region, the embedded target sorting algorithm based on depth network is run, judges target type;
The main control unit 22 uses different embedded target sorting algorithms according to destination number and target location:Such as
Fruit target is multiple, and the position based on each target determines the candidate region of target classification respectively, is calculated using Faster R-CNN
Method carries out target detection;If target is 1, the position based on the target determines object classification process region, and the region is made
For a width complete image, target classification is carried out using the image classification algorithms based on depth network model.
Step 7: if target is intrusion target, by communication unit 24 report comprising target type and positional information,
The warning message of time of fire alarming;If target is non-intrusive target, this warning message is filtered out, and upload and include time of origin
False alarm message;
Step 8: after circumference intrusion alarm server 1 receives warning message or false alarm message, based on the time in message
Stamp, video and the storage of corresponding period are searched for, is recorded as alarm logging or false alarm;
Alarm logging inquiry review intrusion behavior also can be used in circumference intrusion alarm server 1 in the utility model, together
When using in alarm logging picture frame training renewal target classification depth network model, if the depth net for target classification
Network Parameters variation, then the depth network model after renewal is downloaded to the main control unit 22 of periphery intrusion preventing equipment 2;It can be used simultaneously
False alarm record carries out ex-post analysis, prevents from failing to report situation, if any failing to report, can be traced and disposed afterwards.
The characteristics of the utility model is:Periphery intrusion preventing device is by being deployed in the one or more of important zone of protection circumference
Periphery intrusion preventing equipment 2, a set of circumference intrusion alarm server 1 form, and periphery intrusion preventing equipment 2 includes having target positioning energy
The circumference intrusion alarm unit 21 of power, the CCTV camera 23 for integrating infrared supplementary lighting module and power zoom optical lens, operation
The main control unit 22 of sensation target sorting algorithm;The utility model is in the detection perimeter intrusion target of circumference intrusion alarm unit 21
On the basis of information, dynamic adjusts the focal length of CCTV camera 23, makes in monitor video image that target sizes are moderate, avoids small
Target classification error under target size, improves target classification accuracy rate;Alarmed simultaneously according to circumference intrusion alarm unit 21
Target position information in message, it may be determined that video object analyzed area, reduce candidate region quantity and selection calculates, reduce mesh
Mark the complexity of detection algorithm, boosting algorithm real-time.
The utility model and embodiments thereof are described above, this describe it is no restricted, shown in accompanying drawing
Also it is one of embodiment of the present utility model, actual structure is not limited thereto.All in all if this area it is general
Logical technical staff is enlightened by it, in the case where not departing from the utility model and creating objective, without designing with being somebody's turn to do for creativeness
The similar frame mode of technical scheme and embodiment, all should belong to the scope of protection of the utility model.
Claims (8)
1. based on the periphery intrusion preventing device of target position information fusion, including circumference intrusion alarm server(1)Be deployed in
The periphery intrusion preventing equipment of zone of protection(2), it is characterised in that:The periphery intrusion preventing equipment(2)Pass through communication link and week
Boundary's intrusion alarm server(1)Communicated, the periphery intrusion preventing equipment(2)Including circumference intrusion alarm unit(21), it is main
Control unit(22), CCTV camera(23), communication unit(24)And power supply unit(25), the main control unit(22)Respectively with week
Boundary's intrusion alarm unit(21)And CCTV camera(23)Connection, and pass through communication unit(24)With circumference intrusion alarm server
(1)Connection, the CCTV camera(23)Pass through communication unit(24)With circumference intrusion alarm server(1)Connection, the confession
Electric unit(25)Respectively with circumference intrusion alarm unit(21), main control unit(22), CCTV camera(23)And communication unit
(24)Connection, said supply unit(25)For periphery intrusion preventing equipment(2)DC supply is provided;
The circumference intrusion alarm unit(21)For automatic Detection location intrusion target, warning message is concurrently sent to main control unit
(22), the main control unit(22)For Built-in Image processing unit GPU mobile processor, the mobile processor is responsible for processing
Circumference intrusion alarm unit(21)Warning message, intrusion target quantity and positional information in warning message, dynamically set
Put CCTV camera(23)Lens focus and determine target classification visual zone, and run based on the embedded of depth network
Target classification algorithm judges target type, while uploads warning message and give circumference intrusion alarm server(1), the monitoring camera
Machine(23)For monitoring intrusion target position region, simultaneously uploaded videos monitoring data gives circumference intrusion alarm server(1),
The circumference intrusion alarm server(1)According to the timestamp for receiving warning message, the video monitoring number for corresponding to the period is stored
According to.
2. the periphery intrusion preventing device according to claim 1 based on target position information fusion, it is characterised in that described
Communication unit(24)For fiber optic communication or ethernet communication, when periphery intrusion preventing equipment(2)With circumference intrusion alarm server(1)
The distance between when exceeding the farthest transmission range of Ethernet, communication link uses fiber optic communication mode;Otherwise, communication link uses
More inexpensive ethernet communication mode.
3. the periphery intrusion preventing device according to claim 1 based on target position information fusion, it is characterised in that described
Circumference intrusion alarm server(1)It is responsible for one or more periphery intrusion preventing equipment of whole circumference deployment(2), storage,
The monitor video data and circumference intrusion alarm message of circumference are retrieved, and data interaction and connection are carried out with other security protection subsystems
It is dynamic;
The circumference intrusion alarm server(1)To periphery intrusion preventing equipment(2)Management include:Multiple periphery intrusion preventing equipment
(2)Time synchronized, for target classification depth network model storage and maintenance, periphery intrusion preventing equipment(2)State is adopted
Collection configures with running parameter.
4. the periphery intrusion preventing device according to claim 1 based on target position information fusion, it is characterised in that described
Periphery intrusion preventing equipment(2)With the circumference intrusion alarm server(1)Between Content of Communication include:CCTV camera(23)
Monitor video encoding stream be uploaded to circumference intrusion alarm server(1), alarm with target type and target position data
Information reporting is to circumference intrusion alarm server(1), periphery intrusion preventing equipment(2)To circumference intrusion alarm server(1)Report
Oneself state, periphery intrusion preventing equipment(2)From circumference intrusion alarm server(1)The depth network training model of download renewal,
Circumference intrusion alarm server(1)To periphery intrusion preventing equipment(2)The setting of running parameter.
5. the periphery intrusion preventing device according to claim 1 based on target position information fusion, it is characterised in that work as week
Boundary's length is more than single periphery intrusion preventing equipment(2)Monitoring range when, by disposing multiple periphery intrusion preventing equipment(2)Realize
The covering of whole circumference.
6. the periphery intrusion preventing device according to claim 1 based on target position information fusion, it is characterised in that described
Circumference intrusion alarm unit(21)For FMCW radars, 100m is not less than to the detection range of personnel targets, target positioning misses
Difference is no more than 5m, and the destination number that can be detected simultaneously is not less than 10.
7. the periphery intrusion preventing device according to claim 1 based on target position information fusion, it is characterised in that described
CCTV camera(23)For low-light (level) high-definition camera, equipped with power zoom optical lens, built-in infrared supplementary lighting module, Neng Gou
Night carries out light filling.
8. the periphery intrusion preventing device according to claim 7 based on target position information fusion, it is characterised in that described
CCTV camera(23)Video resolution be not less than 1920 × 1080, frame per second is not less than 30 frames/second, built in video compressed encoding
Function, video flowing that can be after output squeezing;The night irradiation distance of infrared supplementary lighting module is not less than under the conditions of normal meteorological
100m, the maximum focal length of optical lens can ensure that pixel count of the human body target under various postures at distance 100m be not small
In 50000.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201720950736.4U CN207164939U (en) | 2017-08-01 | 2017-08-01 | Periphery intrusion preventing device based on target position information fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201720950736.4U CN207164939U (en) | 2017-08-01 | 2017-08-01 | Periphery intrusion preventing device based on target position information fusion |
Publications (1)
Publication Number | Publication Date |
---|---|
CN207164939U true CN207164939U (en) | 2018-03-30 |
Family
ID=61714774
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201720950736.4U Active CN207164939U (en) | 2017-08-01 | 2017-08-01 | Periphery intrusion preventing device based on target position information fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN207164939U (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107331097A (en) * | 2017-08-01 | 2017-11-07 | 中科融通物联科技无锡有限公司 | The periphery intrusion preventing apparatus and method merged based on target position information |
CN108765817A (en) * | 2018-08-17 | 2018-11-06 | 西南交大(上海)智能系统有限公司 | A kind of railroad platform intrusion alarm system |
CN108831087A (en) * | 2018-07-17 | 2018-11-16 | 中创智慧(天津)科技发展股份有限公司 | Circumference optical fiber incudes video monitoring safety management system |
CN110164071A (en) * | 2019-04-29 | 2019-08-23 | 西人马(厦门)科技有限公司 | A kind of security system |
CN111899447A (en) * | 2019-05-06 | 2020-11-06 | 杭州海康威视数字技术股份有限公司 | Monitoring system and method |
CN112419635A (en) * | 2020-12-10 | 2021-02-26 | 武汉理工光科股份有限公司 | Perimeter alarm method integrating grating and video |
CN113447995A (en) * | 2021-06-28 | 2021-09-28 | 广州瀚信通信科技股份有限公司 | Perimeter area intrusion detection management system and detection method |
CN113486777A (en) * | 2021-07-02 | 2021-10-08 | 北京一维大成科技有限公司 | Behavior analysis method and device for target object, electronic equipment and storage medium |
-
2017
- 2017-08-01 CN CN201720950736.4U patent/CN207164939U/en active Active
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107331097A (en) * | 2017-08-01 | 2017-11-07 | 中科融通物联科技无锡有限公司 | The periphery intrusion preventing apparatus and method merged based on target position information |
CN108831087A (en) * | 2018-07-17 | 2018-11-16 | 中创智慧(天津)科技发展股份有限公司 | Circumference optical fiber incudes video monitoring safety management system |
CN108765817A (en) * | 2018-08-17 | 2018-11-06 | 西南交大(上海)智能系统有限公司 | A kind of railroad platform intrusion alarm system |
CN110164071A (en) * | 2019-04-29 | 2019-08-23 | 西人马(厦门)科技有限公司 | A kind of security system |
CN111899447A (en) * | 2019-05-06 | 2020-11-06 | 杭州海康威视数字技术股份有限公司 | Monitoring system and method |
CN112419635A (en) * | 2020-12-10 | 2021-02-26 | 武汉理工光科股份有限公司 | Perimeter alarm method integrating grating and video |
CN112419635B (en) * | 2020-12-10 | 2022-10-04 | 武汉理工光科股份有限公司 | Perimeter alarm method integrating grating and video |
CN113447995A (en) * | 2021-06-28 | 2021-09-28 | 广州瀚信通信科技股份有限公司 | Perimeter area intrusion detection management system and detection method |
CN113447995B (en) * | 2021-06-28 | 2023-09-08 | 广州瀚信通信科技股份有限公司 | Perimeter region intrusion detection management system and detection method |
CN113486777A (en) * | 2021-07-02 | 2021-10-08 | 北京一维大成科技有限公司 | Behavior analysis method and device for target object, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN207164939U (en) | Periphery intrusion preventing device based on target position information fusion | |
CN107331097A (en) | The periphery intrusion preventing apparatus and method merged based on target position information | |
CN104751603B (en) | Crag avalanche monitoring and pre-warning system and method | |
CN103108159B (en) | Electric power intelligent video analyzing and monitoring system and method | |
AU2021201585A1 (en) | Imaging array for bird or bat detection and identification | |
CN101607668B (en) | Embedded computer vision escalator pedestrian flow supervision and alarm device | |
CN101388130B (en) | Multi-grade stereo anti-intruding system, apparatus and implementing method based on wireless sensing net | |
CN103606236B (en) | A kind of Real-time security monitoring system based on distributed fiber optic intrusion alarm unit | |
KR101716365B1 (en) | Module-based intelligent video surveillance system and antitheft method for real-time detection of livestock theft | |
CN111432179A (en) | Intelligent coal conveying belt inspection system and method based on computer vision | |
CN106600872A (en) | Radar video linkage based intelligent boundary security system | |
CN112288984A (en) | Three-dimensional visual unattended substation intelligent linkage system based on video fusion | |
CN110235188A (en) | Video data and GIS for traffic monitoring, event detection and variation prediction map | |
CN104394361A (en) | Pedestrian crossing intelligent monitoring device and detection method | |
CN104123544A (en) | Video analysis based abnormal behavior detection method and system | |
CN204129891U (en) | A kind of high ferro anti-intrusion system along the line | |
CN202815538U (en) | Airport monitoring system with holder control | |
CN105096603A (en) | All-weather detection device | |
CN111144291A (en) | Method and device for distinguishing personnel invasion in video monitoring area based on target detection | |
CN104613892A (en) | Video detection technology and laser ranging technology integrated compound snow depth monitoring system | |
CN106355162A (en) | Method for detecting intrusion on basis of video monitoring | |
CN103929592A (en) | All-dimensional intelligent monitoring equipment and method | |
CN206136125U (en) | Radar video fuses alarm device , system and equipment | |
CN103456024A (en) | Moving object line crossing judgment method | |
CN110012268A (en) | Pipe network AI intelligent control method, system, readable storage medium storing program for executing and equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant |