CN110852187A - Method and system for identifying perimeter intrusion event - Google Patents
Method and system for identifying perimeter intrusion event Download PDFInfo
- Publication number
- CN110852187A CN110852187A CN201911005085.1A CN201911005085A CN110852187A CN 110852187 A CN110852187 A CN 110852187A CN 201911005085 A CN201911005085 A CN 201911005085A CN 110852187 A CN110852187 A CN 110852187A
- Authority
- CN
- China
- Prior art keywords
- intrusion
- network model
- identifying
- signals
- time
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G08B13/181—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using active radiation detection systems
- G08B13/183—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using active radiation detection systems by interruption of a radiation beam or barrier
- G08B13/186—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using active radiation detection systems by interruption of a radiation beam or barrier using light guides, e.g. optical fibres
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention relates to a method and a system for identifying perimeter intrusion events, which utilize multimode optical fibers with a characteristic structure to induce intrusion signals, filter the intrusion signals through wavelet transformation based on the intrusion signals, perform short-time Fourier transformation to obtain a time-frequency diagram, and select a proper network model according to engineering application indexes based on training samples and test samples; and then, identifying the intrusion signal by using the selected network model. The invention can identify the mode of the man-made invasion and the non-man-made invasion events in the complex environment, distinguish the man-made invasion signals and the non-man-made invasion signals, reduce the false alarm rate and the missing report rate, and improve the application of the multimode optical fiber in the monitoring field of the perimeter defense area and the engineering field.
Description
Technical Field
The invention relates to the field of optical fiber perimeter security, in particular to a perimeter intrusion event identification method and a perimeter intrusion event identification system.
Background
The optical fiber perimeter security protection generally has the effects of electromagnetic interference resistance, corrosion resistance, high sensitivity, simple structure, safety, reliability and the like, is generally used for a base station, and mainly aims to prevent illegal invasion behaviors in a complex environment, improve the accuracy rate of the system for identifying human invasion events and improve the accuracy rate of non-human invasion. Thus, great attention is being paid in the museum security field, government health care, aviation and military fields.
In the prior art, chinese patent application 201611266625.8 discloses a distributed fiber fence vibration intrusion recognition system, but the technical scheme thereof needs to calculate framing processing, calculate the zero-crossing rate and zero-crossing rate of framing, needs to intercept useful signals, is insensitive to signal processing, has poor real-time performance, and has redundant calculated amount.
The chinese patent application 201410494088.7 discloses an optical fiber early warning and pattern recognition method, but in the technical scheme, the system light path is complex, the sample is too simple, the features of the intrusion event in the complex environment cannot be extracted, and the intrusion event can only be limited to the intrusion signal in the ideal environment, and the situation is not suitable for the practical application of the engineering.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides a method and a system for identifying perimeter intrusion events, realizes the mode identification of man-made intrusion and non-man-made intrusion events in a complex environment, and can realize low false alarm rate and low false alarm rate.
The technical scheme of the invention is as follows:
a method for identifying perimeter intrusion events comprises the following steps:
1) selecting a network model suitable for identifying the known type of intrusion signal;
2) training by using a training set consisting of known types of intrusion signals containing various noises and by using a selected network model, and identifying the intrusion signals acquired in real time by using the trained network model;
in step 1), the method for selecting an applicable network model is as follows:
1.1) collecting a certain amount of known intrusion signals as training samples and test samples, filtering the training samples and the test samples by adopting wavelet transform, and then carrying out short-time Fourier transform to obtain a corresponding time-frequency graph;
1.2) training samples through different network models respectively by using the image characteristics of the time-frequency diagram;
1.3) identifying the test sample by using a network model;
1.4) calculating the operation time of training samples, the total training time of the training samples and the identification time of each test sample in different network model networks, and selecting the network model with the shortest operation time, the total training time and the identification time.
Preferably, in step 1.1), the different window functions and window widths used for the short-time fourier transform are compared, and the window function and window width adapted to the known type of intrusion signal are selected.
Preferably, in step 1.2), before training a training sample through the network model, selecting a deep learning optimizer, setting batch size and iteration times, and initializing a weight w and a bias value b of the network model; then calculating the deviation of the output value, and calculating the loss value; and optimizing the weight w and the offset b according to the loss value until the deviation meets the requirement.
Preferably, the known types of intrusion signals include man-made intrusion signals, non-man-made intrusion signals; wherein, the man-made invasion signal comprises knocking and shaking, and the non-man-made invasion signal comprises wind blowing and rain falling.
Preferably, the selected network model is a convolutional neural network model of the inclusion-v 2 structure.
A system for identifying perimeter intrusion events comprises a light source, a multimode optical fiber, a photodiode and a data acquisition card, wherein a light source signal passes through the multimode optical fiber and the photodiode and then data acquisition is carried out through the data acquisition card; and inducing the intrusion signal through the multimode optical fiber, and identifying the data acquired under the influence of the intrusion signal based on the identification method.
Preferably, the multimode fiber comprises a front single-mode fiber section, a multimode fiber section and a rear single-mode fiber section which are coupled in sequence.
Preferably, the multimode optical fiber is wound and fixed on a purse net surrounding the perimeter for sensing the intrusion signal.
The invention has the following beneficial effects:
the method and the system for identifying the perimeter intrusion event utilize multimode optical fibers with characteristic structures to induce intrusion signals, filter the intrusion signals through wavelet transformation based on the intrusion signals, perform short-time Fourier transformation to obtain a time-frequency diagram, and select a proper network model according to engineering application indexes based on training samples and test samples; and then, identifying the intrusion signal by using the selected network model. The invention can identify the mode of the man-made invasion and the non-man-made invasion events in the complex environment, distinguish the man-made invasion signals and the non-man-made invasion signals, reduce the false alarm rate and the missing report rate, and improve the application of the multimode optical fiber in the monitoring field of the perimeter defense area and the engineering field.
Drawings
FIG. 1 is a schematic flow diagram of a process according to the present invention;
FIG. 2 is a schematic diagram of a system according to the present invention;
FIG. 3 is a time-frequency plot of an intrusion signal (tap);
FIG. 4 is a time-frequency plot of an intrusion signal (wobble);
FIG. 5 is a time-frequency plot of an intrusion signal (wind);
FIG. 6 is a time-frequency plot of an intrusion signal (raining);
in the figure: 10 is a multimode fiber, 11 is a front single mode fiber segment, 12 is a multimode fiber segment, and 13 is a rear single mode fiber segment.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
The invention provides a method for identifying a perimeter intrusion event and a system for identifying the perimeter intrusion event, aiming at solving the defects in the prior art. The method for identifying the perimeter intrusion event, disclosed by the invention, comprises the following steps as shown in figure 1:
1) selecting a network model suitable for identifying the known type of intrusion signal;
2) the method comprises the steps of utilizing a training set consisting of known types of intrusion signals containing various noises, utilizing a selected network model to train, and utilizing the trained network model to identify the intrusion signals collected in real time.
In order to simplify the identification process and reduce the false alarm rate and the false alarm rate, the invention needs to screen out the network model most suitable for some specific types of intrusion signals, in the embodiment, the method for selecting the applicable network model in the step 1) is as follows:
1.1) collecting a certain amount of known intrusion signals as training samples and test samples, filtering the training samples and the test samples by adopting wavelet transform, and then carrying out short-time Fourier transform to obtain a corresponding time-frequency graph;
wherein, in order to select a window function and a window width adapted to the known type of intrusion signal, in step 1.1) different window functions and window widths for the short time fourier transform are compared, and a window function and a window width adapted to the known type of intrusion signal are selected;
1.2) training samples through different network models respectively by using the image characteristics of the time-frequency diagram;
in order to select the most appropriate network parameters, in step 1.2), before training a training sample through a network model, a deep learning optimizer is selected, the batch size and the iteration times are set, and the weight w and the offset value b of the network model are initialized; then calculating the deviation of the output value, and calculating the loss value; optimizing the weight w and the offset b according to the loss value until the deviation meets the requirement;
1.3) identifying the test sample by using a network model;
1.4) calculating the operation time of training samples, the total training time of the training samples and the identification time of each test sample in different network model networks, and selecting the network model with the shortest operation time, the total training time and the identification time.
In this embodiment, the known types of intrusion signals include man-made intrusion signals and non-man-made intrusion signals; wherein, the man-made invasion signal comprises knocking and shaking, and the non-man-made invasion signal comprises wind blowing and rain falling. Further, the selected network model is a convolutional neural network model of the inclusion-v 2 structure.
Based on the identification method, the invention also provides a system for identifying the perimeter intrusion event, which comprises a light source, a multimode optical fiber 10, a photodiode and a data acquisition card, wherein a light source signal passes through the multimode optical fiber 10 and the photodiode and then data acquisition is carried out through the data acquisition card, wherein the data acquisition card is used for acquiring data; the invasion signal is induced through the multimode optical fiber 10, and the data collected under the influence of the invasion signal is identified based on the identification method.
In this embodiment, the multimode fiber 10 includes a front single-mode fiber segment 11, a multimode fiber segment 12, and a rear single-mode fiber segment 13 coupled in sequence. Wherein, the loss at the welding position of the front single-mode optical fiber section 11 and the multimode optical fiber section 12 is 0.02db, and the loss at the welding position of the rear single-mode optical fiber section 13 and the multimode optical fiber section 12 is 0.01 db.
In practice, the multimode optical fiber 10 is wound and fixed on a purse net surrounding the perimeter for inducing an intrusion signal. Specifically, the length of the whole multimode optical fiber 10 is 300 meters, the multimode optical fiber is wound on a wire mesh and locked by an iron hoop, and the knocking is that an iron rod knocks the wire mesh, and the shaking is that the wire mesh is shaken by hands.
The light source used in this example was a laser with a wavelength of 1550nm and an intensity of 13dbm, coupled to the fusion splice of the front single mode fiber section by a coupler. A1601B data acquisition card of 16-bit 25MSPS is adopted as the data acquisition card, the sampling depth is set to be 256k, and the sampling rate is set to be 100 khz.
In this embodiment, each type of intrusion signal is collected 300 times, and the four types of signals have 1200 samples in total. The samples were divided into a training set of 1020 signals and a test set of 180 signals with a test ratio of 0.15.
In this embodiment, when performing wavelet transform, the db8 wavelet basis is selected and 10-layer decomposition is used. The window function selected for the short-time fourier transform was a kaiser window function with a sidelobe of 0.5, a window width of 4800, a number of overlaps between windows in the fourier transform of 4200, and a sampling rate of 10000 hz.
Wherein the short-time Fourier transform formula is
In this embodiment, the loss value is calculated by using a cross entropy function. The deep learning optimizer adopts an adam optimizer, wherein the learning rate is set to 0.0003, the batch _ size is set to 16, the epoch is set to 8, and the iteration number is 383.
In specific implementation, three classic convolutional network structures, namely inclusion-v 2, inclusion-v 3 and Resnet, are selected in advance, practical application parameters are selected through engineering application indexes, and the convolutional neural network model which is favorable for practical application of the embodiment is selected to be the inclusion-v 2 structure.
After the network model is selected, in step 2), a data set containing a large amount of noise is produced and divided into a training set and a testing set. The training set comprises five kinds of intrusion signals with Gaussian noise of each kind of signal of 30db, 40db, 50db, 60db and 70db, wherein the total number of the intrusion signals is 6000 samples, the 6000 samples are used for training, and then 12 groups of test samples are additionally designed, each group of test samples is 50 samples of 4 kinds of signals, and the 50 samples comprise 10 kinds of 5 kinds of noise. And training the training set in a network model of an initiation-v 2 structure.
And collecting intrusion signals in a severe environment, making a time-frequency diagram, and putting the time-frequency diagram into the network model for testing as shown in figures 3 to 6. Through actual measurement, the recognition rate of the invention on intrusion signals such as knocking, shaking, wind blowing, raining and the like in severe environment can reach 93.83%, 99.49%, 95.93% and 99.83%, and the invention meets the requirement of recognizing different intrusion signals.
The above examples are provided only for illustrating the present invention and are not intended to limit the present invention. Changes, modifications, etc. to the above-described embodiments are intended to fall within the scope of the claims of the present invention as long as they are in accordance with the technical spirit of the present invention.
Claims (8)
1. A method for identifying perimeter intrusion events is characterized by comprising the following steps:
1) selecting a network model suitable for identifying the known type of intrusion signal;
2) training by using a training set consisting of known types of intrusion signals containing various noises and by using a selected network model, and identifying the intrusion signals acquired in real time by using the trained network model;
in step 1), the method for selecting an applicable network model is as follows:
1.1) collecting a certain amount of known intrusion signals as training samples and test samples, filtering the training samples and the test samples by adopting wavelet transform, and then carrying out short-time Fourier transform to obtain a corresponding time-frequency graph;
1.2) training samples through different network models respectively by using the image characteristics of the time-frequency diagram;
1.3) identifying the test sample by using a network model;
1.4) calculating the operation time of training samples, the total training time of the training samples and the identification time of each test sample in different network model networks, and selecting the network model with the shortest operation time, the total training time and the identification time.
2. Method for perimeter intrusion event identification according to claim 1, characterized in that in step 1.1) different window functions and window widths for the short time fourier transformation are compared, and a window function and window width adapted to the known type of intrusion signal is selected.
3. The method for identifying the perimeter intrusion event according to claim 2, wherein in step 1.2), before training the training samples through the network model, a deep learning optimizer is selected, the batch size and the iteration number are set, and the weight w and the offset value b of the network model are initialized; then calculating the deviation of the output value, and calculating the loss value; and optimizing the weight w and the offset b according to the loss value until the deviation meets the requirement.
4. The method for identifying perimeter intrusion events according to any one of claims 1 to 3, wherein the known types of intrusion signals include man-made intrusion signals, non-man-made intrusion signals; wherein, the man-made invasion signal comprises knocking and shaking, and the non-man-made invasion signal comprises wind blowing and rain falling.
5. The method for perimeter intrusion event identification according to claim 4, wherein the selected network model is convolutional neural network model of inclusion-v 2 structure.
6. A system for identifying perimeter intrusion events is characterized by comprising a light source, a multimode optical fiber, a photodiode and a data acquisition card, wherein a light source signal passes through the multimode optical fiber and the photodiode and then data acquisition is carried out through the data acquisition card; sensing an intrusion signal by means of a multimode optical fibre, data collected under the influence of the intrusion signal being identified on the basis of the identification method as claimed in any one of claims 1 to 5.
7. The perimeter intrusion event identification system of claim 6, wherein the multimode optical fiber comprises a front single mode fiber section, a multimode optical fiber section, and a rear single mode fiber section coupled in sequence.
8. The system for identifying fiber perimeter intrusion events of claim 6, wherein multimode optical fibers are wound and fixed on a perimeter-defining seine for sensing intrusion signals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911005085.1A CN110852187B (en) | 2019-10-22 | 2019-10-22 | Method and system for identifying perimeter intrusion event |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911005085.1A CN110852187B (en) | 2019-10-22 | 2019-10-22 | Method and system for identifying perimeter intrusion event |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110852187A true CN110852187A (en) | 2020-02-28 |
| CN110852187B CN110852187B (en) | 2023-04-07 |
Family
ID=69597748
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911005085.1A Active CN110852187B (en) | 2019-10-22 | 2019-10-22 | Method and system for identifying perimeter intrusion event |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110852187B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597994A (en) * | 2020-05-15 | 2020-08-28 | 华侨大学 | Optical fiber perimeter security intrusion event identification model construction method and security system |
| CN111738073A (en) * | 2020-05-16 | 2020-10-02 | 北京信息科技大学 | System and method for identifying optical fiber signals |
| CN111951505A (en) * | 2020-08-25 | 2020-11-17 | 青岛大学 | Fence vibration intrusion positioning and mode identification method based on distributed optical fiber system |
| CN112257533A (en) * | 2020-10-14 | 2021-01-22 | 吉林大学 | Perimeter intrusion detection and identification 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 |
| CN114093106A (en) * | 2021-11-29 | 2022-02-25 | 上海微波技术研究所（中国电子科技集团公司第五十研究所） | Intrusion signal alarm method and system based on Efficinet classified network |
| CN117496650A (en) * | 2024-01-02 | 2024-02-02 | 浙江省白马湖实验室有限公司 | Distributed optical fiber intrusion early warning method and system based on environment embedding |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017036363A1 (en) * | 2015-09-02 | 2017-03-09 | 同方威视技术股份有限公司 | Optical fiber perimeter intrusion signal identification method and device, and perimeter intrusion alarm system |
| CN106503642A (en) * | 2016-10-18 | 2017-03-15 | 长园长通新材料股份有限公司 | A kind of model of vibration method for building up for being applied to optical fiber sensing system |
| CN106600870A (en) * | 2016-12-31 | 2017-04-26 | 上海华魏光纤传感技术有限公司 | Distributed optical fiber fence vibration invasion identifying system |
-
2019
- 2019-10-22 CN CN201911005085.1A patent/CN110852187B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017036363A1 (en) * | 2015-09-02 | 2017-03-09 | 同方威视技术股份有限公司 | Optical fiber perimeter intrusion signal identification method and device, and perimeter intrusion alarm system |
| CN106503642A (en) * | 2016-10-18 | 2017-03-15 | 长园长通新材料股份有限公司 | A kind of model of vibration method for building up for being applied to optical fiber sensing system |
| CN106600870A (en) * | 2016-12-31 | 2017-04-26 | 上海华魏光纤传感技术有限公司 | Distributed optical fiber fence vibration invasion identifying system |
Non-Patent Citations (1)
| Title |
|---|
| 朱程辉等: "光纤入侵行为融合特征的集成识别", 《光电工程》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597994A (en) * | 2020-05-15 | 2020-08-28 | 华侨大学 | Optical fiber perimeter security intrusion event identification model construction method and security system |
| CN111597994B (en) * | 2020-05-15 | 2023-03-07 | 华侨大学 | Optical fiber perimeter security intrusion event identification model construction method and security system |
| CN111738073A (en) * | 2020-05-16 | 2020-10-02 | 北京信息科技大学 | System and method for identifying optical fiber signals |
| CN111951505A (en) * | 2020-08-25 | 2020-11-17 | 青岛大学 | Fence vibration intrusion positioning and mode identification method based on distributed optical fiber system |
| CN112257533A (en) * | 2020-10-14 | 2021-01-22 | 吉林大学 | Perimeter intrusion detection and identification method |
| CN112257533B (en) * | 2020-10-14 | 2022-04-12 | 吉林大学 | Perimeter intrusion detection and identification 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 |
| CN114093106A (en) * | 2021-11-29 | 2022-02-25 | 上海微波技术研究所（中国电子科技集团公司第五十研究所） | Intrusion signal alarm method and system based on Efficinet classified network |
| CN117496650A (en) * | 2024-01-02 | 2024-02-02 | 浙江省白马湖实验室有限公司 | Distributed optical fiber intrusion early warning method and system based on environment embedding |
| CN117496650B (en) * | 2024-01-02 | 2024-03-26 | 浙江省白马湖实验室有限公司 | Distributed optical fiber intrusion early warning method and system based on environment embedding |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110852187B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110852187B (en) | Method and system for identifying perimeter intrusion event | |
| Wu et al. | Separation and determination of the disturbing signals in phase-sensitive optical time domain reflectometry (Φ-OTDR) | |
| US11562224B2 (en) | 1D-CNN-based distributed optical fiber sensing signal feature learning and classification method | |
| CN102045120B (en) | Vibration signal identification method for optical fiber perimeter system | |
| CN111442827B (en) | Optical fiber passive online monitoring system for transformer winding vibration | |
| CN104240455B (en) | A kind of disturbance event recognition methods in distribution type fiber-optic pipeline safety early warning system | |
| CN105023379B (en) | A kind of signal recognition method of airport optical fiber perimeter early warning system | |
| CN110570613A (en) | Fence vibration intrusion positioning and mode identification method based on distributed optical fiber system | |
| CN104729667B (en) | A kind of disturbance kind identification method in distributed optical fiber vibration sensing system | |
| CN106652285A (en) | Distributed multi-defence-area vibration optical fiber perimeter alarm system and perimeter monitoring method | |
| CN104217513B (en) | The method improving phase sensitive optical time domain reflectometer identification intrusion event accuracy rate | |
| WO2001067415A1 (en) | Imaging fire detector | |
| CN103968933A (en) | Fuzzy domain characteristics based optical fiber vibration signal identifying method | |
| CN111104891A (en) | Composite characteristic optical fiber sensing disturbing signal mode identification method based on BiLSTM | |
| CN105841793A (en) | Optical fiber vibration source identification method, device and system | |
| Lyu et al. | Abnormal events detection based on RP and inception network using distributed optical fiber perimeter system | |
| CN110378265A (en) | A kind of incipient fire detection method, computer-readable medium and system | |
| Wang et al. | Multi-branch long short-time memory convolution neural network for event identification in fiber-optic distributed disturbance sensor based on φ-OTDR | |
| CN111597994B (en) | Optical fiber perimeter security intrusion event identification model construction method and security system | |
| CN114093106B (en) | Intrusion signal alarm method and system based on EfficientNET classification network | |
| CN108506736A (en) | A kind of invasion signal diagnostic system and method | |
| Hammer et al. | Automatic detection of wet-snow avalanche seismic signals | |
| CN115265750A (en) | Optical fiber distributed acoustic wave sensing system and method | |
| Runkel et al. | The handbook of acoustic bat detection | |
| CN111951505B (en) | Fence vibration intrusion positioning and mode identification method based on distributed optical fiber system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |