CN111223261A - Composite intelligent production security system and security method thereof - Google Patents
Composite intelligent production security system and security method thereof Download PDFInfo
- Publication number
- CN111223261A CN111223261A CN202010326764.5A CN202010326764A CN111223261A CN 111223261 A CN111223261 A CN 111223261A CN 202010326764 A CN202010326764 A CN 202010326764A CN 111223261 A CN111223261 A CN 111223261A
- Authority
- CN
- China
- Prior art keywords
- voice
- image
- danger area
- terminal
- image sensing
- 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 27
- 239000002131 composite material Substances 0.000 title claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 35
- 230000002159 abnormal effect Effects 0.000 claims abstract description 26
- 230000009429 distress Effects 0.000 claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 238000001514 detection method Methods 0.000 claims description 19
- 230000005540 biological transmission Effects 0.000 claims description 18
- 230000002996 emotional effect Effects 0.000 claims description 17
- 238000005516 engineering process Methods 0.000 claims description 17
- 230000008451 emotion Effects 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 4
- 238000009432 framing Methods 0.000 claims description 4
- 230000005236 sound signal Effects 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 5
- 230000004888 barrier function Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000012706 support-vector machine Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000009545 invasion Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- NGVDGCNFYWLIFO-UHFFFAOYSA-N pyridoxal 5'-phosphate Chemical compound CC1=NC=C(COP(O)(O)=O)C(C=O)=C1O NGVDGCNFYWLIFO-UHFFFAOYSA-N 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000001755 vocal effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000033001 locomotion Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- 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
- G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Child & Adolescent Psychology (AREA)
- Hospice & Palliative Care (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to a composite intelligent production security system and a security method thereof, and the composite intelligent production security system is characterized in that: the system comprises an image sensing terminal, a central processing unit and a central processing unit, wherein the image sensing terminal is used for acquiring image data around a core danger area in real time and processing and analyzing the image data; the voice recognition terminal is used for acquiring voice data around the core danger area in real time and carrying out processing analysis; the controller is used for receiving information data acquired in real time from the image sensor terminal and the voice recognition terminal, calculating the distance of personnel relative to the core danger area, recognizing abnormal distress signals and sending a control instruction to production equipment; and the image sensing terminal and/or the voice recognition terminal are/is communicated and interconnected with the controller in a wired and/or wireless mode. The system solves the production security problem based on image sensing and voice recognition composite intelligence, meets the flexible layout requirement, can identify and distinguish people and objects, and has the advantages of high positioning precision, low probability of false alarm and missed alarm, and stable and reliable performance.
Description
Technical Field
The invention relates to a production protection system, in particular to a composite intelligent production security system and a security method thereof.
Background
The current protection of factory production areas mainly comprises two ways, namely, a physical fence is arranged to isolate people outside the production area, and a grating electronic fence is used for preventing people from entering the production area, wherein the physical fence is formed by arranging guardrails, cages and other isolators, so that the defect that ① is inconvenient for workers and materials to enter and exit the production area in a shutdown state is overcome, and space utilization rate is low due to the fact that the protection boundary of ② cannot be flexibly changed, referring to fig. 1, the grating electronic fence is an intelligent peripheral system formed by combining a pulse generator (host) and the physical fence, is one of active infrared correlation, namely, a plurality of infrared correlation is adopted, a transmitter transmits infrared light to a receiver in a low-frequency emission and time division detection mode, once people or objects block any two adjacent beams of infrared light transmitted by the transmitter for more than 30ms, the receiver immediately outputs an alarm signal, the grating electronic fence has high sensitivity, but has the defects that ① parts occupy a large space and are inconvenient in installation positions, the protection area ② can only be a plane area or a space combined by a plurality of plane areas, the protection area cannot be treated by the space, the safety of the safety area, the safety of the grating electronic fence cannot be mistakenly interfered by people or objects, and the safety of the production area cannot be influenced by the safety of people, and the safety of the production area, even if the safety of the safety barrier is not influenced by the safety of people, the safety of the safety barrier, the safety barrier of people, the safety barrier, the safety.
Therefore, there is a need for further improvements in the protection of existing production areas.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a composite intelligent production security system and a security method thereof.
The purpose of the invention is realized as follows:
the utility model provides a compound intelligent production security protection system which characterized in that: comprises that
The image sensing terminal is used for acquiring image data around the core danger area in real time and carrying out processing analysis;
the voice recognition terminal is used for acquiring voice data around the core danger area in real time and carrying out processing analysis;
the controller is used for receiving information data acquired in real time from the image sensor terminal and the voice recognition terminal, calculating the distance of personnel relative to the core danger area, recognizing abnormal distress signals and sending a control instruction to production equipment;
and the image sensing terminal and/or the voice recognition terminal are/is communicated and interconnected with the controller in a wired and/or wireless mode.
The image sensing terminal comprises an image sensing module for recording image information around the core danger area, an image processing module for converting the image information into corresponding image data, and an image transmission module for transmitting the image data to the controller; the image sensing module, the image processing module and the image transmission module are sequentially connected; the image transmission module is connected with the controller in a wired and/or wireless mode.
And the image processing module is provided with a human body identification program based on an HOG characteristic detection technology.
The voice recognition terminal comprises a voice input module for inputting voice information around a core dangerous area, an emotion classification module for distinguishing the voice information as 'normal' emotional voice or 'panic' emotional voice, a voice processing module for converting the voice information corresponding to the 'panic' emotional voice into voice data, and a voice transmission module for transmitting the voice data to the controller; the voice input module, the emotion classification module, the voice processing module and the voice transmission module are sequentially connected; the voice transmission module is connected with the controller in a wired and/or wireless mode.
The composite intelligent production security system also comprises a driver, a relay and an actuator; the controller is respectively connected with the driver and the relay, and the driver is respectively connected with the relay and the actuator.
The security method of the composite intelligent production security system is characterized in that: comprises the following steps
a. Performing space positioning on the core danger area through the image sensing terminal, and installing a voice recognition terminal;
b. detecting the distance of personnel relative to a core danger area in real time through an image sensing terminal; identifying whether an abnormal distress signal exists around the core dangerous area through a voice identification terminal;
c. and the controller executes a corresponding pre-made decision according to the detection results fed back by the image sensing terminal and the voice recognition terminal.
And (3) carrying out space positioning on the core danger area: firstly, arranging a plurality of calibration plates in the range and/or the edge of a core danger area, and then photographing, positioning and recording by using an image sensing terminal; the calibration plate is an object that is clearly distinguished from the surrounding environment.
Distance of detection personnel relative to the core danger zone: when a person enters a shooting range of the image sensing terminal, the image sensing terminal calculates coordinates of all joint points of the human body on the 2D RGB image, then the 2D RGB image is coupled with the depth image to obtain projection of the human body outline on the depth image so as to calculate 3D coordinates of the human body outline, and finally the distance between the person and the core danger area is calculated through all outline points.
And (3) identifying abnormal distress signals: firstly, collecting external sound signals; then the voice recognition terminal detects and distinguishes voice information and non-voice information, determines the starting point and the ending point of the voice information to perform framing processing on the voice information, and then performs acoustic feature extraction on each frame of the voice information; and finally, performing emotion classification on the extracted acoustic features to judge whether the voice information is normal emotional voice or panic emotional voice, wherein the panic emotional voice is defaulted to be an abnormal distress signal.
The pre-made decision on the controller comprises
When the distance between the personnel and the core danger area is greater than the safety distance and no abnormal distress signal exists, the production equipment normally produces;
when the distance between the personnel and the core danger area is less than the safety distance and no abnormal distress signal exists, the production equipment reduces the speed for production and sends out a warning whistle at the same time;
when the distance between personnel and the core danger area is greater than the safety distance and an abnormal distress signal exists, the production equipment interrupts production and sends out a warning whistle at the same time;
when the distance between the personnel and the core danger area is less than the safe distance and an abnormal distress signal exists, the production equipment is powered off and suddenly stops, and simultaneously, a warning whistle is sent out.
The composite intelligent production security system has the following beneficial effects:
1. making an alarm protection decision by comprehensively using an image sensing terminal and a voice recognition terminal; the distance between personnel and the core danger area can be effectively calculated through the image sensing terminal, whether abnormal distress signals appear around the core danger area or not is recognized through the voice recognition terminal, information data collected by the two terminals are integrated, and the controller takes corresponding decision measures in time according to actual conditions; the image sensing terminal and the voice recognition terminal are matched with each other to work, so that the false alarm and missing report probability of the security system can be greatly reduced, and the security effect is more stable and reliable;
2. the core danger area is determined through calibration, and the distance from a person to the core danger area is calculated through the coordinates of the human body joint points, so that the traditional operation that a protection area/a guardrail needs to be set in a complicated way is avoided, meanwhile, the invasion degree can be quantized according to the distance from the person to the core danger area, so that a corresponding light decision measure can be taken according to the invasion degree, and the influence on normal production can be reduced on the basis of ensuring the safety of the person;
3. because the image sensing terminal and the voice recognition terminal can be in wireless communication connection with the controller respectively, and the image sensing and the voice recognition belong to non-contact sensing technologies without space constraint, the layout and installation of all devices have the maximum flexibility, the device can adapt to different production areas, the universality and the adaptability are strong, and the problem that the installation position of the traditional grating electronic fence is not flexible is solved;
4. because the security system can acquire relevant information through images, people and objects can be easily and accurately distinguished, so that the system can implement corresponding decision measures according to the people or the objects entering the core danger area.
Drawings
Fig. 1 is a schematic diagram of the operation principle of the prior art photogate sub-fence.
Fig. 2 is an architecture diagram of the composite intelligent production security system in an embodiment of the present invention.
FIG. 3 is a chart illustrating decisions to be made by the controller in accordance with one embodiment of the present invention.
Fig. 4 is a control schematic diagram of the composite intelligent production security system in an embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
Referring to fig. 2-4, the composite intelligent production security system comprises
The image sensing terminal is used for acquiring image data around the core danger area in real time and carrying out processing analysis;
the voice recognition terminal is used for acquiring voice data around the core danger area in real time and carrying out processing analysis;
the controller is used for receiving information data acquired in real time from the image sensor terminal and the voice recognition terminal, calculating the distance of personnel relative to the core danger area, recognizing abnormal distress signals and sending a control instruction to production equipment;
the image sensing terminal and the voice recognition terminal are communicated and interconnected with the controller in a wired and/or wireless mode respectively, so that space limitation is effectively eliminated, and the layout of different areas is adapted.
Furthermore, the image sensing terminal comprises an image sensing module for recording image information around the core danger area, an image processing module for converting the image information into corresponding image data, and an image transmission module for transmitting the image data to the controller; the image sensing module, the image processing module and the image transmission module are sequentially in communication connection, and the image transmission module is in communication connection with the controller by utilizing a wired and/or wireless connection technology; the image sensing module is a 2D and/or 3D video camera.
Further, a human body recognition program based on the HOG feature detection technology is arranged on the image processing module. HOG is short for "Histogram of Oriented Gradient", and Chinese is translated into "Histogram of Oriented Gradient"; the HOG feature detection technology is a technology used for object detection in computer vision and image processing, and is characterized by calculating and counting a gradient direction histogram of a local area of an image, namely, effectively detecting object edge features by utilizing orientation and intensity information of edges; HOG is widely used in the fields of vehicle detection, license plate detection, pedestrian detection, and the like. Specifically, the HOG method includes the steps of firstly calculating gradients of images with fixed sizes, then carrying out grid division, calculating gradient orientation and intensity at each point, then forming gradient direction distribution histograms of all pixels in a grid, and finally summarizing to form the whole histogram feature, so that an image detection/identification effect is achieved.
Furthermore, the voice recognition terminal comprises a voice input module for inputting voice information around the core dangerous area, an emotion classification module for distinguishing the voice information as 'normal' emotional voice or 'panic' emotional voice, a voice processing module for converting the voice information corresponding to the 'panic' emotional voice into voice data, and a voice transmission module for transmitting the voice data to the controller; the voice input module, the emotion classification module, the voice processing module and the voice transmission module are sequentially in communication connection, and the voice transmission module is in communication connection with the controller by utilizing a wired and/or wireless connection technology; the emotion classification module can be a classifier such as an SVM (Support Vector Machine) (the SVM is a common discrimination method, the SVM is a supervised learning model and is usually used for pattern recognition, classification and regression analysis), a KNN (K-nearest neighbor) (the KNN is a short term of k-nearest neighbor, the Chinese translation is a proximity algorithm, and the KNN is one of the simplest methods in a data mining classification technology) and the like, and can also be an identification model based on a deep neural network so as to classify emotion (frightened emotion, normal emotion and the like) of a speech signal.
Furthermore, the composite intelligent production security system also comprises a driver, a relay and an actuator; the controller is respectively connected with the driver and the relay, and the driver is respectively connected with the relay and the actuator. The driver is used for controlling the speed of the movement of the actuator according to the power control signal received by the controller. The relay is used for controlling the on-off of a high-power circuit by using a low-current input quantity, and in the embodiment, the relay controls the on-off of the power supply of the execution system (the actuator + the driver) according to the state of a power supply control signal received by the controller (when a security threat is detected, the signal is activated). An actuator is an electromechanical device (e.g., industrial robot, welder, press, grinder, etc.) that performs a production process task.
The security method of the composite intelligent production security system comprises the following steps
a. The image sensing terminal is used for carrying out space positioning on the core dangerous area and installing the voice recognition terminal, so that the image sensing terminal and the voice recognition terminal are respectively communicated with the controller in a wired and/or wireless mode;
b. detecting the distance of the personnel relative to the core danger area in real time through an image sensing terminal: the image sensing module continuously shoots a monitored area (the monitored area covers a core danger area), and transmits image data to the image processing module, and the image processing module executes an image processing flow, namely, a person is identified on an RGB image by using an HOG feature detection technology;
whether an abnormal distress signal exists around the core danger area is identified through a voice identification terminal: namely, the voice recognition terminal continuously records the voice data facing a monitoring area (the monitoring area covers a core dangerous area), and transmits the voice data to the emotion classification module, the emotion classification module transmits 'panic' emotion voice to the voice processing module, and the voice processing module executes a voice processing flow;
c. and the controller executes a corresponding pre-made decision according to the detection results fed back by the image sensing terminal and the voice recognition terminal.
Further, spatial localization is performed on the core danger zone: firstly, arranging a plurality of calibration plates in the range and/or the edge of a core danger area, and then photographing, positioning and recording by using an image sensing terminal; when the core danger area range is large, multiple times of photographing can be carried out, and the system records the set of all positions; a calibration plate is an object that is clearly distinguished from the surrounding environment.
Further, the distance of the detection personnel relative to the core danger zone: when a person enters a shooting range of the image sensing terminal, the image sensing terminal calculates coordinates of all joint points of the human body on the 2D RGB image, then the 2D RGB image is coupled with the depth image to obtain projection of the human body outline on the depth image so as to calculate 3D coordinates of the human body outline, and finally the distance between the person and the core danger area is calculated through all outline points, so that whether the person enters the core danger area is effectively judged; specifically, the actual distance is compared with a preset safety distance, the personnel with the actual distance greater than the safety distance do not enter the core danger area, and the personnel with the actual distance less than the safety distance enter the core danger area.
Furthermore, when the person realizes that the danger is imminent, the person subconsciously makes terrorist sounds such as 'shock and scream', and the sound made by the person needs to be identified; and (3) identifying abnormal distress signals: firstly, collecting external sound signals; then the voice recognition terminal detects and distinguishes voice information and non-voice information, determines the starting point and the ending point of the voice information to perform framing processing on the voice information, and then performs acoustic feature extraction on each frame of the voice information; and finally, performing emotion classification on the extracted acoustic features to judge whether the voice information is normal emotional voice or panic emotional voice, wherein the panic emotional voice is defaulted to be an abnormal distress signal, if the panic emotional voice is detected, the voice recognition terminal immediately starts a corresponding protection decision and sends the protection decision to the controller, if the normal emotional voice and the voice recognition terminal are detected, the judgment of whether the image detects people is performed once by combining with the image signal, if the image detects people, the corresponding decision is executed according to the image detection, if the image detection does not detect people, the image sensing terminal is possibly disabled, and the voice recognition terminal immediately starts the corresponding protection decision and sends the protection decision to the controller. The framing process divides the speech period into segments of a certain duration (one segment is a frame) and allows overlap (e.g., each segment is 0.4 second in duration, and the overlap rate is 50%, i.e., 0.2 second).
Further, the acoustic feature extraction method on the speech recognition terminal includes LPC technology, CEP technology, MEL technology, MFCC technology, and the like, and particularly, the method includes the steps of extracting acoustic features of the speech recognition terminal from the speech recognition terminal, and extracting acoustic features of the speech recognition terminal from the speech recognition terminal
LPC technique: LPC is short for linear predictive coding, and Chinese is translated into linear predictive coding; the LPC is a coding method, and in principle, the LPC generates parameters of vocal tract excitation and a transfer function by analyzing voice waveforms, and the coding of the voice waveforms is actually converted into the coding of the parameters, so that the data volume of the voice is greatly reduced; the LPC analysis parameters are used at the speech recognition terminal to reconstruct the speech by the speech synthesizer (where the speech synthesizer is a discrete time-varying linear filter representing a model of the human speech generating system; where the time-varying linear filter can be used as both a predictor and a speech synthesizer, as a predictor when analyzing the speech waveform, and as a speech generator when synthesizing speech). Specifically, linear predictive analysis of the LPC technique starts with a human phonation mechanism, and through research on a short-tube cascade model of a vocal tract, a transfer function of the system is considered to conform to the form of an all-pole digital filter, so that a signal at n moments can be estimated by linear combination of signals at a plurality of moments; linear prediction coefficients LPCs can be obtained by minimizing the mean square error LMS (LMS is short for "Learning management System") between the sampling value of the actual voice and the sampling value of the linear prediction; the calculation method for the LPC includes an autocorrelation method (Debin Durbin method), a covariance method, a lattice method and the like; the rapid and effective calculation ensures the wide use of the acoustic feature; similar acoustic features to the predictive parameter model of LPC are also line spectral pairs LSP, reflection coefficients, etc.
CEP technique: CEP is an abbreviation of software "Cool edge pro", which is a powerful and effective multitrack recording and audio processing software developed by Adobe Systems, USA; the CEP technology is that a homomorphic processing method is utilized, Discrete Fourier Transform (DFT) is solved for a voice signal, then logarithm is obtained, and inverse transform iDFT is obtained to obtain a cepstrum coefficient; for LPC cepstrum (LPCCEP), after obtaining the linear prediction coefficient of the filter, the linear prediction coefficient can be calculated by a recursion formula; experiments show that the stability of characteristic parameters can be improved by using the cepstrum.
Mel technique: mel is Maya embedded voice; unlike acoustic features obtained by the research of the human phonation mechanism such as LPC technology, Mel cepstrum coefficient MFCC and perceptual linear prediction PLP are acoustic features derived by the research result of the human auditory system; research on human auditory mechanisms has found that when two tones of similar frequencies are emitted simultaneously, a human can only hear one tone; the critical bandwidth refers to the boundary of the bandwidth with abrupt change in subjective feeling, and when the frequency difference between two tones is smaller than the critical bandwidth, a person can hear the two tones as one tone, which is called as a masking effect; the Mel scale is one of the measures for this critical bandwidth.
MFCC technology: MFCC is a short for "Mel Frequency Cepstral coeffients", a feature widely used in automatic speech and speaker recognition; the MFCC principle is that firstly, a time domain signal is converted into a frequency domain by FFT, then a logarithm energy spectrum is convoluted by a triangular filter bank distributed according to Mel scales, finally, Discrete Cosine Transform (DCT) is carried out on a vector formed by the output of each filter, and the first N coefficients are taken; the PLP still uses the debin method to calculate LPC parameters, but also uses a method of Discrete Cosine Transform (DCT) on the logarithmic energy spectrum of auditory excitation when calculating autocorrelation parameters.
Further, referring to fig. 3, when the controller receives the output signal of the image sensing terminal and/or the voice recognition terminal, the controller executes corresponding measures according to the pre-loaded logic decision, so that the production equipment slows down or interrupts production, that is, the system can execute corresponding light and heavy measures according to the degree of human intrusion, thereby effectively avoiding the phenomenon that the production equipment is shut down when light intrusion occurs, so that the production is greatly influenced; specifically, the pre-made decisions on the controller include
When the distance between the personnel and the core danger area is greater than the safety distance and no abnormal distress signal exists, the production equipment normally produces;
when the distance between the personnel and the core danger area is less than the safety distance and no abnormal distress signal exists, the production equipment reduces the speed by 50 percent to produce and simultaneously sends out a warning whistle; it should be noted that the deceleration value can be adjusted accordingly according to the actual situation, and the deceleration range is 10% -90%.
When the distance between personnel and the core danger area is greater than the safety distance and an abnormal distress signal exists, the production equipment interrupts production and sends out a warning whistle at the same time;
when the distance between the personnel and the core danger area is less than the safe distance and an abnormal distress signal exists, the production equipment is powered off and suddenly stops, and simultaneously, a warning whistle is sent out.
The foregoing is a preferred embodiment of the present invention, and the basic principles, principal features and advantages of the invention are shown and described. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are intended to illustrate the principles of the invention, but that various changes and modifications may be made without departing from the spirit and scope of the invention, and the invention is intended to be protected by the following claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. The utility model provides a compound intelligent production security protection system which characterized in that: comprises that
The image sensing terminal is used for acquiring image data around the core danger area in real time and carrying out processing analysis;
the voice recognition terminal is used for acquiring voice data around the core danger area in real time and carrying out processing analysis;
the controller is used for receiving information data acquired in real time from the image sensor terminal and the voice recognition terminal, calculating the distance of personnel relative to the core danger area, recognizing abnormal distress signals and sending a control instruction to production equipment;
and the image sensing terminal and/or the voice recognition terminal are/is communicated and interconnected with the controller in a wired and/or wireless mode.
2. The composite intelligent production security system of claim 1, wherein: the image sensing terminal comprises an image sensing module for recording image information around the core danger area, an image processing module for converting the image information into corresponding image data, and an image transmission module for transmitting the image data to the controller; the image sensing module, the image processing module and the image transmission module are sequentially connected; the image transmission module is connected with the controller in a wired and/or wireless mode.
3. The composite intelligent production security system of claim 2, wherein: and the image processing module is provided with a human body identification program based on an HOG characteristic detection technology.
4. The composite intelligent production security system of claim 1, wherein: the voice recognition terminal comprises a voice input module for inputting voice information around the core danger area, an emotion classification module for distinguishing the voice information, a voice processing module for converting the voice information into voice data and a voice transmission module for sending the voice data to the controller; the voice input module, the emotion classification module, the voice processing module and the voice transmission module are sequentially connected; the voice transmission module is connected with the controller in a wired and/or wireless mode.
5. The composite intelligent production security system of claim 1, wherein: the device also comprises a driver, a relay and an actuator; the controller is respectively connected with the driver and the relay, and the driver is respectively connected with the relay and the actuator.
6. The security method of the composite intelligent production security system of claim 1, characterized in that: comprises the following steps
Performing space positioning on the core danger area through the image sensing terminal, and installing a voice recognition terminal;
detecting the distance of personnel relative to a core danger area in real time through an image sensing terminal; identifying whether an abnormal distress signal exists around the core dangerous area through a voice identification terminal;
and the controller executes a corresponding pre-made decision according to the detection results fed back by the image sensing terminal and the voice recognition terminal.
7. The security method of the composite intelligent production security system according to claim 6, characterized in that: and (3) carrying out space positioning on the core danger area: firstly, arranging a plurality of calibration plates in the range and/or the edge of a core danger area, and then photographing, positioning and recording by using an image sensing terminal; the calibration plate is an object that is clearly distinguished from the surrounding environment.
8. The security method of the composite intelligent production security system according to claim 6, characterized in that: distance of detection personnel relative to the core danger zone: when a person enters a shooting range of the image sensing terminal, the image sensing terminal calculates coordinates of all joint points of the human body on the 2D RGB image, then the 2D RGB image is coupled with the depth image to obtain projection of the human body outline on the depth image so as to calculate 3D coordinates of the human body outline, and finally the distance between the person and the core danger area is calculated through all outline points.
9. The security method of the composite intelligent production security system according to claim 6, characterized in that: and (3) identifying abnormal distress signals: firstly, collecting external sound signals; then the voice recognition terminal detects and distinguishes voice information and non-voice information, determines the starting point and the ending point of the voice information to perform framing processing on the voice information, and then performs acoustic feature extraction on each frame of the voice information; and finally, performing emotion classification on the extracted acoustic features to judge whether the voice information is normal emotional voice or panic emotional voice, wherein the panic emotional voice is defaulted to be an abnormal distress signal.
10. The security method of the composite intelligent production security system according to claim 6, characterized in that: the pre-made decision on the controller comprises
When the distance between the personnel and the core danger area is greater than the safety distance and no abnormal distress signal exists, the production equipment normally produces;
when the distance between the personnel and the core danger area is less than the safety distance and no abnormal distress signal exists, the production equipment reduces the speed for production and sends out a warning whistle at the same time;
when the distance between personnel and the core danger area is greater than the safety distance and an abnormal distress signal exists, the production equipment interrupts production and sends out a warning whistle at the same time;
when the distance between the personnel and the core danger area is less than the safe distance and an abnormal distress signal exists, the production equipment is powered off and suddenly stops, and simultaneously, a warning whistle is sent out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010326764.5A CN111223261B (en) | 2020-04-23 | 2020-04-23 | Composite intelligent production security system and security method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010326764.5A CN111223261B (en) | 2020-04-23 | 2020-04-23 | Composite intelligent production security system and security method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111223261A true CN111223261A (en) | 2020-06-02 |
| CN111223261B CN111223261B (en) | 2020-10-27 |
Family
ID=70826446
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010326764.5A Active CN111223261B (en) | 2020-04-23 | 2020-04-23 | Composite intelligent production security system and security method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111223261B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112349296A (en) * | 2020-11-10 | 2021-02-09 | 胡添杰 | Subway platform safety monitoring method based on voice recognition |
| CN112364696A (en) * | 2020-10-13 | 2021-02-12 | 特斯联科技集团有限公司 | Method and system for improving family safety by using family monitoring video |
| CN112598651A (en) * | 2020-12-24 | 2021-04-02 | 武汉吉电科技有限公司 | Intelligent robot processing production detecting system |
| CN112632399A (en) * | 2021-03-09 | 2021-04-09 | 四川万网鑫成信息科技有限公司 | Topological relation obtaining method and device based on spatial position and storage medium |
| CN114023328A (en) * | 2022-01-06 | 2022-02-08 | 南京速冠信息技术有限公司 | Industrial Internet of things digital information transmission system with optimized production line |
| WO2022183372A1 (en) * | 2021-03-02 | 2022-09-09 | 中国科学院深圳先进技术研究院 | Control method, control apparatus, and terminal device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08237637A (en) * | 1995-02-24 | 1996-09-13 | Clarion Co Ltd | Color detector and warning device |
| CN202422353U (en) * | 2012-01-10 | 2012-09-05 | 广汽本田汽车有限公司 | Video warning system |
| CN102982634A (en) * | 2012-11-13 | 2013-03-20 | 上海交通大学 | Human intrusion detection method with audio and video integration |
| WO2013105264A1 (en) * | 2012-01-13 | 2013-07-18 | 三菱電機株式会社 | Risk measurement system |
| CN104284143A (en) * | 2013-07-03 | 2015-01-14 | 智原科技股份有限公司 | Image monitoring system and method thereof |
| CN105554474A (en) * | 2016-02-01 | 2016-05-04 | 福建省计量科学研究院 | Security monitoring system and method |
| CN105632145A (en) * | 2015-12-30 | 2016-06-01 | 中国神华能源股份有限公司 | Personnel approach protection method and system for excavating mobile equipment |
| CN106128475A (en) * | 2016-07-12 | 2016-11-16 | 华南理工大学 | Wearable intelligent safety equipment based on abnormal emotion speech recognition and control method |
| CN110425005A (en) * | 2019-06-21 | 2019-11-08 | 中国矿业大学 | The monitoring of transportation of belt below mine personnel's human-computer interaction behavior safety and method for early warning |
-
2020
- 2020-04-23 CN CN202010326764.5A patent/CN111223261B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08237637A (en) * | 1995-02-24 | 1996-09-13 | Clarion Co Ltd | Color detector and warning device |
| CN202422353U (en) * | 2012-01-10 | 2012-09-05 | 广汽本田汽车有限公司 | Video warning system |
| WO2013105264A1 (en) * | 2012-01-13 | 2013-07-18 | 三菱電機株式会社 | Risk measurement system |
| CN102982634A (en) * | 2012-11-13 | 2013-03-20 | 上海交通大学 | Human intrusion detection method with audio and video integration |
| CN104284143A (en) * | 2013-07-03 | 2015-01-14 | 智原科技股份有限公司 | Image monitoring system and method thereof |
| CN105632145A (en) * | 2015-12-30 | 2016-06-01 | 中国神华能源股份有限公司 | Personnel approach protection method and system for excavating mobile equipment |
| CN105554474A (en) * | 2016-02-01 | 2016-05-04 | 福建省计量科学研究院 | Security monitoring system and method |
| CN106128475A (en) * | 2016-07-12 | 2016-11-16 | 华南理工大学 | Wearable intelligent safety equipment based on abnormal emotion speech recognition and control method |
| CN110425005A (en) * | 2019-06-21 | 2019-11-08 | 中国矿业大学 | The monitoring of transportation of belt below mine personnel's human-computer interaction behavior safety and method for early warning |
Non-Patent Citations (1)
| Title |
|---|
| 陈万军等: "基于深度信息的人体动作识别研究综述", 《西安理工大学学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112364696A (en) * | 2020-10-13 | 2021-02-12 | 特斯联科技集团有限公司 | Method and system for improving family safety by using family monitoring video |
| CN112364696B (en) * | 2020-10-13 | 2024-03-19 | 特斯联科技集团有限公司 | Method and system for improving family safety by utilizing family monitoring video |
| CN112349296A (en) * | 2020-11-10 | 2021-02-09 | 胡添杰 | Subway platform safety monitoring method based on voice recognition |
| CN112598651A (en) * | 2020-12-24 | 2021-04-02 | 武汉吉电科技有限公司 | Intelligent robot processing production detecting system |
| WO2022183372A1 (en) * | 2021-03-02 | 2022-09-09 | 中国科学院深圳先进技术研究院 | Control method, control apparatus, and terminal device |
| CN112632399A (en) * | 2021-03-09 | 2021-04-09 | 四川万网鑫成信息科技有限公司 | Topological relation obtaining method and device based on spatial position and storage medium |
| CN114023328A (en) * | 2022-01-06 | 2022-02-08 | 南京速冠信息技术有限公司 | Industrial Internet of things digital information transmission system with optimized production line |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111223261B (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111223261B (en) | Composite intelligent production security system and security method thereof | |
| CN109300471B (en) | Intelligent video monitoring method, device and system for field area integrating sound collection and identification | |
| US8164484B2 (en) | Detection and classification of running vehicles based on acoustic signatures | |
| CN102737480B (en) | Abnormal voice monitoring system and method based on intelligent video | |
| US11620898B2 (en) | Visual-acoustic monitoring system for event detection, localization and classification | |
| CN103839373B (en) | A kind of unexpected abnormality event Intelligent Recognition alarm device and warning system | |
| EP2464991B1 (en) | A method for human only activity detection based on radar signals | |
| JP6532106B2 (en) | Monitoring device, monitoring method and program for monitoring | |
| US20160078883A1 (en) | Action analysis device, action analysis method, and action analysis program | |
| CN103839346A (en) | Intelligent door and window anti-intrusion device and system and intelligent door control system | |
| US8965068B2 (en) | Apparatus and method for discriminating disguised face | |
| CN103198838A (en) | Abnormal sound monitoring method and abnormal sound monitoring device used for embedded system | |
| KR101899436B1 (en) | Safety Sensor Based on Scream Detection | |
| JP2012048689A (en) | Abnormality detection apparatus | |
| JP2017062349A (en) | Detection device and control method for the same, and computer program | |
| CN113674768B (en) | Acoustic-based help calling detection method, device, equipment and storage medium | |
| CN110634506A (en) | Voice data processing method and device | |
| WO2008038288A2 (en) | System and method for reducing power consumption in a detection system | |
| CN110861988A (en) | Abnormal voiceprint recognition and fault diagnosis monitoring and alarming system for elevator | |
| KR101736466B1 (en) | Apparatus and Method for context recognition based on acoustic information | |
| WO2009028937A1 (en) | Method and apparatus for detection of specific input signal contributions | |
| Wan et al. | Recognition of potential danger to buried pipelines based on sounds | |
| Cheng et al. | Spectrogram-based classification on vehicles with modified loud exhausts via convolutional neural networks | |
| US20130322690A1 (en) | Situation recognition apparatus and method using object energy information | |
| Zhao et al. | Event classification for living environment surveillance using audio sensor networks |
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 |