CN111489317B - Intelligent cinerary casket storage system - Google Patents

Intelligent cinerary casket storage system Download PDF

Info

Publication number
CN111489317B
CN111489317B CN202010396440.9A CN202010396440A CN111489317B CN 111489317 B CN111489317 B CN 111489317B CN 202010396440 A CN202010396440 A CN 202010396440A CN 111489317 B CN111489317 B CN 111489317B
Authority
CN
China
Prior art keywords
iteration
particle
value
cinerary casket
pixel
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
Application number
CN202010396440.9A
Other languages
Chinese (zh)
Other versions
CN111489317A (en
Inventor
钟丽芳
聂顺新
姚文涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangxi Tianjing Jingcang Technology Co ltd
Original Assignee
Jiangxi Tianjing Jingcang Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangxi Tianjing Jingcang Technology Co ltd filed Critical Jiangxi Tianjing Jingcang Technology Co ltd
Priority to CN202010396440.9A priority Critical patent/CN111489317B/en
Publication of CN111489317A publication Critical patent/CN111489317A/en
Application granted granted Critical
Publication of CN111489317B publication Critical patent/CN111489317B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B17/00—Fire alarms; Alarms responsive to explosion
    • G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
    • G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10048—Infrared image

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Emergency Management (AREA)
  • Business, Economics & Management (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)

Abstract

The utility model provides a cinerary casket intelligence system of depositing, includes cinerary casket storage rack, intelligent monitoring system and intelligent storage management center, cinerary casket storage rack is used for depositing the cinerary casket, intelligent storage monitoring system is used for right cinerary casket storage rack carries out safety monitoring, monitoring system is deposited to intelligence will gather monitoring information transmission to intelligent storage management center to intelligence. The invention has the beneficial effects that: the sensor monitoring technology and the image processing technology are applied to the storage management of the cinerary casket, so that the storage management level of the cinerary casket is improved, and the storage safety of the cinerary casket is improved.

Description

Intelligent cinerary casket storage system
Technical Field
The invention relates to the field of intelligent monitoring, in particular to an intelligent cinerary casket storage system.
Background
The prior centralized cinerary casket storage and management device usually uses cinerary casket storage racks which are arranged in rows and columns for storage, and along with the large storage quantity and large scale of cinerary casket, higher requirements are put forward for storage and management, therefore, in order to strengthen and improve the storage and management level of the cinerary casket, the intelligent technology is applied to the storage and management of the cinerary casket, thereby improving the storage and management level of the cinerary casket and improving the storage safety of the cinerary casket.
Disclosure of Invention
Aiming at the problems, the invention aims to provide an intelligent cinerary casket storage system.
The purpose of the invention is realized by the following technical scheme:
an intelligent cinerary casket storage system comprises a cinerary casket storage rack, an intelligent storage monitoring system and an intelligent storage management center, wherein the cinerary casket storage rack is used for storing cinerary casket, the intelligent storage monitoring system comprises a fire monitoring unit, a sensor monitoring unit and a video monitoring unit, the fire monitoring unit adopts an infrared camera to collect infrared images of the cinerary casket storage rack, the sensor monitoring unit adopts a sensor to collect data of the environment where the cinerary casket storage rack is located, the video monitoring unit is used for collecting video images of the cinerary casket storage rack, the intelligent storage monitoring system transmits the collected monitoring information to the intelligent storage management center, the intelligent storage management center comprises a fire judgment unit, an environment evaluation unit, a danger early warning unit and an information display unit, and the fire judgment unit is used for processing the received infrared images, and judging whether a fire disaster occurs according to the processed infrared image, and making a danger early warning unit perform early warning when the fire disaster is judged to occur, wherein the environment evaluation unit is used for processing the received environment data, comparing the processed environment data with a given environment threshold value, making the danger early warning unit perform early warning when the environment data exceeds the given environment threshold value, and the information display unit is used for displaying the received video image.
The beneficial effects created by the invention are as follows: the image processing technology and the sensor monitoring technology are applied to the storage management of the cinerary casket, the infrared image of the cinerary casket storage rack is collected, and the collected infrared image is processed, so that whether a fire disaster occurs or not is judged, and the effective detection of the fire disaster is realized; the sensor is adopted to collect the data of the environment of the cinerary casket storage rack, so that the environment of the cinerary casket storage rack is effectively monitored, the management level of cinerary casket storage is improved, and the safety of cinerary casket storage is improved.
Drawings
The invention is further described with the aid of the accompanying drawings, in which, however, the embodiments do not constitute any limitation to the invention, and for a person skilled in the art, without inventive effort, further drawings may be derived from the following figures.
FIG. 1 is a schematic diagram of the present invention.
Detailed Description
The invention is further described with reference to the following examples.
Referring to fig. 1, the intelligent storage system for cinerary casket of this embodiment includes a cinerary casket storage rack, an intelligent storage monitoring system and an intelligent storage management center, wherein the cinerary casket storage rack is used for storing cinerary casket, the intelligent storage monitoring system includes a fire monitoring unit, a sensor monitoring unit and a video monitoring unit, the fire monitoring unit adopts an infrared camera to collect infrared image of the cinerary casket storage rack, the sensor monitoring unit adopts a sensor to collect data of environment where the cinerary casket storage rack is located, the video monitoring unit is used for collecting video image of the cinerary casket storage rack, the intelligent storage monitoring system transmits collected monitoring information to the intelligent storage management center, the intelligent storage management center includes a fire judgment unit, an environment evaluation unit, a danger early warning unit and an information display unit, the fire judgment unit is used for receiving and processing the infrared image, and judging whether a fire disaster occurs according to the processed infrared image, and when the fire disaster occurs, making a danger early warning unit perform early warning, wherein the environment evaluation unit is used for performing smooth filtering processing on the received environment data, comparing the processed environment data with a given environment threshold value, and making the danger early warning unit perform early warning when the environment data exceeds the given environment threshold value, and the information display unit is used for displaying the received video image.
Preferably, the fire monitoring unit and the video monitoring unit transmit the acquired images to an intelligent storage management center in a GPRS communication mode.
Preferably, the environment monitoring unit adopts a sensor to collect data of the environment where the cinerary casket storage rack is located, transmits the collected environment data to the sink node through a wireless sensor network, and transmits the environment data to the intelligent storage management center through the sink node.
Preferably, the collected data of the environment where the cinerary casket storage rack is located includes temperature data, humidity data and smoke concentration data.
In the preferred embodiment, the image processing technology and the sensor monitoring technology are applied to the storage management of the cinerary casket, the infrared image of the cinerary casket storage rack is collected, and the collected infrared image is processed, so that whether a fire disaster occurs or not is judged, and the effective detection of the fire disaster is realized; the sensor is adopted to collect the data of the environment of the cinerary casket storage rack, thereby realizing the effective monitoring of the environment of the cinerary casket storage rack, improving the management level of the cinerary casket storage and the safety of the cinerary casket storage
Preferably, the fire determination unit is configured to perform filtering processing on the received infrared image, divide an area image of the cinerary casket storage rack from the filtered infrared image, calculate a mean gray value of the divided area image of the cinerary casket storage rack, compare the calculated mean gray value with a given safety threshold, and determine that a fire occurs when the mean gray value is higher than the given safety threshold.
Preferably, the fire determination unit is configured to perform filtering processing on the received infrared image, where I represents the infrared image currently being processed by the fire determination unit, I (x, y) represents a pixel at a coordinate (x, y) in the infrared image I, f '(x, y) represents a gray value of the pixel I (x, y) after the filtering processing, and an expression of f' (x, y) is as follows:
Figure BDA0002487736410000031
where Ω (x, y) denotes a local neighborhood of 5 × 5 centered on a pixel I (x, y), I (I, j) denotes a pixel at a coordinate (I, j) in the infrared image I, f (I, j) denotes a gradation value of the pixel I (I, j), q (I, j) denotes a weight coefficient of the pixel I (I, j), and the expression of q (I, j) is:
Figure BDA0002487736410000032
in the formula, σdIs the spatial filtering radius, and σd＝0.5，σsIs the value domain filter radius, and σsDefining that the pixel I (x, y) is locally located, where f (x, y) is the gray scale value of the pixel I (x, y), and μ (x, y) is the range correction coefficient corresponding to the pixel I (x, y)The corresponding statistical coefficient in the neighborhood Ω (x, y) is h (x, y), and then h (x, y) is ΣI(m,n)∈Ω(x，y)η (m, n), where I (m, n) is the pixel at coordinate (m, n) in the local neighborhood Ω (x, y), f (m, n) is the gray value corresponding to the pixel I (m, n), η (m, n) is the judgment factor corresponding to the pixel I (m, n), and when | f (x, y) -f (m, n) <' > is equal to y>When P (Ω (x, y)), η (m, n) is 1, and when | f (x, y) -f (m, n) | is less than or equal to P (Ω (x, y)), η (m, n) is 0, where P (Ω (x, y)) is a determination threshold corresponding to a pixel in a local neighborhood Ω (x, y), then η (m, n) is 0
Figure BDA0002487736410000033
Wherein, I (a, b) is a pixel at the coordinate (a, b) in the local neighborhood Ω (x, y), f (a, b) is a gray value corresponding to the pixel I (a, b), and N (Ω (x, y)) is the number of pixels in the local neighborhood Ω (x, y); when in use
Figure BDA0002487736410000034
When u (x, y) is 1; when in use
Figure BDA0002487736410000035
When it is, then
Figure BDA0002487736410000036
Wherein the content of the first and second substances,
Figure BDA0002487736410000037
representing the mean of the grey values of the pixels in the local neighborhood Ω (x, y), fmax(x, y) and fminAnd (x, y) respectively represents the maximum value and the minimum value of the gray value of the pixel in the local neighborhood Ω (x, y), μ (I, j) is a value range correction coefficient corresponding to the pixel I (I, j), and the value of μ (I, j) can be obtained by the same method according to the value range correction coefficient μ (x, y) corresponding to the pixel I (x, y).
The preferred embodiment is used for filtering the received infrared image, calculating the weight coefficient of the local neighborhood pixels participating in filtering according to the spatial similarity and the value domain similarity between the pixel points, and determining the value of the filtering pixel by using weighted average, so that the edge information in the image can be effectively retained while the noise pixel is effectively removed; in view of the above situation, the preferred embodiment introduces both the value domain correction coefficient of the pixel to be filtered and the value domain correction coefficient of the local neighborhood pixel participating in filtering into the value domain similarity calculation part of the pixel, and the introduced value domain correction coefficient can effectively adjust the value of the value domain similarity in a self-adaptive manner according to the abnormal degree of the pixel, so that the value domain similarity calculation part can not be affected by the noise pixel, thereby well measuring the actual value domain similarity between the pixels and improving the accuracy of the output filtering pixel value.
Preferably, the fire judgment unit divides an area image of the cinerary casket storage rack from the filtered infrared image by using a variance method between the maximum classes, and determines an optimal threshold value of the variance method between the maximum classes by using a particle swarm algorithm.
Preferably, the particle swarm algorithm adopts the maximum inter-class variance as a fitness function, and the larger the fitness function value is, the better the optimization result of the particle is.
Preferably, the particles in the population of particles are initialized randomly;
preferably, the iteration interval of the particle group is (0, T)max]Wherein, TmaxFor the maximum iteration number of a given particle swarm, dividing the iteration interval of the particle swarm into m iteration subintervals, and setting TkRepresents the kth iteration subinterval, and
Figure BDA0002487736410000041
k is 1,2, …, m, m being a given positive integer, and m may be TmaxTrimming; at the initial stage of each iteration subinterval, the particles in the particle swarm are divided into particles for exploration and particles for exploration, specifically:
setting the particle swarm to be in the kth iteration subinterval T currentlykDefining a particle i in the particle swarm in a k iteration subinterval TkOfThe optimizing ability value at the initial stage is Ni(k) Then N isi(k) The calculation formula of (2) is as follows:
Figure BDA0002487736410000042
in the formula (I), the compound is shown in the specification,
Figure BDA0002487736410000043
indicates that the particle i is in the second
Figure BDA0002487736410000044
The fitness function value at the time of the secondary iteration,
Figure BDA0002487736410000045
denotes a particle group in
Figure BDA0002487736410000046
Maximum fitness function value, beta, at sub-iterationi(j) Representing the corresponding optimizing judgment function of the particle i in the j iteration, when h isi(j)-hi(j-1)>When 0, then betai(j) When h is equal to 1i(j)-hi(j-1) is less than or equal to 0, then betai(j)＝0，hi(j) Represents the fitness function value h corresponding to the particle i in the j iterationi(j-1) represents the fitness function value corresponding to the particle i in the (j-1) th iteration, s (k) is a time-lag adjusting parameter corresponding to the kth iteration subinterval, and
Figure BDA0002487736410000051
arranging the particles in the particle swarm from high to low according to the optimizing capacity value, and before selection
Figure BDA0002487736410000052
In the kth iteration subinterval TkFor exploration, remainder
Figure BDA0002487736410000053
In the kth iteration subinterval TkFor exploration.
The preferred embodiment divides the iterative process of the particle swarm into a plurality of iterative subintervals, selects particles for exploration and particles for exploration from the particle swarm according to the optimizing capability value of the particles in the initial stage of each iterative subinterval, the optimizing capability value of the particles is comprehensively determined by two parts, the first part judges the optimizing capability of the particles according to the fitness function value when the particles enter the iterative subinterval, the larger the fitness function value when the particles enter the iterative subinterval, the better the current optimizing capability of the particles is, the second part judges the optimizing capability of the particles according to the historical optimizing information of the particles, the comprehensive judgment is carried out according to the optimizing success times of the particles and the optimizing success degree of the particles, the more the optimizing times of the particles are, and the higher the fitness function value of the optimizing success is compared with the fitness function value of the last iteration, the stronger the historical optimizing capability of the particle is, the more time lag phenomenon existing when the current optimizing capability of the particle is judged by adopting the historical optimizing information of the particle is considered, the corresponding time lag adjusting parameter is introduced into the preferred embodiment, the time lag adjusting parameter adjusts the influence degree of the historical optimizing information on the current optimizing capability value of the particle by calculating the iteration number of successful particle optimizing and the distance of the current iteration number, when the iteration number of successful particle optimization is closer to the current iteration number, the influence degree of the historical optimization information on the current optimization capability value of the particle is larger, and when the iteration number of successful particle optimization is farther from the current iteration number, the influence degree of the historical optimizing information on the current optimizing capability value of the particle is reduced, so that the calculated optimizing capability value of the particle can better meet the actual condition; the higher the optimizing capability value of the particle is, the stronger the optimizing capability of the particle is, the higher the optimizing capability value of the particle is, the particles with the higher optimizing capability value are selected from the particle swarm for exploration, the particles with the lower optimizing capability value are used for exploration, in each iteration subinterval, the particles for exploration are optimized from the whole, the particles for exploration are mainly used for developing a new better area, the particles for exploration are mainly used for local optimizing, fine search is carried out near the better area, therefore, the whole and local searching capabilities of the particle swarm algorithm are balanced in each iteration subinterval, when the particle swarm enters the next iteration subinterval, the particles for exploration and the particles for exploration are reselected, and therefore, the searching efficiency of the algorithm is effectively improved.
Preferably, let T be the current iteration number, and T ∈ TkI.e. by
Figure BDA0002487736410000054
Namely, it is
Figure BDA0002487736410000055
Then the particle i is updated at the tth iteration in the following way:
Vi(t+1)＝ωi(t)Vi(t)+c1r1(Xbesti(t)-Xi(t))+c2r2(Xbest(t)-Xi(t))
Figure BDA0002487736410000061
in the formula, Vi(t) and Xi(t) respectively represents the corresponding speed and position, V, of the particle i at the t-th iterationi(t +1) and Xi(t +1) denotes the corresponding velocity and position, Xtest, of the particle i at the (t +1) th iteration, respectivelyi(t) represents the individual optimal solution of particle i at the t-th iteration, Xbox (t) represents the global optimal solution of the particle population at the t-th iteration, c1And c2Represents a learning factor, r1And r2Denotes a random number, X, between (0,1)max(t +1) is a position threshold value, omega, corresponding to the set particle swarm in the (t +1) th iterationi(t) represents the inertial weight factor corresponding to particle i at the t-th iteration, and when particle i is the particle for exploration at the t-th iteration, the inertial weight factor omega corresponding to particle i at the t-th iteration is usedi(t) setting as:
Figure BDA0002487736410000062
when the particle i is a particle for searching in the t-th iteration, the inertia weight factor omega corresponding to the particle i in the t-th iteration is usedi(t) setting as:
Figure BDA0002487736410000063
in the formula, ωk(max) represents the maximum inertial weight factor for a particle in the population at the kth iteration subinterval, and
Figure BDA0002487736410000064
omega (max) and omega (min) are given maximum inertia weight factors and minimum inertia weight factors, rho (k-1) is an optimized detection coefficient of the (k-1) th iteration subinterval, and
Figure BDA0002487736410000065
Figure BDA0002487736410000066
xbox (l) is a global optimal solution of the particle swarm in the first iteration, h (Xbox (l)) represents a fitness function value corresponding to the global optimal solution Xbox (l), Xbox (l-1) is a global optimal solution of the particle swarm in the (l-1) th iteration, h (Xbox (l-1)) represents a fitness function value corresponding to the global optimal solution Xbox (l-1), and h (Xbox (l-1)) represents a fitness function value corresponding to the global optimal solution Xbox (l-1)k-1(max) and hk-1(min) respectively represents the (k-1) th iteration subinterval Tk-1The maximum fitness function value and the minimum fitness function value of the medium particles.
The optimal embodiment is used for setting the inertia weight factors of the particles in the particle swarm, firstly, the maximum inertia weight factor of each iteration subinterval is determined, the larger maximum inertia weight factor is set for the iteration subinterval in the previous stage, the global search capability of the particle swarm algorithm is enhanced, the smaller maximum inertia weight factor is set for the iteration subinterval in the later stage, and the local search capability of the particles is enhanced; setting different inertia weight factors for the particles for exploration and the particles for exploration in each iteration subinterval, wherein the particles for exploration are emphatically used for global search, so a larger inertia weight factor is set, when the inertia weight factors are set for the particles for exploration, an optimizing detection coefficient of a previous iteration subinterval is introduced, the optimizing detection coefficient adjusts the inertia weight factor value of the particles in the current iteration subinterval according to the optimizing condition of the particle swarm in the previous iteration subinterval, when the optimizing process of the particle swarm in the previous iteration subinterval is larger, the inertia weight factor of the particles for exploration in the current iteration subinterval is reduced, so that the particles for exploration are prevented from getting out of the optimal solution to be searched, when the optimizing process of the particle swarm in the previous iteration subinterval is smaller, the inertia weight factor of the particles for exploration in the current iteration subinterval is increased, therefore, the global search capability is enhanced, the particles for searching are mainly used for local search, so that a smaller inertia weight factor is set, and when the inertia weight factor is set for the particles for searching, the optimizing detection coefficient of the previous iteration subinterval and the current iteration frequency are comprehensively introduced, so that the particles for searching are reduced along with the increase of the optimizing detection coefficient and the current iteration frequency, the range of the local search is gradually reduced, and the convergence speed of the algorithm is improved.
Preferably, said Xmax(t +1) is the position threshold value corresponding to the set particle swarm in the (t +1) th iteration, and then the position threshold value X corresponding to the particle swarm in the (t +1) th iterationmaxThe expression of (t +1) is:
Figure BDA0002487736410000071
wherein M is the number of particles in the particle group, δi(t) is the global judgment function of particle i in the t-th iteration, when h (Xbox (t)) -hi(t)<When U (t) is greater than δi(t) 1, when h (Xtest (t)) -hi(t)>When U (t) is greater than δi(t) ═ 0, where h (xtest (t)) is the fitness function value corresponding to the global optimal solution xtest (t), and h (xtest (t)) isi(t)) is the individual optimal solution Xboxi(t) the corresponding fitness function value, U (t) is the t-th iterationA global decision threshold corresponding to the time, and
Figure BDA0002487736410000072
Figure BDA0002487736410000073
wherein h ismid(t) represents the median fitness function of the population at the t-th iteration.
The preferred embodiment is for determining a position threshold for a particle in a population of particles, the position threshold for the population of particles being determined by two parts together, the first part
Figure BDA0002487736410000074
The second part is used for counting the proportion of the current better solution in the particle swarm during the current iteration, when the particle swarm has more better solutions during the current iteration, the value of the position threshold value is reduced, so that the convergence speed of the algorithm can be accelerated, the quality of the solution of the particle swarm algorithm can be guaranteed, and the second part is used for calculating the proportion of the current better solution in the particle swarm during the current iteration, and the second part is used for calculating the solution quality of the particle swarm algorithm
Figure BDA0002487736410000075
The optimization situation and the iteration times of the particles in the particle swarm during the current iteration are jointly determined, the particles in the particle swarm are more concentrated near the global optimal solution along with the increase of the iteration times, namely, the values of the individual optimal solution and the global optimal solution of the particles in the particle swarm are closer, and at the moment, the position threshold value is reduced, so that the convergence of the particle swarm is accelerated.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (5)

1. An intelligent cinerary casket storage system is characterized by comprising a cinerary casket storage rack, an intelligent storage monitoring system and an intelligent storage management center, wherein the cinerary casket storage rack is used for storing cinerary casketThe frame is used for storing the cinerary casket, the intelligent storage monitoring system comprises a fire monitoring unit, a sensor monitoring unit and a video monitoring unit, the fire monitoring unit adopts an infrared camera to collect infrared images of the cinerary casket storage frame, the sensor monitoring unit adopts a sensor to collect data of the environment where the cinerary casket storage frame is located, the video monitoring unit is used for collecting video images of the cinerary casket storage frame, the intelligent storage monitoring system transmits the collected monitoring information to an intelligent storage management center, the intelligent storage management center comprises a fire judging unit, an environment evaluating unit, a danger early warning unit and an information display unit, the fire judging unit is used for processing the received infrared images, judging whether a fire disaster occurs according to the processed infrared images, and making the danger early warning unit give an early warning when the fire disaster occurs, the environment evaluation unit is used for processing the received environment data, comparing the processed environment data with a given environment threshold value, and making the danger early warning unit perform early warning when the environment data exceeds the given environment threshold value, and the information display unit is used for displaying the received video image; the fire judgment unit is used for carrying out filtering processing on the received infrared image, dividing the infrared image after filtering processing into a regional image of the cinerary casket storage rack, calculating a mean value of gray values of the regional image of the cinerary casket storage rack obtained by division, comparing the mean value of the gray values obtained by calculation with a given safety threshold value, and judging that a fire disaster occurs when the mean value of the gray values is higher than the given safety threshold value; the fire judgment unit divides an area image of the cinerary casket storage rack in the filtered infrared image by adopting a maximum inter-class variance method, determines an optimal threshold value of the maximum inter-class variance method by adopting a particle swarm algorithm, and sets an iteration interval of a particle swarm to be (0, T)max]Wherein, TmaxFor the maximum iteration number of a given particle swarm, dividing the iteration interval of the particle swarm into m iteration subintervals, and setting TkRepresents the kth iteration subinterval, and
Figure FDA0003201606890000011
Figure FDA0003201606890000012
m is a given positive integer, and m may be TmaxTrimming; at the initial stage of each iteration subinterval, the particles in the particle swarm are divided into particles for exploration and particles for exploration, specifically:
setting the particle swarm to be in the kth iteration subinterval T currentlykDefining a particle i in the particle swarm in a k iteration subinterval TkHas an initial optimization ability value of Ni(k) Then N isi(k) The calculation formula of (2) is as follows:
Figure FDA0003201606890000013
in the formula (I), the compound is shown in the specification,
Figure FDA0003201606890000014
indicates that the particle i is in the second
Figure FDA0003201606890000015
The fitness function value at the time of the secondary iteration,
Figure FDA0003201606890000016
denotes a particle group in
Figure FDA0003201606890000017
Maximum fitness function value, beta, at sub-iterationi(j) Representing the corresponding optimizing judgment function of the particle i in the j iteration, when h isi(j)-hi(j-1)>When 0, then betai(j) When h is equal to 1i(j)-hi(j-1) is less than or equal to 0, then betai(j)＝0，hi(j) Represents the fitness function value h corresponding to the particle i in the j iterationi(j-1) represents the fitness function value corresponding to the particle i in the (j-1) th iteration, s (k) is a time-lag adjusting parameter corresponding to the kth iteration subinterval, and
Figure FDA0003201606890000021
Figure FDA0003201606890000022
arranging the particles in the particle swarm from high to low according to the optimizing capacity value, and before selection
Figure FDA0003201606890000023
In the kth iteration subinterval TkFor exploration, remainder
Figure FDA0003201606890000024
In the kth iteration subinterval TkFor exploration.
2. The intelligent cinerary casket storage system as claimed in claim 1, wherein said intelligent cinerary casket storage system comprises an environment monitoring unit, said environment monitoring unit adopts sensor to collect the data of the environment of cinerary casket storage rack, and transmits the collected environment data to the aggregation node through wireless sensor network, and the aggregation node transmits the environment data to the intelligent storage management center.
3. The intelligent cinerary casket storage system as claimed in claim 1, wherein said fire disaster determination unit is configured to filter the received infrared image, let I denote the infrared image currently being processed by the fire disaster determination unit, I (x, y) denote the pixel at the coordinate (x, y) in the infrared image I, let f '(x, y) denote the gray value of the pixel I (x, y) after filtering, and the expression of f' (x, y) is:
Figure FDA0003201606890000025
where Ω (x, y) denotes a local neighborhood of 5 × 5 centered on a pixel I (x, y), I (I, j) denotes a pixel at a coordinate (I, j) in the infrared image I, f (I, j) denotes a gradation value of the pixel I (I, j), q (I, j) denotes a weight coefficient of the pixel I (I, j), and the expression of q (I, j) is:
Figure FDA0003201606890000026
in the formula, σdIs the spatial filtering radius, and σd＝0.5，σsIs the value domain filter radius, and σsWhen f (x, y) is the gray scale value of the pixel I (x, y), μ (x, y) is the value range correction coefficient corresponding to the pixel I (x, y), and the statistical coefficient corresponding to the pixel I (x, y) in the local neighborhood Ω (x, y) is defined as h (x, y), then h (x, y) is ΣI(m,n)∈Ω(x,y)η (m, n), where I (m, n) is the pixel at coordinate (m, n) in the local neighborhood Ω (x, y), f (m, n) is the gray value corresponding to the pixel I (m, n), η (m, n) is the judgment factor corresponding to the pixel I (m, n), and when | f (x, y) -f (m, n) <' > is equal to y>When P (Ω (x, y)), η (m, n) is 1, and when | f (x, y) -f (m, n) | is less than or equal to P (Ω (x, y)), η (m, n) is 0, where P (Ω (x, y)) is a determination threshold corresponding to a pixel in a local neighborhood Ω (x, y), then η (m, n) is 0
Figure FDA0003201606890000031
Wherein, I (a, b) is a pixel at the coordinate (a, b) in the local neighborhood Ω (x, y), f (a, b) is a gray value corresponding to the pixel I (a, b), and N (Ω (x, y)) is the number of pixels in the local neighborhood Ω (x, y); when in use
Figure FDA0003201606890000032
Figure FDA0003201606890000033
When u (x, y) is 1; when in use
Figure FDA0003201606890000034
When it is, then
Figure FDA0003201606890000035
Wherein the content of the first and second substances,
Figure FDA0003201606890000036
representing the mean of the grey values of the pixels in the local neighborhood Ω (x, y), fmax(x, y) and fminAnd (x, y) respectively represent the maximum value and the minimum value of the gray value of the pixel in the local neighborhood Ω (x, y), and μ (I, j) is a value range correction coefficient corresponding to the pixel I (I, j).
4. The intelligent cinerary casket storage system as claimed in claim 1, wherein T is set as the current iteration number, and T is T ∈ TkThen, the particle i is updated in the t-th iteration in the following manner:
Vi(t+1)＝ωi(t)Vi(t)+c1r1(Xbesti(t)-Xi(t))+c2r2(Xbest(t)-Xi(t))
Figure FDA0003201606890000037
in the formula, Vi(t) and Xi(t denotes the corresponding velocity and position of the particle i at the t-th iteration, V, respectivelyi(t +1) and Xi(t +1) denotes the corresponding velocity and position, Xtest, of the particle i at the (t +1) th iteration, respectivelyi(t) represents the individual optimal solution of particle i at the t-th iteration, Xbox (t) represents the global optimal solution of the particle population at the t-th iteration, c1And c2Represents a learning factor, r1And r2Denotes a random number, X, between (0,1)max(t +1) is a position threshold value, omega, corresponding to the set particle swarm in the (t +1) th iterationi(t) represents the inertial weight factor corresponding to particle i at the t-th iteration, and when particle i is the particle for exploration at the t-th iteration, the inertial weight factor omega corresponding to particle i at the t-th iteration is usedi(t) setting as:
Figure FDA0003201606890000038
when the particle i is a particle for searching in the t-th iteration, the inertia weight factor omega corresponding to the particle i in the t-th iteration is usedi(t) setting as:
Figure FDA0003201606890000039
in the formula, ωk(max) represents the maximum inertial weight factor for a particle in the population at the kth iteration subinterval, and
Figure FDA00032016068900000310
omega (max) and omega (min) are given maximum inertia weight factors and minimum inertia weight factors, rho (k-1) is an optimized detection coefficient of the (k-1) th iteration subinterval, and
Figure FDA00032016068900000311
Figure FDA00032016068900000312
xbox (l) is a global optimal solution of the particle swarm in the first iteration, h (Xbox (l)) represents a fitness function value corresponding to the global optimal solution Xbox (l), Xbox (l-1) is a global optimal solution of the particle swarm in the (l-1) th iteration, h (Xbox (l-1)) represents a fitness function value corresponding to the global optimal solution Xbox (l-1), and h (Xbox (l-1)) represents a fitness function value corresponding to the global optimal solution Xbox (l-1)k-1(max) and hk-1(min) respectively represents the (k-1) th iteration subinterval Tk-1The maximum fitness function value and the minimum fitness function value of the medium particles.
5. An intelligent cinerary casket storage system as defined in claim 4 wherein said X ismax(t +1) is the position threshold value corresponding to the set particle swarm in the (t +1) th iteration, and then the position threshold value X corresponding to the particle swarm in the (t +1) th iterationmaxThe expression of (t +1) is:
Figure FDA0003201606890000041
wherein M is the number of particles in the particle group, δi(t) is the global judgment function of particle i in the t-th iteration, when h (Xbox (t)) -hi(t)<When U (t) is greater than δi(t) 1, when h (Xtest (t)) -hi(t)>When U (t) is greater than δi(t) ═ 0, where h (cbest (t)) is the fitness function value corresponding to the global optimal solution xtest (t), and h (xtest)i(t)) is the individual optimal solution Xboxi(t) the corresponding fitness function value, U (t) is the corresponding global judgment threshold value in the t iteration, and
Figure FDA0003201606890000042
Figure FDA0003201606890000043
wherein h ismid(t) represents the median fitness function of the population at the t-th iteration.
CN202010396440.9A 2020-05-12 2020-05-12 Intelligent cinerary casket storage system Active CN111489317B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010396440.9A CN111489317B (en) 2020-05-12 2020-05-12 Intelligent cinerary casket storage system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010396440.9A CN111489317B (en) 2020-05-12 2020-05-12 Intelligent cinerary casket storage system

Publications (2)

Publication Number Publication Date
CN111489317A CN111489317A (en) 2020-08-04
CN111489317B true CN111489317B (en) 2021-09-14

Family

ID=71795389

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010396440.9A Active CN111489317B (en) 2020-05-12 2020-05-12 Intelligent cinerary casket storage system

Country Status (1)

Country Link
CN (1) CN111489317B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112351071B (en) * 2020-10-12 2021-06-11 华润三九（枣庄）药业有限公司 Traditional chinese medicine production remote monitering system based on cloud calculates

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1865634A (en) * 2005-01-05 2006-11-22 曾建民 Underground cemetery
CN107103609A (en) * 2017-04-17 2017-08-29 上海电力学院 Niblack power equipment Infrared Image Segmentations based on particle group optimizing
CN107424382A (en) * 2017-07-21 2017-12-01 谢锋 A kind of underground palace monitoring system
CN107452011A (en) * 2017-08-11 2017-12-08 深圳市益鑫智能科技有限公司 A kind of soot dust granule on-line monitoring system in real time
CN108397037A (en) * 2018-03-14 2018-08-14 上海技匠电子科技有限公司 Three-dimensional intelligent ecological saves land the system of burying
CN108492517A (en) * 2018-03-06 2018-09-04 深圳智达机械技术有限公司 A kind of fire monitoring system for building
CN108877127A (en) * 2018-04-27 2018-11-23 西安科技大学 Forest fire detection system and method based on image procossing
CN109506565A (en) * 2018-12-12 2019-03-22 厦门大易孝德智能科技有限公司 A kind of underground palace cemetery park ecology intelligent management system

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
MX2017011282A (en) * 2017-09-04 2019-03-07 Grupo Gayosso S A De C V Illuminated niches for storing cinerary urns.

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1865634A (en) * 2005-01-05 2006-11-22 曾建民 Underground cemetery
CN107103609A (en) * 2017-04-17 2017-08-29 上海电力学院 Niblack power equipment Infrared Image Segmentations based on particle group optimizing
CN107424382A (en) * 2017-07-21 2017-12-01 谢锋 A kind of underground palace monitoring system
CN107452011A (en) * 2017-08-11 2017-12-08 深圳市益鑫智能科技有限公司 A kind of soot dust granule on-line monitoring system in real time
CN108492517A (en) * 2018-03-06 2018-09-04 深圳智达机械技术有限公司 A kind of fire monitoring system for building
CN108397037A (en) * 2018-03-14 2018-08-14 上海技匠电子科技有限公司 Three-dimensional intelligent ecological saves land the system of burying
CN108877127A (en) * 2018-04-27 2018-11-23 西安科技大学 Forest fire detection system and method based on image procossing
CN109506565A (en) * 2018-12-12 2019-03-22 厦门大易孝德智能科技有限公司 A kind of underground palace cemetery park ecology intelligent management system

Also Published As

Publication number Publication date
CN111489317A (en) 2020-08-04

Similar Documents

Publication Publication Date Title
CN111079663B (en) High-altitude parabolic monitoring method and device, electronic equipment and storage medium
CN110542885B (en) Millimeter wave radar target tracking method in complex traffic environment
CN112001339A (en) Pedestrian social distance real-time monitoring method based on YOLO v4
CN111709285A (en) Epidemic situation protection monitoring method and device based on unmanned aerial vehicle and storage medium
CN110427922A (en) One kind is based on machine vision and convolutional neural networks pest and disease damage identifying system and method
CN107240092B (en) Image ambiguity detection method and device
CN110633643A (en) Abnormal behavior detection method and system for smart community
CN112581262A (en) Whale algorithm-based fraud detection method for optimizing LVQ neural network
CN110555870B (en) DCF tracking confidence evaluation and classifier updating method based on neural network
CN112802054B (en) Mixed Gaussian model foreground detection method based on fusion image segmentation
CN105631418A (en) People counting method and device
JP5388829B2 (en) Intruder detection device
CN104077757A (en) Road background extraction and updating method with fusion of real-time traffic state information
CN113409362B (en) High altitude parabolic detection method and device, equipment and computer storage medium
CN110889328A (en) Method, device, electronic equipment and storage medium for detecting road traffic condition
CN111489317B (en) Intelligent cinerary casket storage system
CN103456009A (en) Method, device and monitoring system for target detection
CN109239702B (en) Airport low-altitude flying bird number statistical method based on target state set
CN111008991A (en) Background perception related filtering target tracking method
CN110211153A (en) Method for tracking target, target tracker and computer storage medium
CN115953719A (en) Multi-target recognition computer image processing system
CN116860840A (en) Rapid retrieval method for highway pavement information
CN113990017B (en) Forest and grassland fire early warning system and method based on PNN neural network
CN113838087B (en) Anti-occlusion target tracking method and system
CN106874838A (en) Merge the vision Human bodys&#39; response method of complementary characteristic

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