Disclosure of Invention
In view of the above problems, the present invention aims to provide an intelligent medical care management system based on block chains and image processing.
The purpose of the invention is realized by the following technical scheme:
the intelligent medical care management system based on the block chain and image processing comprises a first information acquisition module, a second information acquisition module, a video monitoring module, an intelligent home control module, a wireless communication module, an intelligent management terminal and a block chain storage module, wherein the first information acquisition module is used for acquiring indoor environment parameter data, the second information acquisition module is used for acquiring human physiological parameter data of the old, the video monitoring module is used for acquiring video images of the old, the first information acquisition module, the second information acquisition module and the video monitoring module transmit the acquired data and the video images to the intelligent management terminal through the wireless communication module, the intelligent management terminal comprises an indoor environment management unit, a human health management unit, an image processing unit and an information display unit, and the indoor environment management unit is used for analyzing the received environment parameter data, when the environmental parameter data is not in a given comfort level environmental parameter data range, the indoor environment management unit sends a control instruction to the intelligent home control module through the wireless communication module, the intelligent home control module controls indoor electrical equipment to adjust the indoor environment according to the received control instruction, the human health management unit is used for analyzing the received human physiological parameter data, when the human physiological parameter data is not in the given safe human physiological parameter data range, early warning is carried out, the image processing unit is used for processing the received video image and displaying the processed video image on the information display unit, and the block chain storage module is used for storing the data received by the intelligent management terminal and the processed video image.
Preferably, the image processing unit is configured to perform denoising processing on the received video image, where I represents the image denoised by the image processing unit, I (x, y) represents a pixel at a coordinate (x, y) in the image I, and perform denoising processing on the pixel I (x, y), and define ρr(x, y) represents the gray-scale detection factor corresponding to the pixel I (x, y), then ρrThe expression of (x, y) is:
where Ω (x, y) represents a local neighborhood of the pixel I (x, y), and Ω (x, y) is a local neighborhood of (2R +1) × (2R +1) centered on the pixel I (x, y), where R is a positive integer, and let c (I) and k (I) represent the length and width of the image I, respectively, then R < min { c (I), k (I) }, h (x, y) represent the grayscale value of the number of pixels I (x, y), I (a, b) represent the pixel at coordinates (a, b) in the image I, and I (a, b) ∈ Ω (x, y), h (a, b) represent the grayscale value of the pixel I (a, b), and M (x, y) represents Ω (x, y) in the local neighborhood;
given a gray detection threshold T (ρ)
r) And regulatory factor
And is
Wherein,
representing the mean, Δ, of the absolute differences between the grey values of the pixels in the local neighborhood Ω (x, y)
mid(x, y) represents the median of the absolute differences between the grey values of the pixels in the local neighborhood Ω (x, y),
when rho
r(x,y)<T(ρ
r) If yes, judging the pixel I (x, y) as a normal pixel; when in use
If so, judging the pixel I (x, y) as noise data; when in use
If yes, judging the pixel I (x, y) as a suspicious pixel;
let H (x, y) denote the gray scale value of the pixel I (x, y) processed by the image processing unit, and when the pixel I (x, y) is determined as a normal pixel, H (x, y) is equal to H (x, y), and when the pixel I (x, y) is determined as a noise pixel or a suspicious pixel, the value of H (x, y) is:
in the formula, #
1(a, b) represents a gradation detection factor ρ
rA first statistical coefficient of (a, b), and
where ρ is
r(a, b) represents a gray-scale detection factor, ω, corresponding to the pixel I (a, b)
1(a, b) represents a first weight coefficient of the pixel I (a, b) to the pixel I (x, y), and
σ
rrepresenting a gray level smoothing factor, η
r(a, b) represents a first weight coefficient ω
1(a, b) a regulatory factor, and
ω
2(a, b) represents a second weight coefficient of the pixel I (a, b) to the pixel I (x, y), and
wherein eta is
s(a, b) represents a second weight coefficient ω
2(a, b) a regulatory factor, and
ψ
2(a, b) represents a gradation detection factor ρ
r(a, b) second statistical coefficient, and
σ
srepresenting a spatial smoothing factor, p
s(x, y) represents a spatial detection factor, ρ, of the pixel I (x, y)
s(max) is the maximum value of the spatial detection factor, ρ, of the pixels in the image I
s(a, b) represents a spatial detection factor of the pixel I (a, b), and ρ
sThe values of (a, b) are determined in the following manner:
let Ω (a, b) denote the local neighborhood of the pixel I (a, b), and Ω (a, b) be the local neighborhood of (2R +1) × (2R +1) centered on the pixel I (a, b), I (p, q) denote the pixel at coordinates (p, q) in the image I, and I (p, q) ∈ Ω (a, b), h (p, q) denote the grayscale value of the pixel I (p, q), given a difference threshold T (Δ), and
wherein,
representing the median function, mean
I(p,q)∈Ω(a,b)L h (p, q) -h (a, b) | represents a mean function; when the pixel I (p, q) satisfies | h (a, b) -h (p, q) | is less than or equal to T (delta), the pixel I (p, q) is marked as 1, when the pixel I (p, q) satisfies | h (a, b) -h (p, q) > T (delta), the pixel I (p, q) is marked as 0, and the pixel marked as 1 in the local neighborhood omega (a, b) forms a set K
1(a, b), then ρ
sThe values of (a, b) are:
wherein, I (c)1,d1) Represents the coordinates (c) in the image I1,d1) A pixel of (b), and I (c)1,d1)∈K1(a, b), I (p ', q') denotes the pixel at the coordinates (p ', q') in the image I, and I (p ', q') is E.OMEGA (a, b), M1(a, b) represents a set K1The number of pixels in (a, b).
The invention has the beneficial effects that: according to the invention, through the sensor technology, the image processing technology, the Internet of things technology and other technologies, the traditional endowment service mode and the management method are improved, so that enough living care and medical care are provided for the old, and the endowment burden of the young is relieved; the method comprises the steps that a characterization node is selected from sensor nodes adopted by a first information acquisition module, acquired environment parameter data are transmitted to a sink node, and the sink node transmits the received environment parameter data to an intelligent management terminal through a wireless communication module. The invention is used for denoising a received video image, a gray detection factor corresponding to a pixel is defined in the denoising process, when the pixel is a normal pixel, the gray value of the pixel is similar to that of surrounding pixels, the corresponding gray detection factor value is smaller, and when the pixel is a noise pixel or an edge pixelWhen the pixel is in use, the gray value of the pixel is larger than the gray value of the pixels around the pixel, the corresponding gray detection factor value is larger, the gray detection threshold value and the adjustment factor are given, when the gray detection factor of the pixel is larger than the given gray detection threshold value, the pixel can be judged to be a noise pixel, when the gray detection factor of the pixel is smaller than the given gray detection threshold value, the pixel can be judged to be a normal pixel, and when the gray detection factor of the pixel is within a certain range of the gray detection threshold value, the noise characteristic of the pixel has uncertainty, based on the above, the preferred embodiment considers the pixel as a suspicious pixel and processes the gray values of the noise pixel and the suspicious pixel, the weighted average result of the gray values of the local neighborhood pixels of the pixel is used as the de-noised gray value of the pixel, and the noise attribute of the local neighborhood pixels is judged by the gray detection factor of the local neighborhood pixels, when the local neighborhood pixel is judged to be a noise pixel through the gray detection factor, the first statistic coefficient of the local neighborhood pixel is made to be 0, namely the influence of the noise local neighborhood pixel on a filtering result is avoided, when the local neighborhood pixel is judged to be a normal pixel or a suspicious pixel through the gray detection factor, the specific gravity of the local neighborhood pixel in the filtering process is determined through the first weight coefficient and the second weight coefficient, in addition to the factors of the traditional local neighborhood pixel and the gray value difference and the distance difference of the pixel, a space detection factor is additionally introduced, and a pixel selected in the local neighborhood of the pixel and the absolute difference of the gray value of the pixel in a threshold value range forms a set K1When the pixel is an edge pixel or a normal pixel, the pixels in the local neighborhood of the pixel, of which the absolute difference value with the gray value of the pixel is within the threshold range, are around the pixel, namely the value of the spatial detection factor is smaller, and when the pixel is a noise pixel, the pixels in the local neighborhood of the pixel, of which the absolute difference value with the gray value of the pixel is within the threshold range, are scattered more randomly, namely the value of the spatial detection factor is larger; when the pixel and its local neighborhood pixels are normal pixels or edge pixels, the pixel and its local neighborhood pixelsThe values of the spatial detection factors of the pixels are all smaller, at this time, the value of the adjustment factor of the first weight coefficient is larger, namely the specific gravity of the local neighborhood pixels in the filtering process is determined mainly by measuring the similarity of the gray values between the local neighborhood pixels and the pixels, thereby playing a role of protecting the edge pixels, when the spatial detection factor of the pixels and the local neighborhood pixels has a larger value, namely the noise pixels exist in the pixels and the local neighborhood pixels, the first weight coefficient measuring the similarity of the gray values between the pixels and the local neighborhood pixels is not adapted any more, therefore, the specific gravity of the first weight coefficient is reduced and the specific gravity of the second weight coefficient is increased to avoid the influence of the noise pixels on the filtering result, namely the specific gravity of the local neighborhood pixels in the filtering process is determined by measuring the distance between the pixels and the local neighborhood pixels, the value of the second weight coefficient is influenced by the spatial detection factor of the pixel and the local neighborhood pixel and the value of the second statistical coefficient in addition to the distance between the local neighborhood pixel and the pixel, when the local neighborhood pixel is a normal pixel and the pixel is a noise pixel, the value of the second weight coefficient is controlled by the second statistical coefficient to be determined by the magnitude of the distance value from the local neighborhood pixel to the pixel, when the value of the spatial detection factor of the local neighborhood pixel is larger, the value of the second weight coefficient is reduced, that is, the influence of the noise local neighborhood pixel on the filtering result is reduced, when the value of the spatial detection factor of the local neighborhood pixel is smaller and the value of the spatial detection factor of the pixel is larger, that is, the local neighborhood pixel may be an edge pixel and the pixel is a noise pixel, and then the uncertainty between the local neighborhood pixel and the pixel is larger, therefore, the value of the second weight coefficient is reduced, namely the uncertainty of the filtering result is reduced; in summary, the preferred embodiment implements effective detection of normal data and noise data in an image through the defined gray detection factor, and implements effective protection of edge pixels and reduction of local neighborhood pixels and suspicious pixels of noise through the defined spatial detection factor when processing the detected noise pixels and suspicious pixelsInfluence of edge local neighborhood pixels on the denoising result.
Detailed Description
The invention is further described with reference to the following examples.
Referring to fig. 1, the intelligent medical care management system based on a block chain and image processing of this embodiment includes a first information acquisition module, a second information acquisition module, a video monitoring module, an intelligent home control module, a wireless communication module, an intelligent management terminal and a block chain storage module, the first information acquisition module is used for acquiring indoor environment parameter data, the second information acquisition module is used for acquiring human physiological parameter data of the elderly, the video monitoring module is used for acquiring video images of the elderly, the first information acquisition module, the second information acquisition module and the video monitoring module transmit the acquired data and video images to the intelligent management terminal through the wireless communication module, the intelligent management terminal includes an indoor environment management unit, a human health management unit, an image processing unit and an information display unit, the indoor environment management unit is used for analyzing the received environment parameter data, when the environment parameter data is not in the given comfort environment parameter data range, the indoor environment management unit sends a control instruction to the intelligent home control module through the wireless communication module, the intelligent home control module controls the indoor electric equipment to regulate the indoor environment according to the received control instruction, the human health management unit is used for analyzing the received human physiological parameter data, when the human body physiological parameter data is not in the given safe human body physiological parameter data range, the image processing unit is used for carrying out pre-warning, carrying out de-noising processing on the received video image, and displaying the denoised video image on an information display unit, wherein the block chain storage module is used for storing the data received by the intelligent management terminal and the processed video image.
According to the preferred embodiment, the traditional endowment service mode and the traditional endowment management method are improved through the sensor technology, the image processing technology, the Internet of things and the like, so that enough living care and medical care are provided for the old, and the burden of endowment for the young is relieved.
Preferably, the first information acquisition module acquires indoor environment parameter data by adopting sensor nodes, selects the characterization nodes from the sensor nodes to transmit the acquired environment parameter data to the sink node, and the sink node transmits the received environment parameter data to the intelligent management terminal through the wireless communication module.
Preferably, the initial energy values of the sensor nodes acquired by the first information acquisition module are all the same.
Preferably, the image processing unit is configured to perform denoising processing on the received video image, where I represents the image denoised by the image processing unit, I (x, y) represents a pixel at a coordinate (x, y) in the image I, and perform denoising processing on the pixel I (x, y), and define ρs(x, y) represents the gray-scale detection factor corresponding to the pixel I (x, y), then ρrThe expression of (x, y) is:
where Ω (x, y) represents a local neighborhood of the pixel I (x, y), and Ω (x, y) is a local neighborhood of (2R +1) × (2R +1) centered on the pixel I (x, y), where R is a positive integer, and let c (I) and k (I) represent the length and width of the image I, respectively, then R < min { c (I), k (I) }, h (x, y) represent the grayscale value of the number of pixels I (x, y), I (a, b) represent the pixel at coordinates (a, b) in the image I, and I (a, b) ∈ Ω (x, y), h (a, b) represent the grayscale value of the pixel I (a, b), and M (x, y) represents Ω (x, y) in the local neighborhood;
given a gray detection threshold T (ρ)
r) And regulatory factor
And is
Wherein,
representing the mean, Δ, of the absolute differences between the grey values of the pixels in the local neighborhood Ω (x, y)
mid(x, y) represents the median of the absolute differences between the grey values of the pixels in the local neighborhood Ω (x, y),
when rho
r(x,y)<T(ρ
r) If yes, judging the pixel I (x, y) as a normal pixel; when in use
If so, judging the pixel I (x, y) as noise data; when in use
If yes, judging the pixel I (x, y) as a suspicious pixel;
let H (x, y) denote the gray scale value of the pixel I (x, y) processed by the image processing unit, and when the pixel I (x, y) is determined as a normal pixel, H (x, y) is equal to H (x, y), and when the pixel I (x, y) is determined as a noise pixel or a suspicious pixel, the value of H (x, y) is:
in the formula, #
1(a, b) represents a gradation detection factor ρ
rA first statistical coefficient of (a, b), and
where ρ is
r(a, b) represents a gray-scale detection factor, ω, corresponding to the pixel I (a, b)
1(a, b) represents a first weight coefficient of the pixel I (a, b) to the pixel I (x, y), and
σ
rrepresenting a gray level smoothing factor, σ
rMay take a value of 0.2, η
r(a, b) represents a first weight coefficient ω
1(a, b) a regulatory factor, and
ω
2(a, b) represents a second weight coefficient of the pixel I (a, b) to the pixel I (x, y), and
wherein eta is
s(a, b) represents a second weight coefficient ω
2(a, b) a regulatory factor, and
ψ
2(a, b) represents a gradation detection factor ρ
r(a, b) second statistical coefficient, and
σ
srepresenting a spatial smoothing factor, σ
sMay take the value of 4, p
s(x, y) represents a spatial detection factor, ρ, of the pixel I (x, y)
s(max) is the maximum value of the spatial detection factor, ρ, of the pixels in the image I
s(a, b) represents a spatial detection factor of the pixel I (a, b), and ρ
sThe values of (a, b) are determined in the following manner:
let Ω (a, b) denote the local neighborhood of the pixel I (a, b), and Ω (a, b) be the local neighborhood of (2R +1) × (2R +1) centered on the pixel I (a, b), I (p, q) denote the pixel at coordinates (p, q) in the image I, and I (p, q) ∈ Ω (a, b), h (p, q) denote the grayscale value of the pixel I (p, q), given a difference threshold T (Δ), and
wherein,
representing the median function, mean
I(p,q)∈Ω(a,b)L h (p, q) -h (a, b) | represents a mean function; when the pixel I (p, q) satisfies | h (a, b) -h (p, q) | is less than or equal to T (delta), the pixel I (p, q) is marked as 1, when the pixel I (p, q) satisfies | h (a, b) -h (p, q) > T (delta), the pixel I (p, q) is marked as 0, and the pixel marked as 1 in the local neighborhood omega (a, b) forms a set K
1(a, b), then ρ
sThe values of (a, b) are:
wherein, I (c)1,d1) Represents the coordinates (c) in the image I1,d1) A pixel of (b), and I (c)1,d1)∈K1(a, b), I (p ', q') denotes the pixel at the coordinates (p ', q') in the image I, and I (p ', q') is E.OMEGA (a, b), M1(a, b) represents a set K1The number of pixels in (a, b); spatial detection factor ρ of a pixel I (x, y)s(x, y) is also calculated in the above manner.
The preferred embodiment is used for denoising a received video image, and in the denoising process, a gray detection factor corresponding to a pixel is defined, when the pixel is a normal pixel, the gray value of the pixel is similar to that of surrounding pixels, the corresponding gray detection factor value is smaller, when the pixel is a noise pixel or an edge pixel, the gray value difference between the pixel and the surrounding pixels is larger, the corresponding gray detection factor value is larger, a gray detection threshold value and an adjustment factor are given, when the gray detection factor of the pixel is more than the given gray detection threshold value, the pixel can be determined to be the noise pixel, and when the gray detection factor of the pixel is less than the given gray detection threshold value, the pixel can be determined to be the noise pixelThe pixel is a normal pixel, and when the gray detection factor of the pixel is within a certain range of the gray detection threshold, the noise characteristic has uncertainty, based on which, the preferred embodiment identifies the pixel as a suspicious pixel, processes the gray values of the noise pixel and the suspicious pixel, adopts the weighted average result of the gray values of the local neighborhood pixels of the pixel as the gray value of the pixel after denoising, judges the noise attribute of the local neighborhood pixels by the gray detection factor of the local neighborhood pixels, when the local neighborhood pixels are judged to be the noise pixels by the gray detection factor, makes the first statistical coefficient of the local neighborhood pixels to be 0, namely avoids the influence of the local neighborhood pixels of the noise on the filtering result, when the local neighborhood pixels are judged to be the normal pixel or the suspicious pixel by the gray detection factor, the specific gravity of the local neighborhood pixels in the filtering process is determined through a first weight coefficient and a second weight coefficient, factors of the traditional local neighborhood pixels and gray value difference and distance difference of the pixels are not introduced into the first weight coefficient and the second weight coefficient, a space detection factor is additionally introduced, and a set K is formed by selecting pixels in the local neighborhood of the pixels, wherein the absolute difference of the gray value of the pixels and the gray value of the pixels is within a threshold range1When the pixel is an edge pixel or a normal pixel, the pixels in the local neighborhood of the pixel, of which the absolute difference value with the gray value of the pixel is within the threshold range, are around the pixel, namely the value of the spatial detection factor is smaller, and when the pixel is a noise pixel, the pixels in the local neighborhood of the pixel, of which the absolute difference value with the gray value of the pixel is within the threshold range, are scattered more randomly, namely the value of the spatial detection factor is larger; when the pixel and the local neighborhood pixel are normal pixels or edge pixels, the values of the spatial detection factors of the pixel and the local neighborhood pixel are smaller, at the moment, the value of the adjustment factor of the first weight coefficient is larger, namely, the specific gravity of the local neighborhood pixel in the filtering process is determined mainly by measuring the similarity of the gray values between the local neighborhood pixel and the pixel, so that the edge pixel is protected, and when the spatial detection factors of the pixel and the local neighborhood pixel exist, the spatial detection factors of the pixel and the local neighborhood pixel are smallerWhen the spatial detection factor value is larger, namely a noise pixel exists in the pixel and the local neighborhood pixel, the first weight coefficient for measuring the similarity of the gray values between the pixel and the local neighborhood pixel is not adapted any more, therefore, in order to avoid the influence of the noise pixel on the filtering result, the proportion of the first weight coefficient is reduced, and the proportion of the second weight coefficient is increased, namely, the proportion of the local neighborhood pixel in the filtering process is determined by measuring the distance between the pixel and the local neighborhood pixel, the value of the second weight coefficient is influenced by the spatial detection factor of the pixel and the local neighborhood pixel and the value of the second statistical coefficient besides the distance between the local neighborhood pixel and the pixel, when the local neighborhood pixel is a normal pixel and the pixel is a noise pixel, the value of the second weight coefficient is controlled by the second statistical coefficient and is determined by the distance value between the local neighborhood pixel and the pixel, when the value of the spatial detection factor of the local neighborhood pixel is larger, reducing the value of a second weight coefficient, namely reducing the influence of the noise local neighborhood pixel on the filtering result, and when the value of the spatial detection factor of the local neighborhood pixel is smaller and the value of the spatial detection factor of the pixel is larger, namely the local neighborhood pixel may be an edge pixel and the pixel is a noise pixel, at the moment, the uncertainty between the local neighborhood pixel and the pixel is larger, so the value of the second weight coefficient is reduced, namely the uncertainty of the filtering result is reduced; in summary, the preferred embodiment implements effective detection of normal data and noise data in an image through the defined gray detection factor, and implements effective protection of edge pixels and reduces the influence of noise local neighborhood pixels and edge local neighborhood pixels on a denoising result through the defined spatial detection factor when processing detected noise pixels and suspicious pixels.
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.