CN114882042B - Internet of things transmission method based on image quality evaluation - Google Patents
Internet of things transmission method based on image quality evaluation Download PDFInfo
- Publication number
- CN114882042B CN114882042B CN202210811735.7A CN202210811735A CN114882042B CN 114882042 B CN114882042 B CN 114882042B CN 202210811735 A CN202210811735 A CN 202210811735A CN 114882042 B CN114882042 B CN 114882042B
- Authority
- CN
- China
- Prior art keywords
- gray level
- gray
- image
- histogram
- frequency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000013441 quality evaluation Methods 0.000 title claims abstract description 20
- 238000009826 distribution Methods 0.000 claims abstract description 77
- 238000004364 calculation method Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000011156 evaluation Methods 0.000 claims abstract description 5
- 238000009499 grossing Methods 0.000 claims description 7
- 238000005520 cutting process Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000001303 quality assessment method Methods 0.000 claims 8
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/97—Determining parameters from multiple pictures
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the field of image transmission, in particular to an internet of things transmission method based on image quality evaluation. Carrying out gray processing on an acquired image to obtain a gray image, and obtaining a gray histogram by using the gray image; dividing the gray level histogram into different region intervals according to the gray level, acquiring the frequency number of each gray level and the frequency of each region interval in the gray level histogram, and calculating the contrast and the distribution degree of the acquired image according to the frequency number of each gray level and the frequency of each region interval; evaluating the image quality by using the acquired image contrast and distribution; and selecting a proper image frame number according to the evaluation result to transmit the image. The invention evaluates the image quality according to the characteristics of the image gray level image, selectively transmits the image, solves the problem of overlarge image transmission quantity, has fewer and simple factors related to the gray level image, can reduce the complexity of calculation, and solves the problem that a complex calculation method cannot be carried out due to limited calculation capability of a camera acquisition end.
Description
Technical Field
The invention relates to the field of image transmission, in particular to an internet of things transmission method based on image quality evaluation.
Background
In industrial production, images on a production line are often required to be acquired, a real-time image transmission technology is required, products in the production process can be monitored in real time through the real-time image transmission technology, problems occurring in the production process can be found in time, and therefore real-time monitoring on the product line is very necessary.
The image real-time transmission technology is to connect a computer and an industrial camera and transmit images in a multi-end acquisition camera to the computer by using a broadband, but in the transmission process, the limitation of the broadband causes that the data volume of the images acquired by a plurality of camera acquisition ends at the same time is too large, the problems that the normal operation cannot be performed or the operation time is too long may occur in the transmission process, and at this time, a plurality of images acquired by the camera are selectively transmitted according to the data volume which can be transmitted by the bandwidth.
However, when some existing technologies transmit images and cannot transmit all the images at the same time under the influence of broadband, the existing technologies transmit the images by compressing the images or cutting the images into blocks and restoring the images after transmission; some adopted calculation methods are too complex, the calculation capacity of the camera acquisition end is limited, the problem that the transmission working efficiency is low due to the fact that the calculation capacity of the camera acquisition end is not enough to support an excessively complex algorithm is solved, and therefore a simple algorithm is needed to support the camera acquisition end to evaluate the image quality, and the transmission efficiency is improved.
Disclosure of Invention
The invention provides an Internet of things transmission method based on image quality evaluation, which aims to solve the problems that the image transmission process cannot normally run or the running time is too long due to the fact that the existing broadband transmission is limited and the image data volume acquired by a plurality of cameras at the same time exceeds the transmission data volume which can be supported by the broadband, and the image transmission efficiency is improved.
Furthermore, because the computing power of the camera acquisition end is limited, and too complex computation needs a large amount of time to be carried out, the method utilizes the characteristics of the gray-scale map to analyze the image quality, has fewer related parameters, is simple and convenient to use, can effectively reduce the complexity of the algorithm of the camera acquisition end, and reduces the computation time of the camera acquisition end.
The internet of things transmission method based on image quality evaluation adopts the following technical scheme, and comprises the following steps:
carrying out graying processing on images acquired by a plurality of sections of cameras at the same time to obtain gray level images, and calculating by utilizing the gray level images to obtain gray level histograms of all the acquired images;
dividing each gray level histogram into different areas according to the gray level;
calculating the contrast of each acquired image according to the range of the gray level in each gray level histogram;
calculating the cutting rate of each gray histogram according to the frequency of the gray level of each gray histogram and the prediction frequency;
after smoothing processing is carried out on each gray level histogram, interval division is carried out according to the trough of the smoothed gray level histogram, and the approximate normal distribution rate of each gray level histogram is calculated according to the skewness and the kurtosis of each interval;
calculating the brightness difference rate of each gray level histogram by using the frequency of the gray level of pure white and pure black in each gray level histogram and the frequency of the white area and the black area;
acquiring the distribution degree of the acquired image corresponding to each gray level histogram by using the cutoff rate, the approximate normal distribution rate and the brightness difference rate of each gray level histogram;
evaluating the quality of all the acquired images by using the obtained contrast and distribution of each acquired image;
and carrying out priority sequencing on the collected images by utilizing the image quality evaluation information, and transmitting the collected images according to the priority sequence, wherein the number of the transmitted images is the data amount which can be transmitted by the bandwidth.
The evaluation parameters of the image quality are the contrast and the distribution degree of each acquired image, and the image quality evaluation value is the sum of the contrast and the distribution degree of each acquired image.
The calculation formula for acquiring the image contrast is as follows:
in the formula:in order to acquire the contrast of the image,is the maximum value of the grey levels in the grey histogram,is the minimum value of the gray levels in the gray histogram.
The distribution degree of the collected images is comprehensively calculated according to the cutoff rate, the approximate normal distribution rate and the brightness difference rate of the gray level histogram;
the calculation formula is as follows:
in the formula:in order to acquire the degree of distribution of the image,is the cut-off rate of the gray-scale histogram,is an approximately normal distribution ratio of the gray histogram,is the light-dark difference rate of the grey level histogram.
The method for calculating the cutoff rate of the gray histogram is as follows:
in the formula:a cut-off rate that is a gray histogram;is a natural constant and is the base number of a natural logarithm;is the frequency count with a gray level of 0,the prediction frequency is 0 gray level;for a frequency count with a gray level of 255,the prediction frequency is 255 gray level;
wherein:
in the formula:is the frequency count with a gray level of 1,is the frequency count for a gray scale level of 254,in order to be a gray scale level,is a gray scaleThe frequency of (c).
The method for calculating the approximate normal distribution rate of the gray level histogram is as follows:
the method comprises the steps of smoothing the gray level histogram to obtain a smoothed gray level histogram by calculating the average frequency of each gray level and the gray levels on the left side and the right side of the gray level histogram, obtaining the gray levels corresponding to wave troughs of the smoothed gray level histogram, arranging the gray levels corresponding to the wave troughs in sequence, and dividing wave trough gray level intervals to obtain an interval set;
and (3) calculating the skewness and kurtosis of the gray level histogram for each divided interval:
the skewness calculation formula is as follows:
in the formula:is the skewness of the gray-scale histogram,the gray levels corresponding to the valleys of the image,in order to be a gray scale level,is a gray scaleThe frequency of (a) to (b) is,as valley gray level intervalThe average of the frequency counts of the gray levels in (a),as valley gray level intervalStandard deviation of frequency of each gray level;
the kurtosis is calculated as follows:
and calculating the approximate normal distribution rate of the image according to the skewness and kurtosis of the calculated gray level histogram, wherein the calculation formula is as follows:
in the formula:is an approximately normal distribution ratio of the image,is the base of the set of intervals,is the base of the natural logarithm and is a natural constant.
The calculation formula of the brightness difference rate of the gray level histogram is as follows:
in the formula:is the light-to-dark difference ratio of the gray histogram,is the frequency of a gray level of 0 i.e. a pure black pixel,at a grey level of 255 i.e. the frequency of a pure white pixel,is a white areaThe frequency of the interval of the region is,a region interval frequency that is a black region;
the frequency calculation formula of the gray scale is as follows:
in the formula:in the form of a gray scale level,is a gray scaleThe frequency of (a) of (b) is,is a gray scaleThe frequency of (a) to (b) is,in order to be the resolution of the grayscale image,is the number of gray levels.
The region interval frequency calculation formula is as follows:
The method for acquiring the bandwidth transmission data volume comprises the following steps:
in the formula:the number of frames for the image transmission,in order to be able to determine the resolution of the image,for the size of each of the pixels of the image,in order to be a wide band,indicating rounding down the resulting frame number.
The invention has the beneficial effects that: the invention utilizes image processing to carry out gray processing on the image collected by the camera, utilizes the gray value histogram of the gray image to analyze the image, evaluates the image quality of the collected image according to the characteristics of the gray image, selectively transmits the image according to the image quality, and can effectively reduce the influence that the image transmission process cannot normally run due to too large image data volume; parameters related to the characteristics of the gray level map are few, and the quality of the image is evaluated by using the characteristics of the gray level map, so that the complexity of calculation can be reduced, and the calculation time of a camera acquisition end can be reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic diagram of the process of the present invention;
fig. 2 is a flowchart of an internet of things transmission method based on image quality evaluation according to the embodiment;
fig. 3 is a flowchart of an internet of things transmission method based on image quality evaluation according to the embodiment;
FIG. 4 is a schematic diagram of a gray level histogram in the present embodiment;
FIG. 5 is a gray level histogram of the divided regions in the present embodiment;
FIG. 6 is a diagram of an under-exposed or over-exposed image and its histogram of gray levels in the present embodiment;
fig. 7 shows an image with an excessive difference between brightness and darkness and a histogram of gray levels thereof in this embodiment.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
An embodiment of the internet of things transmission method based on image quality evaluation according to the present invention is shown in fig. 1 and fig. 2, and is explained below:
and S101, carrying out gray processing on the acquired collected image to obtain a gray image of the collected image.
The gray scale map is also called a gray scale map. The relationship between white and black is logarithmically divided into several levels, called gray scale. The gray scale is divided into 256 steps. An image represented in grayscale is referred to as a grayscale map.
And S102, acquiring a gray level image of the acquired image, and drawing a gray level histogram of the image according to the gray level image of the acquired image.
The gray histogram is to count the occurrence frequency of all pixels in the digital image according to the size of the gray value.
And S103, dividing the gray level histogram into different region intervals according to the gray level, and calculating the frequency of each gray level and the frequency of each region interval in the gray level histogram.
Different region intervals represent different tones, and seven regions are divided according to a gray level space; and calculating the frequency of each gray level and each area interval according to the frequency of each gray level.
And S104, calculating the contrast of the acquired image by using the range of the gray level.
The contrast refers to the measurement of different brightness levels between the brightest white and the darkest black of a bright and dark area in an image, the contrast of an acquired image is one of the measurement standards of the image quality, and the image quality can be objectively judged by evaluating the quality of the image according to the contrast of the acquired image.
And S105, comprehensively calculating the distribution degree of the acquired image by utilizing the cutoff rate, the approximate normal distribution rate and the brightness difference rate of the gray level histogram.
The distribution degree is one of the characteristics of the gray level histogram, can be used for measuring the quality of the image, and can be comprehensively calculated by calculating the cutoff rate, the approximate normal distribution rate and the brightness difference rate of the gray level histogram, so that the distribution degree of the collected image is calculated in a large range, and the image quality can be effectively judged.
S106, calculating the cutoff rate, the approximate normal distribution rate and the brightness difference rate of the gray level histograms according to the characteristic quantity of each gray level histogram.
When the image has the darkest area or the brightest area, namely the image has an underexposure or overexposure phenomenon, the image is shown to be cut off at the leftmost side or the rightmost side on the gray level histogram of the image, namely the curve is sharply increased, the data of the gray level histogram are analyzed, and the cut-off rate of the gray level histogram is obtained;
when the image is under-exposed or over-exposed, the image shows that a large number of dark areas or bright areas exist, the gray level difference of the gray histogram is analyzed, and the brightness difference rate of the gray histogram is obtained;
the gray level histogram of an ideal image is normally distributed, but in practice, the curve of the gray level histogram is not completely normally distributed, a plurality of peaks and troughs exist, the gray level histogram is divided into a plurality of intervals by the aid of the peaks and the troughs, the conditions of the intervals are analyzed, and the approximate normal distribution rate of the intervals is obtained;
and comprehensively calculating the distribution degree of the acquired image according to the cutoff rate, the brightness difference rate and the approximate normal distribution rate of the obtained gray level histogram to evaluate the image quality.
And S107, selectively transmitting the image according to the priority of the image quality.
The contrast and the distribution of the collected images are utilized to comprehensively evaluate the image quality, the collected images are subjected to priority sequencing according to the image quality evaluation value, and the images are selectively transmitted according to the transmittable data volume of the bandwidth.
The beneficial effect of this embodiment lies in:
the characteristics of the image gray level image are integrated, the gray level histogram is analyzed to obtain the contrast and the distribution degree of the collected image, the image quality is evaluated by utilizing the contrast and the distribution degree of the collected image, and the image quality is judged, so that the collected image is selectively transmitted, the adverse effect of image transmission with poor quality on the image transmission is reduced, and the transmission efficiency is improved.
Example 2
The embodiment of the invention provides an internet of things transmission method based on image quality evaluation, as shown in fig. 1 and 3, comprising the following steps:
s201, carrying out graying processing on the acquired collected image to obtain a grayscale image of the collected image.
And carrying out graying processing on each image acquired by the camera acquisition end at the same time to obtain a grayscale image. The image expressed by gray scale is called gray scale image, and the gray scale image divides white and black into a plurality of grades according to logarithmic relation, which is called gray scale; the gray scale is divided into 256 steps.
S202, acquiring a gray level image of the acquired image, and drawing a gray level histogram of the image according to the gray level image of the acquired image.
The image is represented by luminance, which is divided into 256 values from 0 to 255, and the higher the value is, the higher the luminance is represented. Where 0 represents the darkest area in solid black, 255 represents the brightest area in solid white, and the middle number is the gray of different brightness.
The horizontal axis represents luminance values of 0 to 255 and the vertical axis represents the number of pixels corresponding to luminance in the image, and this functional image is called a histogram, as shown in fig. 4. The height of the column in the histogram represents the number of pixels of the brightness in the image, and the distribution and proportion of the brightness in the image can be obtained.
Establishing a coordinate axis, wherein the horizontal axis represents the gray level of an imageExpressed by integers from 0 to 255, the vertical axis representing the corresponding grey levelFrequency ofAnd drawing a function image to obtain a corresponding gray level histogram.
Thus, the gray level histograms of all the images acquired by the camera acquisition end at the same moment are obtained.
And S203, dividing the gray level histogram into different region intervals according to the gray level, and calculating the frequency of each gray level and the frequency of each region interval in the gray level histogram.
1. Dividing each gray level histogram into different region intervals:
dividing the gray histogram into different colors, and dividing the gray level space by the divided regionsSequentially comprises the following steps: pure black colorBlack region of the colorShadow intervalIntermediate interval of toneHigh light intervalAnd white intervalPure white intervalAs shown in fig. 5; the corresponding images are seven areas including a pure black area, a shadow area, a normal brightness area, a highlight area, a white area and a pure white area.
2. Calculating the frequency of each gray level in the gray level histogram:
acquiring the frequency number of each gray level in the gray level histogram, and calculating the frequency of each gray level according to the frequency number of each gray level, wherein the frequency of each gray level is as follows:
in the formula:in order to be a gray scale level,is a gray scaleThe frequency of (a) of (b) is,is a gray scaleThe frequency of (a) to (b) is,the resolution of the grayscale image.
3. And calculating the frequency corresponding to each region interval by using the frequency of each gray level:
the gray scale interval corresponding to each region interval isThen, the frequency of each region interval is:
in the formula:is the frequency of the region interval of the region,is a gray scaleThe frequency of (a) of (b) is,the range of the region.
Thus, the frequency of each gray level and the frequency of each region interval in all the gray level histograms are obtained.
The gray level histogram of a normally exposed image is mainly piled up in the middle part and slowly transits to two sides (the gray level histogram is in normal distribution), and the leftmost side and the rightmost side are not cut off, namely the leftmost side and the rightmost side are not piled up in a large amount; a severely underexposed image with the leftmost side of the gray histogram cut off, i.e., a large number of pixels stacked on the leftmost side, as shown in the left image of fig. 6; for a heavily overexposed image, the rightmost side of the histogram is cut off, i.e., a large number of pixels are piled up on the rightmost side, as shown in the right diagram of fig. 6.
The quality of the image is poor whether the image is over-exposed and under-exposed simultaneously due to incorrect setting of the exposure parameters or due to the ambient light ratio being greater than the camera's tolerance. And two indexes of image contrast and distribution degree are constructed and collected through the distribution characteristics of the gray level histogram to measure the image quality.
And S204, calculating the contrast of each acquired image by using the range of the gray level.
The scale of the brightness difference between the bright area and the dark area in the image indicates the hierarchy of the image, and the wider the brightness distribution, the more hierarchical the image is; expressed on the gray level histogram, a wider histogram reflects wider brightness distribution of the image, whereas a narrower histogram reflects narrow brightness distribution of the image, as shown in the histogram in fig. 6; the image brightness distribution width is noted as contrast.
The contrast of the acquired image is represented by calculating the range of the gray level on the gray level histogram, namely the difference between the maximum value of the gray level and the minimum value of the gray level, so as to measure the image quality.
The acquired image contrast is then:
in the formula:in order to acquire the contrast of an image,is the maximum value of the grey levels in the grey histogram,is the minimum value of the gray levels in the gray histogram.
Thus, the contrast of each acquired image is obtained, and whether the image has an underexposure phenomenon or an overexposure phenomenon is judged according to the obtained contrast.
The contrast of the acquired image is calculated by utilizing the range of the gray level of the image, the calculation method is simple, the calculation amount is small, and the camera acquisition end can more effectively obtain a contrast result so as to evaluate the image quality.
And S205, calculating the cutting rate of the gray level histogram according to the frequency of the gray level and the prediction frequency.
When the image has the darkest area or the brightest area, namely, the image has an underexposure or overexposure phenomenon, the image is shown to have cutting-off on the leftmost side or the rightmost side on the gray level histogram of the image, namely, the curve is increased sharply, the data of the gray level histogram is analyzed, and the cutting-off rate of the gray level histogram is obtained.
Gray level histogram upswingLine explosion, using pure white areas (grey levels)) And a pure black area (gray scale)) Frequency ofAnd prediction frequencyIs expressed by the ratio of (A) to (B).
1. And calculating the prediction frequency of the gray levels of the darkest area and the brightest area.
The prediction frequency is obtained by the distribution characteristics of the gray level frequency of the white area and the black area, and the specific calculation process is as follows:
in the formula:for the frequency count with a gray level of 1,is the frequency count for a gray scale level of 254,in order to be a gray scale level,is a gray scaleThe frequency of (a) to (b) is,the prediction frequency number for a gray level of 0,the prediction frequency is 255 gray levels.
2. And calculating the cutting rate of the gray level histogram according to the frequency of the gray level and the obtained prediction frequency.
The cut-off ratio is calculated as follows:
in the formula:a cut-off rate that is a gray histogram;is a natural constant and is the base number of a natural logarithm;is the frequency count with a gray level of 0,the prediction frequency is 0 gray level;for a frequency count with a gray level of 255,the prediction frequency is 255 gray levels.
Therefore, the cutoff rate of the gray level histogram is obtained, and whether the image is under-exposed or over-exposed can be more accurately determined according to the cutoff rate of the gray level histogram.
And S206, after the gray level histogram is subjected to smoothing processing, interval division is carried out according to the trough of the smoothed gray level histogram, and the approximate normal distribution rate of the gray level histogram is calculated according to the skewness and the kurtosis of each interval.
The gray level histogram of the ideal image is normally distributed, but in practice, a plurality of peaks and troughs exist in the curve of the gray level histogram, the gray level is divided into a plurality of intervals through the peaks and the troughs, and whether each interval is approximately normal or not is judged, so that the approximate normal distribution rate of the histogram is obtained.
1. And dividing the gray level into a plurality of intervals according to the positions of the valleys of the gray level histogram.
Smoothing the grey level histogram
And calculating the average frequency of each gray level, namely the average value of the frequency of the gray level and the gray levels on the left and right sides of the gray level, and smoothing the gray level histogram by using the method. The calculation formula is as follows:
Secondly, interval division is carried out on the gray level histogram according to the gray level corresponding to the position of the wave trough
For the smoothed gray level histogram, acquiring the gray level corresponding to each wave troughThe valley gray levels are aligned according to the order of the gray levels corresponding to the valleysSequencing to obtain a sequence。
Dividing a gray level histogram into a plurality of gray level histograms according to a sequenceEach interval and each interval set is。
At this point, the interval division of the gray level histogram is completed, and further each interval is analyzed.
2. And calculating skewness and kurtosis of each interval in the set.
Calculating the skewness of each interval
Skewness of histogram () To measure the asymmetry of the distribution. The value range is (- ∞, + ∞) when skewness is higher thanWhen the average value is larger than the preset value, the data are distributed on two sides of the average value relatively uniformly; degree of deflectionWhen the probability distribution diagram is biased to the left; degree of deflectionThe probability distribution map is right biased.
For skewness of the set interval, the calculation formula is as follows:
in the formula:is the skewness of the gray-level histogram,the gray levels corresponding to the valleys of the image,in order to be a gray scale level,is a gray scaleThe frequency of (a) to (b) is,as valley gray level intervalThe average of the frequency counts of the gray levels in (a),as valley gray level intervalThe standard deviation of the frequency of each gray level.
Calculating kurtosis of each interval in the set
Kurtosis of histogram () To measure how steep the distribution is. Kurtosis of data with a value range of [1, + ∞) that is completely fit to a normal distributionThe larger the kurtosis value is, the higher the profile is, and the smaller the kurtosis value is, the shorter the profile is.
For the kurtosis of the aggregation interval, the calculation formula is as follows:
in the formula:is the kurtosis of the grey level histogram,the gray levels corresponding to the valleys of the image,in order to be a gray scale level,is a gray scaleThe frequency of (a) to (b) is,as valley gray level intervalThe average value of the frequency counts of the respective gray levels,is a trough gray scale intervalThe standard deviation of the frequency of each gray level.
3. Calculating the approximate normal distribution rate of the gray level histogram by using the skewness and kurtosis of each interval in the set
And judging whether the image is approximately normally distributed or not on the whole according to the situation of the approximately normally distributed state of each section.
The approximate normal distribution ratio calculation formula of the gray level histogram is as follows:
in the formula:is an approximately normal distribution ratio of the image,is the base of the set of intervals,is the base of the natural logarithm and is a natural constant.
Thus, the approximate normal distribution ratio of each gray level histogram is obtained, and the distribution situation of the gray level of the histogram can be further determined.
And S207, calculating the brightness difference rate of the gray level histogram according to the frequency of the gray level and the frequency of the white and black area intervals.
When a large dark area exists and overexposure exists or a large number of bright areas exist and overexposure and underexposure occur simultaneously on an image, the gray histogram shows that the white or black area is large and left or right cut occurs, as shown in fig. 7.
Determining the image exposure condition through the brightness difference of the image, and further judging the image quality, wherein the brightness difference rate is calculated according to the following formula:
in the formula:is the light-to-dark difference ratio of the gray histogram,is the frequency at which the gray level is 0,is a frequency with a gray scale level of 255,is a regionThe frequency of the interval of the region(s),is a regionThe zone interval frequency of (1).
Thus, the brightness difference rate of all the gray level histograms is obtained.
And S208, comprehensively calculating the distribution degree of each acquired image by utilizing the cutoff rate, the approximate normal distribution rate and the brightness difference rate of the gray level histogram.
The cutoff rate, the approximate normal distribution rate and the brightness difference rate of the gray level histogram represent the gray level distribution condition and the image exposure condition of the image, and the quality of the image can be evaluated better through integration.
Comprehensively calculating the cutoff rate, the approximate normal distribution rate and the brightness difference rate of the gray level histogram to obtain the distribution degree of the acquired image, wherein the calculation formula of the distribution degree is as follows:
in the formula:in order to acquire the degree of distribution of the image,is the cut-off rate of the gray-scale histogram,is an approximately normal distribution ratio of the gray histogram,is the light-dark difference rate of the grey level histogram.
Therefore, the distribution degree of each acquired image is obtained, the gray level distribution condition of the image can be reflected, and the quality of the image is evaluated according to the gray level distribution condition.
S209, carrying out image quality evaluation by using the obtained contrast and distribution of the acquired images, and selectively transmitting the images acquired by the camera acquisition end at the same time according to the image quality information.
1. And carrying out image quality evaluation by using the obtained contrast and distribution degree of the acquired image.
And comprehensively evaluating the image quality according to the contrast and the distribution degree of each acquired image, wherein the comprehensive evaluation of the two factors can enable the evaluation result to be more objective and more accurate.
The calculation formula of the image quality is as follows:
in the formula:as an image quality evaluation value, for example,in order to acquire the contrast of the image,the distribution degree of the collected image is obtained.
2. The image is selectively transmitted based on the image quality information.
Determining transmission priority of transmitted image
And arranging the image quality evaluation values of all the images acquired at the same moment from large to small according to the image quality information, and carrying out priority ordering on all the images acquired at the same moment according to the image quality.
② selectively transmitting the image according to priority
And calculating the frame number of image transmission to determine the transmitted image. The image transmission frame number calculation formula is as follows:
in the formula:the number of frames for the image transmission,in order to be able to determine the resolution of the image,for the size of each of the pixels it is,is a broadband, and is characterized by comprising a plurality of groups of antennas,this indicates that the number of frames obtained is rounded down.
According to the priority sequence of image transmission, all images collected at the same time are preceded byAnd transmitting the frame image to finish the image transmission process.
For example: when the data volume which can be transmitted by the bandwidth is 20, the first twenty images in the priority sequence are transmitted according to the priority sequence of all the images acquired by the camera acquisition end at the same moment.
Therefore, the internet of things transmission method based on image quality evaluation is completed.
In the embodiment, the images are selected according to the priority of image transmission, and the transmittable quantity supported by the broadband is calculated to transmit the images, so that the problem that the images cannot normally run in the broadband transmission process is avoided; the characteristics of the gray level histogram are utilized to evaluate and calculate the image quality, the parameters are few, the calculation method is simple and convenient, and the problem that high-complexity calculation cannot be carried out due to the limited calculation capability of a camera acquisition end is solved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. An Internet of things transmission method based on image quality assessment is characterized in that: the method comprises the following steps:
carrying out graying processing on images acquired by a plurality of sections of cameras at the same time to obtain gray level images, and calculating by utilizing the gray level images to obtain gray level histograms of all the acquired images;
dividing each gray level histogram into different areas according to the gray level;
calculating the contrast of each acquired image according to the range of the gray level in each gray level histogram;
calculating the cutting rate of each gray histogram according to the frequency of the gray level of each gray histogram and the prediction frequency;
after smoothing processing is carried out on each gray level histogram, interval division is carried out according to the trough of the smoothed gray level histogram, and the approximate normal distribution rate of each gray level histogram is calculated according to the skewness and the kurtosis of each interval;
calculating the brightness difference rate of each gray level histogram by using the frequency of the gray level of pure white and pure black in each gray level histogram and the frequency of the white area and the black area;
acquiring the distribution degree of the acquired image corresponding to each gray level histogram by utilizing the cutoff rate, the approximate normal distribution rate and the brightness difference rate of each gray level histogram;
evaluating the quality of all the acquired images by using the obtained contrast and distribution of each acquired image;
and carrying out priority sequencing on the collected images by utilizing the image quality evaluation information, and transmitting the collected images according to the priority sequence, wherein the number of the transmitted images is the data amount which can be transmitted by the bandwidth.
2. The transmission method of the internet of things based on the image quality assessment as claimed in claim 1, wherein: the evaluation parameters of the image quality are the contrast and the distribution degree of each acquired image, and the image quality evaluation value is the sum of the contrast and the distribution degree of each acquired image.
3. The transmission method of the internet of things based on the image quality assessment as claimed in claim 2, wherein: the calculation formula of the acquired image contrast is as follows:
4. The transmission method of the internet of things based on the image quality assessment as claimed in claim 2, wherein: the distribution degree of the collected images is comprehensively calculated according to the cutoff rate, the approximate normal distribution rate and the brightness difference rate of the gray level histogram;
the calculation formula is as follows:
5. The transmission method of the internet of things based on the image quality assessment as claimed in claim 4, wherein: the method for calculating the cutoff rate of the gray histogram is as follows:
in the formula:cut-off rate as a histogram of gray levels;is a natural constant and is the base number of a natural logarithm;is the frequency count with a gray level of 0,the prediction frequency is 0 gray level;for a frequency count with a gray level of 255,the prediction frequency is 255 gray levels;
wherein:
6. The transmission method of the internet of things based on the image quality assessment as claimed in claim 4, wherein: the method for calculating the approximate normal distribution rate of the gray level histogram is as follows:
the method comprises the steps of smoothing the gray level histogram to obtain a smoothed gray level histogram by calculating the average frequency of each gray level and the gray levels on the left side and the right side of the gray level histogram, obtaining the gray levels corresponding to wave troughs of the smoothed gray level histogram, arranging the gray levels corresponding to the wave troughs in sequence, and dividing wave trough gray level intervals to obtain an interval set;
and (3) calculating the skewness and kurtosis of the gray level histogram for each divided interval:
the skewness calculation formula is as follows:
in the formula:is the skewness of the gray-scale histogram,the gray levels corresponding to the valleys of the image,in order to be a gray scale level,is a gray scaleThe frequency of (a) is lower than (b),as valley gray level intervalThe average of the frequency counts of the gray levels in (a),as valley gray level intervalStandard deviation of frequency of each gray level;
the kurtosis is calculated as follows:
and calculating the approximate normal distribution rate of the image according to the skewness and kurtosis of the calculated gray level histogram, wherein the calculation formula is as follows:
7. The transmission method of the internet of things based on the image quality assessment as claimed in claim 4, wherein: the calculation formula of the brightness difference rate of the gray level histogram is as follows:
in the formula:is the light-to-dark difference ratio of the gray histogram,at a gray level of 0 i.e. the frequency of a pure black pixel,at a grey level of 255 i.e. the frequency of a pure white pixel,is a white areaThe frequency of the interval of the region is,a region interval frequency that is a black region;
the frequency calculation formula of the gray scale is as follows:
in the formula:in order to be a gray scale level,is a gray scaleThe frequency of (a) is set to be,is a gray scaleThe frequency of (a) to (b) is,in order to be the resolution of the gray-scale image,is the number of gray levels;
the region interval frequency calculation formula is as follows:
8. The transmission method of the internet of things based on the image quality assessment as claimed in claim 1, wherein: the method for acquiring the data volume capable of being transmitted by the bandwidth comprises the following steps:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210811735.7A CN114882042B (en) | 2022-07-12 | 2022-07-12 | Internet of things transmission method based on image quality evaluation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210811735.7A CN114882042B (en) | 2022-07-12 | 2022-07-12 | Internet of things transmission method based on image quality evaluation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114882042A CN114882042A (en) | 2022-08-09 |
CN114882042B true CN114882042B (en) | 2022-09-06 |
Family
ID=82683366
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210811735.7A Active CN114882042B (en) | 2022-07-12 | 2022-07-12 | Internet of things transmission method based on image quality evaluation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114882042B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115511833B (en) * | 2022-09-28 | 2023-06-27 | 广东百能家居有限公司 | Glass surface scratch detecting system |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106204506A (en) * | 2016-06-30 | 2016-12-07 | 刘元生 | Digital picture quality evaluating method before print |
CN109377465A (en) * | 2018-10-26 | 2019-02-22 | 北京布本智能科技有限公司 | A kind of image quality verification method based on image information entropy |
CN114219774B (en) * | 2021-11-30 | 2023-03-28 | 浙江大华技术股份有限公司 | Image quality evaluation method, device, terminal and computer readable storage medium |
CN114494262B (en) * | 2022-04-19 | 2022-07-26 | 广东粤港澳大湾区硬科技创新研究院 | Method and device for evaluating image contrast |
-
2022
- 2022-07-12 CN CN202210811735.7A patent/CN114882042B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN114882042A (en) | 2022-08-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10074164B2 (en) | Method and apparatus for adjusting image brightness | |
US5724456A (en) | Brightness adjustment of images using digital scene analysis | |
US7840084B2 (en) | Digital camera incorporating a sharpness predictor | |
JPH07104921B2 (en) | Image threshold determination method | |
CN114882042B (en) | Internet of things transmission method based on image quality evaluation | |
CN113554629A (en) | Strip steel red rust defect detection method based on artificial intelligence | |
CN115131354B (en) | Laboratory plastic film defect detection method based on optical means | |
CN115633259A (en) | Automatic regulation and control method and system for intelligent camera based on artificial intelligence | |
CN115546203B (en) | Production monitoring and analyzing method based on image data algorithm | |
CN114004834B (en) | Method, equipment and device for analyzing foggy weather condition in image processing | |
US8035703B2 (en) | Device and method for measuring noise characteristics | |
CN113884492B (en) | Ringelmann blackness calibration and detection method and device for motor vehicle exhaust | |
CN114972197A (en) | X-ray film imaging quality evaluation method and system | |
CN111093039B (en) | Exposure evaluation value calculation method, exposure parameter adjustment method and imaging equipment | |
CN112070682A (en) | Method and device for compensating image brightness | |
CN111540042A (en) | Method, device and related equipment for three-dimensional reconstruction | |
CN113905194B (en) | Exposure ratio processing method, terminal equipment and computer storage medium | |
CN115471435A (en) | Image fusion method and device, computer readable medium and electronic equipment | |
CN111928944B (en) | Laser ray detection method, device and system | |
CN117252783B (en) | Definition computing method, device and equipment for defocus blurred image | |
CN116542973B (en) | Image understanding-based precise grading method and device for leather mange defects | |
KR100437807B1 (en) | Method and apparatus for equalizing histogram | |
CN117097901B (en) | Road image data compression storage method | |
CN116912181B (en) | Screen uniformity detection method, system and readable storage medium | |
CN117522869B (en) | Image processing method, defect detection method, system and electronic equipment |
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 |