CN117409373B - Medical logistics box full-period intelligent monitoring system - Google Patents
Medical logistics box full-period intelligent monitoring system Download PDFInfo
- Publication number
- CN117409373B CN117409373B CN202311714068.1A CN202311714068A CN117409373B CN 117409373 B CN117409373 B CN 117409373B CN 202311714068 A CN202311714068 A CN 202311714068A CN 117409373 B CN117409373 B CN 117409373B
- Authority
- CN
- China
- Prior art keywords
- gray level
- gray
- logistics box
- individual
- levels
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 37
- 230000002776 aggregation Effects 0.000 claims abstract description 21
- 238000004220 aggregation Methods 0.000 claims abstract description 21
- 108010015046 cell aggregation factors Proteins 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims description 28
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000004927 fusion Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000009471 action Effects 0.000 claims description 2
- 241000764238 Isis Species 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 9
- 230000001186 cumulative effect Effects 0.000 description 3
- 238000005315 distribution function Methods 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/23—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on positionally close patterns or neighbourhood relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Software Systems (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to a full-period intelligent monitoring system of a medical logistics box, which comprises the following components: obtaining regional characteristics according to gray value differences of adjacent pixel points, obtaining aggregation factors according to distances between the pixel points, adjusting gray level differences by using the aggregation factors to obtain aggregation characteristics, further obtaining individual importance degrees of gray levels, obtaining neighborhood correlation degrees according to the number of the pixel points corresponding to the gray levels with adjacent sizes, and further obtaining new relative frequencies of the gray levels by adjusting coefficients; to enhance and monitor the logistics box image. The invention avoids the condition of unsatisfactory image enhancement effect caused by insufficient consideration of the distribution relation among the pixels corresponding to each gray level when the logistics box image is enhanced, improves the enhancement effect of the logistics box image, and further improves the full period monitoring capability of the logistics box image.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to a full-period intelligent monitoring system of a medical logistics box.
Background
Along with the diversity of the material types in the hospital, the appearance of medical thing flow box has changed the problem that material transmission circulation ability is not enough, but the medical thing flow box is not transparent when transporting on the transportation line, has consequently increased the full cycle monitoring degree of difficulty to the transportation state of thing flow box, if the thing flow box appear damaged scheduling problem, can't effectively trace to the source to the damage condition.
In the current monitoring process of the logistics box, the quality of the shot image is uneven due to the change of the ambient brightness when the image is acquired, so that the shot logistics box image is required to be subjected to equalization enhancement treatment so as to be convenient for breakage detection.
However, the conventional equalization processing is global operation on the image, and specific distribution conditions of pixels corresponding to different gray levels in the logistics box image in the global and local are not considered, so that the image enhancement effect is not ideal, and the capability of full-period monitoring on the medical logistics box is further insufficient.
Disclosure of Invention
The invention provides a full-period intelligent monitoring system of a medical logistics box, which aims to solve the existing problems.
The full-period intelligent monitoring system for the medical logistics box adopts the following technical scheme:
one embodiment of the invention provides a full-cycle intelligent monitoring system for a medical logistics box, which comprises the following modules:
the image acquisition module is used for acquiring a logistics box image, taking one gray level value as one gray level, and the gray level in the logistics box image corresponds to a plurality of pixel points;
the importance degree module is used for obtaining regional characteristics of gray levels corresponding to the pixel points according to gray value differences between the pixel points and adjacent pixel points, and the regional characteristics are used for describing gray level difference degrees between the pixel points under the same gray level and the pixel points in the corresponding neighborhood; acquiring aggregation factors of gray levels corresponding to the pixel points according to the distances between the pixel points, and adjusting the difference between the gray levels by utilizing the aggregation factors to acquire aggregation characteristics of the gray levels, wherein the aggregation characteristics are used for describing the aggregation degree of the pixel points under the same gray level; the fusion result of the regional characteristics and the aggregation characteristics is recorded as the individual importance degree of the gray level, and the individual importance degree is used for describing the degree of the action of the corresponding gray level when the surface of the logistics box is detected;
the gray frequency module is used for obtaining the neighborhood correlation degree of the gray level corresponding to the pixel point according to the number of the gray level corresponding to the pixel point with the adjacent size in the neighborhood of the pixel point, wherein the neighborhood correlation degree is used for describing the correlation degree of the gray level corresponding to the pixel point with the adjacent size on the position distribution of the logistics box image; the fusion result of the gray level difference, the individual importance degree difference and the neighborhood correlation degree is recorded as a gray level adjustment coefficient, the relative frequency of the gray level is obtained, and the gray level relative frequency is adjusted by using the adjustment coefficient to obtain a new relative frequency of the gray level;
and the reconstruction monitoring module is used for enhancing the logistics box image by utilizing the new relative frequency to obtain a new logistics box image and monitoring the new logistics box image under a plurality of times.
Further, the method for obtaining the regional characteristics of the gray level corresponding to the pixel point according to the gray value difference between the pixel point and the adjacent pixel point comprises the following specific steps:
the absolute value of the difference value of the gray value between the pixel point and any pixel point in the 8 neighborhood is marked as a first value, and the accumulated value of the first values of the pixel point and all pixel points in the 8 neighborhood is marked as a second value;
the average value of the second values of all the pixel points corresponding to any gray level is recorded as the third value of the gray level, andregional characteristics, denoted gray level, wherein +.>An exponential function based on a natural constant; />A third value representing a gray level.
Further, the method for obtaining the aggregation factor of the gray level corresponding to the pixel point according to the distance between the pixel points includes the following specific steps:
the Euclidean distance of any two pixel points under the same gray level in the logistics box image is obtained and is recorded as a distance parameter, and the average value of the reciprocal of all the distance parameters under any gray level is recorded as an aggregation factor of the gray level.
Further, the method for obtaining the aggregation characteristic of the gray level by adjusting the difference between the gray levels by using the aggregation factor comprises the following specific steps:
will be the firstGray level and->The absolute value of the difference between the gray levels is recorded as +.>Difference of gray level ∈>Will->Difference of gray level ∈>And->The product between the aggregation factors of the individual gray levels is denoted by +.>Gray value and->Aggregation characteristic parameter between gray levels, wherein +.>;
Will be the firstThe mean value of the aggregate characteristic parameter between the individual gray values and all gray levels is recorded as +.>An aggregate characteristic of the individual gray levels.
Further, the method for marking the fusion result of the regional characteristics and the aggregation characteristics as the individual importance degree of the gray level comprises the following specific steps:
will be the firstRegional characteristics of individual grey levels and +.>The product between the aggregated features of the individual grey levels is noted as +.>Individual importance of individual gray levels.
Further, the method for obtaining the neighborhood correlation degree of the gray level corresponding to the pixel point according to the number of the gray level corresponding to the pixel point with the adjacent size in the neighborhood of the pixel point comprises the following specific steps:
firstly, marking any pixel point as a target pixel point, acquiring the gray level G of the target pixel point, wherein the gray level G is within 8 adjacent areas of the target pixel pointIs marked as the first pixel point of the target pixel point, is to be in 8 adjacent to the target pixel point and has gray level of +.>A second pixel point of the target pixel point is marked;
then, calculating the neighborhood correlation degree of the gray level, wherein the specific calculation method comprises the following steps:
wherein,indicate->Neighborhood correlation of individual gray levelsThe degree; />Indicate->The number of gray levels corresponds to the number of pixels; />Indicate->Corresponding +.>The number of first pixel points of the pixel points; />Indicate->Corresponding +.>The number of second pixels of the pixels.
Further, the method for marking the fusion result of the gray level difference, the individual importance level difference and the neighborhood correlation degree as the gray level adjustment coefficient comprises the following specific steps:
obtaining gray level adjustment parameters according to differences between individual importance levels and gray level differences;
and (5) recording the accumulated results of the individual importance degree, the adjustment parameters and the neighborhood correlation degree of the gray level as the adjustment coefficient of the gray level.
Further, the method for obtaining the gray level adjustment parameter according to the difference between the individual importance degrees and the gray level difference comprises the following specific steps:
wherein,indicate->Adjustment parameters for the individual gray levels; />Indicate->Gray levels; />Indicate->Gray levels; />Indicate->Gray levels; />Indicate->Individual importance of individual gray levels; />Indicate->Individual importance of individual gray levels; />Indicate->Individual importance of individual gray levels; />Indicate->Neighborhood correlation degree of the individual gray levels; />Ai Fosen brackets; />An exponential function based on a natural constant is represented.
Further, the method for obtaining the relative frequency of the gray level, which uses the adjustment coefficient to adjust the relative frequency of the gray level to obtain the new relative frequency of the gray level, includes the following specific steps:
the first image of the logistics boxThe ratio of the number of pixels corresponding to the gray level to the number of all pixels in the logistics box image is marked as +.>The relative frequencies of the individual gray levels;
the new relative frequency of the gray level is obtained by adjusting the relative frequency of the gray level by using the adjustment coefficient, and the specific calculation method comprises the following steps:
wherein,indicate->New relative frequencies of the individual gray levels; />Indicate->The relative frequencies of the individual gray levels; />Indicate->And the adjustment coefficients of the gray levels.
Further, the method for enhancing the logistics box image by using the new relative frequency to obtain a new logistics box image and monitoring the new logistics box image under a plurality of times comprises the following specific steps:
firstly, acquiring a gray distribution histogram formed by new relative frequencies of all gray levels, marking the gray distribution histogram as a new gray distribution histogram, and carrying out image reconstruction on a logistics box image by using the new gray distribution histogram to obtain a new logistics box image;
then, new logistics box images of any logistics box are obtained according to time arrangement in the transportation process, the sequence obtained after arrangement is recorded as a logistics image sequence, the neural network is utilized to detect damage to the new logistics box images in the logistics image sequence, and when the new logistics box images are damaged, the new logistics box images are marked.
The technical scheme of the invention has the beneficial effects that: the distribution of the pixels in the neighborhood of the pixels in the logistics box image and the distribution of the pixels in the same gray level are combined to adjust the relative frequency of each gray level in the logistics box image, so that the problem that the distribution relationship between the pixels corresponding to each gray level is not considered sufficiently when the logistics box image is enhanced, which results in the non-ideal image enhancement effect, the enhancement effect on the logistics box image is improved, and the full period monitoring capability of the logistics box image is further improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a block diagram of a full-cycle intelligent monitoring system for medical logistics boxes.
Detailed Description
In order to further describe the technical means and effects adopted by the medical logistics box full-period intelligent monitoring system for achieving the preset aim of the invention, the following detailed description is given below of the specific implementation, structure, characteristics and effects of the medical logistics box full-period intelligent monitoring system according to the invention by combining the attached drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the full-cycle intelligent monitoring system for the medical logistics box provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a block diagram of a medical logistics box full-cycle intelligent monitoring system according to an embodiment of the present invention is shown, the system includes the following modules:
and the image acquisition module is used for acquiring the logistics box image.
In order to realize the medical logistics box full-period intelligent monitoring system provided by the embodiment, firstly, logistics box images need to be acquired, and the specific process is as follows:
firstly, an infrared sensing device and a camera are arranged at a transmission node, when a medical logistics box reaches an infrared sensing range, the shooting function of the camera is triggered, and an image of the surface of the logistics box is shot and recorded as a logistics box image.
And then preprocessing the logistics box image, wherein the preprocessing process comprises image graying and image noise reduction operation, and an algorithm used for the image noise reduction operation is a Gaussian filtering algorithm.
It should be noted that, in this embodiment, the filter convolution kernel of the preset gaussian filter algorithm isThe present embodiment is not particularly limited, and may be adjusted according to actual conditions.
So far, the logistics box image is obtained through the method.
The importance degree module is used for obtaining regional characteristics of gray levels corresponding to the pixel points according to gray value differences between the pixel points and adjacent pixel points; acquiring aggregation factors of gray levels corresponding to the pixel points according to the distances between the pixel points, and adjusting the difference between the gray levels by utilizing the aggregation factors to acquire aggregation characteristics of the gray levels; the fusion result of the regional features and the aggregate features is recorded as the individual importance degree of the gray scale.
Specifically, in step (1), first, a gray value is used as a gray level, and one gray level in the logistics box image corresponds to a plurality of pixel points.
Then, according to the gray value difference of adjacent pixel points, the regional characteristics of gray level are obtained, and the specific calculation method is as follows:
wherein,indicate->Regional characteristics of individual gray levels; />Representing +.>The number of the gray levels corresponds to the number of the pixel points; />Indicate->Individual gray levelsCorresponding->Gray values of the individual pixels; />Indicate->The corresponding +.>Pixel dot +.>Intra-neighborhood +.>Gray values of the individual pixels; />Representing absolute value symbols; />An exponential function based on a natural constant is represented.
It should be noted that the regional feature is used to describe the gray level difference degree between the pixel point under the same gray level and the pixel point in the corresponding neighborhood.
Note that, for a pixel point corresponding to one gray level, it is connected toThe smaller the difference of gray values between pixel points in the neighborhood, the gray level is distributed on a certain block area; in addition, because a large number of connected areas exist on the surface of the logistics box, the areas are necessarily present, but because the gray values of the pixel points in the connected areas are the same, the provided image information is less; the regional nature of the gray levels reflects the degree of aggregation of the gray levels distributed in the image.
And (2) firstly, acquiring Euclidean distances of any two pixel points in the same gray level in the logistics box image, recording the Euclidean distances as distance parameters, and recording the average value of the reciprocal of all the distance parameters in any gray level as an aggregation factor of the gray level.
It should be noted that, the aggregation factor is used to describe the average distance between all pixels at the same gray level.
Then, the aggregation characteristic of the gray level is obtained, and the specific calculation method comprises the following steps:
wherein the method comprises the steps of,/>Indicate->An aggregate characteristic of the individual gray levels; />Indicate->Gray levels; />Represent the firstGray levels; />Representing absolute value symbols; />Indicate->Aggregation factors for individual gray levels; />An exponential function based on a natural constant is represented.
It should be noted that the aggregation feature is used to describe the aggregation degree of the pixel points under the same gray level.
It should be noted that, first, gray levelCorresponding pixel points, the pixel points and non-gray level in the surrounding neighborhoodOther gray levels (defined here as +.>) The larger the difference between the gray levels, the more gray levels are indicated at this time>Always having a significant difference from the gray level of the pixels in the surrounding neighborhood, the information presented by the location where the gray level is distributed is larger than those gray levels where the difference from the surrounding is not significant. At this time->The value of the portion is larger.
Gray level of the display deviceThe other gray level of the surrounding neighborhood is +.>And gray level +.>The mean value of the mutual distance between the corresponding pixel points is +.>Then at this time, if->The smaller the value of (2) the greyscale +.>Is distributed within a small range, in other words exhibits aggregation, and gray levels +.>Gray level +.>And is also adjacent, if at this point +.>When the value of the part is larger, then the effect is shown to be at gray level +.>Beside the collected area there is a gray level +.>Gray level with very different gray levels +.>Gray level +.>It must be more visible as if there is a black dot next to a white area, then this black dot must be more visible if the gray level +.>Always exhibit such a trend when distributed, the gray level is then +_gray level compared to gray levels without such a trend feature>The individual importance of (a) is necessarily greater.
Step (3), obtaining the individual importance degree of gray level, wherein the specific calculation method comprises the following steps:
wherein,indicate->Individual importance of individual gray levels; />Indicate->Regional characteristics of individual gray levels;indicate->An aggregate characteristic of the individual gray levels.
The individual importance level is used to describe the degree of the effect of the corresponding gray level in the detection of the surface of the logistics box.
It should be noted that, whether an individual gray level is important or not, is related to whether the gray level can represent regional features and aggregate features, if the gray level has obvious regional features, the regional features are generated because the surface of the logistics box is a solid surface, the solid surface is quite close in color before being converted into gray level, and the light intensity reflected when the light source irradiates the surface is quite close on the solid surface, so after being converted into a gray level, the same or quite close gray level should be obtained, and then the region formed by the gray levels is the region where the surface of the logistics box is located. Whereas the aggregate feature is a feature that distinguishes an area constituted by one gray level from an area constituted by another gray level, the present embodiment is provided by the aggregate featureRepresenting gray level +.>The characteristic of a region is that the gray level of the pixel point in a certain region or a plurality of regions and the gray level of the pixel point in the surrounding neighborhood have obvious difference.
To this end, the individual importance level of the gray level is obtained by the above method.
The gray frequency module is used for obtaining the neighborhood correlation degree of the gray level corresponding to the pixel point according to the number of the gray level corresponding to the pixel point in the neighborhood of the pixel point, recording the fusion result of the gray level difference, the individual importance degree difference and the neighborhood correlation degree as the adjustment coefficient of the gray level, obtaining the relative frequency of the gray level, and adjusting the relative frequency of the gray level by using the adjustment coefficient to obtain the new relative frequency of the gray level.
The cumulative distribution function is a cumulative distribution function result of accumulating the relative frequencies of the gray levels to obtain the current gray level, so that for one gray level, the gray level directly related to the gray level in the histogram equalization has only the adjacent previous gray level and the adjacent next gray level. For the transition from individual gray levels to gray levels as represented by the cumulative distribution function, if the greater the importance of a gray level itself as an individual, the more pronounced the correlation between that gray level and the adjacent gray level, then the gray level should be distinguished from the adjacent gray level.
Specifically, in step (1), first, an arbitrary pixel is marked as a target pixel, the gray level G of the target pixel is obtained, and the gray level G is within 8 adjacent to the target pixelIs marked as the first pixel point of the target pixel point, is to be in 8 adjacent to the target pixel point and has gray level of +.>Is marked as a second pixel of the target pixel.
Then, calculating the neighborhood correlation degree of the gray level, wherein the specific calculation method comprises the following steps:
wherein,indicate->Neighborhood correlation degree of the individual gray levels; />Indicate->The number of gray levels corresponds to the number of pixels; />Indicate->Corresponding +.>The number of first pixel points of the pixel points; />Indicate->Corresponding +.>The number of second pixels of the pixels.
It should be noted that, the neighborhood correlation degree is used to describe the correlation degree of the position distribution of the gray level corresponding pixel points with adjacent sizes in the logistics box image.
When the pixels corresponding to the gray levels of the adjacent sizes are also adjacent in position, the degree of correlation between the gray levels and the gray levels of the adjacent sizes is high, that is, the more the number of pixels corresponding to the gray levels of the adjacent sizes in the neighborhood pixel of the pixel is, the higher the neighborhood correlation degree of the pixel is.
It should be noted that, the greater the neighborhood correlation degree of the gray level, the pixel points corresponding to the gray level always tend to be distributed with the pixel points of the adjacent gray level, because the distribution of the gray level on the surface of the logistics box is simple and monotonous, the distribution transition of the gray level is uniform, but if one gray level has a greater role in detecting the surface breakage of the logistics box, that is, the individual importance degree of the gray level is greater, the gray level should appear in one or more areas with uniform gray level distribution, and meanwhile, the gray level is greatly different from the adjacent area in gray level, and if the gray level of the size adjacent to the gray level is always distributed beside the gray level, only the distribution characteristic of the adjacent gray level is close to the gray level, and the distribution characteristic of the gray level on the surface of the logistics box is not close to the gray level, so that the gray level and the adjacent gray level needs to be further distinguished.
The specific calculation method of the gray level adjustment coefficient is as follows:
wherein,indicate->Adjustment coefficients for the individual gray levels; />Indicate->Gray levels; />Indicate->Gray levels; />Indicate->Gray levels; />Indicate->Individual importance of individual gray levels; />Indicate->Individual importance of individual gray levels; />Indicate->Individual importance of individual gray levels; />Indicate->Neighborhood correlation degree of the individual gray levels; />Ai Fosen brackets; />An exponential function based on a natural constant is represented.
The adjustment factor is used to describe the extent to which the gray level plays a role in detecting the surface of the headbox.
Gray level of the display deviceIs>The individual importance of the individual amplitude of the individual value and the adjacent gray level +>And->Related to the degree of relatedness of (1) when->When the conditions of the part are established, the gray level +.>Is to be greater than the adjacent gray level +.>And->The individual importance of the corresponding gray level, that is, the individual importance of the gray level, is more prominent, and on the basis that the larger the individual importance and the correlation degree, the larger the adjustment coefficient of the gray level is, so that the corresponding gray level can be better distinguished from the adjacent gray level after the equalization adjustment.
It should be noted that the object processed in this embodiment is gray scale, that isIn the gray levels, the relative frequency is adjusted based on the relative frequency of the gray levels, and the general idea is to quantify the adjustment amplitude, namely the adjustment coefficient, from the individual importance degree showing individuality and the neighborhood correlation degree showing the adjacent gray levels.
The gray level map of the logistics box is obtained in the above, so that a gray level histogram corresponding to the gray level map of the logistics box can be obtained, and further, the relative frequency of occurrence of different gray levels can be obtained.
Step (3), obtaining the relative frequency of gray level, and the specific calculation method is as follows:
wherein,indicate->The relative frequencies of the individual gray levels; />Indicate->The number of gray levels corresponds to the number of pixels;representing the number of all pixels in the box image.
In the process of equalizing the logistics box image, different gray levels are different in functions of detecting the logistics box surface, so that when the gray level is used for detecting the logistics box surface breakage, the larger the function of detecting the logistics box surface breakage is, the more important the gray level is, and the larger the adjustment coefficient of the gray level is further expressed.
And (4) adjusting the relative frequency of the gray level by using the adjustment coefficient to obtain a new relative frequency of the gray level, wherein the specific calculation method comprises the following steps:
wherein,indicate->New relative frequencies of the individual gray levels; />Indicate->The relative frequencies of the individual gray levels; />Indicate->And the adjustment coefficients of the gray levels.
The new relative frequency is used for describing the frequency of the corresponding gray level after the logistics box image is subjected to the equalization processing.
To this end, a new relative frequency of gray levels is obtained by the above method.
And the reconstruction monitoring module is used for enhancing the logistics box image by utilizing the new relative frequency to obtain a new logistics box image and monitoring the new logistics box image under a plurality of times.
Specifically, first, a gray distribution histogram formed by new relative frequencies of all gray levels is acquired and recorded as a new gray distribution histogram, and the new gray distribution histogram is utilized to reconstruct an image of the logistics box image, so as to obtain a new logistics box image.
Then, new logistics box images of any logistics box are obtained according to time arrangement in the transportation process, the sequence obtained after arrangement is recorded as a logistics image sequence, the neural network is utilized to detect damage to the new logistics box images in the logistics image sequence, and when the new logistics box images are damaged, the new logistics box images are marked so as to carry out full-period intelligent monitoring on the logistics boxes.
This embodiment is completed.
The following examples were usedThe model is used only to represent the negative correlation and the result of the constraint model output is at +.>In the section, other models with the same purpose can be replaced in the implementation, and the embodiment only uses +.>The model is described as an example, without specific limitation, wherein +.>Refers to the input of the model.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. The full-period intelligent monitoring system for the medical logistics box is characterized by comprising the following modules:
the image acquisition module is used for acquiring a logistics box image, taking one gray level value as one gray level, and the gray level in the logistics box image corresponds to a plurality of pixel points;
the importance degree module is used for obtaining regional characteristics of gray levels corresponding to the pixel points according to gray value differences between the pixel points and adjacent pixel points, and the regional characteristics are used for describing gray level difference degrees between the pixel points under the same gray level and the pixel points in the corresponding neighborhood; acquiring aggregation factors of gray levels corresponding to the pixel points according to the distances between the pixel points, and adjusting the difference between the gray levels by utilizing the aggregation factors to acquire aggregation characteristics of the gray levels, wherein the aggregation characteristics are used for describing the aggregation degree of the pixel points under the same gray level; the fusion result of the regional characteristics and the aggregation characteristics is recorded as the individual importance degree of the gray level, and the individual importance degree is used for describing the degree of the action of the corresponding gray level when the surface of the logistics box is detected;
the gray frequency module is used for obtaining the neighborhood correlation degree of the gray level corresponding to the pixel point according to the number of the gray level corresponding to the pixel point with the adjacent size in the neighborhood of the pixel point, wherein the neighborhood correlation degree is used for describing the correlation degree of the gray level corresponding to the pixel point with the adjacent size on the position distribution of the logistics box image; the fusion result of the gray level difference, the individual importance degree difference and the neighborhood correlation degree is recorded as a gray level adjustment coefficient, the relative frequency of the gray level is obtained, and the gray level relative frequency is adjusted by using the adjustment coefficient to obtain a new relative frequency of the gray level;
and the reconstruction monitoring module is used for enhancing the logistics box image by utilizing the new relative frequency to obtain a new logistics box image and monitoring the new logistics box image under a plurality of times.
2. The full-cycle intelligent monitoring system of the medical logistics box according to claim 1, wherein the method for obtaining the regional characteristics of the gray level corresponding to the pixel point according to the gray value difference between the pixel point and the adjacent pixel points comprises the following specific steps:
the absolute value of the difference value of the gray value between the pixel point and any pixel point in the 8 neighborhood is marked as a first value, and the accumulated value of the first values of the pixel point and all pixel points in the 8 neighborhood is marked as a second value;
the average value of the second values of all the pixel points corresponding to any gray level is recorded as the third value of the gray level, andregional characteristics, denoted gray level, wherein +.>An exponential function based on a natural constant; />A third value representing a gray level.
3. The full-cycle intelligent monitoring system of the medical logistics box according to claim 1, wherein the method for obtaining the aggregation factor of the gray level corresponding to the pixel point according to the distance between the pixel points comprises the following specific steps:
the Euclidean distance of any two pixel points under the same gray level in the logistics box image is obtained and is recorded as a distance parameter, and the average value of the reciprocal of all the distance parameters under any gray level is recorded as an aggregation factor of the gray level.
4. The full-cycle intelligent monitoring system of the medical logistics box according to claim 1, wherein the method for obtaining the aggregation characteristic of the gray level by adjusting the difference between the gray levels by using the aggregation factor comprises the following specific steps:
will be the firstGray level and->The absolute value of the difference between the gray levels is recorded as +.>Difference of gray level ∈>Will->Difference of gray level ∈>And->The product between the aggregation factors of the individual gray levels is denoted by +.>Gray value and->Aggregation characteristic parameter between gray levels, wherein +.>;
Will be the firstThe mean value of the aggregate characteristic parameter between the individual gray values and all gray levels is recorded as +.>An aggregate characteristic of the individual gray levels.
5. The medical logistics box full-period intelligent monitoring system of claim 1, wherein the method for marking the fusion result of regional characteristics and aggregation characteristics as the individual importance degree of gray level comprises the following specific steps:
will be the firstRegional characteristics of individual grey levels and +.>The product between the aggregated features of the individual grey levels is noted as +.>Individual importance of individual gray levels.
6. The full-cycle intelligent monitoring system of a medical logistics box according to claim 1, wherein the method for obtaining the neighborhood correlation degree of the gray level corresponding to the pixel point according to the number of the gray level corresponding to the pixel point in the neighborhood of the pixel point comprises the following specific steps:
firstly, marking any pixel point as a target pixel point, acquiring the gray level G of the target pixel point, wherein the gray level G is in 8 adjacent areas of the target pixel pointThe grade isIs marked as the first pixel point of the target pixel point, is to be in 8 adjacent to the target pixel point and has gray level of +.>A second pixel point of the target pixel point is marked;
then, calculating the neighborhood correlation degree of the gray level, wherein the specific calculation method comprises the following steps:
wherein,indicate->Neighborhood correlation degree of the individual gray levels; />Indicate->The number of gray levels corresponds to the number of pixels;indicate->Corresponding +.>The number of first pixel points of the pixel points; />Indicate->Corresponding +.>The number of second pixels of the pixels.
7. The medical logistics box full-period intelligent monitoring system of claim 1, wherein the fusion result of the gray level difference, the individual importance level difference and the neighborhood correlation level is recorded as the adjustment coefficient of the gray level, and the specific method comprises the following steps:
obtaining gray level adjustment parameters according to differences between individual importance levels and gray level differences;
and (5) recording the accumulated results of the individual importance degree, the adjustment parameters and the neighborhood correlation degree of the gray level as the adjustment coefficient of the gray level.
8. The full-cycle intelligent monitoring system of the medical logistics box according to claim 7, wherein the method for obtaining the gray level adjustment parameter according to the difference between the individual importance degrees and the gray level difference comprises the following specific steps:
wherein,indicate->Adjustment parameters for the individual gray levels; />Indicate->Gray levels; />Indicate->Gray levels; />Indicate->Gray levels; />Indicate->Individual importance of individual gray levels; />Represent the firstIndividual importance of individual gray levels; />Indicate->Individual importance of individual gray levels; />Indicate->Neighborhood correlation degree of the individual gray levels; />Ai Fosen brackets; />An exponential function based on a natural constant is represented.
9. The full-cycle intelligent monitoring system of a medical logistics box according to claim 1, wherein the method for obtaining the relative frequency of the gray level and adjusting the relative frequency of the gray level by using the adjustment coefficient to obtain the new relative frequency of the gray level comprises the following specific steps:
the first image of the logistics boxThe ratio of the number of pixels corresponding to the gray level to the number of all pixels in the logistics box image is marked as +.>The relative frequencies of the individual gray levels;
the new relative frequency of the gray level is obtained by adjusting the relative frequency of the gray level by using the adjustment coefficient, and the specific calculation method comprises the following steps:
wherein,indicate->New relative frequencies of the individual gray levels; />Indicate->The relative frequencies of the individual gray levels; />Indicate->And the adjustment coefficients of the gray levels.
10. The full-cycle intelligent monitoring system for medical logistics boxes according to claim 1, wherein the method for enhancing the logistics box image by using the new relative frequency to obtain a new logistics box image and monitoring the new logistics box image at a plurality of times comprises the following specific steps:
firstly, acquiring a gray distribution histogram formed by new relative frequencies of all gray levels, marking the gray distribution histogram as a new gray distribution histogram, and carrying out image reconstruction on a logistics box image by using the new gray distribution histogram to obtain a new logistics box image;
then, new logistics box images of any logistics box are obtained according to time arrangement in the transportation process, the sequence obtained after arrangement is recorded as a logistics image sequence, the neural network is utilized to detect damage to the new logistics box images in the logistics image sequence, and when the new logistics box images are damaged, the new logistics box images are marked.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311714068.1A CN117409373B (en) | 2023-12-14 | 2023-12-14 | Medical logistics box full-period intelligent monitoring system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311714068.1A CN117409373B (en) | 2023-12-14 | 2023-12-14 | Medical logistics box full-period intelligent monitoring system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117409373A CN117409373A (en) | 2024-01-16 |
CN117409373B true CN117409373B (en) | 2024-02-09 |
Family
ID=89491160
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311714068.1A Active CN117409373B (en) | 2023-12-14 | 2023-12-14 | Medical logistics box full-period intelligent monitoring system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117409373B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115690108A (en) * | 2023-01-04 | 2023-02-03 | 山东元旺电工科技有限公司 | Aluminum alloy rod production quality evaluation method based on image processing |
CN115861135A (en) * | 2023-03-01 | 2023-03-28 | 铜牛能源科技(山东)有限公司 | Image enhancement and identification method applied to box panoramic detection |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7403641B2 (en) * | 2004-05-28 | 2008-07-22 | Matsushita Electric Works, Ltd. | Object recognition system |
-
2023
- 2023-12-14 CN CN202311714068.1A patent/CN117409373B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115690108A (en) * | 2023-01-04 | 2023-02-03 | 山东元旺电工科技有限公司 | Aluminum alloy rod production quality evaluation method based on image processing |
CN115861135A (en) * | 2023-03-01 | 2023-03-28 | 铜牛能源科技(山东)有限公司 | Image enhancement and identification method applied to box panoramic detection |
Also Published As
Publication number | Publication date |
---|---|
CN117409373A (en) | 2024-01-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108197546B (en) | Illumination processing method and device in face recognition, computer equipment and storage medium | |
CN110246089B (en) | Bayer domain image noise reduction system and method based on non-local mean filtering | |
CN109064426B (en) | Method and device for suppressing glare in low-illumination image and enhancing image | |
CN104075965B (en) | A kind of micro-image grain graininess measuring method based on watershed segmentation | |
Yuan et al. | Infrared image enhancement using adaptive trilateral contrast enhancement | |
CN111972700B (en) | Cigarette appearance detection method and device, equipment, system and medium thereof | |
Guo et al. | Image dehazing via enhancement, restoration, and fusion: A survey | |
Janani et al. | Infrared image enhancement techniques—A review | |
CN103295225B (en) | Train bogie edge detection method under the conditions of low-light | |
CN110298796B (en) | Low-illumination image enhancement method based on improved Retinex and logarithmic image processing | |
CN114240789A (en) | Infrared image histogram equalization enhancement method based on optimized brightness keeping | |
Iwasokun et al. | Image enhancement methods: a review | |
CN105427255A (en) | GRHP based unmanned plane infrared image detail enhancement method | |
CN109584181A (en) | It is a kind of improved based on Retinex infrared image detail enhancing method | |
Yang et al. | Estimation of signal-dependent noise level function in transform domain via a sparse recovery model | |
Bijelic et al. | Recovering the Unseen: Benchmarking the Generalization of Enhancement Methods to Real World Data in Heavy Fog. | |
CN103177244B (en) | Method for quickly detecting target organisms in underwater microscopic images | |
Hong et al. | Single image dehazing based on pixel-wise transmission estimation with estimated radiance patches | |
Zeng et al. | High dynamic range infrared image compression and denoising | |
CN117152182B (en) | Ultralow-illumination network camera image processing method and device and electronic equipment | |
CN117409373B (en) | Medical logistics box full-period intelligent monitoring system | |
CN117809379A (en) | Intelligent humanoid recognition alarm system and method based on monitoring camera | |
Fuh et al. | Mcpa: A fast single image haze removal method based on the minimum channel and patchless approach | |
CN103595933B (en) | A kind of noise-reduction method of image | |
Tang et al. | Sky-preserved image dehazing and enhancement for outdoor scenes |
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 |