CN116612052B - Building construction safety information management method and system - Google Patents
Building construction safety information management method and system Download PDFInfo
- Publication number
- CN116612052B CN116612052B CN202310868925.7A CN202310868925A CN116612052B CN 116612052 B CN116612052 B CN 116612052B CN 202310868925 A CN202310868925 A CN 202310868925A CN 116612052 B CN116612052 B CN 116612052B
- Authority
- CN
- China
- Prior art keywords
- shadow
- area
- gray
- image
- filtering
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 20
- 238000009435 building construction Methods 0.000 title claims abstract description 18
- 238000001914 filtration Methods 0.000 claims abstract description 124
- 238000000034 method Methods 0.000 claims abstract description 46
- 238000010276 construction Methods 0.000 claims abstract description 39
- 238000009792 diffusion process Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000009826 distribution Methods 0.000 claims abstract description 11
- 230000008859 change Effects 0.000 claims abstract description 10
- 238000010606 normalization Methods 0.000 claims description 20
- 238000013519 translation Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 36
- 230000005540 biological transmission Effects 0.000 abstract description 11
- 238000003860 storage Methods 0.000 abstract description 11
- 238000007906 compression Methods 0.000 abstract description 10
- 230000006835 compression Effects 0.000 abstract description 9
- 238000004458 analytical method Methods 0.000 abstract description 6
- 230000008569 process Effects 0.000 description 12
- 238000012544 monitoring process Methods 0.000 description 7
- 239000004973 liquid crystal related substance Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000003708 edge detection Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000003892 spreading Methods 0.000 description 2
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/172—Caching, prefetching or hoarding of files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/174—Redundancy elimination performed by the file system
- G06F16/1744—Redundancy elimination performed by the file system using compression, e.g. sparse files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a building construction safety information management method and system. According to the method, local gray level difference analysis of edges is carried out on the filtered image of the gray level image of the construction site, so that contrast indexes are obtained; determining a shadow area through local gray level change of non-edge points in the filtered image, and comprehensively analyzing according to gray level areas and position distribution of the shadow area to obtain a shadow diffusion degree index; the filtering indexes are obtained through the contrast indexes and the shadow diffusion degree indexes, all the filtering indexes are obtained under all the high-pass filters with all the sizes corresponding to the gray level images of the construction site, the optimal filtering images are determined, and finally the optimal filtering images are optimized for compression, transmission and storage. According to the invention, through image processing, the image data with stronger redundancy is obtained, so that the image compression effect is improved, the transmission and storage efficiency is improved, and the efficient management of construction safety information can be better realized.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a building construction safety information management method and system.
Background
Because the construction site is complex in environmental factors, a large number of potential safety hazards are generated in the construction process, and the accident rate of the construction industry is increased by the potential safety hazards, so that the safety problem of the construction is always one of the most important problems in the construction. Dynamic monitoring management is adopted in building construction completely, and along with development of technology, the building construction starts to judge the construction environment condition of a building construction site through daily monitoring and manual patrol monitoring so as to ensure safer building construction.
When monitoring is carried out through monitoring, an administrator needs to transmit a monitoring image to other equipment for storage and viewing, but in the existing technology for improving the image compression transmission effect, the shadow effect of a filtering image due to ringing is not considered, the best filtering image cannot be obtained through analysis of pixel points, the efficiency of the image in the transmission and storage processes is low, and effective management of construction safety information is affected.
Disclosure of Invention
In order to solve the technical problems that in the prior art, the shadow effect of a filtered image due to ringing phenomenon is not considered, and the best filtered image cannot be obtained for compression, and the efficiency in the transmission and storage processes is low, the invention aims to provide a building construction safety information management method and system, and the adopted technical scheme is as follows:
the invention provides a building construction safety information management method, which comprises the following steps:
acquiring a gray level image of a building site; filtering the gray level image of the construction site according to a preset high-pass filter to obtain a filtered image, and obtaining edge points in the filtered image;
obtaining a contrast index of the filtered image according to the local gray level difference degree of each edge point in the filtered image; determining a shadow area of the filtered image according to the local gray level change condition of each non-edge point in the filtered image; obtaining a gray scale area characteristic value of each shadow area according to the gray scale and the area size of each shadow area; obtaining shadow interval characteristic values of all shadow areas according to the position distribution conditions among all shadow areas; obtaining shade diffusion degree indexes according to the gray scale area characteristic values and the shade interval characteristic values of all shade areas;
obtaining a filtering index of the filtering image according to the contrast index and the shadow diffusion degree index of the filtering image; calculating the filtering indexes of the filtering images of the gray level image of the building site under a preset number of high-pass filters with different sizes, and determining an optimal filtering image according to the sizes of all the filtering indexes; and adjusting the gray value of the optimal filtering image, compressing the adjusted optimal filtering image, and transmitting and storing the compressed optimal filtering image.
Further, the method for obtaining the contrast index comprises the following steps:
in a preset first range of each edge point, when the absolute value of the gray value difference between the non-edge point and the corresponding edge point is larger than a preset first gray threshold value, marking the corresponding non-edge point as a difference background point of the corresponding edge point; taking the gray value accumulated values of all the difference background points corresponding to the edge points as local difference characteristic values of the corresponding edge points;
and calculating the average value of the local difference characteristic values of all the edge points, and carrying out normalization processing to obtain the contrast index of the filtered image.
Further, the method for acquiring the shadow area comprises the following steps:
when the absolute value of the gray value difference between the non-edge point and the nearest edge point is smaller than or equal to a preset first gray threshold value and larger than a preset second gray threshold value, the corresponding non-edge point is marked as a shadow point; the preset first gray threshold is larger than the preset second gray threshold;
taking a preset second range of each shadow point as a shadow range, and taking a union set of all mutually overlapped shadow ranges to obtain a shadow region when the overlapped shadow ranges exist in the filtered image; when there is no overlap of the shadow ranges, the corresponding shadow range is taken as one shadow region.
Further, the method for acquiring the gray area characteristic value comprises the following steps:
multiplying the total number of the pixel points of each row of pixel points in each shadow area by the area of a preset single pixel point to obtain the row area of each row in each shadow area; multiplying the average gray value of each row of pixel points by the row area to obtain a row gray area characteristic value of each row in each shadow area;
and calculating an average value of the gray area characteristic values of all the rows in each shadow area, and carrying out normalization processing to obtain the gray area characteristic value of each shadow area.
Further, the method for obtaining the shadow interval characteristic value comprises the following steps:
among all the shadow areas, two shadow areas with shortest connecting lines between the central points of each shadow area and other shadow areas are taken as a pair of adjacent shadow areas; optionally, a pair of adjacent shadow areas are used as reference adjacent shadow areas, the shadow area with the smallest area in the reference adjacent shadow areas is used as a first shadow area, and the other shadow area is used as a second shadow area;
obtaining a connecting line between the central points of the first shadow area and the second shadow area, and continuously translating the connecting line, wherein an intersection point exists between the connecting line and the edges of the first shadow area and the second shadow area; taking the intersection point of the connecting line after each translation and the edge of the first shadow area as an adjacent edge point; calculating the minimum distance from each adjacent edge point in the first shadow region to the edge of the second shadow region, and obtaining the adjacent distance of each adjacent edge point; calculating average values of adjacent distances of all adjacent edge points and carrying out normalization processing to obtain adjacent interval characteristic values of reference adjacent shadow areas;
and taking the average value of the adjacent interval characteristic values corresponding to all the adjacent shadow areas as the shadow interval characteristic value of all the shadow areas.
Further, the method for obtaining the filtering index comprises the following steps:
performing negative correlation mapping and normalization processing on the shadow interval characteristic values of the filtered images to obtain shadow feedback indexes; and taking the product of the shadow feedback index and the contrast index as a filtering index of a filtering image.
Further, the method for acquiring the optimal filtering image comprises the following steps:
and taking the filter image corresponding to the maximum filter index in all the filter indexes as an optimal filter image.
Further, the adjusting the gray value of the optimal filtered image specifically includes:
and taking the lowest gray value of the non-edge points in the optimal filtering image as an adjustment gray value, and adjusting the gray values of all the non-edge points into the adjustment gray value.
Further, the method for obtaining the shadow diffusion degree index comprises the following steps:
and calculating an average value of the gray scale area characteristic values of all the shadow areas as a shadow gray scale area characteristic value, and taking the product of the shadow gray scale area characteristic value and the shadow interval characteristic value as a shadow diffusion degree index.
The invention provides a building construction safety information management system, which comprises a memory and a processor, wherein the memory is used for storing information of building construction safety information; the processor executes the calculation program stored in the memory to realize the construction safety information management method.
The invention has the following beneficial effects:
according to the invention, the contrast index is obtained by carrying out local gray level difference analysis on the edges of the filtered image of the gray level image of the construction site, and the filtering effect is reflected by the edge image degree of the high-pass filtering. Further considering the characteristic that a shadow area appears in a ringing phenomenon generated by high-pass filtering, determining the shadow area through local gray level change of non-edge points in a filtered image, comprehensively analyzing according to gray level area and position distribution of the shadow area, obtaining a shadow diffusion degree index, and reflecting the advantages and disadvantages of the filtering effect through the diffusion degree of the shadow. The filtering indexes are obtained through the contrast indexes and the shadow diffusion degree indexes of the filtering images, the filtering effect of the filtering images is comprehensively evaluated, the filtering images corresponding to the optimal filtering effect can be further found, all the filtering indexes are obtained and the optimal filtering images are determined under all the high-pass filters with all the sizes corresponding to the gray images of the construction site, finally, the gray value optimization is carried out on the optimal filtering images, the influence of shadow effect generated by ringing can be effectively reduced, the redundancy of image data is increased, the image compression effect is better, the transmission rate is faster, the storage efficiency is improved, and the efficient management of construction safety information can be better realized.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for managing construction safety information according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a non-optimal filtered image according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a filtering index change according to an embodiment of the invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to the specific implementation, structure, characteristics and effects of a method and a system for managing building construction safety information according to the invention, which are provided by the invention, with reference to the accompanying drawings and preferred embodiments. 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 a method and a system for managing building construction safety information provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for managing building construction safety information according to an embodiment of the present invention is shown, and the method includes the following steps:
s1: acquiring a gray level image of a building site; filtering the gray level image of the construction site according to a preset high-pass filtering window to obtain a filtered image; and determining edge points in the filtered image according to the edge information in the gray level image of the construction site.
In order to ensure the construction safety problem of the building site, the scene of the building site is often required to be detected in real time all the day, the monitored picture is intercepted for storage and transmission, the construction condition is stored while the safety condition of the building construction is monitored, a large amount of redundant information exists in the original monitored picture, such as sky information, so that the image compression effect is often poor, the transmission efficiency and the storage efficiency are influenced, and therefore the compression efficiency of the building site picture is mainly improved.
Although the construction site is complex, the whole edge conditions of the construction area in different construction scenes are different, the construction progress can be intuitively reflected through edge information, and certain detection is carried out on construction tools, for example, potential safety hazards such as damage of a crane in construction or bending of a tower trunk of the crane to a certain extent can be obtained through observation of the edge information.
Firstly, acquiring a building site gray image, in real time monitoring, intercepting any frame of image as the building site image, and carrying out gray processing to obtain the building site gray image, in the process of frequency domain filtering, firstly, obtaining a spectrum centralized image through Fourier transformation, wherein the spectrum centralized image comprises a low-frequency part and a high-frequency part, the high-frequency part corresponds to details and edge parts in the image, namely, areas needing to be observed mainly, so that a high-pass filter is selected for filtering. It should be noted that, the high-pass filters in the graying process, the fourier transform and the frequency domain filtering are all technical means well known to those skilled in the art, and are not described herein.
Because the frequency cut-off of the high-pass filter is different, that is, the filtering effects obtained by the different sizes of the high-pass filter are different, when the selected size is not good, the filtered image will have obvious ringing phenomenon, which affects the subsequent compression process, please refer to fig. 2, which shows a non-optimal filtered image schematic diagram provided by an embodiment of the present invention, and the ringing phenomenon of the filtered image in fig. 2 is obvious. It should be noted that the ringing phenomenon generated by the high-pass filter is a technical effect well known to those skilled in the art, and will not be described in detail herein.
Therefore, in order to find the optimal filtered image, i.e. the filtered image with the smallest ringing phenomenon, the filtered image needs to be analyzed, so in the embodiment of the invention, the canny edge detection operator is adopted to obtain the edge in the filtered image, the pixel points on the edge are marked as edge points, and the ringing phenomenon can be analyzed according to the edge points later. It should be noted that the canny edge detection operator is a technical means well known to those skilled in the art, and is not described herein.
S2: obtaining a contrast index of the filtered image according to the local gray level difference degree of each edge point in the filtered image; determining a shadow area of the filtered image according to the local gray level change condition of each non-edge point in the filtered image; obtaining a gray scale area characteristic value of each shadow area according to the gray scale and the area size of each shadow area; obtaining shadow interval characteristic values of all shadow areas according to the position distribution conditions among all shadow areas; and obtaining shade diffusion degree indexes according to the gray scale area characteristic values and shade interval characteristic values of all shade areas.
When the difference between the edge information in the filtered image and the background is more obvious, the better the effect of the filtered image is, therefore, the contrast between the edge in the filtered image and the background is firstly analyzed, the contrast index of the filtered image is obtained according to the local gray level difference degree of each edge point, and the specific contrast index obtaining method comprises the following steps:
in the embodiment of the invention, the preset first range is a circle which is made by taking an edge point as a center and taking the radius as 10, in the preset first range of each edge point, the local gray level difference condition of each edge point can be analyzed, a background point with larger gray level difference of the edge point is found, when the absolute value of the gray level value difference between a non-edge point and a corresponding edge point is larger than a preset first gray level threshold value, the larger gray level difference between the non-edge point and the corresponding edge point is more likely to be a real background point rather than a shadow point, the corresponding non-edge point is marked as a difference background point of the corresponding edge point, the preset first gray level threshold value is 40, and a specific numerical value implementation can be adjusted according to specific implementation conditions.
And taking the gray value accumulated value of all the difference background points as a local difference characteristic value of the corresponding edge point, reflecting the contrast condition of each edge point and the background in a local range through the integral gray level of the difference background point in the local area, and indicating that the larger the local difference characteristic value is, the larger the pixel value is possibly, and the better the contrast degree is.
Calculating the average value of the local difference characteristic values of all edge points and carrying out normalization processing to obtain a contrast index of a filtered image, and comprehensively analyzing the contrast condition of the whole edge in the filtered image through the contrast index.
In the method, in the process of the invention,expressed as contrast index>Denoted as +.>Local variance feature value of each edge point, +.>Expressed as total number of edge points in the filtered image, < >>It should be noted that, normalization is a technical means well known to those skilled in the art, and the normalization function may be selected by linear normalization or standard normalization, and the specific normalization method is not limited herein.
The contrast condition of edge points in the whole filtering image is comprehensively analyzed by an average value method, the larger the local difference characteristic value of the edge points is, the larger the corresponding contrast index is, the filtering effect of the filtering image can be primarily judged by the contrast, and the filtering effect of the filtering image is poor, but the contrast of some filtering images is good, but the shadow diffusion degree generated by ringing phenomenon is large, and the filtering effect is poor, so that the analysis is further carried out according to the shadow part generated by ringing phenomenon in the filtering image.
Firstly, a shadow area needs to be determined, because the difference between the point of the edge information and the background point in the image after high-pass filtering is larger, and the pixel value of the shadow part is usually positioned in the middle of the edge and the background, the shadow area of the filtered image is determined according to the local gray level change condition of each non-edge point in the filtered image, and the method specifically comprises the following steps:
in order to judge the pixel value state of the non-edge points, the judgment is carried out through the gray level difference between each non-edge point and the nearest edge point, and when the absolute value of the gray level difference between the non-edge point and the nearest edge point is smaller than or equal to a preset first gray level threshold value and larger than a preset second gray level threshold value, the situation that the corresponding non-edge point does not meet the background point is indicated, and the difference between the non-edge point and the nearest edge point is larger, so that the corresponding non-edge point is marked as a shadow point. In the embodiment of the invention, the preset second gray level threshold is 15, the specific numerical value implementation can be adjusted according to the specific implementation condition, and the preset first gray level threshold needs to be larger than the preset second gray level threshold so as to ensure that the judging condition is met.
Since the shadow part in the filtered image is in the area state, the preset second range of each shadow point is taken as a shadow range, in the embodiment of the invention, the preset second range is a circle with each shadow point as the center and the radius size of 4, when overlapping shadow ranges exist in the filtered image, namely, when intersection exists among shadow ranges corresponding to a plurality of shadow points, the shadow ranges are indicated to be corresponding to one shadow region, and therefore, the shadow region is obtained by taking the union of all the shadow ranges overlapped with each other. When there is no overlap of the shadow ranges, it is indicated that the shadow region herein is smaller, and the corresponding single shadow range is taken as one shadow region.
After the shadow area in the filtered image is obtained, the diffusion degree of the shadow area can be analyzed, and the method is mainly used for analyzing two aspects of the gray level area and the separation degree of the shadow. Firstly, the gray scale area of the shadow is larger, when the gray scale of the shadow area is deeper and the area is larger, the filtering effect is poorer, so that the gray scale area characteristic value of each shadow area is obtained according to the gray scale and the area size of each shadow area, and the specific gray scale area characteristic value obtaining method comprises the following steps:
according to the method, each row of pixel points in the shadow area is analyzed, the total number of the pixel points in each row of pixel points in each shadow area is multiplied by the preset single pixel point area to obtain the row area of each row in each shadow area, wherein the preset single pixel point area is a numerical value influenced by shooting equipment, in the embodiment of the invention, the single pixel point area is 1, and the preset single pixel point area is different according to different resolutions of different shooting equipment in an implementation scene. Multiplying the average gray value of each row of pixel points by the row area to obtain the row gray area characteristic value of each row in each shadow area, firstly obtaining the gray area characteristic of each row according to the gray condition and the area condition of each row of pixel points, further calculating the average value of the row gray area characteristic values of all rows in each shadow area, and carrying out normalization processing to obtain the gray area characteristic value of each shadow area. The integral gray scale and area characteristics of each shadow area are reflected through gray scale area characteristic values, and in the embodiment of the invention, the specific expression of the gray scale area characteristic values is as follows:
in the method, in the process of the invention,denoted as +.>Gray area characteristic value of each shadow region, +.>Denoted as +.>Pixel point average gray value of row, +.>Denoted as +.>Total number of pixels of a row, +.>Expressed as presetArea of single pixel->Denoted as +.>Total number of rows of the individual shaded areas. />Represented as a normalization function.
Wherein, the liquid crystal display device comprises a liquid crystal display device,denoted as +.>Row area of rows>Denoted as +.>And when the line gray scale area characteristic value of the line is larger, the gray scale area characteristic value of the corresponding shadow area is larger, and the deeper the gray scale corresponding to the shadow area is, the larger the gray scale area characteristic value of the line is.
After analyzing the gray scale area of the shadow areas, further analyzing the interval condition of the shadow areas, when the distribution of the shadow areas in the filtered image is more concentrated, the ringing generated by the filtered image is stronger, and the filtering effect is poor at the moment.
When calculating the adjacent position distribution of shadow areas, firstly acquiring the adjacent shadow areas, and taking two shadow areas with shortest connecting lines between the central points of each shadow area and other shadow areas as a pair of adjacent shadow areas in all the shadow areas, wherein each shadow area has an adjacent shadow area. Optionally, a pair of adjacent shadow areas are selected as reference adjacent shadow areas, the shadow area with the smallest area in the reference adjacent shadow areas is selected as a first shadow area, the other shadow area is selected as a second shadow area, and the pair of adjacent shadow areas are analyzed, wherein the area of the first shadow area is smaller, and the corresponding edge is possibly shorter, so that the length of the edge can be primarily analyzed through the area, and the subsequent concrete calculation of the shadow interval is facilitated. It should be noted that, the obtaining of the center point of the area is a technical means for a person skilled in the art to obtain the value, and will not be described herein.
And obtaining a connecting line between the central points of the first shadow area and the second shadow area, wherein the connecting line is respectively intersected at each intersection point of the edges of the first shadow area and the edges of the second shadow area, continuously translating the connecting line, and ensuring that the connecting line and the edges of the first shadow area and the second shadow area have one intersection point, otherwise, the translation cannot be realized. And taking the intersection point of the connecting line after each translation and the edge of the first shadow area as an adjacent edge point, wherein the adjacent edge point is also the edge point of the first shadow area close to the edge point of the second shadow area, and screening out the relatively similar edge points between the two shadow areas in a connecting line translation mode.
And calculating the minimum distance from each adjacent edge point in the first shadow region to the edge of the second shadow region, obtaining the adjacent distance of each adjacent edge point, and finding the point-to-point shortest distance condition between the two shadow regions for each adjacent edge point. And calculating average values of adjacent distances of all adjacent edge points, and carrying out normalization processing to obtain adjacent interval characteristic values of the reference adjacent shadow areas. By analyzing all edge points on the edge, the shortest distance between two adjacent shadow areas, namely adjacent interval characteristic values, are found, and in the embodiment of the invention, the specific expression of the adjacent interval characteristic values is as follows:
where X is expressed as a neighboring interval characteristic value,denoted as +.>Adjacent distance of adjacent edge points, +.>Expressed as the total number of adjacent edge points, +.>Represented as a normalization function.
The distribution distance between two adjacent shadow areas is comprehensively reflected in the form of an average value, and when the adjacent distance is larger, the adjacent interval characteristic value between the reference adjacent shadow areas is larger, and the distribution of the shadow areas is more discrete. Further calculating adjacent interval characteristic values between all adjacent shadow areas, taking an average value of the adjacent interval characteristic values corresponding to all the adjacent shadow areas as the shadow interval characteristic values of all the shadow areas, and reflecting the overall distribution interval condition of all the shadow areas in the form of the average value, wherein in the embodiment of the invention, the specific expression of the shadow interval characteristic values is as follows:
in the method, in the process of the invention,expressed as a shadow interval feature value,/->Denoted as +.>For adjacent interval feature values of adjacent shadow areas,expressed as the total number of adjacent shadow areas.
The gray area characteristic value of each shadow area and the shadow interval characteristic value corresponding to the whole shadow area can be obtained, and the gray area characteristic value and the shadow interval characteristic value are integrated to obtain the shadow diffusion degree index, specifically: and calculating an average value of the gray scale area characteristic values of all the shadow areas as a shadow gray scale area characteristic value, and taking the product of the shadow gray scale area characteristic value and the shadow interval characteristic value as a shadow diffusion degree index. In the embodiment of the invention, for the accuracy of subsequent calculation, the specific expression of the shadow diffusion degree index is as follows:
in the method, in the process of the invention,expressed as a shade-spreading degree index,>denoted as +.>Gray area characteristic value of each shadow region, +.>Expressed as a shadow interval characteristic value, W is expressed as the total number of shadow areas.
Wherein, the liquid crystal display device comprises a liquid crystal display device,the shadow gray scale area characteristic value is expressed, the diffusion degree of the shadow is comprehensively reflected in a product form, when the shadow gray scale area characteristic value is larger, the shadow interval characteristic value is larger, the shadow area is more obvious, the shadow diffusion degree is larger, the filtering effect is poorer, and therefore, the shadow gray scale area characteristic value and the shadow interval characteristic value are in positive correlation with the shadow diffusion degree index.
Thus, the analysis of the edge contrast and the shadow condition in the filtered image are completed, and the contrast index and the shadow diffusion degree index are obtained.
S3: obtaining a filtering index of the filtering image according to the contrast index and the shadow diffusion degree index of the filtering image; calculating the filtering indexes of the filtering images of the gray level image of the construction site under a preset number of high-pass filters with different sizes, and determining the optimal filtering image according to the sizes of all the filtering indexes; and (3) adjusting the gray value of the optimal filtering image, compressing the adjusted optimal filtering image, and transmitting and storing the compressed optimal filtering image.
The contrast index and the shadow diffusion degree index obtained according to the step S2 can be used for evaluating the filtering effect of the filtering image, when the contrast is more obvious, the edge is more obvious, the filtering effect is better, when the shadow diffusion degree is less obvious, the filtering effect is better, and the generated ringing phenomenon is less obvious, so that the filtering index of the filtering image is obtained according to the contrast index and the shadow diffusion degree index, and the filtering index is specifically as follows: and carrying out negative correlation mapping and normalization processing on the shadow interval characteristic values of the filtered image to obtain shadow feedback indexes, and taking the product of the shadow feedback indexes and the contrast indexes as the filtering indexes of the filtered image. In the embodiment of the invention, for the accuracy of calculation, the specific expression of the filtering index is:
in the method, in the process of the invention,expressed as a filtering index>Expressed as contrast index>Expressed as a shade-spreading degree index,>expressed as a natural constant.
Wherein, the liquid crystal display device comprises a liquid crystal display device,the index function with the natural constant as the base is used for carrying out negative correlation mapping and normalization, namely shadow feedback indexes, when the shadow diffusion degree index is smaller, the shadow feedback index is larger, the filtering index is larger, and when the contrast index is larger, the filtering index is larger. The shadow diffusion degree index and the filtering index are in negative correlation, and the contrast index and the filtering index are in positive correlation.
At this time, we can obtain the filtering effect of the current filter, in order to find the optimal filtering effect corresponding to the image, construct the high-pass filter that the gray-scale image of building site can correspond to different sizes, in this embodiment of the present invention, the preset number of different sizes are the sizes that the gray-scale image of building site can choose, the preset number is 50, the specific numerical value implementation person can specifically adjust according to the implementation situation. When the selected cut-off frequencies are different, the sizes of the filters are also changed, and the filtering effects are also different, so that the filtering indexes of the filtered images under all the sizes of the high-pass filters are calculated. Referring to fig. 3, a schematic diagram of a change of a filtering index according to an embodiment of the present invention is shown, wherein an abscissa indicates a size of a high-pass filter, and an ordinate indicates the filtering index.
The optimal high-pass filter and the corresponding optimal filtering image can be determined according to the change of the filtering index, when the filtering index is maximum, the size of the corresponding high-pass filter is the optimal size, and the filtering image at the moment is the optimal filtering image. The optimal filtering image is also the image with the best filtering effect and the clearest edge, and the redundancy of the data can be greatly increased when the optimal filtering image is compressed, so that the compression effect is better.
Since a small amount of shadow areas still appear in the filtering process, the final optimal filtering image is adjusted, the lowest gray value of the non-edge points in the optimal filtering image is used as an adjusting gray value, and the gray values of all the non-edge points are adjusted to be the adjusting gray value. The adjusted optimal filtering image has clear edge information and uniform background pixel points, so that the data redundancy in the image is increased, the compressible space of the image is increased, the effects of low transmission quantity and quick transmission are realized, the storage space of the image is greatly saved, and the storage capacity of building construction data is improved.
In summary, the invention obtains the contrast index by carrying out the local gray difference analysis of the edges on the filtered image of the gray image of the construction site, and reflects the filtering effect by the degree of the edge image of the high-pass filtering. Further considering the characteristic that a shadow area appears in a ringing phenomenon generated by high-pass filtering, determining the shadow area through local gray level change of non-edge points, comprehensively analyzing according to gray level area and position distribution of the shadow area, obtaining a shadow diffusion degree index, and reflecting the advantages and disadvantages of a filtering effect through the diffusion degree of the shadow. The filtering indexes are obtained through the contrast indexes and the shadow diffusion degree indexes, the filtering effect of the filtering image is comprehensively evaluated, the filtering image corresponding to the optimal filtering effect can be searched, all the filtering indexes are obtained and the optimal filtering image is determined under all the high-pass filters with all the sizes corresponding to the gray level image of the construction site, the gray level value of the optimal filtering image is finally optimized, the redundancy of the image data is increased, the image compression effect is higher, the transmission rate is higher, and the storage efficiency is improved.
The invention provides a construction safety information management system, which comprises a memory and a processor, wherein the processor executes a computing program stored in the memory to realize the construction safety information management method.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (7)
1. A method for managing construction safety information, the method comprising:
acquiring a gray level image of a building site; filtering the gray level image of the construction site according to a preset high-pass filter to obtain a filtered image, and obtaining edge points in the filtered image;
obtaining a contrast index of the filtered image according to the local gray level difference degree of each edge point in the filtered image; determining a shadow area of the filtered image according to the local gray level change condition of each non-edge point in the filtered image; obtaining a gray scale area characteristic value of each shadow area according to the gray scale and the area size of each shadow area; obtaining shadow interval characteristic values of all shadow areas according to the position distribution conditions among all shadow areas; obtaining shade diffusion degree indexes according to the gray scale area characteristic values and the shade interval characteristic values of all shade areas;
obtaining a filtering index of the filtering image according to the contrast index and the shadow diffusion degree index of the filtering image; calculating the filtering indexes of the filtering images of the gray level image of the building site under a preset number of high-pass filters with different sizes, and determining an optimal filtering image according to the sizes of all the filtering indexes; gray value adjustment is carried out on the optimal filtering image, and the adjusted optimal filtering image is compressed, transmitted and stored;
the method for acquiring the contrast index comprises the following steps:
in a preset first range of each edge point, when the absolute value of the gray value difference between the non-edge point and the corresponding edge point is larger than a preset first gray threshold value, marking the corresponding non-edge point as a difference background point of the corresponding edge point; taking the gray value accumulated values of all the difference background points corresponding to the edge points as local difference characteristic values of the corresponding edge points;
calculating the average value of the local difference characteristic values of all the edge points and carrying out normalization processing to obtain a contrast index of the filtered image;
the method for acquiring the filtering index comprises the following steps:
performing negative correlation mapping and normalization processing on the shadow interval characteristic values of the filtered images to obtain shadow feedback indexes; taking the product of the shadow feedback index and the contrast index as a filtering index of a filtering image;
the method for acquiring the shadow diffusion degree index comprises the following steps:
and calculating an average value of the gray scale area characteristic values of all the shadow areas as a shadow gray scale area characteristic value, and taking the product of the shadow gray scale area characteristic value and the shadow interval characteristic value as a shadow diffusion degree index.
2. The construction safety information management method according to claim 1, wherein the method for acquiring the shadow area comprises:
when the absolute value of the gray value difference between the non-edge point and the nearest edge point is smaller than or equal to a preset first gray threshold value and larger than a preset second gray threshold value, the corresponding non-edge point is marked as a shadow point; the preset first gray threshold is larger than the preset second gray threshold;
taking a preset second range of each shadow point as a shadow range, and taking a union set of all mutually overlapped shadow ranges to obtain a shadow region when the overlapped shadow ranges exist in the filtered image; when there is no overlap of the shadow ranges, the corresponding shadow range is taken as one shadow region.
3. The construction safety information management method according to claim 1, wherein the method for acquiring the gray area characteristic value comprises the steps of:
multiplying the total number of the pixel points of each row of pixel points in each shadow area by the area of a preset single pixel point to obtain the row area of each row in each shadow area; multiplying the average gray value of each row of pixel points by the row area to obtain a row gray area characteristic value of each row in each shadow area;
and calculating an average value of the gray area characteristic values of all the rows in each shadow area, and carrying out normalization processing to obtain the gray area characteristic value of each shadow area.
4. The construction safety information management method according to claim 1, wherein the method for acquiring the shadow interval characteristic value comprises:
among all the shadow areas, two shadow areas with shortest connecting lines between the central points of each shadow area and other shadow areas are taken as a pair of adjacent shadow areas; optionally, a pair of adjacent shadow areas are used as reference adjacent shadow areas, the shadow area with the smallest area in the reference adjacent shadow areas is used as a first shadow area, and the other shadow area is used as a second shadow area;
obtaining a connecting line between the central points of the first shadow area and the second shadow area, and continuously translating the connecting line, wherein an intersection point exists between the connecting line and the edges of the first shadow area and the second shadow area; taking the intersection point of the connecting line after each translation and the edge of the first shadow area as an adjacent edge point; calculating the minimum distance from each adjacent edge point in the first shadow region to the edge of the second shadow region, and obtaining the adjacent distance of each adjacent edge point; calculating average values of adjacent distances of all adjacent edge points and carrying out normalization processing to obtain adjacent interval characteristic values of reference adjacent shadow areas;
and taking the average value of the adjacent interval characteristic values corresponding to all the adjacent shadow areas as the shadow interval characteristic value of all the shadow areas.
5. The construction safety information management method according to claim 1, wherein the obtaining method of the optimal filtering image comprises:
and taking the filter image corresponding to the maximum filter index in all the filter indexes as an optimal filter image.
6. The method for managing building construction safety information according to claim 1, wherein the adjusting the gray value of the optimal filtering image specifically comprises:
and taking the lowest gray value of the non-edge points in the optimal filtering image as an adjustment gray value, and adjusting the gray values of all the non-edge points into the adjustment gray value.
7. A construction safety information management system comprises a memory and a processor; the processor executes the computer program stored in the memory to implement a construction safety information management method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310868925.7A CN116612052B (en) | 2023-07-17 | 2023-07-17 | Building construction safety information management method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310868925.7A CN116612052B (en) | 2023-07-17 | 2023-07-17 | Building construction safety information management method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116612052A CN116612052A (en) | 2023-08-18 |
| CN116612052B true CN116612052B (en) | 2023-09-22 |
Family
ID=87678571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310868925.7A Active CN116612052B (en) | 2023-07-17 | 2023-07-17 | Building construction safety information management method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116612052B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114118144A (en) * | 2021-11-11 | 2022-03-01 | 陈稷峰 | Anti-interference accurate aerial remote sensing image shadow detection method |
| WO2022166865A1 (en) * | 2021-02-08 | 2022-08-11 | 瞬联软件科技（北京）有限公司 | Shadow elimination method and apparatus for text image, and electronic device |
| CN116309579A (en) * | 2023-05-19 | 2023-06-23 | 惠州市宝惠电子科技有限公司 | Transformer welding seam quality detection method using image processing |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7236266B2 (en) * | 2003-01-23 | 2007-06-26 | Kabushiki Kaisha Toshiba | Image processing apparatus and image processing method |
-
2023
- 2023-07-17 CN CN202310868925.7A patent/CN116612052B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022166865A1 (en) * | 2021-02-08 | 2022-08-11 | 瞬联软件科技（北京）有限公司 | Shadow elimination method and apparatus for text image, and electronic device |
| CN114118144A (en) * | 2021-11-11 | 2022-03-01 | 陈稷峰 | Anti-interference accurate aerial remote sensing image shadow detection method |
| CN116309579A (en) * | 2023-05-19 | 2023-06-23 | 惠州市宝惠电子科技有限公司 | Transformer welding seam quality detection method using image processing |
Non-Patent Citations (4)
| Title |
|---|
| 一种面向目标区域的快速去模糊算法;李沛秦;谢剑斌;陈章永;程永茂;刘通;;信号处理(第08期);全文 * |
| 基于动态纹理分析的蓝宝石熔体状态识别方法;毛颖杰;李钰;王坤;康周茂;;人工晶体学报(第04期);全文 * |
| 基于标记分水岭算法的高分辨率遥感图像分割方法;孙颖;何国金;;科学技术与工程(第11期);全文 * |
| 航空图像中阴影区域的检测;杨益军, 赵荣椿, 汪文秉;信号处理(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116612052A (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116186634B (en) | Intelligent management system for construction data of building engineering | |
| US10074164B2 (en) | Method and apparatus for adjusting image brightness | |
| CN110895806A (en) | Method and system for detecting screen display defects | |
| US8160397B1 (en) | Method for automatic alignment of raster data with vector data in a geographic information system | |
| CN112381784A (en) | Equipment detecting system based on multispectral image | |
| CN105678700A (en) | Image interpolation method and system based on prediction gradient | |
| EA004910B1 (en) | Method and apparatus for determining regions of interest in images and for image transmission | |
| CN115314714B (en) | Data compression method for weld image storage | |
| CN109726649B (en) | Remote sensing image cloud detection method and system and electronic equipment | |
| CN115619793B (en) | Power adapter appearance quality detection method based on computer vision | |
| CN115661669B (en) | Method and system for monitoring illegal farmland occupancy based on video monitoring | |
| US11567207B2 (en) | Apparatus and method for efficient point cloud feature extraction and segmentation framework | |
| Silvestre-Blanes | Structural similarity image quality reliability: Determining parameters and window size | |
| CN114241386A (en) | Method for detecting and identifying hidden danger of power transmission line based on real-time video stream | |
| CN116188495A (en) | High-efficiency processing method for homeland monitoring data | |
| CN116612052B (en) | Building construction safety information management method and system | |
| CN114820438A (en) | Method and system for detecting surface material defects of silencer | |
| CN116343051B (en) | Geological environment monitoring method and system based on remote sensing image | |
| CN112070682A (en) | Method and device for compensating image brightness | |
| CN113112431A (en) | Image processing method in embedded system | |
| CN117640932A (en) | Neurology image compression transmission method for telemedicine | |
| CN106778822B (en) | Image straight line detection method based on funnel transformation | |
| CN111833341A (en) | Method and device for determining stripe noise in image | |
| CN112508832A (en) | Object-oriented remote sensing image data space-time fusion method, system and equipment | |
| CN115294035B (en) | Bright spot positioning method, bright spot positioning device, electronic equipment and storage medium |
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 |