CN116386074A - Intelligent processing and management system for garden engineering design data - Google Patents
Intelligent processing and management system for garden engineering design data Download PDFInfo
- Publication number
- CN116386074A CN116386074A CN202310664441.0A CN202310664441A CN116386074A CN 116386074 A CN116386074 A CN 116386074A CN 202310664441 A CN202310664441 A CN 202310664441A CN 116386074 A CN116386074 A CN 116386074A
- Authority
- CN
- China
- Prior art keywords
- image
- tile
- sliding window
- window
- images
- 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.)
- Granted
Links
- 238000013461 design Methods 0.000 title claims abstract description 79
- 238000012545 processing Methods 0.000 title claims abstract description 40
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 230000011218 segmentation Effects 0.000 claims abstract description 15
- 239000013598 vector Substances 0.000 claims description 45
- 230000009466 transformation Effects 0.000 claims description 28
- 238000013519 translation Methods 0.000 claims description 27
- 238000007726 management method Methods 0.000 claims description 26
- 239000011159 matrix material Substances 0.000 claims description 19
- 238000000034 method Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 6
- 238000013523 data management Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 2
- 238000003672 processing method Methods 0.000 claims 1
- 238000001228 spectrum Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 3
- 238000013467 fragmentation Methods 0.000 description 3
- 238000006062 fragmentation reaction Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/42—Document-oriented image-based pattern recognition based on the type of document
- G06V30/422—Technical drawings; Geographical maps
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/414—Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/418—Document matching, e.g. of document images
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to an intelligent processing and management system for garden engineering design data, which comprises the following components: and performing tile segmentation on the acquired design image, and analyzing the interrelation between the tile window image and the pixel points in the sliding window image by utilizing the sliding window to obtain the similarity characteristics between the corresponding window images. According to the invention, the acquired design image is segmented and traversed, the similarity characteristics between different window images are obtained according to the similarity and the position relation between the pixel points in the images corresponding to different windows, the translational invariance and the rotational invariance of template matching are enhanced, the accuracy of template matching is improved, the fragmented intelligent management of garden engineering design related image data is realized through the fragmented template matching and analysis of the design image, and the processing and management efficiency of the image data is improved.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to an intelligent processing and management system for garden engineering design data.
Background
At present, garden images in many scenes are subjected to global template matching processing, but the same targets are difficult to match after rotation in the matching process, and particularly, a plurality of identical planting areas in garden engineering design images are repeated, and information is repeated in a large amount, so that the repeated partial images are required to be stored, and the occupied storage space is reduced;
because the template matching has the limitations, the image with translation transformation can be matched, but when the matching target in the image is subjected to rotation transformation, the template matching method is invalid, so that the condition of low matching accuracy of the template matching method occurs, and the image processing and management effects are not ideal.
In order to perform intelligent processing on a garden engineering design drawing, the invention utilizes the correlation characteristic of a frequency spectrum image and combines the position relation among pixel points in the image to perform regular analysis on images of different areas in the design image, so as to realize merging processing of the area images, enhance translational invariance and rotation invariance of a template matching method and realize intelligent processing and management of garden engineering design data.
Disclosure of Invention
The invention provides an intelligent processing and management system for garden engineering design data, which aims to solve the existing problems.
The intelligent processing and management system for the garden engineering design data adopts the following technical scheme:
the invention provides a garden engineering design data intelligent processing and management system, which comprises the following modules:
an image data acquisition module: obtaining a preprocessed garden engineering design drawing, and recording the preprocessed garden engineering design drawing as a design image;
an image window segmentation module: equally dividing the design image to obtain a plurality of tile window images, constructing a sliding window to traverse the design image, and obtaining a plurality of sliding window images;
a rotation analysis module: acquiring frequency, amplitude, phase and frequency vectors corresponding to all pixel points in all tile window images and sliding window images, marking an array formed by the frequency, amplitude and phase of any pixel point as a frequency domain space vector, and acquiring translatory property between the tile window images and the sliding window images according to the frequency domain space vector of any pixel point in the tile window images and the frequency domain space vector of all pixel points in the sliding window images; obtaining a similar image group according to the size of the translation property, and obtaining a two-dimensional rotation matrix among the pixel points according to the frequency vectors of the pixel points in the similar image group; according to the average value of the corresponding two-dimensional rotation matrixes among all pixel points in the tile window image and the sliding window image and any two-dimensional rotation matrix, the rotatability between the tile window image and the sliding window image is obtained;
similarity analysis module: obtaining similarity characteristics between the tile window image and the sliding window image according to fusion of translativity and rotatableness between the tile window image and the sliding window image;
an image data management module: according to the size of the similarity characteristic between the tile window image and the sliding window image, intelligent processing and management of the design image are realized.
Further, the equally dividing the design image to obtain a plurality of tile window images, constructing a sliding window to traverse the design image to obtain a plurality of sliding window images, comprising the following specific steps:
marking the graying garden engineering design drawing as a design image;
carrying out tile segmentation on the design image by utilizing the preset size of a tile window to obtain a plurality of area blocks with the same size, and recording images corresponding to the area blocks as tile window images;
constructing a sliding window with the preset step length as a sliding step length and the window size equal to the preset tile window size, traversing the design image, and marking the image in the sliding window as a sliding window image in the process of traversing the design image by the sliding window.
Further, the translation property is obtained by the following steps:
firstly, processing all tile window images and sliding window images by utilizing Fourier transformation to obtain frequencies, amplitudes and phases corresponding to all pixel points in the tile window images and the sliding window images;
then, the frequency domain space vector of the ith pixel point in the tile window image is recorded as
The frequency domain space vector of the jth pixel point in the sliding window image is marked as +.>
And acquiring the translation between any tile window image and any sliding window image according to the frequency domain space vector:
wherein ,
representing the translatory property between tile window image and sliding window image,/->
Frequency domain space vector representing ith pixel point in tile window image, +.>
A frequency domain space vector representing a j-th pixel point in the sliding window image; />
Representing the acquisition of cosine similarity between vectors in brackets; />
And (3) representing the maximum value of cosine similarity between any pixel point in the acquired tile window image and the frequency domain space vectors of all pixel points in the sliding window image.
Further, the rotatability is obtained by the following steps:
step (1), acquiring corresponding tile window images and sliding window images when the translativity is larger than a preset translativity threshold value, and recording the tile window images and the sliding window images as similar image groups;
step (2), acquiring any pixel point in the tile window image of the similar image group, and marking two pixel points corresponding to the cosine similarity maximum value of the frequency domain space vector as similar pixel points between the cosine similarity maximum value of the frequency domain space vector and all pixel points in the sliding window image of the similar image group;
step (3), obtaining the included angle of the frequency vector between the similar pixel points by using an inverse cosine function, recording the included angle as a rotation angle, and obtaining a two-dimensional rotation matrix corresponding to the similar pixel points according to the rotation angle:
wherein ,
represents the rotation angle between similar pixels +.>
The corresponding two-dimensional rotation matrix; />
Representing the rotation angle between similar pixel points; />
Representing a cosine function; />
Representing a sine function;
step (4), obtaining the average value of the two-dimensional rotation matrixes corresponding to all similar pixel points in the similar image group, and marking the average value as the average value matrix corresponding to the similar image group; and acquiring standard deviations of cosine similarity between two-dimensional rotation matrixes corresponding to all similar pixel points and a mean matrix corresponding to the similar image group, and recording the inverted numbers of the standard deviations as the rotatability between the tile window image and the sliding window image in the similar image group.
Further, the similarity feature comprises the following specific steps:
the method for acquiring the similarity characteristics between the tile window image and the sliding window image in the similar image group comprises the following steps:
wherein ,
representing similarity features between tile window image and sliding window image,/for>
Representing a translatory property between the tile window image and the sliding window image; />
Representing the rotatability between the tile window image and the sliding window image.
Further, according to the size of the similarity feature between the tile window image and the sliding window image, the intelligent processing and management of the design image are realized, and the method comprises the following specific steps:
firstly, carrying out linear normalization on similarity features between all tile window images and sliding window images;
then, obtaining a similar image group which is larger than a preset similarity threshold value in normalized similarity characteristics between all tile window images and sliding window images, and simultaneously obtaining translation transformation and rotation transformation matrixes between the tile window images and the sliding window images in the similar image group;
and finally, selecting and deleting the sliding window image in the similar image group, storing the tile window image, reducing repeated storage of the same object in the design image, and realizing intelligent processing and management of garden engineering design related image data.
The technical scheme of the invention has the beneficial effects that: the acquired design image is segmented and traversed, and according to the similarity of relevant parameters in the frequency domain space between pixel points in the images corresponding to different windows and the position relation in the airspace image, the similarity between the images of different windows is obtained, so that the translational invariance and the rotational invariance of template matching are enhanced, the accuracy of template matching is improved, the fragmentation intelligent management of garden engineering design relevant image data is realized through the fragmentation template matching and analysis of the design image, and the processing and management efficiency of the image data is 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 flow diagram of a system for intelligent processing and management of garden engineering design data according to the present invention;
fig. 2 is a design image.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of a specific implementation, structure, characteristics and effects of a garden engineering design data intelligent processing and management system according to the invention in combination with 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 invention provides a specific scheme of a garden engineering design data intelligent processing and management system, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a block flow diagram of a system for intelligent processing and managing of garden engineering design data according to an embodiment of the present invention is shown, where the system includes the following blocks:
an image data acquisition module: and obtaining a garden engineering design image, and preprocessing the image.
And obtaining a garden engineering design drawing, carrying out graying treatment on the garden engineering design drawing, and marking an image obtained after the graying treatment as a design image, as shown in fig. 2.
An image window segmentation module: and performing tile segmentation on the design image to obtain a plurality of tile window images with equal sizes, and constructing a sliding window to traverse the design image.
In the embodiment, tile segmentation is utilized to process a design image, and as the same vegetation or articles exist in the design image under different positions, rotation transformation occurs, in the follow-up of the embodiment, similar analysis is carried out on each region in the image by utilizing the characteristic information of geometric similarity in the image and combining Fourier transformation;
and (3) carrying out characteristic morphological analysis on the segmented image, and analyzing the situations of different vegetation and different kinds of articles in the image. And (5) analyzing and matching by utilizing the spectrum characteristics of the target to obtain the similarity of the same repeated target. And (3) performing spectrum analysis in the same window, and performing feature matching processing on the waveform change of the signals in the window by utilizing the feature information of the spectrum to obtain the similarity of the spectrum.
Firstly, carrying out tile segmentation processing on a design image to obtain a plurality of area blocks with the same size, and marking images corresponding to the area blocks as tile window images so as to facilitate subsequent image similarity analysis by using the tile window images;
when the design image is subjected to tile segmentation, the size of a preset tile window is as follows
That is, the side length of the tile window image is 3 pixels, and the tile window image has 9 pixel points in total; in addition, when the design image is subjected to tile segmentation processing, segmentation is started from top to bottom and from left to right, and when the segmentation is insufficient to the end, the segmentation is performed>
When the tile window with the size is used, the last row or the last column of the image is supplemented with the row or the column with the gray value of 0, so that the sizes of all the tile windows are guaranteed to be +.>
Size of the product.
Then, constructing a structure with a preset step length of 2 and a size of
Traversing the design image, and marking the image in the sliding window as a sliding window image in the process of traversing the design image by the sliding window;
it should be noted that, the size of the sliding window image should be consistent with the size of the tile window image, so that the similar analysis is conveniently performed by using the spectrums of the sliding window image and the tile window image, and the processing and management of the image data are further convenient.
So far, a plurality of tile window images and sliding window images are obtained.
A rotation analysis module: and carrying out Fourier transform on the tile window image and the sliding window image, acquiring related parameters, and analyzing the rotation characteristics between the tile window image and the sliding window image.
Since the translation transformation of any image does not affect the spectrum image corresponding to the image, that is, after any image is subjected to the translation transformation, the corresponding spectrum image remains unchanged, after the translation transformation, the relevant parameters of the corresponding pixel points obtained by fourier transformation remain unchanged, and the rotation transformation of the image affects the change of the frequency domain image corresponding to the image, in order to make the fourier transformation with translation invariance, when the tile window image and the sliding window image are subjected to template matching, the template matching has the characteristic of rotation invariance, firstly, the translation between the tile window image and the sliding window image needs to be analyzed, that is, whether the sliding window image can be obtained through the translation transformation of the tile window image is analyzed, and then, the rotation between the tile window image and the sliding window image is obtained according to the translation analysis result, that is, whether the sliding window image can be obtained through the rotation transformation of the tile window image is analyzed.
And (1) processing all the tile window images and the sliding window images by utilizing Fourier transformation, and carrying out centering operation on each corresponding frequency spectrum image to obtain the frequency, amplitude, phase and frequency vector corresponding to each pixel point in the tile window images and the sliding window images.
And (2) carrying out translation analysis on any tile window image.
Taking an array formed by the frequency, the amplitude and the phase of any pixel point in the tile window image and the sliding window image as a frequency domain space vector corresponding to the pixel point, namely
, wherein ,/>
Representing the frequency of the pixel, < >>
Representing the amplitude of the pixel,/, for>
Representing the phase of the pixel point;
the frequency domain space vector of the ith pixel point in the tile window image is recorded as
The frequency domain space vector of the jth pixel point in the sliding window image is marked as +.>
And acquiring the translation between any tile window image and any sliding window image according to the frequency domain space vector:
wherein ,
representing the translatory property between tile window image and sliding window image,/->
Frequency domain space vector representing ith pixel point in tile window image, +.>
A frequency domain space vector representing a j-th pixel point in the sliding window image; />
Representing the acquisition of cosine similarity between vectors in brackets; />
And (3) representing the maximum value of cosine similarity between any pixel point in the acquired tile window image and the frequency domain space vectors of all pixel points in the sliding window image.
And obtaining the translativity between all the tile window images and all the sliding window images according to the translativity obtaining method between the tile window images and the sliding window images.
The smaller the translatory between the tile window image and the sliding window image, the more likely the relation between the tile window image and the sliding window image is that there is no translational transformation; conversely, when the translativity between the tile window image and the sliding window image is larger, the more likely a translation transformation relation exists between the tile window image and the sliding window image;
therefore, a translation threshold is preset, and rotation analysis is carried out on the tile window image and the sliding window image with the translation larger than the translation threshold;
it should be noted that, the translational threshold is preset to be 0.9 according to experience, and can be adjusted according to actual situations.
And (3) further analyzing the tile window image and the sliding window image according to the size of the translativity between the tile window image and the sliding window image, and obtaining the rotatability between the tile window image and the sliding window image.
In the process of window sliding matching targets, waveforms with the same parameters and frequencies thereof are encountered
Amplitude->
Phase->
When they are similar, but there may be rotation transformation, the corresponding rotation angle is marked +.>
Therefore, the rotation angle needs to be obtained according to the position relation of the pixel points between the tile window image and the sliding window image;
firstly, acquiring a corresponding tile window image and a sliding window image when the translation is larger than a preset translation threshold value, and marking the tile window image and the sliding window image as a similar image group;
then, any pixel point in the tile window image of the similar image group and the cosine similarity maximum value of the frequency domain space vector between all pixel points in the sliding window image of the similar image group are obtained, and two pixel points corresponding to the cosine similarity maximum value of the frequency domain space vector are marked as similar pixel points;
finally, according to the frequency vector of the pixel points obtained by Fourier transformation, the rotation angle between the similar pixel points in the similar image group is obtained:
wherein ,
representing the frequency vector of the corresponding pixel point of the similar pixel point in the tile window image; />
Representing the frequency vector of the corresponding pixel point of the similar pixel point in the sliding window image; sign->
Representing the dot product operation between the vectors,
representing an inverse cosine function.
According to the rotation angles among the similar pixel points, a two-dimensional rotation matrix corresponding to the rotation angles among the similar pixel points is obtained:
wherein ,
represents the rotation angle between similar pixels +.>
The corresponding two-dimensional rotation matrix; />
Representing the rotation angle between similar pixel points; />
Representing a cosine function; />
Representing a sine function.
Step (4), obtaining the average value of the two-dimensional rotation matrix corresponding to all similar pixel points in the similar image group, and marking the average value as a mean matrix
Acquiring rotatability between the tile window image and the sliding window image in the similar image group according to the mean matrix:
wherein ,
representing a two-dimensional rotation matrix corresponding to an nth similar pixel point in the similar image group; />
Representing a mean matrix corresponding to the similar image group; />
Representing a cosine function; />
The standard deviation of the sequences within brackets is shown.
When the two-dimensional rotation matrixes of all similar pixel points in the similar image group are similar, the corresponding rotation performance is larger, the rotation transformation is more likely to exist between the corresponding tile window image and the sliding window image, and the same object is more likely to be corresponding.
Similarity analysis module: according to the translatory property and the rotary property between the tile window image and the sliding window image, the method for obtaining the similarity characteristic between the tile window image and the sliding window image comprises the following steps:
wherein ,
representing similarity features between tile window image and sliding window image,/for>
Representing a translatory property between the tile window image and the sliding window image; />
Representing the rotatability between the tile window image and the sliding window image.
Analyzing the relation situation between the tile window image and the sliding window image according to the similarity characteristics between the tile window image and the sliding window image, and reflecting the translation property of the translation transformation relation between the tile window image and the sliding window image
The larger, at the same time, the rotatability reflecting that the tile window image and the sliding window image have a rotation transformation relationship +.>
The larger the similarity feature between the tile window image and the sliding window image, the larger the similarity feature will be, and the more likely the object reflected between the tile window image and the sliding window image will be the same object.
An image data management module: according to the similarity characteristics between all the tile window images and the sliding window images, intelligent and efficient management of the design images is achieved.
Firstly, carrying out linear normalization on similarity features between all tile window images and sliding window images;
then, obtaining a similar image group which is larger than a preset similarity threshold value in normalized similarity characteristics between all tile window images and sliding window images, and simultaneously obtaining translation transformation and rotation transformation matrixes between the tile window images and the sliding window images in the similar image group;
finally, selecting and deleting the sliding window image in the similar image group, storing the tile window image, reducing repeated storage of the same object in the design image, and realizing fragmentation management of the design image by performing tile segmentation on the design image, wherein when the image corresponding to any one object is called, more convenient use and management are realized, namely intelligent processing and management of garden engineering design related image data are realized;
it should be noted that, the preset similarity threshold is set to 0.8 according to experience, and may be adjusted according to practical situations, which is not limited in this embodiment.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (6)
1. An intelligent processing and management system for garden engineering design data is characterized by comprising the following modules:
an image data acquisition module: obtaining a preprocessed garden engineering design drawing, and recording the preprocessed garden engineering design drawing as a design image;
an image window segmentation module: equally dividing the design image to obtain a plurality of tile window images, constructing a sliding window to traverse the design image, and obtaining a plurality of sliding window images;
a rotation analysis module: acquiring frequency, amplitude, phase and frequency vectors corresponding to all pixel points in all tile window images and sliding window images, marking an array formed by the frequency, amplitude and phase of any pixel point as a frequency domain space vector, and acquiring translatory property between the tile window images and the sliding window images according to the frequency domain space vector of any pixel point in the tile window images and the frequency domain space vector of all pixel points in the sliding window images; obtaining a similar image group according to the size of the translation property, and obtaining a two-dimensional rotation matrix among the pixel points according to the frequency vectors of the pixel points in the similar image group; according to the average value of the corresponding two-dimensional rotation matrixes among all pixel points in the tile window image and the sliding window image and any two-dimensional rotation matrix, the rotatability between the tile window image and the sliding window image is obtained;
similarity analysis module: obtaining similarity characteristics between the tile window image and the sliding window image according to fusion of translativity and rotatableness between the tile window image and the sliding window image;
an image data management module: according to the size of the similarity characteristic between the tile window image and the sliding window image, intelligent processing and management of the design image are realized.
2. The intelligent processing and managing system for garden engineering design data according to claim 1, wherein the steps of equally dividing the design image to obtain a plurality of tile window images, constructing a sliding window to traverse the design image to obtain a plurality of sliding window images, and comprising the following specific steps:
marking the graying garden engineering design drawing as a design image;
carrying out tile segmentation on the design image by utilizing the preset size of a tile window to obtain a plurality of area blocks with the same size, and recording images corresponding to the area blocks as tile window images;
constructing a sliding window with the preset step length as a sliding step length and the window size equal to the preset tile window size, traversing the design image, and marking the image in the sliding window as a sliding window image in the process of traversing the design image by the sliding window.
3. The intelligent processing and managing system for garden engineering design data according to claim 1, wherein the translation is obtained by the following steps:
firstly, processing all tile window images and sliding window images by utilizing Fourier transformation to obtain frequencies, amplitudes and phases corresponding to all pixel points in the tile window images and the sliding window images;
then, the frequency domain space vector of the ith pixel point in the tile window image is recorded as
The frequency domain space vector of the jth pixel point in the sliding window image is marked as +.>
And acquiring the translation between any tile window image and any sliding window image according to the frequency domain space vector:
wherein ,
representing the translatory property between tile window image and sliding window image,/->
Frequency domain space vector representing ith pixel point in tile window image, +.>
A frequency domain space vector representing a j-th pixel point in the sliding window image; />
Representing the acquisition of cosine similarity between vectors in brackets; />
Representing cosine similarity of any pixel point in the acquired tile window image and frequency domain space vectors of all pixel points in the sliding window imageMaximum value.
4. The intelligent processing and managing system for garden engineering design data according to claim 1, wherein the rotatability is obtained by the following method:
step (1), acquiring corresponding tile window images and sliding window images when the translativity is larger than a preset translativity threshold value, and recording the tile window images and the sliding window images as similar image groups;
step (2), acquiring any pixel point in the tile window image of the similar image group, and marking two pixel points corresponding to the cosine similarity maximum value of the frequency domain space vector as similar pixel points between the cosine similarity maximum value of the frequency domain space vector and all pixel points in the sliding window image of the similar image group;
step (3), obtaining the included angle of the frequency vector between the similar pixel points by using an inverse cosine function, recording the included angle as a rotation angle, and obtaining a two-dimensional rotation matrix corresponding to the similar pixel points according to the rotation angle:
wherein ,
represents the rotation angle between similar pixels +.>
The corresponding two-dimensional rotation matrix; />
Representing the rotation angle between similar pixel points; />
Representing a cosine function; />
Representing a sine function;
step (4), obtaining the average value of the two-dimensional rotation matrixes corresponding to all similar pixel points in the similar image group, and marking the average value as the average value matrix corresponding to the similar image group; and acquiring standard deviations of cosine similarity between two-dimensional rotation matrixes corresponding to all similar pixel points and a mean matrix corresponding to the similar image group, and recording the inverted numbers of the standard deviations as the rotatability between the tile window image and the sliding window image in the similar image group.
5. The intelligent processing and managing system for garden engineering design data according to claim 1, wherein the similarity feature comprises the following specific steps:
the method for acquiring the similarity characteristics between the tile window image and the sliding window image in the similar image group comprises the following steps:
wherein ,
representing similarity features between tile window image and sliding window image,/for>
Representing a translatory property between the tile window image and the sliding window image; />
Representing the rotatability between the tile window image and the sliding window image.
6. The intelligent processing and management system for garden engineering design data according to claim 1, wherein the intelligent processing and management for the design image is realized according to the size of the similarity feature between the tile window image and the sliding window image, and the intelligent processing and management method comprises the following specific steps:
firstly, carrying out linear normalization on similarity features between all tile window images and sliding window images;
then, obtaining a similar image group which is larger than a preset similarity threshold value in normalized similarity characteristics between all tile window images and sliding window images, and simultaneously obtaining translation transformation and rotation transformation matrixes between the tile window images and the sliding window images in the similar image group;
and finally, selecting and deleting the sliding window image in the similar image group, storing the tile window image, reducing repeated storage of the same object in the design image, and realizing intelligent processing and management of garden engineering design related image data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310664441.0A CN116386074B (en) | 2023-06-07 | 2023-06-07 | Intelligent processing and management system for garden engineering design data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310664441.0A CN116386074B (en) | 2023-06-07 | 2023-06-07 | Intelligent processing and management system for garden engineering design data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116386074A true CN116386074A (en) | 2023-07-04 |
| CN116386074B CN116386074B (en) | 2023-08-15 |
Family
ID=86971710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310664441.0A Active CN116386074B (en) | 2023-06-07 | 2023-06-07 | Intelligent processing and management system for garden engineering design data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116386074B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556695A (en) * | 2009-05-15 | 2009-10-14 | 广东工业大学 | Image matching method |
| CN102654902A (en) * | 2012-01-16 | 2012-09-05 | 江南大学 | Contour vector feature-based embedded real-time image matching method |
| CN106952257A (en) * | 2017-03-21 | 2017-07-14 | 南京大学 | A kind of curved surface label open defect detection method based on template matches and Similarity Measure |
| CN111507890A (en) * | 2020-04-13 | 2020-08-07 | 北京字节跳动网络技术有限公司 | Image processing method, image processing device, electronic equipment and computer readable storage medium |
| CN114298977A (en) * | 2021-12-08 | 2022-04-08 | 无锡尚实电子科技有限公司 | Complex background image defect detection method based on frequency domain template matching |
| US20220164920A1 (en) * | 2020-11-20 | 2022-05-26 | Xiaomi Technology (Wuhan) Co., Ltd. | Method for processing image, electronic equipment, and storage medium |
| CN115761734A (en) * | 2022-10-29 | 2023-03-07 | 福州大学 | Object pose estimation method based on template matching and probability distribution |
| CN116189194A (en) * | 2023-04-27 | 2023-05-30 | 北京中昌工程咨询有限公司 | Drawing enhancement segmentation method for engineering modeling |
-
2023
- 2023-06-07 CN CN202310664441.0A patent/CN116386074B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556695A (en) * | 2009-05-15 | 2009-10-14 | 广东工业大学 | Image matching method |
| CN102654902A (en) * | 2012-01-16 | 2012-09-05 | 江南大学 | Contour vector feature-based embedded real-time image matching method |
| CN106952257A (en) * | 2017-03-21 | 2017-07-14 | 南京大学 | A kind of curved surface label open defect detection method based on template matches and Similarity Measure |
| CN111507890A (en) * | 2020-04-13 | 2020-08-07 | 北京字节跳动网络技术有限公司 | Image processing method, image processing device, electronic equipment and computer readable storage medium |
| US20220164920A1 (en) * | 2020-11-20 | 2022-05-26 | Xiaomi Technology (Wuhan) Co., Ltd. | Method for processing image, electronic equipment, and storage medium |
| CN114298977A (en) * | 2021-12-08 | 2022-04-08 | 无锡尚实电子科技有限公司 | Complex background image defect detection method based on frequency domain template matching |
| CN115761734A (en) * | 2022-10-29 | 2023-03-07 | 福州大学 | Object pose estimation method based on template matching and probability distribution |
| CN116189194A (en) * | 2023-04-27 | 2023-05-30 | 北京中昌工程咨询有限公司 | Drawing enhancement segmentation method for engineering modeling |
Non-Patent Citations (3)
| Title |
|---|
| LATHA, Y. M.: "Rotation and translation invariant content based color image retrieval", 《WMSCI 2007 : 11TH WORLD MULTI-CONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL V, POST CONFERENCE ISSUE, PROCEEDINGS》 * |
| 唐子成;冯玉田;侯玖廷;: "基于图像的智能燃气表自动检测系统设计", 电子测量技术, no. 16 * |
| 李艳: "在线掌纹匹配技术的研究", 《中国优秀硕士学位论文全文数据库(信息科技辑)》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116386074B (en) | 2023-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hassanein et al. | A survey on Hough transform, theory, techniques and applications | |
| CN102508917B (en) | Multi-dimensional object robust high-speed retrieval and positioning method for some feature images | |
| CN102541954A (en) | Method and system for searching trademarks | |
| WO2023035119A1 (en) | Method and system for extracting hyperbolic wave from ground penetrating radar image | |
| CN115267724B (en) | Position re-identification method of mobile robot capable of estimating pose based on laser radar | |
| Tekeste et al. | Advanced local binary patterns for remote sensing image retrieval | |
| CN111062321A (en) | SAR detection method and system based on deep convolutional network | |
| CN111507340B (en) | Target point cloud data extraction method based on three-dimensional point cloud data | |
| Obulesu et al. | Content based image retrieval using multi motif co-occurrence matrix | |
| CN116386074B (en) | Intelligent processing and management system for garden engineering design data | |
| Ullah et al. | Gender recognition from face images with dyadic wavelet transform and local binary pattern | |
| CN1790374A (en) | Face recognition method based on template matching | |
| Yin et al. | A new similarity measurement method for time series based on image fusion of recurrence plots and wavelet scalogram | |
| Jobay et al. | Quantum inspired shape representation for content based image retrieval | |
| Ju et al. | Image segmentation based on the HSI color space and an improved mean shift | |
| CN103150726B (en) | A kind of image partition method based on Two-Dimensional Generalized S-transformation | |
| Han et al. | Iris recognition based on a novel normalization method and contourlet transform | |
| CN112667842B (en) | Image texture retrieval method | |
| Rakshit | New curvelet features for image indexing and retrieval | |
| Chen et al. | Fast texture feature extraction method based on segmentation for image retrieval | |
| CN112241759B (en) | Pyramid decomposition method and system for multi-scale geometric analysis | |
| CN109784195B (en) | Fingerprint identification method and system for enterprise fingerprint card punching | |
| Pang et al. | Image Quick Search Based on F-shift Transformation | |
| Brar et al. | Analysis of rotation invariant template matching techniques for trademarks | |
| CN117115463A (en) | Neural network input image sampling method based on wavelet decomposition |
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 |