Light steel keel standard construction rechecking method based on real mold superposition
By acquiring and comparing outline and projection images of light steel keel, clustering and computational methods were used to solve the problem of inaccurate judgments caused by reliance on worker experience, thus achieving higher accuracy in construction quality assessment.
Patent Information
- Application Number
- CN202510700668.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-28
- Publication Date
- 2025-09-23
AI Technical Summary
In existing technologies, the assessment of the construction quality of light steel keel relies too heavily on workers' experience, resulting in low accuracy.
By acquiring the outline image of the keel to be evaluated and the projected image of the keel model, clustering and comparison are performed. The final evaluation result is output using Hamming distance, overlapping area and multidimensional vector calculation.
It improves the accuracy of judging the construction quality of light steel keel, reduces the reliance on workers' experience, and achieves higher judgment accuracy.
Smart Images

Figure CN120689640A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of keel construction, in particular to a method for reviewing construction specifications of light steel keels based on real mold superposition. Background Art
[0002] The keel is a building material used to support shapes and fix structures in the construction industry. It is more widely used in the construction industry. After the keel is tied or fixed, it is generally judged by experienced craftsmen through visual inspection to see if the keel is basically consistent with the model. This method relies too much on manual experience and the accuracy of the judgment is relatively low. Summary of the Invention
[0003] In view of this, the purpose of the present invention is to provide a light steel keel standard construction review method based on real mold superposition, which changes the problem of over-reliance on workers' experience and has a higher accuracy of judgment than manual judgment.
[0004] The present invention provides a method for reviewing the construction specifications of a light steel keel based on real mold superposition, comprising the following steps:
[0005] Obtaining an outline image of the keel to be evaluated and a projection image of the keel model to form an image set;
[0006] performing clustering processing on the contour pictures and the projection pictures in the picture set to obtain a plurality of clustering result sets, wherein the clustering result sets include the contour pictures and the projection pictures;
[0007] The contour images and projection images in the clustering result set are compared to obtain the final evaluation results.
[0008] In one embodiment, obtaining a contour image of the keel to be evaluated further includes:
[0009] Obtaining initial images of the keel to be evaluated in order;
[0010] Obtain the outline image corresponding to the initial image.
[0011] In one embodiment, obtaining a projection image of the keel model further includes:
[0012] Get the keel model;
[0013] Obtain several projection images according to the preset projection method.
[0014] In one embodiment, clustering the contour pictures and the projection pictures in the picture set to obtain a plurality of clustering result sets, wherein the clustering result sets include the contour pictures and the projection pictures, further comprises:
[0015] Obtaining multidimensional vectors corresponding to the contour image and the projection image;
[0016] Calculating the Hamming distance between the multidimensional vector of the contour image and the multidimensional vector of the projection image;
[0017] The contour image and the projection image are clustered according to the Hamming distance to obtain a plurality of clustering result sets.
[0018] In one embodiment, comparing the contour image and the projection image in the clustering result set to obtain a final evaluation result further includes:
[0019] Aligning the outline image and the projection image;
[0020] Calculating the overlapping area between the contour image and the projection image;
[0021] Obtain preliminary assessment results based on the overlapping area;
[0022] The final evaluation result is obtained by calculation based on several related preliminary evaluation results.
[0023] In one embodiment, obtaining a preliminary evaluation result based on the overlapped area further includes:
[0024] Obtaining the area of the projected image;
[0025] The ratio of the overlapped area to the area of the projected image is calculated to obtain a preliminary evaluation result.
[0026] In one embodiment, the calculating based on the plurality of related preliminary evaluation results to obtain a final evaluation result further includes:
[0027] Obtaining preliminary evaluation results related to each other based on the multidimensional vectors;
[0028] calculating an average of the relevant preliminary assessment results;
[0029] The average value is compared with a corresponding threshold value to obtain the final evaluation result.
[0030] The method for reviewing the construction specifications of light steel keels based on real mold superposition provided by the present invention classifies and compares the obtained contour image of the keel to be evaluated and the projection image of the keel model, and outputs the final evaluation result based on the comparison, thereby changing the problem of over-reliance on workers' experience. Compared with manual judgment, the judgment accuracy is higher. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.
[0032] Figure 1 This is a structural schematic diagram of the standard construction review method for light steel keels based on real mold superposition provided by the present invention. DETAILED DESCRIPTION
[0033] Specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the described embodiments are merely some, and not all, of the embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the description of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.
[0034] In the description of the present invention, unless otherwise specified or limited, the terms "disposed," "installed," and "connected" should be understood broadly. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; and direct or indirect connections through an intermediary. Those skilled in the art will understand the specific meanings of these terms based on the specific circumstances.
[0035] The directions or positional relationships indicated by terms such as "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inside" and "outside" are based on the directions or positional relationships shown in the accompanying drawings, or are the directions or positional relationships in which the inventive product is usually placed when in use. They are only for the convenience and simplification of description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operate in a specific direction. Therefore, they should not be understood as limiting the present invention.
[0036] The terms "first," "second," "third," etc. are merely used to distinguish between elements of similar nature and do not indicate or imply relative importance or a particular order.
[0037] The terms "comprises," "comprising," or any other variations thereof, are intended to cover a non-exclusive inclusion of elements other than the listed elements and may also include additional elements not specifically listed.
[0038] See also Figure 1 The method for reviewing the construction specifications of light steel keels based on real mold superposition provided by the present invention includes the following steps:
[0039] S1, obtaining an outline image of the keel to be evaluated and a projection image of the keel model to form an image set.
[0040] It is understandable that the above steps may further include:
[0041] S101, obtaining initial images of the keel to be evaluated in sequence.
[0042] It can be understood that the order in this embodiment refers to obtaining images of all surfaces of the keel to be evaluated, ie, initial images, in a certain order.
[0043] S102: Obtain a contour image corresponding to the initial image.
[0044] It can be known that some edge algorithms can be used to obtain the wheel buckle image corresponding to the initial image.
[0045] S2, performing clustering processing on the contour images and projection images in the image set to obtain a plurality of clustering result sets, wherein the clustering result sets include the contour images and projection images.
[0046] It is understandable that the above steps may further include:
[0047] S201, obtaining a keel model.
[0048] It can be understood that the above-mentioned keel to be evaluated is constructed based on the keel model.
[0049] S202: Obtain a plurality of projection images according to a preset projection method.
[0050] It is understandable that projection processing is performed on each surface of the keel model to obtain projection images of each surface.
[0051] S203, obtaining multi-dimensional vectors corresponding to the contour image and the projection image.
[0052] It can be understood that the feature information of the contour image is obtained and represented by a multi-dimensional vector.
[0053] S204, calculating the Hamming distance between the multidimensional vector of the contour image and the multidimensional vector of the projection image;
[0054] S205 , clustering the contour image and the projection image according to the Hamming distance to obtain several clustering result sets.
[0055] It can be understood that when the value of the Hamming distance is less than the corresponding threshold, it can be considered that the contour image and the projection image are images of the same plane. When the value of the Hamming distance is less than the corresponding threshold, it can be considered that the contour image and the projection image are not images of the same plane. Each contour image has a corresponding projection image, and the clustering result set includes a contour image and a projection image.
[0056] S3, compare the contour images and projection images in the clustering result set to obtain the final evaluation results.
[0057] It is understandable that the above steps may further include:
[0058] S301: Align the outline image and the projection image.
[0059] It can be understood that the alignment method can be to select several feature points on the contour image, and correspondingly select corresponding feature points on the projection image, and correspond the feature points of the contour image with the feature points of the projection image, so as to achieve alignment of the contour image and the projection image.
[0060] S302: Calculate the overlapping area between the contour image and the projection image.
[0061] It is understandable that only the overlapping area between the contour image and the projection image is calculated, and the overlapping area is the same portion between the contour image and the projection image by default.
[0062] S303: Obtain a preliminary evaluation result based on the overlapping area.
[0063] S303a, obtaining the area of the projected image.
[0064] It can be understood that the area of the projected image is the benchmark. The area of the projected image refers to the total area of each feature on the projected image. The grayscale value of the feature is different from the grayscale value of the blank area, and the area of the blank area is not included.
[0065] S303b, calculating the ratio of the overlapped area to the area of the projected image to obtain a preliminary evaluation result.
[0066] It can be understood that the ratio of the overlapping area to the area of the projected image can represent the probability that the two are identical, and this result is only a preliminary evaluation result of one of the surfaces.
[0067] S304, calculating based on several relevant preliminary evaluation results to obtain a final evaluation result.
[0068] S304a, obtaining preliminary evaluation results of mutual correlation based on the multi-dimensional vectors.
[0069] It is understandable that all preliminary evaluation results belonging to the same keel to be evaluated are obtained based on the feature information.
[0070] S304b, calculating the average value of the relevant preliminary evaluation results;
[0071] S304c, comparing the average value with the corresponding threshold to obtain a final evaluation result.
[0072] It can be seen that when the average value is not less than the corresponding threshold value, it is assumed that the keel to be evaluated meets the quality requirements; when the average value is less than the corresponding threshold value, it is assumed that the keel to be evaluated does not meet the quality requirements.
[0073] From the above description, it can be known that the light steel keel standard construction review method based on real mold superposition provided by the present invention classifies and compares the obtained contour image of the keel to be evaluated and the projection image of the keel model, and outputs the final evaluation result based on the comparison, which changes the problem of over-reliance on workers' experience, and has a higher accuracy of judgment than manual judgment.
[0074] The foregoing description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be readily conceived by a person skilled in the art within the technical scope disclosed herein are intended to be encompassed within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.
Claims
1. A method for reviewing the construction specifications of light steel keels based on real mold superposition, characterized in that: The steps include: Obtaining an outline image of the keel to be evaluated and a projection image of the keel model to form an image set; performing clustering processing on the contour pictures and the projection pictures in the picture set to obtain a plurality of clustering result sets, wherein the clustering result sets include the contour pictures and the projection pictures; The contour images and projection images in the clustering result set are compared to obtain the final evaluation results.
2. The method for reviewing the construction specifications of light steel keels based on real mold superposition according to claim 1 is characterized in that: The step of obtaining the outline image of the keel to be evaluated further includes: Obtaining initial images of the keel to be evaluated in order; Obtain the outline image corresponding to the initial image.
3. The method for reviewing the construction specifications of light steel keels based on real mold superposition according to claim 1 is characterized in that: The obtaining of the projection image of the keel model further includes: Get the keel model; Obtain several projection images according to the preset projection method.
4. The method for reviewing the construction specifications of light steel keels based on real mold superposition according to claim 3 is characterized in that: The clustering process is performed on the contour pictures and the projection pictures in the picture set to obtain a plurality of clustering result sets, wherein the clustering result sets include the contour pictures and the projection pictures, further comprising: Obtaining multidimensional vectors corresponding to the contour image and the projection image; Calculating the Hamming distance between the multidimensional vector of the contour image and the multidimensional vector of the projection image; The contour image and the projection image are clustered according to the Hamming distance to obtain a plurality of clustering result sets.
5. The method for reviewing the construction specifications of light steel keels based on real mold superposition according to claim 4 is characterized in that: The comparing the contour image and the projection image in the clustering result set to obtain a final evaluation result further includes: Aligning the outline image and the projection image; Calculating the overlapping area between the contour image and the projection image; Obtain preliminary assessment results based on the overlapping area; The final evaluation result is obtained by calculation based on several related preliminary evaluation results.
6. The method for reviewing the construction specifications of light steel keels based on real mold superposition according to claim 5 is characterized in that: The obtaining of a preliminary evaluation result according to the overlapped area further includes: Obtaining the area of the projected image; The ratio of the overlapped area to the area of the projected image is calculated to obtain a preliminary evaluation result.
7. The method for reviewing the construction specifications of light steel keels based on real mold superposition according to claim 5 is characterized in that: The calculation based on the several related preliminary evaluation results to obtain the final evaluation result further includes: Obtaining preliminary evaluation results related to each other based on the multidimensional vectors; calculating an average of the relevant preliminary assessment results; The average value is compared with a corresponding threshold value to obtain the final evaluation result.