CN113657925A - Civil engineering cost management method based on artificial intelligence - Google Patents
Civil engineering cost management method based on artificial intelligence Download PDFInfo
- Publication number
- CN113657925A CN113657925A CN202110854449.4A CN202110854449A CN113657925A CN 113657925 A CN113657925 A CN 113657925A CN 202110854449 A CN202110854449 A CN 202110854449A CN 113657925 A CN113657925 A CN 113657925A
- Authority
- CN
- China
- Prior art keywords
- construction
- thermodynamic diagram
- simulated
- acquiring
- area
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- 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
- G06T2207/30241—Trajectory
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention relates to the technical field of artificial intelligence, in particular to a civil engineering cost management method based on artificial intelligence. The method comprises the steps of obtaining a construction area through a panoramic overlook image of a construction scene when the construction is not carried out, and obtaining an initial simulation thermodynamic diagram of the construction area; acquiring an actual thermodynamic diagram of an actual panoramic thermodynamic image acquired in real time; and judging the construction condition according to the distance between the first pixel points corresponding to the maximum heat value in the initial simulation thermodynamic diagram and the actual thermodynamic diagram, and adjusting the engineering cost according to the efficacy deviation and the position deviation when the abnormal construction is confirmed. The method can be used for quickly and effectively analyzing construction abnormity only according to the simulated thermodynamic diagram and the actual thermodynamic diagram of the construction area, and further accurately adjusting the engineering cost through the acquired abnormal information, so that the error of engineering cost adjustment is reduced.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a civil engineering cost management method based on artificial intelligence.
Background
The engineering cost has the problems of heavy design and light management, and aiming at the cost management, the prior art generally monitors a potential abnormal source in real time in the construction process so as to trace the cause of the engineering progress deviation and further adjust the engineering cost according to the deviation.
In practice, the inventors found that the above prior art has the following disadvantages: the fact that a plurality of monitoring ports are needed for real-time monitoring of potential abnormal sources can lead to cost increase, partial abnormal conditions are difficult to directly sense through a monitoring mode, limitation on the monitoring ports is large, tracing to abnormal conditions of personnel in a construction process is difficult to conduct under the condition that a fixed-point monitoring mode is not adopted, and cost adjustment cannot be accurately conducted.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a civil engineering cost management method based on artificial intelligence, which adopts the following technical scheme:
one embodiment of the invention provides a civil engineering cost management method based on artificial intelligence, which comprises the following specific steps:
acquiring a panoramic overhead image of a construction scene when not constructed to acquire a construction area; taking a construction starting position as a center, constructing an elliptical area according to the gravity center and the shape direction of the construction area, taking a part containing the construction area in the elliptical area as an area to be processed, and acquiring an initial simulation thermodynamic diagram of the area to be processed;
acquiring an actual panoramic overhead image of the construction site in real time, and acquiring an actual thermodynamic diagram of the actual panoramic overhead image; respectively obtaining first pixel points corresponding to the maximum heat value in the initial simulation thermodynamic diagram and the actual thermodynamic diagram, and judging the construction condition according to the distance between the first pixel points;
when the construction is confirmed to be abnormal, acquiring a simulated thermodynamic diagram corresponding to the distance equal to a distance threshold, and acquiring an efficacy deviation according to the simulated thermodynamic diagram and the construction efficacy of the initial simulated thermodynamic diagram; if the efficacy deviation cannot be obtained, obtaining position deviation according to abnormal pixel points in the simulated thermodynamic diagram;
and adjusting the construction cost according to the efficacy deviation and the position deviation.
Preferably, the method for acquiring an initial simulated thermodynamic diagram of the region to be processed includes:
constructing a covariance matrix from the major and minor axes of the elliptical region and the shape direction;
constructing a two-dimensional Gaussian probability density function of a space dimension by using the covariance matrix and the center, and obtaining a first heat value of each pixel point in the construction area according to the two-dimensional Gaussian probability density function to obtain a first simulated thermodynamic diagram;
and obtaining a second simulated thermodynamic diagram of the area to be processed according to the first simulated thermodynamic diagram.
Preferably, after the second simulated thermodynamic diagram is obtained, the method for optimizing the second simulated thermodynamic diagram includes:
acquiring a second pixel point which does not belong to the construction area in the area to be processed based on the second simulated thermodynamic diagram, and optimizing the first thermal value of the pixel point in the construction area according to the first thermal value of the second pixel point to obtain a third simulated thermodynamic diagram;
constructing a one-dimensional Gaussian distribution function of a time dimension according to the sampling time, the construction efficacy, the number of construction people and a second thermal value of the third simulation thermodynamic diagram of the actual panoramic overlook image;
and updating the second thermal force value of each pixel point in the third simulated thermodynamic diagram by using the one-dimensional Gaussian distribution function to obtain an initial fourth simulated thermodynamic diagram.
Preferably, the method for updating the second thermal force value of each pixel point in the third simulated thermodynamic diagram by using the one-dimensional gaussian distribution function to obtain an initial fourth simulated thermodynamic diagram includes:
updating the second heat value of each pixel point by using the one-dimensional Gaussian distribution function based on each time point between the initial sampling time and the sampling time of the actual panoramic image, so as to obtain an updated simulated thermodynamic diagram corresponding to each time point;
and thermally superposing the updated second thermal value of the pixel point corresponding to each time point based on the updated simulated thermodynamic diagram to obtain the initial fourth simulated thermodynamic diagram corresponding to the sampling time.
Preferably, the method for correcting the covariance matrix includes:
and acquiring the construction track type of the construction area, and correcting the covariance matrix according to the construction track type.
Preferably, the method for judging the construction condition according to the distance between the first pixel points comprises the following steps:
acquiring Euclidean distance between the first pixel points, and determining that construction is normal when the Euclidean distance is smaller than or equal to the distance threshold; otherwise, confirming that the construction is abnormal.
Preferably, when both the efficacy deviation and the position deviation cannot be obtained, it is determined that both the efficacy deviation and the position deviation exist in the construction area.
Preferably, the method for acquiring the center of gravity of the construction area includes:
and acquiring a first moment of the construction area, and taking the first moment as the gravity center.
Preferably, the method for acquiring the shape direction of the construction area includes:
and acquiring a second moment of the construction area, and taking the second moment as the shape direction.
The embodiment of the invention at least has the following beneficial effects: the method can be used for quickly and effectively analyzing construction abnormity only according to the simulated thermodynamic diagram and the actual thermodynamic diagram of the construction area, and further accurately adjusting the engineering cost through the acquired abnormal information, so that the error of engineering cost adjustment is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart showing steps of a civil engineering cost management method based on artificial intelligence according to an embodiment of the present invention;
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description, the structure, the features and the functions of the method for managing civil engineering construction cost based on artificial intelligence according to the present invention will be made with reference to the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
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 concrete scheme of the civil engineering cost management method based on artificial intelligence provided by the invention is concretely described below with reference to the attached drawings.
The embodiment of the invention aims at the following specific scenes: the construction cost progress management under the civil engineering scene mainly analyzes around the construction process management in the whole process construction cost management, the actual scene takes a single-layer scene as an analysis object, and the single-layer scene such as single-layer floor construction, road construction and the like can be similar to the scene of plane construction operation; the method comprises the steps that an RGB camera is arranged in a plane scene for image acquisition, the RGB camera is arranged at a high position and is fixed in pose, a panoramic image can be acquired by arranging a plurality of RGB cameras in an image splicing mode, and a panoramic overlook image of the plane scene can be acquired by subsequent processing through default
Referring to fig. 1, a flowchart of steps of a civil engineering cost management method based on artificial intelligence according to an embodiment of the present invention is shown, where the method specifically includes the following steps:
s001, acquiring a panoramic overlook image of a construction scene when the construction is not carried out so as to acquire a construction area; and taking the construction starting position as a center, constructing an elliptical area according to the gravity center and the shape direction of the construction area, taking the part of the elliptical area containing the construction area as an area to be processed, and acquiring a simulated thermodynamic diagram of the area to be processed.
Specifically, under the condition of no construction, the RGB camera is used for collecting a panoramic overlook image of a construction scene, the construction area of the obtained panoramic overlook image is divided, the pose of the camera is fixed, so that the construction area is manually divided only by the known construction area in the cost design, and the divided construction area is stored in a binary image mode, namely the pixel value of the pixel point of the construction area is set to be 1, and the pixel values of other pixel points are set to be 0.
And acquiring construction cost design information comprising the number of construction persons, construction efficacy and construction starting position, wherein the construction efficacy is the workload which can be completed by a constructor in one day. Processing the binary image of the construction area, acquiring a first moment of the construction area, and taking the first moment as the gravity center; and acquiring a second moment of the construction area, and taking the second moment as the shape direction theta. In order to ensure that the construction area can be covered as much as possible, an elliptical area is constructed based on the construction area, and the construction method comprises the following steps: obtaining a major axis a and a minor axis b of the elliptical area according to the gravity center and the shape direction of the construction area; at the construction starting position (x)s，ys) An elliptical region is constructed for the center, combining the major and minor axes. Since the straight line where the minor axis is located equally divides the elliptical region, a portion of the elliptical region including the construction region is set as a region to be processed.
Constructing a covariance matrix from the major and minor axes of the elliptical region and the shape direction, the covariance matrix being
Two-dimensional Gaussian probability density function for constructing space dimension by using covariance matrix and center
Obtaining a first heat value of each pixel point in a construction area according to a two-dimensional Gaussian probability density function to obtain a first simulated thermodynamic diagram; and reserving the part of the area to be processed in the first simulated thermodynamic diagram as a second simulated thermodynamic diagram, and setting the thermal value of the pixel points of other areas as 0.
Because the region to be processed has spatial redundancy relative to the construction region, and the position corresponding to the redundancy does not usually have the situation that a constructor stays in the construction process, the second simulated thermodynamic diagram is optimized to improve the representation capability and accuracy of the second simulated thermodynamic diagram, and the optimization method of the second simulated thermodynamic diagram is as follows:
1) and based on the second simulated thermodynamic diagram, acquiring a second pixel point which does not belong to the construction area in the to-be-processed area, and optimizing a first thermal value of the pixel point in the construction area according to the first thermal value of the second pixel point to obtain a third simulated thermodynamic diagram.
As an example, traversing row by row from a short axis included in the region to be processed along the shape direction, taking any row of pixel points as an example, acquiring all second pixel points in the row, which belong to the region to be processed but do not belong to the construction region, uniformly distributing the sum of the first thermal values of the pixel points to the pixel points in the row, which belong to the construction region, and setting the first thermal values of the second pixel points to be 0; after the to-be-processed area is traversed, the maximum thermal value in the construction area is obtained and is zoomed to 1, then the zoom scale can be obtained, the thermal values of other pixel points in the construction area are zoomed in the same size by utilizing the zoom scale, and then a third simulation thermodynamic diagram of the to-be-processed area is obtained.
It should be noted that, if there is any column of pixels belonging to the second pixel, the first thermal value of the column of pixels is directly set to 0.
2) And constructing a one-dimensional Gaussian distribution function of a time dimension by the acquisition time, the construction efficiency, the number of construction people and a second thermal value of a third simulation thermodynamic diagram of the panoramic overlook image.
Specifically, the formula of the one-dimensional gaussian distribution function is:
wherein epsilon is an expected construction period corresponding to the construction cost; μ is the mean, set to 0; t is the adjusted sampling time, and t is t' -alpha (1-h)i) Obtaining, wherein h1A second heat value of the ith pixel point in the third simulated thermodynamic diagram; t' is the sampling time of the actual panoramic overhead image; alpha is an adjustment coefficient obtained based on the construction efficiency S and the number of persons under construction n, i.e.
And m is the number of pixel points in the construction area.
3) On the basis of each time point between the initial sampling time of the actual panoramic overlook image and the sampling time, updating the second heat force value of each pixel point by using a one-dimensional Gaussian distribution function, and further obtaining an updated simulated thermodynamic diagram corresponding to each time point, and on the basis of the updated simulated thermodynamic diagram of each time point, performing thermal superposition on the updated second heat force value of the pixel point corresponding to each time point to obtain an initial fourth simulated thermodynamic diagram corresponding to the sampling time, wherein a thermal superposition formula is as follows:
wherein the content of the first and second substances,
a forgetting coefficient, which is usually set to 0.95; z' is a heat value superposed at the current moment; z is the thermodynamic value of the previous moment; z is the thermodynamic value at the present moment.
It should be noted that the initial fourth simulated thermodynamic diagram can represent the stay probability of the constructor at each moment.
S002, acquiring an actual panoramic overlook image of the construction site in real time, and acquiring an actual thermodynamic diagram of the actual panoramic overlook image; and respectively obtaining first pixel points corresponding to the maximum heat value in the initial simulation thermodynamic diagram and the actual thermodynamic diagram, and judging the construction condition according to the distance between the first pixel points.
Specifically, an actual panoramic overlook image of a construction scene is collected in real time by an RGB camera, and the actual panoramic overlook image is subjected to a key point prediction network to obtain a corresponding actual thermodynamic diagram.
Preferably, in the embodiment of the invention, the key points of the steps of the constructors are used as labels.
Because the initial fourth simulated thermodynamic diagram can only represent the stop probability of each constructor when no actual construction track exists, the method for correcting the initial fourth simulated thermodynamic diagram based on the construction track type corresponding to the actual thermodynamic diagram in the embodiment of the present invention includes: in the embodiment of the invention, the construction track type of the construction area is prior transverse S-shaped operation and longitudinal S-shaped operation, wherein the direction parallel to the shape is transverse, and the direction vertical to the shape is longitudinal. If the type of the construction track is transverse, the fourth simulated thermodynamic diagram does not need to be corrected; if the construction track type is vertical, the covariance matrix in the step S001 is changed to
And further acquiring an initial fourth simulation thermodynamic diagram by using the changed covariance matrix.
The type of the construction trajectory can be determined by the change of the real-time thermodynamic diagram.
Further, first pixel points corresponding to the maximum heat value in the initial fourth simulated thermodynamic diagram and the actual thermodynamic diagram are respectively extracted, the Euclidean distance between the first pixel points is calculated, and when the Euclidean distance is smaller than or equal to a distance threshold value, the construction is determined to be normal; otherwise, confirming that the construction is abnormal.
Step S003, when the construction is confirmed to be abnormal, acquiring a simulated thermodynamic diagram corresponding to the distance equal to the distance threshold, and acquiring an efficacy deviation according to the construction efficacy of the simulated thermodynamic diagram and the initial simulated thermodynamic diagram; and if the efficacy deviation cannot be obtained, obtaining the position deviation according to the abnormal pixel points in the simulated thermodynamic diagram.
Specifically, when it is determined that the construction is abnormal, the one-dimensional gaussian distribution function of the time dimension is traced to the source to analyze the change of the construction efficacy, that is, the changed construction efficacy and the corresponding start time of the change are obtained, and then the analysis method of the change of the construction efficacy is as follows: based on the known sampling time and the construction efficacy before the change of the actual thermodynamic diagram, obtaining an unknown construction efficacy after the change and a fourth simulated thermodynamic diagram corresponding to the change starting moment, and enabling the Euclidean distance between the fourth simulated thermodynamic diagram and a first pixel point corresponding to the maximum heat value in the actual thermodynamic diagram to be equal to a distance threshold; under the condition that the sampling time of the known actual thermodynamic diagram is fixed, the same fourth simulated thermodynamic diagrams may be generated at different changed construction efficacies and different change starting moments, so that two frames of actual thermodynamic diagrams at different sampling moments need to be traced, namely two unknown fourth simulated thermodynamic diagrams generated at the changed construction efficacies and the change starting moments are obtained according to the sampling moments and the construction efficacies before change corresponding to the two known different actual thermodynamic diagrams, and the Euclidean distance between the two fourth simulated thermodynamic diagrams and the first pixel point corresponding to the maximum heat value in the actual thermodynamic diagram is equal to the distance threshold value and is used as a limiting condition to search two unknown parameters of the changed construction efficacies and the change starting moments; and if the search is successful, confirming the change condition of the construction efficacy, and further obtaining the efficacy deviation by using the changed construction efficacy and the construction efficacy of the initial fourth simulated thermodynamic diagram.
When the efficacy deviation cannot be obtained, tracing the two-dimensional Gaussian probability density function of the space dimension to analyze the construction abnormal points, namely obtaining changed pixel points and the change degree of the pixel points, wherein the analysis method of the construction abnormal points comprises the following steps: acquiring a corresponding fourth simulated thermodynamic diagram based on the known sampling time of the actual thermodynamic diagram and the unknown position and degree of the changed pixel point, and enabling the Euclidean distance between the fourth simulated thermodynamic diagram and a first pixel point corresponding to the maximum heat value in the actual thermodynamic diagram to be equal to a distance threshold; under the condition that the sampling time of the actual thermodynamic diagram is fixed, the pixel point positions and the change degrees of different changes may generate the same fourth simulated thermodynamic diagram, so that two frames of actual thermodynamic diagrams at different sampling times are required to trace the source, namely two fourth simulated thermodynamic diagrams are generated according to the sampling time, the changed pixel point positions and the change degrees corresponding to the two frames of different actual thermodynamic diagrams, and the Euclidean distance between the first pixel points corresponding to the maximum thermodynamic values of the two fourth simulated thermodynamic diagrams and the actual thermodynamic diagram is equal to a distance threshold value to be used as a limiting condition to search two unknown parameters of the changed pixel point positions and the change degrees; if the search is successful, the occurrence of construction abnormal points is confirmed, and the obtained changed pixel point position and the obtained change degree are used as the position deviation.
In addition, the method for determining the efficacy deviation and the position deviation is only used for determining that the efficacy deviation and the position deviation exist in the construction area at the same time if the efficacy deviation or the position deviation cannot be obtained under the condition that the efficacy change and the construction abnormal point exist once.
And step S004, adjusting the construction cost according to the efficacy deviation and the position deviation.
Specifically, the acquired deviation information is directly transmitted to a construction cost terminal, and the construction cost terminal performs reasonable engineering construction cost management according to the deviation information, wherein the deviation information comprises efficacy deviation and position deviation.
If the fact that the construction area has the effect deviation and the position deviation at the same time is confirmed, a project cost worker needs to be dispatched to a construction site to adjust the project cost according to actual conditions.
It should be noted that, in the embodiment of the present invention, the engineering cost is adjusted according to the abnormal condition of the construction efficacy of the constructor during the construction process, and the implementer of the abnormal condition caused by other factors such as the price change of the work material and the environmental factor can still adjust the construction cost by using the existing cost management method.
In summary, the embodiment of the present invention provides a civil engineering cost management method based on artificial intelligence, in which a construction area is obtained by using a panoramic overhead image of a construction scene when the construction is not performed, and an initial simulation thermodynamic diagram of the construction area is obtained; acquiring an actual thermodynamic diagram of an actual panoramic thermodynamic image acquired in real time; and judging the construction condition according to the distance between the first pixel points corresponding to the maximum heat value in the initial simulation thermodynamic diagram and the actual thermodynamic diagram, and adjusting the engineering cost according to the efficacy deviation and the position deviation when the abnormal construction is confirmed. The method can be used for quickly and effectively analyzing construction abnormity only according to the simulated thermodynamic diagram and the actual thermodynamic diagram of the construction area, and further accurately adjusting the engineering cost through the acquired abnormal information, so that the error of engineering cost adjustment is reduced.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A civil engineering cost management method based on artificial intelligence is characterized by comprising the following steps:
acquiring a panoramic overhead image of a construction scene when not constructed to acquire a construction area; taking a construction starting position as a center, constructing an elliptical region according to the gravity center and the shape direction of the construction region, taking a part of the elliptical region containing the construction region as a region to be processed, and acquiring the initial simulation thermodynamic diagram of the region to be processed;
acquiring an actual panoramic overhead image of the construction site in real time, and acquiring an actual thermodynamic diagram of the actual panoramic overhead image; respectively obtaining first pixel points corresponding to the maximum heat value in the initial simulation thermodynamic diagram and the actual thermodynamic diagram, and judging the construction condition according to the distance between the first pixel points;
when the construction is confirmed to be abnormal, acquiring a simulated thermodynamic diagram corresponding to the distance equal to a distance threshold, and acquiring an efficacy deviation according to the simulated thermodynamic diagram and the construction efficacy of the initial simulated thermodynamic diagram; if the efficacy deviation cannot be obtained, obtaining position deviation according to abnormal pixel points in the simulated thermodynamic diagram;
and adjusting the construction cost according to the efficacy deviation and the position deviation.
2. The method of claim 1, wherein the method of obtaining an initial simulated thermodynamic diagram of the area to be treated comprises:
constructing the covariance matrix from the major and minor axes of the elliptical region and the shape direction;
constructing a two-dimensional Gaussian probability density function of a space dimension by using the covariance matrix and the center, and obtaining a first heat value of each pixel point in the construction area according to the two-dimensional Gaussian probability density function to obtain a first simulated thermodynamic diagram;
and obtaining a second simulated thermodynamic diagram of the area to be processed according to the first simulated thermodynamic diagram.
3. The method of claim 2, wherein after obtaining the second simulated thermodynamic diagram, the method of optimizing the second simulated thermodynamic diagram comprises:
acquiring a second pixel point which does not belong to the construction area in the area to be processed based on the second simulated thermodynamic diagram, and optimizing the first thermal value of the pixel point in the construction area according to the first thermal value of the second pixel point to obtain a third simulated thermodynamic diagram;
constructing a one-dimensional Gaussian distribution function of a time dimension according to the sampling time, the construction efficacy, the number of construction people and a second thermal value of the third simulation thermodynamic diagram of the actual panoramic overlook image;
and updating the second thermal force value of each pixel point in the third simulated thermodynamic diagram by using the one-dimensional Gaussian distribution function to obtain an initial fourth simulated thermodynamic diagram.
4. The method of claim 3, wherein the step of updating the second thermal force value for each pixel in the third simulated thermodynamic diagram with the one-dimensional Gaussian distribution function to obtain an initial fourth simulated thermodynamic diagram comprises:
updating the second heat value of each pixel point by using the one-dimensional Gaussian distribution function based on each time point between the initial sampling time and the sampling time of the actual panoramic image, so as to obtain an updated simulated thermodynamic diagram corresponding to each time point;
and thermally superposing the updated second thermal value of the pixel point corresponding to each time point based on the updated simulated thermodynamic diagram to obtain the initial fourth simulated thermodynamic diagram corresponding to the sampling time.
5. The method of claim 2, wherein the method for modifying the covariance matrix comprises:
and acquiring the construction track type of the construction area, and correcting the covariance matrix according to the construction track type.
6. The method of claim 1, wherein the method for determining the construction condition according to the distance between the first pixel points comprises:
acquiring Euclidean distance between the first pixel points, and determining that construction is normal when the Euclidean distance is smaller than or equal to the distance threshold; otherwise, confirming that the construction is abnormal.
7. The method of claim 1, wherein the efficacy deviation and the location deviation are determined to be present in the construction area simultaneously when neither of the efficacy deviation and the location deviation is available.
8. The method of claim 1, wherein the method of obtaining the center of gravity of the construction area comprises:
and acquiring a first moment of the construction area, and taking the first moment as the gravity center.
9. The method as claimed in claim 1, wherein the method for obtaining the shape direction of the construction area comprises:
and acquiring a second moment of the construction area, and taking the second moment as the shape direction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110854449.4A CN113657925B (en) | 2021-07-28 | 2021-07-28 | Civil engineering cost management method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110854449.4A CN113657925B (en) | 2021-07-28 | 2021-07-28 | Civil engineering cost management method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113657925A true CN113657925A (en) | 2021-11-16 |
| CN113657925B CN113657925B (en) | 2023-08-22 |
Family
ID=78478831
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110854449.4A Active CN113657925B (en) | 2021-07-28 | 2021-07-28 | Civil engineering cost management method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113657925B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782449A (en) * | 2022-06-23 | 2022-07-22 | 中国科学技术大学 | Method, system, equipment and storage medium for extracting key points in lower limb X-ray image |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107766375A (en) * | 2016-08-19 | 2018-03-06 | 华为技术有限公司 | A kind of method and device for generating thermodynamic chart |
| CN109983508A (en) * | 2016-11-15 | 2019-07-05 | 谷歌有限责任公司 | Fast Flourier color constancy |
| JP2019211870A (en) * | 2018-05-31 | 2019-12-12 | 株式会社日立ソリューションズ東日本 | Inventory management device and inventory management method |
| CN111369657A (en) * | 2020-03-09 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Three-dimensional thermodynamic diagram generation method and device, computer equipment and storage medium |
| WO2020233221A1 (en) * | 2019-05-22 | 2020-11-26 | 北京京东尚科信息技术有限公司 | Heatmap analysis method, device, and system |
| CN112699806A (en) * | 2020-12-31 | 2021-04-23 | 罗普特科技集团股份有限公司 | Three-dimensional point cloud target detection method and device based on three-dimensional heat map |
| CN113095129A (en) * | 2021-03-01 | 2021-07-09 | 北京迈格威科技有限公司 | Attitude estimation model training method, attitude estimation device and electronic equipment |
-
2021
- 2021-07-28 CN CN202110854449.4A patent/CN113657925B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107766375A (en) * | 2016-08-19 | 2018-03-06 | 华为技术有限公司 | A kind of method and device for generating thermodynamic chart |
| CN109983508A (en) * | 2016-11-15 | 2019-07-05 | 谷歌有限责任公司 | Fast Flourier color constancy |
| JP2019211870A (en) * | 2018-05-31 | 2019-12-12 | 株式会社日立ソリューションズ東日本 | Inventory management device and inventory management method |
| WO2020233221A1 (en) * | 2019-05-22 | 2020-11-26 | 北京京东尚科信息技术有限公司 | Heatmap analysis method, device, and system |
| CN111369657A (en) * | 2020-03-09 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Three-dimensional thermodynamic diagram generation method and device, computer equipment and storage medium |
| CN112699806A (en) * | 2020-12-31 | 2021-04-23 | 罗普特科技集团股份有限公司 | Three-dimensional point cloud target detection method and device based on three-dimensional heat map |
| CN113095129A (en) * | 2021-03-01 | 2021-07-09 | 北京迈格威科技有限公司 | Attitude estimation model training method, attitude estimation device and electronic equipment |
Non-Patent Citations (5)
| Title |
|---|
| SEGUIN, B ET AL.: "IRSUTE: A minisatellite concept for the estimation of surface heat fluxes exchanged by the continental biosphere at a local site", 7TH INTERNATIONAL SYMPOSIUM ON PHYSICAL MEASUREMENTS AND SIGNATURES IN REMOTE SENSING * |
| 王耸: "建筑工程造价各个阶段控制要点", 中国科技博览 * |
| 詹显军;裴涛涛;周济兵;: "基于热力图的地铁车站变形可视化分析", 现代隧道技术, no. 01 * |
| 那田: "基于图像像素点的前方车辆距离检测研究", 农业装备与车辆工程, vol. 54, no. 7 * |
| 霍东辉;侯新玉;林洪彬;尚志宏;: "施工沥青路面红外热图像的消噪方法", 黑龙江交通科技, no. 02 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782449A (en) * | 2022-06-23 | 2022-07-22 | 中国科学技术大学 | Method, system, equipment and storage medium for extracting key points in lower limb X-ray image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113657925B (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112183788B (en) | Domain adaptive equipment operation detection system and method | |
| CN111079655B (en) | Method for recognizing human body behaviors in video based on fusion neural network | |
| US11900676B2 (en) | Method and apparatus for detecting target in video, computing device, and storage medium | |
| Peddi et al. | Development of human pose analyzing algorithms for the determination of construction productivity in real-time | |
| CN112183313A (en) | SlowFast-based power operation field action identification method | |
| WO2023030182A1 (en) | Image generation method and apparatus | |
| CN107527045A (en) | A kind of human body behavior event real-time analysis method towards multi-channel video | |
| CN112580434B (en) | Face false detection optimization method and system based on depth camera and face detection equipment | |
| CN114998830A (en) | Wearing detection method and system for safety helmet of transformer substation personnel | |
| CN113837097B (en) | Unmanned aerial vehicle edge calculation verification system and method for visual target identification | |
| Jiang et al. | Application research of key frames extraction technology combined with optimized faster R-CNN algorithm in traffic video analysis | |
| CN113657925A (en) | Civil engineering cost management method based on artificial intelligence | |
| Shi et al. | A lightweight YOLOv5 transmission line defect detection method based on coordinate attention | |
| CN115223043A (en) | Strawberry defect detection method and device, computer equipment and storage medium | |
| CN116614705A (en) | Coal face camera regulation and control system based on multi-mode video feature analysis | |
| CN116432736A (en) | Neural network model optimization method and device and computing equipment | |
| CN117237884A (en) | Interactive inspection robot based on berth positioning | |
| CN110378916B (en) | TBM image slag segmentation method based on multitask deep learning | |
| CN116958927A (en) | Method and device for identifying short column based on BEV (binary image) graph | |
| CN109493279B (en) | Large-scale unmanned aerial vehicle image parallel splicing method | |
| KR20210095925A (en) | camera positioning | |
| CN111127355A (en) | Method for finely complementing defective light flow graph and application thereof | |
| CN113420919B (en) | Engineering anomaly control method based on unmanned aerial vehicle visual perception | |
| Liu et al. | Abnormal behavior analysis strategy of bus drivers based on deep learning | |
| CN114419018A (en) | Image sampling method, system, device and 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 |