CN112070740A - BIM-based port storage yard accumulated water imaging method, system and control equipment - Google Patents

BIM-based port storage yard accumulated water imaging method, system and control equipment Download PDF

Info

Publication number
CN112070740A
CN112070740A CN202010924565.4A CN202010924565A CN112070740A CN 112070740 A CN112070740 A CN 112070740A CN 202010924565 A CN202010924565 A CN 202010924565A CN 112070740 A CN112070740 A CN 112070740A
Authority
CN
China
Prior art keywords
ponding
information
bim
yard
grade
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.)
Withdrawn
Application number
CN202010924565.4A
Other languages
Chinese (zh)
Inventor
王坚
曹智梅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN202010924565.4A priority Critical patent/CN112070740A/en
Publication of CN112070740A publication Critical patent/CN112070740A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00Geometric image transformations in the plane of the image
    • G06T3/40Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4038Image mosaicing, e.g. composing plane images from plane sub-images
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • G06T7/62Analysis of geometric attributes of area, perimeter, diameter or volume
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10024Color image
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20081Training; Learning
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20084Artificial neural networks [ANN]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20212Image combination
    • G06T2207/20221Image fusion; Image merging
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30204Marker

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Geometry (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to the technical field of BIM, in particular to a BIM-based port storage yard accumulated water imaging method, a system and control equipment, wherein an initial BIM model is constructed based on the storage information and layout information of the current port storage yard area; collecting a ponding area image shot by a camera of an area to be measured; and generating thermodynamic diagrams through feature extraction, superposing the thermodynamic diagrams within set time in a pixel superposition mode, judging the ponding grade of the ponding key point according to the superposed thermodynamic diagrams, and mapping the ponding grade to the initial BIM model for display. Thereby generate the heating power image in the storage yard on BIM model, make things convenient for managers in time to discover the unusual region of ponding in the storage yard, in time handle, the work efficiency of effective promotion.

Description

BIM-based port storage yard accumulated water imaging method, system and control equipment
Technical Field
The invention relates to the technical field of BIM, in particular to a BIM-based port storage yard accumulated water imaging method, system and control equipment.
Background
With the increasing degree of openness of China, international trade is prosperous, and the total quantity of import and export of commodities is kept at the advanced level of the world. Harbor ports are also playing an increasingly important role as an important medium for foreign commerce. The harbor of the seaport is mainly responsible for the input and output of container cargo, and mainly consists of a shore bridge and a container yard. Wherein, the goods yard is the main concentrated area for storing the goods at the inlet and the outlet.
In port construction, a drainage system of a storage yard is a necessary facility, the drainage requirement can be met under the general condition, but the storage yard can be caused by continuous strong rainfall, or the drainage system is blocked, and the storage yard can be caused by wrong stacking of goods or containers, and the storage yard for partially storing coal and ore has the risk of collapsing a goods pile; in addition, some containers store wood or other cargo that is sensitive to standing water. The soaking of the accumulated water can cause the goods to deteriorate, thereby causing great economic loss.
At present, to the monitoring of ponding, because the restriction of instrument, detect ponding in the storage yard and mainly rely on the manual work to patrol and examine, however, storage yard area of operation is huge, patrols and examines position and ponding degree that unable real-time discovery ponding exists, leads to in time carrying out the drainage management and control, has great risk.
Therefore, how to rapidly and accurately monitor the position and the degree of the accumulated water in the storage yard so as to process the accumulated water in time is a technical problem which needs to be solved urgently at present.
Disclosure of Invention
The invention aims to provide a BIM-based port storage yard accumulated water imaging method, a BIM-based port storage yard accumulated water imaging system and a BIM-based port storage yard accumulated water imaging control device, so that accumulated water in a storage yard can be monitored quickly and accurately.
The embodiment of the invention provides the following scheme:
in a first aspect, an embodiment of the present invention provides a port yard ponding imaging method based on BIM, where the method includes the following steps:
1) constructing an initial BIM (building information modeling) model based on the storage information and layout information of the current port yard area;
2) collecting ponding area images shot by a camera arranged in a to-be-detected area of a port yard according to a set sampling time interval;
3) extracting characteristic information of the ponding region image obtained at each sampling moment, and obtaining a corresponding ponding region thermodynamic diagram containing ponding key points according to the characteristic information and a thermodynamic diagram generation method; within a set time, overlapping the thermodynamic diagrams of the ponding areas corresponding to a plurality of sampling moments to obtain the overlapped thermodynamic diagrams; the superposition operation comprises the step of adding pixel values of corresponding positions in the ponding region thermodynamic diagrams at different sampling moments;
4) extracting ponding grade characteristics in the superposed thermodynamic diagram, and predicting ponding grade information of ponding key points according to the ponding grade characteristics and a preset ponding grade judgment rule;
5) and mapping the superimposed thermodynamic diagram and the grade information of the corresponding ponding key points to the initial BIM model for display.
In a possible embodiment, in the step 1), the storage information of the current port yard area includes a cargo code and a cargo quantity; the layout information includes field layout design parameters, shelf size, geographical location coordinate information for the current area, and the image sensor model, resolution, number used in the current area, and their respective numbering information inside the port.
In a possible embodiment, in the step 3), generating a ponding area thermodynamic diagram by using the trained neural network model includes:
collecting image data of the ponding area, and marking the central point position and the barrier position of the ponding area;
and convolving the marked obstacle scatter diagram with a Gaussian kernel to obtain a ponding area thermodynamic diagram of the ponding key points.
In a possible embodiment, in the step 4), the water level is determined by using a trained water level classification model, input information of the water level classification model is superimposed thermodynamic diagram information, output information of the water level classification model is water level information in the storage yard area, and supervision information of the water level classification model is water level classification rules.
In a possible embodiment, the set time is determined according to the drainage capacity of the yard and the nature of the stored goods.
In a possible embodiment, the step 5) further includes performing image stitching and image fusion operations on the superimposed thermodynamic diagrams corresponding to different cameras to form a panoramic thermodynamic diagram image.
In a possible embodiment, the method further comprises the step of carrying out image preprocessing operations on the ponding area image shot by the camera, wherein the image preprocessing operations comprise image filtering, noise reduction and distortion correction.
In a second aspect, an embodiment of the present invention provides a BIM-based port yard ponding imaging system, where the system includes:
the model establishing module is used for establishing an initial BIM model based on the storage information and the layout information of the current port yard area;
the image information acquisition module is used for acquiring ponding area images shot by a camera arranged in a to-be-detected area of the port yard according to a set sampling time interval;
the thermodynamic diagram generation module is used for extracting the characteristic information of the ponding region image obtained at each sampling moment and obtaining a corresponding ponding region thermodynamic diagram containing ponding key points according to the characteristic information and a thermodynamic diagram generation method; within a set time, overlapping the thermodynamic diagrams of the ponding areas corresponding to a plurality of sampling moments to obtain the overlapped thermodynamic diagrams; the superposition operation comprises the step of adding pixel values of corresponding positions in the ponding region thermodynamic diagrams at different sampling moments;
the ponding grade judging module is used for extracting the ponding grade characteristics in the superposed thermodynamic diagram and predicting the ponding grade information of the ponding key points according to the ponding grade characteristics and a preset ponding grade judging rule;
and the image mapping module is used for mapping the superposed thermodynamic diagram and the grade information of the corresponding ponding key points to the initial BIM model for display.
In a possible embodiment, when the model building module builds the model, the storage information of the current port yard area comprises a cargo code and a cargo quantity; the layout information includes field layout design parameters, shelf size, geographical location coordinate information for the current area, and the image sensor model, resolution, number used in the current area, and their respective numbering information inside the port.
In a possible embodiment, the thermodynamic diagram generation module generates a ponding area thermodynamic diagram by using a trained neural network model, and includes:
the characteristic extraction module is used for acquiring image data of the ponding area and marking the central point position and the barrier position of the ponding area;
and the convolution processing module is used for convolving the marked obstacle scatter diagram with a Gaussian kernel to obtain a ponding region thermodynamic diagram of the ponding key points.
In a possible embodiment, the ponding grade determination module determines the ponding grade by using a trained ponding grade classification model, the input information of the ponding grade classification model is the superposed thermodynamic diagram information, the output is the ponding grade information in the storage yard area, and the supervision information is a ponding grade classification rule.
In a possible embodiment, the set time is determined according to the drainage capacity of the yard and the nature of the stored goods.
In a possible embodiment, the image mapping module further includes an image stitching and fusing module, which is configured to perform image stitching and image fusing operations on the superimposed thermodynamic diagrams corresponding to different cameras to form a panoramic thermodynamic diagram image.
In a possible embodiment, the method further comprises the step of carrying out image preprocessing operations on the ponding area image shot by the camera, wherein the image preprocessing operations comprise image filtering, noise reduction and distortion correction.
In a third aspect, an embodiment of the present invention provides a port yard ponding imaging control device based on BIM, including:
a memory for storing a computer program;
a processor for executing the computer program to implement the steps of the BIM-based port yard ponding imaging method of any one of the first aspects.
Compared with the prior art, the invention has the beneficial effects that:
according to the method, after a BIM initial model based on the current port storage yard area is constructed, image characteristics are extracted according to the content collected by each camera to be detected, thermodynamic diagram information of the water accumulation area is finally obtained, thermodynamic diagrams in set time are added, the added thermodynamic diagram characteristics are extracted, the accumulated water level information in the port storage yard is predicted, and the superposed thermodynamic diagrams and level information are mapped to the BIM model to be displayed, so that the environment of the port storage yard area is visually presented, data visualization is realized at a web end, the accumulated water thermodynamic diagrams and accumulated water level information in the storage yard are displayed, an alarm can be sent in time according to the level information to remind storage yard managers to take corresponding measures, and the storage yard safety is effectively improved.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present specification, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 shows a flow chart of a BIM-based port yard waterlogging imaging method in an embodiment of the invention;
fig. 2 shows a block diagram of a BIM-based port yard ponding imaging system in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments, and all other embodiments obtained by those skilled in the art based on the embodiments of the present invention belong to the scope of protection of the embodiments of the present invention.
In order to ensure real-time monitoring of the storage environment of the container goods in the storage yard, the condition of accumulated water in the storage yard needs to be monitored in time, but the operation area of the storage yard is huge, and the position and the accumulated water degree of the accumulated water cannot be found in real time by means of manual inspection or inspection by robots and the like.
Therefore, after the inventor of the present invention has conducted an in-depth analysis on the phenomenon, the inventor of the present invention has proposed an imaging method for displaying the accumulated water situation in the port storage yard, and hopefully, the method can display the real-time change situation of the accumulated water in the storage yard on a thermodynamic diagram and can display the change situation on a three-dimensional model, and further, the inventor of the present invention has proposed the following scheme:
as shown in fig. 1, the BIM-based port yard accumulated water imaging method provided by the embodiment of the present invention is applied to a controller for modeling simulation and visualization of a yard, where the controller may be any control chip such as an industrial personal computer, a single chip, an FPGA, or a PLC, which can implement functions such as sampling, calculation, and control.
Specifically, the BIM-based port storage yard ponding imaging method comprises the following steps 1 to 5:
step 1, constructing an initial BIM model based on the storage information and the layout information of the current port yard area.
In order to implement the method of the invention, a BIM model of the current port yard region needs to be constructed first. The BIM (building information model) of the port yard area is an information processing platform based on the BIM and has a specific information exchange standard. The storage information of the current port yard area comprises goods codes and goods quantity; the layout information includes field layout design parameters, shelf size, geographical location coordinate information for the current area, and the image sensor model, resolution, number used in the current area, and their respective numbering information inside the port.
The specific installation height and the number of the cameras need to be determined according to the field implementation condition and the visual angle of the cameras, and it needs to be ensured that two adjacent cameras need to have a certain overlapping area, so that the subsequent splicing operation is facilitated.
And 2, acquiring the ponding area images shot by the cameras arranged in the to-be-detected area of the port yard according to the set sampling time interval.
The invention mainly aims to detect accumulated water in a port heap area.
It should be noted that, the invention adopts a color camera to acquire the image information in the heap area; the camera is erected on the lighting lamp post of the storage yard.
The BIM of the port yard area simultaneously receives data (images) sensed by all sensors (cameras) in the current area, stores corresponding sensor information into a central storage server according to a set rule, and regularly updates the sensor information in a covering manner according to the capacity of the server so as to inquire historical data.
Step 3, extracting the characteristic information of the ponding region image obtained at each sampling moment, and obtaining a corresponding ponding region thermodynamic diagram containing ponding key points according to the characteristic information and a thermodynamic diagram generation method; within a set time, overlapping the thermodynamic diagrams of the ponding areas corresponding to a plurality of sampling moments to obtain the overlapped thermodynamic diagrams; the superposition operation comprises the addition of pixel values of corresponding positions in the ponding region thermodynamic diagrams at different sampling moments.
The reasons for water accumulation in the yard are many, for example: the stacked goods or containers are not placed according to the regulations, so that the drainage port is shielded; the goods are scraped due to wind, and finally the drainage port is shielded, and the like.
Therefore, after the image information of the port storage yard area is obtained, the characteristics of the image information of the storage yard area are extracted by adopting a ponding information encoder EncodeA to obtain the characteristics FeatureMapa of the ponding area; and decoding the characteristic information through a ponding information decoder DecoderA to finally obtain thermodynamic diagram information Heatmap of the ponding area. The thermodynamic diagram generation method belongs to the prior art in the field, and is not described herein again.
It should be noted that, a port is usually close to the sea, and the instantaneous rainfall is large when it rains. At this time, even if the drain port is not blocked, a small amount of accumulated water may be present even if the instantaneous rainfall is too large, in which case the accumulated water does not exist for a long time. The accumulated water is rapidly reduced along with the reduction of the rainfall or the increase of the drainage capacity. This does not have a significant effect on the cargo or container.
Therefore, the invention adopts a thermodynamic diagram superposition mode, as shown in fig. 1, thermodynamic diagrams are superposed in a period of time, and the superposition result of the thermodynamic diagrams is counted. The superposition mode is eltwise, and specifically comprises the following steps: after the thermodynamic diagrams are generated, the thermodynamic diagrams in the period are added, that is, the addition of the pixel values at the corresponding positions is performed, and the thermodynamic diagrams are added in a queue manner.
And after the superposed thermodynamic diagram Heatmap _ T is obtained, adopting a water level coder EncoderB to extract the superposed water level feature FeaturemapB, further adopting a full connection layer FC to flatten the feature and predicting water level information.
And 4, extracting the accumulated water grade characteristics in the superposed thermodynamic diagram, and predicting the accumulated water grade information of the accumulated water key points according to the accumulated water grade characteristics and a pre-established accumulated water grade judgment rule.
The accumulated water grade prediction module inputs the superposed thermodynamic diagram information and outputs the accumulated water grade information in the storage yard area. The supervision information is manually labeled water grade classification. And updating the network by adopting a cross entropy loss function, and finally obtaining the level information of the accumulated water in the storage yard.
Therefore, the prediction of the water level information in the storage yard is completed.
And 5, mapping the superposed thermodynamic diagrams and the grade information of the corresponding ponding key points to the initial BIM model for display.
In order to visually present the environment of a port storage yard area, the invention integrates a BIM (building information modeling) model of the storage yard area into a system developed by WebGIS (Web geographic information system), updates a space model of the storage yard area in real time by calling an information exchange module, obtains the reading of a sensor at a corresponding position, performs data visualization at a Web end, displays a storage yard accumulated water thermodynamic diagram and accumulated water grade information, and timely sends out a warning to remind storage yard managers to take corresponding measures according to the grade information.
In one possible embodiment, generating a ponding region thermodynamic diagram using a trained neural network model comprises:
collecting image data of the ponding area, and marking the central point position and the barrier position of the ponding area;
and convolving the marked obstacle scatter diagram with a Gaussian kernel to obtain a ponding area thermodynamic diagram of the ponding key points.
Specifically, the input of the waterlogged area thermodynamic diagram detection network is three-channel color image information, and the supervision information is a thermodynamic diagram of waterlogging. The generation mode of the thermodynamic diagram comprises two steps, firstly, image data are collected and labeled, the position of a central point of a water accumulation area is marked, and the position is expressed by (x, y), wherein x represents the abscissa of a key point in an image, and y represents the ordinate of the key point in the image; and then convolving the marked obstacle scatter diagram with a Gaussian kernel to obtain a ponding key point thermodynamic diagram. The specific procedures are well known and will not be described in detail herein.
And performing iterative updating on network parameters by adopting a cross entropy loss function as a loss function in the training process of the waterlogged area thermodynamic diagram detection network, and finally obtaining thermodynamic diagram information of each waterlogged area in the current image.
In a possible embodiment, the ponding grade is judged by using a trained ponding grade classification model, the input information of the ponding grade classification model is the superposed thermodynamic diagram information, the output is the ponding grade information in the storage yard area, and the supervision information is a ponding grade classification rule.
The accumulated water grade prediction module inputs the superposed thermodynamic diagram information and outputs the accumulated water grade information in the storage yard area. The supervision information is manually labeled water grade classification. And updating the network by adopting a cross entropy loss function, and finally obtaining the level information of the accumulated water in the storage yard.
Therefore, the prediction of the water level information in the storage yard is completed.
In a possible embodiment, the set time is determined according to the drainage capacity of the yard and the nature of the stored goods.
In the present invention, the duration of the thermodynamic diagrams to be superimposed can be flexibly adjusted by the implementer according to the actual scene, the drainage capacity of the storage yard, the nature of the stored goods, and other factors.
In a possible embodiment, the method further comprises the step of performing image splicing and image fusion operations on the superimposed thermodynamic diagrams corresponding to different cameras to form a panoramic thermodynamic diagram image.
Specifically, images shot by the camera and superimposed thermodynamic diagram information are subjected to image splicing and affine transformation to a BIM storage yard plane, and predicted ponding grade information is uploaded to the BIM information exchange module.
In the above embodiment, a preprocessing operation needs to be performed on a color image, image stitching is completed on the basis of image preprocessing, and image preprocessing includes methods such as image filtering, denoising, distortion correction, and the like, and the principles of these methods are well known and are not described herein; the images collected by each camera are subjected to perspective transformation, so that all the images are converted into the same visual angle, and splicing is facilitated.
Further, the image stitching and fusing process of the embodiment includes the following steps:
first, feature points of an image are extracted.
The method of feature points is often used because it is easier to handle transformation relationships such as rotation, affine, perspective, and the like between images. There are many methods for detecting feature points, for example, Harris corner detection algorithm, L _ ORB feature point detection algorithm, SIFT key point detection algorithm, FAST feature point detection algorithm, etc. are well known.
It should be noted that, in the invention, container goods are mainly stored in the port yard, and the edge and corner features are obvious, so the Harris corner is adopted as the feature point of the image in the invention.
And after the feature points are extracted, converting the feature points into data representation in a fixed format by adopting a feature descriptor.
Secondly, matching the feature points of the adjacent images, and finding out the corresponding positions of the feature points in the images to be spliced in the reference image by adopting a certain matching strategy so as to determine the transformation relation between the two images.
It should be noted that, when matching feature points, there is an interference term in the feature points, that is, there may be an erroneous match. Therefore, the RANSAC feature point matching and filtering algorithm is adopted in the invention to filter the feature points and improve the accuracy of feature point matching. The RANSAC feature point matching algorithm is adopted, so that the base lines of the two cameras cannot be too long, and the overlapping area is large enough. After the correct feature point pairs are determined, affine transformation matrixes of two adjacent images are calculated, the two images are converted into a coordinate system through affine transformation, and coarse-grained image splicing is achieved preliminarily.
And finally, carrying out image fusion on the spliced image.
The image fusion technology mainly comprises an average value method, a hat function method, a weighted average method, a pyramid, a gradient and the like. The invention uses a weighted average method to endow the two images with corresponding weights, and then adds the weights to obtain a fused spliced image.
Because the difference of camera and illumination intensity can cause an image inside to and the inhomogeneous of luminance between the image, the light and shade alternation can appear in the image after the concatenation, causes very big inconvenience for observing like this. The common processing mode is to correct illumination nonuniformity in one image through an illumination model of a camera, then establish a histogram mapping table between two adjacent images through the relationship between overlapping areas of the two adjacent images, and perform integral mapping transformation on the two images through the mapping table, so as to finally achieve the consistency of the integral brightness and color.
And splicing and fusing the image information after the thermodynamic diagrams in the storage yard area are superposed according to the same method to form a panoramic thermodynamic diagram image, so that the panoramic thermodynamic diagram image is more intuitive to display.
In a possible embodiment, the method further comprises the step of carrying out image preprocessing operations on the ponding area image shot by the camera, wherein the image preprocessing operations comprise image filtering, noise reduction and distortion correction.
The image preprocessing method is characterized in that preprocessing operation is carried out on color images, image splicing is completed on the basis of image preprocessing, the image preprocessing comprises image filtering denoising, distortion correction and other methods, the principles of the methods are well known, and details are not repeated herein.
The invention realizes the visual display of the yard ponding thermodynamic diagram and the ponding grade information at the web end, and timely sends out warning to remind the yard management personnel to take corresponding measures according to the grade information.
Based on the same inventive concept as the method, the embodiment of the present invention further provides a port yard ponding imaging system based on BIM, as shown in fig. 2, which is a schematic structural diagram of the embodiment of the system, and the system includes:
the model establishing module 101 is used for establishing an initial BIM model based on the storage information and the layout information of the current port yard area;
the image information acquisition module 102 is used for acquiring ponding area images shot by a camera arranged in a to-be-detected area of a port yard according to a set sampling time interval;
the thermodynamic diagram generation module 103 is used for extracting feature information of the ponding region image obtained at each sampling moment, and obtaining a corresponding ponding region thermodynamic diagram containing ponding key points according to the feature information and a thermodynamic diagram generation method; within a set time, overlapping the thermodynamic diagrams of the ponding areas corresponding to a plurality of sampling moments to obtain the overlapped thermodynamic diagrams; the superposition operation comprises the step of adding pixel values of corresponding positions in the ponding region thermodynamic diagrams at different sampling moments;
the ponding grade judging module 104 is used for extracting the ponding grade characteristics in the superposed thermodynamic diagram and predicting ponding grade information of the ponding key points according to the ponding grade characteristics and a preset ponding grade judging rule;
and the image mapping module 105 is configured to map the superimposed thermodynamic diagram and the grade information of the corresponding water accumulation key points to the initial BIM model for display.
In a possible embodiment, when the model building module builds the model, the storage information of the current port yard area comprises a cargo code and a cargo quantity; the layout information includes field layout design parameters, shelf size, geographical location coordinate information for the current area, and the image sensor model, resolution, number used in the current area, and their respective numbering information inside the port.
In a possible embodiment, the thermodynamic diagram generation module generates a ponding area thermodynamic diagram by using a trained neural network model, and includes:
the characteristic extraction module is used for acquiring image data of the ponding area and marking the central point position and the barrier position of the ponding area;
and the convolution processing module is used for convolving the marked obstacle scatter diagram with a Gaussian kernel to obtain a ponding region thermodynamic diagram of the ponding key points.
In a possible embodiment, the ponding grade determination module determines the ponding grade by using a trained ponding grade classification model, the input information of the ponding grade classification model is the superposed thermodynamic diagram information, the output is the ponding grade information in the storage yard area, and the supervision information is a ponding grade classification rule.
In a possible embodiment, the set time is determined according to the drainage capacity of the yard and the nature of the stored goods.
In a possible embodiment, the image mapping module further includes an image stitching and fusing module, which is configured to perform image stitching and image fusing operations on the superimposed thermodynamic diagrams corresponding to different cameras to form a panoramic thermodynamic diagram image.
In a possible embodiment, the method further comprises the step of carrying out image preprocessing operations on the ponding area image shot by the camera, wherein the image preprocessing operations comprise image filtering, noise reduction and distortion correction.
Based on the same inventive concept as that in the foregoing embodiments, an embodiment of the present invention further provides a BIM-based port yard ponding imaging control apparatus, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the BIM-based port yard ponding imaging method when executing the program.
Based on the same inventive concept as in the previous embodiments, embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the BIM-based port yard ponding imaging method described above.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (modules, systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (9)

1. A BIM-based port storage yard ponding imaging method is characterized by comprising the following steps:
1) constructing an initial BIM (building information modeling) model based on the storage information and layout information of the current port yard area;
2) collecting ponding area images shot by a camera arranged in a to-be-detected area of a port yard according to a set sampling time interval;
3) extracting characteristic information of the ponding region image obtained at each sampling moment, and obtaining a corresponding ponding region thermodynamic diagram containing ponding key points according to the characteristic information and a thermodynamic diagram generation method; within a set time, overlapping the thermodynamic diagrams of the ponding areas corresponding to a plurality of sampling moments to obtain the overlapped thermodynamic diagrams; the superposition operation comprises the step of adding pixel values of corresponding positions in the ponding region thermodynamic diagrams at different sampling moments;
4) extracting ponding grade characteristics in the superposed thermodynamic diagram, and predicting ponding grade information of ponding key points according to the ponding grade characteristics and a preset ponding grade judgment rule;
5) and mapping the superimposed thermodynamic diagram and the grade information of the corresponding ponding key points to the initial BIM model for display.
2. The BIM-based port yard ponding imaging method according to claim 1, wherein in the step 1), the storage information of the current port yard area includes cargo code, cargo quantity; the layout information includes field layout design parameters, shelf size, geographical location coordinate information for the current area, and the image sensor model, resolution, number used in the current area, and their respective numbering information inside the port.
3. The BIM-based port yard ponding imaging method according to claim 1, wherein in the step 3), the ponding area thermodynamic diagram is generated by using the trained neural network model, and the method comprises the following steps:
collecting image data of the ponding area, and marking the central point position and the barrier position of the ponding area;
and convolving the marked obstacle scatter diagram with a Gaussian kernel to obtain a ponding area thermodynamic diagram of the ponding key points.
4. The BIM-based port storage yard ponding imaging method of claim 1, wherein in the step 4), the ponding grade is judged by using a trained ponding grade classification model, the input information of the ponding grade classification model is superimposed thermodynamic diagram information, the output is ponding grade information in a storage yard area, and the supervision information is a ponding grade classification rule.
5. The BIM-based port yard ponding imaging method of claim 1, wherein the set time is determined according to yard drainage capacity, nature of stored cargo.
6. The BIM-based port storage yard ponding imaging method according to claim 1, characterized in that the step 5) further comprises image stitching and image fusion operations on the corresponding superimposed thermodynamic diagrams of different cameras to form a panoramic thermodynamic diagram image.
7. The BIM-based port yard ponding imaging method of claim 1, further comprising performing image preprocessing operations including image filtering, noise reduction and distortion correction on the ponding region image captured by the camera.
8. The utility model provides a harbour yard ponding imaging system based on BIM which characterized in that includes:
the model establishing module is used for establishing an initial BIM model based on the storage information and the layout information of the current port yard area;
the image information acquisition module is used for acquiring ponding area images shot by a camera arranged in a to-be-detected area of the port yard according to a set sampling time interval;
the thermodynamic diagram generation module is used for extracting the characteristic information of the ponding region image obtained at each sampling moment and obtaining a corresponding ponding region thermodynamic diagram containing ponding key points according to the characteristic information and a thermodynamic diagram generation method; within a set time, overlapping the thermodynamic diagrams of the ponding areas corresponding to a plurality of sampling moments to obtain the overlapped thermodynamic diagrams; the superposition operation comprises the step of adding pixel values of corresponding positions in the ponding region thermodynamic diagrams at different sampling moments;
the ponding grade judging module is used for extracting the ponding grade characteristics in the superposed thermodynamic diagram and predicting the ponding grade information of the ponding key points according to the ponding grade characteristics and a preset ponding grade judging rule;
and the image mapping module is used for mapping the superposed thermodynamic diagram and the grade information of the corresponding ponding key points to the initial BIM model for display.
9. A BIM-based port yard ponding imaging control device, comprising:
a memory for storing a computer program;
a processor for executing said computer program to carry out the steps of the BIM based port yard ponding imaging method of any one of claims 1 to 7.
CN202010924565.4A 2020-09-05 2020-09-05 BIM-based port storage yard accumulated water imaging method, system and control equipment Withdrawn CN112070740A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010924565.4A CN112070740A (en) 2020-09-05 2020-09-05 BIM-based port storage yard accumulated water imaging method, system and control equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010924565.4A CN112070740A (en) 2020-09-05 2020-09-05 BIM-based port storage yard accumulated water imaging method, system and control equipment

Publications (1)

Publication Number Publication Date
CN112070740A true CN112070740A (en) 2020-12-11

Family

ID=73665667

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010924565.4A Withdrawn CN112070740A (en) 2020-09-05 2020-09-05 BIM-based port storage yard accumulated water imaging method, system and control equipment

Country Status (1)

Country Link
CN (1) CN112070740A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112966782A (en) * 2021-04-09 2021-06-15 深圳市豪恩汽车电子装备股份有限公司 Multi-view-angle feature-fused road surface water detection and identification method
CN114202908A (en) * 2021-12-13 2022-03-18 中国平安财产保险股份有限公司 Vehicle early warning method, device, equipment and storage medium based on disaster weather

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112966782A (en) * 2021-04-09 2021-06-15 深圳市豪恩汽车电子装备股份有限公司 Multi-view-angle feature-fused road surface water detection and identification method
CN114202908A (en) * 2021-12-13 2022-03-18 中国平安财产保险股份有限公司 Vehicle early warning method, device, equipment and storage medium based on disaster weather

Similar Documents

Publication Publication Date Title
CN101625723A (en) Rapid image-recognizing method of power line profile
TW201118804A (en) Method and system for object detection
CN114743119B (en) High-speed rail contact net hanger nut defect detection method based on unmanned aerial vehicle
CN107833203A (en) A kind of horizontal plane identification and water level method for real-time measurement based on image procossing
CN112070740A (en) BIM-based port storage yard accumulated water imaging method, system and control equipment
CN112330593A (en) Building surface crack detection method based on deep learning network
CN112215308B (en) Single-order detection method and device for hoisted object, electronic equipment and storage medium
CN108010025A (en) Switch and indicator lamp positioning and state identification method of screen cabinet based on RCNN
CN115597494B (en) Precision detection method and system for prefabricated part preformed hole based on point cloud
CN116777898B (en) Method for realizing crack measurement in 3D printing retaining wall construction process based on AFFormer
CN112330597A (en) Image difference detection method and device and computer equipment
CN115019254A (en) Method, device, terminal and storage medium for detecting foreign matter invasion in power transmission area
CN107977531A (en) A kind of method that ground resistance hard measurement is carried out based on image procossing and field mathematical model
Shajahan et al. Automated inspection of monopole tower using drones and computer vision
CN105427276A (en) Camera detection method based on image local edge characteristics
CN113311507A (en) Typhoon path identification method and device
CN115331166B (en) Intelligent monitoring and early warning method and system for grid trash remover
CN112861681B (en) Pipe gallery video intelligent analysis method and system based on cloud processing
CN115880642A (en) Marine target proximity degree early warning method and system based on machine vision
CN112784914B (en) Pipe gallery video intelligent attribute detection method and system based on cloud processing
CN112132135B (en) Power grid transmission line detection method based on image processing and storage medium
CN113298755B (en) Method and device for rapidly detecting ecological environment change patch based on time sequence image
CN105241886B (en) A kind of earthen ruins crack detection method based on HVS and wave filter
CN112116561B (en) Power grid transmission line detection method and device based on image processing fusion network weight
CN105427295B (en) A kind of image-recognizing method and image identification system based on weld seam

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
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20201211