CN116051980A - Building identification method, system, electronic equipment and medium based on oblique photography - Google Patents
Building identification method, system, electronic equipment and medium based on oblique photography Download PDFInfo
- Publication number
- CN116051980A CN116051980A CN202211601675.2A CN202211601675A CN116051980A CN 116051980 A CN116051980 A CN 116051980A CN 202211601675 A CN202211601675 A CN 202211601675A CN 116051980 A CN116051980 A CN 116051980A
- Authority
- CN
- China
- Prior art keywords
- building
- oblique photography
- model
- independent
- neural network
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 claims abstract description 48
- 238000004458 analytical method Methods 0.000 claims abstract description 32
- 238000003708 edge detection Methods 0.000 claims abstract description 29
- 238000003062 neural network model Methods 0.000 claims description 44
- 238000012549 training Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 7
- 238000000926 separation method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 5
- 238000012795 verification Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/04—Architectural design, interior design
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention discloses a building identification method, a system, electronic equipment and a medium based on oblique photography, wherein the building identification method based on oblique photography comprises the following steps: generating an oblique photography three-dimensional model based on the oblique photography three-dimensional data, and performing edge detection analysis on the oblique photography three-dimensional model to obtain a building contour; overlapping the building outline into the oblique photography three-dimensional model, and separating an independent model of the corresponding building from the oblique photography three-dimensional model by taking the building outline as a boundary; building contour recognition is carried out on the side face of the independent model, and a side face detection result of the independent model is obtained; judging whether the side is available or not based on the side detection result, if yes, acquiring point clouds of different side boundaries of the independent model based on the determined side range and overlook range; and calculating the distance between the point clouds in the point cloud set, taking the two point clouds with the distance within a set threshold value as intersection points, and obtaining the range of the building. The building identification method based on oblique photography solves the problems that in the prior art, the operation process of building identification based on oblique photography needs to be connected with tax discs, and the time and the trouble are taken.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a building identification method, a system, electronic equipment and a medium based on oblique photography.
Background
The oblique photography technology acquires images from one vertical, four oblique and five different visual angles synchronously, so that abundant high-resolution textures of the top surface and the side view of a building are acquired, the ground object condition can be truly reflected, the object texture information can be acquired with high precision, and a real three-dimensional city model can be generated through advanced positioning, fusion, modeling and other technologies; however, due to the automatic modeling mechanism of oblique photography, the established live-action model is an area 'skin', objects in the three-dimensional model cannot be selected and managed independently, GIS operations such as attribute query and space query cannot be performed, and the value and practicability of three-dimensional data are reduced.
For oblique photography three-dimensional data, manual intervention is performed by taking continuous oblique photography data as a base data source. And importing the modeling result into software for fine editing, and achieving a separation effect on the original scene through model reconstruction to achieve model singulation. An edge detection algorithm is used in the process of automatic singulation, and data extraction of the orthoedges of the building is performed based on an orthogram of oblique photographing three-dimensional data. And then, based on the lowest value of the data, extracting a data base to realize building identification, and extracting the whole building.
However, a single orthographic edge detection algorithm is used to perform building identification of three-dimensional data, and a data boundary is intercepted by a top view, so that errors may occur in the boundary.
Disclosure of Invention
The embodiment of the invention aims to provide a building identification method, a system, electronic equipment and a medium based on oblique photography, which are used for solving the problem that in the prior art, a single orthographic edge detection algorithm is used for generating errors on boundaries.
In order to achieve the above object, an embodiment of the present invention provides a building identification method based on oblique photography, the method specifically including:
acquiring oblique photography three-dimensional data;
generating an oblique photography three-dimensional model based on the oblique photography three-dimensional data, and performing edge detection analysis on the oblique photography three-dimensional model to obtain a building contour;
superimposing the building contour into the oblique photography three-dimensional model, and separating an independent model of a corresponding building from the oblique photography three-dimensional model with the building contour as a boundary;
building contour recognition is carried out on the side face of the independent model, and a side face detection result of the independent model is obtained;
judging whether the side is available or not based on the side detection result, if yes, acquiring point clouds of different side boundaries of the independent model based on the determined side range and overlook range;
and calculating the distance between the point clouds in the point cloud set, taking the two point clouds with the distance within a set threshold value as intersection points, and obtaining the range of the building.
Based on the technical scheme, the invention can also be improved as follows:
further, the generating a oblique photography three-dimensional model based on the oblique photography three-dimensional data, performing edge detection analysis on the oblique photography three-dimensional model to obtain a building contour, includes:
constructing a first neural network model and training the first neural network model;
acquiring an orthographic image of the oblique photography three-dimensional model;
and carrying out edge detection analysis on the orthographic image through the trained first neural network model to obtain the building outline.
Further, the identifying the building contour on the side of the independent model to obtain the side detection result of the independent model includes:
acquiring an image of the independent model, and acquiring a side surface of the independent model based on the image;
constructing a second neural network model and training the second neural network model;
building contour recognition is carried out on the side face through the trained second neural network model, and a side face detection result of the independent model is obtained; the side detection result comprises a ground base line, an area size and identification confidence of the independent model.
Further, the determining whether the side is available based on the side detection result, if yes, obtaining point clouds of different side boundaries of the independent model based on the determined side range and the overlook range, includes:
enlarging the intercepting range of the side surface when the side surface is not available;
and carrying out building contour recognition on the side surfaces of the independent models again to obtain side surface detection results of the independent models.
A tilt photography-based building identification system, comprising:
the acquisition module is used for acquiring oblique photographing three-dimensional data;
the analysis module is used for generating an oblique photography three-dimensional model based on the oblique photography three-dimensional data, and carrying out edge detection analysis on the oblique photography three-dimensional model to obtain a building contour;
a separation module for superimposing the building contour into the oblique photography three-dimensional model, separating an independent model of a corresponding building from the oblique photography three-dimensional model with the building contour as a boundary;
the identification module is used for carrying out building contour identification on the side face of the independent model to obtain a side face detection result of the independent model;
the judging module is used for judging whether the side face is available or not based on the side face detection result, and if yes, acquiring point clouds of different side face boundaries of the independent model based on the determined side face range and the overlooking range;
the first acquisition module is used for calculating the distance between the point clouds in the point cloud set, taking the two point clouds with the distance within a set threshold value as intersection points, and acquiring the range of the building.
Further, the building identification system further includes:
the second acquisition module is used for acquiring an orthographic image of the oblique photography three-dimensional model;
the first building module is used for building a first neural network model and training the first neural network model;
the trained first neural network model is used for carrying out edge detection analysis on the orthographic image to obtain the building outline.
Further, the building identification system further includes:
the third acquisition module is used for acquiring images of the independent models and acquiring the side surfaces of the independent models based on the images;
the second building module is used for building a second neural network model and training the second neural network model;
the trained second neural network model is used for carrying out building contour recognition on the side face to obtain a side face detection result of the independent model; the side detection result comprises a ground base line, an area size and identification confidence of the independent model.
Further, the judging module is further configured to:
enlarging the intercepting range of the side surface when the side surface is not available;
the identification module is also used for:
and carrying out building contour recognition on the side surfaces of the independent models again to obtain side surface detection results of the independent models.
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method when the computer program is executed.
A non-transitory computer readable medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method.
The embodiment of the invention has the following advantages:
according to the building identification method based on oblique photography, three-dimensional data of oblique photography are collected; generating an oblique photography three-dimensional model based on the oblique photography three-dimensional data, and performing edge detection analysis on the oblique photography three-dimensional model to obtain a building contour; superimposing the building contour into the oblique photography three-dimensional model, and separating an independent model of a corresponding building from the oblique photography three-dimensional model with the building contour as a boundary; building contour recognition is carried out on the side face of the independent model, and a side face detection result of the independent model is obtained; judging whether the side is available or not based on the side detection result, if yes, acquiring point clouds of different side boundaries of the independent model based on the determined side range and overlook range; calculating the distance between the point clouds, and taking the two point clouds with the distance within a set threshold as intersection points to obtain the range of the building; the problem that in the prior art, errors exist in boundaries due to the fact that a single orthographic edge detection algorithm is used is solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those of ordinary skill in the art that the drawings in the following description are exemplary only and that other implementations can be obtained from the extensions of the drawings provided without inventive effort.
The structures, proportions, sizes, etc. shown in the present specification are shown only for the purposes of illustration and description, and are not intended to limit the scope of the invention, which is defined by the claims, so that any structural modifications, changes in proportions, or adjustments of sizes, which do not affect the efficacy or the achievement of the present invention, should fall within the ambit of the technical disclosure.
FIG. 1 is a flow chart of a tilt photography based building identification method of the present invention;
FIG. 2 is a block diagram of a tilt-camera based building identification system of the present invention;
FIG. 3 is a block diagram of a tilt-camera based building identification system of the present invention;
fig. 4 is a schematic diagram of an entity structure of an electronic device according to the present invention.
The system comprises an acquisition module 10, an analysis module 20, a separation module 30, an identification module 40, a judgment module 50, a first acquisition module 60, a second acquisition module 70, a first construction module 80, a third acquisition module 90, a second construction module 100, an electronic device 110, a processor 1101, a memory 1102 and a bus 1103.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the present application described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the present application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate an azimuth or a positional relationship based on that shown in the drawings. These terms are used primarily to better describe the present application and its embodiments and are not intended to limit the indicated device, element or component to a particular orientation or to be constructed and operated in a particular orientation.
Also, some of the terms described above may be used to indicate other meanings in addition to orientation or positional relationships, for example, the term "upper" may also be used to indicate some sort of attachment or connection in some cases. The specific meaning of these terms in this application will be understood by those of ordinary skill in the art as appropriate.
In addition, the term "plurality" shall mean two as well as more than two.
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 is a flowchart of an embodiment of a building identification method based on oblique photography, and as shown in fig. 1, the building identification method based on oblique photography provided by the embodiment of the invention comprises the following steps:
s101, acquiring oblique photography three-dimensional data;
specifically, the oblique photography technology is a high-new technology developed in recent years in the international mapping field, and overtakes the limitation that the original orthographic image can only be photographed from a vertical angle, and the user is introduced into the real visual world conforming to the human vision by carrying a plurality of sensors on the same flight platform and collecting images from five different angles such as a vertical angle, four inclinations and the like.
S102, generating an oblique photography three-dimensional model based on the oblique photography three-dimensional data, and performing edge detection analysis on the oblique photography three-dimensional model to obtain a building contour;
and submitting the acquired oblique photography three-dimensional data to a cloud server, wherein the cloud server automatically constructs the acquired oblique photography three-dimensional data into a three-dimensional model taking a triangular surface as a basic unit, namely, an oblique photography three-dimensional model by utilizing an algorithm workflow formed by SFM (Structure from Motion) + MVS (Multi View Stereo) +mesh+texture.
Specifically, a first neural network model is built, and the first neural network model is trained;
acquiring an orthographic image of the oblique photography three-dimensional model;
and carrying out edge detection analysis on the orthographic image through the trained first neural network model to obtain the building outline.
Dividing a plurality of orthographic images into a training set, a verification set and a test set;
training the first neural network model based on the training set;
performing performance verification on the first neural network model based on the verification set, and storing the first neural network model meeting performance conditions;
and evaluating edge detection analysis capability of the first neural network model based on the test set.
S103, overlapping the building outline into the oblique photography three-dimensional model, and separating an independent model of the corresponding building from the oblique photography three-dimensional model by taking the building outline as a boundary;
specifically, by performing an orthographic edge detection analysis on oblique three-dimensional data, a preliminary model of the oblique three-dimensional model is cut out from the oblique three-dimensional data, and an independent model of the preliminary detection is obtained.
S104, carrying out building contour recognition on the side surfaces of the independent models to obtain side surface detection results of the independent models.
Specifically, an image of the independent model is obtained, and the side face of the independent model is obtained based on the image;
constructing a second neural network model and training the second neural network model;
building contour recognition is carried out on the side face through the trained second neural network model, and a side face detection result of the independent model is obtained; the side detection result comprises a ground base line, an area size and identification confidence of the independent model.
Dividing a plurality of images into a training set, a verification set and a test set;
training the second neural network model based on the training set;
performing performance verification on the second neural network model based on the verification set, and storing the second neural network model meeting performance conditions;
building contour recognition capabilities of the second neural network model are evaluated based on the test set.
And S105, judging whether the side is available or not based on the side detection result, and if so, acquiring point clouds of different side boundaries of the independent model based on the determined side range and the overlook range.
Specifically, when the side surface is not available, enlarging the interception range of the side surface;
and carrying out building contour recognition on the side surfaces of the independent models again to obtain side surface detection results of the independent models. And (3) judging a single-sided detection result through comprehensive analysis of the ground base line, the area size and the recognition confidence of the independent model. If the feasibility of the current side face is low, based on 20% of the length of the top view, expanding the intercepting range of the current side face, executing again, carrying out normal incidence edge detection analysis, and executing again the building range extraction; if the current side is determined to be more feasible, the current side is available.
S106, calculating the distance between the point clouds in the point cloud set, taking the two point clouds with the distance within a set threshold value as intersection points, and obtaining the range of the building.
Specifically, the point data set of the product appearance surface obtained by the measuring instrument in the reverse engineering is also called point cloud, the number of points obtained by using a three-dimensional coordinate measuring machine is usually small, the distance between the points is also large, and the point data set is called sparse point cloud; the point cloud obtained by using the three-dimensional laser scanner or the photographic scanner has larger and denser point number, and is called dense point cloud.
According to the building identification method based on oblique photography, three-dimensional data of oblique photography are collected; generating an oblique photography three-dimensional model based on the oblique photography three-dimensional data, and performing edge detection analysis on the oblique photography three-dimensional model to obtain a building contour; superimposing the building contour into the oblique photography three-dimensional model, and separating an independent model of a corresponding building from the oblique photography three-dimensional model with the building contour as a boundary; building contour recognition is carried out on the side face of the independent model, and a side face detection result of the independent model is obtained; judging whether the side is available or not based on the side detection result, if yes, acquiring point clouds of different side boundaries of the independent model based on the determined side range and overlook range; and calculating the distance between the point clouds in the point cloud set, taking the two point clouds with the distance within a set threshold value as intersection points, and obtaining the range of the building. The problem that in the prior art, errors exist in boundaries due to the fact that a single orthographic edge detection algorithm is used is solved.
The method is mainly applied to building identification of the oblique photography three-dimensional data, and the identified oblique photography three-dimensional data is more accurate. In the building identification process of the oblique photography three-dimensional data, the method is used for carrying out gradual analysis on irregular buildings in analysis data through a gradual analysis flow, and obtaining a more accurate building range and improving the accuracy of building identification through two-dimensional data analysis and three-dimensional point cloud boundary extraction methods on different sides.
Fig. 2-3 are flowcharts of an embodiment of a building identification system based on oblique photography according to the present invention, and as shown in fig. 2-3, the building identification system based on oblique photography according to the embodiment of the present invention includes:
an acquisition module 10 for acquiring oblique photography three-dimensional data;
an analysis module 20, configured to generate a oblique photography three-dimensional model based on the oblique photography three-dimensional data, and perform edge detection analysis on the oblique photography three-dimensional model to obtain a building contour;
a separation module 30 for superimposing the building outline into the oblique photography three-dimensional model, separating an independent model of a corresponding building from the oblique photography three-dimensional model with the building outline as a boundary;
the identifying module 40 is configured to identify a building contour on a side of the independent model, so as to obtain a side detection result of the independent model;
a judging module 50, configured to judge whether the side is available based on the side detection result, and if yes, obtain point clouds of different side boundaries of the independent model based on the determined side range and the overlook range;
the first obtaining module 60 is configured to calculate a distance between the point clouds, and obtain a range of the building by taking two point clouds with a distance within a set threshold as an intersection point.
A second acquisition module 70 for acquiring an orthographic image of the oblique photography three-dimensional model;
a first building module 80, configured to build a first neural network model and train the first neural network model;
the trained first neural network model is used for carrying out edge detection analysis on the orthographic image to obtain the building outline.
A third obtaining module 90, configured to obtain an image of the independent model, and obtain a side surface of the independent model based on the image;
the second building module is used for building a second neural network model and training the second neural network model;
the trained second neural network model is used for carrying out building contour recognition on the side face to obtain a side face detection result of the independent model; the side detection result comprises a ground base line, an area size and identification confidence of the independent model.
The judging module 50 is further configured to:
enlarging the intercepting range of the side surface when the side surface is not available;
the identification module 40 is further configured to:
and carrying out building contour recognition on the side surfaces of the independent models again to obtain side surface detection results of the independent models.
According to the building identification system based on oblique photography, oblique photography three-dimensional data are collected through the collection module 10, an oblique photography three-dimensional model is generated through the analysis module 20 based on the oblique photography three-dimensional data, and edge detection analysis is carried out on the oblique photography three-dimensional model to obtain a building contour; superimposing the building contour into the oblique photography three-dimensional model by a separation module 30, separating an independent model of a corresponding building from the oblique photography three-dimensional model with the building contour as a boundary; performing building contour recognition on the side surfaces of the independent models through the recognition module 40 to obtain side surface detection results of the independent models; judging whether the side is available or not based on the side detection result by a judging module 50, and if so, acquiring point clouds of different side boundaries of the independent model based on the determined side range and overlook range; the first obtaining module 60 calculates the distance between the point clouds, and uses the two point clouds with the distance within the set threshold as the intersection point to obtain the range of the building. The problem that in the prior art, errors exist in boundaries due to the fact that a single orthographic edge detection algorithm is used is solved.
Fig. 4 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present invention, as shown in fig. 4, an electronic device 110 includes: a processor 1101 (processor), a memory 1102 (memory), and a bus 1103;
the processor 1101 and the memory 1102 perform communication with each other through a bus 1103;
the processor 1101 is configured to invoke program instructions in the memory 1102 to perform the methods provided by the above-described method embodiments, for example, including: acquiring oblique photography three-dimensional data; generating an oblique photography three-dimensional model based on the oblique photography three-dimensional data, and performing edge detection analysis on the oblique photography three-dimensional model to obtain a building contour; superimposing the building contour into the oblique photography three-dimensional model, and separating an independent model of a corresponding building from the oblique photography three-dimensional model with the building contour as a boundary; building contour recognition is carried out on the side face of the independent model, and a side face detection result of the independent model is obtained; judging whether the side is available or not based on the side detection result, if yes, acquiring point clouds of different side boundaries of the independent model based on the determined side range and overlook range; and calculating the distance between the point clouds in the point cloud set, taking the two point clouds with the distance within a set threshold value as intersection points, and obtaining the range of the building.
The present embodiment provides a non-transitory computer readable medium storing computer instructions that cause a computer to perform the methods provided by the above-described method embodiments, for example, including: acquiring oblique photography three-dimensional data; generating an oblique photography three-dimensional model based on the oblique photography three-dimensional data, and performing edge detection analysis on the oblique photography three-dimensional model to obtain a building contour; superimposing the building contour into the oblique photography three-dimensional model, and separating an independent model of a corresponding building from the oblique photography three-dimensional model with the building contour as a boundary; building contour recognition is carried out on the side face of the independent model, and a side face detection result of the independent model is obtained; judging whether the side is available or not based on the side detection result, if yes, acquiring point clouds of different side boundaries of the independent model based on the determined side range and overlook range; and calculating the distance between the point clouds in the point cloud set, taking the two point clouds with the distance within a set threshold value as intersection points, and obtaining the range of the building.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware associated with program instructions, where the foregoing program may be stored in a computer readable medium, and when executed, the program performs steps including the above method embodiments; and the aforementioned medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
The apparatus embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable medium such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method of the respective embodiments or parts of the embodiments.
While the invention has been described in detail in the foregoing general description and specific examples, it will be apparent to those skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.
Claims (10)
1. A building identification method based on oblique photography, which is characterized by comprising the following steps:
acquiring oblique photography three-dimensional data;
generating an oblique photography three-dimensional model based on the oblique photography three-dimensional data, and performing edge detection analysis on the oblique photography three-dimensional model to obtain a building contour;
superimposing the building contour into the oblique photography three-dimensional model, and separating an independent model of a corresponding building from the oblique photography three-dimensional model with the building contour as a boundary;
building contour recognition is carried out on the side face of the independent model, and a side face detection result of the independent model is obtained;
judging whether the side is available or not based on the side detection result, if yes, acquiring point clouds of different side boundaries of the independent model based on the determined side range and overlook range;
and calculating the distance between the point clouds in the point cloud set, taking the two point clouds with the distance within a set threshold value as intersection points, and obtaining the range of the building.
2. The oblique photography-based building identification method of claim 1, wherein the generating an oblique photography three-dimensional model based on the oblique photography three-dimensional data, performing edge detection analysis on the oblique photography three-dimensional model, and obtaining a building contour, comprises:
constructing a first neural network model and training the first neural network model;
acquiring an orthographic image of the oblique photography three-dimensional model;
and carrying out edge detection analysis on the orthographic image through the trained first neural network model to obtain the building outline.
3. The oblique photography-based building identification method of claim 1, wherein the performing building contour identification on the side of the independent model to obtain the side detection result of the independent model comprises:
acquiring an image of the independent model, and acquiring a side surface of the independent model based on the image;
constructing a second neural network model and training the second neural network model;
building contour recognition is carried out on the side face through the trained second neural network model, and a side face detection result of the independent model is obtained; the side detection result comprises a ground base line, an area size and identification confidence of the independent model.
4. The oblique photography-based building identification method of claim 3, wherein the determining whether the side is available based on the side detection result, if so, based on the determined side range and top view range, obtaining point clouds of different side boundaries of the independent model comprises:
enlarging the intercepting range of the side surface when the side surface is not available;
and carrying out building contour recognition on the side surfaces of the independent models again to obtain side surface detection results of the independent models.
5. A tilt photography-based building identification system, comprising:
the acquisition module is used for acquiring oblique photographing three-dimensional data;
the analysis module is used for generating an oblique photography three-dimensional model based on the oblique photography three-dimensional data, and carrying out edge detection analysis on the oblique photography three-dimensional model to obtain a building contour;
a separation module for superimposing the building contour into the oblique photography three-dimensional model, separating an independent model of a corresponding building from the oblique photography three-dimensional model with the building contour as a boundary;
the identification module is used for carrying out building contour identification on the side face of the independent model to obtain a side face detection result of the independent model;
the judging module is used for judging whether the side face is available or not based on the side face detection result, and if yes, acquiring point clouds of different side face boundaries of the independent model based on the determined side face range and the overlooking range;
the first acquisition module is used for calculating the distance between the point clouds in the point cloud set, taking the two point clouds with the distance within a set threshold value as intersection points, and acquiring the range of the building.
6. The oblique photography-based building identification system of claim 5, further comprising:
the second acquisition module is used for acquiring an orthographic image of the oblique photography three-dimensional model;
the first building module is used for building a first neural network model and training the first neural network model;
the trained first neural network model is used for carrying out edge detection analysis on the orthographic image to obtain the building outline.
7. The oblique photography-based building identification system of claim 6, further comprising:
the third acquisition module is used for acquiring images of the independent models and acquiring the side surfaces of the independent models based on the images;
the second building module is used for building a second neural network model and training the second neural network model;
the trained second neural network model is used for carrying out building contour recognition on the side face to obtain a side face detection result of the independent model; the side detection result comprises a ground base line, an area size and identification confidence of the independent model.
8. The oblique photography-based building identification system of claim 7, wherein the determination module is further configured to:
enlarging the intercepting range of the side surface when the side surface is not available;
the identification module is also used for:
and carrying out building contour recognition on the side surfaces of the independent models again to obtain side surface detection results of the independent models.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 4 when the computer program is executed.
10. A non-transitory computer readable medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211601675.2A CN116051980B (en) | 2022-12-13 | 2022-12-13 | Building identification method, system, electronic equipment and medium based on oblique photography |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211601675.2A CN116051980B (en) | 2022-12-13 | 2022-12-13 | Building identification method, system, electronic equipment and medium based on oblique photography |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116051980A true CN116051980A (en) | 2023-05-02 |
| CN116051980B CN116051980B (en) | 2024-02-09 |
Family
ID=86124559
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211601675.2A Active CN116051980B (en) | 2022-12-13 | 2022-12-13 | Building identification method, system, electronic equipment and medium based on oblique photography |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116051980B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116777913A (en) * | 2023-08-22 | 2023-09-19 | 青岛市勘察测绘研究院 | Method, device, equipment and medium for detecting registration precision of three-dimensional model |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056659A (en) * | 2016-05-27 | 2016-10-26 | 山东科技大学 | Building corner space position automatic extraction method in vehicle laser scanning point cloud |
| CN108171720A (en) * | 2018-01-08 | 2018-06-15 | 武汉理工大学 | A kind of oblique photograph model object frontier probe method based on geometrical statistic information |
| CN111381245A (en) * | 2020-02-29 | 2020-07-07 | 天津大学 | Laser SLAM self-adaptive resolution grid map construction method |
| CN112396641A (en) * | 2020-11-17 | 2021-02-23 | 中国矿业大学(北京) | Point cloud global registration method based on congruent two-baseline matching |
| CN112927370A (en) * | 2021-02-25 | 2021-06-08 | 苍穹数码技术股份有限公司 | Three-dimensional building model construction method and device, electronic equipment and storage medium |
| CN113689567A (en) * | 2021-07-23 | 2021-11-23 | 深圳市顺欣同创科技有限公司 | Method for building in cloud end single oblique photography model |
| CN114120149A (en) * | 2021-11-09 | 2022-03-01 | 肇庆市城市规划设计院 | Oblique photogrammetry building feature point extraction method and device, electronic equipment and medium |
| CN114241211A (en) * | 2021-11-26 | 2022-03-25 | 中国船舶重工集团公司第七0四研究所 | Laser radar point cloud feature-based shoreline extraction method |
| CN114494292A (en) * | 2022-01-19 | 2022-05-13 | 武汉大势智慧科技有限公司 | Method and system for extracting building facade glass area |
| CN114511601A (en) * | 2022-01-21 | 2022-05-17 | 武汉称象科技有限公司 | Point cloud registration method based on neighborhood grid Gaussian weighted top view |
| CN114549562A (en) * | 2021-12-30 | 2022-05-27 | 深圳高速工程顾问有限公司 | UNet-based semi-automated oblique photography live-action model building singulation method, system, equipment and storage medium |
-
2022
- 2022-12-13 CN CN202211601675.2A patent/CN116051980B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056659A (en) * | 2016-05-27 | 2016-10-26 | 山东科技大学 | Building corner space position automatic extraction method in vehicle laser scanning point cloud |
| CN108171720A (en) * | 2018-01-08 | 2018-06-15 | 武汉理工大学 | A kind of oblique photograph model object frontier probe method based on geometrical statistic information |
| CN111381245A (en) * | 2020-02-29 | 2020-07-07 | 天津大学 | Laser SLAM self-adaptive resolution grid map construction method |
| CN112396641A (en) * | 2020-11-17 | 2021-02-23 | 中国矿业大学(北京) | Point cloud global registration method based on congruent two-baseline matching |
| CN112927370A (en) * | 2021-02-25 | 2021-06-08 | 苍穹数码技术股份有限公司 | Three-dimensional building model construction method and device, electronic equipment and storage medium |
| CN113689567A (en) * | 2021-07-23 | 2021-11-23 | 深圳市顺欣同创科技有限公司 | Method for building in cloud end single oblique photography model |
| CN114120149A (en) * | 2021-11-09 | 2022-03-01 | 肇庆市城市规划设计院 | Oblique photogrammetry building feature point extraction method and device, electronic equipment and medium |
| CN114241211A (en) * | 2021-11-26 | 2022-03-25 | 中国船舶重工集团公司第七0四研究所 | Laser radar point cloud feature-based shoreline extraction method |
| CN114549562A (en) * | 2021-12-30 | 2022-05-27 | 深圳高速工程顾问有限公司 | UNet-based semi-automated oblique photography live-action model building singulation method, system, equipment and storage medium |
| CN114494292A (en) * | 2022-01-19 | 2022-05-13 | 武汉大势智慧科技有限公司 | Method and system for extracting building facade glass area |
| CN114511601A (en) * | 2022-01-21 | 2022-05-17 | 武汉称象科技有限公司 | Point cloud registration method based on neighborhood grid Gaussian weighted top view |
Non-Patent Citations (1)
| Title |
|---|
| 石信肖: "基于点云的建筑物立面图快速绘制", 《北京测绘》, pages 1 - 4 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116777913A (en) * | 2023-08-22 | 2023-09-19 | 青岛市勘察测绘研究院 | Method, device, equipment and medium for detecting registration precision of three-dimensional model |
| CN116777913B (en) * | 2023-08-22 | 2023-11-03 | 青岛市勘察测绘研究院 | Method, device, equipment and medium for detecting registration precision of three-dimensional model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116051980B (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110363858B (en) | Three-dimensional face reconstruction method and system | |
| CN111063021B (en) | Method and device for establishing three-dimensional reconstruction model of space moving target | |
| US7509241B2 (en) | Method and apparatus for automatically generating a site model | |
| US9087408B2 (en) | Systems and methods for generating depthmaps | |
| CN102804231B (en) | Piecewise planar reconstruction of three-dimensional scenes | |
| Habib et al. | Generation of complex polyhedral building models by integrating stereo-aerial imagery and lidar data | |
| CN110866531A (en) | Building feature extraction method and system based on three-dimensional modeling and storage medium | |
| CN107924571A (en) | Three-dimensional reconstruction is carried out to human ear from a cloud | |
| KR20170068462A (en) | 3-Dimensional Model Generation Using Edges | |
| KR20180035869A (en) | Method, device, terminal device and storage medium | |
| CN103247045A (en) | Method of obtaining artificial scene main directions and image edges from multiple views | |
| JP4058293B2 (en) | Generation method of high-precision city model using laser scanner data and aerial photograph image, generation system of high-precision city model, and program for generation of high-precision city model | |
| CN106023147B (en) | The method and device of DSM in a kind of rapidly extracting linear array remote sensing image based on GPU | |
| CN114332134B (en) | Building facade extraction method and device based on dense point cloud | |
| CN113538501A (en) | Low-altitude image DSM generation building edge refinement method | |
| CN116051980B (en) | Building identification method, system, electronic equipment and medium based on oblique photography | |
| Wang et al. | A method for detecting windows from mobile LiDAR data | |
| Ebrahimikia et al. | True orthophoto generation based on unmanned aerial vehicle images using reconstructed edge points | |
| Rothermel et al. | Fast and robust generation of semantic urban terrain models from UAV video streams | |
| KR20060127519A (en) | Spatial information structure method based image and system thereof | |
| CN114529689B (en) | Ceramic cup defect sample amplification method and system based on antagonistic neural network | |
| Zhang et al. | Primitive-based building reconstruction by integration of Lidar data and optical imagery | |
| CN107808160B (en) | Three-dimensional building extraction method and device | |
| JP4714050B2 (en) | 3D shape model generation system | |
| CN110021041B (en) | Unmanned scene incremental gridding structure reconstruction method based on binocular camera |
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 |