CN109269472B - Method, device and storage medium for extracting feature line of oblique photogrammetry building - Google Patents

Abstract

The invention discloses a method, device and storage medium for extracting characteristic lines of buildings by oblique photogrammetry. The method includes: constructing a three-dimensional model of a specified building according to a multi-view oblique image; Three points that are not collinear in the 3D model are selected to calculate the optimal plane corresponding to the facade; the intersection of the façade. The above method can accurately extract the characteristic line of the building according to the multi-view oblique image, and improve the surveying and mapping accuracy and efficiency of the building.

Description

Method, device and storage medium for extracting feature line of oblique photogrammetry building

technical field

The invention relates to the technical field of architectural surveying and mapping, in particular to a method, a device and a storage medium for extracting characteristic lines of buildings by oblique photogrammetry.

Background technique

Oblique photogrammetry is a high-tech emerging in the field of international photogrammetry in recent years. It acquires rich high-resolution textures of the top and side views of buildings by collecting images from different perspectives. It can not only truly reflect the situation of ground objects and obtain the texture information of objects with high precision, but also generate nearly real three-dimensional city models through advanced positioning, fusion, modeling and other technologies.

Oblique images allow users to observe objects from multiple angles and reflect the actual situation of objects more realistically, which greatly makes up for the shortcomings of traditional orthophoto applications. Through supporting applications, point clouds and real-world 3D models can be generated directly based on the result images, and users can click and measure from multiple angles, expanding the application of oblique photogrammetry technology.

The real 3D model is generally generated by the veneer of massive point clouds based on the triangulation. As the camera resolution of oblique photogrammetry is getting higher and higher and the number of lenses is also increasing, the data volume of the 3D model of the real scene increases geometrically, and the efficiency of directly using the triangulation to realize the feature line search is getting lower and lower; In addition, due to the constraints of the characteristics of the triangulation network itself, it has a good fitting effect on surfaces, but it is difficult to accurately fit linear targets with non-smooth building outlines. The sharp corners of the target in the view are likely to cause a large selection deviation; in addition, due to the influence of trees, vegetation and other features, the feature lines of many buildings cannot be directly displayed on the oblique image. The above problems will lead to insufficient extraction accuracy of building feature lines and low efficiency, and it is difficult to meet the occasions where high precision requirements for building measurement are required in the fields of planning, construction, urban management and municipal administration.

SUMMARY OF THE INVENTION

Based on this, the present invention provides a method, device and storage medium for extracting characteristic lines of buildings by oblique photogrammetry, which can accurately extract characteristic lines of buildings based on multi-view oblique images and improve the accuracy and efficiency of building surveying and mapping.

An embodiment of the present invention provides a method for extracting characteristic lines of buildings from oblique photogrammetry, including:

According to the multi-view oblique image, construct the real 3D model of the specified building;

Three non-collinear points are selected from the outer facade of the three-dimensional model of the real scene to calculate the optimal plane corresponding to the outer facade;

According to the optimal plane corresponding to the two adjacent facades in the three-dimensional model of the real scene, the intersection line of the two adjacent facades is calculated.

Preferably, the three non-collinear points are selected from the outer facade of the three-dimensional model of the real scene to calculate the optimal plane corresponding to the outer facade, which specifically includes:

计算所述外立面对应的最优平面；

Calculate the optimal plane corresponding to the outer facade;

Wherein, P ₁ (x ₁ , y ₁ , z ₁ ), P ₂ (x ₂ , y ₂ , z ₂ ), P ₃ (x ₃ , y ₃ , z ₃ ) are the non-collinear facades The coordinates corresponding to the three points.

Preferably, calculating the intersection line of the two adjacent facades according to the optimal plane corresponding to the two adjacent facades in the three-dimensional model of the real scene specifically includes:

Calculate the direction vector of the intersection line and the specified coordinates passing through the intersection line according to the normal vector of the optimal plane corresponding to the two adjacent facades;

According to the direction vector of the intersection line and the specified coordinates passing through the intersection line, the intersection line of the two adjacent facades is obtained.

Preferably, according to the normal vectors of the optimal planes corresponding to the two adjacent facades, the direction vector of the intersection line and the specified coordinates passing through the intersection line are calculated, specifically including:

计算所述交线的方向向量；According to the formula

Calculate the direction vector of the intersection line;

计算过所述交线的指定坐标；According to the formula

Calculated the specified coordinates of the intersection line;

分别为两个相邻的外立面对应的最优平面的法向量。in,

are the normal vectors of the optimal planes corresponding to the two adjacent facades, respectively.

Preferably, obtaining the intersection line of the two adjacent facades according to the direction vector of the intersection line and the specified coordinates passing through the intersection line specifically includes:

计算所述交线的方程，以获得所述两个相邻的外立面的交线；According to the formula

calculating the equation of the intersection line to obtain the intersection line of the two adjacent facades;

Wherein, (0, y ₀ , z ₀ ) are the designated coordinates passing through the intersection line, and t is a parameter.

Preferably, before constructing the real-life 3D model of the designated building according to the multi-view oblique images, the method further includes:

According to the position data and attitude data of the multi-view oblique image, aerial triangulation, geometric correction, coordinate conversion and image stitching are performed on the multi-view oblique image.

The embodiment of the present invention also provides a device for extracting characteristic lines of buildings from oblique photogrammetry, including:

The model building module is used to construct a real 3D model of a specified building based on multi-view oblique images;

a plane calculation module, used to select three non-collinear points from the outer facade of the three-dimensional model of the real scene to calculate the optimal plane corresponding to the outer facade;

The intersection line calculation module is configured to calculate the intersection line of the two adjacent outer facades according to the optimal plane corresponding to the two adjacent outer facades in the three-dimensional model of the real scene.

An embodiment of the present invention further provides an apparatus for extracting feature lines of a building using oblique photogrammetry, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor executing The computer program implements the above-mentioned method for extracting characteristic lines of buildings from oblique photogrammetry.

An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, wherein when the computer program runs, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned A method for extracting characteristic lines of buildings in oblique photogrammetry.

Compared with the prior art, the beneficial effect of the method for extracting feature lines of oblique photogrammetry buildings provided by the embodiments of the present invention is that: the method for extracting feature lines of buildings using oblique photogrammetry includes: constructing a specified model according to multi-view oblique images. The real 3D model of the building; three non-collinear points are selected from the external facade of the real three-dimensional model to calculate the optimal plane corresponding to the external facade; For the optimal plane corresponding to the facade, the intersection of the two adjacent facades is calculated. The above method can accurately extract the characteristic line of the building according to the multi-view oblique image, and improve the surveying and mapping accuracy and efficiency of the building.

Description of drawings

Fig. 1 is a flow chart of a method for extracting characteristic lines of oblique photogrammetry buildings provided by an embodiment of the present invention;

Fig. 2 is a schematic diagram of some representative characteristic lines of a schematic building;

Fig. 3 is the schematic diagram that the corresponding plane is determined by the three-point vector;

Fig. 4 is the schematic diagram of solving the direction vector of the intersection line according to the normal vector of two adjacent plane sums;

FIG. 5 is a schematic diagram of an apparatus for extracting characteristic lines of buildings in oblique photogrammetry according to an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Please refer to FIG. 1 , which is a flowchart of a method for extracting feature lines of oblique photogrammetry buildings provided by an embodiment of the present invention. The method for extracting feature lines of oblique photogrammetry buildings includes:

S100: Construct a real-life 3D model of a designated building according to the multi-view oblique image;

The building feature line to be extracted is the intersection formed by the intersection of two adjacent facades. Building feature lines are straight lines such as various edge lines and intersection lines that reflect the outer contour of a building, including but not limited to the intersection lines between building surfaces, the edge lines formed by the building facade and the top surface, the slope lines of the slope, and The slope toe line, etc., can be determined according to the complexity of the building and the fineness of the modeling requirements; for example, see the schematic diagram of some representative characteristic lines of a schematic building shown in FIG. 2 .

S200: Selecting three non-collinear points from the outer facade of the three-dimensional model of the real scene to calculate the optimal plane corresponding to the outer facade;

In this embodiment, since three non-collinear points can uniquely determine a plane, the plane can be determined by directly specifying three characteristic positions on any external facade in the three-dimensional model of the real scene, or through design drawings, On-site measurement and other methods can directly obtain and input point coordinates. The principle of point selection is that it is located on the corresponding building surface, and has high image recognition, which is easy to click. At the same time, in order to improve the calculation accuracy of the elevation, it is recommended that the distance between the two points be as far as possible.

与平面M₁相垂直的关系进行解算。Referring to Figure 3, the three points P ₁ (x ₁ , y ₁ , z ₁ ), P ₂ (x ₂ , y ₂ , z ₂ ), P ₃ (x ₃ , y ₃ , z ₃ ) are not collinear with the facades ) as an example, solve to obtain the optimal plane M ₁ . The present invention uses the normal vector determined by the vector P ₁ P ₂ and the vector P ₁ P ₃

_The relationship perpendicular to the plane M1 is solved.

S300: Calculate the intersection line of the two adjacent facades according to the optimal plane corresponding to the two adjacent facades in the three-dimensional model of the real scene.

All feature lines to be extracted in the three-dimensional model of the real scene are processed sequentially according to the above steps. The generated intersection lines can be displayed directly to user equipment or used for high-precision modeling of buildings. It can also be converted to a different coordinate system for other displays. In addition, if necessary, the specific coordinate value of the characteristic line at the specified position can be directly given by the straight line equation.

The invention realizes the automatic construction and extraction of feature lines for multi-view oblique images in an interactive process, generates corresponding feature lines based on the construction of adjacent facades, and ensures the accuracy of feature lines through the constraints of multiple surfaces , rigor and robustness. The invention improves the shortcomings of the traditional method in terms of operation efficiency, convenience and accuracy. Moreover, even for the feature lines of buildings that cannot be directly seen on the image due to problems such as occlusion, viewing angle, etc., the present invention can be used to accurately extract the feature lines of buildings. efficiency. It has broad application prospects in related fields such as UAV low-altitude aerial surveys, ground or aerial oblique photogrammetry, and rapid measurement of large-scale topographic maps.

In an optional embodiment, S200: Select three non-collinear points from the outer facade of the three-dimensional model of the real scene to calculate the optimal plane corresponding to the outer facade, which specifically includes:

计算所述外立面对应的最优平面；According to the formula

Calculate the optimal plane corresponding to the outer facade;

Wherein, P ₁ (x ₁ , y ₁ , z ₁ ), P ₂ (x ₂ , y ₂ , z ₂ ), P ₃ (x ₃ , y ₃ , z ₃ ) are the non-collinear facades The coordinates corresponding to the three points.

In an optional embodiment, calculating the intersection line of the two adjacent facades according to the optimal plane corresponding to the two adjacent facades in the three-dimensional model of the real scene, specifically includes: :

Calculate the direction vector of the intersection line and the specified coordinates passing through the intersection line according to the normal vector of the optimal plane corresponding to the two adjacent facades;

According to the direction vector of the intersection line and the specified coordinates passing through the intersection line, the intersection line of the two adjacent facades is obtained.

In an optional embodiment, according to the normal vectors of the optimal planes corresponding to two adjacent facades, the direction vector of the intersection line and the specified coordinates passing through the intersection line are calculated, specifically including:

计算所述交线的方向向量；According to the formula

Calculate the direction vector of the intersection line;

计算过所述交线的指定坐标；According to the formula

Calculated the specified coordinates of the intersection line;

Assuming that x=0 in the specified coordinates passing through the intersection line, the specified coordinates passing through the intersection line can be solved as (0, y ₀ , z ₀ ) through the above formula.

分别为两个相邻的外立面对应的最优平面的法向量。in,

are the normal vectors of the optimal planes corresponding to the two adjacent facades, respectively.

Referring to Fig. 4, according to the normal vectors of the two adjacent facades M ₁ and M ₂ , the direction vector of the intersection line L is obtained by using the orthogonality

In an optional embodiment, obtaining the intersection line of the two adjacent facades according to the direction vector of the intersection line and the specified coordinates passing through the intersection line specifically includes:

计算所述交线的方程，以获得所述两个相邻的外立面的交线；According to the formula

calculating the equation of the intersection line to obtain the intersection line of the two adjacent facades;

Wherein, (0, y ₀ , z ₀ ) are the designated coordinates passing through the intersection line, and t is a parameter.

In an optional embodiment, S100: according to the multi-view oblique image, before constructing the real-life three-dimensional model of the specified building, the method further includes:

According to the position data and attitude data of the multi-view oblique image, aerial triangulation, geometric correction, coordinate conversion and image stitching are performed on the multi-view oblique image.

Due to the low altitude and high resolution of UAVs, and limited by the viewing angle, the surveying and mapping of large buildings such as houses can only be fully covered by collecting multi-angle images from multiple stations. Therefore, it is necessary to collect multi-view images of designated buildings Oblique images, and based on the position (GPS) data and attitude (POS) data of the multi-view oblique images, the general methods are used for aerial triangulation, geometric correction, coordinate transformation and image stitching and other preprocessing, resulting in a large amount of data and a high degree of overlap. And the image data with rich viewing angles, so that the constructed point cloud and the real 3D model are in the same space rectangular coordinate system as the measurement projection plane, which is convenient for subsequent unified processing.

If the multi-view oblique image adopts other coordinate systems such as geodetic latitude and longitude coordinates or instrument coordinates, image coordinates, etc., it can also be converted to a space rectangular coordinate system in advance.

Further, the construction process of the three-dimensional model of the real scene is as follows:

(1) according to the position data and the attitude data, perform aerial triangulation on the multi-view oblique images to obtain high-precision outer orientation elements of all images,

(2) A high-density 3D point cloud is obtained by intensive matching of the multi-view oblique image and the external orientation elements based on the distortion-corrected multi-view image, and a 3D TIN model is constructed;

The dense matching of multi-view images can obtain high-density digital point clouds, and the digital table and model (DSM) can be used for later model construction and orthophoto generation by optimizing the network construction algorithm. After the multi-view oblique image is combined with the aerial triangulation, the external orientation elements of each image are calculated, and the best image matching unit is analyzed and selected for feature matching and pixel-by-pixel matching. The introduction of parallel algorithms can improve the calculation efficiency. After obtaining high-density DSM data, filtering can be performed, that is, different matching units are fused to form a unified DSM. The high-density point cloud data obtained through dense matching is very large and needs to be cut and divided into blocks. According to the computer performance and the set priority, the irregular triangulation network can be constructed for the diced point cloud data. Specifically: (1) using the multi-view oblique image information of the same object at different angles, and adopting a matching strategy that refers to the multi-view oblique image is not fixed pixel by pixel; (2) based on the redundant information of multi-view matching to avoid occlusion pair matching In addition, the parallel algorithm is introduced to improve the computing efficiency to quickly and accurately obtain the coordinates of the point with the same name on the multi-view oblique image, and then obtain the high-density 3D point cloud data of the ground objects; (3) Based on the point cloud, construct different levels of detail (Levels of Detail) triangulation network (TIN) model. By optimizing the triangulation network, the size of the inner triangles is adjusted to a ratio matching the resolution of the original multi-view oblique image, and the triangulation network in relatively flat areas is simplified by analyzing the changes of the continuum, reducing data redundancy, and obtaining TIN model vector architecture.

(3) According to the angle between the normal equation of each triangular facet in the 3D TIN model and the two-dimensional image (that is, the multi-view oblique image), the corresponding optimal texture information is selected to realize the automatic association of textures;

Automatic texture mapping is mainly based on tile technology, that is, the entire modeling area is divided into several sub-regions (tiles) of a certain size, and each tile is packaged and established as a task based on the parallel processing mechanism of the cluster processing system. The computing node performs the registration and texture attachment of the model and the texture image, and at the same time establishes a multi-detail and multi-level LOD for the textured model, which is convenient for optimizing the corresponding file organization structure and improving the efficiency of hierarchical browsing of the model, so as to generate the final Realistic 3D model.

(4) Output and obtain the three-dimensional model of the real scene.

An embodiment of the present invention further provides an apparatus for extracting feature points of a building using oblique photogrammetry, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor executes The computer program implements the above-mentioned method for extracting feature points of buildings by oblique photogrammetry.

Please refer to FIG. 5 , which is a schematic diagram of a device for extracting characteristic lines of buildings using oblique photogrammetry provided by an embodiment of the present invention. The device for extracting characteristic lines of buildings using oblique photogrammetry includes:

The model building module 1 is used to build a real 3D model of a designated building according to the multi-view oblique image;

The building feature line to be extracted is the intersection formed by the intersection of two adjacent facades. Building feature lines are straight lines such as various edge lines and intersection lines that reflect the outer contour of a building, including but not limited to the intersection lines between building surfaces, the edge lines formed by the building facade and the top surface, the slope lines of the slope, and The slope toe line, etc., can be determined according to the complexity of the building and the fineness of the modeling requirements; for example, see the schematic diagram of some representative characteristic lines of a schematic building shown in FIG. 2 .

The plane calculation module 2 is used to select three non-collinear points from the outer facade of the three-dimensional model of the real scene to calculate the optimal plane corresponding to the outer facade;

In this embodiment, since three non-collinear points can uniquely determine a plane, the plane can be determined by directly specifying three characteristic positions on any external facade in the three-dimensional model of the real scene, or through design drawings, On-site measurement and other methods can directly obtain and input point coordinates. The principle of point selection is that it is located on the corresponding building surface, and has high image recognition, which is easy to click. At the same time, in order to improve the calculation accuracy of the elevation, it is recommended that the distance between the two points be as far as possible.

与平面M₁相垂直的关系进行解算。Referring to Figure 3, the three points P ₁ (x ₁ , y ₁ , z ₁ ), P ₂ (x ₂ , y ₂ , z ₂ ), P ₃ (x ₃ , y ₃ , z ₃ ) are not collinear with the facades ) as an example, solve to obtain the optimal plane M ₁ . The present invention uses the normal vector determined by the vector P ₁ P ₂ and the vector P ₁ P ₃

_The relationship perpendicular to the plane M1 is solved.

The intersection line calculation module 3 is configured to calculate the intersection line of the two adjacent outer facades according to the optimal plane corresponding to the two adjacent outer facades in the three-dimensional model of the real scene.

All feature lines to be extracted in the three-dimensional model of the real scene are processed sequentially according to the above steps. The generated intersection lines can be displayed directly to user equipment or used for high-precision modeling of buildings. It can also be converted to a different coordinate system for other displays. In addition, if necessary, the specific coordinate value of the characteristic line at the specified position can be directly given by the straight line equation.

The invention realizes the automatic construction and extraction of feature lines for multi-view oblique images in an interactive process, generates corresponding feature lines based on the construction of adjacent facades, and ensures the accuracy of feature lines through the constraints of multiple surfaces , rigor and robustness. The invention improves the shortcomings of the traditional method in terms of operation efficiency, convenience and accuracy. Moreover, even for the feature lines of buildings that cannot be directly seen on the image due to problems such as occlusion, viewing angle, etc., the present invention can be used to accurately extract the feature lines of buildings. efficiency. It has broad application prospects in related fields such as UAV low-altitude aerial surveys, ground or aerial oblique photogrammetry, and rapid measurement of large-scale topographic maps.

In an optional embodiment, the plane calculation module 2 is specifically configured to calculate according to the formula

计算所述外立面对应的最优平面；

Calculate the optimal plane corresponding to the outer facade;

Wherein, P ₁ (x ₁ , y ₁ , z ₁ ), P ₂ (x ₂ , y ₂ , z ₂ ), P ₃ (x ₃ , y ₃ , z ₃ ) are the non-collinear facades The coordinates corresponding to the three points.

In an optional embodiment, the intersection calculation module 3 specifically includes:

The intersection line feature calculation unit is used to calculate the direction vector of the intersection line and the specified coordinates passing through the intersection line according to the normal vector of the optimal plane corresponding to the two adjacent facades;

The intersection line obtaining unit is configured to obtain the intersection line of the two adjacent facades according to the direction vector of the intersection line and the specified coordinates passing through the intersection line.

In an optional embodiment, the intersection line feature calculation unit includes:

计算所述交线的方向向量；Direction vector calculation unit, used to calculate according to the formula

Calculate the direction vector of the intersection line;

计算过所述交线的指定坐标；Coordinate calculation unit, used to calculate according to the formula

Calculated the specified coordinates of the intersection line;

Assuming that x=0 in the specified coordinates passing through the intersection line, the specified coordinates passing through the intersection line can be solved as (0, y ₀ , z ₀ ) through the above formula.

分别为两个相邻的外立面对应的最优平面的法向量。in,

are the normal vectors of the optimal planes corresponding to the two adjacent facades, respectively.

Referring to Fig. 4, according to the normal vectors of the two adjacent facades M ₁ and M ₂ , the direction vector of the intersection line L is obtained by using the orthogonality

计算所述交线的方程，以获得所述两个相邻的外立面的交线；In an optional embodiment, the intersection line obtaining unit is specifically configured to

calculating the equation of the intersection line to obtain the intersection line of the two adjacent facades;

Wherein, (0, y ₀ , z ₀ ) are the designated coordinates passing through the intersection line, and t is a parameter.

In an optional embodiment, the device for extracting characteristic lines of buildings from oblique photogrammetry further includes:

The data preprocessing module is configured to perform aerial triangulation, geometric correction, coordinate conversion and image stitching on the multi-view oblique image according to the position data and attitude data of the multi-view oblique image.

Due to the low altitude and high resolution of UAVs, and limited by the viewing angle, the surveying and mapping of large buildings such as houses can only be fully covered by collecting multi-angle images from multiple stations. Therefore, it is necessary to collect multi-view images of designated buildings Oblique images, and based on the position (GPS) data and attitude (POS) data of the multi-view oblique images, the general methods are used for aerial triangulation, geometric correction, coordinate transformation and image stitching and other preprocessing, resulting in a large amount of data and a high degree of overlap. And the image data with rich viewing angles, so that the constructed point cloud and the real 3D model are in the same space rectangular coordinate system as the measurement projection plane, which is convenient for subsequent unified processing.

If the multi-view oblique image adopts other coordinate systems such as geodetic latitude and longitude coordinates or instrument coordinates, image coordinates, etc., it can also be converted to a space rectangular coordinate system in advance.

Further, the construction process of the three-dimensional model of the real scene is as follows:

(1) according to the position data and the attitude data, perform aerial triangulation on the multi-view oblique images to obtain high-precision outer orientation elements of all images,

(2) A high-density 3D point cloud is obtained by intensive matching of the multi-view oblique image and the external orientation elements based on the distortion-corrected multi-view image, and a 3D TIN model is constructed;

The dense matching of multi-view images can obtain high-density digital point clouds, and the digital table and model (DSM) can be used for later model construction and orthophoto generation by optimizing the network construction algorithm. After the multi-view oblique image is combined with the aerial triangulation, the external orientation elements of each image are calculated, and the best image matching unit is analyzed and selected for feature matching and pixel-by-pixel matching. The introduction of parallel algorithms can improve the calculation efficiency. After obtaining high-density DSM data, filtering can be performed, that is, different matching units are fused to form a unified DSM. The high-density point cloud data obtained through dense matching is very large and needs to be cut and divided into blocks. According to the computer performance and the set priority, the irregular triangulation network can be constructed for the diced point cloud data. Specifically: (1) using the multi-view oblique image information of the same object at different angles, and adopting a matching strategy that refers to the multi-view oblique image is not fixed pixel by pixel; (2) based on the redundant information of multi-view matching to avoid occlusion pair matching In addition, the parallel algorithm is introduced to improve the computing efficiency to quickly and accurately obtain the coordinates of the point with the same name on the multi-view oblique image, and then obtain the high-density 3D point cloud data of the ground objects; (3) Based on the point cloud, construct different levels of detail (Levels of Detail) triangulation network (TIN) model. By optimizing the triangulation network, the size of the inner triangles is adjusted to a ratio matching the resolution of the original multi-view oblique image, and the triangulation network in relatively flat areas is simplified by analyzing the changes of the continuum, reducing data redundancy, and obtaining TIN model vector architecture.

(3) According to the angle between the normal equation of each triangular facet in the 3D TIN model and the two-dimensional image (that is, the multi-view oblique image), the corresponding optimal texture information is selected to realize the automatic association of textures;

Automatic texture mapping is mainly based on tile technology, that is, the entire modeling area is divided into several sub-regions (tiles) of a certain size, and each tile is packaged and established as a task based on the parallel processing mechanism of the cluster processing system. The computing node performs the registration and texture attachment of the model and the texture image, and at the same time establishes a multi-detail and multi-level LOD for the textured model, which is convenient for optimizing the corresponding file organization structure and improving the efficiency of hierarchical browsing of the model, so as to generate the final Realistic 3D model.

(4) Output and obtain the three-dimensional model of the real scene.

An embodiment of the present invention further provides an apparatus for extracting feature points of a building using oblique photogrammetry, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor executes The computer program implements the above-mentioned method for extracting feature points of buildings by oblique photogrammetry.

An embodiment of the present invention further provides an apparatus for extracting feature lines of a building using oblique photogrammetry, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor executing The computer program implements the above-mentioned method for extracting characteristic lines of buildings from oblique photogrammetry.

Exemplarily, the computer program may be divided into one or more modules/units, and the one or more modules/units are stored in the memory and executed by the processor to accomplish the present invention. The one or more modules/units may be a series of computer program instruction segments capable of accomplishing specific functions, and the instruction segments are used to describe the execution process of the computer program in the apparatus for extracting characteristic lines of buildings using oblique photogrammetry. For example, the computer program can be divided into functional modules of the apparatus for extracting characteristic lines of buildings with oblique photogrammetry as shown in FIG. 5 .

The device for extracting characteristic lines of buildings by tilt photogrammetry can be computing devices such as mobile phones, desktop computers, notebooks, palmtop computers, and cloud servers. The device for extracting characteristic lines of buildings using oblique photogrammetry may include, but is not limited to, a processor and a memory. For example, the apparatus for extracting characteristic lines of buildings using oblique photogrammetry may further include input and output devices, network access devices, buses, and the like.

The processor may be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf processors Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., the processor is the control center of the device for extracting characteristic lines of a building in oblique photogrammetry, and uses various interfaces and lines to connect the entire system. Oblique photogrammetry of various parts of the building feature line extraction device.

The memory can be used to store the computer program and/or module, and the processor implements the tilt by running or executing the computer program and/or module stored in the memory and calling the data stored in the memory. Various functions of the photogrammetric building feature line extraction device. The memory may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the storage data area may store Data (such as audio data, phonebook, etc.) created according to the usage of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, internal memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

Wherein, if the integrated modules/units of the device for extracting characteristic lines of buildings using oblique photogrammetry are implemented in the form of software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the processes in the methods of the above embodiments, and can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer When the program is executed by the processor, the steps of the foregoing method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form, and the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable media may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer-readable media Electric carrier signals and telecommunication signals are not included.

An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, wherein when the computer program runs, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned A method for extracting characteristic lines of buildings in oblique photogrammetry.

Compared with the prior art, the beneficial effect of the method for extracting feature lines of oblique photogrammetry buildings provided by the embodiments of the present invention is that: the method for extracting feature lines of buildings using oblique photogrammetry includes: constructing a specified model according to multi-view oblique images. The real 3D model of the building; three non-collinear points are selected from the external facade of the real three-dimensional model to calculate the optimal plane corresponding to the external facade; For the optimal plane corresponding to the facade, the intersection of the two adjacent facades is calculated. The above method can accurately extract the characteristic line of the building according to the multi-view oblique image, and improve the surveying and mapping accuracy and efficiency of the building.

It should be noted that the device embodiments described above are only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical unit, that is, it can be located in one place, or it can be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative effort.

The above are the preferred embodiments of the present invention, it should be pointed out that for those skilled in the art, without departing from the principles of the present invention, several improvements and modifications can also be made, and these improvements and modifications are also regarded as the present invention. the scope of protection of the invention.

Claims (5)

1. a method for extracting characteristic lines of oblique photogrammetry buildings, is characterized in that, comprises: According to the multi-view oblique image, construct the real 3D model of the specified building; Three non-collinear points are selected from the outer facade of the three-dimensional model of the real scene to calculate the optimal plane corresponding to the outer facade; Calculate the intersection line of the two adjacent facades according to the optimal plane corresponding to the two adjacent facades in the three-dimensional model of the real scene; The selection of three non-collinear points from the outer façade of the three-dimensional model of the real scene to calculate the optimal plane corresponding to the outer façade specifically includes: According to the formula

Calculate the optimal plane corresponding to the outer facade; Wherein, P ₁ (x ₁ , y ₁ , z ₁ ), P ₂ (x ₂ , y ₂ , z ₂ ), P ₃ (x ₃ , y ₃ , z ₃ ) are the non-collinear facades The coordinates corresponding to the three points; The calculation of the intersection line of the two adjacent facades according to the optimal plane corresponding to the two adjacent facades in the three-dimensional model of the real scene specifically includes: According to the formula

Calculate the direction vector of the intersection line; According to the formula

Calculated the specified coordinates of the intersection line; in,

are the normal vectors of the optimal planes corresponding to the two adjacent facades; According to the formula

calculating the equation of the intersection line to obtain the intersection line of the two adjacent facades; Wherein, (0, y ₀ , z ₀ ) are the designated coordinates passing through the intersection line, and t is a parameter. 2. The method for extracting feature lines of oblique photogrammetry buildings as claimed in claim 1, wherein, before constructing the real 3D model of the designated building according to the multi-view oblique image, the method further comprises: According to the position data and attitude data of the multi-view oblique image, aerial triangulation, geometric correction, coordinate conversion and image stitching are performed on the multi-view oblique image. 3. A device for extracting characteristic lines of oblique photogrammetry buildings, characterized in that, comprising: The model building module is used to construct a real 3D model of a specified building based on multi-view oblique images; a plane calculation module, used to select three non-collinear points from the outer facade of the three-dimensional model of the real scene to calculate the optimal plane corresponding to the outer facade; an intersection calculation module, configured to calculate the intersection of the two adjacent facades according to the optimal plane corresponding to the two adjacent facades in the three-dimensional model of the real scene; The plane calculation module is specifically used to calculate according to the formula

Calculate the optimal plane corresponding to the outer facade; Wherein, P ₁ (x ₁ , y ₁ , z ₁ ), P ₂ (x ₂ , y ₂ , z ₂ ), P ₃ (x ₃ , y ₃ , z ₃ ) are the non-collinear facades The coordinates corresponding to the three points; The intersection line calculation module is specifically used to calculate according to the formula

Calculate the direction vector of the intersection line; According to the formula

Calculated the specified coordinates of the intersection line; in,

are the normal vectors of the optimal planes corresponding to the two adjacent facades; According to the formula

calculating the equation of the intersection line to obtain the intersection line of the two adjacent facades; Wherein, (0, y ₀ , z ₀ ) are the designated coordinates passing through the intersection line, and t is a parameter. 4. An apparatus for extracting characteristic lines of buildings using oblique photogrammetry, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor executing the When the computer program is used, the method for extracting characteristic lines of buildings in oblique photogrammetry according to any one of claims 1 to 2 is realized. 5. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored computer program, wherein, when the computer program is run, the device where the computer-readable storage medium is located is controlled to execute as claimed in the claims The method for extracting characteristic lines of oblique photogrammetry buildings according to any one of 1 to 2.

Images