CN115457413A - Information extraction method, device, computer equipment, storage medium - Google Patents

Abstract

The present application relates to an information extraction method, device, computer equipment, storage medium and computer program product. The method includes: receiving an image of a target object; constructing a three-dimensional model corresponding to the image of the target object according to the image of the target object; obtaining a target reference plane based on the three-dimensional model, and performing unit extraction on the target reference plane A plurality of information units are obtained; the information units satisfying the target condition are calculated to obtain target area information. By adopting the method, the information of the target object can be extracted rapidly and in batches.

Description

Information extraction method, device, computer equipment, storage medium

technical field

The present application relates to the field of computer vision, in particular to an information extraction method, device, computer equipment, storage medium and computer program product.

Background technique

In recent years, with the advancement of technologies and methods such as UAV telemetry, the resolution of the remote sensing data captured by it has been high enough to contain all the information required for the calculation of the potential of distributed photovoltaics on the rooftops of urban buildings.

However, compared with the development of remote sensing technology, the development of remote sensing image information extraction technology is still relatively backward. Traditional technologies are based on satellite remote sensing images, manual measurement, etc. Since satellite remote sensing images can only be used for rough building edge information extraction, the accuracy is low, and manual measurement is inefficient, time-consuming and laborious. At present, how to batch and quickly extract urban building roof information is an urgent problem to be solved.

Contents of the invention

Based on this, it is necessary to provide an information extraction method, device, computer equipment, computer-readable storage medium, and computer program product that can perform batch, fast, and accurate information extraction on target objects for the above technical problems.

In a first aspect, the present application provides an information extraction method, the method comprising:

Receive the image of the target object;

Constructing a three-dimensional model corresponding to the target object image according to the target object image;

obtaining a target reference plane based on the three-dimensional model, and performing unit extraction on the target reference plane to obtain a plurality of information units;

The information units satisfying the target condition are calculated to obtain the target area information.

In one of the embodiments, the target reference plane is obtained based on the three-dimensional model, and the target reference plane is extracted to obtain a plurality of information units, including:

performing target detection in the three-dimensional model to obtain a target cube;

Projecting the target cube to obtain the target datum plane;

The target reference plane is cut according to a preset threshold to obtain a plurality of the information units.

In one of the embodiments, the calculation of the information units satisfying the target condition to obtain the target area information includes:

drawing a plumb line at the target position of each of the information units to obtain an intersection point between the plumb line and the three-dimensional model;

When the intersection point is a target intersection point, it is determined that the information unit where the target intersection point is located satisfies a target condition;

The information unit where the target intersection is located is extracted, and the target area information is obtained according to the information unit where the target intersection is located.

In one of the embodiments, the determination method of the target intersection includes:

Obtain the reference plane according to the intersection point;

judging the intersection point according to the reference plane and a preset value;

When the difference between the intersection point and the reference plane is greater than the preset value, it is determined that the intersection point is a target intersection point.

In one of the embodiments, drawing a plumb line at the target position of each information unit to obtain the intersection point between the plumb line and the three-dimensional model includes:

drawing a plumb line at the target position of each of the information units to obtain at least one initial intersection point between the plumb line and the three-dimensional model;

Screening is performed from the initial intersection points according to a preset method to obtain intersection points between the plumb line and the model.

In one of the embodiments, the extraction of a plurality of information units based on the three-dimensional model, and the acquisition of the target area information based on the plurality of information units and the three-dimensional model is achieved through information extraction based on workflow in advance. The model is obtained after running according to the preset parameters.

In a second aspect, the present application also provides an information extraction device, which includes:

The receiving module is used to receive the image of the target object;

A construction module, configured to construct a three-dimensional model corresponding to the target object image according to the target object image;

A unit extraction module, configured to obtain a target reference plane based on the three-dimensional model, and perform unit extraction on the target reference plane to obtain a plurality of information units;

A calculation module, configured to perform calculation on said information units to obtain target area information when at least one of said information units meets a target condition.

In a third aspect, the present application also provides a computer device, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the method in any one of the above embodiments when executing the computer program A step of.

In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method in any one of the above-mentioned embodiments is implemented. step.

In a fifth aspect, the present application further provides a computer program product, the computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method in any one of the foregoing embodiments are implemented.

In the above information extraction method, device, computer equipment, storage medium and computer program product, the server first receives the image of the target object, and then constructs a three-dimensional model corresponding to the target object based on the image of the target object, and then obtains the target reference plane based on the three-dimensional model, and The unit is extracted from the target datum plane to obtain multiple information units, and finally the information units satisfying the conditions are calculated to obtain the target area information. First of all, the server uses the target area information obtained from the target object image, so there is no need for manual on-site measurement, which can reduce a lot of manual expenditure; secondly, the information unit required to calculate the target area information can be screened through the target condition, and the target can be realized. The area information is calculated in batches, and the calculation of the target area information by using the information units meeting the target conditions can reduce the amount of calculation, so as to achieve fast calculation to obtain the target area information.

Description of drawings

Fig. 1 is an application environment diagram of the information extraction method in an embodiment;

Fig. 2 is a schematic flow chart of an information extraction method in an embodiment;

Fig. 3 is a schematic diagram of a three-dimensional model in an embodiment;

Fig. 4 is a schematic diagram of unit extraction in an embodiment;

Fig. 5 is a schematic diagram of drawing a plumb line in one embodiment;

FIG. 6 is a schematic flow chart of calculating target area information using a workflow model in an embodiment;

Fig. 7 is a schematic diagram of the steps of applying the information extraction method to the roof of a building in an embodiment;

Fig. 8 is a schematic diagram of a target object image of oblique photography in an embodiment;

Fig. 9 is a structural block diagram of an information extraction device in an embodiment;

Figure 10 is a diagram of the internal structure of a computer device in one embodiment.

detailed description

In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

The information extraction method provided in the embodiment of the present application may be applied in the application environment shown in FIG. 1 . Wherein, the terminal 102 communicates with the server 104 through the network. The data storage system can store data that needs to be processed by the server 104 . The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The terminal 102 sends the image of the target object to the server 104. After receiving the image of the target object, the server 104 constructs a three-dimensional model corresponding to the image of the target object according to the image of the target object, and then obtains the target reference plane based on the three-dimensional model, and performs unit extraction on the target reference plane. Get multiple information units. After the information unit is obtained, it is judged whether the information unit satisfies the target condition, and the information unit satisfying the target condition is calculated to obtain the target area information. Among them, the terminal 102 can be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices, and the Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. . Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, and the like. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

In one embodiment, as shown in FIG. 2, a method for extracting information is provided. The method is applied to the server 104 in FIG. 1 as an example for illustration, including the following steps:

S202. Receive an image of a target object.

Among them, the target object refers to the object that needs to be extracted, which can be a pre-designated building, such as an office building, or a building or area, such as drawn in the form of a closed polygon on the UAV aerial survey map. Out of the area to which the target building belongs.

Optionally, the target object image sent by the terminal to the server is compressed, so the server first decompresses the target object image after receiving it, and then further processes the target object image, and the terminal sends the compressed target object image to the server , it is possible to quickly send a large number of target object images to the server at the same time, so that the server can perform batch processing on the target object images.

Optionally, when the terminal is a UAV, parameters such as the flight height (the flight height is generally the height of the highest point in the target building plus more than 10 meters), route overlap rate and other parameters can be set in the UAV remote control system. After oblique photography is performed according to the above parameters, the captured image of the target object is sent to the server.

S204. Construct a three-dimensional model corresponding to the target object image according to the target object image.

Optionally, the image of the target object can be imported into the Dajiang Zhitu software, and the preset parameters can be set. The Jiangzhitu software will build a 3D model according to the image of the target object and the set parameters. It can be combined with Figure 3, which is an implementation The schematic diagram of the 3D model in the example. Wherein, the preset parameters refer to the parameters required for constructing the 3D model, and the preset parameters may be the format of the 3D model (such as OBJ format), accuracy, and the like.

Optionally, after the service obtains the image of the target object, it may perform preprocessing on the image of the target object, such as enhancing and denoising, so as to establish a more accurate 3D model.

S206. Obtain the target reference plane based on the three-dimensional model, and perform unit extraction on the target reference plane to obtain a plurality of information units.

Among them, the target datum plane refers to the datum plane used to extract the unit of the target object, which is a plane kept horizontal to the building in the 3D model, which can be obtained after the target detection of the 3D model; the information unit refers to the plane from the target datum plane Obtained in , including the unit of 3D model information.

Optionally, after the server performs target recognition on the 3D model, it can obtain a cube including all objects in the 3D model whose xyz axes are parallel, and then use the Z-axis plane of the cube as the target reference plane.

Optionally, after obtaining the target datum plane, the server performs unit extraction on the target datum plane, wherein the unit extraction may be cut from the target datum plane according to a preset threshold to obtain multiple information units. Wherein, the preset threshold refers to a preset size for cutting the target reference plane. For example, the preset threshold can be set to 0.1m (centimeter), and then the server divides the target reference plane according to 0.1m to obtain multiple The default threshold is the unit of side length (0.1m*0.1m).

S208. Calculate the information units satisfying the target condition to obtain target area information.

Wherein, the target area information refers to information such as the contour and area of the target object that is finally needed, which can be calculated according to the information unit.

Among them, the target condition refers to the pre-set condition for judging the information unit. For example, if the roof area of the building is currently calculated, then the target condition can be set as whether the information unit is a roof unit, that is, whether it is a building Information unit on the roof.

After obtaining the information unit, the server first judges whether the information unit satisfies the target condition, so as to obtain all the information units that meet the target condition, and then calculates the target area information according to all the information units that meet the target condition, for example, for all the information units in the information unit The contour of the included target object is calculated to obtain the contour of the completed target object.

Optionally, the target condition can be set as the information unit is the location of the area to be extracted and whether it is a roof unit, and the area information of any object in the 3D model can be calculated by setting the area location. Exemplarily, if it is necessary to calculate the roof profile of building A in the 3D model, then the target condition can be set as the area position of building A and both are roof units, so that the server can calculate the building A when making a judgment. Filter information units other than the roof unit of object A, and then calculate the roof profile of building A based on the roof unit of building A.

In the above information extraction method, the server first receives the image of the target object, and then constructs a 3D model corresponding to the target object based on the image of the target object, and then obtains the target reference plane based on the 3D model, and performs unit extraction on the target reference plane to obtain multiple pieces of information units, and finally calculate the information units that meet the conditions to obtain the target area information. First of all, the server uses the target area information obtained from the target object image, so there is no need for manual on-site measurement, which can reduce a lot of manual expenditure; secondly, the information unit required to calculate the target area information can be screened through the target condition, and the target can be realized. Batch and accurate calculation of area information, and the use of information units that meet the target conditions to calculate target area information can reduce the amount of calculation to achieve rapid calculation to obtain target area information.

In one embodiment, the target reference plane is obtained based on the 3D model, and a plurality of information units are obtained by performing unit extraction on the target reference plane, including: performing target detection in the 3D model to obtain the target cube; projecting the target cube to obtain the target Datum plane: cut the target datum plane according to the preset threshold to obtain multiple information units.

Among them, the target cube refers to the cube that can include the smallest volume of the entire target object after the target detection on the 3D model and whose sides are parallel to the xyz axis, so as to avoid the excessive size of the target cube and cause waste in the subsequent calculation process.

The server performs target detection in the 3D model to obtain a target cube that can include the entire target object, and then projects the target cube. Optionally, the target cube can be projected onto the world XY plane to obtain the target reference plane. Then, the target reference plane is cut according to the preset threshold to obtain a plurality of information units with the preset threshold as the side length.

As shown in FIG. 4 , FIG. 4 is a schematic diagram of unit extraction in an embodiment. The cube in the figure is the target cube, the object inside the cube is the target object, and the grid above the cube is a plurality of information units.

In the above embodiments, the reason why the server uses the target cube is to ensure that the target reference plane obtained later can cover the entire target object.

In one embodiment, calculating the information units satisfying the target condition to obtain the target area information includes: drawing a plumb line at the target position of each information unit to obtain the intersection point of the vertical line and the three-dimensional model; when the intersection point is the target intersection point , determine that the information unit where the target intersection is located satisfies the target condition; extract the information unit where the target intersection is located, and calculate according to the information unit where the target intersection is located to obtain the target area information.

Wherein, the target position refers to a preset position on the information unit, and the target position may be the center of each information unit.

The server draws a plumb line with a preset length at the target position of each information unit, so that the intersection point of the plumb line and the three-dimensional model can be obtained. When the intersection point is the target intersection point, it can be determined that the information unit where the target intersection point is located satisfies the target condition. Then, the information unit where the target intersection is located is extracted, and calculation is performed based on the information unit where the target intersection is located to obtain target area information.

Exemplarily, if the target area information to be obtained is the building roof outline of the target object, then the target condition can be set as whether the information unit is a roof unit, that is, whether it is an information unit that constitutes the roof of the building, and the target intersection is the roof intersection, When the intersection point between the plumb line of the information sheet and the 3D model is the roof intersection point, it is determined that the information unit where the target intersection point is located meets the target condition, that is, the information unit where the target intersection point is located is a roof unit, and then the calculation is performed based on the information unit where the target intersection point is located To obtain the target area information, for example, splicing according to the roof profile included in the roof unit, the building roof profile of the target object can be obtained.

As shown in FIG. 5 , FIG. 5 is a schematic diagram of drawing a plumb line in an embodiment. The straight line perpendicular to the information unit in the figure is a plumb line, so that the intersection point with the three-dimensional model can be obtained by drawing the plumb line.

In the above-mentioned embodiment, the server can obtain the intersection point with the 3D model by drawing a plumb line, and then judge whether the intersection point is the target intersection point, and then calculate according to the information unit where the target intersection point is located, obtain the target area information, and extract Calculation by the information unit where the target intersection point is located can reduce the amount of calculation, so as to achieve fast calculation to obtain the information of the target area.

In one embodiment, the method for judging the target intersection includes: obtaining the reference plane according to the intersection point; judging the intersection point according to the reference plane and a preset value; when the difference between the intersection point and the reference plane is greater than the preset value, determining that the intersection point is target intersection.

Wherein, the reference plane refers to a plane obtained according to the intersection point and used for judging whether the intersection point is a target intersection point, which may be a plane where the intersection point with the smallest value is located based on the calculation of the server according to the intersection points.

Wherein, the preset value refers to a preset value, which is an index used to measure whether the intersection point is a target intersection point.

The server will extract the value of each intersection point on the Z plane, and then select the intersection point with the smallest Z value as the reference plane, that is, the intersection point with the smallest Z value as the ground, and then calculate the difference between the intersection point and the reference plane. When the difference between them is greater than the preset value, the intersection point is determined as the target intersection point.

In the above embodiment, the server can determine whether the current intersection point is the target intersection point according to the difference between the intersection point and the reference plane, so as to obtain the target area information by subsequent calculation of the information unit where the target intersection point is located.

In one embodiment, drawing a plumb line at the target position of each information unit to obtain the intersection point of the plumb line and the three-dimensional model includes: drawing a plumb line at the target position of each information unit to obtain at least one vertical line and the three-dimensional model The initial intersection point of the model; filter from the initial intersection points according to the preset method to obtain the intersection point between the plumb line and the model.

Wherein, the initial intersection point is the intersection point obtained by intersecting the plumb line and the three-dimensional model, and at least one initial intersection point can be obtained by intersecting the plumb line corresponding to each information unit and the three-dimensional model.

Wherein, the preset method refers to a preset method of screening the intersection points from the initial intersection points, for example, the intersection point with the largest Z value in each unit.

Draw a plumb line at the target position of each information unit to obtain at least one initial intersection point where the plumb line intersects with the 3D model, and then filter from the initial intersection points corresponding to each information unit according to a preset method to obtain the vertical line and the 3D model. The intersection point of the 3D model.

Optionally, the server draws a long enough plumb line through the center of each unit, and then selects the point with the largest Z value from the initial intersection points corresponding to each information unit as the lead The intersection point of the vertical line with the model.

In the above embodiment, the server obtains the intersection points of the plumb line and the model from the initial intersection points through a preset method, so that the intersection points that can be used to judge the target condition can be quickly obtained.

In one embodiment, multiple information units are extracted based on the 3D model, and the information of the target area is obtained based on the multiple information units and the 3D model, which is obtained by running an information extraction model based on workflow in advance according to preset parameters. .

Optionally, when the 3D model is imported into Rhino (Rhinoceros, a 3D modeling software), the model file can be processed through Rhino's built-in visual programming platform Grasshopper (a visual programming language) to realize the extraction of target area information. After the 3D model is imported into Rhino, it becomes multiple Mesh objects. Rhino and Grasshopper support operations such as connecting, exploding, and intersecting Mesh objects.

With reference to FIG. 6 , FIG. 6 is a schematic flowchart of calculating target area information by using a workflow model in an embodiment. In order to extract the roof outline, a Workflow is built in Grasshopper. As long as the imported Obj model is selected at the input end of the Workflow, the program can automatically run according to the preset accuracy and height threshold, and calculate the roof outline and area. Among them, the height threshold is used to ensure that the target reference plane is higher than the highest point of the Mesh object. The entire Workflow is divided into four parts: building and subdividing the datum plane, calculating the intersection of plumb lines, judging the intersection of the roof, and screening the roof unit.

In the above embodiments, the fully automatic extraction of target area information can be realized by means of the information extraction model constructed in advance based on the workflow.

In one embodiment, with reference to FIG. 7 , FIG. 7 is a schematic diagram of steps in which the information extraction method is applied to a building roof in one embodiment.

S702. Determine the building that needs to measure the photovoltaic potential of the roof. Select the building or area that needs to measure the photovoltaic potential of the roof (referred to as the "target building" in this project) according to the needs, and form a closed polygon on the UAV aerial survey map. Draw the geographic location where the target building belongs.

S704, using the UAV to take oblique photography of the target building. In the remote control system of the UAV, parameters such as the flight height (the flight height is generally the height of the highest point in the target building plus 10 meters or more), route overlap rate and other parameters are set, and oblique photography is performed. Some oblique photography pictures are shown in Figure 8.

S706, constructing a three-dimensional model of the target building. Import the pictures taken by oblique photography into Dajiang Zhitu software, set the expected 3D model format (such as OBJ format), precision and other parameters, carry out 3D modeling, and obtain the 3D model of the target building, as shown in Figure 3.

S708, extracting roof information of the target building. Import the 3D model of the target building into Rhino, and the model file can be processed through Grasshopper, a visual programming platform that comes with Rhino, to realize the extraction of information such as the edge and area of the roof of the target building. After the Obj model is imported into Rhino, it becomes multiple Mesh objects. Rhino and Grasshopper support operations such as connection, explosion, and intersection of Mesh objects.

S710, in order to extract the roof outline, build Workflow in Grasshopper, as long as the imported Obj model is selected at the input end of Workflow, the program can automatically run according to the preset accuracy and height threshold, and calculate the roof outline and area. The entire Workflow is divided into four parts: constructing and subdividing the datum plane, calculating the intersection of plumb lines, judging the intersection of the roof, and screening the roof unit:

1. Construct and subdivide the datum. (1) Use the Bounding box battery (that is, the packaged code unit, through which the target detection of the 3D model can be directly obtained to obtain the bounding cube) to obtain the bounding cube of the Obj model, and project it onto the world XY plane to obtain the Obj model (2) According to the set precision (such as 0.1m), divide the datum plane into units (0.1m*0.1m) with the set precision as the side length.

2. Calculate the intersection point of the plumb line. (1) Draw a long enough plumb line through the center of each unit; (2) Use Mesh|Curve (that is, the packaged code unit, through which the intersection point of the plumb line and the Mesh object can be obtained) battery to find out The intersection point between each vertical line and the Obj grid object; (3) If a line has multiple intersection points, the point with the largest Z value (the highest point) shall prevail.

3. Determine the roof intersection. (1) Extract the Z value of each intersection point to obtain the minimum Z value; (2) It may be considered that the minimum Z value is the ground, and according to the set height threshold (such as 24m), the intersection point with Z value > height threshold can be considered is the intersection with the roof.

4. Screen the roof unit. (1) Extract the datum unit corresponding to the intersection point of the roof, that is, get all the roof units; (2) Calculate the area and extract the roof outline according to the extracted unit.

It should be noted that, in this embodiment, the target object is the target building, and the roof information is the target area information.

In the above-mentioned embodiment, firstly, the information extraction of the target area can be realized without manual on-site measurement; secondly, the rapid and accurate extraction of roof edges and areas of a large number of dense buildings in the city can be realized.

It should be understood that although the steps in the flow charts involved in the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flow charts involved in the above-mentioned embodiments may include multiple steps or stages, and these steps or stages are not necessarily executed at the same time, but may be performed at different times For execution, the execution order of these steps or stages is not necessarily performed sequentially, but may be executed in turn or alternately with other steps or at least a part of steps or stages in other steps.

Based on the same inventive concept, an embodiment of the present application further provides an information extraction device for implementing the above-mentioned information extraction method. The solution to the problem provided by the device is similar to the implementation described in the above method, so for the specific limitations in one or more embodiments of the information extraction device provided below, please refer to the above definition of the information extraction method, I won't repeat them here.

In one embodiment, as shown in FIG. 9 , an information extraction device is provided, including: a receiving module 100, a building module 200, a unit extraction module 300 and a calculation module 400, wherein:

A receiving module 100, configured to receive an image of a target object;

A construction module 200, configured to construct a three-dimensional model corresponding to the target object image according to the target object image;

A unit extraction module 300, configured to obtain a target reference plane based on a three-dimensional model, and perform unit extraction on the target reference plane to obtain a plurality of information units;

The calculation module 400 is configured to calculate the information units satisfying the target condition to obtain target area information.

In one embodiment, the above-mentioned unit extraction module includes:

The detection unit is used for detecting the target in the three-dimensional model to obtain the target cube.

The projection unit is configured to project the target cube to obtain the target reference plane.

The cutting unit is configured to cut the target reference plane according to a preset threshold to obtain a plurality of information units.

In one embodiment, the above calculation module 400 includes:

The drawing unit is configured to draw a plumb line at the target position of each information unit, and obtain an intersection point between the plumb line and the three-dimensional model.

The judging unit is configured to judge that the information unit where the target intersection is located satisfies the target condition when the intersection is the target intersection.

The target extraction unit is configured to extract the information unit where the target intersection is located, and obtain target area information according to the information unit where the target intersection is located.

In one embodiment, the above-mentioned judging unit includes:

The intersection subunit is used to obtain the datum plane according to the intersection point.

The threshold judging subunit is used to judge the intersection point according to the reference plane and the preset value.

The target judging subunit is used for judging the intersection point as the target intersection point when the difference between the intersection point and the reference plane is greater than a preset value.

In one embodiment, the above-mentioned drawing unit includes:

The preprocessing subunit is used to draw a plumb line at the target position of each information unit, and obtain at least one initial intersection point between the plumb line and the 3D model.

The screening subunit is used to screen the initial intersection points according to a preset method to obtain the intersection points between the plumb line and the model.

In one embodiment, the above calculation module 400 is obtained by running an information extraction model constructed in advance based on workflow according to preset parameters.

Each module in the above-mentioned information extraction device can be fully or partially realized by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure may be as shown in FIG. 10 . The computer device includes a processor, memory and a network interface connected by a system bus. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs and databases. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing target object extraction data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an information extraction method is realized.

Those skilled in the art can understand that the structure shown in Figure 10 is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation to the computer equipment on which the solution of this application is applied. The specific computer equipment can be More or fewer components than shown in the figures may be included, or some components may be combined, or have a different arrangement of components.

In one embodiment, a computer device is provided, including a memory and a processor, a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: receiving an image of a target object; The three-dimensional model corresponding to the object image; the target reference plane is obtained based on the three-dimensional model, and the target reference plane is extracted to obtain multiple information units; the information units that meet the target conditions are calculated to obtain the target area information.

In one embodiment, when the processor executes the computer program, the target reference plane is obtained based on the three-dimensional model, and the target reference plane is extracted to obtain multiple information units, including: performing target detection in the three-dimensional model to obtain the target cube; Project the target cube to obtain the target reference plane; cut the target reference plane according to the preset threshold to obtain multiple information units.

In one embodiment, when the processor executes the computer program, the calculation of the information units meeting the target conditions to obtain the target area information includes: drawing a plumb line at the target position of each information unit to obtain the plumb line and the three-dimensional model When the intersection point is the target intersection point, it is determined that the information unit where the target intersection point is located satisfies the target condition; the information unit where the target intersection point is located is extracted, and the target area information is obtained according to the information unit where the target intersection point is located.

In one embodiment, the judging method of the target intersection point realized when the processor executes the computer program includes: obtaining the reference plane according to the intersection point; judging the intersection point according to the reference plane and a preset value; when the difference between the intersection point and the reference plane When it is greater than the preset value, it is determined that the intersection point is the target intersection point.

In one embodiment, when the processor executes the computer program, drawing a plumb line at the target position of each information unit to obtain the intersection point of the plumb line and the three-dimensional model includes: drawing a plumb line at the target position of each information unit , to obtain at least one initial intersection point between the plumb line and the three-dimensional model; and filter the initial intersection points according to a preset method to obtain the intersection point between the plumb line and the model.

In one embodiment, when the processor executes the computer program, extracting multiple information units based on the three-dimensional model, and obtaining the target area information based on the multiple information units and the three-dimensional model is through the information extraction based on the pre-built workflow. The model is obtained after running according to the preset parameters.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: receiving an image of a target object; The corresponding three-dimensional model; the target datum plane is obtained based on the three-dimensional model, and the unit extraction of the target datum plane is performed to obtain multiple information units; the information units satisfying the target conditions are calculated to obtain the target area information.

In one embodiment, when the computer program is executed by the processor, the target reference plane is obtained based on the three-dimensional model, and the target reference plane is extracted to obtain multiple information units, including: performing target detection in the three-dimensional model to obtain the target cube ;Project the target cube to obtain the target reference plane; cut the target reference plane according to the preset threshold to obtain multiple information units.

In one embodiment, when the computer program is executed by the processor, the calculation of the information units satisfying the target conditions to obtain the target area information includes: drawing a plumb line at the target position of each information unit to obtain the vertical line and the three-dimensional The intersection point of the model; when the intersection point is the target intersection point, it is determined that the information unit where the target intersection point is located meets the target condition; the information unit where the target intersection point is located is extracted, and the target area information is obtained according to the information unit where the target intersection point is located.

In one embodiment, the method for judging the target intersection point realized when the computer program is executed by the processor includes: obtaining the reference plane according to the intersection point; judging the intersection point according to the reference plane and a preset value; when the difference between the intersection point and the reference plane When the value is greater than the preset value, it is judged that the intersection point is the target intersection point.

In one embodiment, when the computer program is executed by the processor, drawing a plumb line at the target position of each information unit to obtain the intersection point of the plumb line and the three-dimensional model includes: drawing a plumb line at the target position of each information unit Lines to obtain at least one initial intersection point between the plumb line and the 3D model; filter the initial intersection points according to a preset method to obtain the intersection point between the plumb line and the model.

In one embodiment, when the computer program is executed by the processor, multiple information units are extracted based on the 3D model, and the information of the target area is obtained based on the multiple information units and the 3D model through the information constructed in advance based on the workflow The extraction model is obtained after running according to preset parameters.

In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the following steps are implemented: receiving an image of a target object; constructing a three-dimensional model corresponding to the image of the target object according to the image of the target object ; The target datum plane is obtained based on the three-dimensional model, and a plurality of information units are obtained by unit extraction of the target datum plane; information units satisfying the target condition are calculated to obtain target area information.

In one embodiment, when the computer program is executed by the processor, the image of the target object is received; according to the image of the target object, a three-dimensional model corresponding to the image of the target object is constructed; the target reference plane is obtained based on the three-dimensional model, and the target reference plane is Perform unit extraction to obtain multiple information units; calculate information units that meet the target conditions to obtain target area information.

In one embodiment, when the computer program is executed by the processor, the target reference plane is obtained based on the three-dimensional model, and the target reference plane is extracted to obtain multiple information units, including: performing target detection in the three-dimensional model to obtain the target cube ;Project the target cube to obtain the target reference plane; cut the target reference plane according to the preset threshold to obtain multiple information units.

In one embodiment, when the computer program is executed by the processor, the calculation of the information units satisfying the target conditions to obtain the target area information includes: drawing a plumb line at the target position of each information unit to obtain the vertical line and the three-dimensional The intersection point of the model; when the intersection point is the target intersection point, it is determined that the information unit where the target intersection point is located meets the target condition; the information unit where the target intersection point is located is extracted, and the target area information is obtained according to the information unit where the target intersection point is located.

In one embodiment, the method for judging the target intersection point realized when the computer program is executed by the processor includes: obtaining the reference plane according to the intersection point; judging the intersection point according to the reference plane and a preset value; when the difference between the intersection point and the reference plane When the value is greater than the preset value, it is judged that the intersection point is the target intersection point.

In one embodiment, when the computer program is executed by the processor, drawing a plumb line at the target position of each information unit to obtain the intersection point of the plumb line and the three-dimensional model includes: drawing a plumb line at the target position of each information unit Lines to obtain at least one initial intersection point between the plumb line and the 3D model; filter the initial intersection points according to a preset method to obtain the intersection point between the plumb line and the model.

In one embodiment, when the computer program is executed by the processor, multiple information units are extracted based on the 3D model, and the information of the target area is obtained based on the multiple information units and the 3D model through the information constructed in advance based on the workflow The extraction model is obtained after running according to preset parameters.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the computer programs can be stored in a non-volatile computer-readable memory In the medium, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any reference to storage, database or other media used in the various embodiments provided in the present application may include at least one of non-volatile and volatile storage. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive variable memory (ReRAM), magnetic variable memory (Magnetoresistive Random Access Memory, MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (Phase Change Memory, PCM), graphene memory, etc. The volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory. As an illustration and not a limitation, the RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM). The databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a blockchain-based distributed database, etc., but is not limited thereto. The processors involved in the various embodiments provided by this application can be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., and are not limited to this.

The technical features of the above embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered to be within the range described in this specification.

The above-mentioned embodiments only express several implementation modes of the present application, and the description thereof is relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be determined by the appended claims.

Claims (10)

1. An information extraction method, characterized in that the method comprises:

receiving a target object image;

constructing a three-dimensional model corresponding to the target object image according to the target object image;

obtaining a target datum plane based on the three-dimensional model, and performing unit extraction on the target datum plane to obtain a plurality of information units;

and calculating the information units meeting the target conditions to obtain target area information.

2. The method of claim 1, wherein obtaining a target datum based on the three-dimensional model and performing unit extraction on the target datum to obtain a plurality of information units comprises:

carrying out target detection in the three-dimensional model to obtain a target cube;

projecting the target cube to obtain the target reference surface;

and cutting the target datum plane according to a preset threshold value to obtain a plurality of information units.

3. The method of claim 1, wherein calculating the information units satisfying the target condition to obtain target area information comprises:

drawing a plumb line at the target position of each information unit to obtain an intersection point of the plumb line and the three-dimensional model;

when the intersection point is a target intersection point, judging that the information unit where the target intersection point is located meets a target condition;

and extracting the information unit where the target intersection point is located, and calculating according to the information unit where the target intersection point is located to obtain the target area information.

4. The method according to claim 3, wherein the manner of determining the target intersection point comprises:

obtaining a reference plane according to the intersection point;

judging the intersection point according to the reference surface and a preset numerical value;

and when the difference value between the intersection point and the reference plane is larger than the preset value, judging that the intersection point is a target intersection point.

5. The method of claim 3, wherein said drawing a plumb line at a target location of each of said information units, resulting in an intersection of said plumb line with said three-dimensional model, comprises:

drawing plumb lines at the target positions of the information units to obtain an initial intersection point of at least one plumb line and the three-dimensional model;

and screening from the initial intersection points according to a preset method to obtain the intersection point of the plumb line and the three-dimensional model.

6. The method according to claim 1, wherein the extracting a plurality of information units based on the three-dimensional model, and the obtaining of the target area information according to the plurality of information units and the three-dimensional model are obtained by operating an information extraction model constructed in advance based on a workflow according to preset parameters.

7. An information extraction apparatus, characterized in that the apparatus comprises:

the receiving module is used for receiving the target object image;

the building module is used for building a three-dimensional model corresponding to the target object image according to the target object image;

the unit extraction module is used for obtaining a target datum plane based on the three-dimensional model and performing unit extraction on the target datum plane to obtain a plurality of information units;

and the calculation module is used for calculating the information units meeting the target conditions to obtain target area information.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.

9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.

Images