CN116310226B

CN116310226B - Three-dimensional object hierarchical model generation method, device, equipment and storage medium

Info

Publication number: CN116310226B
Application number: CN202310549081.XA
Authority: CN
Inventors: 黄惠; 潘珊珊
Original assignee: Shenzhen University
Current assignee: Shenzhen University
Priority date: 2023-05-16
Filing date: 2023-05-16
Publication date: 2023-08-18
Anticipated expiration: 2043-05-16
Also published as: CN116310226A

Abstract

The application relates to a three-dimensional object hierarchical model generation method, a device, equipment and a storage medium. The method comprises the following steps: acquiring a three-dimensional object model with a plurality of faces, which is created for a target object; extracting planes in the three-dimensional object model to obtain a plane set; performing plane classification on the plane set to obtain a main plane set and a detail structure plane set; clustering detail structure planes in the set of detail structure planes to obtain at least one subset; the detail structure planes in each subset are used to construct the same detail structure; generating a detail level model of the target object in response to the detail structure selection operation; the detail level model includes a main structure constructed from a set of main planes and a detail structure generated from a corresponding subset of the detail structures selected by the detail structure selection operation and embedded on the main structure. By adopting the method, the flexibility of generating the detail level model of the target object can be improved.

Description

Three-dimensional object hierarchical model generation method, device, equipment and storage medium

Technical Field

The present application relates to the field of three-dimensional reconstruction technologies, and in particular, to a method, an apparatus, a device, and a storage medium for generating a three-dimensional object hierarchical model.

Background

With the development of computer technology, LOD (level of detail) reconstruction technology has emerged. LOD reconstruction techniques refer to techniques that reconstruct a detail level model of a three-dimensional object from a three-dimensional object model of the three-dimensional object. When reconstructing a detail level model by using the LOD reconstruction technology, the detail level models with different degrees of fineness are usually displayed according to the distance from the viewpoint of the user to the center point of the detail level model.

However, in the conventional LOD reconstruction technology, a detail structure with a specific fine degree can only be displayed according to the distance from the user viewpoint to the center point of the detail level model, so that different user requirements cannot be met, and the method is not flexible enough.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a three-dimensional object hierarchical model generation method, apparatus, computer device, and computer-readable storage medium that can improve flexibility.

In a first aspect, the present application provides a method for generating a three-dimensional object hierarchical model, the method comprising:

acquiring a three-dimensional object model with a plurality of faces, which is created for a target object;

extracting planes in the three-dimensional object model to obtain a plane set;

performing plane classification on the plane set to obtain a main plane set and a detail structure plane set;

Clustering detail structure planes in the set of detail structure planes to obtain at least one subset; the detail structure planes in each subset are used to construct the same detail structure;

generating a detail level model of the target object in response to the detail structure selection operation; the detail level model includes a main structure constructed from a set of main planes and a detail structure generated from a corresponding subset of the detail structures selected by the detail structure selection operation and embedded on the main structure.

In some embodiments, classifying planes from the set of planes results in a set of principal planes and a set of detail structure planes, including:

dividing a bounding box of the three-dimensional object model to obtain a plurality of polyhedrons;

determining the position relation between each polyhedron and the three-dimensional object model; the positional relationship includes that the polyhedron is positioned inside the three-dimensional object model or outside the three-dimensional object model;

judging whether the common surface of adjacent polyhedrons is covered by the two-dimensional contour of the three-dimensional object model or not according to adjacent polyhedrons with the same position relation; the two-dimensional contour is obtained by projecting points of each plane of the three-dimensional object model onto the corresponding plane of the three-dimensional object model and calculating the contour of the projected points on each plane; deleting the common plane to combine the adjacent polyhedrons to obtain a plurality of connected components under the condition that the common plane is not covered by the two-dimensional contour;

From the plurality of connected components, a set of principal planes and a set of detail structure planes are determined.

In some embodiments, determining the set of principal planes and the set of detail structure planes from the plurality of connected components includes:

classifying the plurality of connected components according to the position relation to obtain a main body internal connected component and a main body external connected component;

determining a set of main body planes according to an intersection between a plane set corresponding to the main body internal connected component and a plane set corresponding to the main body external connected component;

a set of detail structure planes is determined from planes in the set of planes other than the set of body planes.

In some embodiments, classifying the plurality of connected components according to the positional relationship to obtain a body-internal connected component and a body-external connected component includes:

determining a maximum connected component which is located inside the three-dimensional object model from the plurality of connected components as a main body inside connected component according to the position relation, and determining a maximum connected component which is located outside the three-dimensional object model from the plurality of connected components as a main body outside connected component;

determining a set of detail structure planes from planes of the set of planes other than the set of body planes, comprising:

Determining a discrete connected component which is located inside the three-dimensional object model and is other than the connected component inside the main body among the connected components as a detail connected component inside;

determining a discrete connected component which is outside the three-dimensional object model and is outside the main body and is outside the three-dimensional object model from the connected components as a detail outside connected component;

and determining planes corresponding to the detail internal connected component and the detail external connected component as detail structure planes to obtain a set of detail structure planes.

In some embodiments, the method further comprises:

according to the proportion similarity of the detail structures formed by the subsets and the embedding relation between the detail structures formed by the subsets and the main body planes, grouping the subsets to obtain the detail structure plane combinations; wherein, the detail structure planes corresponding to the subsets belonging to the same group are embedded in the same main body plane, and the detail structures formed by the subsets belonging to the same group meet the preset proportion similarity condition;

in response to a detail structure selection operation, generating a detail level model of the target object, comprising:

in response to the detail structure selection operation, determining a detail structure plane combination specified by the detail structure selection operation;

And constructing a main structure based on the collection of main planes, and constructing corresponding detail structures based on each subset in the designated detail structure plane combination respectively to generate a detail level model of the target object.

In some embodiments, the method further comprises:

regularized detection is carried out on main body planes in a main body plane set in the detail level model, and plane parameters of the main body planes are adjusted to enable the two main body planes to be kept parallel under the condition that any two main body planes with plane included angles in a first preset angle range exist in the main body plane set;

under the condition that any two main body planes with plane included angles in a second preset angle range exist in the set of main body planes, plane parameters of the main body planes are adjusted so that the two main body planes are kept orthogonal;

and under the condition that any two parallel main body planes exist in the set of the main body planes, and the plane distance between the two parallel main body planes is smaller than a preset distance threshold value, the plane parameters of the parallel main body planes are adjusted so that the two parallel main body planes are kept coplanar.

In some embodiments, the method further comprises:

regularization detection is carried out on the detail structure in the detail level model, and when at least one target detail structure exists in the detail structure and the target detail structure is embedded in the vertical face of the main structure, the target detail structure is replaced by the template grid.

In a second aspect, the present application further provides a three-dimensional object hierarchical model generating device, where the device includes:

the acquisition module is used for acquiring a three-dimensional object model which is created for the target object and has a plurality of faces; extracting planes in the three-dimensional object model to obtain a plane set;

the classification module is used for carrying out plane classification on the plane set to obtain a main body plane set and a detail structure plane set; clustering detail structure planes in the set of detail structure planes to obtain at least one subset; the detail structure planes in each subset are used to construct the same detail structure;

the generation module is used for responding to the detail structure selection operation and generating a detail level model of the target object; the detail level model includes a main structure constructed from a set of main planes and a detail structure generated from a corresponding subset of the detail structures selected by the detail structure selection operation and embedded on the main structure.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of the method described above when the processor executes the computer program.

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the method described above.

In a fifth aspect, the present application also provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, implements the steps of the method described above.

According to the three-dimensional object hierarchical model generation method, the three-dimensional object hierarchical model generation device, the computer equipment, the storage medium and the computer program product, planes in the three-dimensional object model of the target object are extracted to obtain the plane set, the plane set is subjected to plane classification to obtain the main body plane set and the detail structure plane set, the detail structure planes in the detail structure plane set are clustered to obtain the sub-set of the detail structure planes forming at least one detail structure, the selected detail structure is embedded into the main body structure constructed by the main body plane set in response to the selection operation on the detail structure to obtain the detail hierarchical model of the target object, the detail structure displayed by the detail hierarchical model can be flexibly selected through the selection operation on the detail structure, and therefore the flexibility of generating the detail hierarchical model of the target object is improved.

Drawings

FIG. 1 is a flow diagram of a method of generating a three-dimensional object hierarchy model in one embodiment;

FIG. 2 is a schematic diagram of classifying planes of a collection of planes in one embodiment;

FIG. 3 is a flow chart of a method for generating a three-dimensional object hierarchy model in another embodiment;

FIG. 4 is a block diagram of a three-dimensional object hierarchy model generation apparatus in one embodiment;

FIG. 5 is a block diagram of the structure of a classification module in one embodiment;

fig. 6 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

It will be appreciated that with advances in three-dimensional reconstruction techniques, such as photogrammetry and lidar scanning, it is easier to reconstruct finer three-dimensional object models, and thus three-dimensional reconstruction techniques such as urban landscapes, three-dimensional map navigation, geographic information systems, etc. are used in many scenarios. However, when a three-dimensional reconstruction technique is used to reconstruct a detail level model, a detail structure with a specific fine degree is usually displayed according to a distance from a user viewpoint to a center point of the detail level model, so that the detail level structure obtained by reconstruction is not flexible enough to select and cannot meet the requirements of different users.

In some embodiments, as shown in fig. 1, a three-dimensional object hierarchical model generating method is provided, and the method is applied to computer equipment for illustration, and specifically includes the following steps:

step 101, a three-dimensional object model with multiple faces created for a target object is acquired.

The three-dimensional object model is a model formed by a series of space sampling points on the surface of the target object, and comprises a three-dimensional point cloud model or a triangular grid model.

In some embodiments, when the three-dimensional object model is a triangular mesh model, the plurality of faces of the three-dimensional object model refer to a plurality of triangular meshes that make up the three-dimensional object model. When the three-dimensional object model is a polygonal mesh model, the plurality of faces of the three-dimensional object model refer to a plurality of polygonal meshes constituting the three-dimensional object model. And the plane of the three-dimensional object model refers to the three-dimensional plane of the three-dimensional object model. That is, the plane of the three-dimensional object model and the plane of the three-dimensional object model are two completely different concepts.

And 102, extracting planes in the three-dimensional object model to obtain a plane set.

Wherein, the plane set refers to a set composed of three-dimensional planes of the three-dimensional object model. It can be understood that, since the target object is composed of a main structure and a detail structure, the three-dimensional object model of the target object also has the main structure and the detail structure, and the extracted plane set includes the main plane for constructing the main structure and the detail structure plane for constructing the detail structure.

The main structure is a structure which plays a main role in bearing and transmitting force in the structure of the target object, so the main structure is a structure which is not embedded in any structure. Accordingly, the body plane of the body structure is the plane that is not embedded in any structure.

The detailed structure refers to a structure embedded over the body structure.

For ease of understanding, taking the example that the target object is a building entity in an urban landscape, the main structure refers to the structural configuration of the building entity, including a roof, a wall, a foundation, and the like. The detailed structure refers to a structure other than the main structure, including windows, chimneys, doors, stairs, and the like.

Illustratively, the computer device performs a plane extraction process on the three-dimensional object model to extract each plane in the three-dimensional object model, so as to obtain a plane set composed of a plurality of planes in the three-dimensional object model, i.e. obtain a plane set composed of a main body plane for constructing the main body structure and a detail structure plane for constructing the detail structure.

In some embodiments, the planes in the three-dimensional object model are extracted by a region growing algorithm using default parameters (distance threshold=0.3, angle threshold=40, minimum region size=25).

And 103, carrying out plane classification on the plane set to obtain a main plane set and a detail structure plane set.

Wherein the set of body planes is a set of body planes that build the body structure.

The set of detail structure planes is a set of detail structure planes that build a detail structure.

It will be appreciated that, in order to facilitate flexible selection of the detail structure displayed by the detail level model, it is necessary to perform plane classification on the plane set to obtain a set of principal planes for building the principal structure and a set of detail structure planes for building the detail structure, so that the principal structure can be built according to the set of principal planes, and the detail structure can be built according to the set of detail structure planes.

Illustratively, the computer device classifies principal planes in the plane set into a class based on a plurality of polyhedrons obtained by dividing a bounding box of the three-dimensional object model and a position relation of the polyhedrons and the three-dimensional object model to obtain a set of principal planes; the detail structure planes in the plane set are classified into one type, and the set of detail structure planes is obtained.

Step 104, clustering detail structure planes in the set of detail structure planes to obtain at least one subset; the detail structure planes in each subset are used to construct the same detail structure.

Wherein a subset is a collection of detail structure planes that make up the same detail structure. For example, the detail structure planes that make up the same window are a subset.

The computer device clusters detail structure planes in the collection of detail structure planes, and groups the detail structure planes forming the same detail structure into one type to obtain at least one subset, namely, a collection of detail structure planes forming at least one same detail structure.

Step 105, responding to the detail structure selection operation, and generating a detail level model of the target object; the detail level model includes a main structure constructed from a set of main planes and a detail structure generated from a corresponding subset of the detail structures selected by the detail structure selection operation and embedded on the main structure.

Wherein the selecting operation is an operation for selecting a detail structure to be added to the main structure, i.e. for selecting which detail structure to be added to the main structure.

Illustratively, prior to performing the detail structure selection operation, the computer device builds the main structure from the set of main body planes and provides the detail structure for selection by the user object, and upon selection of the detail structure added to the main structure by the user object, the computer device embeds the selected detail structure onto the main structure in response to the detail structure selection operation, thereby generating a detail level model of the target object.

It will be appreciated that the requirements of different user objects for the detail structure exhibited by the detail-level model of the target object are different. Therefore, through interaction with the user object, the detail structure is provided for the user object to select, so that the user object can autonomously select the detail structure displayed by the detail level model, and the selected detail structure is embedded into the main structure, so that the detail level model meeting the user requirement is obtained, and the flexibility of generating the detail level model of the target object is improved.

In some embodiments, the detail structure selection operation selects a set of detail structure combinations embedded in the same plane of the body that satisfy a predetermined scale similarity condition. A step of generating a detail level model of the target object in response to the detail structure selection operation, comprising: and responding to the detail structure selection operation, determining the detail structure combination specified by the detail structure selection operation, and embedding each detail structure in the detail structure combination into the same main body plane to obtain a detail level model of the target object.

In the three-dimensional object hierarchical model generation method, the planes in the three-dimensional object model of the target object are extracted to obtain the plane set, the plane set is subjected to plane classification to obtain the main plane set and the detail structure plane set, the detail structure planes in the detail structure plane set are clustered to obtain the sub-set of the detail structure planes forming at least one detail structure, the target detail structure is embedded into the main structure constructed by the main plane set in response to the selection operation of the target detail structure to obtain the detail hierarchical model of the target object, and the detail structure displayed by the detail hierarchical model can be flexibly selected by the selection operation of the target detail structure, so that the flexibility of generating the detail hierarchical model of the target object is improved.

In some embodiments, classifying planes from the set of planes results in a set of principal planes and a set of detail structure planes, including: dividing a bounding box of the three-dimensional object model to obtain a plurality of polyhedrons; determining the position relation between each polyhedron and the three-dimensional object model; the positional relationship includes that the polyhedron is positioned inside the three-dimensional object model or outside the three-dimensional object model; judging whether the common surface of adjacent polyhedrons is covered by the two-dimensional contour of the three-dimensional object model or not according to adjacent polyhedrons with the same position relation; the two-dimensional contour is obtained by projecting points of each plane of the three-dimensional object model onto the corresponding plane of the three-dimensional object model and calculating the contour of the projected points on each plane; deleting the common plane to combine the adjacent polyhedrons to obtain a plurality of connected components under the condition that the common plane is not covered by the two-dimensional contour; from the plurality of connected components, a set of principal planes and a set of detail structure planes are determined.

Wherein the bounding box of the three-dimensional object model is a geometry that contains the three-dimensional object model. It will be appreciated that the three-dimensional object model is composed of a main body structure and a detail structure, and the main body structure is usually only one, and the detail structure includes at least one, and it is obvious that the main body structure and the detail structure are composed of a plurality of polyhedrons, so that when the bounding box of the three-dimensional object model is divided, a plurality of polyhedrons are obtained, that is, the main body structure is composed of main body polyhedrons, and the detail structure is composed of detail polyhedrons. Accordingly, the plane on the body polyhedron is the body plane, and the plane on the detail polyhedron is the detail structure plane.

In some embodiments, the two-dimensional contour of the extracted plane on the three-dimensional object model is obtained when the boundary point extraction is performed on the plane projection point using an α -shape algorithm (rolling sphere algorithm). The α -shape algorithm is an algorithm for extracting boundary points, and by properly setting the value of α, the balance between the two-dimensional contour of the plane on the three-dimensional object model and the hole formed by embedding the detail structure into the main body structure can be maintained, that is, the extracted two-dimensional contour approaches to the actual contour of the plane on the three-dimensional object model, the main body plane contour is not affected by the detail structure embedded thereon, and the main body structure and the detail structure can be determined by the two-dimensional contour.

Illustratively, the computer device divides a bounding box of the three-dimensional object model to obtain a plurality of polyhedrons; the positional relationship of each polyhedron and the three-dimensional object model is determined, that is, whether each polyhedron is located inside the three-dimensional object model or outside the three-dimensional object model is determined. For adjacent polyhedrons having the same positional relationship, it is determined whether the common face of the adjacent polyhedron is covered by the two-dimensional contour of the three-dimensional object model, that is, for polyhedrons that are both located inside the three-dimensional object model and are adjacent, or for polyhedrons that are both located outside the three-dimensional object model and are adjacent, it is determined whether the common face of the adjacent polyhedron is covered by the two-dimensional contour of the three-dimensional object model, to determine whether the adjacent polyhedrons belong to the same connected component. Under the condition that the common plane is not covered by the two-dimensional outline, the adjacent polyhedrons are indicated to belong to the same connected component, and the common plane is deleted to combine the adjacent polyhedrons, so that the connected component formed by the adjacent polyhedrons is obtained. The set of principal planes and the set of detail structure planes are determined from a plurality of connected components and positional relationships, that is, from connected components constituted by adjacent polyhedrons, and connected components constituted by a single polyhedron.

When a polyhedron is adjacent to a plurality of polyhedrons, and the common surface of the polyhedron and the adjacent polyhedron is not covered by the two-dimensional contour, the polyhedron and the adjacent polyhedrons belong to the same connected component. For example, when the polyhedron a is adjacent to the polyhedron B and the polyhedron a is adjacent to the polyhedron C, and the common plane of the polyhedron a and the polyhedron B is not covered by the two-dimensional contour, the polyhedron a and the polyhedron B and the polyhedron C belong to the same communication component, and the common plane of the polyhedron a and the polyhedron B and the common plane of the polyhedron a and the polyhedron C are deleted to combine the polyhedrons A, B, C, thereby obtaining a communication component.

In some embodiments, where the common face is covered by a two-dimensional contour, it is indicated that adjacent polyhedrons do not belong to the same connected component, i.e., adjacent polyhedrons each constitute one connected component. It is understood that the polyhedrons that are not connected to any polyhedron individually constitute one connected component.

In the above embodiment, the bounding boxes of the three-dimensional object model are divided to obtain a plurality of polyhedrons, according to the positional relationship between each polyhedron and the three-dimensional object model, whether adjacent polyhedrons with the same positional relationship belong to the same connected component is judged according to the two-dimensional outline of the three-dimensional object model, so as to obtain a plurality of connected components, and according to the plurality of connected components, a set of main body planes and a set of detail structure planes are obtained, so that the planes in the plane set are accurately classified, and the accuracy of the main body structure constructed based on the set of main body planes and the detail structure constructed based on the set of detail structure planes is ensured.

In some embodiments, determining the set of principal planes and the set of detail structure planes from the plurality of connected components includes: classifying the plurality of connected components according to the position relation to obtain a main body internal connected component and a main body external connected component; determining a set of main body planes according to an intersection between a plane set corresponding to the main body internal connected component and a plane set corresponding to the main body external connected component; a set of detail structure planes is determined from planes in the set of planes other than the set of body planes.

Wherein the principal internal connected component is the largest connected component located inside the three-dimensional object model. The principal external connected component is the largest connected component that is located outside the three-dimensional object model.

It will be appreciated that since the connected components are obtained by combining the single polyhedron or the adjacent polyhedrons after deleting the common plane, the positional relationship of the connected components is the same as that of the single polyhedron or the adjacent polyhedron after deleting the common plane.

Illustratively, the computer apparatus classifies the plurality of connected components according to a positional relationship, that is, classifies the plurality of connected components according to a positional relationship of the connected components, to obtain a subject-internal connected component located inside the three-dimensional object model and a subject-external connected component located outside the three-dimensional object model. And determining the set of the main body planes according to the intersection between the plane set corresponding to the main body internal connected component and the plane set corresponding to the main body external connected component. Since the body plane of the body structure is a plane that is not embedded in any structure, the detail structure is typically embedded above the body structure, and thus a set of planes that are shared by the body internal communication component and the body external communication component is a collection of body planes. A set of detail structure planes is determined from planes in the set of planes other than the set of body planes.

In the above embodiment, the set of the main body planes is determined according to the intersection set between the plane set corresponding to the main body internal communication component and the plane set corresponding to the main body external communication component, so that the planes in the plane set are accurately classified, and the accuracy of the main body structure constructed based on the set of the main body planes and the accuracy of the detail structure constructed based on the set of the detail structure planes are ensured.

In some embodiments, classifying the plurality of connected components according to the positional relationship to obtain a body-internal connected component and a body-external connected component includes: determining a maximum connected component which is located inside the three-dimensional object model from the plurality of connected components as a main body inside connected component according to the position relation, and determining a maximum connected component which is located outside the three-dimensional object model from the plurality of connected components as a main body outside connected component; determining a set of detail structure planes from planes of the set of planes other than the set of body planes, comprising: determining a discrete connected component which is located inside the three-dimensional object model and is other than the connected component inside the main body among the connected components as a detail connected component inside; determining a discrete connected component which is outside the three-dimensional object model and is outside the main body and is outside the three-dimensional object model from the connected components as a detail outside connected component; and determining planes corresponding to the detail internal connected component and the detail external connected component as detail structure planes to obtain a set of detail structure planes.

In the above embodiment, the plurality of connected components are divided according to the positional relationship, so as to obtain the main body external connected component, the main body internal connected component, the detail internal connected component and the detail external connected component, so that accurate division of the connected components is realized, the collection of detail structure planes is determined based on the detail internal connected component and the detail external connected component, and the accuracy of the detail structure constructed based on the collection of detail structure planes is ensured.

In some embodiments, as shown in fig. 2, a schematic diagram for classifying planes of a plane set is provided, and an example in which a target object is a building is described, where:

reference numeral 20 denotes a plane extracted from the three-dimensional object model and a schematic drawing of its two-dimensional contour, and reference numeral 21 denotes a schematic drawing of dividing a bounding box of the three-dimensional object model into a plurality of polyhedrons. The plurality of polyhedrons are partitioned into a body inside connected component 23, a body outside connected component 24, a detail inside connected component 22, and a detail outside connected component 25 according to the two-dimensional contour of the three-dimensional object model.

Wherein the main body internal connected component 23 is the largest connected component located inside the three-dimensional object model.

The subject external connected component 24 is the largest connected component that is located outside the three-dimensional object model.

The detail interior connected component 22 is a discrete connected component that is located within the three-dimensional object model.

The detail exterior connected component 25 is a discrete connected component located outside the three-dimensional object model.

It will be appreciated that the intersection between the sets of planes corresponding to the body-internal connected component 23 and the body-external connected component 24 is the set 26 of body planes.

In some embodiments, the method further comprises: according to the proportion similarity of the detail structures formed by the subsets and the embedding relation between the detail structures formed by the subsets and the main body planes, grouping the subsets to obtain the detail structure plane combinations; wherein, the detail structure planes corresponding to the subsets belonging to the same group are embedded in the same main body plane, and the detail structures formed by the subsets belonging to the same group meet the preset proportion similarity condition.

The ratio similarity is used for representing whether two detail structures belong to a similarity or not.

The preset proportion similarity condition refers to a preset condition that each detail structure is similar. The preset scale similarity condition includes that the shape of the detail structures is the same or that the volumes of the detail structures are within a preset volume range. It can be understood that the volume of the detail structure being within the preset volume range means that different preset volume ranges are set for different types of detail structures, and the volumes of the detail structures belonging to the same type are within the same preset volume range.

The embedding relationship is used to characterize the principal plane of the principal structure in which the detail structure is embedded, i.e., by the embedding relationship it is possible to determine in which principal plane of the principal structure the detail structure is embedded.

The computer device determines the proportion similarity between the detail structures formed by the subsets and the embedding relationship between the detail structures formed by the subsets and the main body planes, groups the subsets to obtain the detail structure plane combinations, namely, the detail structures which meet the preset proportion similarity condition in the detail structures formed by the subsets and are embedded in the same main body plane are divided into a group to group the subsets to obtain the detail structure plane combinations.

In some embodiments, the predetermined scale similarity condition includes the shape of the detail structures being identical; according to the proportion similarity of the detail structures formed by the subsets and the embedding relation between the detail structures formed by the subsets and the main body planes, the step of grouping the subsets to obtain the detail structure plane combinations comprises the following steps: according to the proportion similarity of the detail structures formed by the subsets, namely the detail structures which are identical in shape and embedded in the same main body plane in the detail structures formed by the subsets are divided into a group, so that the detail structure plane combinations are obtained.

In some embodiments, the predetermined scale similarity condition includes a volume of the detail structure being within a predetermined volume range; according to the proportion similarity of the detail structures formed by the subsets and the embedding relation between the detail structures formed by the subsets and the main body planes, the step of grouping the subsets to obtain the detail structure plane combinations comprises the following steps: according to the proportion similarity of detail structures formed by the subsets, namely the detail structures which are embedded in the same main body plane and have the volumes within the same preset volume range are divided into a group, so that the plane combination of the detail structures is obtained.

In some embodiments, in response to a detail structure selection operation, the step of generating a detail level model of the target object comprises: in response to the detail structure selection operation, determining a detail structure plane combination specified by the detail structure selection operation; and constructing a main structure based on the collection of main planes, and constructing corresponding detail structures based on each subset in the designated detail structure plane combination respectively to generate a detail level model of the target object.

Illustratively, the computer device, in response to a detail structure selection operation, determines a detail structure plane combination specified by the detail structure selection operation, constructs a subject structure based on a set of subject planes, constructs corresponding detail structures based on respective subsets of the specified detail structure plane combination, and embeds the respective constructed detail structures onto a same subject plane of the subject structure to generate a detail level model of the target object. It will be appreciated that the detail structures constructed based on the subsets in the same detail structure plane combination satisfy the condition of similar preset proportions and are embedded in the same main body plane, so that when the detail selection operation selects the detail structure plane combination, each detail structure constructed based on the detail structure plane combination can be embedded in the same main body plane of the main body structure.

In the above embodiment, since the detail structure plane combination is determined through the detail structure selection operation, each detail structure which is embedded in the same main body plane in the detail structure plane combination and satisfies the preset proportion similarity condition is added to the main body structure, so that the flexibility of generating the detail level model of the target object can be improved, and different user requirements can be satisfied.

In addition, compared with the traditional method for displaying the detail structure with a specific fine degree according to the distance from the user viewpoint to the center point of the detail level model, the method can also avoid a great number of meaningless intermediate state detail structures in the generated detail level model.

In some embodiments, the method further comprises: regularized detection is carried out on main body planes in a main body plane set in the detail level model, and plane parameters of the main body planes are adjusted to enable the two main body planes to be kept parallel under the condition that any two main body planes with plane included angles in a first preset angle range exist in the main body plane set; under the condition that any two main body planes with plane included angles in a second preset angle range exist in the set of main body planes, plane parameters of the main body planes are adjusted so that the two main body planes are kept orthogonal; and under the condition that any two parallel main body planes exist in the set of the main body planes, and the plane distance between the two parallel main body planes is smaller than a preset distance threshold value, the plane parameters of the parallel main body planes are adjusted so that the two parallel main body planes are kept coplanar.

The first preset angle range is used for judging whether the two main body planes are approximately parallel or not, namely, when the plane included angle between the two main body planes is located in the first preset angle range, the two main body planes are approximately parallel.

The second preset angle range is used for judging whether the two main body planes are approximately orthogonal, namely, when the plane included angle between the two main body planes is positioned in the first preset angle range, the two main body planes are approximately orthogonal.

The preset distance threshold is used for judging whether the two parallel main body planes are coplanar or not, namely, when the plane distance between the two parallel main body planes is smaller than the preset distance threshold, the two parallel main body planes are approximately coplanar.

It will be appreciated that to improve the quality of the detail level model, regularization detection of the principal planes in the collection of principal planes is required to determine that any two principal planes that need to be kept parallel, orthogonal or coplanar remain parallel, orthogonal or coplanar, respectively.

For example, the computer device performs regularization detection on principal planes in the set of principal planes in the detail level model, that is, detects whether any two principal planes in the set of principal planes have plane included angles in a first preset angle range, plane included angles in a second preset angle range, or plane distances less than a preset distance threshold; and under the condition that any two main body planes with plane included angles in a first preset angle range exist in the set of main body planes, namely, any two approximately parallel main body planes exist in the set of main body planes, adjusting the plane parameters of any one of the two main body planes so that the two main body planes are kept parallel. And under the condition that any two main body planes with included plane angles in a second preset angle range exist in the set of main body planes, namely, any two approximately orthogonal main body planes exist in the set of main body planes, adjusting the plane parameters of any one of the two main body planes so that the two main body planes are kept orthogonal. When there are any two parallel main body planes in the set of main body planes and the plane distance between the two parallel main body planes is smaller than the preset distance threshold, it is indicated that the two parallel main body planes are approximately coplanar, the plane parameters of the parallel main body planes are adjusted, that is, the plane parameters of any one of the two main body planes are adjusted, so that the two parallel main body planes remain coplanar.

In the above embodiment, by performing regularization detection on the principal plane in the principal plane set of the detail level model, when the plane included angle in the principal plane set is in the first preset angle range, and the plane included angle is in the second preset angle range or any two principal planes with a plane distance smaller than the preset distance threshold, the plane parameters of the principal planes are adjusted, so that any two principal planes that need to be kept parallel, orthogonal or coplanar are correspondingly kept parallel, orthogonal or coplanar, thereby improving the quality of the detail level model.

In some embodiments, the method further comprises: regularization detection is carried out on the detail structure in the detail level model, and when at least one target detail structure exists in the detail structure and the target detail structure is embedded in the vertical face of the main structure, the target detail structure is replaced by the template grid.

Wherein the template grid is a standard detail structure. It will be appreciated that, due to the limited performance of the acquisition device that acquires the three-dimensional object model, the quality of the detail structure in the three-dimensional object model is typically worse than the main structure, so to improve the quality of the detail-level model, regularization detection of the detail structure in the detail-level model is required to determine whether there is at least one target detail structure embedded in the facade of the main structure in the detail structure. In the case that at least one target detail structure exists in the detail structure and the target detail structure is embedded in the elevation of the main structure, the template grid is used for replacing the target detail structure, so that the quality of the detail level model is improved.

In some embodiments, regularization is performed for the detail structure in the detail-level model, and in the case where there are at least two target detail structures in the detail structure and the target detail structure is embedded in a facade of the body structure, then the target detail structure is replaced with a template grid. It will be appreciated that when there are at least two target detail structures in the detail structure, the quality of the detail structure in the three-dimensional object model is typically worse than the main structure due to the limited performance of the acquisition device that acquires the three-dimensional object model, so that the at least two target detail structures are replaced with the template mesh to improve the quality of the detail structure and thus the quality of the detail level model.

In some embodiments, as shown in fig. 3, a flowchart of another three-dimensional object hierarchical model generating method is provided, and the method is applied to a computer device for illustration, and specifically includes the following steps:

step 301, a three-dimensional object model with multiple faces created for a target object is acquired.

And 302, extracting planes in the three-dimensional object model to obtain a plane set.

Step 303, dividing the bounding box of the three-dimensional object model to obtain a plurality of polyhedrons.

Step 304, determining the position relation between each polyhedron and the three-dimensional object model; the positional relationship includes that the polyhedron is located inside the three-dimensional object model or outside the three-dimensional object model.

Step 305, judging whether the common surface of adjacent polyhedrons is covered by the two-dimensional contour of the three-dimensional object model or not for the adjacent polyhedrons with the same positional relationship; the two-dimensional contour is obtained by projecting points of each plane of the three-dimensional object model onto the corresponding plane of the three-dimensional object model and calculating the contour of the projected points on each plane; in the case where the common plane is not covered by the two-dimensional contour, the common plane is deleted to merge the adjacent polyhedrons, resulting in a plurality of connected components.

Step 306, determining the maximum connected component which is positioned inside the three-dimensional object model from the connected components as the main body internal connected component according to the position relation, and determining the maximum connected component which is positioned outside the three-dimensional object model from the connected components as the main body external connected component; and determining the set of the main body planes according to the intersection between the plane set corresponding to the main body internal connected component and the plane set corresponding to the main body external connected component.

Step 307 of determining, as a detail interior connected component, a discrete connected component which is located inside the three-dimensional object model and is other than the main body interior connected component among the plurality of connected components; determining a discrete connected component which is outside the three-dimensional object model and is outside the main body and is outside the three-dimensional object model from the connected components as a detail outside connected component; and determining planes corresponding to the detail internal connected component and the detail external connected component as detail structure planes to obtain a set of detail structure planes.

Step 308, in response to the detail structure selection operation, determining a detail structure plane combination specified by the detail structure selection operation; and constructing a main structure based on the collection of main planes, and constructing corresponding detail structures based on each subset in the designated detail structure plane combination respectively to generate a detail level model of the target object.

In some embodiments, the step of obtaining a combination of detail structure planes includes: according to the proportion similarity of the detail structures formed by the subsets and the embedding relation between the detail structures formed by the subsets and the main body planes, grouping the subsets to obtain the detail structure plane combinations; wherein, the detail structure planes corresponding to the subsets belonging to the same group are embedded in the same main body plane, and the detail structures formed by the subsets belonging to the same group meet the preset proportion similarity condition.

Step 309, regularizing the principal planes in the set of principal planes in the detail level model, so that any two principal planes that need to be parallel, orthogonal or coplanar remain parallel, orthogonal or coplanar.

Specifically, regularization detection is performed on main body planes in a main body plane set in the detail level model, and plane parameters of the main body planes are adjusted so that the two main body planes are kept parallel under the condition that any two main body planes with plane included angles in a first preset angle range exist in the main body plane set; under the condition that any two main body planes with plane included angles in a second preset angle range exist in the set of main body planes, plane parameters of the main body planes are adjusted so that the two main body planes are kept orthogonal; and under the condition that any two parallel main body planes exist in the set of the main body planes, and the plane distance between the two parallel main body planes is smaller than a preset distance threshold value, the plane parameters of the parallel main body planes are adjusted so that the two parallel main body planes are kept coplanar.

Step 310, regularizing the detail structure in the detail level model, and if at least one target detail structure exists in the detail structure and the target detail structure is embedded in the vertical face of the main structure, replacing the target detail structure with the template grid.

In the three-dimensional object hierarchical model generation method, the planes in the three-dimensional object model of the target object are extracted to obtain the plane set, the plane set is subjected to plane classification to obtain the main plane set and the detail structure plane set, the detail structure planes in the detail structure plane set are clustered to obtain the detail structure plane subset forming at least one detail structure, the detail structure is embedded into the main structure constructed by the main plane set in response to the selection operation of the detail structure to obtain the detail hierarchical model of the target object, and the detail structure displayed by the detail hierarchical model can be flexibly selected by the selection operation of the detail structure, so that the flexibility of generating the detail hierarchical model of the target object is improved.

In addition, regularization detection is carried out on the detail level model, so that any two main body planes which are required to be parallel, orthogonal or coplanar are kept parallel, orthogonal or coplanar; in the case that at least one target detail structure exists in the selected detail structure and the target detail structure is embedded in the vertical face of the main structure, the template grid is used for replacing the target detail structure, so that the quality of the detail level model is improved.

It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a three-dimensional object hierarchical model generating device for realizing the three-dimensional object hierarchical model generating method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the device for generating a three-dimensional object hierarchy model provided below may refer to the limitation of the method for generating a three-dimensional object hierarchy model hereinabove, and will not be repeated herein.

In one embodiment, as shown in fig. 4, there is provided a three-dimensional object hierarchical model generating apparatus, including: an acquisition module 401, a classification module 402 and a generation module 403.

An acquisition module 401 for acquiring a three-dimensional object model having a plurality of faces created for a target object; and extracting planes in the three-dimensional object model to obtain a plane set.

A classification module 402, configured to perform plane classification on the plane set to obtain a set of principal planes and a set of detail structure planes; clustering detail structure planes in the set of detail structure planes to obtain at least one subset; the detail structure planes in each subset are used to construct the same detail structure.

A generation module 403, configured to generate a detail level model of the target object in response to the detail structure selection operation; the detail level model includes a main structure constructed from a set of main planes and a detail structure generated from a corresponding subset of the detail structures selected by the detail structure selection operation and embedded on the main structure.

In some embodiments, as shown in fig. 5, the classification module 402 includes a dividing unit 402a, a first determining unit 402b, a merging unit 402c, and a second determining unit 402d, wherein:

The dividing unit 402a is configured to divide the bounding box of the three-dimensional object model to obtain a plurality of polyhedrons.

A first determining unit 402b for determining a positional relationship between each polyhedron and the three-dimensional object model; the positional relationship includes that the polyhedron is located inside the three-dimensional object model or outside the three-dimensional object model.

A merging unit 402c for judging, for adjacent polyhedrons having the same positional relationship, whether or not the common face of the adjacent polyhedron is covered by the two-dimensional contour of the three-dimensional object model; the two-dimensional contour is obtained by projecting points of each plane of the three-dimensional object model onto the corresponding plane of the three-dimensional object model and calculating the contour of the projected points on each plane; in the case where the common plane is not covered by the two-dimensional contour, the common plane is deleted to merge the adjacent polyhedrons, resulting in a plurality of connected components.

A second determining unit 402d for determining a set of principal planes and a set of detail structure planes from the plurality of connected components.

In some embodiments, the classification module 402 is configured to classify the plurality of connected components according to a positional relationship to obtain a body internal connected component and a body external connected component; determining a set of main body planes according to an intersection between a plane set corresponding to the main body internal connected component and a plane set corresponding to the main body external connected component; a set of detail structure planes is determined from the planes of the set of planes other than the set of body planes.

In some embodiments, the classification module 402 is specifically configured to determine, according to a positional relationship, a maximum connected component, which is located inside the three-dimensional object model, of the plurality of connected components as a main body inside connected component, and determine, as a main body outside connected component, a maximum connected component, which is located outside the three-dimensional object model, of the plurality of connected components; determining a set of detail structure planes from planes of the set of planes other than the set of body planes, comprising: determining a discrete connected component which is located inside the three-dimensional object model and is other than the connected component inside the main body among the connected components as a detail connected component inside; determining a discrete connected component which is outside the three-dimensional object model and is outside the main body and is outside the three-dimensional object model from the connected components as a detail outside connected component; and determining planes corresponding to the detail internal connected component and the detail external connected component as detail structure planes to obtain a set of detail structure planes.

In some embodiments, the classification module 402 is further configured to group the subsets according to the proportion similarity of the detail structures formed by the subsets and the embedding relationship between the detail structures formed by the subsets and the planes of the main bodies, so as to obtain the plane combinations of the detail structures; wherein, the detail structure planes corresponding to the subsets belonging to the same group are embedded in the same main body plane, and the detail structures formed by the subsets belonging to the same group meet the preset proportion similarity condition.

A generation module 403 for determining, in response to the detail structure selection operation, a detail structure plane combination specified by the detail structure selection operation; and constructing a main structure based on the collection of main planes, and constructing corresponding detail structures based on each subset in the designated detail structure plane combination respectively to generate a detail level model of the target object.

In some embodiments, the generating module 403 is further configured to perform regularization detection on a principal plane in the set of principal planes in the detail level model, and adjust a plane parameter of the principal plane so that the two principal planes remain parallel when there are any two principal planes in the set of principal planes whose plane included angles lie in the first preset angle range; under the condition that any two main body planes with plane included angles in a second preset angle range exist in the set of main body planes, plane parameters of the main body planes are adjusted so that the two main body planes are kept orthogonal; and under the condition that any two parallel main body planes exist in the set of the main body planes, and the plane distance between the two parallel main body planes is smaller than a preset distance threshold value, the plane parameters of the parallel main body planes are adjusted so that the two parallel main body planes are kept coplanar.

In some embodiments, the generating module 403 is further configured to perform regularization detection on the detail structures in the detail level model, and in a case where at least one target detail structure exists in the detail structures and the target detail structure is embedded in a facade of the main structure, replace the target detail structure with the template grid.

The respective modules in the three-dimensional object hierarchical model generating apparatus described above may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing 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 and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method of generating a three-dimensional object-level model. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.

It will be appreciated by those skilled in the art that the structure shown in FIG. 6 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method embodiments described above.

In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.

Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims

1. A method for generating a three-dimensional object hierarchical model, the method comprising:

extracting planes in the three-dimensional object model to obtain a plane set;

dividing the bounding box of the three-dimensional object model to obtain a plurality of polyhedrons;

determining the position relation between each polyhedron and the three-dimensional object model; the positional relationship includes the polyhedron being located inside the three-dimensional object model or outside the three-dimensional object model;

Judging whether a common surface of adjacent polyhedrons with the same position relation is covered by a two-dimensional contour of the three-dimensional object model or not; the two-dimensional contour is obtained by projecting points of each plane of the three-dimensional object model onto the corresponding plane of the three-dimensional object model and calculating the contour of the projected points on each plane;

deleting the common plane to combine the adjacent polyhedrons to obtain a plurality of connected components under the condition that the common plane is not covered by the two-dimensional contour;

determining a set of main body planes according to the intersection between the plane set corresponding to the main body internal communication component and the plane set corresponding to the main body external communication component;

determining a set of detail structure planes according to planes in the plane set except for the set of main body planes; clustering detail structure planes in the set of detail structure planes to obtain at least one subset; the detail structure planes in each subset are used to construct the same detail structure;

Generating a detail level model of the target object in response to a detail structure selection operation; the detail level model includes a main structure constructed from the set of main planes and the detail structure generated from the corresponding subset of the detail structure selected by the detail structure selection operation and embedded on the main structure.

2. The method of claim 1, wherein classifying the plurality of connected components according to the positional relationship to obtain a body-internal connected component and a body-external connected component comprises:

determining a maximum connected component which is located inside the three-dimensional object model from the connected components as a main body internal connected component, and determining a maximum connected component which is located outside the three-dimensional object model from the connected components as a main body external connected component;

said determining a set of detail structure planes from planes of said set of planes other than said set of body planes, comprising:

determining a discrete connected component of the plurality of connected components that is located inside the three-dimensional object model, except for the subject internal connected component, as a detail internal connected component;

Determining a discrete connected component of the plurality of connected components that is outside the three-dimensional object model and that is outside the subject external connected component as a detail external connected component;

and determining planes corresponding to the detail internal communication component and the detail external communication component as detail structure planes, and obtaining a set of detail structure planes.

3. The method according to claim 1, wherein the method further comprises:

grouping the subsets according to the proportion similarity of the detail structures formed by the subsets and the embedding relation between the detail structures formed by the subsets and the main body planes to obtain the detail structure plane combinations; wherein, the detail structure planes corresponding to the subsets belonging to the same group are embedded in the same main body plane, and the detail structures formed by the subsets belonging to the same group meet the preset proportion similarity condition;

the generating a detail-level model of the target object in response to a detail-structure-selection operation includes:

in response to a detail structure selection operation, determining a detail structure plane combination specified by the detail structure selection operation;

And constructing a main structure based on the set of main planes, and constructing corresponding detail structures based on each subset in the designated detail structure plane combination respectively to generate a detail level model of the target object.

4. A method according to any one of claims 1 to 3, further comprising:

regularization detection is carried out on main body planes in a main body plane set in the detail level model, and plane parameters of the main body planes are adjusted so that the two main body planes are kept parallel under the condition that any two main body planes with plane included angles in a first preset angle range exist in the main body plane set;

when any two main body planes with plane included angles in a second preset angle range exist in the set of main body planes, plane parameters of the main body planes are adjusted so that the two main body planes are kept orthogonal;

and when any two parallel main body planes exist in the set of the main body planes, and the plane distance between the two parallel main body planes is smaller than a preset distance threshold, adjusting the plane parameters of the parallel main body planes so that the two parallel main body planes are kept coplanar.

5. The method according to claim 4, wherein the method further comprises: and performing regularization detection on the detail structures in the detail level model, and replacing the target detail structures by template grids under the condition that at least one target detail structure exists in the detail structures and the target detail structures are embedded in the elevation of the main structure.

6. A three-dimensional object hierarchical model generation apparatus, the apparatus comprising:

the classification module is used for dividing the bounding box of the three-dimensional object model to obtain a plurality of polyhedrons;

determining the position relation between each polyhedron and the three-dimensional object model; the positional relationship includes the polyhedron being located inside the three-dimensional object model or outside the three-dimensional object model; judging whether a common surface of adjacent polyhedrons with the same position relation is covered by a two-dimensional contour of the three-dimensional object model or not; the two-dimensional contour is obtained by projecting points of each plane of the three-dimensional object model onto the corresponding plane of the three-dimensional object model and calculating the contour of the projected points on each plane; deleting the common plane to combine the adjacent polyhedrons to obtain a plurality of connected components under the condition that the common plane is not covered by the two-dimensional contour; classifying the plurality of connected components according to the position relation to obtain a main body internal connected component and a main body external connected component; determining a set of main body planes according to the intersection between the plane set corresponding to the main body internal communication component and the plane set corresponding to the main body external communication component; determining a set of detail structure planes according to planes in the plane set except for the set of main body planes; clustering detail structure planes in the set of detail structure planes to obtain at least one subset; the detail structure planes in each subset are used to construct the same detail structure;

The generation module is used for responding to the detail structure selection operation and generating a detail level model of the target object; the detail level model includes a main structure constructed from the set of main planes and the detail structure generated from the corresponding subset of the detail structure selected by the detail structure selection operation and embedded on the main structure.

7. The apparatus of claim 6, wherein the generating module is further configured to perform regularization detection for a principal plane in a set of principal planes in the detail level model, and adjust a plane parameter of the principal plane if there are any two principal planes in the set of principal planes whose plane included angles lie in a first preset angle range, so that the two principal planes remain parallel; when any two main body planes with plane included angles in a second preset angle range exist in the set of main body planes, plane parameters of the main body planes are adjusted so that the two main body planes are kept orthogonal; and when any two parallel main body planes exist in the set of the main body planes, and the plane distance between the two parallel main body planes is smaller than a preset distance threshold, adjusting the plane parameters of the parallel main body planes so that the two parallel main body planes are kept coplanar.

8. The apparatus of claim 6, wherein the generation module is further configured to perform regularization detection for a detail structure in the detail-level model, wherein in the case where at least one target detail structure is present in the detail structure and the target detail structure is embedded in a facade of the body structure, then replace the target detail structure with a template grid.

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.