House three-dimensional reconstruction and ground recognition method, device, equipment and storage medium

Abstract

The embodiment of the present invention provides a method, device, equipment and storage medium for three-dimensional reconstruction of a house and ground recognition. The ground recognition method includes: obtaining three-dimensional point cloud data corresponding to the house based on multiple images obtained by shooting the house, and the multiple images contain the ground of the house. According to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data, the three-dimensional point cloud data are grouped to determine the three-dimensional point cloud data contained in each of the set multiple height intervals. According to the horizontal plane coordinate values ​​of the three-dimensional point cloud data contained in each of the multiple height intervals, the target height interval corresponding to the ground is determined, and according to the height coordinate values ​​of the three-dimensional point cloud data contained in the target height interval, the plane where the ground is located is determined, thereby completing accurate recognition of the ground.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a method, device, equipment and storage medium for three-dimensional reconstruction of a house and ground recognition. Background Art

[0002] For example, when a user rents or buys a house, it may be inconvenient for the user to visit the house in person. In order to enable the user to view the overall situation of the house online, the house can be reconstructed in three dimensions in advance to obtain a 3D house model for the user to view.

[0003] For example, when a user is decorating a house, the user wants to see in advance the effect of placing a certain object on the ground in a certain place in the room. To this end, the house can be reconstructed in 3D in advance, and the image of the above object can be superimposed on the reconstructed ground to provide it to the user for viewing.

[0004] Whether it is to reconstruct the floor plan of a house or to view the decoration effect of an object placed on the ground, a common premise is that the ground needs to be recognized during the 3D reconstruction of the house. Therefore, how to complete the ground recognition task conveniently and accurately is an urgent problem to be solved. Summary of the invention

[0005] The embodiments of the present invention provide a three-dimensional reconstruction of a house and ground recognition method, device, equipment and storage medium, which can conveniently and accurately recognize the plane where the ground is located from the three-dimensional reconstruction data of the house.

[0006] In a first aspect, an embodiment of the present invention provides a ground recognition method, the method comprising:

[0007] Acquire three-dimensional point cloud data corresponding to the house according to a plurality of images obtained by photographing the house, wherein the plurality of images include the ground surface of the house;

[0008] The three-dimensional point cloud data are grouped according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data to determine the three-dimensional point cloud data included in each of the set multiple height intervals;

[0009] Determining a target height interval corresponding to the ground according to horizontal plane coordinate values ​​of the three-dimensional point cloud data respectively included in the plurality of height intervals;

[0010] The plane where the ground is located is determined according to the height coordinate values ​​of the three-dimensional point cloud data included in the target height interval.

[0011] In a second aspect, an embodiment of the present invention provides a ground recognition device, the device comprising:

[0012] An acquisition module, used to acquire three-dimensional point cloud data corresponding to the house according to a plurality of images obtained by photographing the house, wherein the plurality of images include the ground of the house;

[0013] A grouping module, used for grouping the three-dimensional point cloud data according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data, so as to determine the three-dimensional point cloud data contained in each of the set multiple height intervals;

[0014] The determination module is used to determine the target height interval corresponding to the ground according to the horizontal plane coordinate values ​​of the three-dimensional point cloud data contained in each of the multiple height intervals, and determine the plane where the ground is located according to the height coordinate values ​​of the three-dimensional point cloud data contained in the target height interval.

[0015] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores executable code, and when the executable code is executed by the processor, the processor can at least implement the ground recognition method in the first aspect.

[0016] In a fourth aspect, an embodiment of the present invention provides a non-temporary machine-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor can at least implement the ground recognition method in the first aspect.

[0017] In a fifth aspect, an embodiment of the present invention provides a method for three-dimensional reconstruction of a house, the method comprising:

[0018] Acquire three-dimensional point cloud data corresponding to the house according to a plurality of images obtained by photographing the house, wherein the plurality of images include the ground surface of the house;

[0019] The three-dimensional point cloud data are grouped according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data to determine the three-dimensional point cloud data included in each of the set multiple height intervals;

[0020] Determining a target height interval corresponding to the ground according to horizontal plane coordinate values ​​of the three-dimensional point cloud data respectively included in the plurality of height intervals;

[0021] Determining the plane where the ground is located according to the height coordinate values ​​of the three-dimensional point cloud data included in the target height interval;

[0022] According to the determination result of the plane where the ground is located, the three-dimensional reconstruction of the house is performed.

[0023] In a sixth aspect, an embodiment of the present invention provides a three-dimensional reconstruction device for a house, the device comprising:

[0024] An acquisition module, used to acquire three-dimensional point cloud data corresponding to the house according to a plurality of images obtained by photographing the house, wherein the plurality of images include the ground of the house;

[0025] A grouping module, used for grouping the three-dimensional point cloud data according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data, so as to determine the three-dimensional point cloud data contained in each of the set multiple height intervals;

[0026] A determination module, configured to determine a target height interval corresponding to the ground according to the horizontal plane coordinate values ​​of the three-dimensional point cloud data respectively included in the plurality of height intervals; and determine a plane where the ground is located according to the height coordinate values ​​of the three-dimensional point cloud data included in the target height interval;

[0027] The reconstruction module is used to perform three-dimensional reconstruction of the house according to the determination result of the plane where the ground is located.

[0028] In the seventh aspect, an embodiment of the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores executable code, and when the executable code is executed by the processor, the processor can at least implement the three-dimensional reconstruction method of the house in the fifth aspect.

[0029] In an eighth aspect, an embodiment of the present invention provides a non-temporary machine-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor can at least implement the three-dimensional reconstruction method of a house in the fifth aspect.

[0030] In a ninth aspect, an embodiment of the present invention provides a method for displaying home deployment, the method comprising:

[0031] Acquire three-dimensional point cloud data corresponding to the house according to a plurality of images obtained by photographing the house, wherein the plurality of images include the ground surface of the house;

[0032] The three-dimensional point cloud data are grouped according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data to determine the three-dimensional point cloud data included in each of the set multiple height intervals;

[0033] Determining a target height interval corresponding to the ground according to horizontal plane coordinate values ​​of the three-dimensional point cloud data respectively included in the plurality of height intervals;

[0034] Determining the plane where the ground is located according to the height coordinate values ​​of the three-dimensional point cloud data included in the target height interval;

[0035] According to the determination result of the plane where the ground is located, the house is reconstructed in three dimensions, and the target object is displayed on the reconstructed ground.

[0036] In a tenth aspect, an embodiment of the present invention provides a display device for home deployment, the device comprising:

[0037] An acquisition module, used to acquire three-dimensional point cloud data corresponding to the house according to a plurality of images obtained by photographing the house, wherein the plurality of images include the ground of the house;

[0038] A grouping module, used for grouping the three-dimensional point cloud data according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data, so as to determine the three-dimensional point cloud data contained in each of the set multiple height intervals;

[0039] A determination module, configured to determine a target height interval corresponding to the ground according to the horizontal plane coordinate values ​​of the three-dimensional point cloud data respectively included in the plurality of height intervals; and determine a plane where the ground is located according to the height coordinate values ​​of the three-dimensional point cloud data included in the target height interval;

[0040] The display module is used to perform three-dimensional reconstruction of the house according to the determination result of the plane where the ground is located, and to display the target object on the reconstructed ground.

[0041] In the eleventh aspect, an embodiment of the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores executable code, and when the executable code is executed by the processor, the processor can at least implement the home deployment display method in the ninth aspect.

[0042] In the twelfth aspect, an embodiment of the present invention provides a non-temporary machine-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor can at least implement the home deployment display method in the ninth aspect.

[0043] In an embodiment of the present invention, a camera can be used to photograph a house to obtain multiple images, and the multiple images include the ground of the house. After obtaining the multiple images, the camera can perform three-dimensional reconstruction of the house based on the multiple images. During the reconstruction process, three-dimensional reconstruction data including three-dimensional point cloud data corresponding to the house will be output. These three-dimensional point cloud data can reflect the visual texture features of various objects in the house (such as various objects, walls, floors, etc.), and it can be understood that the three-dimensional point cloud data is composed of three-dimensional coordinate points. In this article, ground recognition can be considered as finding the plane where the ground is located in the three-dimensional point cloud data, that is, determining the depth of the ground (referring to the depth information corresponding to the ground in the three-dimensional coordinate system corresponding to the reconstruction process).

[0044] In order to identify the plane where the ground is located from the above three-dimensional point cloud data, first, multiple height intervals are pre-set, and the three-dimensional point cloud data are grouped according to the height coordinate values ​​(i.e., Z-axis coordinate values) corresponding to each of the three-dimensional point cloud data to determine the three-dimensional point cloud data contained in each of the multiple height intervals; secondly, according to the horizontal plane coordinate values ​​(i.e., X-axis coordinate values ​​and Y-axis coordinate values) of the three-dimensional point cloud data contained in each of the multiple height intervals, the target height interval corresponding to the ground is determined; finally, according to the height coordinate values ​​of the three-dimensional point cloud data contained in the target height interval, the plane where the ground is located is determined to complete the preparatory identification of the ground. In this solution, it is only necessary to take a comprehensive picture of the house with a camera, and based on the above-mentioned image processing of the multiple images taken, the task of ground identification can be easily completed. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 A flow chart of a ground recognition method provided by an embodiment of the present invention;

[0047] Figure 2 A flowchart of a method for implementing step 102 provided in one embodiment of the present invention;

[0048] Figure 3 for Figure 2 A schematic diagram of the execution result of the method shown;

[0049] Figure 4 A flowchart of a method for implementing step 103 provided in one embodiment of the present invention;

[0050] Figure 5 for Figure 4 A schematic diagram of the execution result of the method shown;

[0051] Figure 6 A flow chart of a three-dimensional house reconstruction method provided by an embodiment of the present invention;

[0052] Figure 7a A schematic diagram of a panoramic view provided by an embodiment of the present invention;

[0053] Figure 7b A schematic diagram of a three-dimensional reconstruction result of a house provided by an embodiment of the present invention;

[0054] Figure 8 A flowchart of a method for displaying home deployment provided by an embodiment of the present invention;

[0055] Fig. 9 A schematic diagram of a display effect of a home deployment provided by an embodiment of the present invention;

[0056] Fig.10 A schematic diagram of the structure of a ground identification device provided by an embodiment of the present invention;

[0057] Fig.11 For Fig.10 A schematic diagram of the structure of an electronic device corresponding to the ground identification device provided in the illustrated embodiment;

[0058] Fig.12 A schematic diagram of the structure of a three-dimensional house reconstruction device provided by an embodiment of the present invention;

[0059] Fig.13 For Fig.12 A schematic diagram of the structure of an electronic device corresponding to the house three-dimensional reconstruction device provided in the illustrated embodiment;

[0060] Fig.14 A schematic diagram of the structure of a display device for home deployment provided by an embodiment of the present invention;

[0061] Fig.15 For Fig.14 A schematic diagram of the structure of an electronic device corresponding to a display device deployed in a home provided by the illustrated embodiment. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0064] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0065] The ground recognition method provided in the embodiment of the present invention can be executed by an electronic device with shooting and image processing capabilities, such as a camera, a mobile phone and other devices.

[0066] Figure 1 A flow chart of a ground recognition method provided by an embodiment of the present invention is as follows: Figure 1 As shown, the following steps may be included:

[0067] 101. According to a plurality of images obtained by photographing the house, three-dimensional point cloud data corresponding to the house is obtained, wherein the plurality of images include the ground surface of the house.

[0068] 102. Group the three-dimensional point cloud data according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data to determine the three-dimensional point cloud data included in each of the set multiple height intervals.

[0069] 103. Determine a target height interval corresponding to the ground according to horizontal plane coordinate values ​​of the three-dimensional point cloud data contained in each of the plurality of height intervals.

[0070] 104. Determine the plane where the ground is located according to the height coordinate values ​​of the three-dimensional point cloud data included in the target height interval.

[0071] The house mentioned in the embodiment of the present invention may be a residence, a factory building, an office, etc.

[0072] The purpose of the ground recognition method provided by the embodiment of the present invention is to identify the plane where the ground is located in the three-dimensional reconstruction data during the three-dimensional reconstruction of a house.

[0073] In summary, a certain algorithm can be used to obtain the 3D reconstruction data of the house. The input of the algorithm is a plurality of images obtained by photographing the house, wherein the plurality of images contain the ground of the house. The output of the algorithm is called 3D reconstruction data, and the 3D reconstruction data includes the 3D point cloud data corresponding to the house described in this article. Based on this, identifying the plane where the ground is located in the 3D reconstruction data can be considered as identifying the 3D point cloud data corresponding to the ground in the 3D point cloud data, thereby knowing the plane where the ground is located.

[0074] In actual applications, users (the users in this article may refer to the staff who perform the task of 3D reconstruction of the house) can hold an electronic device with a camera function (such as a camera) and move around the house to take pictures to obtain the above-mentioned multiple images. The user needs to take a comprehensive picture of the house. In simple terms, the so-called comprehensive picture means that the user will take pictures of the ground, walls, ceilings, and main objects in the house that reflect the structure of the house. In fact, taking a house as an example, a house generally contains multiple rooms or independent spaces, such as a master bedroom, a second bedroom, a kitchen, a bathroom, and a living room. The multiple images taken by the user include several images corresponding to each room.

[0075] The images taken by the user can be panoramic images. The user can take a panoramic photo in each space, and can take more photos for larger spaces (such as living rooms). When taking photos, the user's position should be in the middle of the space as much as possible, and the corners of the space can be seen, so that the captured image can include the global information of the space.

[0076] In addition, in fact, the user can also take a video of the house by recording, and then extract some key image frames from the video by frame processing as the above multiple images. Among them, the so-called key image frames are image frames that reflect the structure of the house and the layout of the internal furnishings.

[0077] In practical applications, the algorithm used to obtain 3D reconstruction data can be any of the following algorithms, of course, but not limited to: Structure from Motion (SFM) algorithm, Simultaneous Localization and Mapping (SLAM) algorithm.

[0078] In addition, in actual applications, some requirements can be pre-set to determine whether multiple images taken by the user meet the requirements. When some images do not meet the requirements, the user can be prompted to retake the photos. These requirements are, for example, that the brightness of the surrounding environment should not be excessive or too dark, the photographer and other people should not be included in the image, the image should include the ground, etc. When an image is identified as not meeting a certain requirement, the image can be removed, and corresponding prompt information can be output to inform the photographer why the image he / she took does not meet the requirements, so that he / she can make improvements based on this and take qualified images.

[0079] Of course, in practical applications, some preprocessing can be performed on multiple images to improve the quality of the images, such as image enhancement processing.

[0080] After the multiple images are input into the above algorithm, the algorithm will output 3D reconstruction data. As mentioned above, the 3D reconstruction data includes 3D point cloud data corresponding to the house, and these 3D point cloud data are sparse 3D point cloud data. Optionally, in addition to this, the 3D reconstruction data may also include other data information such as camera pose data (reflecting the movement trajectory of the camera).

[0081] In simple terms, the above three-dimensional point cloud data can be considered as a collection of several three-dimensional coordinate points. These three-dimensional point cloud data can reflect the visual texture characteristics of many objects in the house (such as various objects placed, walls, floors, etc.).

[0082] After obtaining the above-mentioned three-dimensional point cloud data, it is necessary to identify the plane where the ground is located from these three-dimensional point cloud data, referring to the identification process of steps 102-104.

[0083] The following is a detailed introduction to the ground recognition process.

[0084] In step 102, the three-dimensional point cloud data are grouped according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data, so as to determine the three-dimensional point cloud data included in each of the set multiple height intervals.

[0085] In actual applications, when a user holds a camera to take pictures of a house, relative to the position of the camera, some of the photographed objects are above the camera (higher than the camera position) and some are below the camera (lower than the camera position). Therefore, if a certain camera position is used as the origin of the three-dimensional coordinate system reconstructed by the camera, from the perspective of the Z axis reflecting the height, some of the above three-dimensional point cloud data correspond to the positive direction of the Z axis, and some correspond to the negative direction of the Z axis.

[0086] Optionally, the origin can be used as the initial point in advance, and multiple equally spaced height intervals can be set along the positive and negative directions of the Z axis. Assuming that the value range of each height interval is 1 cm, then starting from the coordinate origin, along the positive direction of the Z axis, a height interval of 1 cm can be defined: [0, 1], [1, 2], [2, 3], etc., and along the negative direction of the Z axis, a height interval of 1 cm can also be defined: [-1, 0], [-2, -1], [-3, -2], etc.

[0087] Afterwards, the height intervals to which the three-dimensional point cloud data respectively belong are determined according to the height coordinate values ​​(ie, Z-axis coordinate values) corresponding to the three-dimensional point cloud data, thereby realizing grouping processing of the three-dimensional point cloud data according to the height coordinate values.

[0088] It is worth noting that for the task of ground recognition, since the ground is located below the camera position, that is, the ground depth (referring to the depth of the ground in the three-dimensional coordinate system reconstructed by the camera, i.e., the height) is in the negative direction of the Z axis. Therefore, optionally, Figure 2 As shown, step 102 can also be specifically implemented as the following steps:

[0089] 201. According to the height coordinate values ​​corresponding to the three-dimensional point cloud data, three-dimensional point cloud data having height coordinate values ​​less than a preset threshold are screened out from the three-dimensional point cloud data.

[0090] 202. Group the three-dimensional point cloud data whose height coordinate values ​​are less than a preset threshold value to determine the three-dimensional point cloud data contained in each of the set multiple height intervals.

[0091] Optionally, the preset threshold may be set to zero.

[0092] The above-mentioned multiple height intervals can be determined in the following ways:

[0093] Determine the minimum height coordinate value in the three-dimensional point cloud data corresponding to the house; determine the difference between the preset threshold and the minimum height coordinate value, the preset threshold is greater than the minimum height coordinate value; determine multiple height intervals based on the difference and a preset number of groups.

[0094] In fact, the above three-dimensional point cloud data grouping process is equivalent to the process of establishing a histogram that reflects the distribution of the height coordinate values ​​of the three-dimensional point cloud data corresponding to the house. Figure 3 To illustrate by way of example.

[0095] exist Figure 3 In the figure, it is assumed that in all the three-dimensional point cloud data corresponding to the house, the corresponding minimum height coordinate value in the negative direction of the Z axis is represented by minZ, and it is assumed that minZ = -100 cm, the maximum height coordinate value is 0, and it is assumed that the preset number of groups is 100 groups. Based on this, a histogram is drawn.

[0096] To put it simply, first, divide the difference between 0 and minZ by the number of groups 100 to get the width of the group interval: (0-minZ) / 100. Then, calculate the boundary positions of each group. Generally speaking, the boundary positions of each group can be calculated starting from the first group. The lower boundary of the first group is the minimum value (i.e. minZ) minus half of the minimum measurement unit (assuming 1 cm), and the upper boundary of the first group is its lower boundary value plus the group interval. The lower boundary of the second group is the upper boundary value of the first group, and the lower boundary value of the second group plus the group interval is the upper boundary value of the second group, and so on. At this point, 100 groups of height intervals can be obtained. Then, count the frequency of occurrence of data in each group, that is, the number of three-dimensional point cloud data contained in each height interval. Finally, use the group interval as the base and the frequency as the height to make a rectangular diagram of each group, so as to finally form the following Figure 3 The histogram shown in Figure 3 Not all 100 sets of height ranges are shown, only some are shown.

[0097] It should be noted that in actual applications, the 3D point cloud data corresponding to the house obtained actually contains some outliers. In order to reduce the amount of calculation and improve the recognition accuracy, the outliers in the 3D point cloud data can be removed. For the ground recognition scene, these outliers may include reflections of objects such as lights on the ground.

[0098] The method of removing outliers can adopt a certain clustering algorithm to identify and remove outliers.

[0099] Optionally, outliers can be removed in the following manner: for any height interval i among the multiple height intervals, if the number of three-dimensional point cloud data included in the height interval i is less than a set number, the three-dimensional point cloud data included in the height interval i is removed. In this case, the three-dimensional point cloud data included in the height interval i is considered to be an outlier.

[0100] Assuming that the frequency corresponding to a certain set of height intervals in the histogram (i.e., the height of the rectangular graph) is lower than the set threshold, the three-dimensional point cloud data contained in this set of height intervals is considered to be an outlier and should be removed.

[0101] After completing the grouping of the three-dimensional point cloud data into multiple height intervals according to the height coordinate values, in step 103, the target height interval corresponding to the ground is determined according to the horizontal plane coordinate values ​​(referring to the X-axis coordinate value and the Y-axis coordinate value) of the three-dimensional point cloud data contained in each of the multiple height intervals.

[0102] Alternatively, if Figure 4 As shown, step 103 can be specifically implemented by the following steps:

[0103] 401. For any height interval i among a plurality of height intervals, determine a first horizontal plane coordinate range corresponding to the height interval i according to a minimum X-axis coordinate value, a maximum X-axis coordinate value, a minimum Y-axis coordinate value, and a maximum Y-axis coordinate value in the three-dimensional point cloud data contained in the height interval i.

[0104] 402. Determine a second horizontal plane coordinate range corresponding to the house according to a minimum X-axis coordinate value, a maximum X-axis coordinate value, a minimum Y-axis coordinate value, and a maximum Y-axis coordinate value in the three-dimensional point cloud data corresponding to the house.

[0105] 403. Determine area ratios between first horizontal plane coordinate ranges corresponding to each of the plurality of height intervals and the second horizontal plane coordinate range.

[0106] 404. Determine a height interval corresponding to a first horizontal plane coordinate range whose area ratio to the second horizontal plane coordinate range is greater than a set threshold as a target height interval corresponding to the ground.

[0107] For ease of understanding, the following Figure 5 To illustrate Figure 4 The implementation process of the illustrated embodiment.

[0108] exist Figure 5 The three-dimensional point cloud data, i.e., three-dimensional coordinate points, are indicated by black dots in the figure, and each three-dimensional coordinate point has a three-dimensional coordinate represented by (x, y, z).

[0109] Find the maximum and minimum values ​​of the plane coordinate values ​​in all three-dimensional coordinate points, that is, the minimum X-axis coordinate value, the maximum X-axis coordinate value, the minimum Y-axis coordinate value, and the maximum Y-axis coordinate value. Assume that the minimum X-axis coordinate value in all three-dimensional point cloud data is represented as minX1, the maximum X-axis coordinate value is represented as maxX2, the minimum Y-axis coordinate value is represented as minY1, and the maximum Y-axis coordinate value is represented as maxY2. Then, as Figure 5 As shown in , a corresponding rectangular frame A is drawn with (minX1, minY1), (maxX2, minY1), (maxX2, maxY2), and (minX1, maxY2) as vertices as the above-mentioned second horizontal plane coordinate range.

[0110] Similarly, similar processing is performed on the three-dimensional point cloud data contained in each height interval. Assume that for a certain height interval i, the maximum and minimum values ​​of the plane coordinate values ​​are found in the three-dimensional point cloud data contained therein, that is, the minimum X-axis coordinate value, the maximum X-axis coordinate value, the minimum Y-axis coordinate value, and the maximum Y-axis coordinate value. Assume that the minimum X-axis coordinate value in the three-dimensional point cloud data contained in the height interval i is represented as minX3, the maximum X-axis coordinate value is represented as maxX4, the minimum Y-axis coordinate value is represented as minY3, and the maximum Y-axis coordinate value is represented as maxY4. Then, as Figure 5 As shown in , a corresponding rectangular frame Bi is drawn with (minX3, minY3), (maxX4, minY3), (maxX4, maxY4), and (minX3, maxY4) as vertices as the first horizontal plane coordinate range corresponding to the above-mentioned height interval i.

[0111] Through the above steps, the first horizontal plane coordinate ranges corresponding to the multiple height intervals can be obtained, so that the target height interval corresponding to the ground can be determined according to the first horizontal plane coordinate ranges corresponding to the multiple height intervals.

[0112] Specifically, the area ratios between the first horizontal plane coordinate ranges corresponding to each of the multiple height intervals and the second horizontal plane coordinate ranges can be determined, and the ratios are used as the scores of the corresponding height intervals. For the height interval i in the above example, the area ratio is the ratio between the area corresponding to the rectangular frame Bi and the area corresponding to the rectangular frame A, expressed as: Bi / A. Afterwards, the height interval corresponding to the first horizontal plane coordinate range whose area ratio with the second horizontal plane coordinate range is greater than a set threshold is determined as the target height interval corresponding to the ground. The set threshold can be set to a value less than 1 and close to 1, such as 0.8.

[0113] Optionally, the target height interval corresponding to the ground may be found in the following manner:

[0114] A plurality of height intervals are traversed in order from low to high values ​​to determine that the height interval corresponding to the first horizontal plane coordinate range whose area ratio between the first and second horizontal plane coordinate ranges is greater than a set threshold is the target height interval corresponding to the ground.

[0115] Among them, taking the case where multiple height intervals are divided at (minZ, 0) along the negative direction of the Z axis, the order of the height intervals from low to high refers to the order from the height interval corresponding to the height coordinate value minZ to the height interval corresponding to the height coordinate value 0.

[0116] The reason why the height interval corresponding to the first horizontal plane coordinate range whose area ratio between the first and second horizontal plane coordinate ranges traversed along this direction is greater than the set threshold is taken as the target height interval corresponding to the ground is because: compared with other objects in the house, the plane area of ​​the ground is larger and the ground is lower.

[0117] Of course, the method for finding the target height interval corresponding to the ground is not limited to the above method. For example, if the area ratio between the first horizontal plane coordinate range and the second horizontal plane coordinate range corresponding to each height interval is found in sequence, and the area ratio between the first horizontal plane coordinate range and the second horizontal plane coordinate range is greater than the set threshold, there are multiple first horizontal plane coordinate ranges, then the height interval with the smallest value can be determined from the height intervals corresponding to the multiple first horizontal plane coordinate ranges as the target height interval corresponding to the ground. For example, assuming that the area ratio between the first horizontal plane coordinate range and the second horizontal plane coordinate range corresponding to the height interval (-80.5, -79.5) is greater than the set threshold 0.8, and assuming that the area ratio between the first horizontal plane coordinate range and the second horizontal plane coordinate range corresponding to the height interval (-10.5, -9.5) is also greater than the set threshold 0.8, then the height interval (-80.5, -79.5) with the smallest value can be determined as the target height interval corresponding to the ground.

[0118] It is worth noting that in an optional embodiment, the above-mentioned second horizontal plane coordinate range does not need to be calculated, but only the first horizontal plane coordinate range corresponding to each height interval is calculated. Thus, the height interval corresponding to the first horizontal plane coordinate range with the largest area in the first horizontal plane coordinate ranges corresponding to each height interval can be determined as the target height interval corresponding to the ground.

[0119] Finally, the plane where the ground is located is determined according to the height coordinate values ​​of the three-dimensional point cloud data included in the target height interval. Optionally, the plane corresponding to the average height coordinate value of the three-dimensional point cloud data included in the target height interval can be determined as the plane where the ground is located. That is, the height coordinate values ​​of the three-dimensional point cloud data included in the target height interval are averaged, and the calculated average height value is the ground depth.

[0120] Optionally, after determining the plane where the ground is located, confirmation information corresponding to the determination result can be output to the user for the user to confirm whether to modify the determination result. When the user modifies the determination result, the user's modification information can be recorded to facilitate the subsequent optimization of the determination process of the plane where the ground is located in combination with the modification information.

[0121] In summary, in this solution, it is only necessary to use a camera to take a comprehensive picture of the house, and based on the above-mentioned image processing on the multiple images taken, the ground can be easily and accurately recognized, that is, the plane where the ground is located can be found in the three-dimensional point cloud data obtained by three-dimensional reconstruction of the house.

[0122] In addition, in actual applications, in addition to the ground plane, there may be other planes in the house, such as window sills, stove tops, desktops, etc. The recognition principles for the locations of other types of planes are similar to the recognition principles for the ground plane introduced above. Therefore, the above-mentioned recognition principles for the ground plane can be applied to the recognition of other planes in the house.

[0123] In summary, in this solution, it is only necessary to use a camera to take a comprehensive picture of the house, and based on the above-mentioned image processing on the multiple images taken, the ground can be easily and accurately recognized, that is, the plane where the ground is located can be found in the three-dimensional point cloud data obtained by three-dimensional reconstruction of the house.

[0124] The above-mentioned determination result of the plane where the ground is located can be applied to some application scenarios, such as the above-mentioned scenario of three-dimensional reconstruction of a house, and another example is the scenario of house decoration.

[0125] Figure 6 A flowchart of a three-dimensional house reconstruction method provided by an embodiment of the present invention, such as Figure 6 As shown, the method may include the following steps:

[0126] 601. Acquire three-dimensional point cloud data corresponding to the house based on a plurality of images obtained by photographing the house, wherein the plurality of images include the ground surface of the house.

[0127] 602. Group the three-dimensional point cloud data according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data to determine the three-dimensional point cloud data included in each of the set multiple height intervals.

[0128] 603. Determine a target height interval corresponding to the ground based on the horizontal plane coordinate values ​​of the three-dimensional point cloud data included in each of the multiple height intervals, and determine the plane where the ground is located based on the height coordinate values ​​of the three-dimensional point cloud data included in the target height interval.

[0129] 604. Based on the result of determining the plane where the ground is located, perform three-dimensional reconstruction of the house.

[0130] In this paper, the purpose of three-dimensional reconstruction of the house is mainly to establish a three-dimensional floor plan of the house.

[0131] Generally speaking, a complete house will include at least one room (or space). Based on this, in summary, the process of three-dimensional reconstruction of a house includes: establishing a three-dimensional model of a single room (the model can be understood as a floor plan), and then based on the determination result of the plane where the above-mentioned ground is located, projecting the three-dimensional models of each room onto the determined ground, and finally completing the three-dimensional reconstruction of the house based on the connection relationship between the rooms.

[0132] Among them, the establishment of a three-dimensional model of a single room, the determination of the connection relationship between rooms, etc. can be achieved by referring to existing related technologies.

[0133] For ease of understanding, the following Figure 7a and Figure 7b To illustrate the three-dimensional reconstruction process of a house.

[0134] exist Figure 7a In this paper, we only take a panoramic image as an example. Assume that the panoramic image is an image obtained by photographing a house. In this image, the main structure of the house and the ground are all photographed. By processing the panoramic image with the SFM algorithm, several 3D point cloud data can be obtained. By performing the above processing on several 3D point cloud data, the plane where the ground in the house is located can be identified. Then the house is reconstructed in 3D, and the reconstruction result is assumed to be Figure 7b It is worth noting that Figure 7b The three-dimensional model shown in Figure 7a The panorama shown in the figure does not match. Figure 7b The figure is only used to illustrate the three-dimensional reconstruction result of the house.

[0135] For the descriptions not elaborated in detail in this embodiment, please refer to the related introductions in other embodiments above and will not be repeated here.

[0136] Figure 8 This is a flow chart of a method for displaying home deployment provided by an embodiment of the present invention, such as Figure 8 As shown, the method may include the following steps:

[0137] 801. Acquire three-dimensional point cloud data corresponding to the house based on a plurality of images obtained by photographing the house, wherein the plurality of images include the ground surface of the house.

[0138] 802. Group the three-dimensional point cloud data according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data to determine the three-dimensional point cloud data included in each of the set multiple height intervals.

[0139] 803. Determine a target height interval corresponding to the ground based on the horizontal plane coordinate values ​​of the three-dimensional point cloud data contained in each of the multiple height intervals, and determine the plane where the ground is located based on the height coordinate values ​​of the three-dimensional point cloud data contained in the target height interval.

[0140] 804. Perform three-dimensional reconstruction of the house based on the result of determining the plane where the ground is located, and display the target object on the reconstructed ground.

[0141] After the house is reconstructed in 3D, a user (such as the owner of the house) can preview the decoration effect based on the 3D reconstruction result. For example, suppose the user wants to place a sofa and a TV cabinet on the ground and wants to see the effect after placement in advance. At this time, the user can load the 3D reconstruction result of the house, that is, the reconstructed floor plan, through an application in the terminal device. After that, suppose the application provides a variety of decoration item models (such as a variety of furniture, home appliances, etc.) for users to choose from. The user can select the item model they need to use and locate the selected element to a certain position on the ground, so that the effect of placing the above item model at that position on the ground can be seen.

[0142] For example Fig. 9 As shown in , a sofa is placed on the ground, and the user can view the deployment effect of the sofa from different angles by changing the viewing angle of the three-dimensional floor plan.

[0143] In addition, in actual applications, optionally, the above application can also make decoration recommendations to users. For example, different items are usually placed on the floors of different spaces, and the items that are generally placed on the floors of different spaces can be summarized. Based on this, in the obtained three-dimensional floor plan, items corresponding to the floors of the corresponding spaces can be recommended for users to choose. Users select the required items and position the selected items at the ground locations where they need to be placed.

[0144] For the descriptions not elaborated in detail in this embodiment, please refer to the related introductions in other embodiments above and will not be repeated here.

[0145] The ground recognition device, the house 3D reconstruction device, and the home deployment display device of one or more embodiments of the present invention are described in detail below. Those skilled in the art will appreciate that these devices can be configured using commercially available hardware components through the steps taught in this solution.

[0146] Fig.10 A schematic diagram of the structure of a ground identification device provided by an embodiment of the present invention is shown in FIG. Fig.10 As shown, the ground identification device includes: an acquisition module 11, a grouping module 12, and a determination module 13.

[0147] The acquisition module 11 is used to acquire three-dimensional point cloud data corresponding to the house based on multiple images obtained by photographing the house, wherein the multiple images include the ground surface of the house.

[0148] The grouping module 12 is used to group the three-dimensional point cloud data according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data, so as to determine the three-dimensional point cloud data contained in each of the set multiple height intervals.

[0149] The determination module 13 is used to determine the target height interval corresponding to the ground according to the horizontal plane coordinate values ​​of the three-dimensional point cloud data contained in each of the multiple height intervals, and determine the plane where the ground is located according to the height coordinate values ​​of the three-dimensional point cloud data contained in the target height interval.

[0150] Optionally, the grouping module 12 can be specifically used to: filter out three-dimensional point cloud data with height coordinate values ​​less than a preset threshold from the three-dimensional point cloud data according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data; group the three-dimensional point cloud data with height coordinate values ​​less than the preset threshold to determine the three-dimensional point cloud data contained in each of the set multiple height intervals.

[0151] Optionally, the preset threshold is zero.

[0152] Among them, optionally, the grouping module 12 can also be used to: determine the minimum height coordinate value in the three-dimensional point cloud data corresponding to the house; determine the difference between the preset threshold and the minimum height coordinate value, and the preset threshold is greater than the minimum height coordinate value; determine the multiple height intervals based on the difference and the preset number of groups.

[0153] Optionally, in the process of determining the target height interval corresponding to the ground, the determination module 13 can be specifically used to: for any height interval i among the multiple height intervals, determine the first horizontal plane coordinate range corresponding to the height interval i according to the minimum X-axis coordinate value, the maximum X-axis coordinate value, the minimum Y-axis coordinate value and the maximum Y-axis coordinate value in the three-dimensional point cloud data contained in the height interval i; determine the target height interval corresponding to the ground according to the first horizontal plane coordinate ranges corresponding to each of the multiple height intervals.

[0154] Among them, optionally, in the process of determining the target height interval corresponding to the ground according to the first horizontal plane coordinate ranges corresponding to each of the multiple height intervals, the determination module 13 can be specifically used to: determine the second horizontal plane coordinate range corresponding to the house according to the minimum X-axis coordinate value, the maximum X-axis coordinate value, the minimum Y-axis coordinate value and the maximum Y-axis coordinate value in the three-dimensional point cloud data corresponding to the house; determine the area ratios between the first horizontal plane coordinate ranges corresponding to each of the multiple height intervals and the second horizontal plane coordinate range; determine the height interval corresponding to the first horizontal plane coordinate range whose area ratio to the second horizontal plane coordinate range is greater than a set threshold as the target height interval corresponding to the ground.

[0155] Among them, optionally, in the process of determining that the height interval corresponding to the first horizontal plane coordinate range whose area ratio to the second horizontal plane coordinate range is greater than a set threshold is the target height interval corresponding to the ground, the determination module 13 can be specifically used to: traverse the multiple height intervals in order from low to high values ​​to determine that the height interval corresponding to the first horizontal plane coordinate range whose area ratio to the second horizontal plane coordinate range is greater than the set threshold is the target height interval corresponding to the ground.

[0156] Among them, optionally, in the process of determining that the height interval corresponding to the first horizontal plane coordinate range whose area ratio with the second horizontal plane coordinate range is greater than a set threshold is the target height interval corresponding to the ground, the determination module 13 can also be used for: if there are multiple first horizontal plane coordinate ranges whose area ratio with the second horizontal plane coordinate range is greater than the set threshold, then determine the height interval with the smallest value from the height intervals corresponding to the multiple first horizontal plane coordinate ranges as the target height interval corresponding to the ground.

[0157] Optionally, in the process of determining the plane where the ground is located based on the height coordinate values ​​of the three-dimensional point cloud data contained in the target height interval, the determination module 13 can be specifically used to: determine that the plane corresponding to the average height coordinate value of the three-dimensional point cloud data contained in the target height interval is the plane where the ground is located.

[0158] Optionally, the grouping module 12 may also be used to remove outlier points in the three-dimensional point cloud data corresponding to the house.

[0159] Optionally, in removing outliers in the three-dimensional point cloud data corresponding to the house, the grouping module 12 can be specifically used for: for any height interval i among the multiple height intervals, if the number of three-dimensional point cloud data contained in the height interval i is less than a set number, then removing the three-dimensional point cloud data contained in the height interval i.

[0160] Fig.10 The ground recognition device shown can perform the aforementioned Figures 1 to 5 For the method provided in the illustrated embodiment, for the part not described in detail in this embodiment, reference can be made to the relevant description of the aforementioned embodiment, which will not be described again here.

[0161] In one possible design, the above Fig.10 The structure of the ground identification device shown can be implemented as an electronic device. Fig.11 As shown, the electronic device may include: a first processor 21 and a first memory 22. The first memory 22 stores executable code. When the executable code is executed by the first processor 21, at least the first processor 21 can implement the above-mentioned Figures 1 to 5 The ground recognition method provided in the illustrated embodiment.

[0162] The structure of the electronic device may further include a first communication interface 23 for communicating with other devices or a communication network.

[0163] In addition, an embodiment of the present invention provides a non-transitory machine-readable storage medium, wherein an executable code is stored on the non-transitory machine-readable storage medium. When the executable code is executed by a processor of an electronic device, the processor executes the aforementioned Figures 1 to 5 The ground recognition method provided in the illustrated embodiment.

[0164] Fig.12 A schematic diagram of the structure of a three-dimensional house reconstruction device provided by an embodiment of the present invention is shown in FIG. Fig.12 As shown, the device includes: an acquisition module 31, a grouping module 32, a determination module 33, and a reconstruction module 34.

[0165] The acquisition module 31 is used to acquire three-dimensional point cloud data corresponding to the house based on multiple images obtained by photographing the house, wherein the multiple images include the ground surface of the house.

[0166] The grouping module 32 is used to group the three-dimensional point cloud data according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data, so as to determine the three-dimensional point cloud data contained in each of the set multiple height intervals.

[0167] The determination module 33 is used to determine the target height interval corresponding to the ground according to the horizontal plane coordinate values ​​of the three-dimensional point cloud data contained in each of the multiple height intervals, and determine the plane where the ground is located according to the height coordinate values ​​of the three-dimensional point cloud data contained in the target height interval.

[0168] The reconstruction module 34 is used to perform three-dimensional reconstruction of the house according to the determination result of the plane where the ground is located.

[0169] Fig.12 The device shown can perform the aforementioned Figure 6 For the method provided in the illustrated embodiment, for the part not described in detail in this embodiment, reference can be made to the relevant description of the aforementioned embodiment, which will not be described again here.

[0170] In one possible design, the above Fig.12 The structure of the house three-dimensional reconstruction device shown can be realized as an electronic device. Fig.13 As shown, the electronic device may include: a second processor 41 and a second memory 42. The second memory 42 stores executable code. When the executable code is executed by the second processor 41, at least the second processor 41 can implement the above-mentioned Figure 6 The three-dimensional reconstruction method of a house is provided in the illustrated embodiment.

[0171] The structure of the electronic device may further include a second communication interface 43 for communicating with other devices or a communication network.

[0172] In addition, an embodiment of the present invention provides a non-transitory machine-readable storage medium, wherein an executable code is stored on the non-transitory machine-readable storage medium. When the executable code is executed by a processor of an electronic device, the processor executes the aforementioned Figure 6 The three-dimensional reconstruction method of a house is provided in the illustrated embodiment.

[0173] Fig.14 This is a schematic diagram of a display device for home deployment according to an embodiment of the present invention. Fig.14 As shown, the device includes: an acquisition module 51, a grouping module 52, a determination module 53, and a display module 54.

[0174] The acquisition module 51 is used to acquire three-dimensional point cloud data corresponding to the house based on multiple images obtained by photographing the house, wherein the multiple images include the ground of the house.

[0175] The grouping module 52 is used to group the three-dimensional point cloud data according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data, so as to determine the three-dimensional point cloud data contained in each of the set multiple height intervals.

[0176] The determination module 53 is used to determine the target height interval corresponding to the ground according to the horizontal plane coordinate values ​​of the three-dimensional point cloud data contained in each of the multiple height intervals, and determine the plane where the ground is located according to the height coordinate values ​​of the three-dimensional point cloud data contained in the target height interval.

[0177] The display module 54 is used to perform three-dimensional reconstruction of the house according to the determination result of the plane where the ground is located, and display the target object on the reconstructed ground.

[0178] Fig.14 The device shown can perform the aforementioned Figure 8 For the method provided in the illustrated embodiment, for the part not described in detail in this embodiment, reference can be made to the relevant description of the aforementioned embodiment, which will not be described again here.

[0179] In one possible design, the above Fig.14 The structure of the display device for home deployment shown can be implemented as an electronic device. Fig.15 As shown, the electronic device may include: a third processor 61 and a third memory 62. The third memory 62 stores executable code. When the executable code is executed by the third processor 61, at least the third processor 61 can implement the above-mentioned Figure 8 A method for displaying home deployment is provided in the illustrated embodiment.

[0180] The structure of the electronic device may further include a third communication interface 63 for communicating with other devices or a communication network.

[0181] In addition, an embodiment of the present invention provides a non-transitory machine-readable storage medium, wherein an executable code is stored on the non-transitory machine-readable storage medium. When the executable code is executed by a processor of an electronic device, the processor executes the aforementioned Figure 8 A method for displaying home deployment is provided in the illustrated embodiment.

[0182] The device embodiments described above are merely illustrative, wherein the modules described as separate components may or may not be physically separated. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. Those of ordinary skill in the art may understand and implement the present invention without creative effort.

[0183] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course can also be implemented by combining hardware and software. Based on such an understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a computer product, and the present invention can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0184] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A ground recognition method, characterized in that: include: Acquire three-dimensional point cloud data corresponding to the house according to a plurality of images obtained by photographing the house, wherein the plurality of images include the ground surface of the house; The three-dimensional point cloud data are grouped according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data to determine the three-dimensional point cloud data included in each of the set multiple height intervals; For any height interval among the multiple height intervals, determine a first horizontal plane coordinate range corresponding to the any height interval according to a minimum X-axis coordinate value, a maximum X-axis coordinate value, a minimum Y-axis coordinate value, and a maximum Y-axis coordinate value in the three-dimensional point cloud data contained in the any height interval; Determine a target height interval corresponding to the ground according to the first horizontal plane coordinate ranges corresponding to each of the plurality of height intervals; The plane where the ground is located is determined according to the height coordinate values ​​of the three-dimensional point cloud data included in the target height interval.

2. The method according to claim 1, characterized in that: The grouping of the three-dimensional point cloud data according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data to determine the three-dimensional point cloud data contained in each of the set multiple height intervals includes: According to the height coordinate values ​​corresponding to the three-dimensional point cloud data, three-dimensional point cloud data having a height coordinate value less than a preset threshold are screened out from the three-dimensional point cloud data; The three-dimensional point cloud data whose height coordinate values ​​are less than a preset threshold are grouped to determine the three-dimensional point cloud data contained in each of the set multiple height intervals.

3. The method according to claim 2, characterized in that The preset threshold is zero.

4. The method according to claim 2, characterized in that: The method further comprises: Determine the minimum height coordinate value in the three-dimensional point cloud data corresponding to the house; Determine a difference between the preset threshold and the minimum height coordinate value, the preset threshold being greater than the minimum height coordinate value; The multiple height intervals are determined according to the difference and a preset number of groups.

5. The method according to claim 1, characterized in that The step of determining a target height interval corresponding to the ground according to the first horizontal plane coordinate ranges corresponding to each of the plurality of height intervals includes: Determine a second horizontal plane coordinate range corresponding to the house according to a minimum X-axis coordinate value, a maximum X-axis coordinate value, a minimum Y-axis coordinate value, and a maximum Y-axis coordinate value in the three-dimensional point cloud data corresponding to the house; Determine area ratios between the first horizontal plane coordinate ranges corresponding to each of the plurality of height intervals and the second horizontal plane coordinate range; The height interval corresponding to the first horizontal plane coordinate range whose area ratio to the second horizontal plane coordinate range is greater than a set threshold is determined as the target height interval corresponding to the ground.

6. The method according to claim 5, characterized in that The step of determining that the height interval corresponding to the first horizontal plane coordinate range whose area ratio to the second horizontal plane coordinate range is greater than a set threshold is the target height interval corresponding to the ground includes: The multiple height intervals are traversed in order from low to high values ​​to determine that the height interval corresponding to the first horizontal plane coordinate range whose area ratio between the first and second horizontal plane coordinate ranges is greater than a set threshold is the target height interval corresponding to the ground.

7. The method according to claim 5, characterized in that The step of determining that the height interval corresponding to the first horizontal plane coordinate range whose area ratio to the second horizontal plane coordinate range is greater than a set threshold is the target height interval corresponding to the ground includes: If there are multiple first horizontal plane coordinate ranges whose area ratio to the second horizontal plane coordinate range is greater than a set threshold, the height interval with the smallest value is determined from the height intervals corresponding to the multiple first horizontal plane coordinate ranges as the target height interval corresponding to the ground.

8. The method according to claim 1, characterized in that: The step of determining the plane where the ground is located according to the height coordinate values ​​of the three-dimensional point cloud data included in the target height interval includes: The plane corresponding to the average height coordinate value of the three-dimensional point cloud data included in the target height interval is determined to be the plane where the ground is located.

9. The method according to claim 1, characterized in that: The method further comprises: Remove outliers in the three-dimensional point cloud data corresponding to the house.

10. The method according to claim 9, characterized in that The removing of outliers in the three-dimensional point cloud data corresponding to the house comprises: For any height interval among the multiple height intervals, if the amount of three-dimensional point cloud data included in the any height interval is less than a set amount, the three-dimensional point cloud data included in the any height interval is removed.

11. A ground identification device, characterized in that: include: An acquisition module, used to acquire three-dimensional point cloud data corresponding to the house according to a plurality of images obtained by photographing the house, wherein the plurality of images include the ground of the house; A grouping module, used for grouping the three-dimensional point cloud data according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data, so as to determine the three-dimensional point cloud data contained in each of the set multiple height intervals; A determination module is used to determine, for any height interval among the multiple height intervals, a first horizontal plane coordinate range corresponding to the any height interval based on a minimum X-axis coordinate value, a maximum X-axis coordinate value, a minimum Y-axis coordinate value and a maximum Y-axis coordinate value in the three-dimensional point cloud data contained in the any height interval, determine a target height interval corresponding to the ground based on the first horizontal plane coordinate ranges corresponding to each of the multiple height intervals, and determine the plane where the ground is located based on the height coordinate values ​​of the three-dimensional point cloud data contained in the target height interval.

12. An electronic device, characterized in that: include: A memory and a processor; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor executes the ground recognition method as described in any one of claims 1 to 10.

13. A non-transitory machine-readable storage medium, characterized in that: The non-transitory machine-readable storage medium stores executable code, and when the executable code is executed by a processor of an electronic device, the processor is caused to execute the ground recognition method as described in any one of claims 1 to 10.

14. A three-dimensional reconstruction method for a house, characterized in that: include: Acquire three-dimensional point cloud data corresponding to the house according to a plurality of images obtained by photographing the house, wherein the plurality of images include the ground surface of the house; The three-dimensional point cloud data are grouped according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data to determine the three-dimensional point cloud data included in each of the set multiple height intervals; For any height interval among the multiple height intervals, determine a first horizontal plane coordinate range corresponding to the any height interval according to a minimum X-axis coordinate value, a maximum X-axis coordinate value, a minimum Y-axis coordinate value, and a maximum Y-axis coordinate value in the three-dimensional point cloud data contained in the any height interval; Determine a target height interval corresponding to the ground according to the first horizontal plane coordinate ranges corresponding to each of the plurality of height intervals; Determine the plane where the ground is located according to the height coordinate values ​​of the three-dimensional point cloud data included in the target height interval; According to the determination result of the plane where the ground is located, the three-dimensional reconstruction of the house is performed.

15. An electronic device, characterized in that: include: A memory and a processor; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor executes the three-dimensional reconstruction method of a house as described in claim 14.

16. A method for displaying home furnishing deployment, characterized in that: include: Acquire three-dimensional point cloud data corresponding to the house according to a plurality of images obtained by photographing the house, wherein the plurality of images include the ground surface of the house; The three-dimensional point cloud data are grouped according to the height coordinate values ​​corresponding to each of the three-dimensional point cloud data to determine the three-dimensional point cloud data included in each of the set multiple height intervals; For any height interval among the multiple height intervals, determine a first horizontal plane coordinate range corresponding to the any height interval according to a minimum X-axis coordinate value, a maximum X-axis coordinate value, a minimum Y-axis coordinate value, and a maximum Y-axis coordinate value in the three-dimensional point cloud data contained in the any height interval; Determine a target height interval corresponding to the ground according to the first horizontal plane coordinate ranges corresponding to each of the plurality of height intervals; Determining the plane where the ground is located according to the height coordinate values ​​of the three-dimensional point cloud data included in the target height interval; According to the determination result of the plane where the ground is located, the house is reconstructed in three dimensions, and the target object is displayed on the reconstructed ground.

17. An electronic device, characterized in that: include: A memory and a processor; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor executes the home deployment display method as described in claim 16.

Images