CN111308495A - Method for generating indoor house type 3D data through radar ranging - Google Patents
Method for generating indoor house type 3D data through radar ranging Download PDFInfo
- Publication number
- CN111308495A CN111308495A CN202010176033.7A CN202010176033A CN111308495A CN 111308495 A CN111308495 A CN 111308495A CN 202010176033 A CN202010176033 A CN 202010176033A CN 111308495 A CN111308495 A CN 111308495A
- Authority
- CN
- China
- Prior art keywords
- wall
- data
- line
- indoor
- generating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
Abstract
The invention discloses a method for generating indoor house type 3D data by radar ranging, which comprises the following steps: s1, scanning and collecting two-dimensional wall data of the indoor environment; s2, generating an indoor space point cloud picture; s3, obtaining an indoor house type contour map, and performing denoising treatment to generate a linear house type sketch; s4, obtaining the vertex information of the wall line in the sketch and the space coordinates of each wall member; s5, generating a three-dimensional model of the wall based on line data of the sketch and vertex data of the wall line, and combining the three-dimensional model of the wall with each wall component according to the space coordinates of each wall component to generate a 3D house type model; and S6, generating 3D data of the indoor house type. According to the method, the indoor space point cloud picture is generated according to the two-dimensional wall data acquired by scanning, the point cloud picture is processed to obtain the indoor house type outline picture, the linear house type sketch processed by denoising the outline picture is obtained, the extraction of the indoor wall and the member characteristics is more accurate, and the generated 3D house type model is high in precision.
Description
Technical Field
The invention relates to the technical field of house type measurement, in particular to a method for generating indoor house type 3D data through radar ranging.
Background
With the development of measurement hardware devices and the development of software image recognition technology, the measurement form and precision of the technology, including the speed of image recognition, become stronger, and the application technology in the indoor measurement direction is also possible to be innovated. In the field of indoor house type measurement, the development of portable equipment, particularly the development of hardware equipment such as mobile phones and the like and the popularization of 4G and 5G networks are benefited, so that the rapid acquisition of house type field data becomes possible.
In the existing indoor environment measurement technology, three-dimensional reconstruction is carried out on the basis of an image recognition mode, namely, characteristics of indoor wall bodies and indoor members are obtained through image characteristic recognition, and the characteristics obtained through the reconstruction mode have large errors, so that the generated indoor house type model has low precision.
In addition, the infrared laser Bluetooth distance measuring instrument is mostly adopted in the field of indoor household type measurement to measure the length of a single line and is combined with App software to transmit and collect data, the efficiency of data collection is low, and the collection precision is greatly influenced by the operation proficiency of a collector.
Disclosure of Invention
The invention aims to provide a method for generating indoor house type 3D data by radar ranging, which can generate a high-precision indoor house type model.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for generating indoor house type 3D data by radar ranging comprises the following steps:
s1, performing omnibearing laser ranging scanning on the indoor space, and scanning and collecting two-dimensional wall data of the indoor environment;
s2, generating an indoor space point cloud picture with data point location two-dimensional coordinate information through mapping software;
s3, processing the indoor space point cloud picture through algorithm calculation and image recognition to obtain an indoor house type contour map, and denoising the contour map to generate a linear house type sketch;
s4, converting line data of the line body house type sketch into a JSON data format, and performing deserialization extraction to obtain vertex information of wall lines in the sketch and space coordinates of wall components;
s5, generating a three-dimensional model of the wall based on line data of the sketch and vertex data of the wall line, and combining the three-dimensional model of the wall with each wall component according to the space coordinates of each wall component to generate a 3D house type model;
and S6, perfecting the indoor measurement data, and finally generating 3D data of the indoor house type.
Further, in step S2, the two-dimensional point cloud data is identified and converted by an image identification algorithm, and the breakpoints or wrong details of the scanned image are corrected to form a house-type plan view close to the real scene.
Further, step S3 is specifically:
s31, picture preprocessing: carrying out binarization and morphological processing on the point cloud bitmap to distinguish a foreground and a background;
s32, forming a contour diagram: finding out the outline of which the area in the preprocessed image meets a certain condition according to a findContours function of opencv, and deleting redundant parts to obtain a house type main body;
s33, contour map data identification: traversing the contour map, finding out a pixel coordinate with a pixel value of 255, and obtaining a line segment endpoint coordinate;
s34, straight line approximation: traversing the identified straight line data, and combining the line segments which are connected end to end but staggered into a straight line;
s35, adjusting the straight-line end point data: traversing the straight line data, and unifying the end point data of the straight line and the end point data of the straight line connected with the end point data;
s36, secondarily integrating straight lines and deleting redundant line segments: traversing the straight line data, integrating the staggered straight lines into a straight line and deleting redundant line segments;
s37, closed straight line data: and (3) selecting two ends of a certain straight line as a starting point and an end point, traversing the detected straight line data from the starting point to the end point, and connecting the unclosed line segments to generate the line body house type sketch.
Further, the specific process of step S37 is:
traversing the detected linear data from the starting point, and marking the linear data and the end point coordinates of the connecting line which is being searched currently;
if the two ends of the straight line are connected in a wired mode, no processing is carried out, if a wireless section connection condition exists at one end of the straight line, the straight line connected with the wireless section also exists at the other end point is found out, the distance between the two end points is the nearest, and line segment data connecting the two straight lines is added;
and when the marked coordinates return to the end point, traversing is completed, the straight line is closed, and a linear house type sketch is generated.
Further, the generation process of the three-dimensional wall model in step S5 is as follows:
generating a contour line of the wall according to the line data of the sketch and the thickness of the wall;
respectively generating a wall ground surface of the house, a top surface of the house, an inner wall surface of the house and an outer wall surface of the house according to the wall contour line and the vertex data of the wall line to obtain a model surface of the wall;
and generating a three-dimensional model of the wall body according to the molded surface of the wall body model.
Further, the process of generating the wall three-dimensional model according to the wall model surface comprises the following steps:
obtaining four vertexes of the wall surface according to line data of the sketch and vertex data of the wall body line;
and on the vertical plane of the wall line, three non-repetitive vertexes are respectively used for anticlockwise connection, and triangular surface processing is carried out, wherein all the triangular surfaces form a three-dimensional model forming the house wall.
Further, the process of merging the three-dimensional wall model and the wall members in step S5 is as follows:
and judging the inclusion relationship between the wall three-dimensional model and the wall member, hollowing out the position of the wall three-dimensional model containing the wall member according to the type, height and size of the wall member, and merging by using the wall member.
Furthermore, the indoor space is scanned in an all-dimensional mode by adopting the 360-degree laser scanning range radar, and the 360-degree laser scanning range radar is subjected to tilt compensation by utilizing an algorithm in combination with a degree of freedom inertial navigation system.
After adopting the technical scheme, compared with the background technology, the invention has the following advantages:
1. according to the method, the indoor space point cloud picture is generated according to the two-dimensional wall data acquired by scanning, the point cloud picture is processed to obtain the indoor house type outline picture, the linear house type sketch processed by denoising the outline picture is obtained, the extraction of the indoor wall and the member characteristics is more accurate, and the generated 3D house type model is high in precision.
2. The invention adopts the 360-degree laser scanning range radar to carry out all-dimensional scanning on the indoor space, combines the freedom degree inertial navigation system and utilizes the algorithm to carry out tilt compensation on the 360-degree laser scanning range radar, thereby not only improving the efficiency of data acquisition, but also ensuring that the acquisition precision is not influenced by the operation proficiency of an acquirer.
Drawings
FIG. 1 is a block flow diagram of the present invention;
FIG. 2 is a block flow diagram of a schematic representation of a cable house layout;
FIG. 3 is a schematic diagram of a point cloud picture;
FIG. 4 is a plan view of a house in a near reality scenario;
FIG. 5 is a diagram illustrating the effect of preprocessing the picture in step S31;
fig. 6 is a profile view formed in step S32;
fig. 7 is a diagram illustrating the effect of the processing in step S34;
fig. 8 is a diagram illustrating the effect of the processing in step S35;
fig. 9 is a diagram showing the effect of the processing in step S36;
fig. 10 is a schematic diagram of the line house type generated in step S37.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In the present invention, it should be noted that the terms "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are all based on the orientation or positional relationship shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the apparatus or element of the present invention must have a specific orientation, and thus, should not be construed as limiting the present invention.
Examples
Referring to fig. 1, the invention discloses a method for generating indoor house type 3D data by radar ranging, comprising the steps of S1-S6:
and S1, performing omnibearing laser ranging scanning on the indoor space, and scanning and collecting two-dimensional wall data of the indoor environment.
In this embodiment, adopt 360 laser scanning range radar to carry out all-round scanning to the indoor space to combine degree of freedom inertial navigation system, utilize the algorithm to carry out the slope compensation to 360 laser scanning range radar, just so can hand this kind of 360 laser scanning range radar of high accuracy and remove fast in the indoor environment fast, scan and gather the two-dimensional wall body data of indoor environment.
The high-precision 360-degree laser scanning ranging mapping radar combines technologies such as mapping construction and real-time positioning, the high-speed scanning measurement of an indoor environment is carried out by the aid of the laser radar, an SLAM engine, a real-time positioning algorithm chip and the like, and meanwhile, the large-area indoor high-precision mapping construction and real-time positioning can be achieved by the aid of a high-performance SLAM map optimization engine and a fine mapping construction technology.
S2, generating an indoor space point cloud picture with data point location two-dimensional coordinate information through SLAM mapping software, wherein the generated point cloud picture in BMP format is shown in figure 3.
In the step S2, the two-dimensional point cloud data is identified and converted by an image identification algorithm, the break point or the wrong detail of the scanned image is corrected, a house-type plan close to the real scene is formed, and the corrected arc plan is as shown in fig. 4.
And S3, processing the indoor space point cloud picture through algorithm calculation and image recognition to obtain an indoor house type contour map, and denoising the contour map to generate a linear house type sketch.
As shown in fig. 1 and fig. 2, step S3 specifically includes:
s31, picture preprocessing: binarization and morphological processing are performed on the point cloud bitmap to distinguish a foreground from a background, and comparison is performed before and after preprocessing of the image, as shown in fig. 5.
S32, forming a contour diagram: and finding out the outline with the area meeting a certain condition in the preprocessed image according to a findContours function of opencv, and deleting redundant parts to obtain the house-type main body, as shown in fig. 6.
S33, contour map data identification: and traversing the contour map, finding out the pixel coordinate with the pixel value of 255, and obtaining the coordinates of the line segment end points.
S34, straight line approximation: because a point cloud bitmap obtained by radar scanning may have a situation that one straight line is staggered into two or three straight lines, the identified straight line data must be traversed, and line segments which are connected end to end but staggered are combined into one straight line, as shown in fig. 7.
S35, adjusting the straight-line end point data: since the end points do not coincide between individual connected straight lines, it is necessary to traverse the straight line data and unify the end point data of the straight line with the end point data of the straight line connected thereto, as shown in fig. 8.
S36, secondarily integrating straight lines and deleting redundant line segments: it can be seen from fig. 8 that there are some cases where the individual lines are also staggered, and there are some extra small line segments, so that traversing the line data, integrating the staggered lines into a line, and deleting the extra line segments, as shown in fig. 9.
S37, closed straight line data: selecting two ends of a certain straight line as a starting point and an end point, traversing the detected straight line data from the starting point to the end point, connecting the unclosed line segments to generate a line body house type sketch, and obtaining the final result shown in figure 10.
The specific process of step S37 is:
and selecting two ends of a certain straight line as a starting point and an end point, traversing the detected straight line data from the starting point, and marking the straight line data and the end point coordinates of the connecting line which is being searched currently.
If the two ends of the straight line are connected in a wired mode, no processing is conducted, if a wireless section is connected at one end of the straight line, the straight line connected with the wireless section at the other end point is found out, the distance between the two end points is the nearest, and line segment data connecting the two straight lines is added.
And when the marked coordinates return to the end point, traversing is completed, the straight line is closed, and a linear house type sketch is generated.
And S4, converting line data (size, angle and the like) of the linear house type sketch into a JSON data format, and performing deserialization extraction to obtain vertex information of wall lines in the sketch and space coordinates of wall members.
And S5, generating a three-dimensional model of the wall based on line data of the sketch and vertex data of the wall line, and combining the three-dimensional model of the wall with the wall members to generate the 3D house type model according to the space coordinates of the wall members.
The generation process of the three-dimensional wall model in the step S5 is as follows:
generating a contour line of the wall according to the line data of the sketch and the thickness of the wall; respectively generating a wall ground surface of the house, a top surface of the house, an inner wall surface of the house and an outer wall surface of the house according to the wall contour line and the vertex data of the wall line to obtain a model surface of the wall; and generating a three-dimensional model of the wall body according to the molded surface of the wall body model.
The process of generating the three-dimensional model of the wall body according to the molded surface of the wall body model comprises the following steps:
obtaining four vertexes of the wall surface according to line data of the sketch and vertex data of the wall body line; and on the vertical plane of the wall line, three non-repetitive vertexes are respectively used for anticlockwise connection, and triangular surface processing is carried out, wherein all the triangular surfaces form a three-dimensional model forming the house wall.
The process of combining the three-dimensional wall model and the wall members in the step S5 is as follows:
judging the inclusion relationship between the wall three-dimensional model and the wall member, performing segmentation processing on the wall according to the type, height and size of the wall member, hollowing out the position of the wall three-dimensional model containing the wall member, combining the wall members, and processing the positions into a left drawing of the wall member, a middle drawing of the wall member and a right drawing of the wall member.
Drawing the left part and the right part of the member wall: and combining the acquired information of the segmented wall body with the height and width of the member causing the segmentation to generate a starting drawing point of the segmented wall body, connecting the drawing points at the bottom and the top in a counterclockwise manner, and performing polygonal division to obtain the left part and the right part of the member wall body which are formed by a plurality of triangular surface sets.
Drawing the middle part of the component wall: and connecting the top boundary point of the segmented component with the top boundary point of the middle wall body and the bottom boundary point of the segmented component with the bottom boundary point of the middle wall body anticlockwise, and performing polygonal division to obtain the middle part of the component wall body formed by a plurality of triangular surface sets.
Converting the spatial coordinates and spatial dimensions of the member into vertex data resulting in a partition wall, comprising: calculating the space coordinate C of the center of the component and the space size S (x, y, z) of the component respectively according to formulas, and obtaining a top boundary point and a bottom boundary point of the component (P1-P8), wherein the calculation formulas are as follows:
P1＝P(C.x+S.x，C.y+S.y，C.z+S.z)
P2＝P(C.x+S.x，C.y+S.y，C.z-S.z)
P3＝P(C.x+S.x，C.y-S.y，C.z+S.z)
P4＝P(C.x-S.x，C.y+S.y，C.z+S.z)
P5＝P(C.x+S.x，C.y-S.y，C.z-S.z)
P6＝P(C.x-S.x，C.y+S.y，C.z-S.z)
P7＝P(C.x-S.x，C.y-S.y，C.z+S.z)
P8＝P(C.x-S.x，C.y-S.y，C.z-S.z)
in the formula, C (x, y, z) is the member center coordinate, and S (x, y, z) is the space size of the member.
And S6, perfecting various indoor measurement data according to the actually measured wall height and the actual parameters of various components, and finally generating 3D data of indoor house types.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A method for generating indoor house type 3D data by radar ranging is characterized by comprising the following steps: the method comprises the following steps:
s1, performing omnibearing laser ranging scanning on the indoor space, and scanning and collecting two-dimensional wall data of the indoor environment;
s2, generating an indoor space point cloud picture with data point location two-dimensional coordinate information through mapping software;
s3, processing the indoor space point cloud picture through algorithm calculation and image recognition to obtain an indoor house type contour map, and denoising the contour map to generate a linear house type sketch;
s4, converting line data of the line body house type sketch into a JSON data format, and performing deserialization extraction to obtain vertex information of wall lines in the sketch and space coordinates of wall components;
s5, generating a three-dimensional model of the wall based on line data of the sketch and vertex data of the wall line, and combining the three-dimensional model of the wall with each wall component according to the space coordinates of each wall component to generate a 3D house type model;
and S6, perfecting the indoor measurement data, and finally generating 3D data of the indoor house type.
2. The method of radar ranging generating indoor dwelling size 3D data as claimed in claim 1, wherein: and in the step of S2, the two-dimensional point cloud data is identified and converted through an image identification algorithm, the breakpoint or wrong details of the scanning image are corrected, and a house type plane image close to a real scene is formed.
3. The method of radar ranging generating indoor dwelling size 3D data as claimed in claim 2, wherein: step S3 specifically includes:
s31, picture preprocessing: carrying out binarization and morphological processing on the point cloud bitmap to distinguish a foreground and a background;
s32, forming a contour diagram: finding out the outline of which the area in the preprocessed image meets a certain condition according to a findContours function of opencv, and deleting redundant parts to obtain a house type main body;
s33, contour map data identification: traversing the contour map, finding out a pixel coordinate with a pixel value of 255, and obtaining a line segment endpoint coordinate;
s34, straight line approximation: traversing the identified straight line data, and combining the line segments which are connected end to end but staggered into a straight line;
s35, adjusting the straight-line end point data: traversing the straight line data, and unifying the end point data of the straight line and the end point data of the straight line connected with the end point data;
s36, secondarily integrating straight lines and deleting redundant line segments: traversing the straight line data, integrating the staggered straight lines into a straight line and deleting redundant line segments;
s37, closed straight line data: and (3) selecting two ends of a certain straight line as a starting point and an end point, traversing the detected straight line data from the starting point to the end point, and connecting the unclosed line segments to generate the line body house type sketch.
4. The method of radar ranging generating indoor dwelling size 3D data as claimed in claim 3, wherein: the specific process of step S37 is:
traversing the detected linear data from the starting point, and marking the linear data and the end point coordinates of the connecting line which is being searched currently;
if the two ends of the straight line are connected in a wired mode, no processing is carried out, if a wireless section connection condition exists at one end of the straight line, the straight line connected with the wireless section also exists at the other end point is found out, the distance between the two end points is the nearest, and line segment data connecting the two straight lines is added;
and when the marked coordinates return to the end point, traversing is completed, the straight line is closed, and a linear house type sketch is generated.
5. The method of radar ranging generating indoor dwelling size 3D data as claimed in claim 1, wherein: the generation process of the three-dimensional wall model in the step S5 is as follows:
generating a contour line of the wall according to the line data of the sketch and the thickness of the wall;
respectively generating a wall ground surface of the house, a top surface of the house, an inner wall surface of the house and an outer wall surface of the house according to the wall contour line and the vertex data of the wall line to obtain a model surface of the wall;
and generating a three-dimensional model of the wall body according to the molded surface of the wall body model.
6. The method of radar ranging generating indoor dwelling size 3D data as claimed in claim 5, wherein: the process of generating the three-dimensional model of the wall body according to the molded surface of the wall body model comprises the following steps:
obtaining four vertexes of the wall surface according to line data of the sketch and vertex data of the wall body line;
and on the vertical plane of the wall line, three non-repetitive vertexes are respectively used for anticlockwise connection, and triangular surface processing is carried out, wherein all the triangular surfaces form a three-dimensional model forming the house wall.
7. The method of radar ranging generating indoor dwelling size 3D data as claimed in claim 5, wherein: the process of combining the three-dimensional wall model and the wall members in the step S5 is as follows:
and judging the inclusion relationship between the wall three-dimensional model and the wall member, hollowing out the position of the wall three-dimensional model containing the wall member according to the type, height and size of the wall member, and merging by using the wall member.
8. The method of radar ranging generating indoor dwelling size 3D data as claimed in claim 1, wherein: the indoor space is scanned in all directions by adopting the 360-degree laser scanning range radar, and the 360-degree laser scanning range radar is subjected to tilt compensation by utilizing an algorithm in combination with a degree of freedom inertial navigation system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010176033.7A CN111308495B (en) | 2020-03-13 | 2020-03-13 | Method for generating indoor house type 3D data through radar ranging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010176033.7A CN111308495B (en) | 2020-03-13 | 2020-03-13 | Method for generating indoor house type 3D data through radar ranging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111308495A true CN111308495A (en) | 2020-06-19 |
| CN111308495B CN111308495B (en) | 2022-03-08 |
Family
ID=71156907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010176033.7A Active CN111308495B (en) | 2020-03-13 | 2020-03-13 | Method for generating indoor house type 3D data through radar ranging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111308495B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113592976A (en) * | 2021-07-27 | 2021-11-02 | 美智纵横科技有限责任公司 | Map data processing method and device, household appliance and readable storage medium |
| CN115861039A (en) * | 2022-11-21 | 2023-03-28 | 北京城市网邻信息技术有限公司 | Information display method, device, equipment and medium |
| CN117824663A (en) * | 2024-03-05 | 2024-04-05 | 南京思伽智能科技有限公司 | Robot navigation method based on hand-drawn scene graph understanding |
| CN117824663B (en) * | 2024-03-05 | 2024-05-10 | 南京思伽智能科技有限公司 | Robot navigation method based on hand-drawn scene graph understanding |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971098A (en) * | 2014-05-19 | 2014-08-06 | 北京明兰网络科技有限公司 | Method for recognizing wall in house type image and method for automatically correcting length ratio of house type image |
| CN105279787A (en) * | 2015-04-03 | 2016-01-27 | 北京明兰网络科技有限公司 | Method for generating three-dimensional (3D) building model based on photographed house type image identification |
| CN108446830A (en) * | 2018-02-13 | 2018-08-24 | 厦门知本家科技有限公司 | A kind of house type Sunlight Analysis method based on mobile device end |
| US20180284246A1 (en) * | 2017-03-31 | 2018-10-04 | Luminar Technologies, Inc. | Using Acoustic Signals to Modify Operation of a Lidar System |
| CN109828284A (en) * | 2019-03-18 | 2019-05-31 | 上海盎维信息技术有限公司 | The method and device of actual measurement actual quantities based on artificial intelligence |
| CN110490916A (en) * | 2019-04-12 | 2019-11-22 | 北京城市网邻信息技术有限公司 | Three dimensional object modeling method and equipment, image processing apparatus and medium |
-
2020
- 2020-03-13 CN CN202010176033.7A patent/CN111308495B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971098A (en) * | 2014-05-19 | 2014-08-06 | 北京明兰网络科技有限公司 | Method for recognizing wall in house type image and method for automatically correcting length ratio of house type image |
| CN105279787A (en) * | 2015-04-03 | 2016-01-27 | 北京明兰网络科技有限公司 | Method for generating three-dimensional (3D) building model based on photographed house type image identification |
| US20180284246A1 (en) * | 2017-03-31 | 2018-10-04 | Luminar Technologies, Inc. | Using Acoustic Signals to Modify Operation of a Lidar System |
| CN108446830A (en) * | 2018-02-13 | 2018-08-24 | 厦门知本家科技有限公司 | A kind of house type Sunlight Analysis method based on mobile device end |
| CN109828284A (en) * | 2019-03-18 | 2019-05-31 | 上海盎维信息技术有限公司 | The method and device of actual measurement actual quantities based on artificial intelligence |
| CN110490916A (en) * | 2019-04-12 | 2019-11-22 | 北京城市网邻信息技术有限公司 | Three dimensional object modeling method and equipment, image processing apparatus and medium |
Non-Patent Citations (4)
| Title |
|---|
| 何静 等: "移动房产测绘信息系统的APP服务研究", 《现代测绘》 * |
| 史向阳: "室内激光点云的三维场景快速重建", 《测绘地理信息》 * |
| 董景利: "徕卡RTC360三维激光扫描仪在建筑立面改造中的应用", 《测绘通报》 * |
| 马焜阳: "利用Faster R-CNN自动识别建筑平面图", 《测绘科学技术学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113592976A (en) * | 2021-07-27 | 2021-11-02 | 美智纵横科技有限责任公司 | Map data processing method and device, household appliance and readable storage medium |
| WO2023005195A1 (en) * | 2021-07-27 | 2023-02-02 | 美智纵横科技有限责任公司 | Map data processing method and apparatus, and household appliance and readable storage medium |
| CN115861039A (en) * | 2022-11-21 | 2023-03-28 | 北京城市网邻信息技术有限公司 | Information display method, device, equipment and medium |
| CN117824663A (en) * | 2024-03-05 | 2024-04-05 | 南京思伽智能科技有限公司 | Robot navigation method based on hand-drawn scene graph understanding |
| CN117824663B (en) * | 2024-03-05 | 2024-05-10 | 南京思伽智能科技有限公司 | Robot navigation method based on hand-drawn scene graph understanding |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111308495B (en) | 2022-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Motavalli | Review of reverse engineering approaches | |
| CN113436260B (en) | Mobile robot pose estimation method and system based on multi-sensor tight coupling | |
| CN109144072A (en) | A kind of intelligent robot barrier-avoiding method based on three-dimensional laser | |
| CN111308495B (en) | Method for generating indoor house type 3D data through radar ranging | |
| CN105783779B (en) | The real-time form identification of rail profile and distortion calibration method based on three layers of matching | |
| Zhao et al. | Reconstruction of textured urban 3D model by fusing ground-based laser range and CCD images | |
| CN106323286B (en) | A kind of robot coordinate system and the transform method of three-dimensional measurement coordinate system | |
| CN112446844B (en) | Point cloud feature extraction and registration fusion method | |
| CN111913169A (en) | Method, equipment and storage medium for correcting laser radar internal reference and point cloud data | |
| CN115479598A (en) | Positioning and mapping method based on multi-sensor fusion and tight coupling system | |
| Wagner et al. | Fusion of laser-scan and image data for deformation monitoring–concept and perspective | |
| CN112033385B (en) | Pier pose measuring method based on mass point cloud data | |
| Zhou et al. | Sparse point cloud generation based on turntable 2D lidar and point cloud assembly in augmented reality environment | |
| CN114897967B (en) | Material form identification method for autonomous operation of excavating equipment | |
| CN113532424A (en) | Integrated equipment for acquiring multidimensional information and cooperative measurement method | |
| Jokinen | Building 3-D city models from multiple unregistered profile maps | |
| Xie et al. | Map merging with terrain-adaptive density using mobile 3D laser scanner | |
| CN107246863A (en) | A kind of irregular bore tunnel inwall image projecting method of deploying | |
| CN105955272A (en) | Fusion method for multiple flight time sensors of service robot | |
| Zhou et al. | A novel method for reconstructing general 3D curves from stereo images | |
| Xue et al. | Research of vehicle monocular measurement system based on computer vision | |
| CN109129468B (en) | Mobile robot based on MYRIO platform | |
| CN116051629B (en) | Autonomous navigation robot-oriented high-precision visual positioning method | |
| CN112767460B (en) | Spatial fingerprint image registration element feature description and matching method | |
| CN117237557B (en) | Urban mapping data processing method based on point cloud data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |