CN112365534B - Large coal pile volume measurement method based on monocular camera three-dimensional reconstruction - Google Patents
Large coal pile volume measurement method based on monocular camera three-dimensional reconstruction Download PDFInfo
- Publication number
- CN112365534B CN112365534B CN202011263711.XA CN202011263711A CN112365534B CN 112365534 B CN112365534 B CN 112365534B CN 202011263711 A CN202011263711 A CN 202011263711A CN 112365534 B CN112365534 B CN 112365534B
- Authority
- CN
- China
- Prior art keywords
- volume
- point
- coal pile
- dimensional
- dimensional reconstruction
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/10—Geometric effects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a monocular camera three-dimensional reconstruction-based large-scale coal pile volume measurement method, which uses an unmanned aerial vehicle to carry a monocular camera, realizes autonomous positioning and navigation of the unmanned aerial vehicle, samples data of a coal pile and reconstructs the coal pile in a three-dimensional manner to calculate the volume, and arranges a two-dimensional code for coal pile scale reduction in the coal pile. Compared with the prior art, the method has the advantages that the automation of the whole operation process can be realized, more manpower and material resources are saved, the real volume of the coal pile can be obtained in a short time, the measurement precision can be ensured to meet the actual production requirement, and the like.
Description
Technical Field
The invention relates to a large coal pile volume measuring method, in particular to a large coal pile volume measuring method based on monocular camera three-dimensional reconstruction.
Background
In a thermal power plant, the volume measurement of a large coal pile is often required, and the mapping is difficult. The traditional method adopts a manual measurement mode, a large amount of manpower, material resources and time are needed to shape the coal pile, and then the volume is estimated through manual measurement. At present, some superior inventions can more accurately acquire the volume of the coal pile.
The Chinese patent publication No. CN1022441C discloses an automatic measuring device for the volume of a large coal pile by searching, which carries out sampling and distance measurement on the surface height of the large coal pile point by point, and comprises a mechanical scanning system and a photoelectric detection system, so that the volume of the large coal pile can be rapidly measured.
Chinese patent publication No. CN 101858730A discloses a method for automatically measuring the volume of a coal pile and a special device thereof, wherein a cruise trolley is used to carry a laser range finder, and the laser range finder is used to perform range finding sampling at a plurality of positions on the top of the coal pile, so as to establish a three-dimensional map of a scene of the coal pile for volume measurement.
Chinese patent publication No. CN 106875440A discloses a method and apparatus for calculating the volume of a coal pile, which performs a large amount of data sampling on the coal pile through a camera, performs three-dimensional reconstruction using image data satisfying requirements, can accurately acquire a three-dimensional model of the coal pile for volume estimation, but requires an actual coal pile dimension when estimating the volume, cannot acquire a true dimension of a reconstruction model when performing sampling reconstruction using a monocular camera, and causes a certain influence on the volume estimation of the coal pile, and can acquire a true dimension of the reconstruction model based on the three-dimensional reconstruction of a binocular camera, but calibration accuracy of the binocular camera cannot be guaranteed, which further affects measurement accuracy, and equipment price is high.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a large coal pile volume measuring method based on monocular camera three-dimensional reconstruction.
The purpose of the invention can be realized by the following technical scheme:
a method for measuring the volume of a large coal pile based on monocular camera three-dimensional reconstruction is characterized in that an unmanned aerial vehicle is used for carrying a monocular camera, autonomous positioning and navigation of the unmanned aerial vehicle are achieved, data sampling and three-dimensional reconstruction are carried out on the coal pile to calculate the volume, and meanwhile two-dimensional codes for coal pile scale reduction are arranged in the coal pile.
Preferably, the method comprises in particular the steps of:
step 1) data collection;
step 2), obtaining an effective 3D point set;
step 3), space transformation is carried out, and all three-dimensional point clouds are projected onto a two-dimensional plane to obtain a 2D point set;
step 4), obtaining a Delaunay triangulation network, and triangulating the 2D point set to obtain the Delaunay triangulation network;
and 5) converting the solution of the point cloud volume after three-dimensional reconstruction into the solution of a plurality of triangular prism integrals through the steps, and eliminating the triangular prism volume values of which partial deviations exceed a set threshold value through an algorithm.
Preferably, the step 1) data collection specifically includes:
and continuously acquiring a scene by adopting a monocular camera, taking the acquired image as input, and obtaining a point cloud of the scene through three-dimensional reconstruction.
Preferably, the step 2) of obtaining the effective 3D point set specifically includes:
in the process of generating the point cloud, the contents of partial non-interesting areas and a plurality of discrete error noise points are added into the point cloud result, and the point cloud result is removed by the following method:
201 Aiming at the non-interested region, directly cutting and removing the non-interested region through a three-dimensional space plane equation;
202 For random error noise points, culling by an outlier detection algorithm.
Preferably, 201) is specifically:
in the point cloud after three-dimensional reconstruction, only a 3D point set in an interested region needs to be collected, a space tangent plane equation is solved through the common constraint of the solved horizontal plane equation and the known three-dimensional point coordinates in the scene, the scene is cut, and therefore the non-interested region is directly removed.
Preferably, the outlier detection algorithm in 202) is specifically:
for each point, calculate its average distance to all nearby points, define the points whose average distance is outside the standard range as outliers and remove from the data.
Preferably, the spatial transformation in step 3) is specifically:
301 Obtaining normal vectors of the xy plane equation in the point cloud horizontal plane and the reference coordinate system, P (A, B, C) and Q (0,0,1);
302 All 3D point sets O (x) 0 ,y 0 ,z 0 ) Projecting the horizontal plane according to the following formula to obtain a new 3D point set P (x) p ,y p ,z p )
Wherein D is a fourth parameter of the horizontal plane equation;
simultaneously, the distance d between each three-dimensional space point and the equation of the horizontal plane is calculated according to the following formula
303 Calculate the rotation angle: the rotation angle θ between the two vectors is calculated according to the following equation
Wherein P and Q are two three-dimensional vectors;
304 Calculate the rotation axis: when the rotation angle is calculated, the plane where the angle is located is a plane formed by P and Q, the rotation axis must be perpendicular to the plane, and the vector before rotation is assumed to be a (a) 1 ,a 2 ,a 3 ) After rotation the vector is b (b) 1 ,b 2 ,b 3 ) The rotation axis c (c) is defined by the cross product 1 ,c 2 ,c 3 ) Is composed of
305 The rotation angle, the expression of the rotation axis, is converted into a rotation matrix R according to the rodrieger rotation formula;
306 Set of 3D points P (x) p ,y p ,z p ) And right multiplying the rotation matrix R to obtain a series of 3D point sets on the same plane, and extracting x and y values of all the 3D points to form a 2D point set p (x, y).
Preferably, the step 4) of obtaining the Delaunay triangulation network specifically includes:
401 Constructing a super triangle which contains all scattered points and putting the super triangle into a triangle linked list;
402 Sequentially inserting scattered points in the point set, finding out a triangle (called as an influence triangle of the point) of which the circumscribed circle comprises the insertion point from the triangle linked list, deleting the common edge of the influence triangle, and connecting the insertion point with all vertexes of the influence triangle, thereby completing the insertion of one point in the Delaunay triangle linked list;
403 According to the optimization criterion, optimizing the local newly formed triangles, and putting the formed triangles into a Delaunay triangle linked list;
404 ) loop through 402) until all the scatter points have been inserted.
Preferably, the set of triangles and the distance corresponding to each vertex in the triangles are obtained through the above process, the average value of the distances of the three vertices is taken as the height of the triangular prism, and the area of each triangle is calculated according to the following formula, so that the volume of all the triangular prisms can be obtained:
preferably, the triangular prism volume value with partial deviation exceeding the set threshold is removed by an algorithm and a box diagram method, specifically:
the 5 characteristic data values in the data are required to be solved, including the lower quartile Q 1 Upper quartile Q 3 Four-bit spacing IQR = Q 3 -Q 1 And an upper limit Q 3 +1.5IQR and lower limit Q 1 1.5IQR, eliminating the content outside the upper and lower limits, finally combining the estimated scale and the volume of all effective triangular prisms according to the following formula to estimate the actual volume value of the interested area in the object,
wherein K is a scale factor recovered in the point cloud processing process, d j Is the length of the side edge of a triangular prism, here
The volume is obtained by taking the average length of the side edges of the triangular prism as the height.
Compared with the prior art, the unmanned aerial vehicle carries the monocular camera, autonomous positioning and navigation of the unmanned aerial vehicle are achieved, data sampling and three-dimensional reconstruction are carried out on the coal pile to calculate the volume, a small number of two-dimensional codes need to be arranged in the coal pile, and scale reduction of the coal pile is facilitated. Through actual scene measurement, the invention can realize the automation of the whole operation process, save more manpower and material resources, can obtain the real volume of the coal pile in a short time, and can ensure that the measurement precision meets the actual production requirement.
Drawings
FIG. 1 is a schematic diagram of a three-dimensional reconstruction point cloud result;
FIG. 2 is a schematic diagram of a three-dimensional reconstructed region of interest;
FIG. 3 is a diagram illustrating a point cloud after statistical filtering;
FIG. 4 is a schematic diagram of a Delaunay triangulation network;
FIG. 5 is a box diagram illustration;
FIG. 6 is a flow chart of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
In order to solve the problem of volume measurement of the coal pile after three-dimensional reconstruction, the invention provides a set of flow combining computer vision and geometric calculation, and the actual volume of the coal pile can be solved on the basis after the horizontal plane and the proportional scale of the point cloud after three-dimensional reconstruction are obtained.
The innovation points of the invention comprise:
1) When the volume of the coal pile is calculated, the calculation of the point cloud volume is converted into the integral of a plurality of triangular prism volumes
2) In the calculation of the coal pile volume, outliers are presented by line graphs.
The technical scheme adopted by the invention for solving the technical problem is as follows:
firstly, projecting all point cloud results on a horizontal plane, and rejecting abnormal points according to the actual space constraint of a scene and a filtering method.
Further, three-dimensional space points are converted into a 2D point set on a horizontal plane through space transformation.
Further, solving a Delaunay triangulation network for all point sets, and calculating the area and the corresponding horizontal height of each triangle to obtain the volume of the triangular prism
And finally, removing abnormal triangular prisms, and summing the integrals of all effective triangular prisms to obtain the total volume.
As shown in fig. 6, the method for measuring the volume of the large coal pile based on the monocular camera three-dimensional reconstruction of the present invention specifically comprises the following steps:
1. data collection: the scene can be continuously acquired through a monocular camera, the acquired images are used as input, the point cloud of the scene is obtained through three-dimensional reconstruction, and the point cloud result is shown in figure 1.
2. Obtaining a valid 3D point set: the contents of partial non-interesting regions and some discrete error noise points are added to the point cloud result in the process of generating the point cloud. Aiming at the two situations, the invention respectively provides the following corresponding solutions:
1) Aiming at the non-interested region, the non-interested region is directly cut and removed through a three-dimensional space plane equation;
2) Aiming at random error noise points, the random error noise points are removed through an outlier detection algorithm.
For the scheme 1), in the point cloud after the three-dimensional reconstruction, only a 3D point set in the region of interest needs to be collected, as shown in fig. 2, only the region in the red block diagram is the region of interest, and the scene can be cut by solving a space tangent plane equation through the joint constraint of the solved horizontal plane equation and the known three-dimensional point coordinates in the scene.
For scheme 2), the invention uses a statistical filter to perform a statistical analysis on the neighborhood of each point and prunes off some points that do not meet the standard, and the specific method is to calculate the distance distribution from the point to the adjacent point in the input data, and calculate the average distance from each point to all the adjacent points (assuming that the obtained result is a gaussian distribution, and the shape is determined by the mean and standard deviation), then the points whose average distance is outside the standard range can be defined as outliers and removed from the data. After filtering the discrete points in the point cloud by using statistical filtering, as shown in fig. 3.
3. Spatial transformation: through the steps, an effective 3D point set can be obtained, all three-dimensional point clouds need to be projected to a two-dimensional plane in the subsection to obtain a 2D point set, and the simplified steps are as follows:
1) Obtaining the normal vectors of the xy plane equation in the point cloud horizontal plane and the reference coordinate system, P (A, B, C) and Q (0,0,1)
2) Set all 3D points O (x) 0 ,y 0 ,z 0 ) A new set of 3D points P (x) is obtained by projecting onto the horizontal plane according to the following formula p ,y p ,z p )
Meanwhile, the distance from each three-dimensional space point to the equation of the horizontal plane can be calculated according to the following formula
3) Calculating a rotation angle: the rotation angle between the two vectors is calculated as follows
4) Calculating a rotating shaft: when the rotation angle is calculated, it is known that the plane in which the angle is located is a plane formed by P and Q, and the rotation axis must be perpendicular to the plane. Assume that the pre-rotation vector is a (a) 1 ,a 2 ,a 3 ) After rotation the vector is b (b) 1 ,b 2 ,b 3 ) The rotation axis c (c) is defined by the cross product 1 ,c 2 ,c 3 ) Is composed of
5) Converting the rotation angle, the expression of the rotation axis, into a rotation matrix R according to the Rodrigue rotation formula
6) Set P (x) of 3D points p ,y p ,z p ) Multiplying the rotation matrix R to the right can obtain a series of 3D point sets on the same plane (all converted point z values are the same), and extracting the x and y values of all the 3D points to form a 2D point set p (x, y).
The 2D point sets converted from the 3D point sets on the same plane and the distance value D corresponding to each 2D point set can be obtained through the steps.
4. Acquiring a Delaunay triangulation network: triangulating the set of 2D points yields a Delaunay triangulation, which is a set of connected but non-overlapping triangles whose circumcircles do not contain any other point of the face region, as shown in fig. 4. The general steps for obtaining the Delaunay triangular mesh are as follows:
1) Constructing a super triangle, including all scatter points, and putting the super triangle into a triangle linked list;
2) Inserting scattered points in the point set in sequence, finding out a triangle (called as an influence triangle of the point) of which the circumscribed circle comprises an insertion point from the triangle linked list, deleting a common edge of the influence triangle, and connecting the insertion point with all vertexes of the influence triangle, thereby completing the insertion of one point in the Delaunay triangle linked list;
3) Optimizing the local newly formed triangles according to an optimization criterion, and putting the formed triangles into a Delaunay triangle linked list;
4) And (5) circularly executing the step 2 until all scatter points are inserted.
Because the Delaunay subdivision has the characteristics of being closest (a triangle is formed by the nearest three points and all line segments do not intersect) and regional (a vertex is newly added, deleted and moved, only the adjacent triangle is influenced), the method is adopted for fitting the plane formed by the point set. The set of triangles and the distance corresponding to each vertex in the triangles can be obtained through the process, the average value of the distances of the three vertices is taken as the height of the triangular prism, and the area of each triangle is calculated according to the following formula, so that the volume of all the triangular prisms can be obtained.
5. Integrating triangular prisms: through the steps, the solution of the point cloud volume after three-dimensional reconstruction can be converted into the solution of the integrals of the triangular prisms, and the volume values of all the triangular prisms are distributed in a certain interval (not completely obeying positive and negative distribution), so that the partial triangular prism volume values with large deviation are removed through an algorithm. The invention adopts a box diagram method to deal with the problem, the box diagram is not influenced by abnormal values, the discrete distribution situation of the data can be accurately and stably described, and the cleaning of the data is also facilitated. The boxplot shown in FIG. 5 mainly requires solving 5 characteristic data values in the data, including the lower quartile Q 1 Upper quartile Q 3 Four-bit spacing IQR = Q 3 -Q 1 And an upper limit Q 3 +1.5IQR and lower limit Q 1 And (4) 1.5IQR, eliminating the contents outside the upper limit and the lower limit, and finally combining the estimated scale and the volume of all effective triangular prisms according to the following formula to estimate the actual volume value of the region of interest in the object.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the 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 measuring the volume of a large coal pile based on monocular camera three-dimensional reconstruction is characterized in that an unmanned aerial vehicle is used for carrying a monocular camera, autonomous positioning and navigation of the unmanned aerial vehicle are achieved, data sampling and three-dimensional reconstruction are carried out on the coal pile to calculate the volume, and meanwhile two-dimensional codes for coal pile scale reduction are arranged in the coal pile;
the method specifically comprises the following steps:
step 1) data collection;
step 2), obtaining an effective 3D point set;
step 3), performing spatial transformation, namely projecting all three-dimensional point clouds onto a two-dimensional plane to obtain a 2D point set;
step 4), obtaining a Delaunay triangulation network, and triangulating the 2D point set to obtain the Delaunay triangulation network;
step 5) converting the solution of the point cloud volume after three-dimensional reconstruction into the solution of a plurality of triangular prism integrals, and eliminating the triangular prism volume values with partial deviation exceeding a set threshold value through an algorithm;
the spatial transformation in the step 3) is specifically as follows:
301 Obtaining normal vectors of xy plane equations in the horizontal plane of the point cloud and the reference coordinate system, P (A, B, C) and Q (0,0,1);
302 All 3D point sets O (x) 0 ,y 0 ,z 0 ) Projecting the horizontal plane according to the following formula to obtain a new 3D point set P (x) p ,y p ,z p )
Wherein D is a fourth parameter of the horizontal plane equation;
simultaneously, the distance d between each three-dimensional space point and the equation of the horizontal plane is calculated according to the following formula
303 Calculate the rotation angle: the rotation angle θ between the two vectors is calculated according to the following equation
Wherein P and Q are two three-dimensional vectors;
304 Calculate the rotation axis: when the rotation angle is calculated, the plane where the angle is located is a plane composed of P and Q, the rotation axis must be perpendicular to the plane, and the vector a (a) before rotation is assumed to be 1 ,a 2 ,a 3 ) After rotation the vector is b (b) 1 ,b 2 ,b 3 ) The rotation axis c (c) is defined by the cross product 1 ,c 2 ,c 3 ) Is composed of
305 The rotation angle, the expression of the rotation axis, is converted into a rotation matrix R according to the rodrieger rotation formula;
306 Set of 3D points P (x) p ,y p ,z p ) And multiplying the rotation matrix R right to obtain a series of 3D point sets on the same plane, and extracting x and y values of all 3D points to form a 2D point set p (x, y).
2. The method for measuring the volume of the large coal pile based on the monocular camera three-dimensional reconstruction as recited in claim 1, wherein the step 1) data collection specifically comprises:
and continuously acquiring a scene by adopting a monocular camera, taking the acquired image as input, and obtaining a point cloud of the scene through three-dimensional reconstruction.
3. The method for measuring the volume of the large coal pile based on the monocular camera three-dimensional reconstruction as recited in claim 1, wherein the step 2) of obtaining the effective 3D point set specifically comprises:
in the process of generating the point cloud, the contents of partial non-interesting areas and some discrete error noise points are added into the point cloud result, and the point cloud result is removed by the following method:
201 Aiming at the non-interested region, directly cutting and removing the non-interested region through a three-dimensional space plane equation;
202 For random error noise points, culling by an outlier detection algorithm.
4. The method for measuring the volume of the large coal pile based on the monocular camera three-dimensional reconstruction according to claim 3, wherein 201) specifically comprises:
in the point cloud after three-dimensional reconstruction, only a 3D point set in an interested region needs to be collected, a space tangent plane equation is solved through the joint constraint of the solved horizontal plane equation and the known three-dimensional point coordinates in the scene to cut the scene, and therefore the non-interested region is directly removed.
5. The method for measuring the volume of the large coal pile based on the monocular camera three-dimensional reconstruction as recited in claim 3, wherein the outlier detection algorithm in 202) is specifically:
for each point, calculate its average distance to all nearby points, define the points whose average distance is outside the standard range as outliers and remove them from the data.
6. The method for measuring the volume of the large coal pile based on the monocular camera three-dimensional reconstruction as recited in claim 1, wherein the step 4) of obtaining the Delaunay triangulation network specifically comprises:
401 Constructing a super triangle, containing all scatter points, and putting into a triangle linked list;
402 Sequentially inserting scattered points in the point set, finding out a triangle (called as an influence triangle of the point) of which the circumscribed circle comprises the insertion point from the triangle linked list, deleting the common edge of the influence triangle, and connecting the insertion point with all vertexes of the influence triangle, thereby completing the insertion of one point in the Delaunay triangle linked list;
403 According to the optimization criterion, optimizing the local newly formed triangles, and putting the formed triangles into a Delaunay triangle linked list;
404 ) loop through 402) until all the scatter points have been inserted.
7. The method for measuring the volume of the large coal pile based on the monocular camera three-dimensional reconstruction as recited in claim 6, wherein the set of triangles and the distance corresponding to each vertex in the triangle are obtained through the above process, the average value of the distances of the three vertices is taken as the height of the triangular prism, and the area of each triangle is calculated according to the following formula, so that the volume of all the triangular prisms can be obtained:
8. the method for measuring the volume of the large coal pile based on the monocular camera three-dimensional reconstruction as recited in claim 7, wherein the triangular prism volume values with partial deviation exceeding the set threshold are removed by an algorithm and a box chart method is adopted, specifically:
the 5 characteristic data values in the data are required to be solved, including the lower quartile Q 1 Upper quartile Q 3 Four-bit spacing IQR = Q 3 -Q 1 And an upper limit Q 3 +1.5IQR and lower limit Q 1 1.5IQR, eliminating the content outside the upper and lower limits, finally combining the estimated scale and the volume of all effective triangular prisms according to the following formula to estimate the actual volume value of the interested area in the object,
wherein K is a scale factor recovered in the point cloud processing process, d j Is the length of the side edge of a triangular prism, here
d j The volume is obtained by taking the average length of the side edges of the triangular prism as the height.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011263711.XA CN112365534B (en) | 2020-11-12 | 2020-11-12 | Large coal pile volume measurement method based on monocular camera three-dimensional reconstruction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011263711.XA CN112365534B (en) | 2020-11-12 | 2020-11-12 | Large coal pile volume measurement method based on monocular camera three-dimensional reconstruction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112365534A CN112365534A (en) | 2021-02-12 |
| CN112365534B true CN112365534B (en) | 2023-02-03 |
Family
ID=74514622
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011263711.XA Active CN112365534B (en) | 2020-11-12 | 2020-11-12 | Large coal pile volume measurement method based on monocular camera three-dimensional reconstruction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112365534B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114111567A (en) * | 2021-09-26 | 2022-03-01 | 华能国际电力股份有限公司大连电厂 | Method and device for measuring coal pile for raw coal bunker |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1653202A1 (en) * | 2004-10-11 | 2006-05-03 | Robert Schmidt | Method and device for measurement of a volume flow of a belt conveyor |
| CN104778720A (en) * | 2015-05-07 | 2015-07-15 | 东南大学 | Rapid volume measurement method based on spatial invariant feature |
| CN109870106A (en) * | 2019-02-14 | 2019-06-11 | 南京邮电大学 | A kind of building volume measurement method based on unmanned plane picture |
| CN111429504A (en) * | 2020-03-02 | 2020-07-17 | 武汉大学 | Automatic material pile extraction and volume measurement method and system based on three-dimensional point cloud |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777604B (en) * | 2016-12-02 | 2020-04-21 | 重庆市勘测院 | Circular tube tee joint construction method |
| CN109389635A (en) * | 2018-09-11 | 2019-02-26 | 常州大学 | A kind of coal yard excavation amount calculation method based on unmanned plane image sequence |
| CN110893617B (en) * | 2018-09-13 | 2021-09-17 | 深圳市优必选科技有限公司 | Obstacle detection method and device and storage device |
| CN109341626B (en) * | 2018-10-24 | 2020-11-06 | 中国铁道科学研究院集团有限公司标准计量研究所 | Straightness calculation method, and method for calculating difference between maximum diameter and minimum diameter of cross section |
-
2020
- 2020-11-12 CN CN202011263711.XA patent/CN112365534B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1653202A1 (en) * | 2004-10-11 | 2006-05-03 | Robert Schmidt | Method and device for measurement of a volume flow of a belt conveyor |
| CN104778720A (en) * | 2015-05-07 | 2015-07-15 | 东南大学 | Rapid volume measurement method based on spatial invariant feature |
| CN109870106A (en) * | 2019-02-14 | 2019-06-11 | 南京邮电大学 | A kind of building volume measurement method based on unmanned plane picture |
| CN111429504A (en) * | 2020-03-02 | 2020-07-17 | 武汉大学 | Automatic material pile extraction and volume measurement method and system based on three-dimensional point cloud |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112365534A (en) | 2021-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110717983B (en) | Building elevation three-dimensional reconstruction method based on knapsack type three-dimensional laser point cloud data | |
| CN110340891B (en) | Mechanical arm positioning and grabbing system and method based on point cloud template matching technology | |
| Tóvári et al. | Segmentation based robust interpolation-a new approach to laser data filtering | |
| CN109900338B (en) | Method and device for measuring volume of pavement pit | |
| CN112595258A (en) | Ground object contour extraction method based on ground laser point cloud | |
| CN107481274B (en) | Robust reconstruction method of three-dimensional crop point cloud | |
| CN111553292B (en) | Rock mass structural plane identification and occurrence classification method based on point cloud data | |
| CN113791400B (en) | Stair parameter autonomous detection method based on laser radar | |
| CN104809759A (en) | Large-area unstructured three-dimensional scene modeling method based on small unmanned helicopter | |
| CN109816664A (en) | A kind of three-dimensional point cloud dividing method and device | |
| dos Santos et al. | Extraction of building roof boundaries from LiDAR data using an adaptive alpha-shape algorithm | |
| CN112233249A (en) | B spline surface fitting method and device based on dense point cloud | |
| CN110794413A (en) | Method and system for detecting power line of point cloud data of laser radar segmented by linear voxels | |
| CN109919955A (en) | The tunnel axis of ground formula laser radar point cloud extracts and dividing method | |
| CN112687005A (en) | Coal pile volume measurement method based on three-dimensional reconstruction | |
| CN116152306A (en) | Method, device, apparatus and medium for determining masonry quality | |
| CN107679458A (en) | The extracting method of roadmarking in a kind of road color laser point cloud based on K Means | |
| CN113763529B (en) | Substation modeling method based on three-dimensional scanning | |
| WO2016207669A2 (en) | A method of generating a three dimensional representation of an environment or system | |
| CN112365534B (en) | Large coal pile volume measurement method based on monocular camera three-dimensional reconstruction | |
| CN112687010B (en) | Digital metering method of end frame drilling jig | |
| CN117036944B (en) | Tree carbon sink amount calculating method and system based on point cloud data and image recognition | |
| CN112161568A (en) | Large coal pile volume measuring method based on multi-view common camera | |
| CN112505723B (en) | Three-dimensional map reconstruction method based on navigation point selection | |
| Zhang et al. | Building extraction from high-resolution remote sensing images based on GrabCut with automatic selection of foreground and background samples |
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 |