CN112116549A - Method and device for evaluating point cloud map precision - Google Patents
Method and device for evaluating point cloud map precision Download PDFInfo
- Publication number
- CN112116549A CN112116549A CN201910476434.1A CN201910476434A CN112116549A CN 112116549 A CN112116549 A CN 112116549A CN 201910476434 A CN201910476434 A CN 201910476434A CN 112116549 A CN112116549 A CN 112116549A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- point
- characteristic
- feature
- real
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/337—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving reference images or patches
-
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Abstract
The invention discloses a method and a device for evaluating point cloud map precision, and relates to the technical field of computers. One embodiment of the method comprises: s101, selecting characteristic ground objects on a point cloud map; s102, obtaining coordinates of feature points of the feature ground objects in the real world to generate a feature point coordinate graph; s103, selecting at least two real feature points on the feature point coordinate graph, and determining point cloud feature points corresponding to the at least two real feature points on the point cloud map; s104, calculating the real distance between the selected real feature points on the feature point coordinate graph, and calculating the point cloud distance between the selected point cloud feature points on the point cloud map; and S105, evaluating the precision of the point cloud map according to the distance difference between the real distance and the point cloud distance. The embodiment reduces the manpower and time required for measuring the characteristic edge line, and improves the reliability of the point cloud map precision.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for evaluating point cloud map precision.
Background
In recent years, with the development of technologies such as robots, drones, and autopilot, the SLAM technology has received more and more attention. Slam (simultaneous Localization and mapping), i.e., simultaneous Localization and mapping, refers to a process of fusing observation data based on Localization. The result of the SLAM after fusing the data is a point cloud map with a free space rectangular coordinate system. Unlike the traditional point cloud map constructed by using a GPS, an inertial navigation system, and the like, the SLAM point cloud map is unconstrained and transformable, so that the accuracy of the point cloud map cannot be evaluated directly through the coordinates of a single feature point on the point cloud map like the traditional point cloud map.
The currently common method for evaluating the precision of the SLAM point cloud map is a length direct comparison method: directly measuring the length of the characteristic sideline of the characteristic ground objects such as a flower bed sideline, a deceleration strip, a ground marking, a tree pit and the like in the real world through a steel ruler, a meter ruler, a laser range finder and the like, namely the length of the geometric sideline of the characteristic ground objects which can be identified by naked eyes; and then comparing the measured length of the characteristic edge line with the length of the corresponding characteristic edge line on the SLAM point cloud map, and calculating a difference value so as to obtain the precision of the point cloud map.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art: when the characteristic edge line of the characteristic ground object is measured outdoors, at least two persons are needed at the same time, and only one sample can be obtained when the characteristic edge line is measured once, so that a great deal of time and labor are needed when a large number of samples are needed; because the length of characteristic ground objects such as flower beds, tree pits, ground marked lines and the like is within 20 meters, and the length of a measured sample is within 20 meters, the precision of the SLAM point cloud map of a larger scene cannot be evaluated; in addition, a plurality of feature edges of the directly measured feature ground object are independent of each other and lack of relevance, so that when the point cloud map has distortion, deformation and the like, the accuracy of the point cloud map cannot be well evaluated.
Disclosure of Invention
In view of this, the present invention provides a method and an apparatus for evaluating the accuracy of a point cloud map, which can efficiently obtain a large number of samples for evaluating the accuracy of the point cloud map, can evaluate point cloud maps of scenes of various scales, and can truly reflect the accuracy of an SLAM point cloud map when the point cloud map is distorted or deformed.
To achieve the above object, according to a first aspect of the present invention, there is provided a method for evaluating a point cloud map accuracy. The method comprises the following steps: selecting characteristic ground objects on the point cloud map; acquiring coordinates of characteristic points of the characteristic ground objects in the real world to generate a characteristic point coordinate graph; selecting at least two real feature points on the feature point coordinate graph, and determining point cloud feature points corresponding to the at least two real feature points on the point cloud map; calculating the real distance between the selected real feature points on the feature point coordinate graph, and calculating the point cloud distance between the selected point cloud feature points on the point cloud map so as to determine the distance difference between the real distance and the point cloud distance; and evaluating the precision of the point cloud map according to the distance difference between the real distance and the point cloud distance.
Optionally, obtaining coordinates of feature points of the feature ground objects in the real world by a real-time dynamic difference method to form a feature point coordinate graph;
optionally, the method further comprises: selecting a first point cloud characteristic point and a second point cloud characteristic point on the point cloud map, and determining a first real characteristic point and a second real characteristic point corresponding to the first point cloud characteristic point and the second point cloud characteristic point on the characteristic point coordinate map; translating the point cloud map to enable the first point cloud characteristic point to be overlapped with the first real characteristic point; rotating the point cloud map by taking the first point cloud feature point as a reference point to enable the second point cloud feature point to be close to the second real feature point; and determining other point cloud characteristic points corresponding to other real characteristic points on the point cloud map based on a distance nearest principle.
Optionally, the first point cloud feature point and the second point cloud feature point are two feature points with the farthest distance on the point cloud map; and when a plurality of pairs of point cloud characteristic points with the farthest distance exist or a plurality of characteristic lines with the point cloud characteristic points as end points exist, selecting the end points of the characteristic lines with the closest distance to the middle position of the point cloud map as the first point cloud characteristic points and the second point cloud characteristic points.
Optionally, determining the number, the position and the distance of the at least two feature points selected on the feature point coordinate graph according to the characteristics of the selected feature; the characteristics of the characteristic ground features comprise: the number of the characteristic ground features, the shapes of the characteristic ground features and the sizes of the characteristic ground features.
Optionally, the accuracy of the point cloud map is evaluated according to a variance, a standard deviation or a maximum value of a distance difference value between the real distance and the point cloud distance.
To achieve the above object, according to a second aspect of the present invention, there is provided an apparatus for evaluating point cloud map accuracy, comprising: the system comprises a ground object selection module, a coordinate graph generation module, a characteristic point selection module and a distance calculation module; the ground object selection module is used for selecting characteristic ground objects on a point cloud map; the coordinate graph generating module is used for acquiring the coordinates of the characteristic points of the characteristic ground features in the real world so as to generate a characteristic point coordinate graph; the characteristic point selection module is used for selecting at least two real characteristic points on the characteristic point coordinate graph and determining point cloud characteristic points corresponding to the at least two real characteristic points on the point cloud map; the distance calculation module is used for calculating the real distance between the selected real feature points on the feature point coordinate map, calculating the point cloud distance between the selected point cloud feature points on the point cloud map and determining the distance difference between the real distance and the point cloud distance; and evaluating the precision of the point cloud map according to the distance difference between the real distance and the point cloud distance.
Optionally, the feature point selecting module is further configured to: selecting a first point cloud characteristic point and a second point cloud characteristic point on the point cloud map, and determining a first real characteristic point and a second real characteristic point corresponding to the first point cloud characteristic point and the second point cloud characteristic point on the characteristic point coordinate map; translating the point cloud map to enable the first point cloud characteristic point to be overlapped with the first real characteristic point; rotating the point cloud map by taking the first point cloud feature point as a reference point to enable the second point cloud feature point to be close to the second real feature point; and determining other point cloud characteristic points corresponding to other real characteristic points on the point cloud map based on a distance nearest principle.
To achieve the above object, according to a third aspect of the present invention, there is provided a server for evaluating a point cloud map accuracy, comprising: one or more processors; a storage device to store one or more programs that, when executed by the one or more processors, cause the one or more processors to implement any of the methods for evaluating point cloud map accuracy as described above.
In order to achieve the above object, according to a fourth aspect of the present invention, there is provided a computer-readable medium having stored thereon a computer program which, when executed by a processor, implements any one of the methods for evaluating point cloud map accuracy as described above.
The invention has the following advantages or beneficial effects: because the distance between the characteristic points on the characteristic point coordinate graph is adopted to replace the actual measured length of the characteristic edge line in the prior art to be compared with the distance between the corresponding characteristic points on the point cloud map, the technical problems that a large amount of manpower and material resources are required to be invested to obtain a large amount of characteristic edge line lengths and the obtained characteristic edge line lengths are within 20 meters in the prior art are solved, the efficiency of evaluating the precision of the point cloud map is greatly improved, and the scale of the scene of the point cloud map which can be evaluated is expanded; in addition, the calculated distance between the feature points not only comprises the length corresponding to the feature edge line of the feature ground object, but also comprises the length of a non-feature edge line or the length of a virtual feature edge line, so that when the point cloud map has distortion, deformation and the like, the length of the virtual feature edge line can well reflect relative errors of the point cloud map caused by the distortion, the deformation and the like, and the accuracy of the precision of the estimated point cloud map is further improved to a certain extent.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of a main flow of a method for evaluating point cloud map accuracy according to an embodiment of the invention;
FIG. 2a is a schematic diagram of a feature edge of a feature according to an embodiment of the present invention;
FIG. 2b is a schematic illustration of feature points according to an embodiment of the invention;
FIG. 2c is a schematic diagram of a feature edge line formed by selected point cloud feature points according to an embodiment of the present invention
FIG. 2d is a schematic diagram of a virtual feature edge line formed by selected point cloud feature points according to an embodiment of the invention
FIG. 2e is a schematic diagram of a point cloud map with distortion according to an embodiment of the invention;
FIG. 3 is a schematic diagram of a main flow of a method for rough registration of a point cloud map and a feature point coordinate map according to an embodiment of the invention;
FIG. 4a is a schematic diagram of a point cloud map and a feature point coordinate graph according to an embodiment of the present invention
FIG. 4b is a schematic diagram of the translated point cloud map and the feature point coordinate graph according to the embodiment of the invention
FIG. 4c is a schematic diagram of a rotated point cloud map and a feature point coordinate graph according to an embodiment of the invention
FIG. 4d is a schematic diagram of another rotated point cloud map and a feature point coordinate graph according to an embodiment of the invention
FIG. 5 is a schematic diagram of the main modules of an apparatus for evaluating the accuracy of a point cloud map according to an embodiment of the present invention;
FIG. 6 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 7 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Referring to fig. 1, an embodiment of the present invention provides a method for evaluating accuracy of a point cloud map, as shown in fig. 1, which may specifically include the following steps:
and step S101, selecting characteristic ground features on the point cloud map.
There are various features in the real world, such as roads, buildings, blocks, bridges, etc. Point cloud maps can be used to reflect the real world, but different surface features appear differently in point cloud maps: some ground objects are fuzzy, the boundaries are not clear, or the boundaries are clear but characteristic points cannot be determined, such as a round well cover; some ground objects are clear, the characteristic points are obvious and easy to identify, so that the ground objects are called as characteristic ground objects, such as speed bumps, ground marked lines, tree pits, flower beds and the like. Therefore, for the convenience of subsequent identification and measurement, the characteristic feature with obvious characteristic points is selected on the point cloud map, and then the characteristic feature is used for obtaining the corresponding characteristic feature in the real world.
And step S102, acquiring coordinates of the characteristic points of the characteristic ground features in the real world to generate a characteristic point coordinate graph.
The characteristic sidelines refer to geometrical shape sidelines which can be recognized by naked eyes of characteristic ground objects such as speed bumps, ground marked lines, tree pits, flower beds and the like. Specifically, referring to fig. 2a, the line segments marked as 1, 2, 3, 4, and 5 shown in the figure are characteristic edge lines, where the line segment 4 is a characteristic edge line of the flower bed, and the length of the line segment is the length of the corresponding characteristic edge line.
In order to evaluate the accuracy of the point cloud map, the length of the feature edge lines of the feature features in the point cloud map or the distance between the feature points needs to be obtained, and the length of the feature edge lines of the feature features in the point cloud map or the distance between the feature points needs to be compared with the real length of the feature edge lines of the corresponding feature features in the real world or the distance between the feature points. Therefore, it is necessary to locate or measure the end point of the feature in the real world or the real position or relative position of the feature point to obtain the coordinates of the feature point, and further form a feature point coordinate graph, so that the feature point or the feature in the feature point coordinate graph has a corresponding feature point or feature on the point cloud map. The term "correspondence" refers to different expressions of feature points of the same feature or the same point of the same feature on a point cloud map and a feature point coordinate map, and if the feature points are described by using the same arrow top as the feature points, the feature points are marked as point cloud feature points a on the point cloud map and as real feature points a 'on the feature point coordinate map, the point cloud feature points a correspond to the real feature points a'.
In a possible implementation manner, the coordinates of the characteristic points of the characteristic feature in the real world are obtained through a real-time dynamic difference method, so as to form a characteristic point coordinate graph. The Real-time kinematic difference (RTK) is a Real-time kinematic positioning technique based on carrier phase observation, is a commonly used GPS measurement method, and can obtain centimeter-level positioning accuracy outdoors in Real time. The working mode of the real-time dynamic difference method is that a reference station is erected on a known point, a receiver sends an observed value and coordinate information of the reference station to a rover receiver by means of a radio station, the rover receiver receives data from the reference station through the radio station or a data chain, meanwhile, GPS observation data are collected, a carrier phase differential observation equation is formed in the system, a Kalman filtering technology is adopted to obtain three-dimensional coordinates of a point to be measured through real-time processing, and the precision can reach the centimeter level. It can be understood that the three-dimensional coordinates with the measurement points obtained by the real-time dynamic difference method in this embodiment are absolute real geographic coordinates of the points to be measured, that is, longitude data, latitude data, and the like are included.
Step S103, selecting at least two real feature points on the feature point coordinate graph, and determining point cloud feature points corresponding to the at least two real feature points on the point cloud map.
Since one or more characteristic features exist in each area and each characteristic feature has a plurality of measurable points in the real world or on a point cloud map reflecting the real world, it is not desirable to measure all the characteristic points of all the characteristic features due to the limitations of time, effort, etc. in the measurement. Therefore, it is necessary to make certain measurement rules for facies, including the number of selected feature points with measurement, the intervals between the feature points, the positions of the feature points, and the like.
In a possible implementation mode, the number, the position and the distance of the at least two feature points selected on the feature point coordinate graph are determined according to the characteristics of the selected feature ground objects; the characteristics of the characteristic ground features comprise: the number of the characteristic ground features, the shapes of the characteristic ground features and the sizes of the characteristic ground features.
The feature points selected by different feature ground objects can be different, for example, for the arrow-shaped ground mark line, the feature point positioned at the top end of the arrow can be selected for measurement; for the deceleration strip, the characteristic points at two ends of deceleration can be selected for measurement; for the crosswalk, the characteristic point at the end point of the marked line positioned at the outermost side of the crosswalk can be selected for measurement. Specifically, referring to fig. 2B, the feature points A, B1, B2, C1, C2 in the feature point coordinate graph may be selected for measurement. On the other hand, when the number of the characteristic features is large or the distribution is dense, several or more characteristic points of the representative characteristic features may be selected for measurement, for example, when the number of the characteristic feature tree pits is large, a measurement density of one characteristic feature, that is, a distance interval between the measured characteristic features may be set, taking a value of 30 meters as an example, only tree pits with a distance interval greater than or equal to 30 meters are selected for measurement, that is, one tree pit is measured every 30 meters on average, and tree pits within a range where the distance between two tree pits is less than 30 meters are ignored. In addition, a feature point measurement density, that is, a selective measurement feature point, may be set according to the size of the feature or the number of feature points, for example, the feature point measurement density is 20 meters, and one feature point is selected per 20 meters on average to perform measurement, while feature points located within a range of 20 meters between two feature points are ignored, and the number of measured feature points may also be determined according to actual requirements, for example, 20 or 30 feature points are selected per kilometer.
Step S104, calculating the real distance between the selected real feature points on the feature point coordinate map, and calculating the point cloud distance between the selected point cloud feature points on the point cloud map to determine the distance difference between the real distance and the point cloud distance.
Calculating the real distance between any two real feature points for the selected real feature points; similarly, for the selected point cloud feature points, calculating the point cloud distance between any two point cloud feature points; and then, calculating the distance difference between the point cloud distance and the real distance according to the corresponding relation of the characteristic points. It can be understood that, when the number of the selected point cloud feature points or the actual feature points is large, the distance between the feature points can be selectively calculated according to the actual situation. Specifically, referring to fig. 2c and 2d, under the condition that the real feature points selected on the feature point coordinate graph are respectively marked as 1 ', 2', 3 ', 4', 5 ', 6', 7 ', 8', 9 ', 10', the point cloud feature points selected on the point cloud map are correspondingly respectively marked as 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 (as shown in fig. 2c or 2 d); then, the true distances between any two true feature points, such as 1 '2', 1 '3', 1 '5', 2 '3', etc., may be calculated, or the true distances between some true feature points may be calculated selectively, which is described in this embodiment by taking the calculation of the true distances 1 '2', 3 '4', 5 '6', 7 '8', 9 '10' and 1 '3', 1 '8', 1 '9', 2 '8', 2 '9' as examples; correspondingly calculating point cloud distances 12, 34, 56, 78, 910 and 13, 18, 19, 28, 29 among the point cloud feature points; calculating the distance difference between the real distance 1 '2' and the point cloud distance 12 as d12, calculating the distance difference between the real distance 3 '4' and the point cloud distance 34 as d34, and repeating the steps until all the distance differences d12, d34, d56, d78, d910, d13, d18, d19, d28 and d29 are obtained.
And step S105, evaluating the precision of the point cloud map according to the distance difference between the real distance and the point cloud distance.
On the basis of obtaining the difference value between the real distance and the point cloud distance, whether the precision of the point cloud map meets the requirement can be judged according to the actual application requirement of the point cloud map, and if the precision of the point cloud map exceeds a certain precision threshold value, the precision of the point cloud map is judged according to whether the maximum value, the average value, the variance, the standard deviation and the like in the distance difference value exceed a certain precision threshold value. Wherein the standard deviation and the average value can be calculated according to the following formula:
where σ is the standard deviation and diIs the ith difference, d0Is the difference average.
Specifically, referring to fig. 2c and fig. 2d, the distance differences d12, d34, d56, d78, d910, d13, d18, d19, d28, and d29 obtained as above are still used as examples for explanation: if the evaluation is carried out based on the maximum value in the distance difference values, the maximum values in d12, d34, d56, d78, d910, d13, d18, d19, d28 and d29 are selected through comparison and screening, whether the precision of the point cloud map meets the requirement is judged according to whether the maximum values reach the precision threshold value, and if the maximum value in the distance difference values is larger than or equal to the precision threshold value, the precision of the point cloud map is judged not to meet the requirement and cannot be used; and if the maximum value in the distance difference values is lower than the precision threshold value, judging that the precision of the fixed point cloud map meets the requirement, and using the fixed point cloud map.
It should be noted that, referring to fig. 2d and fig. 2e, in the above embodiment, when the accuracy of the point cloud map is evaluated, not only the real distances 1 '2', 3 '4', 5 '6', 7 '8', 9 '10' representing the lengths of the real feature edges of the feature, but also the lengths of the feature edges of the non-feature or the lengths 1 '3', 1 '8', 1 '9', 2 '8', 2 '9' of the virtual feature edges are calculated, and the corresponding point cloud distances 12, 34, 56, 78, 910 and 13, 18, 19, 28, 29 in the point cloud map are also calculated, so that even when the point cloud map has distortion or deformation as shown in fig. 2e, the combination of the lengths of the real feature edges and the lengths of the virtual feature edges can well reflect the accuracy of the point cloud map, and have higher reliability.
Referring to fig. 3, on the basis of the foregoing embodiment, with respect to step S103 in the foregoing embodiment, an embodiment of the present invention further provides a method for determining point cloud feature points corresponding to the at least two real feature points on the point cloud map based on rough registration between the point cloud map and a feature point coordinate map, which may specifically include the following steps:
and step S1031, selecting first point cloud characteristic points and second point cloud characteristic points on the point cloud map, and determining first real characteristic points and second real characteristic points corresponding to the first point cloud characteristic points and the second point cloud characteristic points on the characteristic point coordinate map.
The first point cloud characteristic points and the second point cloud characteristic points selected here are mainly used for realizing rough registration of the point cloud map and the characteristic point coordinate map, and further facilitating selection of corresponding point cloud characteristic points and real characteristic points. Therefore, characteristic point pairs which are marked or are convenient to distinguish can be selected from the point cloud map as the first point cloud characteristic points and the second point cloud characteristic points, such as characteristic points located at the outermost periphery of the point cloud map, characteristic points located at the central position of the point cloud map, and the like, in a manual selection or image recognition mode.
In a possible implementation manner, the first point cloud feature point and the second point cloud feature point are two feature points which are farthest away on the point cloud map; and when a plurality of pairs of point cloud characteristic points with the farthest distance exist or a plurality of characteristic lines with the point cloud characteristic points as end points exist, selecting the end points of the characteristic lines with the closest distance to the middle position of the point cloud map as the first point cloud characteristic points and the second point cloud characteristic points. Specifically, referring to fig. 4a, two feature points A, B with the farthest distance on the point cloud map are selected as a first point cloud feature point and a second point cloud feature point respectively; and the real feature points a and B corresponding to the first point cloud feature point A and the second point cloud feature point B on the feature point coordinate graph are the first real feature point a and the second real feature point B.
Step S1032, translating the point cloud map to enable the first point cloud characteristic point to be overlapped with the first real characteristic point.
Specifically, referring to fig. 4a and 4b, with the first real feature point a as a reference, the point cloud map is translated along the arrow direction shown in fig. 4a until the first point cloud feature point a coincides with the first real feature point a, and at this time, the position relationship formed by the point cloud map and the feature point coordinate map is as shown in fig. 4 b.
Step S1033, using the first point cloud feature point as a reference point, rotating the point cloud map to make the second point cloud feature point close to the second real feature point.
It can be understood that, because a certain error exists between the constructed point cloud map and the real world, when the first point cloud feature point a and the first real feature point a are already overlapped, and then the first point cloud feature point a is taken as a reference point, and the point cloud map is rotated to enable the second point cloud feature point B to approach the second real feature point B, a situation that the second point cloud feature point B and the second real feature point B are overlapped may exist (as shown in fig. 4 c), a situation that the second point cloud feature point B and the second real feature point B cannot be overlapped may also exist (as shown in fig. 4 d), if the second point cloud feature point B and the second real feature point B cannot be overlapped and the distance between the point cloud feature points is large, it is indicated that a difference map between the map and the feature point coordinate map is large or the accuracy of the point cloud map is low, and the current point cloud map should be abandoned. Therefore, the accuracy of the point cloud map can be pre-evaluated based on the proximity of the second point cloud feature point B and the second real feature point B, that is, whether the minimum distance between the second point cloud feature point B and the second real feature point B exceeds the threshold distance, and further consideration is given to whether to continue evaluating the accuracy of the current point cloud map or to discard the current point cloud map.
Step S1034, based on the distance nearest principle, determining other point cloud characteristic points corresponding to other real characteristic points on the point cloud map.
Specifically, referring to fig. 4c and 4d, when the second point cloud feature point B and the second real feature point B are completely overlapped or the minimum distance between the second point cloud feature point B and the second real feature point B is smaller than the threshold distance, based on the distance closest principle, the point cloud feature point corresponding to the real feature point is selected on the point cloud map to measure the point cloud distance and the real distance.
It can be understood that although the point cloud map is three-dimensional (the coordinate axis X, Y, Z is taken as an example for explanation), when the point cloud map is constructed by methods such as SLAM, the Z axis is vertical upwards by default, so that the obtained point cloud map and the real world or feature point coordinate map are parallel in the height direction, and further, in the process of controlling the point cloud map and the feature point coordinate map to approach or roughly register, the problems of pitching and overturning do not need to be considered, and only rotation and translation need to be performed in the plane formed by X, Y. Meanwhile, because the height of the point cloud is controlled within 10-20 meters, in such a small range, the precision in the elevation direction is generally within 10cm and cannot be accumulated, and because the tolerance to the relative precision of the elevation is large in the using process of the point cloud map, the relative precision of the elevation completely meets the application requirement at ordinary times, the elevation factor is not needed to be considered in the precision evaluation, only the relative precision of the plane is concerned, and therefore, the relative precision in the X, Y direction only needs to be evaluated by rotating and translating in the plane formed by X, Y.
Referring to fig. 5, an embodiment of the present invention provides an apparatus 500 for evaluating accuracy of a point cloud map, including: the system comprises a ground feature selection module 501, a coordinate graph generation module 502, a feature point selection module 503 and a distance calculation module 504; wherein the content of the first and second substances,
the surface feature selection module 501 is configured to select a feature surface feature on a point cloud map;
the coordinate graph generating module 502 is configured to obtain coordinates of feature points of the feature features in the real world, so as to generate a feature point coordinate graph;
the feature point selecting module 503 is configured to select at least two real feature points on the feature point coordinate map, and determine point cloud feature points corresponding to the at least two real feature points on the point cloud map;
the distance calculation module 504 is configured to calculate a real distance between selected real feature points on the feature point coordinate map, and calculate a point cloud distance between the selected point cloud feature points on the point cloud map, so as to determine a distance difference between the real distance and the point cloud distance; and evaluating the precision of the point cloud map according to the distance difference between the real distance and the point cloud distance.
In an optional implementation manner, the feature point selecting module 503 is further configured to: selecting a first point cloud characteristic point and a second point cloud characteristic point on the point cloud map, and determining a first real characteristic point and a second real characteristic point corresponding to the first point cloud characteristic point and the second point cloud characteristic point on the characteristic point coordinate map; translating the point cloud map to enable the first point cloud characteristic point to be overlapped with the first real characteristic point; rotating the point cloud map by taking the first point cloud feature point as a reference point to enable the second point cloud feature point to be close to the second real feature point; and determining other point cloud characteristic points corresponding to other real characteristic points on the point cloud map based on a distance nearest principle.
To sum up, according to the method or the apparatus for evaluating the accuracy of the point cloud map provided in the embodiment of the present invention, the actual distance between the actual feature points on the feature point coordinate map is used to replace the actual measured length of the feature edge line in the prior art and the point cloud distance between the corresponding point cloud feature points on the point cloud map, so as to overcome the technical problems that a large amount of manpower and material resources are required to be invested to obtain a large amount of feature edge line lengths and the obtained feature edge line lengths are within 20 meters in the prior art, thereby greatly improving the efficiency of evaluating the accuracy of the point cloud map, and simultaneously expanding the scale of the scene of the point cloud map that can be evaluated; in addition, the calculated distance between the feature points not only comprises the length corresponding to the feature edge line of the feature ground object, but also comprises the length of a non-feature edge line or the length of a virtual feature edge line, so that when the point cloud map has distortion, deformation and the like, the length of the virtual feature edge line can well reflect relative errors of the point cloud map caused by the distortion, the deformation and the like, and the accuracy of the precision of the estimated point cloud map is further improved to a certain extent.
Fig. 6 illustrates an exemplary system architecture 600 of a method or apparatus for evaluating point cloud map accuracy to which embodiments of the invention may be applied.
As shown in fig. 6, the system architecture 600 may include terminal devices 601, 602, 603, a network 604, and a server 605. The network 604 serves to provide a medium for communication links between the terminal devices 601, 602, 603 and the server 605. Network 604 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.
A user may use the terminal devices 601, 602, 603 to interact with the server 605 via the network 604 to receive or send messages or the like. Various communication client applications, such as shopping applications, web browser applications, search applications, instant messaging tools, mailbox clients, social platform software, and the like, may be installed on the terminal devices 601, 602, and 603.
The terminal devices 601, 602, 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 605 may be a server that provides various services, such as a background management server that supports shopping websites browsed by users using the terminal devices 601, 602, and 603. The background management server can analyze and process the received data such as the product information query request and the like, and feed back the processing results such as the calculated real distance, the point cloud distance, the distance difference value and the like to the terminal equipment.
It should be noted that the method for evaluating the accuracy of the point cloud map provided by the embodiment of the present invention is generally executed by the server 605, and accordingly, the apparatus for evaluating the accuracy of the point cloud map is generally disposed in the server 605.
It should be understood that the number of terminal devices, networks, and servers in fig. 6 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 7, shown is a block diagram of a computer system 700 suitable for use with a terminal device implementing an embodiment of the present invention. The terminal device shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 7, the computer system 700 includes a Central Processing Unit (CPU)701, which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data necessary for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
The following components are connected to the I/O interface 705: an input portion 706 including a keyboard, a mouse, and the like; an output section 707 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 708 including a hard disk and the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read out therefrom is mounted into the storage section 708 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 709, and/or installed from the removable medium 711. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 701.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor comprises a ground feature selection module, a coordinate graph generation module, a feature point selection module and a distance calculation module. Wherein the names of the modules do not in some cases constitute a limitation of the module itself. For example, the feature selection module may also be described as a "module for selecting a characteristic feature".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: selecting characteristic ground objects on the point cloud map; acquiring coordinates of characteristic points of the characteristic ground objects in the real world to generate a characteristic point coordinate graph; selecting at least two real feature points on the feature point coordinate graph, and determining point cloud feature points corresponding to the at least two real feature points on the point cloud map; calculating the real distance between the selected real feature points on the feature point coordinate graph, and calculating the point cloud distance between the selected point cloud feature points on the point cloud map so as to determine the distance difference between the real distance and the point cloud distance; and evaluating the precision of the point cloud map according to the distance difference between the real distance and the point cloud distance.
According to the technical scheme of the embodiment of the invention, the actual distance between the actual characteristic points on the characteristic point coordinate graph is adopted to replace the actual measured length of the characteristic edge line in the prior art to be compared with the point cloud distance between the corresponding point cloud characteristic points on the point cloud map, so that the technical problems that a large amount of characteristic edge line lengths can be obtained only by investing a large amount of manpower and material resources and the obtained characteristic edge line lengths are within 20 meters in the prior art are solved, the efficiency of evaluating the precision of the point cloud map is greatly improved, and the scale of the scene of the point cloud map which can be evaluated is expanded; in addition, the calculated distance between the feature points not only comprises the length corresponding to the feature edge line of the feature ground object, but also comprises the length of a non-feature edge line or the length of a virtual feature edge line, so that when the point cloud map has distortion, deformation and the like, the length of the virtual feature edge line can well reflect relative errors of the point cloud map caused by the distortion, the deformation and the like, and the accuracy of the precision of the estimated point cloud map is further improved to a certain extent.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for evaluating point cloud map accuracy, comprising:
selecting characteristic ground objects on the point cloud map;
acquiring coordinates of characteristic points of the characteristic ground objects in the real world to generate a characteristic point coordinate graph;
selecting at least two real feature points on the feature point coordinate graph, and determining point cloud feature points corresponding to the at least two real feature points on the point cloud map;
calculating the real distance between the selected real feature points on the feature point coordinate graph, and calculating the point cloud distance between the selected point cloud feature points on the point cloud map so as to determine the distance difference between the real distance and the point cloud distance;
and evaluating the precision of the point cloud map according to the distance difference between the real distance and the point cloud distance.
2. The method of claim 1, wherein the coordinates of the feature points of the feature in the real world are obtained by a real-time dynamic difference method to form a feature point coordinate graph.
3. The method for assessing point cloud map accuracy of claim 1, further comprising:
selecting a first point cloud characteristic point and a second point cloud characteristic point on the point cloud map, and determining a first real characteristic point and a second real characteristic point corresponding to the first point cloud characteristic point and the second point cloud characteristic point on the characteristic point coordinate map;
translating the point cloud map to enable the first point cloud characteristic point to be overlapped with the first real characteristic point;
rotating the point cloud map by taking the first point cloud feature point as a reference point to enable the second point cloud feature point to be close to the second real feature point;
and determining other point cloud characteristic points corresponding to other real characteristic points on the point cloud map based on a distance nearest principle.
4. The method for evaluating the accuracy of a point cloud map of claim 3, wherein the first point cloud feature point and the second point cloud feature point are two feature points on the point cloud map that are farthest away;
and when a plurality of pairs of point cloud characteristic points with the farthest distance exist or a plurality of characteristic lines with the point cloud characteristic points as end points exist, selecting the end points of the characteristic lines with the closest distance to the middle position of the point cloud map as the first point cloud characteristic points and the second point cloud characteristic points.
5. The method for evaluating the accuracy of a point cloud map of claim 1, wherein the number, location, and distance of the at least two feature points selected on the feature point coordinate graph are determined according to the characteristics of the selected feature; the characteristics of the characteristic ground features comprise: the number of the characteristic ground features, the shapes of the characteristic ground features and the sizes of the characteristic ground features.
6. The method for evaluating the accuracy of a point cloud map of claim 1, wherein the accuracy of the point cloud map is evaluated according to a variance, standard deviation, or maximum of a distance difference of the real distance and the point cloud distance.
7. An apparatus for evaluating point cloud map accuracy, comprising: the system comprises a ground object selection module, a coordinate graph generation module, a characteristic point selection module and a distance calculation module; wherein the content of the first and second substances,
the ground object selection module is used for selecting characteristic ground objects on the point cloud map;
the coordinate graph generating module is used for acquiring the coordinates of the characteristic points of the characteristic ground features in the real world so as to generate a characteristic point coordinate graph;
the characteristic point selection module is used for selecting at least two real characteristic points on the characteristic point coordinate graph and determining point cloud characteristic points corresponding to the at least two real characteristic points on the point cloud map;
the distance calculation module is used for calculating the real distance between the selected real feature points on the feature point coordinate map, calculating the point cloud distance between the selected point cloud feature points on the point cloud map and determining the distance difference between the real distance and the point cloud distance; and evaluating the precision of the point cloud map according to the distance difference between the real distance and the point cloud distance.
8. The apparatus for evaluating the accuracy of a point cloud map of claim 7, wherein the feature point selection module is further configured to:
selecting a first point cloud characteristic point and a second point cloud characteristic point on the point cloud map, and determining a first real characteristic point and a second real characteristic point corresponding to the first point cloud characteristic point and the second point cloud characteristic point on the characteristic point coordinate map;
translating the point cloud map to enable the first point cloud characteristic point to be overlapped with the first real characteristic point;
rotating the point cloud map by taking the first point cloud feature point as a reference point to enable the second point cloud feature point to be close to the second real feature point;
and determining other point cloud characteristic points corresponding to other real characteristic points on the point cloud map based on a distance nearest principle.
9. An electronic device for evaluating point cloud map accuracy, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.
10. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910476434.1A CN112116549A (en) | 2019-06-03 | 2019-06-03 | Method and device for evaluating point cloud map precision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910476434.1A CN112116549A (en) | 2019-06-03 | 2019-06-03 | Method and device for evaluating point cloud map precision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112116549A true CN112116549A (en) | 2020-12-22 |
Family
ID=73795188
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910476434.1A Pending CN112116549A (en) | 2019-06-03 | 2019-06-03 | Method and device for evaluating point cloud map precision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112116549A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112634260A (en) * | 2020-12-31 | 2021-04-09 | 上海商汤智能科技有限公司 | Map evaluation method and device, electronic equipment and storage medium |
| CN113344866A (en) * | 2021-05-26 | 2021-09-03 | 长江水利委员会水文局长江上游水文水资源勘测局 | Point cloud comprehensive precision evaluation method |
| CN113656529A (en) * | 2021-09-16 | 2021-11-16 | 北京百度网讯科技有限公司 | Road precision determination method and device and electronic equipment |
| TWI766744B (en) * | 2021-06-29 | 2022-06-01 | 鴻海精密工業股份有限公司 | Point cloud density adjustment method, computer device and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105953805A (en) * | 2016-04-29 | 2016-09-21 | 百度在线网络技术（北京）有限公司 | Method and device for verifying map |
| CN106776996A (en) * | 2016-12-02 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for testing the accuracy of high accuracy map |
| CN106846308A (en) * | 2017-01-20 | 2017-06-13 | 广州市城市规划勘测设计研究院 | The detection method and device of the topographic map precision based on a cloud |
| CN107944018A (en) * | 2017-12-11 | 2018-04-20 | 江苏省测绘工程院 | A kind of automatic quality detecting method of map vector positional precision based on laser point cloud data |
| CN108510530A (en) * | 2017-02-28 | 2018-09-07 | 深圳市朗驰欣创科技股份有限公司 | A kind of three-dimensional point cloud matching process and its system |
| CN108549375A (en) * | 2018-04-16 | 2018-09-18 | 戴姆勒股份公司 | Dotted object precision quality appraisal procedure based on random optimization in high-precision map |
| CN108564874A (en) * | 2018-05-07 | 2018-09-21 | 腾讯大地通途（北京）科技有限公司 | Method, the method for model training, equipment and the storage medium of surface mark extraction |
| CN109064506A (en) * | 2018-07-04 | 2018-12-21 | 百度在线网络技术（北京）有限公司 | Accurately drawing generating method, device and storage medium |
| KR101954963B1 (en) * | 2018-01-15 | 2019-03-07 | 주식회사 스트리스 | System and Method for Automatic Construction of Numerical Digital Map and High Definition Map |
-
2019
- 2019-06-03 CN CN201910476434.1A patent/CN112116549A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105953805A (en) * | 2016-04-29 | 2016-09-21 | 百度在线网络技术（北京）有限公司 | Method and device for verifying map |
| CN106776996A (en) * | 2016-12-02 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for testing the accuracy of high accuracy map |
| CN106846308A (en) * | 2017-01-20 | 2017-06-13 | 广州市城市规划勘测设计研究院 | The detection method and device of the topographic map precision based on a cloud |
| CN108510530A (en) * | 2017-02-28 | 2018-09-07 | 深圳市朗驰欣创科技股份有限公司 | A kind of three-dimensional point cloud matching process and its system |
| CN107944018A (en) * | 2017-12-11 | 2018-04-20 | 江苏省测绘工程院 | A kind of automatic quality detecting method of map vector positional precision based on laser point cloud data |
| KR101954963B1 (en) * | 2018-01-15 | 2019-03-07 | 주식회사 스트리스 | System and Method for Automatic Construction of Numerical Digital Map and High Definition Map |
| CN108549375A (en) * | 2018-04-16 | 2018-09-18 | 戴姆勒股份公司 | Dotted object precision quality appraisal procedure based on random optimization in high-precision map |
| CN108564874A (en) * | 2018-05-07 | 2018-09-21 | 腾讯大地通途（北京）科技有限公司 | Method, the method for model training, equipment and the storage medium of surface mark extraction |
| CN109064506A (en) * | 2018-07-04 | 2018-12-21 | 百度在线网络技术（北京）有限公司 | Accurately drawing generating method, device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 秦红艳;: "三维激光扫描技术检测测绘成果精度的应用", 测绘工程, no. 10 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112634260A (en) * | 2020-12-31 | 2021-04-09 | 上海商汤智能科技有限公司 | Map evaluation method and device, electronic equipment and storage medium |
| CN113344866A (en) * | 2021-05-26 | 2021-09-03 | 长江水利委员会水文局长江上游水文水资源勘测局 | Point cloud comprehensive precision evaluation method |
| TWI766744B (en) * | 2021-06-29 | 2022-06-01 | 鴻海精密工業股份有限公司 | Point cloud density adjustment method, computer device and storage medium |
| CN113656529A (en) * | 2021-09-16 | 2021-11-16 | 北京百度网讯科技有限公司 | Road precision determination method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112116549A (en) | Method and device for evaluating point cloud map precision | |
| US10534870B2 (en) | Methods, apparatuses and computer program products for automatic, non-parametric, non-iterative three dimensional geographic modeling | |
| JP2019512668A (en) | Root deviation recognition method, terminal, and storage medium | |
| KR20150124396A (en) | System and Method for Location Determination, Mapping, and Data Management through Crowdsourcing | |
| WO2022089018A1 (en) | Method and apparatus for slicing three-dimensional vector data of three-dimensional vector map, and electronic device | |
| JP7210086B2 (en) | AREA DIVISION METHOD AND DEVICE, ELECTRONIC DEVICE AND PROGRAM | |
| CN111339692B (en) | Laser point cloud data-based power line sag determination method and device | |
| US10380454B2 (en) | Identifying a visual center of a polygon | |
| CN114882316A (en) | Target detection model training method, target detection method and device | |
| Carneiro et al. | Digital urban morphometrics: automatic extraction and assessment of morphological properties of buildings | |
| CN113654536A (en) | Beidou RTK-based national forest and grass monitoring method, device, equipment and medium | |
| CN113280764A (en) | Power transmission and transformation project disturbance range quantitative monitoring method and system based on multi-satellite cooperation technology | |
| CN112686945A (en) | Web-based three-dimensional terrain surface area measurement method | |
| CN113758492A (en) | Map detection method and device | |
| Ma et al. | Hybrid model for realistic and efficient estimation of highway sight distance using airborne LiDAR data | |
| CN111523057A (en) | Base map acquisition method, device, equipment and storage medium based on terrain mapping | |
| CN113822892B (en) | Evaluation method, device and equipment of simulated radar and computer storage medium | |
| CN113724229B (en) | Method and device for determining elevation difference and electronic equipment | |
| CN113269827B (en) | Method and computing device for realizing automatic calibration | |
| CN115640372A (en) | Method, device, system, equipment and medium for guiding area of indoor plane | |
| CN115527028A (en) | Map data processing method and device | |
| Lohani et al. | Effect of data density, scan angle, and flying height on the accuracy of building extraction using LiDAR data | |
| CN108834053B (en) | Positioning method, device and equipment | |
| CN113532424A (en) | Integrated equipment for acquiring multidimensional information and cooperative measurement method | |
| CN111356072B (en) | Position estimation method and device for indoor positioning and readable storage medium |
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 |