CN117128950A - Point cloud map construction method and device, electronic equipment and storage medium - Google Patents
Point cloud map construction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117128950A CN117128950A CN202311098177.5A CN202311098177A CN117128950A CN 117128950 A CN117128950 A CN 117128950A CN 202311098177 A CN202311098177 A CN 202311098177A CN 117128950 A CN117128950 A CN 117128950A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- pose
- cloud data
- key frame
- coordinate system
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 claims description 43
- 238000005457 optimization Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 10
- 238000013519 translation Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
Abstract
The embodiment of the invention discloses a point cloud map construction method, a device, electronic equipment and a storage medium, wherein after collected point cloud data are classified according to the intensity of a locating signal of a viaduct, a key frame in first point cloud data is identified, the pose of the current key frame under a first coordinate system is optimized, and the point cloud position of the current key frame is adjusted by utilizing the optimized first target pose to obtain first target point cloud data; identifying a key frame in the second point cloud data and a closed-loop frame of each key frame, optimizing the pose of the current key frame under the first coordinate system according to the pose of the closed-loop frame of the current key frame under the first coordinate system, and adjusting the point cloud position of the current key frame by utilizing the optimized second target pose to obtain second target point cloud data; and converting the first target point cloud data and the second target point cloud data into point cloud data under a second coordinate system to obtain a point cloud map. The invention can accurately build the map in places with complex roads and unstable GPS signals.
Description
Technical Field
The embodiment of the invention relates to the technical field of automatic driving, in particular to a point cloud map construction method, a device, electronic equipment and a storage medium.
Background
In the field of autopilot, it is often necessary to map the environment and then implement positioning functions in the map that is built. In the related art, a single laser radar or camera is mainly used for building a point cloud map for the surrounding environment in the vehicle driving process, and most of technical schemes can be solved for some common road building, but the scheme cannot cope with the scene of difficult or inaccurate building caused by complex roads like viaducts and unstable global positioning system (Global Positioning System, GPS) signals.
Disclosure of Invention
The embodiment of the invention provides a point cloud map construction method, a device, an electronic and a storage medium, which can be used for accurately constructing a map in a place with complex roads and unstable global positioning system signals.
In a first aspect, the present invention provides a method for constructing a point cloud map, where the method includes:
classifying the acquired point cloud data of the viaduct according to the intensity of the positioning signal of the viaduct to obtain first point cloud data and second point cloud data, wherein the intensity of the positioning signal is higher when the first point cloud data is acquired than that when the second point cloud data is acquired;
Identifying key frames in the first point cloud data, optimizing the pose of the current key frame under a first coordinate system according to the pose of each key frame under the first coordinate system to obtain a first target pose, and adjusting the point cloud position of the current key frame by using the first target pose to obtain first target point cloud data;
identifying key frames in the second point cloud data, identifying closed-loop frames of the key frames, optimizing the pose of the current key frame under the first coordinate system according to the pose of the closed-loop frame of the current key frame under the first coordinate system to obtain a second target pose, and adjusting the point cloud position of the current key frame by utilizing the second target pose to obtain second target point cloud data;
and converting the first target point cloud data and the second target point cloud data into point cloud data under a second coordinate system to obtain a point cloud map of the overpass.
In a second aspect, the present invention provides a point cloud map construction apparatus, including:
the classification module is used for classifying the acquired point cloud data of the viaduct according to the intensity of the positioning signal of the viaduct to obtain first point cloud data and second point cloud data, wherein the intensity of the positioning signal is higher when the first point cloud data is acquired than when the second point cloud data is acquired;
The pose adjustment module is used for identifying key frames in the first point cloud data, optimizing the pose of the current key frame under the first coordinate system according to the pose of each key frame under the first coordinate system to obtain a first target pose, and adjusting the point cloud position of the current key frame by utilizing the first target pose to obtain first target point cloud data;
the position and pose module is further used for identifying key frames in the second point cloud data and identifying closed-loop frames of the key frames, optimizing the pose of the current key frame under the first coordinate system according to the pose of the closed-loop frame of the current key frame under the first coordinate system to obtain a second target pose, and adjusting the point cloud position of the current key frame by utilizing the second target pose to obtain second target point cloud data;
and the determining module is used for converting the first target point cloud data and the second target point cloud data into point cloud data under a second coordinate system to obtain a point cloud map of the overpass.
In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the point cloud map construction method according to any embodiment of the present invention when executing the program.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a point cloud map construction method according to any of the embodiments of the present invention.
According to the scheme, the acquired point cloud data of the viaduct can be classified according to the intensity of the positioning signal of the viaduct to obtain the first point cloud data and the second point cloud data, and the intensity of the positioning signal is higher when the first point cloud data is acquired than when the second point cloud data is acquired; the method comprises the steps of identifying key frames in first point cloud data, optimizing the pose of a current key frame under a first coordinate system according to the pose of each key frame under the first coordinate system to obtain a first target pose, and adjusting the point cloud position of the current key frame by using the first target pose to obtain first target point cloud data; identifying key frames in the second point cloud data, identifying closed-loop frames of the key frames, optimizing the pose of the current key frame under the first coordinate system according to the pose of the closed-loop frame of the current key frame under the first coordinate system to obtain a second target pose, and adjusting the point cloud position of the current key frame by utilizing the second target pose to obtain second target point cloud data; and converting the first target point cloud data and the second target point cloud data into point cloud data under a second coordinate system to obtain a point cloud map of the overpass. According to the method, the acquired overpass data are classified, key frames of point cloud data of roads with good GPS are identified, and the pose of the current key frame under a first coordinate system is optimized according to the pose of each key frame under the first coordinate system. And identifying a key frame of point cloud data of the road with weak or no GPS signals, and optimizing the pose of the current frame under a first coordinate system by utilizing a closed-loop frame of the current key frame. According to the method, aiming at places with different GPS signal intensities, different modes are adopted to build the map, so that the accuracy of building the point cloud map at places with complex roads and unstable GPS signals is improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and should not be considered as limiting the scope, and that other related drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a point cloud map construction method according to an embodiment of the present invention;
fig. 2 is a second schematic flow chart of a point cloud map construction method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a point cloud map building apparatus according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order that the manner in which the invention may be better understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. All other embodiments, which can be made by those skilled in the art based on the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the invention described herein may be practiced otherwise than as specifically illustrated and described. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the invention, the technical scheme can be applied to the point cloud map construction of complex roads and roads with unstable GPS signal intensity, for example: and (5) constructing a point cloud map of the viaduct. In the following description, the technical scheme of the present invention will be described by taking a point cloud map construction scene of a viaduct as an example, but it should be noted that the technical scheme of the present invention is not only applicable to the point cloud map construction of a viaduct, but is not limited herein.
As shown in fig. 1, fig. 1 is a schematic flow diagram of a point cloud map construction method provided by an embodiment of the present invention, where the point cloud map construction method provided by the embodiment of the present invention may be implemented by a point cloud map construction device provided by the embodiment of the present invention, and the device may be implemented in a software and/or hardware manner. In a specific embodiment, the apparatus may be integrated in an electronic device, which may be a computer, a server, or the like. Referring to fig. 1, the data processing method of the present embodiment specifically may include the following steps:
s101, classifying the acquired point cloud data of the viaduct according to the intensity of the locating signal of the viaduct to obtain first point cloud data and second point cloud data, wherein the intensity of the locating signal is higher when the first point cloud data is acquired than when the second point cloud data is acquired.
When the point cloud map of the viaduct is constructed, because roads with different GPS signal strengths exist in the viaduct, such as the upper layer of the viaduct is good in GPS signal, and the lower layer of the viaduct is weak in GPS signal or completely free of GPS signal, the roads of the viaduct can be classified according to the GPS signal strength, the point cloud map is constructed by single driving of the roads with good GPS signal, the point cloud map is constructed by multiple driving of the roads with weak GPS signal or completely free of GPS signal, and finally the point cloud data in the point cloud map of the single driving and the point cloud map of the multiple driving are spliced to obtain the point cloud map of the viaduct.
Specifically, the preset sensor may be used to collect point cloud data of the viaduct, where the point cloud data may be data collected in a preset time by the laser radar, an intensity threshold of a positioning signal or an intensity interval of the positioning signal is set to classify the point cloud data collected by different signal intensities of the viaduct, so as to obtain first point cloud data and second point cloud data, where the first point cloud data may be data of a road with a good collected GPS signal, such as point cloud data of an upper layer of the viaduct, and the second point cloud data may be data of a road with a weak or no collected GPS signal, such as point cloud data of a lower layer of the viaduct.
S102, identifying key frames in the first point cloud data, optimizing the pose of the current key frame under the first coordinate system according to the pose of each key frame under the first coordinate system to obtain a first target pose, and adjusting the point cloud position of the current key frame by using the first target pose to obtain first target point cloud data.
In particular, a key frame may refer to a key preset sensor data frame, and a pose is a position and a pose describing a certain object (such as a coordinate) under a specified coordinate system. And identifying a key frame in each frame containing the first point cloud data, optimizing the pose of the current key frame in the first coordinate system according to the pose of each key frame in the first coordinate system to obtain a first target pose, and finally adjusting the point cloud position of the current frame in the first coordinate system according to the obtained first target pose to obtain relatively accurate point cloud data in the first coordinate system. The first coordinate system may be a mileage coordinate system.
Specifically, when judging whether the current frame is a key frame or not, determining the translation distance and the time interval of the current frame and the last key frame, setting a translation distance threshold and a time interval threshold, and if the translation distance is not less than the translation distance threshold and the time interval is not less than the time interval threshold, determining the current frame as the key frame. If the current frame is the first frame, the current frame is the key frame.
By way of example, after the sensor is used to collect a plurality of frames of the overhead bridge including the first point cloud data, taking the 4 th frame as an example, whether the 4 th frame is a key frame or not can be judged through the translation distance between the 4 th frame and the last key frame and a time interval, if the 4 th frame is a key frame, the pose of the 4 th key frame can be optimized by using the 4 th key frame and other key frames, for example, the next key frame of the 4 th key frame, so as to obtain a more accurate pose of the 4 th key frame, namely, a first target pose, and according to the first target pose, the point cloud position of the 4 th frame under a first coordinate system, for example, under the odometer coordinate, is adjusted, so that more accurate point cloud data is obtained. And recalculating and splicing the point cloud data under the coordinate system of the odometer according to the pose of the first target to form accurate point cloud data.
S103, identifying key frames in the second point cloud data, identifying closed-loop frames of the key frames, optimizing the pose of the current key frame under the first coordinate system according to the pose of the closed-loop frame of the current key frame under the first coordinate system to obtain a second target pose, and adjusting the point cloud position of the current key frame by using the second target pose to obtain second target point cloud data.
Specifically, a key frame is identified in each frame containing second point cloud data, namely, each frame of a road with weak or no signal of the acquired GPS signal strength, and a closed-loop frame of the key frame is identified, wherein the closed-loop frame is a frame forming loop constraint with the current frame. And then optimizing the pose of the current key frame under the first coordinate system according to the pose of the closed-loop frame under the first coordinate system to obtain a second target pose, and finally adjusting the point cloud position of the current frame under the first coordinate system according to the obtained second target pose to obtain relatively accurate point cloud data under the first coordinate system.
In this embodiment, if the current frame is a key frame, in determining which frame and the current key frame form a loop constraint in each collected frame data, the determination may be made by the translation distance, the interval time and the SC description factor, and if a certain frame and the current key frame form the loop constraint, the certain frame is a closed loop frame of the current key frame.
By way of example, after a plurality of frames of the viaduct including the second point cloud data are collected by using the sensor, taking the 4 th frame as an example, whether the 4 th frame is a key frame or not can be judged through the translation distance and the time interval of the 4 th frame and the last key frame, if the 4 th frame is the key frame, a closed loop frame which forms loop constraint with the 4 th key frame is determined, the pose of the current key frame is optimized by using the closed loop frame, a more accurate pose of the current key frame, namely a second target pose, and according to the second target pose, the point cloud position of the current frame under the first coordinate system, such as the odometer coordinate, is adjusted, so that more accurate point cloud data are obtained. And recalculating and splicing the point cloud data under the odometer coordinate system according to the second target pose to form more accurate point cloud data.
In the present embodiment, there is no order of S102 and S103.
S104, converting the first target point cloud data and the second target point cloud data into point cloud data under a second coordinate system, and obtaining a point cloud map of the overpass.
Specifically, the first target point cloud data and the second target point cloud data in the first coordinate system can be converted into the second coordinate system according to the pose relation, and a point cloud map of the overpass is obtained. The second coordinate system may be a station-center coordinate system.
It can be understood that in this embodiment, the collected point cloud data of the overpass is classified according to the intensity of the locating signal of the overpass to obtain first point cloud data and second point cloud data, where the intensity of the locating signal is higher when the first point cloud data is collected than when the second point cloud data is collected; the method comprises the steps of identifying key frames in first point cloud data, optimizing the pose of a current key frame under a first coordinate system according to the pose of each key frame under the first coordinate system to obtain a first target pose, and adjusting the point cloud position of the current key frame by using the first target pose to obtain first target point cloud data; identifying key frames in the second point cloud data, identifying closed-loop frames of the key frames, optimizing the pose of the current key frame under the first coordinate system according to the pose of the closed-loop frame of the current key frame under the first coordinate system to obtain a second target pose, and adjusting the point cloud position of the current key frame by utilizing the second target pose to obtain second target point cloud data; and converting the first target point cloud data and the second target point cloud data into point cloud data under a second coordinate system to obtain a point cloud map of the overpass. According to the method, the acquired overpass data are classified, key frames of point cloud data of roads with good GPS are identified, and the pose of the current key frame under the first coordinate system is optimized according to the pose of each key frame under the first coordinate system. And identifying a key frame of point cloud data of the road with weak or no GPS signals, and optimizing the pose of the current frame under a first coordinate system by utilizing a closed-loop frame of the current key frame. According to the method, aiming at places with different GPS signal intensities, different modes are adopted to build the map, so that the accuracy of building the point cloud map at places with complex roads and unstable GPS signals is improved.
The method for constructing a point cloud map according to the embodiment of the present invention is further described below, as shown in fig. 2, and fig. 2 is a second schematic flow chart of the method for constructing a point cloud map according to the embodiment of the present invention. The method specifically comprises the following steps:
s201, classifying the acquired point cloud data of the overpass according to the intensity of the positioning signal of the overpass to obtain first point cloud data and second point cloud data, wherein the intensity of the positioning signal is higher when the first point cloud data is acquired than when the second point cloud data is acquired.
Specifically, the preset sensor may be used to collect point cloud data of the viaduct, where the point cloud data may be data collected in a preset time by the laser radar, an intensity threshold of a positioning signal or an intensity interval of the positioning signal is set to classify the point cloud data collected by different signal intensities of the viaduct, so as to obtain first point cloud data and second point cloud data, where the first point cloud data may be data of a road with a good collected GPS signal, such as point cloud data of an upper layer of the viaduct, and the second point cloud data may be data of a road with a weak or no collected GPS signal, such as point cloud data of a lower layer of the viaduct.
S202, clustering the first point cloud data of the current frame to obtain a plurality of clusters.
Specifically, when the map is built on the road with good GPS signals, the collected first point cloud data may be clustered, and when the map is built on the road with weak or no GPS signals, the collected second point cloud data may be clustered.
S203, calculating the current point data and preset point data of each cluster in the plurality of clusters to obtain a calculation result.
Specifically, the current point data in each cluster can be subjected to square sum operation of depth differences with preset data in the same cluster, such as front and back ten point data, so as to obtain an operation result, namely the curvature.
S204, determining the current point data with the operation result larger than the operation threshold value as the surface characteristic point.
S205, determining the current point data with the operation result not larger than the operation threshold value as the line characteristic point.
In the present embodiment, the operation result, that is, the curvature is used to distinguish the surface feature point and the line feature point in each cluster. And determining the current point data with the operation result being larger than the operation threshold value as the surface characteristic point, and determining the current point data with the operation result not being larger than the operation threshold value as the line characteristic point. Wherein, S204 and S205 have no sequence.
S206, determining a first residual equation based on the line characteristic points, and determining a second residual equation based on the surface characteristic points;
s207, determining a first pose of the current frame based on the first residual equation and the second residual equation.
And S208, adjusting the point cloud position of the current frame under the first coordinate system according to the first pose to obtain an adjusted current frame.
After clustering the current frame and classifying the point data of each cluster into line characteristic points and surface characteristic points, the point cloud registration between frames can be performed by utilizing the line characteristic points and the surface characteristic points in the current frame and the characteristic points of the previous frame in the current frame. The essence of point cloud registration is the process of converting the point cloud from the lidar coordinate system to the world coordinate system. Specifically, a first residual equation of a minimum distance from a point to a line based on a line feature point and a second residual equation of a minimum distance from a surface feature point are determined, an optimal solution of a current frame from a start frame is determined based on the determined first residual equation and the determined second residual equation, and the optimal solution is determined as a first pose of the current frame in a first coordinate system. And adjusting the point cloud position of the current frame under a first coordinate system according to the first pose, namely performing preliminary calculation and splicing on the point cloud data under the first coordinate system to form preliminary point cloud data.
S209, determining a third residual equation based on the adjusted line characteristic points of the current frame and the line characteristic points of the local map.
S210, determining a fourth residual equation based on the adjusted surface feature points of the current frame and the surface feature points of the local map.
Specifically, the local map may be a local map constructed by a preset number of frames, such as 50 frames, around the current frame, the current frame and the local map are matched based on the first pose of the current frame, a third residual equation of a minimum distance is determined based on the surface feature point of the current frame and the surface feature point of the local map, and a fourth residual equation is determined based on the line feature point of the current frame and the line feature point of the local map.
S211, determining the pose of the adjusted current frame under the first coordinate system according to the third residual equation and the fourth residual equation.
Specifically, an optimal solution is determined according to the third residual equation and the fourth residual equation, and the optimal solution is used as the pose of the current frame in the first coordinate system.
S212, identifying whether the current frame is the current key frame, and determining the pose of the adjacent key frame of the current key frame under the first coordinate system.
Specifically, after each frame of the acquired overhead bridge is subjected to inter-frame registration and registration with a local map, the pose of each frame under the first coordinate system is obtained, and then the key frame is identified. Whether the current frame is a key frame can be identified by a translation distance and a time interval between the current frame and a previous key frame. If the translation distance is not less than the translation distance threshold and the time interval is not less than the time interval threshold, the current frame is a key frame, and when the current frame is the key frame, the pose of the adjacent frame of the current frame, such as the next key frame, under the first coordinate system is determined.
S213, taking the pose relation between the pose of the current key frame under the first coordinate system and the pose of the adjacent key frame under the first coordinate system as an edge;
s214, determining the pose output by the inertial navigation system as a vertex when the intensity of the positioning signal is larger than a preset signal intensity threshold;
and S215, determining an optimization model by using the edges and the vertexes, determining a first target pose according to the optimization model, and adjusting the point cloud position of the current key frame by using the first target pose to obtain first target point cloud data.
Specifically, because accumulated errors exist in the long-time integration process of the odometer, the pose of the key frame can be globally optimized, and the accumulated errors are reduced. The pose relationship of the pose of the current frame under the first coordinate system and the pose of the next key frame under the first coordinate system can be used as edges, the pose output by the inertial navigation system is used as a vertex to determine an optimization model when the GPS positioning signal strength is good, namely the positioning signal strength is greater than the preset positioning signal strength, for example, a least square method is determined, and the result obtained by the optimization model is used as the more accurate pose of the current key frame.
S216, clustering the second point cloud data of the current frame to obtain a plurality of clusters.
S217, calculating the current point data and preset point data of each cluster in the plurality of clusters to obtain an operation result.
And S218, determining the current point data with the operation result larger than the operation threshold value as the surface characteristic point.
S219, determining the current point data with the operation result not larger than the operation threshold value as the line characteristic point.
S220, determining a sixth residual equation based on the line characteristic points, and determining a seventh residual equation based on the surface characteristic points.
S221, determining the initial pose of the current frame based on a sixth residual equation and a seventh residual equation.
S222, adjusting the point cloud position of the current frame under the first coordinate system according to the initial pose, and obtaining the adjusted current frame.
S223, determining an eighth residual equation based on the adjusted line characteristic points of the current frame and the line characteristic points of the local map.
S224, determining a ninth residual equation based on the adjusted surface feature points of the current frame and the surface feature points of the local map.
S225, determining the pose of the adjusted current frame under the first coordinate system according to the eighth residual equation and the ninth residual equation.
In the present embodiment, S216 to S215 are clustering the second point cloud data and extracting the feature points, and performing registration between frames, registration between frames and a local map, and the like according to the extracted feature points. The specific process is the same as the process of processing the first point cloud data, and will not be described in detail here.
S226, identifying whether the current frame is a current key frame, and determining a closed loop frame forming loop constraint with the current key frame; determining the pose of the closed-loop frame under a first coordinate system;
after classifying to obtain second point cloud data, clustering the second point cloud data of each frame to obtain a plurality of clusters, extracting line characteristics and surface characteristics of the point data of each cluster, registering frames and local maps according to the line characteristic points and the surface characteristic points, and identifying whether the current frame is a key frame or not by taking the current frame as an example after obtaining the pose of each frame under a first coordinate system collected under a GPS positioning signal weak or no-signal road, and if the current frame is the key frame, determining a closed-loop frame forming loop constraint with the current key frame and the pose of the closed-loop frame under the first coordinate system.
And S227, determining a fifth residual equation based on the pose relation between the pose of the current key frame under the first coordinate system and the pose of the closed-loop frame under the first coordinate system.
S228, determining the optimized pose of the current key frame under the first coordinate according to the fifth residual equation, and adjusting the point cloud position of the current key frame according to the optimized pose to obtain an adjusted current frame.
In this embodiment, a fifth residual equation is determined according to the pose relationship between the poses of the current key frame and the closed-loop frame under the first coordinate system, an optimal solution is determined according to the fifth residual equation as the optimized pose of the current key frame under the first coordinate system, and the point cloud position of the current key frame is adjusted based on the first optimized pose, so as to obtain the adjusted current frame.
And S229, performing pose optimization on the adjusted current frame by using a preset factor graph to obtain a second target pose, and adjusting the point cloud position of the current key frame by using the second target pose to obtain second target point cloud data.
The preset factor graph may be composed of radar mileage factors, inertial measurement unit integral factors, wheel speed meter factors, etc., and is not limited herein, specifically, for a road with weak or no GPS positioning signal, various factors may be constructed to constrain the error accumulation process, so as to improve the accuracy of graph construction. The pose of the adjusted current frame can be further optimized by constructing a factor graph, the pose of the adjusted current frame can be optimized by utilizing a preset factor graph, the offset error of the inertial measurement unit can be optimized, the offset error of the inertial measurement unit after optimization can continue to participate in the integration of the inertial measurement unit at the next time, the optimization process of the factor graph at the next time is further participated, and the accuracy of determining the pose of the current frame is improved.
S230, converting the first target point cloud data and the second target point cloud data into point cloud data under a second coordinate system, and obtaining the point cloud data under the second coordinate system.
And S231, performing splicing and sparsification processing on the point cloud data under the second coordinate system to obtain a point cloud map of the viaduct.
Specifically, after the first target point cloud data and the second target point cloud data are obtained, the first target point cloud data and the second target point cloud data are transferred to a second coordinate system according to the pose relation, then the point cloud data of each road of the viaduct under the second coordinate system are spliced, and if an overlapped area exists, the point cloud data can be manually moved by means of manpower, so that the point cloud data are in accordance with the actual situation. And meanwhile, sparse processing can be carried out on the point cloud data with excessive overlapping areas, so that a point cloud map of the viaduct is obtained. After the point cloud data of the viaduct are obtained, manual inspection and repair can be further performed, and the accuracy of the determined point cloud map is improved.
It can be appreciated that in this embodiment, the collected point cloud data of the overpass is classified according to the intensity of the positioning signal, so as to obtain the first point cloud data with good GPS positioning signal and the second point cloud data with weak or no GPS positioning signal. Registering frames and local maps according to the point cloud data of each frame to obtain an initial pose of each acquired frame under a first coordinate system; and (3) carrying out key frame identification on the current frame acquired by the road with good GPS positioning signals, if the current frame is a key frame, further determining the pose output by the inertial navigation system when the strength of the positioning signals is greater than a preset signal strength threshold value as a vertex to construct an optimization model by taking the pose relation between the current key frame and the adjacent key frame as a side, thereby improving the accuracy of the pose of the current frame under a first coordinate system and further improving the precision of image construction. And meanwhile, the identification of the key frame is carried out on the current frame acquired by the road with weak GPS positioning signal or no signal, if the current frame is the key frame, the pose of the current key frame is optimized through the closed-loop frame and the preset factor graph, so that the accuracy of the pose of the current frame under the first coordinate system is improved, and the precision of the graph construction is further improved. And (3) carrying out sparsification processing on the point cloud data under the second coordinate system, so that the established point cloud map of the viaduct is more reliable and accurate.
Fig. 3 is a schematic structural diagram of a point cloud map construction device according to an embodiment of the present invention, where, as shown in fig. 3, the device may specifically include:
the classification module 301 is configured to classify, according to intensity of a positioning signal of a viaduct, acquired point cloud data of the viaduct, to obtain first point cloud data and second point cloud data, where intensity of the positioning signal is higher when the first point cloud data is acquired than intensity of the positioning signal when the second point cloud data is acquired;
the pose adjustment module 302 is configured to identify a keyframe in the first point cloud data, optimize a pose of a current keyframe in a first coordinate system according to a pose of each keyframe in the first coordinate system to obtain a first target pose, and adjust a point cloud position of the current keyframe by using the first target pose to obtain first target point cloud data;
the pose adjustment module 302 is further configured to identify a keyframe in the second point cloud data and identify a closed-loop frame of each keyframe, optimize a pose of a current keyframe in the first coordinate system according to a pose of the closed-loop frame of the current keyframe in the first coordinate system, obtain a second target pose, and adjust a point cloud position of the current keyframe by using the second target pose to obtain second target point cloud data;
The map determining module 303 is configured to convert the first target point cloud data and the second target point cloud data into point cloud data in a second coordinate system, and obtain a point cloud map of the overpass.
In an embodiment, the point cloud map building device further includes a determining equation module, wherein the determining equation module is used for identifying key frames in the first point cloud data, optimizing the pose of the current key frame in the first coordinate system according to the pose of each key frame in the first coordinate system to obtain a first target pose, adjusting the point cloud position of the current key frame by using the first target pose, and classifying the first point cloud data before obtaining the first target point cloud data to determine line feature points and surface feature points of the current frame; determining a first residual equation based on the line feature points and a second residual equation based on the plane feature points; a first pose of the current frame is determined based on the first residual equation and the second residual equation.
In one embodiment, the classification module 301 is specifically configured to:
clustering the first point cloud data of the current frame to obtain a plurality of clusters;
calculating the current point data and preset point data of each cluster in the plurality of clusters to obtain an operation result;
Determining the current point data with the operation result larger than an operation threshold value as a surface characteristic point;
and determining the current point data with the operation result not larger than the operation threshold value as a line characteristic point.
In an embodiment, the determining equation module is specifically configured to, after determining the first pose of the current frame based on the first residual equation and the second residual equation:
according to the first pose, adjusting the point cloud position of the current frame under the first coordinate system to obtain an adjusted current frame;
determining a third residual equation based on the adjusted line feature points of the current frame and the line feature points of the local map;
determining a fourth residual equation based on the adjusted surface feature points of the current frame and the surface feature points of the local map;
and determining the pose of the adjusted current frame under a first coordinate system according to the third residual equation and the fourth residual equation.
In one embodiment, the pose adjustment module 302 is specifically configured to:
identifying whether the current frame is a current key frame or not, and determining the pose of an adjacent key frame of the current key frame under a first coordinate system;
taking the pose relation between the pose of the current key frame under the first coordinate system and the pose of the adjacent key frame under the first coordinate system as an edge;
Determining the pose output by the inertial navigation system as a vertex when the strength of the positioning signal is greater than a preset signal strength threshold;
and determining an optimization model by utilizing the edges and the vertexes, determining a first target pose according to the optimization model, and adjusting the point cloud position of the current key frame by utilizing the first target pose to obtain first target point cloud data.
In one embodiment, the pose adjustment module 302 is specifically configured to:
identifying whether the current frame is a current key frame or not, and determining a closed loop frame forming loop constraint with the current key frame; determining the pose of the closed-loop frame under the first coordinate system;
determining a fifth residual equation based on a pose relationship between the pose of the current key frame in the first coordinate system and the pose of the closed-loop frame in the first coordinate system;
determining an optimized pose of the current key frame under the first coordinate according to the fifth residual equation, and adjusting the point cloud position of the current key frame according to the optimized pose to obtain the adjusted current frame;
and performing pose optimization on the adjusted current frame by using a preset factor graph to obtain a second target pose, and adjusting the point cloud position of the current key frame by using the second target pose to obtain second target point cloud data.
In one embodiment, the map determining module 303 is specifically configured to:
converting the first target point cloud data and the second target point cloud data into point cloud data under a second coordinate system to obtain point cloud data under the second coordinate system;
and performing splicing and sparsification processing on the point cloud data under the second coordinate system to obtain the point cloud map of the viaduct.
In the device, the acquired point cloud data of the viaduct can be classified according to the intensity of the positioning signal of the viaduct to obtain the first point cloud data and the second point cloud data, wherein the intensity of the positioning signal is higher when the first point cloud data is acquired than when the second point cloud data is acquired; the method comprises the steps of identifying key frames in first point cloud data, optimizing the pose of a current key frame under a first coordinate system according to the pose of each key frame under the first coordinate system to obtain a first target pose, and adjusting the point cloud position of the current key frame by using the first target pose to obtain first target point cloud data; identifying key frames in the second point cloud data, identifying closed-loop frames of the key frames, optimizing the pose of the current key frame under the first coordinate system according to the pose of the closed-loop frame of the current key frame under the first coordinate system to obtain a second target pose, and adjusting the point cloud position of the current key frame by utilizing the second target pose to obtain second target point cloud data; and converting the first target point cloud data and the second target point cloud data into point cloud data under a second coordinate system to obtain a point cloud map of the overpass. According to the method, the acquired overpass data are classified, key frames of point cloud data of roads with good GPS are identified, and the pose of the current key frame under a first coordinate system is optimized according to the pose of each key frame under the first coordinate system. And identifying a key frame of point cloud data of the road with weak or no GPS signals, and optimizing the pose of the current frame under a first coordinate system by utilizing a closed-loop frame of the current key frame. According to the method, aiming at places with different GPS signal intensities, different modes are adopted to build the map, so that the accuracy of building the point cloud map at places with complex roads and unstable GPS signals is improved.
The embodiment of the invention also provides electronic equipment, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes the point cloud map construction method provided by any one of the embodiments when executing the program.
The embodiment of the invention also provides a computer readable medium, on which a computer program is stored, which when executed by a processor, implements the point cloud map construction method provided by any of the above embodiments.
Referring now to FIG. 4, there is illustrated a schematic diagram of a computer system 400 suitable for use in implementing the electronic device of the present invention. The electronic device shown in fig. 4 is only an example and should not impose any limitation on the functionality and scope of use of the present invention.
As shown in fig. 4, the computer system 400 includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. In the RAM403, various programs and data required for the operation of the computer system 400 are also stored. The CPU401, ROM 402, and RAM403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
The following components are connected to the I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output portion 407 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage section 408 including a hard disk or the like; and a communication section 409 including a network interface card such as a LAN card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. The drive 410 is also connected to the I/O interface 405 as needed. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.
In particular, according to embodiments of the present disclosure, the processes described above with reference to 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 shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 409 and/or installed from the removable medium 411. The above-described functions defined in the system of the present invention are performed when the computer program is executed by a Central Processing Unit (CPU) 401.
The computer readable medium shown in the present invention may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any 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 context of this document, 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, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. 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 flowcharts 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 and/or units described in the present invention may be implemented in software or in hardware. The described modules and/or units may also be provided in a processor, e.g., may be described as: a processor includes a determination classification module, an adjustment pose module, and a determination module. The names of these modules do not constitute a limitation on the module itself in some cases.
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 present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to include:
classifying the acquired point cloud data of the viaduct according to the intensity of the positioning signal of the viaduct to obtain first point cloud data and second point cloud data, wherein the intensity of the positioning signal is higher when the first point cloud data is acquired than that when the second point cloud data is acquired;
identifying key frames in the first point cloud data, optimizing the pose of the current key frame under a first coordinate system according to the pose of each key frame under the first coordinate system to obtain a first target pose, and adjusting the point cloud position of the current key frame by using the first target pose to obtain first target point cloud data;
identifying key frames in the second point cloud data, identifying closed-loop frames of the key frames, optimizing the pose of the current key frame under the first coordinate system according to the pose of the closed-loop frame of the current key frame under the first coordinate system to obtain a second target pose, and adjusting the point cloud position of the current key frame by utilizing the second target pose to obtain second target point cloud data;
And converting the first target point cloud data and the second target point cloud data into point cloud data under a second coordinate system to obtain a point cloud map of the overpass.
According to the scheme, the acquired point cloud data of the viaduct are classified according to the intensity of the locating signal of the viaduct to obtain first point cloud data and second point cloud data, and the intensity of the locating signal is higher when the first point cloud data is acquired than when the second point cloud data is acquired; the method comprises the steps of identifying key frames in first point cloud data, optimizing the pose of a current key frame under a first coordinate system according to the pose of each key frame under the first coordinate system to obtain a first target pose, and adjusting the point cloud position of the current key frame by using the first target pose to obtain first target point cloud data; identifying key frames in the second point cloud data, identifying closed-loop frames of the key frames, optimizing the pose of the current key frame under the first coordinate system according to the pose of the closed-loop frame of the current key frame under the first coordinate system to obtain a second target pose, and adjusting the point cloud position of the current key frame by utilizing the second target pose to obtain second target point cloud data; and converting the first target point cloud data and the second target point cloud data into point cloud data under a second coordinate system to obtain a point cloud map of the overpass. According to the method, the acquired overpass data are classified, key frames of point cloud data of roads with good GPS are identified, and the pose of the current key frame under a first coordinate system is optimized according to the pose of each key frame under the first coordinate system. And identifying a key frame of point cloud data of the road with weak or no GPS signals, and optimizing the pose of the current frame under a first coordinate system by utilizing a closed-loop frame of the current key frame. According to the method, aiming at places with different GPS signal intensities, different modes are adopted to build the map, so that the accuracy of building the point cloud map at places with complex roads and unstable GPS signals is improved.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
It should be noted that, in the technical solution of the present disclosure, the related aspects of collecting, updating, analyzing, processing, using, transmitting, storing, etc. of the personal information of the user all conform to the rules of the related laws and regulations, and are used for legal purposes without violating the public order colloquial. Necessary measures are taken for the personal information of the user, illegal access to the personal information data of the user is prevented, and the personal information security, network security and national security of the user are maintained.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method of point cloud map construction, the method comprising:
classifying the acquired point cloud data of the viaduct according to the intensity of the positioning signal of the viaduct to obtain first point cloud data and second point cloud data, wherein the intensity of the positioning signal is higher when the first point cloud data is acquired than that when the second point cloud data is acquired;
identifying key frames in the first point cloud data, optimizing the pose of the current key frame under a first coordinate system according to the pose of each key frame under the first coordinate system to obtain a first target pose, and adjusting the point cloud position of the current key frame by using the first target pose to obtain first target point cloud data;
identifying key frames in the second point cloud data, identifying closed-loop frames of the key frames, optimizing the pose of the current key frame under the first coordinate system according to the pose of the closed-loop frame of the current key frame under the first coordinate system to obtain a second target pose, and adjusting the point cloud position of the current key frame by utilizing the second target pose to obtain second target point cloud data;
and converting the first target point cloud data and the second target point cloud data into point cloud data under a second coordinate system to obtain a point cloud map of the overpass.
2. The method of claim 1, wherein the identifying key frames in the first point cloud data optimizes a pose of a current key frame in a first coordinate system according to a pose of each key frame in the first coordinate system to obtain a first target pose, and adjusts a point cloud position of the current key frame using the first target pose to obtain first target point cloud data, the method further comprising:
classifying the first point cloud data, and determining line characteristic points and surface characteristic points of the current frame;
determining a first residual equation based on the line feature points and a second residual equation based on the plane feature points;
a first pose of the current frame is determined based on the first residual equation and the second residual equation.
3. The method of claim 2, wherein classifying the first point cloud data to determine line feature points and surface feature points of a current frame comprises:
clustering the first point cloud data of the current frame to obtain a plurality of clusters;
calculating the current point data and preset point data of each cluster in the plurality of clusters to obtain an operation result;
Determining the current point data with the operation result larger than an operation threshold value as a surface characteristic point;
and determining the current point data with the operation result not larger than the operation threshold value as a line characteristic point.
4. The method of claim 2, wherein after the determining the first pose of the current frame based on the first residual equation and the second residual equation, the method further comprises:
according to the first pose, adjusting the point cloud position of the current frame under the first coordinate system to obtain an adjusted current frame;
determining a third residual equation based on the adjusted line feature points of the current frame and the line feature points of the local map;
determining a fourth residual equation based on the adjusted surface feature points of the current frame and the surface feature points of the local map;
and determining the pose of the adjusted current frame under a first coordinate system according to the third residual equation and the fourth residual equation.
5. The method of claim 1, wherein the identifying the key frames in the first point cloud data, optimizing the pose of the current key frame in the first coordinate system according to the pose of each key frame in the first coordinate system, obtaining a first target pose, and adjusting the point cloud position of the current key frame by using the first target pose, obtaining first target point cloud data, comprises:
Identifying whether the current frame is a current key frame or not, and determining the pose of an adjacent key frame of the current key frame under a first coordinate system;
taking the pose relation between the pose of the current key frame under the first coordinate system and the pose of the adjacent key frame under the first coordinate system as an edge;
determining the pose output by the inertial navigation system as a vertex when the strength of the positioning signal is greater than a preset signal strength threshold;
and determining an optimization model by utilizing the edges and the vertexes, determining a first target pose according to the optimization model, and adjusting the point cloud position of the current key frame by utilizing the first target pose to obtain first target point cloud data.
6. The method of claim 1, wherein the identifying the key frame in the second point cloud data and identifying the closed-loop frame of each key frame, optimizing the pose of the current key frame in the first coordinate system according to the pose of the closed-loop frame of the current key frame in the first coordinate system to obtain a second target pose, and adjusting the point cloud position of the current key frame using the second target pose to obtain second target point cloud data, comprises:
identifying whether the current frame is a current key frame or not, and determining a closed loop frame forming loop constraint with the current key frame; determining the pose of the closed-loop frame under the first coordinate system;
Determining a fifth residual equation based on a pose relationship between the pose of the current key frame in the first coordinate system and the pose of the closed-loop frame in the first coordinate system;
determining an optimized pose of the current key frame under the first coordinate according to the fifth residual equation, and adjusting the point cloud position of the current key frame according to the optimized pose to obtain the adjusted current frame;
and performing pose optimization on the adjusted current frame by using a preset factor graph to obtain a second target pose, and adjusting the point cloud position of the current key frame by using the second target pose to obtain second target point cloud data.
7. The method of claim 1, wherein the converting the first target point cloud data and the second target point cloud data into point cloud data in a second coordinate system, to obtain the overpass point cloud map, comprises:
converting the first target point cloud data and the second target point cloud data into point cloud data under a second coordinate system to obtain point cloud data under the second coordinate system;
and performing splicing and sparsification processing on the point cloud data under the second coordinate system to obtain the point cloud map of the viaduct.
8. A point cloud map construction apparatus, characterized in that the apparatus comprises:
the classification module is used for classifying the acquired point cloud data of the viaduct according to the intensity of the positioning signal of the viaduct to obtain first point cloud data and second point cloud data, wherein the intensity of the positioning signal is higher when the first point cloud data is acquired than when the second point cloud data is acquired;
the pose adjustment module is used for identifying key frames in the first point cloud data, optimizing the pose of the current key frame under the first coordinate system according to the pose of each key frame under the first coordinate system to obtain a first target pose, and adjusting the point cloud position of the current key frame by utilizing the first target pose to obtain first target point cloud data;
the position and pose module is further used for identifying key frames in the second point cloud data and identifying closed-loop frames of the key frames, optimizing the pose of the current key frame under the first coordinate system according to the pose of the closed-loop frame of the current key frame under the first coordinate system to obtain a second target pose, and adjusting the point cloud position of the current key frame by utilizing the second target pose to obtain second target point cloud data;
And the determining module is used for converting the first target point cloud data and the second target point cloud data into point cloud data under a second coordinate system to obtain a point cloud map of the overpass.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the point cloud mapping method according to any of claims 1 to 7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the point cloud map construction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311098177.5A CN117128950A (en) | 2023-08-29 | 2023-08-29 | Point cloud map construction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311098177.5A CN117128950A (en) | 2023-08-29 | 2023-08-29 | Point cloud map construction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117128950A true CN117128950A (en) | 2023-11-28 |
Family
ID=88857905
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311098177.5A Pending CN117128950A (en) | 2023-08-29 | 2023-08-29 | Point cloud map construction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117128950A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117475092A (en) * | 2023-12-27 | 2024-01-30 | 安徽蔚来智驾科技有限公司 | Pose optimization method, pose optimization equipment, intelligent equipment and medium |
-
2023
- 2023-08-29 CN CN202311098177.5A patent/CN117128950A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117475092A (en) * | 2023-12-27 | 2024-01-30 | 安徽蔚来智驾科技有限公司 | Pose optimization method, pose optimization equipment, intelligent equipment and medium |
| CN117475092B (en) * | 2023-12-27 | 2024-03-19 | 安徽蔚来智驾科技有限公司 | Pose optimization method, pose optimization equipment, intelligent equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111386559B (en) | Method and system for judging whether target road facilities exist at intersection or not | |
| CN106997466B (en) | Method and device for detecting road | |
| CN103093186A (en) | Systems and methods for improving image recognition | |
| CN117128950A (en) | Point cloud map construction method and device, electronic equipment and storage medium | |
| CN111461981A (en) | Error estimation method and device for point cloud splicing algorithm | |
| CN110163900B (en) | Method and device for adjusting point cloud data | |
| WO2019097422A2 (en) | Method and system for enhanced sensing capabilities for vehicles | |
| CN112487115A (en) | Method, device and equipment for determining pollution source and storage medium | |
| CN117633137A (en) | Map data analysis and extraction method and system based on deep learning | |
| CN112883236A (en) | Map updating method, map updating device, electronic equipment and storage medium | |
| CN117197639A (en) | True value acquisition method and device, electronic equipment and storage medium | |
| CN116091716A (en) | High-precision map automatic manufacturing system and method based on deep learning | |
| CN114136327B (en) | Automatic checking method and system for recall ratio of broken line segment | |
| CN107084728B (en) | Method and device for detecting digital map | |
| CN113450794B (en) | Navigation broadcasting detection method and device, electronic equipment and medium | |
| CN113111860B (en) | Road mobile source emission calculation method, device, equipment and medium | |
| CN114998863A (en) | Target road identification method, target road identification device, electronic equipment and storage medium | |
| CN115019511A (en) | Method and device for identifying illegal lane change of motor vehicle based on automatic driving vehicle | |
| Sharma et al. | Deep Learning-Based Object Detection and Classification for Autonomous Vehicles in Different Weather Scenarios of Quebec, Canada | |
| CN112434644A (en) | Vehicle image processing method and device, electronic equipment and storage medium | |
| CN112001738A (en) | Method for constructing multi-factor logistics product price model and application method thereof | |
| CN116007638B (en) | Vehicle track map matching method and device, electronic equipment and vehicle | |
| CN115512336B (en) | Vehicle positioning method and device based on street lamp light source and electronic equipment | |
| CN114427876B (en) | Automatic checking method and system for association relation of traffic sign | |
| CN116976539B (en) | Route layout optimization method, device and equipment based on traffic noise |
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 |