CN112767545A - Point cloud map construction method, device, equipment and computer storage medium - Google Patents
Point cloud map construction method, device, equipment and computer storage medium Download PDFInfo
- Publication number
- CN112767545A CN112767545A CN202110066842.7A CN202110066842A CN112767545A CN 112767545 A CN112767545 A CN 112767545A CN 202110066842 A CN202110066842 A CN 202110066842A CN 112767545 A CN112767545 A CN 112767545A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- track
- preset
- constraint condition
- closed
- 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
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Graphics (AREA)
- Navigation (AREA)
Abstract
The invention discloses a point cloud map construction method, a point cloud map construction device, point cloud map construction equipment and a computer storage medium. The point cloud map construction method comprises the following steps: acquiring a first point cloud track corresponding to a target moment and state information of a positioning signal at the target moment; when the state information is in a first state, carrying out closed-loop detection on the first point cloud track according to a preset first closed-loop detection algorithm to generate a first track constraint condition corresponding to the first point cloud track; and generating a point cloud map based on the first track constraint condition and the first point cloud track. According to the embodiment of the invention, the robustness of closed loop detection can be improved, the accumulated error is effectively reduced, and the point cloud map with the global consistency is quickly constructed.
Description
Technical Field
The invention belongs to the technical field of high-precision maps, and particularly relates to a point cloud map construction method, a point cloud map construction device, point cloud map construction equipment and a computer storage medium.
Background
With the development of vehicle automatic driving technology, automatic driving of vehicles on open roads often requires reference to vehicle automatic driving in combination with high-precision maps. For example, the high-precision map can be used for unmanned path planning, and can also be applied to unmanned positioning and the like.
The point cloud map is a very important map layer of a high-precision map, And is constructed mainly according to laser synchronous positioning And map construction (SLAM). In the running process of the laser SLAM, ideally, the position and the attitude of a vehicle at the same place are the same, but because the sensor has errors caused by noise and measurement, accumulated errors are more and more, the position and the attitude of the vehicle are greatly different even if the vehicle returns to the same place which passes through before, so that the track of the vehicle cannot form a closed loop, and a point cloud map with the global consistency cannot be effectively constructed.
Disclosure of Invention
The embodiment of the invention provides a point cloud map construction method, a point cloud map construction device, point cloud map construction equipment and a computer storage medium, which can improve the robustness of closed loop detection, effectively reduce accumulated errors and realize rapid construction of a point cloud map with global consistency.
In a first aspect, an embodiment of the present invention provides a point cloud map construction method, where the method includes:
acquiring a first point cloud track corresponding to a target moment and state information of a positioning signal at the target moment;
when the state information is in a first state, performing closed-loop detection on a first point cloud track according to a preset first closed-loop detection algorithm to generate a first track constraint condition corresponding to the first point cloud track;
and generating a point cloud map based on the first track constraint condition and the first point cloud track.
In some implementations of the first aspect, the first closed-loop detection algorithm is preset to be a Scan Context algorithm.
In some implementations of the first aspect, generating the point cloud map based on the first trajectory constraint and the first point cloud trajectory includes:
determining a first number of first track constraint conditions in a preset first time period, wherein the first preset time period is a time period before a target moment;
when the first number is larger than a preset first threshold value, correcting the first point cloud track corresponding to the first track constraint condition according to each first track constraint condition to obtain a corrected first point cloud track set;
and generating a point cloud map according to the corrected first point cloud track set.
In some implementations of the first aspect, when the state information is the second state, the method further includes:
performing closed-loop detection on the first point cloud track according to preset second closed-loop detection to generate a second track constraint condition corresponding to the first point cloud track;
determining a first number of first trajectory constraints within a preset first time period, comprising:
determining the sum of a first track constraint condition and a second track constraint condition in a preset first time period to obtain a first quantity;
when the first number is greater than a preset first threshold, modifying the first point cloud trajectory corresponding to the first trajectory constraint condition according to each first trajectory constraint condition to obtain a modified first point cloud trajectory set, including:
and correcting the first point cloud track corresponding to the first track constraint condition and the first point cloud track corresponding to the second track constraint condition according to each first track constraint condition to obtain a corrected first point cloud track set.
In some implementation manners of the first aspect, before obtaining the first point cloud trajectory corresponding to the target time, the method further includes:
acquiring a first point cloud data set in a preset first time period;
and generating a first point cloud track based on the first preset point cloud registration algorithm and a first point cloud data set in a preset first time period.
In some implementation manners of the first aspect, performing closed-loop detection on the first point cloud trajectory according to a preset first closed-loop detection algorithm to generate a first trajectory constraint condition corresponding to the first point cloud trajectory, including:
obtaining a descriptor of second point cloud data of a target moment;
determining a first preset number of third point cloud data with the similarity meeting a preset third threshold value with the second point cloud data from the first point cloud data set according to the descriptor of the second point cloud data and a preset K-dimensional retrieval tree of the first point cloud data set;
determining third point cloud data matched with the second point cloud data in the first preset number of third point cloud data according to a second preset point cloud registration algorithm to obtain fourth point cloud data;
and generating a first track constraint condition according to the second point cloud data and the fourth point cloud data.
In some implementation manners of the first aspect, before obtaining the first point cloud track corresponding to the target time and the state information of the positioning signal at the target time, the method further includes:
within a second preset time period, respectively carrying out closed-loop detection on the second point cloud track according to a preset first closed-loop detection algorithm and a preset second closed-loop detection algorithm to obtain a first detection result and a second detection result, wherein the second preset time period is a time period before the first preset time period;
and determining a preset first threshold according to the first detection result and the second point detection result.
In a second aspect, an embodiment of the present invention provides a point cloud map building apparatus, where the apparatus includes:
the acquisition module is used for acquiring a first point cloud track corresponding to the target moment and state information of a positioning signal at the target moment;
the detection module is used for carrying out closed-loop detection on the first point cloud track according to a preset first closed-loop detection algorithm when the state information is in a first state, and generating a first track constraint condition corresponding to the first point cloud track;
and the map generation module is used for generating a point cloud map based on the first track constraint condition and the first point cloud track.
In a third aspect, the present invention provides a point cloud map construction apparatus, comprising: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the point cloud map construction method of the first aspect or any of the realizable manners of the first aspect.
In a fourth aspect, the present invention provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method for constructing a point cloud map according to the first aspect or any one of the realizable manners of the first aspect is implemented.
The embodiment of the invention provides a point cloud map construction method, wherein when a first point cloud track is subjected to closed-loop detection, an algorithm for the closed-loop detection is determined according to state information of a positioning signal, especially when the state information of the positioning signal is the first state information, a Scan Context closed-loop detection algorithm is adopted to generate a first track constraint condition, and the condition that the robustness is low due to the fact that the same closed-loop detection algorithm is adopted in different states and the precision is low or even the closed-loop detection algorithm cannot be used is avoided; and then, generating a point cloud map based on the first track constraint condition and the first point cloud track, improving the overall robustness of the closed loop detection process, eliminating accumulated errors and quickly constructing the point cloud map with the global consistency.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
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 schematic structural diagram of a point cloud map building apparatus 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.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
With the development of vehicle automatic driving technology, automatic driving of vehicles on open roads often requires reference to vehicle automatic driving in combination with high-precision maps. For example, the high-precision map can be used for unmanned path planning, and can also be applied to unmanned positioning and the like.
The point cloud map is a very important map layer of a high-precision map, And is constructed mainly according to laser synchronous positioning And map construction (SLAM). In the running process of the laser SLAM, closed-loop detection needs to be carried out on the obtained track, ideally, the position and the attitude of the vehicle at the same place are the same, but due to the fact that the sensor has errors caused by noise and measurement, accumulated errors are more and more, even if the vehicle returns to the same place where the vehicle passes before, the obtained position and the attitude are greatly different, the track of the vehicle cannot form a closed loop, and therefore a point cloud map which is globally consistent cannot be effectively constructed. For example, closed-loop detection based on a satellite positioning system is possible, but the closed-loop detection based on the satellite positioning system is not only costly, but also has the problems of low precision and even no usability in some occlusion scenes, and therefore, the closed-loop detection based on the satellite positioning system has the disadvantage of relatively low robustness.
In order to solve the problems in the prior art, the embodiment of the invention provides a point cloud map construction method, in the point cloud map construction process, a closed loop detection method currently used for closed loop detection is determined by judging state information of a positioning signal, closed loop detection is carried out by using the closed loop detection method with high confidence level, and corresponding track constraint conditions are generated, so that the overall robustness of the closed loop detection process is improved, accumulated errors are eliminated, and a point cloud map with the same overall situation is quickly constructed.
The point cloud map construction method provided by the embodiment of the invention is introduced below. Fig. 1 is a schematic flow chart illustrating a point cloud map construction method according to an embodiment of the present invention. As shown in fig. 1, the method may include S110-S130:
s110, acquiring a first point cloud track corresponding to the target time and state information of the positioning signal at the target time.
In some embodiments, point cloud data may be acquired in real-time by a lidar, each of which may include three-dimensional coordinates, reflection Intensity information (Intensity), and the like. The laser radar can be installed on movable equipment such as automobiles and robots.
The laser radar can continuously acquire point cloud data, and in some embodiments, a first point cloud data set in a preset first time period is acquired; and then, generating a first point cloud track based on a first preset point cloud registration algorithm and a first point cloud data set in a preset first time period.
For example, when the vehicle moves, the laser radar acquires point cloud data through continuous acquisition, and the motion track of the vehicle can be tracked. The preset Point cloud registration algorithm may be, for example, an Iterative Closest Point (ICP) algorithm, a Normal Distribution Transform (NDT) algorithm, or the like.
For example, the first time period may be a target time and a time period before the target time, during which the lidar may collect multiple frames of point cloud data, thereby obtaining a first point data set. In the process of acquiring point cloud data by the laser radar, matching is performed on each frame of point cloud data acquired before the current frame through a preset point cloud registration algorithm based on the point cloud data acquired before the current frame, so that a first point cloud track can be generated, wherein the first point cloud data set comprises the point cloud data acquired before the current frame.
Due to the fact that the laser radar has measurement errors and calculation accuracy errors in combination with a registration algorithm, the errors are gradually accumulated along with the lapse of a time period, and a point cloud map with the same global situation is difficult to obtain. For example, when the accumulated error is larger and larger, even if a vehicle carrying the laser radar moves to the original position after moving for a certain route, the obtained movement track does not form a track closed loop, and therefore, in order to obtain a globally consistent point cloud map, in the process of obtaining the point cloud track, closed loop detection is performed to reduce the accumulated error, that is, a corresponding constraint condition is generated by identifying a scene that has passed through the past so as to reduce the accumulated error.
In some embodiments, to improve the accuracy of the closed-loop detection and avoid the occurrence of accumulated errors, the detection algorithm for the closed-loop detection may be determined in conjunction with the state of the positioning signal. Therefore, in embodiment S110 of the present invention, at the target time, in addition to acquiring the first point cloud track corresponding to the target time, it is also necessary to acquire the state information of the positioning signal at the target time.
The positioning signal may be a Global Navigation Satellite System (GNSS) based positioning signal, for example.
The state information of the positioning signal at the target moment can be judged by evaluating the number of satellites which can be observed at the target moment and the signal-to-noise ratio. When the state information is the first state, that is, the GNSS signal state is poor, it is difficult to obtain accurate closed-loop detection based on the GNSS signal, and thus S120 may be performed.
S120, performing closed-loop detection on the first point cloud track according to a preset first closed-loop detection algorithm, and generating a first track constraint condition corresponding to the first point cloud track.
In some embodiments, generating the first trajectory constraint may be, first, obtaining a descriptor of the second point cloud data at the target time.
The second point cloud data is point cloud data obtained at a target moment, and the point cloud data directly obtained by the laser radar is three-dimensional data. And acquiring a descriptor of the second point cloud data, namely, reducing the three-dimensional point cloud data into a two-dimensional matrix. Because of the noise existing in the laser radar measurement, in order to fully utilize the statistical characteristics of the laser radar measurement area, the average height or the average reflection intensity of the measured data of the laser radar in the measurement area can be calculated, so that the value of the two-dimensional matrix is the average height.
And then, according to the descriptor of the second point cloud data and a preset K-dimensional retrieval tree of the first point cloud data set, determining a first preset number of third point cloud data which have the similarity with the second point cloud data and meet a preset third threshold from the first point cloud data set.
Wherein the first point cloud data set is point cloud data before the target time. And adding the point cloud data to a preset K-dimensional retrieval tree every time the laser radar obtains one point cloud data. Determining a first predetermined amount of third point cloud data from the first point cloud data set may be enhanced by using a predetermined K-dimensional search tree of the first point cloud data set.
And then, according to a second preset point cloud registration algorithm, determining third point cloud data matched with the second point cloud data in the first preset number of third point cloud data to obtain fourth point cloud data.
When the second point cloud data is matched with the third point cloud data, the second point cloud data is subjected to feature extraction, and the three-dimensional data is set to be two-dimensional data, so that in order to improve the matching accuracy, the third point cloud data with a first preset number of similarity degrees meeting a preset third threshold value is determined for the second point cloud data. The first preset number may be a plurality, for example, five.
In the step, third point cloud data matched with the second point cloud data are determined from the plurality of third point cloud data through a second preset point cloud registration algorithm, and fourth point cloud data are obtained. Wherein the second preset point cloud registration algorithm may be, for example, an ICP registration algorithm.
After the fourth point cloud data is obtained, the next step may be performed next.
And finally, generating a first track constraint condition according to the second point cloud data and the fourth point cloud data.
In order to improve the precision and the calculation speed of the closed-loop detection, the preset first closed-loop detection algorithm may be a Scan Context algorithm.
After obtaining the first trajectory constraint and the first point cloud trajectory, S130 may be performed next.
And S130, generating a point cloud map based on the first track constraint condition and the first point cloud track.
In some embodiments, to reduce the computational burden and avoid redundant computation, a first number of first trajectory constraints within a preset first time period may be determined, where the first preset time period is a time period before the first time; when the first number is larger than a preset first threshold value, correcting the first point cloud track corresponding to the first track constraint condition according to each first track constraint condition to obtain a corrected first point cloud track set; and finally, generating a point cloud map according to the corrected first point cloud track set.
Further, in some embodiments, the positioning signals may be GNSS based positioning signals. And evaluating according to the number of the satellites observed at the target moment and the signal-to-noise ratio, and judging the state information of the positioning signal at the target moment. When the state information is in the second state, that is, the GNSS signal state is good, accurate closed-loop detection can be performed based on the GNSS signal. That is, when the state information of the positioning signal is in the second state, the closed loop detection may perform the following steps: firstly, carrying out closed-loop detection on a first point cloud track according to preset second closed-loop detection, and generating a second track constraint condition corresponding to the first point cloud track. Next, the sum of the first trajectory constraint condition and the second trajectory constraint condition within a preset first time period is determined to obtain a first number. And when the first quantity is larger than a preset first threshold value, correcting the first point cloud track corresponding to the first track constraint condition and the first point cloud track corresponding to the second track constraint condition according to each first track constraint condition to obtain a corrected first point cloud track set.
Therefore, in the embodiment S130 of the present invention, a point cloud map is generated according to the corrected first point cloud trajectory set, and a second constraint condition generated based on a GNSS may be further included to improve the overall robustness of the closed-loop detection process. Moreover, because various closed-loop detection algorithms can be fused, for example, when the closed-loop detection based on the GNSS has the problem that the shielding environment has large errors or even no signal, the Scan Context algorithm can be combined, and the robustness of the closed-loop detection is improved. Closed loop detection of a large scene can be realized, and accumulated errors can be effectively reduced.
In some embodiments, in order to reduce consumption of computing resources and improve accuracy of positioning detection, a preset first threshold may be set in advance as whether to modify the first point cloud trajectory based on the generated constraint condition.
Therefore, before acquiring the first point cloud track corresponding to the target time and the state information of the positioning signal at the target time, the method may further include the following steps: within a second preset time period, respectively carrying out closed-loop detection on the second point cloud track according to a preset first closed-loop detection algorithm and a preset second closed-loop detection algorithm to obtain a first detection result and a second detection result, wherein the second preset time period is a time period before the first preset time period; and determining a preset first threshold according to the first detection result and the second detection result.
For example, in a second preset time period, starting a GNSS and Scan Context detection closed loop and performing closed loop detection, for example, for a point cloud track obtained at the same time, when the GNSS state is good and a closed loop is detected, but the Scan Context does not detect a closed loop, a preset first threshold may be increased; similarly, for the point cloud tracks obtained at the same moment, when the closed loop is not detected by the GNSS and the closed loop is detected by the Scan Context, the preset first threshold value may be reduced to improve the detection accuracy of the closed loop detection process.
According to the point cloud map construction method, after the first point cloud track is obtained, when the first point cloud track is subjected to closed-loop detection, an algorithm for closed-loop detection next is determined according to the state information of the positioning signal, especially when the state information of the positioning signal is the first state information, a Scan Context closed-loop detection algorithm is adopted to generate a first track constraint condition, and the situation that the robustness is low due to the fact that the positioning signal is in different states and the same closed-loop detection algorithm is adopted when the positioning signal is low in precision and even cannot be used is avoided; and then, generating the point cloud map based on the first track constraint condition and the first point cloud track, improving the overall robustness of the closed loop detection process, eliminating accumulated errors and quickly constructing the point cloud map with the global consistency.
Fig. 2 is a schematic structural diagram of a point cloud mapping apparatus according to an embodiment of the present invention, and as shown in fig. 2, the point cloud mapping apparatus 200 may include: an acquisition module 210, a detection module 220, and a map generation module 230.
The obtaining module 210 is configured to obtain a first point cloud track corresponding to a target time and state information of a positioning signal at the target time;
the detection module 220 is configured to perform closed-loop detection on the first point cloud trajectory according to a preset first closed-loop detection algorithm when the state information is in the first state, and generate a first trajectory constraint condition corresponding to the first point cloud trajectory;
and a map generating module 230, configured to generate a point cloud map based on the first trajectory constraint and the first point cloud trajectory.
In some embodiments, the first closed-loop detection algorithm is preset to be a Scan Context algorithm.
In some embodiments, the map generation module 230 is further configured to determine a first number of first trajectory constraints within a preset first time period, where the first preset time period is a time period before the target time; when the first number is larger than a preset first threshold value, correcting the first point cloud track corresponding to the first track constraint condition according to each first track constraint condition to obtain a corrected first point cloud track set; and generating a point cloud map according to the corrected first point cloud track set.
In some embodiments, the map generating module 230 is further configured to perform closed-loop detection on the first point cloud trajectory according to a preset second closed-loop detection, and generate a second trajectory constraint condition corresponding to the first point cloud trajectory; determining the sum of a first track constraint condition and a second track constraint condition in a preset first time period to obtain a first quantity; and correcting the first point cloud track corresponding to the first track constraint condition and the first point cloud track corresponding to the second track constraint condition according to each first track constraint condition to obtain a corrected first point cloud track set.
In some embodiments, the obtaining module 210 is further configured to obtain a first point cloud data set within a preset first time period; and generating a first point cloud track based on the first preset point cloud registration algorithm and a first point cloud data set in a preset first time period.
In some embodiments, the detection module 220 is further configured to obtain a descriptor of the second point cloud data at the target time; determining a first preset number of third point cloud data with the similarity meeting a preset third threshold value with the second point cloud data from the first point cloud data set according to the descriptor of the second point cloud data and a preset K-dimensional retrieval tree of the first point cloud data set; determining third point cloud data matched with the second point cloud data in the first preset number of third point cloud data according to a second preset point cloud registration algorithm to obtain fourth point cloud data; and generating a first track constraint condition according to the second point cloud data and the fourth point cloud data.
In some embodiments, the point cloud map construction apparatus 200 may further include a threshold generation module, configured to perform closed-loop detection on the second point cloud trajectory according to a preset first closed-loop detection algorithm and a preset second closed-loop detection algorithm within a second preset time period, to obtain a first detection result and a second detection result, where the second preset time period is a time period before the first preset time period; and determining a preset first threshold according to the first detection result and the second point detection result.
It can be understood that the point cloud map construction apparatus 200 according to the embodiment of the present invention may correspond to an execution main body of the point cloud map construction method according to the embodiment of the present invention, and specific details of operations and/or functions of each module/unit of the point cloud map construction apparatus 200 may refer to the description of the corresponding part in the point cloud map construction method according to the embodiment of the present invention, which is not described herein again for brevity.
According to the point cloud map construction device, after the first point cloud track is obtained, when the first point cloud track is subjected to closed-loop detection, an algorithm for closed-loop detection next is determined according to the state information of the positioning signal, especially when the state information of the positioning signal is the first state information, a Scan Context closed-loop detection algorithm is adopted to generate a first track constraint condition, and the situation that due to the fact that the positioning signal is in different states, when the same closed-loop detection algorithm is adopted, the accuracy is low and even the closed-loop detection algorithm cannot be used, the robustness is low is avoided; and then, generating a point cloud map based on the first track constraint condition and the first point cloud track, improving the overall robustness of the closed loop detection process, eliminating accumulated errors and quickly constructing the point cloud map with the global consistency.
Fig. 3 is a schematic diagram of a hardware structure of a point cloud map building apparatus according to an embodiment of the present invention.
As shown in fig. 3, the point cloud map building apparatus 300 in the present embodiment includes an input apparatus 301, an input interface 302, a central processor 303, a memory 304, an output interface 305, and an output apparatus 306. The input interface 302, the central processing unit 303, the memory 304, and the output interface 305 are connected to each other through a bus 310, and the input device 301 and the output device 306 are connected to the bus 310 through the input interface 302 and the output interface 305, respectively, and further connected to other components of the point cloud map construction device 300.
Specifically, the input device 301 receives input information from the outside and transmits the input information to the central processor 303 through the input interface 302; central processor 303 processes the input information based on computer-executable instructions stored in memory 304 to generate output information, stores the output information temporarily or permanently in memory 304, and then transmits the output information to output device 306 through output interface 305; the output device 306 outputs the output information to the outside of the point cloud map building device 300 for use by the user.
That is, the point cloud map building apparatus shown in fig. 3 may also be implemented to include: a memory storing computer-executable instructions; and a processor that, when executing computer executable instructions, may implement the point cloud mapping method described in connection with the example shown in fig. 1.
In one embodiment, the point cloud mapping apparatus 300 shown in fig. 3 includes: a memory 304 for storing programs; the processor 303 is configured to execute a program stored in the memory to execute the point cloud map construction method provided by the embodiment of the present invention.
An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium has computer program instructions stored thereon; the computer program instructions, when executed by the processor, implement the point cloud map construction method provided by the embodiments of the invention.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic Circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor Memory devices, Read-Only memories (ROMs), flash memories, Erasable Read-Only memories (EROMs), floppy disks, Compact disk Read-Only memories (CD-ROMs), optical disks, hard disks, optical fiber media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
Aspects of the present disclosure are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As described above, only the specific embodiments of the present invention are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.
Claims (10)
1. A point cloud map construction method, the method comprising:
acquiring a first point cloud track corresponding to a target moment and state information of a positioning signal at the target moment;
when the state information is in a first state, performing closed-loop detection on the first point cloud track according to a preset first closed-loop detection algorithm to generate a first track constraint condition corresponding to the first point cloud track;
generating the point cloud map based on the first trajectory constraint and the first point cloud trajectory.
2. The method of claim 1, wherein the default first closed-loop detection algorithm is a Scan Context algorithm.
3. The method of claim 1 or 2, wherein the generating the point cloud map based on the first trajectory constraint and the first point cloud trajectory comprises:
determining a first number of the first trajectory constraints within a preset first time period, wherein the first preset time period is a time period before the target time;
when the first number is larger than a preset first threshold value, correcting a first point cloud track corresponding to the first track constraint condition according to each first track constraint condition to obtain a corrected first point cloud track set;
and generating the point cloud map according to the corrected first point cloud track set.
4. The method of claim 3, wherein when the state information is the second state, the method further comprises:
performing closed-loop detection on the first point cloud track according to preset second closed-loop detection to generate a second track constraint condition corresponding to the first point cloud track;
the determining the first number of the first trajectory constraints within the preset first time period includes:
determining the sum of the first track constraint condition and the second track constraint condition in the preset first time period to obtain a first quantity;
when the first number is greater than a preset first threshold, modifying the first point cloud trajectory corresponding to the first trajectory constraint condition according to each first trajectory constraint condition to obtain a modified first point cloud trajectory set, including:
and correcting the first point cloud track corresponding to the first track constraint condition and the first point cloud track corresponding to the second track constraint condition according to each first track constraint condition to obtain the corrected first point cloud track set.
5. The method of claim 1, wherein before obtaining the first point cloud trajectory corresponding to the target time, the method further comprises:
acquiring a first point cloud data set in the preset first time period;
and generating the first point cloud track based on a first preset point cloud registration algorithm and a first point cloud data set in the preset first time period.
6. The method according to claim 1, wherein the performing closed-loop detection on the first point cloud trajectory according to a preset first closed-loop detection algorithm to generate a first trajectory constraint condition corresponding to the first point cloud trajectory comprises:
obtaining a descriptor of second point cloud data of a target moment;
determining a first preset number of third point cloud data with the similarity meeting a preset third threshold value with the second point cloud data from the first point cloud data set according to the descriptor of the second point cloud data and the preset K-dimensional retrieval tree of the first point cloud data set;
determining third point cloud data matched with the second point cloud data in the first preset number of third point cloud data according to a second preset point cloud registration algorithm to obtain fourth point cloud data;
and generating the first track constraint condition according to the second point cloud data and the fourth point cloud data.
7. The method according to claim 4, wherein before the obtaining the state information of the first point cloud track corresponding to the target time and the positioning signal at the target time, the method further comprises:
within a second preset time period, respectively carrying out closed-loop detection on a second point cloud track according to the preset first closed-loop detection algorithm and the preset second closed-loop detection algorithm to obtain a first detection result and a second detection result, wherein the second preset time period is a time period before the first preset time period;
and determining the preset first threshold according to the first detection result and the second point measurement result.
8. A point cloud mapping apparatus, the apparatus comprising:
the acquisition module is used for acquiring a first point cloud track corresponding to the target moment and state information of a positioning signal at the target moment;
the detection module is used for carrying out closed-loop detection on the first point cloud track according to a preset first closed-loop detection algorithm when the state information is in a first state, and generating a first track constraint condition corresponding to the first point cloud track;
and the map generation module is used for generating the point cloud map based on the first track constraint condition and the first point cloud track.
9. A point cloud mapping apparatus, the apparatus comprising: a processor, and a memory storing computer program instructions;
the processor reads and executes the computer program instructions to implement the point cloud mapping method of any of claims 1-7.
10. A computer storage medium having stored thereon computer program instructions which, when executed by a processor, implement the point cloud mapping method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110066842.7A CN112767545A (en) | 2021-01-19 | 2021-01-19 | Point cloud map construction method, device, equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110066842.7A CN112767545A (en) | 2021-01-19 | 2021-01-19 | Point cloud map construction method, device, equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112767545A true CN112767545A (en) | 2021-05-07 |
Family
ID=75702983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110066842.7A Pending CN112767545A (en) | 2021-01-19 | 2021-01-19 | Point cloud map construction method, device, equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112767545A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113485346A (en) * | 2021-07-15 | 2021-10-08 | 上海交通大学 | Autonomous navigation method of mobile robot in nuclear accident complex environment |
| CN116030134A (en) * | 2023-02-14 | 2023-04-28 | 长沙智能驾驶研究院有限公司 | Positioning method, apparatus, device, readable storage medium and program product |
| CN118053153A (en) * | 2024-04-16 | 2024-05-17 | 之江实验室 | Point cloud data identification method and device, storage medium and electronic equipment |
-
2021
- 2021-01-19 CN CN202110066842.7A patent/CN112767545A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113485346A (en) * | 2021-07-15 | 2021-10-08 | 上海交通大学 | Autonomous navigation method of mobile robot in nuclear accident complex environment |
| CN113485346B (en) * | 2021-07-15 | 2022-07-22 | 上海交通大学 | Autonomous navigation method of mobile robot in nuclear accident complex environment |
| CN116030134A (en) * | 2023-02-14 | 2023-04-28 | 长沙智能驾驶研究院有限公司 | Positioning method, apparatus, device, readable storage medium and program product |
| CN118053153A (en) * | 2024-04-16 | 2024-05-17 | 之江实验室 | Point cloud data identification method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7179110B2 (en) | Positioning method, device, computing device, computer-readable storage medium and computer program | |
| JP6760114B2 (en) | Information processing equipment, data management equipment, data management systems, methods, and programs | |
| US8838374B2 (en) | Automatic correction of past position errors for location and inventory tracking | |
| CN112113574B (en) | Method, apparatus, computing device and computer-readable storage medium for positioning | |
| EP2400270B9 (en) | Track information generating device, track information generating method, and computer-readable storage medium | |
| US12005907B2 (en) | Method for determining position data and/or motion data of a vehicle | |
| CN110900602B (en) | Positioning recovery method and device, robot and storage medium | |
| CN110889808A (en) | Positioning method, device, equipment and storage medium | |
| CN112817026A (en) | Method, device and equipment for determining pose of moving object and storage medium | |
| JP6302848B2 (en) | Map generation system and map generation method | |
| CN114111774B (en) | Vehicle positioning method, system, equipment and computer readable storage medium | |
| CN111915675B (en) | Particle drift-based particle filtering point cloud positioning method, device and system thereof | |
| CN112767545A (en) | Point cloud map construction method, device, equipment and computer storage medium | |
| US20220075074A1 (en) | Obstacle detection device and obstacle detection method | |
| CN114111775B (en) | Multi-sensor fusion positioning method and device, storage medium and electronic equipment | |
| CN113721248B (en) | Fusion positioning method and system based on multi-source heterogeneous sensor | |
| KR20210111181A (en) | Method, apparatus, device and medium for detecting environmental change | |
| CN112700479A (en) | Registration method based on CNN point cloud target detection | |
| CN115375870B (en) | Loop detection optimization method, electronic equipment and computer readable storage device | |
| US20230417931A1 (en) | Method for real-time position estimate correction of a movable object | |
| CN115077541A (en) | Positioning method and device for automatic driving vehicle, electronic equipment and storage medium | |
| CN112362044A (en) | Indoor positioning method, device, equipment and system | |
| CN114264301A (en) | Vehicle-mounted multi-sensor fusion positioning method and device, chip and terminal | |
| CN115390086A (en) | Fusion positioning method and device for automatic driving, electronic equipment and storage medium | |
| CN110986966A (en) | Automatic driving positioning method and system for long-distance tunnel |
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 |