CN115265577B - Topological relation construction method, system and moving tool based on Voronoi diagram - Google Patents
Topological relation construction method, system and moving tool based on Voronoi diagram Download PDFInfo
- Publication number
- CN115265577B CN115265577B CN202211205646.4A CN202211205646A CN115265577B CN 115265577 B CN115265577 B CN 115265577B CN 202211205646 A CN202211205646 A CN 202211205646A CN 115265577 B CN115265577 B CN 115265577B
- Authority
- CN
- China
- Prior art keywords
- data
- voronoi
- distance
- current
- pixel point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- 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
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- 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
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30172—Centreline of tubular or elongated structure
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Instructional Devices (AREA)
Abstract
The embodiment of the invention relates to the technical field of automatic driving, in particular to a topological relation construction method, a topological relation construction system and a moving tool based on a Voronoi diagram, wherein the topological relation construction method comprises the following steps: carrying out binarization processing on the map according to the passable and impassable attributes to obtain binarization matrix data; performing distance transformation processing on the binarization matrix data to obtain a distance transformation graph; processing the distance transformation graph to obtain Veno skeleton data; and determining a Voronoi point from the Voronoi skeleton data, and constructing a topological relation of the passable area according to the Voronoi point. The method provided by the invention is simple in principle and easy to implement, and meets the technical requirement of the unmanned vehicle on the planning of the operation scene path, so that the adaptability of the unmanned vehicle to the unstructured road environment is improved.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a topological relation construction method and system based on a voronoi diagram and a mobile tool.
Background
The automatic driving technology is a hot topic in recent years, and the automatic driving brings subversive changes in the fields of relieving traffic jam, improving road safety, reducing air pollution and the like. As the process of autodrive commercialization continues to advance, two different commercial directions develop: passenger cars under structured roads and low-speed unmanned vehicles under unstructured roads.
In two commercialization directions, low-speed unmanned sweeper vehicles, unmanned express delivery vehicles and the like under unstructured roads provide substantial application scenarios for commercialization landing of automatic driving technologies. In an unstructured road, the automatic driving path is unreasonable in planning, the road traffic capacity and the vehicle obstacle avoidance capacity are directly affected, and the operation efficiency, the quality, the user experience and the like of the unmanned vehicle are reduced. Therefore, how to plan a high-quality obstacle avoidance path is very important. The path planning method based on the topological relation has high efficiency and path optimality, and is widely applied to path planning of unmanned vehicles.
At present, the topological relation construction methods which are applied in the automatic driving industry are a topological relation construction method based on the driving situation of a lane and a topological relation construction method based on random sampling points.
Firstly, under the condition of following traffic rules, setting lane driving situation and a change critical line by using lane separation lines, ground printed marks, vehicle length, vehicle dynamic characteristics and the like on a road; secondly, generating a lane-level passable interval set (lane area) according to the lane driving situation and the change critical line; and finally, constructing a lane-level topological relation of the passable areas from the connection relation among the lane areas. However, the topological relation construction method based on the lane driving situation is only applicable to the structured road, and under the unstructured road, the lane driving situation and the change critical line cannot be constructed, so that a complete passable area topological relation cannot be constructed.
Firstly, setting a plurality of random sampling points in a vehicle passable area, and ensuring that any sampling point is not collided with an obstacle; secondly, searching K adjacent sampling points for each sampling point according to a KNN (K-Nearest Neighbor) algorithm and establishing connection; and finally, constructing a topological relation of the passable area according to the connection relation of each sampling point.
The topological relation construction method based on random sampling points can lead to unreasonable distribution if the sampling points are too few or too many; if the parameters in the KNN algorithm are not properly set, the generated topological relation is unreasonable or too complex; if the passable area is too narrow or dense obstacles exist in the area, the effect of random sampling is not good, so that the topological relation is lost.
Therefore, the efficient, low-consumption and complete topological relation construction method is the premise of guaranteeing high obstacle avoidance capacity and efficient and safe operation of the automatic driving vehicle.
Disclosure of Invention
The invention aims to provide a topological relation construction method based on a Voronoi diagram aiming at the defects in the prior art, and can provide a reliable theoretical basis for path planning of movable equipment.
In order to achieve the above object, in a first aspect of the present invention, a topological relation construction method based on a voronoi diagram is provided, where the method includes:
carrying out binarization processing on the map according to the passable and impassable attributes to obtain binarization matrix data;
performing distance transformation processing on the binarization matrix data to obtain a distance transformation graph;
processing the distance transformation graph to obtain Voronoi skeleton data;
and determining a Veno point from the Veno skeleton data, and constructing a topological relation of the passable area according to the Veno point.
In a second aspect of the present invention, a topological relation construction system based on a voronoi diagram is provided, including:
the map processing module is used for carrying out binarization processing on a map according to the passable and impassable attributes to obtain binarization matrix data;
the distance transformation module is used for carrying out distance transformation processing on the binarization matrix data to obtain a distance transformation graph;
the voronoi skeleton data generation module is used for processing the distance transformation graph to obtain voronoi skeleton data;
and the topological relation construction module is used for determining a Vono point from the Vono skeleton data and constructing the topological relation of the passable area according to the Vono point.
In a third aspect of the present invention, a chip system is provided, which includes a processor, the processor is coupled to a memory, the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the method for constructing a topological relation according to any one of the first aspect is implemented.
In a fourth aspect of the present invention, there is provided a computer server comprising: a memory, a processor, and a transceiver;
the processor is configured to be coupled with the memory, read and execute instructions in the memory, so as to implement the topological relation construction method according to any one of the first aspect;
the transceiver is coupled to the processor, and the processor controls the transceiver to transmit and receive messages.
In a fifth aspect of the present invention, there is provided a computer-readable storage medium, which includes a program or an instruction, and when the program or the instruction runs on a computer, the topological relation construction method according to any one of the above first aspects is implemented.
In a sixth aspect of the present invention, there is provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the topological relation construction method of any one of the above first aspects.
In a seventh aspect of the invention, a mobile tool is provided, comprising the computer server of the fourth aspect.
According to the topological relation construction method based on the Voronoi diagram, the map is processed to obtain the binary matrix data, then the distance transformation processing is carried out on the binary matrix data to obtain the Voronoi skeleton data, the Voronoi skeleton data is further optimized and screened to obtain the Voronoi points, and finally the topological relation of the operation environment is constructed according to the Voronoi points, so that the topological relation construction efficiency is improved, the principle is simple and easy to realize, the technical requirement of the unmanned vehicle on the operation scene path planning is met, and the adaptability of the unmanned vehicle to the unstructured road environment is improved.
Drawings
Fig. 1 is a flowchart of a topology relationship construction method based on a voronoi diagram according to an embodiment of the present invention;
fig. 2 is a second flowchart of a topology relationship construction method based on a voronoi diagram according to a first embodiment of the present invention;
fig. 3 is a third flowchart of a topology relationship construction method based on a voronoi diagram according to a first embodiment of the present invention;
fig. 4 is a fourth flowchart of a topology relationship construction method based on a voronoi diagram according to an embodiment of the present invention;
fig. 5 is a fifth flowchart of a topology relationship construction method based on a voronoi diagram according to a first embodiment of the present invention;
fig. 6 is a sixth flowchart of a topology relationship construction method based on a voronoi diagram according to an embodiment of the present invention;
fig. 7 is a schematic diagram of voronoi skeleton data processed in an application scenario according to an embodiment of the present invention;
FIG. 8 is a schematic illustration of a resulting Veno point determined based on the Veno skeleton data shown in FIG. 7;
FIG. 9 is a schematic view of a passable area topological relation established based on the Veno point shown in FIG. 8;
fig. 10 is a seventh flowchart of a topology relationship construction method based on a voronoi diagram according to an embodiment of the present invention;
fig. 11 is a block diagram of a topology relationship building system based on a voronoi diagram according to a second embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
The topological relation construction method based on the Veno diagram provided by the embodiment of the invention is applied to the field of automatic driving, and can meet the technical requirement of an unmanned vehicle on the planning of the operation scene path of an unstructured road, thereby improving the adaptability of the unmanned vehicle to the unstructured road.
The main execution unit in the present application is a terminal, a server, or a processor having a computing function in a device. In one example, when the method is applied to an unmanned Vehicle, the execution subject of the method is an unmanned Vehicle Control Unit (AVCU), i.e., a central processing Unit of the unmanned Vehicle, which corresponds to the "brain" of the unmanned Vehicle.
Example one
Fig. 1 is a flowchart of a topological relation construction method based on a voronoi diagram, and as shown in fig. 1, the present application includes the following steps:
and 110, carrying out binarization processing on the map according to the passable and impassable attributes to obtain binarization matrix data.
First, a map of the mobile device operating environment is obtained.
The operation environment comprises a structured road and an unstructured road. The map may be a grid map or a high-precision semantic map. In this example, the map is explained by taking a high-precision semantic map as an example.
Secondly, preprocessing the map to obtain binary matrix data of the operation environment of the movable equipment.
Specifically, according to a high-precision semantic map protocol, a map of the operating environment is converted into two regional attributes of a passable region and a non-passable region, namely the map of the operating environment is converted into a binary image. The impassable area can be understood as an obstacle area or an off-map area of the operating environment. In one specific example, the accessible area is represented by 1 and the non-accessible area is represented by 0.
And step 120, performing distance transformation processing on the binarization matrix data to obtain a distance transformation graph.
The process of the distance conversion processing is specifically performed by the steps as shown in fig. 2:
In one example, the preset first traversal rule refers to performing a "Z" type traversal starting from the top left corner of the image for the pixel points in the binarized matrix data. The first direction can be understood as the upper position of each pixel point. The second direction can be understood as the left position of each pixel point. The traversal only completes the distance data of the upstream pixel point and the front row pixel point of the current pixel point. The distance data can be understood as the closest distance of the pixel point from the image boundary.
And step 122, generating first distance data of the current pixel point according to the distance data of the first direction pixel point and the distance data of the second direction pixel point, and updating the first distance data into the distance data of the current pixel point.
Specifically, first, the distance data of the first direction pixel points and the distance data of the second direction pixel points are compared, and the smaller distance data of the first direction pixel points and the second direction pixel points is obtained. And secondly, adding the smaller distance data with a preset threshold value to obtain first distance data of the current pixel point. For example and without limitation, for convenience of calculation, the preset threshold is represented by k, and the value may be 1.
And step 123, traversing the pixel points in the distance transformation graph according to a preset second traversal rule, and acquiring distance data of the third-direction pixel points and distance data of the fourth-direction pixel points of the current pixel points.
In one example, the preset second traversal rule refers to performing a "Z" type reverse traversal on the binarized matrix data from the lower right corner of the image. I.e. the second traversal rule and the first traversal rule are traversed in the opposite order. The third direction can be understood as the lower position of each pixel point. The fourth direction can be understood as the right position of each pixel point. The traversal completes the distance data of the downlink pixel point and the subsequent pixel point of the current pixel point.
The specific implementation process of this step is similar to that of step 122, but the direction is different, and is not described herein again.
And step 130, processing the distance transformation graph to obtain the Voronoi skeleton data.
Specifically, the pixels in the distance transformation graph are traversed, if the distance data of the surrounding pixels of the current pixel is not larger than the distance data of the current pixel, the position data of the current pixel is recorded, and the current pixel is determined to be the voronoi skeleton data.
After obtaining the voronoi skeleton data, the application further includes the steps as shown in fig. 3:
Specifically, the preset fifth direction may be understood as N grid directions around the current voronoi skeleton data, and eight directions around each candidate voronoi skeleton point, i.e., up, down, left, right, left-up, left-down, right-up, and right-down, are specifically selected in this example. The preset sixth direction may be understood as a cross direction of the non-voronoi skeleton data corresponding to the current voronoi skeleton data, that is, up, down, left, and right.
And 132, processing the current voronoi skeleton data according to the first quantity and the second quantity.
Specifically, if the first number and the second number meet a preset first condition or the distribution of peripheral voronoi skeleton data of the current voronoi skeleton data meets a preset second condition, the current voronoi skeleton data is retained; if the first quantity and the second quantity meet a preset third condition, determining the current voronoi skeleton data as undetermined data to be judged next time; and if the first quantity and the second quantity do not meet the preset first condition or third condition and the current Weino framework data do not meet the second condition, rejecting the current Weino framework data.
In a specific example, the first number is represented by M, and 0 < M < 8. The second quantity is represented by N, 0 ≦ N ≦ 4.
By way of example and not limitation, the preset first condition is: m <3 and N =1.
The preset second condition is as follows: the distribution of peripheral voronoi skeleton data of the current voronoi skeleton data meets the condition that a horizontal shape or a vertical shape in a preset sixth direction exists, or angular lattice points (upper, lower, left and right) in a preset fifth direction are not voronoi skeleton data but the peripheral points of the angular lattice points are voronoi skeleton data.
The preset third condition is as follows: m ≧ 5 and N ≧ 3.
By executing the steps, refinement of the Voronoi skeleton data is completed.
Further, before traversing the voronoi skeleton data, the voronoi skeleton data is preferably supplemented. As shown in fig. 4, specifically includes:
step S1, traversal iteration is carried out on the Voronoi skeleton data, and whether non-Voronoi skeleton data exist in a preset fifth direction around the current Voronoi skeleton data or not is judged. If yes, go to step S2, otherwise go to step 131.
And S2, judging whether all the preset sixth directions of the non-voronoi skeleton data are voronoi skeleton data. If so, step S3 is executed, otherwise, step 131 is executed, that is, the obtained voronoi skeleton data is directly traversed.
And S3, supplementing the non-voronoi skeleton data into voronoi skeleton data.
The candidate Weino framework data are supplemented through the steps, the phenomenon that individual candidate Weino framework data are mistakenly taken or mistakenly taken as non-candidate Weino framework data due to the defects of the algorithm can be overcome, and accordingly the candidate Weino framework data are missing is caused, namely the method cannot lack real Weino framework data due to the limitation of the algorithm, and therefore the integrity of the Weino framework is guaranteed.
As a preferable scheme, after the voronoi skeleton data is supplemented and refined, the voronoi skeleton data is also optimized in the application.
As shown in fig. 5 in particular:
and step 133, acquiring nodes with branches according to the refined candidate voronoi skeleton data.
Here, the node having a branch may be understood as a plurality of voronoi skeleton data existing around the current voronoi skeleton data. For example, the number of the plurality may be specifically 3 or more.
And 135, optimizing the refined Voronoi skeleton data according to the branch length.
The process is specifically executed by the following steps:
first, the branch length is compared to a preset length threshold.
And secondly, when the branch length is smaller than a preset length threshold value, removing all the voronoi skeleton data on the branch to obtain optimized voronoi skeleton data. Namely, all the Weino framework data on the branches are removed from the refined Weino framework data, the cutting of the invalid branches is completed, and the optimized Weino framework data is obtained.
And 140, determining a Veno point from the Veno skeleton data, and constructing a topological relation of the passable area according to the Veno point.
The black dots as in fig. 7 are the voronoi skeleton data, and this step may be specifically performed by the sub-steps as shown in fig. 6.
The voronoi skeleton data may be specifically supplemented and optimized voronoi skeleton data, or may be voronoi skeleton data directly obtained in step 130.
The judgment method is as shown in figure 10,
The branch node can be understood as that a plurality of candidate voronoi skeleton data exist around the current voronoi skeleton data. For example, the number of the plurality may be specifically 3 or more. The absence of a branch node may be understood as the first node being in a straight line or the branch where the first node is located having been deleted.
And step 1412, traversing the branch nodes, traversing the Veno skeleton data by utilizing a preset extension mode and recording the extension times.
In this example, the preset extending mode is specifically extending by using a cross shape.
Specifically, the triangular dots shown in fig. 8 are voronoi dots. Fig. 9 shows a constructed topological relation (i.e., voronoi diagram), in which a black line represents a connecting line between two voronoi points, i.e., a voronoi edge.
And step 143, removing the current voronoi skeleton data.
According to the topological relation construction method based on the Voronoi diagram, the map is processed to obtain the binary matrix data, then the distance transformation processing is carried out on the binary matrix data to obtain the Voronoi skeleton data, the Voronoi skeleton data is further optimized and screened to obtain the Voronoi points, and finally the topological relation of the operation environment is constructed according to the Voronoi points, so that the topological relation construction efficiency is improved, the principle is simple and easy to realize, the technical requirement of the unmanned vehicle on the operation scene path planning is met, and the adaptability of the unmanned vehicle to the unstructured road environment is improved.
Example two
Fig. 11 is a topological relation constructing system based on a voronoi diagram according to a second embodiment of the present invention, including:
the map processing module 10 is used for carrying out binarization processing on the map according to the passable and impassable attributes to obtain binarization matrix data;
a distance transformation module 20, configured to perform distance transformation processing on the binarized matrix data to obtain a distance transformation map;
the voronoi skeleton data generation module 30 is configured to process the distance transformation map to obtain voronoi skeleton data;
and the topological relation construction module 40 is used for determining a voronoi point from the voronoi skeleton data and constructing the topological relation of the passable area according to the voronoi point.
The topological relation construction system based on the voronoi diagram provided by the second embodiment of the present invention can execute the method steps in the above method embodiments, where the map processing module 10 implements step 110, the distance transformation module 20 implements step 120, the voronoi skeleton data generation module 30 implements step 130, and the topological relation construction module 40 implements step 140.
The specific implementation principle and technical effect are similar, and are not described in detail herein.
It should be noted that the division of each module of the above apparatus is only a logical division, and all or part of the actual implementation may be integrated into one physical entity or may be physically separated. And these modules can all be implemented in the form of software invoked by a processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the determining module may be a processing element separately set up, or may be integrated into a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and a processing element of the apparatus calls and executes the function of the determining module. The other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.
For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), etc. For another example, when some of the above modules are implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor that can call the program code. As another example, these modules may be integrated together and implemented in the form of a System-on-a-chip (SOC).
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, bluetooth, microwave, etc.) means.
EXAMPLE III
A third embodiment of the present invention provides a chip system, which includes a processor, where the processor is coupled to a memory, where the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the method for constructing a topological relation according to any one of the foregoing embodiments is implemented.
Example four
An embodiment of the present invention provides a computer server, including: a memory, a processor, and a transceiver;
the processor is configured to be coupled to the memory, read and execute the instructions in the memory, so as to implement the topological relation construction method according to any one of the above embodiments;
the transceiver is coupled to the processor, and the processor controls the transceiver to transmit and receive messages.
EXAMPLE five
An embodiment of the present invention provides a computer-readable storage medium, which includes a program or an instruction, and when the program or the instruction runs on a computer, the topology relation construction method according to any one of the above embodiments is implemented.
Example six
An embodiment of the present invention provides a computer program product including instructions, which, when the computer program product runs on a computer, causes the computer to execute the topological relation construction method according to any one of the above embodiments.
EXAMPLE seven
The seventh embodiment of the present invention provides a mobile tool, which includes the computer server described in the fourth embodiment.
The moving tool may be any tool that can be moved, for example, a Vehicle (e.g., a floor-cleaning Vehicle, a vacuum cleaner, a sweeper, a logistics Vehicle, a passenger Vehicle, a bus, a van, a truck, a trailer, a dump truck, a crane, an excavator, a scraper, a road train, a sweeper, a sprinkler, a garbage truck, an engineering truck, a rescue Vehicle, a logistics car, an Automatic Guided Vehicle (AGV), etc.), a motorcycle, a bicycle, a tricycle, a cart, a robot, a sweeper, a balance car, etc., and the type of the moving tool is not strictly limited in the present application, and is not exhaustive.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM drive train control method, or any other form of storage medium known in the art.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (12)
1. A topological relation construction method based on a Voronoi diagram is characterized by comprising the following steps:
carrying out binarization processing on the map according to the passable and impassable attributes to obtain binarization matrix data;
performing distance transformation processing on the binarization matrix data to obtain a distance transformation graph;
processing the distance transformation graph to obtain Voronoi skeleton data;
determining a Veno point from the Veno skeleton data, and constructing a topological relation of a passable area according to the Veno point;
the distance transformation processing on the binarization matrix data specifically comprises the following steps:
traversing the pixels in the binarization matrix data according to a preset first traversal rule, and acquiring distance data of the first direction pixels and distance data of the second direction pixels of the current pixels; generating first distance data of the current pixel point according to the distance data of the first direction pixel point and the distance data of the second direction pixel point, and updating the first distance data into the distance data of the current pixel point;
traversing the pixel points in the distance transformation graph according to a preset second traversal rule, and acquiring distance data of a third-direction pixel point and distance data of a fourth-direction pixel point of the current pixel point; generating second distance data of the current pixel point according to the distance data of the third-direction pixel point and the distance data of the fourth-direction pixel point, and updating the second distance data into the distance data of the current pixel point; obtaining an optimized distance transformation graph according to the distance transformation graph; wherein the second traversal rule and the first traversal rule have opposite traversal orders.
2. The voronoi diagram-based topological relation construction method according to claim 1, wherein the distance transformation diagram is processed to obtain voronoi skeleton data, and specifically comprises:
and traversing the pixel points in the distance transformation graph, recording the position data of the current pixel point if the distance data of the surrounding pixel points of the current pixel point is not more than the distance data of the current pixel point, and determining the current pixel point as the Voronoi skeleton data.
3. The voronoi diagram-based topological relation construction method according to claim 2, further comprising, after obtaining voronoi skeleton data:
traversing the Voronoi skeleton data, and counting a first quantity of Voronoi skeleton data contained in the current Voronoi skeleton data in a preset fifth direction and a second quantity of Voronoi skeleton data contained in a preset sixth direction; and processing the current Voronoi skeleton data according to the first quantity and the second quantity.
4. The voronoi diagram-based topological relation construction method according to claim 3, wherein before traversing voronoi skeleton data, the method further comprises: optimizing the Weino skeleton data;
optimizing the voronoi skeleton data, specifically comprising:
traversing and iterating the voronoi skeleton data, and judging whether non-voronoi skeleton data exists in a preset fifth direction around the current voronoi skeleton data or not; if yes, judging whether all the preset sixth directions of the non-voronoi skeleton data are voronoi skeleton data; and if so, supplementing the non-voronoi skeleton data into voronoi skeleton data.
5. The voronoi diagram-based topological relation construction method according to claim 3, wherein processing the current voronoi skeleton data according to the first number and the second number specifically includes:
if the first quantity and the second quantity meet a preset first condition or the distribution of the peripheral Weino framework data of the current Weino framework data meets a preset second condition, the current Weino framework data is reserved;
if the first quantity and the second quantity meet a preset third condition, determining the current voronoi skeleton data as undetermined data to be judged next time;
and if the first quantity and the second quantity do not meet the preset first condition or third condition and the current Weino framework data do not meet the second condition, rejecting the current Weino framework data.
6. The voronoi diagram-based topological relation construction method according to claim 1, wherein voronoi points are determined from voronoi skeleton data, and a topological relation of passable areas is constructed according to the voronoi points, specifically comprising:
traversing the voronoi skeleton data, judging whether the current voronoi skeleton data meets a preset fourth condition, recording the current voronoi skeleton data as voronoi points if the current voronoi skeleton data meets the preset fourth condition, and recording the connection relationship between the current voronoi points and the previous voronoi points as voronoi edges; thereby forming the topological relation of the passable area.
7. The voronoi diagram-based topological relation construction method according to claim 6, wherein traversing voronoi skeleton data, and judging whether current voronoi skeleton data meets a preset fourth condition, specifically comprises:
traversing the Weino skeleton data, obtaining branch nodes, and setting the first Weino skeleton data as branch points if no branch node exists;
traversing branch nodes, traversing the Voronoi skeleton data by using a preset extension mode and recording the extension times; and if the extension times of the current Weino framework data are not less than a preset time threshold value, or the current Weino framework data are branch nodes, or the current Weino framework data cannot continue to be extended, determining that the current Weino framework data meet a preset fourth condition.
8. A topological relation construction system based on a Voronoi diagram is characterized by comprising the following steps:
the map processing module is used for carrying out binarization processing on the map according to the passable and impassable attributes to obtain binarization matrix data;
the distance transformation module is used for carrying out distance transformation processing on the binarization matrix data to obtain a distance transformation graph;
the voronoi skeleton data generation module is used for processing the distance transformation graph to obtain voronoi skeleton data;
the topological relation construction module is used for determining a Veno point from the Veno skeleton data and constructing a topological relation of a passable area according to the Veno point;
the distance transformation module is specifically used for traversing the pixel points in the binarization matrix data according to a preset first traversal rule, and obtaining distance data of the first direction pixel points and distance data of the second direction pixel points of the current pixel points; generating first distance data of the current pixel point according to the distance data of the first direction pixel point and the distance data of the second direction pixel point, and updating the first distance data into the distance data of the current pixel point;
traversing the pixel points in the distance transformation graph according to a preset second traversal rule, and acquiring distance data of a third-direction pixel point and distance data of a fourth-direction pixel point of the current pixel point; generating second distance data of the current pixel point according to the distance data of the third-direction pixel point and the distance data of the fourth-direction pixel point, and updating the second distance data into the distance data of the current pixel point; obtaining an optimized distance transformation graph according to the distance transformation graph; wherein the second traversal rule and the first traversal rule have opposite traversal orders.
9. A chip system, comprising a processor coupled with a memory, wherein the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the method for constructing the voronoi diagram-based topology relation according to any one of claims 1 to 7 is implemented.
10. A computer server, comprising: a memory, a processor, and a transceiver;
the processor is used for being coupled with the memory, reading and executing instructions in the memory so as to realize the topological relation construction method based on the Voronoi diagram in any one of claims 1 to 7;
the transceiver is coupled to the processor, and the processor controls the transceiver to transmit and receive messages.
11. A computer-readable storage medium, comprising a program or instructions for implementing the voronoi diagram-based topological relation construction method according to any one of claims 1 to 7 when the program or instructions are run on a computer.
12. A mobile tool comprising the computer server of claim 10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211205646.4A CN115265577B (en) | 2022-09-30 | 2022-09-30 | Topological relation construction method, system and moving tool based on Voronoi diagram |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211205646.4A CN115265577B (en) | 2022-09-30 | 2022-09-30 | Topological relation construction method, system and moving tool based on Voronoi diagram |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115265577A CN115265577A (en) | 2022-11-01 |
CN115265577B true CN115265577B (en) | 2023-02-10 |
Family
ID=83758142
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211205646.4A Active CN115265577B (en) | 2022-09-30 | 2022-09-30 | Topological relation construction method, system and moving tool based on Voronoi diagram |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115265577B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103837154A (en) * | 2014-03-14 | 2014-06-04 | 北京工商大学 | Path planning method and system |
CN106651821A (en) * | 2016-11-25 | 2017-05-10 | 北京邮电大学 | Topological map fusion method based on secondary moment maintenance propagation algorithm and topological map fusion system thereof |
CN106682787A (en) * | 2017-01-09 | 2017-05-17 | 北京航空航天大学 | Method for quickly generating generalized Voronoi diagram based on wavefront algorithm |
CN108664022A (en) * | 2018-04-27 | 2018-10-16 | 湘潭大学 | A kind of robot path planning method and system based on topological map |
CN110703747A (en) * | 2019-10-09 | 2020-01-17 | 武汉大学 | Robot autonomous exploration method based on simplified generalized Voronoi diagram |
CN113536837A (en) * | 2020-04-15 | 2021-10-22 | 杭州萤石软件有限公司 | Region division method and device for indoor scene |
CN115063548A (en) * | 2022-06-15 | 2022-09-16 | 东南大学 | Incremental Voronoi network construction method |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013228701A (en) * | 2012-03-28 | 2013-11-07 | Giken Shoji International Co Ltd | Map mesh data generation system and mesh data generation method |
CN109213169A (en) * | 2018-09-20 | 2019-01-15 | 湖南万为智能机器人技术有限公司 | The paths planning method of mobile robot |
-
2022
- 2022-09-30 CN CN202211205646.4A patent/CN115265577B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103837154A (en) * | 2014-03-14 | 2014-06-04 | 北京工商大学 | Path planning method and system |
CN106651821A (en) * | 2016-11-25 | 2017-05-10 | 北京邮电大学 | Topological map fusion method based on secondary moment maintenance propagation algorithm and topological map fusion system thereof |
CN106682787A (en) * | 2017-01-09 | 2017-05-17 | 北京航空航天大学 | Method for quickly generating generalized Voronoi diagram based on wavefront algorithm |
CN108664022A (en) * | 2018-04-27 | 2018-10-16 | 湘潭大学 | A kind of robot path planning method and system based on topological map |
CN110703747A (en) * | 2019-10-09 | 2020-01-17 | 武汉大学 | Robot autonomous exploration method based on simplified generalized Voronoi diagram |
CN113536837A (en) * | 2020-04-15 | 2021-10-22 | 杭州萤石软件有限公司 | Region division method and device for indoor scene |
CN115063548A (en) * | 2022-06-15 | 2022-09-16 | 东南大学 | Incremental Voronoi network construction method |
Non-Patent Citations (2)
Title |
---|
Sören Schwertfeger,et al..Evaluation of map quality by matching and scoring high-level, topological map structures.《2013 IEEE International Conference on Robotics and Automation》.2013, * |
基于栅格地图的分层式机器人路径规划算法;余等;《中国科学院大学学报》;20130715(第04期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN115265577A (en) | 2022-11-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11709058B2 (en) | Path planning method and device and mobile device | |
CN108519605B (en) | Road edge detection method based on laser radar and camera | |
CN108519094B (en) | Local path planning method and cloud processing terminal | |
CN108256577B (en) | Obstacle clustering method based on multi-line laser radar | |
CN107703945A (en) | A kind of intelligent farm machinery paths planning method of multiple targets fusion | |
CN114111825B (en) | Path planning method, path planning device, electronic equipment, engineering machinery and storage medium | |
CN110954122A (en) | Automatic driving track generation method under high-speed scene | |
WO2024149060A1 (en) | Free space and road edge detection method and apparatus, and related device | |
CN111295666A (en) | Lane line detection method, device, control equipment and storage medium | |
CN112513876B (en) | Road surface extraction method and device for map | |
WO2023155580A1 (en) | Object recognition method and apparatus | |
CN117227755A (en) | Automatic driving decision method and system based on reinforcement learning under complex traffic scene | |
CN115082888A (en) | Lane line detection method and device | |
CN115265577B (en) | Topological relation construction method, system and moving tool based on Voronoi diagram | |
CN114092909A (en) | Lane line extraction method and device, vehicle and storage medium | |
CN113297939A (en) | Obstacle detection method, system, terminal device and storage medium | |
CN113256595A (en) | Map creation method, map creation device, map creation equipment and computer storage medium | |
CN109683613A (en) | It is a kind of for determining the method and apparatus of the ancillary control information of vehicle | |
CN112733934B (en) | Multi-mode feature fusion road scene semantic segmentation method in complex environment | |
CN115525943A (en) | Method and system for constructing three-dimensional road model based on bus line topological relation | |
CN117761721A (en) | Passable area detection method, passable area detection device and moving tool | |
CN114021334A (en) | Traffic flow simulation method and system based on data driving and user editing | |
CN117664128A (en) | Scheduling path generation method, generation device, robot, and storage medium | |
CN117576948A (en) | Intersection motor vehicle flow multi-mode conflict risk identification method considering queue characteristics | |
Hu | Application and Development Research of Artificial Intelligence Technology in the Field of Transportation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |