CN114694106A - Extraction method and device of road detection area, computer equipment and storage medium - Google Patents
Extraction method and device of road detection area, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114694106A CN114694106A CN202011595392.2A CN202011595392A CN114694106A CN 114694106 A CN114694106 A CN 114694106A CN 202011595392 A CN202011595392 A CN 202011595392A CN 114694106 A CN114694106 A CN 114694106A
- Authority
- CN
- China
- Prior art keywords
- grid
- point cloud
- road
- effective
- data
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 238000000605 extraction Methods 0.000 title claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000006243 chemical reaction Methods 0.000 claims description 74
- 238000000034 method Methods 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 29
- 238000001914 filtration Methods 0.000 claims description 18
- 230000008859 change Effects 0.000 claims description 15
- 230000009466 transformation Effects 0.000 claims description 11
- 238000005070 sampling Methods 0.000 abstract description 5
- 238000003708 edge detection Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The application relates to a road detection area extraction method, a road detection area extraction device, computer equipment and a storage medium, wherein the acquired point cloud is subjected to rasterization processing after being converted into a rectangular coordinate system, so that the point cloud collection is subjected to downsampling. And fitting based on the down-sampling result to obtain the road boundary. The scheme of the embodiment can quickly realize boundary identification and is insensitive to the number of point clouds. Therefore, the requirement of road surface edge detection on point cloud acquisition equipment can be reduced.
Description
Technical Field
The present application relates to the field of intelligent transportation technologies, and in particular, to a method and an apparatus for extracting a road detection area, a computer device, and a storage medium.
Background
In unmanned driving, the boundary position of a road determines the range within which an unmanned vehicle can run, so that the accurate positioning of the boundary line of the road is an important task in the unmanned automatic driving, and the unmanned vehicle cannot go beyond the boundary line which cannot be driven only by accurately identifying the boundary of the road. In addition, in the target detection system, the road boundary can limit the search area, so that unnecessary interference is reduced, the calculation amount is reduced, and the detection accuracy is obviously improved.
The most commonly used information for roadside identification is image data collected by a camera, but the image is easily affected by uneven illumination, road shadow and the like, and is difficult to apply at night.
The laser radar is not affected by the outside such as illumination, shadow, not only can normally work under the severe weather condition, but also has wide detection range, long measurement distance and high measurement precision, thereby being widely used in the field of road boundary detection.
Although the three-dimensional laser radar has high data acquisition speed, dense point cloud and rich scene targets, the acquired data has mass characteristics, the conventional method has long processing time and cannot meet the real-time requirement, and meanwhile, the road boundary information is often shielded by vehicles to cause the condition that the boundary information is lost and cannot be detected.
Disclosure of Invention
In view of the above, it is necessary to provide a road detection area extraction method, apparatus, computer device, and storage medium that can solve the above-mentioned problems.
A road detection area extraction method comprises the following steps:
carrying out coordinate change on the acquired point cloud data collected by the laser radar to obtain conversion data under a space rectangular coordinate system with the laser radar as an origin;
projecting the conversion data onto a two-dimensional grid map set in a preset detection range to obtain an effective grid; fitting the effective grid to obtain a grid expression result; the grid expression result comprises a boundary grid and/or a lane grid;
and determining the boundary of the road based on the point cloud data corresponding to the grid expression result.
As an optional implementation manner, coordinate transformation is performed on the acquired point cloud data collected by the laser radar to obtain conversion data in a spatial rectangular coordinate system with the laser radar as an origin, including:
carrying out coordinate change on the acquired point cloud data acquired by the laser radar to obtain initial conversion data;
and carrying out point cloud filtering processing on the initial conversion data to obtain the conversion data.
As an optional implementation manner, performing point cloud filtering processing on the initial conversion data to obtain the conversion data includes:
and filtering initial conversion point cloud data corresponding to the ground point and/or filtering initial point cloud data with the height value larger than a preset threshold value to obtain the conversion data.
As an optional implementation manner, the obtaining of initial conversion data by performing coordinate change on the point cloud data acquired by the acquired vehicle-mounted laser radar includes:
setting the obtained current position of the laser radar as the origin of coordinates of a space rectangular coordinate system;
and converting the point cloud data in the point cloud data into data under a space rectangular coordinate system based on the scanning angle of the laser point in the point cloud data, and initially converting the data.
As an optional implementation manner, the projecting the conversion data onto a two-dimensional grid map established within a preset detection range to obtain an effective grid includes:
performing projection processing on the conversion data under the space rectangular coordinate system on the two-dimensional grid map according to a space position;
judging whether projected conversion data exists on each grid in the two-dimensional grid map;
if so, the grid in which the projection transformation data exists is determined to be an effective grid.
As an optional implementation, the method further comprises:
acquiring the times that the effective grid becomes a road boundary grid within a preset time period by combining historical information;
if the times are larger than a preset threshold value, increasing the fitting weight of the effective grid; the fitting weights are used for the fitting operation.
As an optional implementation, the method further comprises:
and if the times are smaller than a preset threshold value, reducing the fitting weight of the effective grid.
As an optional implementation, the fitting the effective grid to obtain a grid expression result includes:
and taking the row sequence number and the column sequence number of the effective grid as input of fitting operation, and executing curve or straight line fitting operation on the effective grid to obtain a road grid and/or lane grid.
As an optional implementation, before taking the row sequence number and the column sequence number of the effective grid as the input of the fitting operation, and performing a curve and straight line fitting operation on the effective grid, the method further includes:
dividing the effective grid into a first effective grid and a second effective grid according to the spatial position of the effective grid;
respectively performing curve or straight line fitting operation on the first effective grid and the second effective grid to obtain a first road grid and a second road grid;
taking a grid between the first road boundary and the second road boundary as the lane grid.
An extraction device of a road detection area, the device comprising:
the coordinate conversion module is used for carrying out coordinate change on the acquired point cloud data collected by the vehicle-mounted laser radar so as to obtain conversion data under a space rectangular coordinate system with the laser radar as an origin;
the fitting module is used for projecting the conversion data onto a two-dimensional grid map set in a preset detection range to obtain an effective grid; fitting the effective grid to obtain a grid expression result; the grid expression result comprises a boundary grid and/or a lane grid;
and the output module is used for determining the boundary of the road based on the position information of the point cloud data corresponding to the grid expression result.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method in the embodiments of the present application when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method in the embodiments of the application.
According to the method, the device, the computer equipment and the storage medium for extracting the road detection area, the acquired point cloud is converted into the rectangular coordinate system and then subjected to rasterization processing, so that the point cloud collection is subjected to down-sampling. And fitting based on the down-sampling result to obtain the road boundary. The scheme of the embodiment can quickly realize boundary identification and is insensitive to the number of point clouds. Therefore, the requirement of road surface edge detection on point cloud acquisition equipment can be reduced.
Drawings
FIG. 1 is a diagram illustrating an exemplary embodiment of a method for extracting a road detection area;
FIG. 2 is a schematic view of a laser radar mounted on a vehicle head for performing a local scan according to an embodiment;
FIG. 3 is a schematic diagram of a 360-degree omni-directional scanning scenario of a lidar mounted on a roof of a vehicle in one embodiment;
FIG. 4 is a schematic diagram of a transformation of point cloud data to a spatial rectangular coordinate system according to an embodiment;
FIG. 5 is a diagram showing the expression result in one example;
FIG. 6 is a schematic representation of a road boundary in one embodiment;
FIG. 7 is a schematic flow chart of the refinement step of step S110 in one embodiment;
FIG. 8 is a schematic flow chart of the refinement step of step S120 in one embodiment;
FIG. 9 is a block diagram showing an example of a configuration of an apparatus for extracting a road detection area;
FIG. 10 is a diagram showing an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In one embodiment, as shown in fig. 1, a method for extracting a road detection area is provided, which is described by taking a roadside device as an example, and includes the following steps:
and 110, carrying out coordinate change on the acquired point cloud data acquired by the laser radar to obtain conversion data under a space rectangular coordinate system with the laser radar as an origin.
The point cloud data in the embodiment can be collected by a laser radar arranged on the head or the roof of the vehicle, the laser radar can perform 360-degree omnidirectional scanning or local angle scanning, and the laser radar can be a multi-line laser radar or a single-line laser radar. Fig. 2 is a schematic view of a scene of local scanning performed by a laser radar installed at the head of a vehicle, and fig. 3 is a schematic view of a scene of 360-degree omni-directional scanning performed by a laser radar installed at the roof of a vehicle.
After point cloud data (the data are ranging values of a plurality of scanning points of the laser radar) is acquired, the point cloud data needs to be converted into a space rectangular coordinate system according to an angle, and the space rectangular coordinate system takes the center of the laser radar as an origin. The conversion diagram is shown in fig. 4.
Step 120, projecting the conversion data onto a two-dimensional grid map established in a preset detection range to obtain an effective grid; and fitting the effective grid to obtain a grid expression result.
Wherein the grid expression result comprises a boundary grid and/or a lane grid. And projecting the conversion data onto a two-dimensional grid map established in a preset detection range, and when more than 1 point cloud exists in a certain grid, considering the grid to be effective (namely an effective grid). And performing linear or curve fitting operation on the effective grid to obtain a grid expression result. The expression results are shown in FIG. 5.
And step 130, determining the boundary of the road based on the point cloud data corresponding to the grid expression result.
And extracting corresponding point cloud data according to the boundary grid and/or the lane grid to obtain the boundary of the road. Optionally the point cloud data may contain location information. Fig. 6 is a schematic diagram of a road boundary output by the method according to the embodiment of the present application.
In the extraction method of the road detection area, the acquired point cloud is converted into a rectangular coordinate system and then is subjected to rasterization processing, so that the point cloud collection is subjected to down-sampling. And fitting based on the down-sampling result to obtain the road boundary. The scheme of the embodiment can quickly realize boundary identification and is insensitive to the number of point clouds. Therefore, the requirement of road surface edge detection on point cloud acquisition equipment can be reduced.
In one embodiment, as shown in fig. 7, step S110 includes:
and step 111, carrying out coordinate change on the acquired point cloud data acquired by the laser radar to obtain initial conversion data.
The method comprises the step of transferring the acquired point cloud data collected by the laser radar to a space rectangular coordinate system. Specifically, the obtained current position of the laser radar is set as the origin of coordinates of a space rectangular coordinate system; and converting the point cloud data in the point cloud data into data under a space rectangular coordinate system based on the scanning angle of the laser point in the point cloud data, and initially converting the data.
And 112, carrying out point cloud filtering processing on the initial conversion data to obtain the conversion data.
After the three-dimensional point cloud is obtained, ground points and possible interference points such as leaves, advertising boards, lamp poles and the like extending to a road need to be removed. And filtering initial conversion point cloud data corresponding to the ground point and/or filtering initial point cloud data with the height value larger than a preset threshold value to obtain the conversion data. For example, points that are considered to be all ground points that are less than a certain height threshold are culled. Similarly, the disturbance point cloud above the road can be removed according to the height threshold value, which can be 2 meters or other suitable values, i.e. points exceeding 2 meters are discarded without participating in the subsequent calculation.
The embodiment provides the interference points, which is beneficial to the execution of the subsequent steps and obtains a more refined fitting result.
In one embodiment, as shown in fig. 8, step S120 includes:
step S121, performing projection processing on the conversion data in the spatial rectangular coordinate system on the two-dimensional grid map according to the spatial position.
Taking the point cloud collected by the laser radar at the end of the vehicle as an example, 30 meters each of the left side and the right side of the vehicle can be set, and 120 meters ahead of the vehicle can be used as a detection range, and the 60 × 120 meter region is rasterized, and each grid can be set to be 0.3 × 0.3 meter, namely a 200 × 400 grid map. After the grid map is set, projection processing is performed on the conversion data in the spatial rectangular coordinate system on the two-dimensional grid map according to the spatial position.
Step S122, determining whether there is projected transformation data on each grid in the two-dimensional grid map.
In step S123, if yes, the grid with the projection conversion data is determined to be an effective grid.
Optionally, in order to improve the stability of the extraction method of the road detection area provided by the present application in the execution process, the number of times that the effective grid becomes a road boundary grid within a preset time period may be obtained in combination with historical information; if the times are larger than a preset threshold value, increasing the fitting weight of the effective grid; the fitting weights are used for the fitting operation. Further, if the number of times is smaller than a preset threshold, the fitting weight of the effective grid may be reduced. The scheme of the embodiment can be stably fitted according to the historical information under the condition that the road boundary disappears momentarily.
In one embodiment, step S120 further comprises: and taking the row sequence number and the column sequence number of the effective grid as input of fitting operation, and executing curve or straight line fitting operation on the effective grid to obtain a road grid and/or lane grid. Specifically, the effective grid is divided into a first effective grid and a second effective grid (corresponding to two boundaries of a lane) according to the spatial position of the effective grid; respectively performing curve or straight line fitting operation on the first effective grid and the second effective grid to obtain a first road grid and a second road grid; taking a grid between the first road boundary and the second road boundary as the lane grid. Alternatively, the fitting method may employ a random sample consensus method (RANSAC) or other methods.
It should be understood that although the steps in the flowcharts of fig. 1, 7 and 8 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1, 7 and 8 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in fig. 9, there is provided an extraction device of a road detection area, the device including:
the coordinate conversion module 10 is configured to perform coordinate change on the acquired point cloud data acquired by the vehicle-mounted laser radar to obtain conversion data in a spatial rectangular coordinate system with the laser radar as an origin;
the fitting module 20 is configured to project the conversion data onto a two-dimensional grid map established within a preset detection range to obtain an effective grid; fitting the effective grid to obtain a grid expression result; the grid expression result comprises a boundary grid and/or a lane grid;
and the output module 30 is used for determining the boundary of the road based on the position information of the point cloud data corresponding to the grid expression result.
In one embodiment, the coordinate conversion module 10 is configured to perform coordinate change on the acquired point cloud data acquired by the laser radar to obtain initial conversion data; and carrying out point cloud filtering processing on the initial conversion data to obtain the conversion data.
In one embodiment, the coordinate conversion module 10 is configured to filter out initial conversion point cloud data corresponding to a ground point and/or filter out initial point cloud data with a height value greater than a preset threshold, so as to obtain the conversion data.
In one embodiment, the coordinate conversion module 10 is configured to set the acquired current position of the laser radar as a coordinate origin of a spatial rectangular coordinate system; and converting the point cloud data in the point cloud data into data under a space rectangular coordinate system based on the scanning angle of the laser point in the point cloud data, and initially converting the data.
In one embodiment, the fitting module 20 is configured to perform projection processing on the transformed data in the spatial rectangular coordinate system on the two-dimensional grid map according to a spatial position; judging whether projected conversion data exists on each grid in the two-dimensional grid map; if so, the grid in which the projection transformation data exists is determined to be an effective grid.
In one embodiment, the fitting module 20 is configured to, in combination with the history information, obtain the number of times that the effective grid becomes a road boundary grid within a preset time period; if the times are larger than a preset threshold value, increasing the fitting weight of the effective grid; the fitting weights are used for the fitting operation.
In one embodiment, the fitting module 20 is configured to decrease the fitting weight of the effective grid if the number of times is smaller than a preset threshold.
In one embodiment, the fitting module 20 is configured to use the row sequence number and the column sequence number of the effective grid as input of a fitting operation, and perform a curve or straight line fitting operation on the effective grid to obtain a road grid and/or a lane grid.
In one embodiment, the fitting module 20 is configured to divide the effective grid into a first effective grid and a second effective grid according to the spatial position of the effective grid; respectively performing curve or straight line fitting operation on the first effective grid and the second effective grid to obtain a first road grid and a second road grid; taking a grid between the first road boundary and the second road boundary as the lane grid.
For the specific definition of the extraction device of the road detection area, reference may be made to the above definition of the extraction method of the road detection area, and details are not described here. The modules in the above road detection area extraction device may be wholly or partially implemented by software, hardware, or a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a road detection area extraction method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
carrying out coordinate change on the acquired point cloud data collected by the laser radar to obtain conversion data under a space rectangular coordinate system with the laser radar as an origin;
projecting the conversion data onto a two-dimensional grid map set in a preset detection range to obtain an effective grid; fitting the effective grid to obtain a grid expression result; the grid expression result comprises a boundary grid and/or a lane grid;
and determining the boundary of the road based on the point cloud data corresponding to the grid expression result.
In one embodiment, the processor, when executing the computer program, performs the steps of: carrying out coordinate change on the acquired point cloud data acquired by the laser radar to obtain initial conversion data; and carrying out point cloud filtering processing on the initial conversion data to obtain the conversion data.
In one embodiment, the processor, when executing the computer program, performs the steps of: and filtering initial conversion point cloud data corresponding to the ground point and/or filtering initial point cloud data with the height value larger than a preset threshold value to obtain the conversion data.
In one embodiment, the processor, when executing the computer program, performs the steps of: setting the obtained current position of the laser radar as the origin of coordinates of a space rectangular coordinate system; and converting the point cloud data in the point cloud data into data under a space rectangular coordinate system based on the scanning angle of the laser point in the point cloud data, and initially converting the data.
In one embodiment, the processor, when executing the computer program, performs the steps of: performing projection processing on the conversion data under the space rectangular coordinate system on the two-dimensional grid map according to a space position; judging whether projected conversion data exists on each grid in the two-dimensional grid map; if so, the grid in which the projection transformation data exists is determined to be an effective grid.
In one embodiment, the processor, when executing the computer program, performs the steps of: acquiring the times that the effective grid becomes a road boundary grid within a preset time period by combining historical information; if the times are larger than a preset threshold value, increasing the fitting weight of the effective grid; the fitting weights are used for the fitting operation.
In one embodiment, the processor, when executing the computer program, performs the steps of: and if the times are smaller than a preset threshold value, reducing the fitting weight of the effective grid.
In one embodiment, the processor, when executing the computer program, performs the steps of: and taking the row sequence number and the column sequence number of the effective grid as input of fitting operation, and executing curve or straight line fitting operation on the effective grid to obtain a road grid and/or lane grid.
In one embodiment, the processor, when executing the computer program, performs the steps of: dividing the effective grid into a first effective grid and a second effective grid according to the spatial position of the effective grid; respectively performing curve or straight line fitting operation on the first effective grid and the second effective grid to obtain a first road grid and a second road grid; taking a grid between the first road boundary and the second road boundary as the lane grid.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
carrying out coordinate change on the acquired point cloud data collected by the laser radar to obtain conversion data under a space rectangular coordinate system with the laser radar as an origin;
projecting the conversion data onto a two-dimensional grid map set in a preset detection range to obtain an effective grid; fitting the effective grid to obtain a grid expression result; the grid expression result comprises a boundary grid and/or a lane grid;
and determining the boundary of the road based on the point cloud data corresponding to the grid expression result.
In one embodiment, the computer program when executed by the processor implements the steps of: carrying out coordinate change on the acquired point cloud data acquired by the laser radar to obtain initial conversion data; and carrying out point cloud filtering processing on the initial conversion data to obtain the conversion data.
In one embodiment, the computer program when executed by the processor implements the steps of: and filtering initial conversion point cloud data corresponding to the ground point and/or filtering initial point cloud data with the height value larger than a preset threshold value to obtain the conversion data.
In one embodiment, the computer program when executed by the processor implements the steps of: setting the obtained current position of the laser radar as the origin of coordinates of a space rectangular coordinate system; and converting the point cloud data in the point cloud data into data under a space rectangular coordinate system based on the scanning angle of the laser point in the point cloud data, and initially converting the data.
In one embodiment, the computer program when executed by the processor implements the steps of: performing projection processing on the conversion data under the space rectangular coordinate system on the two-dimensional grid map according to a space position; judging whether projected conversion data exists on each grid in the two-dimensional grid map; if so, the grid in which the projection conversion data exists is determined to be a valid grid.
In one embodiment, the computer program when executed by the processor implements the steps of: acquiring the times of the effective grid becoming a road boundary grid in a preset time period by combining historical information; if the times are larger than a preset threshold value, increasing the fitting weight of the effective grid; the fitting weights are used for the fitting operation.
In one embodiment, the computer program when executed by the processor implements the steps of: and if the times are smaller than a preset threshold value, reducing the fitting weight of the effective grid.
In one embodiment, the computer program when executed by the processor implements the steps of: and taking the row sequence number and the column sequence number of the effective grid as input of fitting operation, and executing curve or straight line fitting operation on the effective grid to obtain a road grid and/or lane grid.
In one embodiment, the computer program when executed by the processor implements the steps of: dividing the effective grid into a first effective grid and a second effective grid according to the spatial position of the effective grid; respectively performing curve or straight line fitting operation on the first effective grid and the second effective grid to obtain a first road grid and a second road grid; taking a grid between the first road boundary and the second road boundary as the lane grid.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (12)
1. A road detection area extraction method is characterized by comprising the following steps:
carrying out coordinate change on the acquired point cloud data collected by the laser radar to obtain conversion data under a space rectangular coordinate system with the laser radar as an origin;
projecting the conversion data onto a two-dimensional grid map set in a preset detection range to obtain an effective grid; fitting the effective grid to obtain a grid expression result; the grid expression result comprises a boundary grid and/or a lane grid;
and determining the boundary of the road based on the point cloud data corresponding to the grid expression result.
2. The method of claim 1, wherein performing coordinate transformation on the acquired point cloud data collected by the laser radar to obtain conversion data in a spatial rectangular coordinate system with the laser radar as an origin comprises:
carrying out coordinate change on the acquired point cloud data acquired by the laser radar to obtain initial conversion data;
and carrying out point cloud filtering processing on the initial conversion data to obtain the conversion data.
3. The method of claim 2, wherein performing point cloud filtering on the initial transformation data to obtain the transformation data comprises:
and filtering initial conversion point cloud data corresponding to the ground point and/or filtering initial point cloud data with the height value larger than a preset threshold value to obtain the conversion data.
4. The method according to claim 2, wherein the step of performing coordinate transformation on the acquired point cloud data acquired by the vehicle-mounted laser radar to obtain initial conversion data comprises:
setting the obtained current position of the laser radar as the origin of coordinates of a space rectangular coordinate system;
and converting the point cloud data in the point cloud data into data under a space rectangular coordinate system based on the scanning angle of the laser point in the point cloud data, and initially converting the data.
5. The method of claim 1, wherein the projecting the transformed data onto a two-dimensional grid map established within a preset detection range, and the obtaining an effective grid comprises:
performing projection processing on the conversion data under the space rectangular coordinate system on the two-dimensional grid map according to a space position;
judging whether projected conversion data exists on each grid in the two-dimensional grid map;
if so, the grid in which the projection transformation data exists is determined to be an effective grid.
6. The method of claim 5, further comprising:
acquiring the times that the effective grid becomes a road boundary grid within a preset time period by combining historical information;
if the times are larger than a preset threshold value, increasing the fitting weight of the effective grid; the fitting weights are used for the fitting operation.
7. The method of claim 6, further comprising:
and if the times are smaller than a preset threshold value, reducing the fitting weight of the effective grid.
8. The method of claim 1, wherein fitting the effective grid to obtain a grid expression result comprises:
and taking the row sequence number and the column sequence number of the effective grid as input of fitting operation, and executing curve or straight line fitting operation on the effective grid to obtain a road grid and/or lane grid.
9. The method of claim 8, wherein prior to performing a curve and line fitting operation on the active grid using the row sequence number and the column sequence number of the active grid as inputs to the fitting operation, the method further comprises:
dividing the effective grid into a first effective grid and a second effective grid according to the spatial position of the effective grid;
respectively performing curve or straight line fitting operation on the first effective grid and the second effective grid to obtain a first road grid and a second road grid;
taking a grid between the first road boundary and the second road boundary as the lane grid.
10. An extraction device of a road detection area, characterized in that the device comprises:
the coordinate conversion module is used for carrying out coordinate change on the acquired point cloud data collected by the vehicle-mounted laser radar so as to obtain conversion data under a space rectangular coordinate system with the laser radar as an origin;
the fitting module is used for projecting the conversion data onto a two-dimensional grid map set in a preset detection range to obtain an effective grid; fitting the effective grid to obtain a grid expression result; the grid expression result comprises a boundary grid and/or a lane grid;
and the output module is used for determining the boundary of the road based on the position information of the point cloud data corresponding to the grid expression result.
11. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 9 when executing the computer program.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011595392.2A CN114694106A (en) | 2020-12-29 | 2020-12-29 | Extraction method and device of road detection area, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011595392.2A CN114694106A (en) | 2020-12-29 | 2020-12-29 | Extraction method and device of road detection area, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114694106A true CN114694106A (en) | 2022-07-01 |
Family
ID=82131977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011595392.2A Pending CN114694106A (en) | 2020-12-29 | 2020-12-29 | Extraction method and device of road detection area, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114694106A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117491983A (en) * | 2024-01-02 | 2024-02-02 | 上海几何伙伴智能驾驶有限公司 | Method for realizing passable region boundary acquisition and target relative position discrimination |
-
2020
- 2020-12-29 CN CN202011595392.2A patent/CN114694106A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117491983A (en) * | 2024-01-02 | 2024-02-02 | 上海几何伙伴智能驾驶有限公司 | Method for realizing passable region boundary acquisition and target relative position discrimination |
| CN117491983B (en) * | 2024-01-02 | 2024-03-08 | 上海几何伙伴智能驾驶有限公司 | Method for realizing passable region boundary acquisition and target relative position discrimination |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108319655B (en) | Method and device for generating grid map | |
| US10964054B2 (en) | Method and device for positioning | |
| EP3620823B1 (en) | Method and device for detecting precision of internal parameter of laser radar | |
| CN110889808B (en) | Positioning method, device, equipment and storage medium | |
| CN108763287A (en) | On a large scale can traffic areas driving map construction method and its unmanned application process | |
| CN113761999B (en) | Target detection method and device, electronic equipment and storage medium | |
| CN111179274B (en) | Map ground segmentation method, device, computer equipment and storage medium | |
| CN111192295A (en) | Target detection and tracking method, related device and computer readable storage medium | |
| CN110135278B (en) | Obstacle detection method and device and electronic equipment | |
| CN114485698B (en) | Intersection guide line generation method and system | |
| CN112505671B (en) | Millimeter wave radar target positioning method and device under GNSS signal missing environment | |
| CN115273039B (en) | Small obstacle detection method based on camera | |
| CN113945937A (en) | Precision detection method, device and storage medium | |
| CN113096181B (en) | Method and device for determining equipment pose, storage medium and electronic device | |
| CN114694106A (en) | Extraction method and device of road detection area, computer equipment and storage medium | |
| CN114488178A (en) | Positioning method and device | |
| CN110174115B (en) | Method and device for automatically generating high-precision positioning map based on perception data | |
| CN112150522A (en) | Remote sensing image registration method, device, equipment, storage medium and system | |
| CN114419573A (en) | Dynamic occupancy grid estimation method and device | |
| CN111380529A (en) | Mobile equipment positioning method, device and system and mobile equipment | |
| CN114694107A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN113763308B (en) | Ground detection method, device, server and medium | |
| CN113421306A (en) | Positioning initialization method, system and mobile tool | |
| CN113312403A (en) | Map acquisition method and device, electronic equipment and storage medium | |
| CN114066739A (en) | Background point cloud filtering method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231208 Address after: 430200, 7th floor, Building 3, Phase II, Modern Service Industry Demonstration Base, Huazhong University of Science and Technology Science Park, Guandong Street, Donghu New Technology Development Zone, Wuhan City, Hubei Province Applicant after: Wuhan Wanji Photoelectric Technology Co.,Ltd. Address before: Wanji space, building 12, Zhongguancun Software Park, yard 8, Dongbei Wangxi Road, Haidian District, Beijing 100193 Applicant before: BEIJING WANJI TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right |