CN110298311A - Surface gathered water detection method and device - Google Patents
Surface gathered water detection method and device Download PDFInfo
- Publication number
- CN110298311A CN110298311A CN201910577870.8A CN201910577870A CN110298311A CN 110298311 A CN110298311 A CN 110298311A CN 201910577870 A CN201910577870 A CN 201910577870A CN 110298311 A CN110298311 A CN 110298311A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- coordinate system
- grating map
- vehicle
- under
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of surface gathered water detection methods, comprising: obtains multiframe laser point cloud information；Obtain the first grating map occupied by the point cloud cavity of present frame point cloud；According to the location information of vehicle and the first grating map, the second grating map occupied by the point cloud cavity under the second coordinate system is determined；Tracking processing is carried out to each grid cell, and carries out coordinate conversion after tracking processing, obtains the third grating map under the first coordinate system；Obtain the profile of each connected region of the bianry image of third grating map；When the first water surface area is not more than preset first threshold, corresponding profile is filtered out；According to remaining profile, position of the surface gathered water under the first coordinate system is determined.The detecting sensor of existing automatic driving vehicle is directly utilized as a result, and this method does not need a large amount of artificial mark work that effective water detection function can be realized, in addition, the principle of the algorithm is concisely easy to Project Realization, it is at low cost high-efficient.
Description
Technical field
The present invention relates to data processing field more particularly to a kind of surface gathered water detection method and device.
Background technique
In recent years, automatic driving vehicle constructs in more scenes such as intelligent transportation trip, logistics distribution, cleaning operation
The Applied D emonstration of smart city life.However there is still a need for choose in face of many before realizing round-the-clock operation for automatic driving vehicle
War, such as the weather conditions such as big sleet, the surface conditions such as ponding accumulated snow can all impact the safety traffic of vehicle.Therefore,
The sensory perceptual system of automatic driving vehicle also needs to have the road like such as surface gathered water on the basis of having detection of obstacles function
The detection of condition.
Water detection scheme in road surface has detection method based on special optical device or near field radar means at present
Detection method also has the image processing method based on deep learning.
It is less disclosed in water detection scheme based on mobile lidar, and relevant mature technology is not found.It is based on
The detection technique of special optical equipment or near field radar equipment, it is often expensive in practical applications, and be easy by outer
The influence of boundary's environment.Vision solution based on deep learning, it is deep although the variation to environment has certain adaptability
The training of degree learning model is needed using a large amount of labeled data collection, and the cost is relatively high.
Summary of the invention
The purpose of the embodiment of the present invention is that a kind of surface gathered water detection method and device are provided, to solve to exist in the prior art
When carrying out surface gathered water detection, higher cost, and vulnerable to extraneous the problem of influencing.
To solve the above problems, in a first aspect, the present invention provides a kind of surface gathered water detection method, the method packet
It includes:
Obtain multiframe laser point cloud information；
The laser point cloud information described in every frame is handled, and is obtained under the first coordinate system, the point cloud cavity of present frame point cloud
The first occupied grating map；Described cloud cavity is laser radar point cloud when ponding road surface is without echo or echo exception
The figure shown；
Obtain the location information of vehicle；
It according to the location information of vehicle and first grating map, determines under the second coordinate system, the point of present frame point cloud
Second grating map occupied by cloud cavity；
Second grating map is decomposed, multiple grid cells are obtained；
Tracking processing is carried out to each grid cell, and carries out coordinate conversion after tracking processing, obtains the first seat
Third grating map under mark system；
The third grating map is converted into bianry image；The bianry image includes one or more connected regions；
Obtain the profile of each connected region of the bianry image；Each corresponding profile of the connected region；
Calculate corresponding first water surface area of each profile；
When first water surface area is not more than preset first threshold, corresponding profile is filtered out；
According to the remaining profile after corresponding profile is filtered out, position of the surface gathered water under the first coordinate system is determined.
In one possible implementation, described that tracking processing is carried out to each grid cell, it specifically includes:
By the grid cell, it is overlapped in the confidence level of present frame and the confidence level of former frame, is set when superimposed
When reliability is not less than preset confidence threshold value, retain the grid cell；When superimposed confidence level is less than preset confidence
When spending threshold value, the grid cell is deleted.
In one possible implementation, described that the laser point cloud information is handled, obtain the first coordinate system
Under, the first grating map occupied by the point cloud cavity of present frame point cloud specifically includes:
Extract point cloud information of the first quantity ring in vehicle first direction of laser point cloud；
Extract the Null Spot or abnormal point in the first quantity ring in the point cloud information of each ring；
It according to the Null Spot or abnormal point, obtains under the first coordinate system, the first of each ring midpoint cloud cavity is empty
The beginning and end of hole line segment obtains the first empty line segment of each ring；
Calculated the intersection point of a plurality of equal part ray of the origin of the first coordinate system and the first empty line segment of each ring；
When there are intersection point, maximum two intersection points of neighbor distance are extracted, and by maximum two intersection points of the neighbor distance
Corresponding line segment as etc. divide the on ray second empty line segment；
According to the described second empty line segment, the first grating map is determined.
In one possible implementation, the location information for obtaining vehicle, specifically includes:
By the Global Satellite Navigation System on vehicle, the location information of vehicle is obtained.
In one possible implementation, the location information according to vehicle and first grating map determine
Under second coordinate system, the second grating map occupied by present frame point cloud is specifically included:
According to the location information of vehicle, the first grating map under first coordinate system is subjected to coordinate conversion, is obtained
Under second coordinate system, the second grating map of one or more occupied by present frame point cloud；Wherein, the first coordinate system is vehicle seat
Mark system, the second coordinate system are global coordinate system.
In one possible implementation, after the method further include:
When being provided at least two laser radars on vehicle, to the grid of the corresponding surface gathered water of multiple laser radars
Figure carries out fusion treatment, obtains the location information of target surface gathered water.
Second aspect, the present invention provides a kind of surface gathered water detection device, described device includes:
Preprocessing module, the preprocessing module is for obtaining multiframe laser point cloud information；The laser point cloud described in every frame
Information is handled, and is obtained under the first coordinate system, the first grating map occupied by the point cloud cavity of present frame point cloud；The point
The figure that cloud cavity is shown by laser radar point cloud when ponding road surface is without echo or echo exception；
Tracking module, the tracking module are used to obtain the location information of vehicle；According to the location information of vehicle and described
First grating map determines under the second coordinate system that present frame point cloud puts the second grating map occupied by cloud cavity；To described
Second grating map is decomposed, and multiple grid cells are obtained；Tracking processing is carried out to each grid cell, and is being tracked
Coordinate conversion is carried out after processing, obtains the third grating map under the first coordinate system；
Post-processing module, the post-processing module are used to the third grating map being converted to bianry image；Described two
Being worth image includes one or more connected regions；Obtain one or more profiles of the bianry image；Each connected region
Domain corresponds to a profile；Calculate corresponding first water surface area of each profile；When first water surface area is no more than pre-
If first threshold when, filter out corresponding profile；According to the remaining profile after corresponding profile is filtered out, determine surface gathered water
Position under one coordinate system.
The third aspect, the present invention provides a kind of equipment, the equipment includes memory and processor, and the memory is used
In storage program, the processor is used to execute the method as described in first aspect is any.
Fourth aspect, the present invention provides a kind of computer program products comprising instruction, when the computer program produces
When product are run on computers, so that the computer executes the method as described in first aspect is any.
5th aspect, the present invention provides a kind of computer readable storage medium, on the computer readable storage medium
It is stored with computer program, the method as described in first aspect is any is realized when the computer program is executed by processor.
By applying surface gathered water detection method and device provided in an embodiment of the present invention, existing automatic Pilot is directly utilized
The detection of road pavement ponding can be realized in the detecting sensor of vehicle, and does not need a large amount of artificial mark work, in addition, the dress
The principle set concisely is easy to Project Realization, at low cost high-efficient.
Detailed description of the invention
Fig. 1 is the surface gathered water detection method flow diagram that the embodiment of the present invention one provides；
Fig. 2 is the schematic diagram that laser radar point cloud cavity is caused on the ponding road surface that the embodiment of the present invention one provides；
Fig. 3 is the first empty line segment, the second empty line segment schematic diagram that the embodiment of the present invention one provides；
Fig. 4 is that the second empty line segment that the embodiment of the present invention one provides is converted to the schematic diagram of the first grating map；
Fig. 5 A is the surface gathered water actual scene figure that the embodiment of the present invention one provides；
Fig. 5 B is the surface gathered water detection effect figure that the embodiment of the present invention one provides；
Fig. 6 is surface gathered water structure of the detecting device schematic diagram provided by Embodiment 2 of the present invention.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that for just
Part relevant to related invention is illustrated only in description, attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is the surface gathered water detection method flow diagram that the embodiment of the present invention one provides.The application scenarios of this method
For automatic driving vehicle, the executing subject of this method is automatic driving vehicle control unit (the Automated Vehicle of vehicle
Control Unit, AVCU), AVCU is the processor of automatic driving vehicle.As shown in Figure 1, method includes the following steps:
Step 101, multiframe laser point cloud information is obtained.
Specifically, being provided with laser radar on automatic driving vehicle, ponding road surface forms mirror surface to the harness of laser radar
Reflection, so that the situation-without return value or return value exception of laser radar point cloud be caused to form the phenomenon in some cloud cavities.Figure
2 cause the schematic diagram in laser radar point cloud cavity for the ponding road surface that the embodiment of the present invention one provides.
Step 102, every frame laser point cloud information is handled, is obtained under the first coordinate system, the point cloud of present frame point cloud
First grating map occupied by cavity；Point cloud cavity is laser radar point cloud when ponding road surface is without echo or echo exception
The figure shown.
Specifically, step 102 the following steps are included:
Firstly, taking the first quantity ring of laser point cloud in the point cloud information of vehicle first direction；Then, the first number is extracted
Measure the Null Spot or abnormal point in a ring in the point cloud information of each ring；Then, it according to Null Spot or abnormal point, obtains
Under first coordinate system, the beginning and end of the empty line segment of the first of each ring midpoint cloud cavity obtains the first of each ring
Empty line segment；；Then, a plurality of equal part ray of the origin of the first coordinate system and the first empty line segment of each ring were calculated
Intersection point；Then, when there are intersection point, maximum two intersection points of neighbor distance are extracted, and the neighbor distance maximum two are handed over
The corresponding line segment of point as etc. the second cavity line segment on minute ray；Finally, according to the second empty line segment, with determining the first grid
Figure.
Wherein, there is grating map, grating map, including the multiple grid divided according to preset interval under the first coordinate system
Lattice, for example, can be divided according to 0.1 meter of interval.First quantity can be 4, and first direction is vehicle front.It is each
The quantity of the empty line segment of the first of ring can be 0, be also possible to multiple, and the application does not limit this.
In the following, the step is specifically described in conjunction with attached drawing 3 and 4 pair.
The executing subject of the step can be preprocessing module, which extracts first in laser radar vertical array harness
Bottom (nearest apart from ground) 4 harness before vehicle to upper point cloud information, to the nothing in each point cloud harness
Effect point or abnormal point extract, and obtain longest cavity line segment, i.e., the position of the beginning and end of the first empty line segment, example
And it is non-limiting, the first empty line segment is referring to 3 real segments in Fig. 3.Then, a plurality of equal part for calculating vehicle coordinate origin is penetrated
The intersection point of line and a plurality of first empty line segment, intersection point A, B and C point as shown in Figure 4.Divide ray finally, for every etc., if
Maximum two intersection points of neighbor distance are then extracted there are intersection point, and as the second empty line segment on the equal part ray,
The line segment that A, C point as shown in Figure 4 is constituted is the second empty line segment.
As shown in Figure 4, the second empty line segment that condition is met on all equal part rays the ponding water surface is converted to occupy
The first grating map.
Wherein, in the first coordinate system, vehicle front region is divided into multiple adjacent cells regions, is then calculated by line
Grid cell occupied by section AC.First grating map occupied by the final output present frame ponding water surface.
Step 103, the location information of vehicle is obtained.
Specifically, Global Satellite Navigation System (the Global Navigation Satellite on vehicle can be passed through
System, GNSS), obtain the location information of vehicle.The location information includes location information of the vehicle under global coordinate system, should
Location information includes latitude and longitude information.
Step 104, it according to the location information of vehicle and the first grating map, determines under the second coordinate system, present frame point cloud
Point cloud cavity occupied by the second grating map.
The executing subject of the step can be tracking module, since the first grid of preprocessing module output is based on first
Coordinate system, i.e., from vehicle coordinate system, and the coordinate system is moving coordinate system, cannot achieve the tracking of static grid.Therefore, it completes
It after the ponding water surface of single frames point cloud information occupies the detection of grid, is executed by tracking module, coordinate system conversion is being carried out, by the
One coordinate system is converted to the second coordinate system, by carrying out to each grid cell in the second grating map under the second coordinate system
Tracking, thus the stability of achievement unit point detection noise filtered out and guarantee the first exported grid.The tracking module is main
It is the location information using vehicle, the water surface detected under vehicle coordinate system is occupied into the first grid and is transformed into global coordinate system
Under, the tracing task of static grid is then realized below the coordinate system of the static state.
Specifically, the first grating map under the first coordinate system is carried out coordinate conversion, is obtained according to the location information of vehicle
To under the second coordinate system, the second grating map of one or more occupied by the present frame ponding water surface.Wherein, the first coordinate system is
Vehicle axis system, the second coordinate system are global coordinate system.
Step 105, the second grating map is decomposed, obtains multiple grid cells.
Specifically, grid cell herein, can be minimum grid cell.
Step 106, tracking processing is carried out to each grid cell, and carries out coordinate system conversion after tracking processing, obtained
Third grating map under first coordinate system.
Wherein, tracking processing mainly includes the generation of new grid cell, the state update and failure for having tracked grid cell
The deletion of grid cell.
Specifically, in one example, grid cell is folded in the confidence level of present frame and the confidence level of previous frame
Add, when superimposed confidence level is not less than preset confidence threshold value, retains grid cell；When superimposed confidence level is less than
When preset confidence threshold value, grid cell is deleted.
Wherein, whether confidence level can be sets according to grid cell with the presence or absence of echo data or echo data extremely
It is fixed.There is no for exception and echo data, corresponding confidence level is low, and vice versa.
After carrying out tracking processing, new grating map is obtained, after which is carried out coordinate conversion, is obtained
Third grating map under first coordinate system.
Step 107, third grating map is converted into bianry image.
Wherein, the executing subject of the step can be post-processing module, which can use related algorithm, will
Third grating map is converted to bianry image.Bianry image refers to: it is exactly white, the no centre of gray value that each pixel, which is not black,
The image of transition.Bianry image is generally used to descriptive text or figure, its advantage is that occupied space is few, can describe profile, no
Details can be described.The bianry image being converted into, including one or more connected regions.There is identical picture in connected region, that is, image
The image-region for the foreground pixel point composition that element is worth and position is adjacent.
Step 108, the profile of each connected region of the bianry image is obtained.
Wherein, the corresponding profile of each connected region.Those skilled in the art can use the prior art, extract two
It is worth the profile of image, the application does not limit this.
Step 109, corresponding first water surface area of each profile is calculated.
Step 110, when the first water surface area is not more than preset first threshold, corresponding profile is filtered out.
Step 111, according to the remaining profile after corresponding profile is filtered out, position of the surface gathered water under the first coordinate system is determined
It sets.
Specifically, according to automatic driving vehicle can the traffic capacity, when the first water surface area detected be greater than a fixed number
When value (such as 4m2), this method can just export corresponding ponding water detection result.
After filtering out the first water surface area no more than the profile of preset first threshold, using remaining profile as target
Profile determines grating map occupied by the objective contour, and using occupied grating map as the corresponding position of surface gathered water
It sets.Fig. 5 A and Fig. 5 B are respectively practical surface gathered water image and surface gathered water detection image.
Further, when being provided with no less than two laser radars on vehicle, two laser radars all detect road
The detection image of area water can merge the detection grating map of two surface gathered waters, obtain final surface gathered water
Location information.
It is understood that in the application, with no restriction to the type of laser radar；Had chosen in the application before vehicle to
4 laser point cloud harness of lower section carry out water detection, and the present invention includes but is not limited to this kind of configuration mode.The application include but
It is not limited to use the equal part ray of origin, non-equal part ray can also be used, require nothing more than ray by the original from vehicle coordinate system
Point.
The surface gathered water detection method provided by the application embodiment of the present invention one, directly utilizes existing automatic driving vehicle
Detecting sensor can be realized, and this method does not need a large amount of artificial mark work that effective water detection function can be realized
Can, in addition, the principle of this method is concisely easy to Project Realization, it is at low cost high-efficient.
Fig. 6 is surface gathered water structure of the detecting device schematic diagram provided by Embodiment 2 of the present invention.Surface gathered water detection dress
Setting can apply in surface gathered water detection method, as shown in fig. 6, the surface gathered water detection device includes: preprocessing module
601, tracking module 602 and post-processing module 603.
Preprocessing module 601 is for obtaining multiframe laser point cloud information；Every frame laser point cloud information is handled, is obtained
Under first coordinate system, the first grating map occupied by the point cloud cavity of present frame point cloud；Point cloud cavity is laser radar point cloud
The figure shown when ponding road surface is without echo or echo exception；
Tracking module 602 is used to obtain the location information of vehicle；According to the location information of vehicle and the first grating map, really
Under fixed second coordinate system, the second grating map occupied by the point cloud cavity of present frame point cloud；Second grating map is divided
Solution, obtains multiple grid cells；Tracking processing is carried out to each grid cell, and carries out coordinate conversion after tracking processing, is obtained
Third grating map under to the first coordinate system；
Post-processing module 603 is used to third grating map being converted to bianry image；Bianry image includes one or more
Connected region；Obtain one or more profiles of bianry image；The corresponding profile of each connected region；Calculate each profile pair
The first water surface area answered；When the first water surface area is not more than preset first threshold, corresponding profile is filtered out；According to filtering out
Remaining profile after corresponding profile determines position of the surface gathered water under the first coordinate system.
Specifically acting on for modules is identical described in embodiment one, and details are not described herein again.
By applying surface gathered water detection device provided by Embodiment 2 of the present invention, existing automatic driving vehicle is directly utilized
Detecting sensor can be realized, and the device does not need a large amount of artificial mark work that effective water detection function can be realized
Can, in addition, the principle of the device is concisely easy to Project Realization, it is at low cost high-efficient.
The embodiment of the present invention three provides a kind of equipment, including memory and processor, and memory is deposited for storing program
Reservoir can be connect by bus with processor.Memory can be nonvolatile storage, such as hard disk drive and flash memory, storage
Software program and device driver are stored in device.Software program is able to carry out the above method provided in an embodiment of the present invention
Various functions；Device driver can be network and interface drive program.Processor is for executing software program, the software journey
Sequence is performed, the method that can be realized the offer of the embodiment of the present invention one.
The embodiment of the present invention four provides a kind of computer program product comprising instruction, when computer program product is being counted
When being run on calculation machine, so that computer executes the method that the embodiment of the present invention one provides.
The embodiment of the present invention five provides a kind of computer readable storage medium, is stored on computer readable storage medium
Computer program realizes the method that the embodiment of the present invention one provides when computer program is executed by processor.
Professional should further appreciate that, described in conjunction with the examples disclosed in the embodiments of the present disclosure
Unit and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, hard in order to clearly demonstrate
The interchangeability of part and software generally describes each exemplary composition and step according to function in the above description.
These functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.
Professional technician can use different methods to achieve the described function each specific application, but this realization
It should not be considered as beyond the scope of the present invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can be executed with hardware, processor
The combination of software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only memory
(ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technical field
In any other form of storage medium well known to interior.
Above specific embodiment has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
Illustrate, it should be understood that the above is only a specific embodiment of the invention, the protection model that is not intended to limit the present invention
It encloses, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should be included in the present invention
Protection scope within.
Claims (10)
1. a kind of surface gathered water detection method, which is characterized in that the described method includes:
Obtain multiframe laser point cloud information；
The laser point cloud information described in every frame is handled, and is obtained under the first coordinate system, shared by the point cloud cavity of present frame point cloud
According to the first grating map；Described cloud cavity is for laser radar point cloud on ponding road surface without echo or echo exception Shi Suobiao
The figure revealed；
Obtain the location information of vehicle；
It according to the location information of vehicle and first grating map, determines under the second coordinate system, the point cloud of present frame point cloud is empty
Second grating map occupied by hole；
Second grating map is decomposed, multiple grid cells are obtained；
Tracking processing is carried out to each grid cell, and carries out coordinate conversion after tracking processing, obtains the first coordinate system
Under third grating map；
The third grating map is converted into bianry image；The bianry image includes one or more connected regions；
Obtain the profile of each connected region of the bianry image；Each corresponding profile of the connected region；
Calculate corresponding first water surface area of each profile；
When first water surface area is not more than preset first threshold, corresponding profile is filtered out；
According to the remaining profile after corresponding profile is filtered out, position of the surface gathered water under the first coordinate system is determined.
2. the method according to claim 1, wherein described carry out tracking processing to each grid cell,
It specifically includes:
It is overlapped, the grid cell when superimposed confidence level in the confidence level of present frame and the confidence level of former frame
When not less than preset confidence threshold value, retain the grid cell；When superimposed confidence level is less than preset confidence level threshold
When value, the grid cell is deleted.
3. being obtained the method according to claim 1, wherein described handle the laser point cloud information
Under first coordinate system, the first grating map occupied by the point cloud cavity of present frame point cloud is specifically included:
Extract point cloud information of the first quantity ring in vehicle first direction of laser point cloud；
Extract the Null Spot or abnormal point in the first quantity ring in the point cloud information of each ring；
It according to the Null Spot or abnormal point, obtains under the first coordinate system, the empty line of the first of each ring midpoint cloud cavity
The beginning and end of section obtains the first empty line segment of each ring；
Calculated the intersection point of a plurality of equal part ray of the origin of the first coordinate system and the first empty line segment of each ring；
When there are intersection point, maximum two intersection points of neighbor distance are extracted, and maximum two intersection points of the neighbor distance is corresponding
Line segment as etc. divide the on ray second empty line segment；
According to the described second empty line segment, the first grating map is determined.
4. the method according to claim 1, wherein the location information for obtaining vehicle, specifically includes:
By the Global Satellite Navigation System on vehicle, the location information of vehicle is obtained.
5. the method according to claim 1, wherein the location information according to vehicle and first grid
Map determines under the second coordinate system that the second grating map occupied by present frame point cloud specifically includes:
According to the location information of vehicle, the first grating map under first coordinate system is subjected to coordinate conversion, obtains second
Under coordinate system, the second grating map of one or more occupied by present frame point cloud；Wherein, the first coordinate system is vehicle coordinate
System, the second coordinate system are global coordinate system.
6. the method according to claim 1, wherein after the method further include:
When being provided at least two laser radars on vehicle, to the grating map of the corresponding surface gathered water of multiple laser radars into
Row fusion treatment obtains the location information of target surface gathered water.
7. a kind of surface gathered water detection device, which is characterized in that described device includes:
Preprocessing module, the preprocessing module is for obtaining multiframe laser point cloud information；The laser point cloud information described in every frame
It is handled, is obtained under the first coordinate system, the first grating map occupied by the point cloud cavity of present frame point cloud；Described cloud sky
The figure that hole is shown by laser radar point cloud when ponding road surface is without echo or echo exception；
Tracking module, the tracking module are used to obtain the location information of vehicle；According to the location information of vehicle and described first
Grating map determines under the second coordinate system that present frame point cloud puts the second grating map occupied by cloud cavity；To described second
Grating map is decomposed, and multiple grid cells are obtained；Tracking processing is carried out to each grid cell, and is handled in tracking
Coordinate conversion is carried out afterwards, obtains the third grating map under the first coordinate system；
Post-processing module, the post-processing module are used to the third grating map being converted to bianry image；The binary map
As including one or more connected regions；Obtain one or more profiles of the bianry image；Each connected region pair
Answer a profile；Calculate corresponding first water surface area of each profile；When first water surface area is no more than preset
When first threshold, corresponding profile is filtered out；According to the remaining profile after corresponding profile is filtered out, determine that surface gathered water is sat first
Position under mark system.
8. a kind of equipment, which is characterized in that the equipment includes memory and processor, and the memory is used to store program,
The processor requires any method of 1-6 for perform claim.
9. a kind of computer program product comprising instruction, which is characterized in that when the computer program product on computers
When operation, so that the computer executes the method as described in claim 1-6 is any.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the method as described in claim 1-6 is any when the computer program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910577870.8A CN110298311B (en) | 2019-06-28 | 2019-06-28 | Method and device for detecting surface water accumulation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910577870.8A CN110298311B (en) | 2019-06-28 | 2019-06-28 | Method and device for detecting surface water accumulation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110298311A true CN110298311A (en) | 2019-10-01 |
| CN110298311B CN110298311B (en) | 2021-05-07 |
Family
ID=68029357
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910577870.8A Active CN110298311B (en) | 2019-06-28 | 2019-06-28 | Method and device for detecting surface water accumulation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110298311B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111461982A (en) * | 2020-03-30 | 2020-07-28 | 北京百度网讯科技有限公司 | Method and device for splicing point clouds |
| CN112585656A (en) * | 2020-02-25 | 2021-03-30 | 华为技术有限公司 | Method and device for identifying special road conditions, electronic equipment and storage medium |
| CN112666553A (en) * | 2020-12-16 | 2021-04-16 | 动联(山东)电子科技有限公司 | Road ponding identification method and equipment based on millimeter wave radar |
| CN114814796A (en) * | 2022-07-01 | 2022-07-29 | 陕西欧卡电子智能科技有限公司 | Method, device and equipment for extracting water surface travelable area based on high-precision map |
| CN116311095A (en) * | 2023-03-16 | 2023-06-23 | 广州市衡正工程质量检测有限公司 | Pavement detection method based on region division, computer equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050825A (en) * | 2013-03-13 | 2014-09-17 | 厦门歌乐电子企业有限公司 | Terminal device carried at vehicle, vehicle, prompting method of puddle pavement |
| CN105717514A (en) * | 2014-12-22 | 2016-06-29 | 通用汽车环球科技运作有限责任公司 | Road surface reflectivity detection by lidar sensor |
| US9495764B1 (en) * | 2016-03-21 | 2016-11-15 | URC Ventures, Inc. | Verifying object measurements determined from mobile device images |
| CN106325132A (en) * | 2016-09-23 | 2017-01-11 | 常州大学怀德学院 | Road waterlogging monitoring system |
| CN107092803A (en) * | 2017-05-12 | 2017-08-25 | 长安大学 | A kind of road pools zone recognition methods based on three-dimensional line laser technology |
| CN108664715A (en) * | 2018-04-26 | 2018-10-16 | 长安大学 | A kind of surface gathered water track triple assessment and traffic safety analysis method |
| CN109670404A (en) * | 2018-11-23 | 2019-04-23 | 江苏理工学院 | A kind of road ponding image detection method for early warning based on mixed model |
| US10816993B1 (en) * | 2019-11-23 | 2020-10-27 | Ha Q Tran | Smart vehicle |
-
2019
- 2019-06-28 CN CN201910577870.8A patent/CN110298311B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050825A (en) * | 2013-03-13 | 2014-09-17 | 厦门歌乐电子企业有限公司 | Terminal device carried at vehicle, vehicle, prompting method of puddle pavement |
| CN105717514A (en) * | 2014-12-22 | 2016-06-29 | 通用汽车环球科技运作有限责任公司 | Road surface reflectivity detection by lidar sensor |
| US9495764B1 (en) * | 2016-03-21 | 2016-11-15 | URC Ventures, Inc. | Verifying object measurements determined from mobile device images |
| CN106325132A (en) * | 2016-09-23 | 2017-01-11 | 常州大学怀德学院 | Road waterlogging monitoring system |
| CN107092803A (en) * | 2017-05-12 | 2017-08-25 | 长安大学 | A kind of road pools zone recognition methods based on three-dimensional line laser technology |
| CN108664715A (en) * | 2018-04-26 | 2018-10-16 | 长安大学 | A kind of surface gathered water track triple assessment and traffic safety analysis method |
| CN109670404A (en) * | 2018-11-23 | 2019-04-23 | 江苏理工学院 | A kind of road ponding image detection method for early warning based on mixed model |
| US10816993B1 (en) * | 2019-11-23 | 2020-10-27 | Ha Q Tran | Smart vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 陆侃: "道路结冰与积水智能传感器系统研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112585656A (en) * | 2020-02-25 | 2021-03-30 | 华为技术有限公司 | Method and device for identifying special road conditions, electronic equipment and storage medium |
| CN111461982A (en) * | 2020-03-30 | 2020-07-28 | 北京百度网讯科技有限公司 | Method and device for splicing point clouds |
| CN111461982B (en) * | 2020-03-30 | 2023-09-22 | 北京百度网讯科技有限公司 | Method and apparatus for splice point cloud |
| CN112666553A (en) * | 2020-12-16 | 2021-04-16 | 动联(山东)电子科技有限公司 | Road ponding identification method and equipment based on millimeter wave radar |
| CN112666553B (en) * | 2020-12-16 | 2023-04-18 | 动联(山东)电子科技有限公司 | Road ponding identification method and equipment based on millimeter wave radar |
| CN114814796A (en) * | 2022-07-01 | 2022-07-29 | 陕西欧卡电子智能科技有限公司 | Method, device and equipment for extracting water surface travelable area based on high-precision map |
| CN116311095A (en) * | 2023-03-16 | 2023-06-23 | 广州市衡正工程质量检测有限公司 | Pavement detection method based on region division, computer equipment and storage medium |
| CN116311095B (en) * | 2023-03-16 | 2024-01-02 | 广州市衡正工程质量检测有限公司 | Pavement detection method based on region division, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110298311B (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298311A (en) | Surface gathered water detection method and device | |
| CN109541634B (en) | Path planning method and device and mobile device | |
| US11282210B2 (en) | Method and apparatus for segmenting point cloud data, storage medium, and electronic device | |
| CN110674705B (en) | Small-sized obstacle detection method and device based on multi-line laser radar | |
| Clode et al. | The automatic extraction of roads from LIDAR data | |
| CN109584294B (en) | Pavement point cloud extraction method and device based on laser point cloud | |
| RU2571871C2 (en) | Method of determining road boundaries, shape and position of objects on road, and device therefor | |
| CN105158762A (en) | Identifying and tracking convective weather cells | |
| CN110246183B (en) | Wheel grounding point detection method, device and storage medium | |
| CN111209780A (en) | Lane line attribute detection method and device, electronic device and readable storage medium | |
| CN111179274B (en) | Map ground segmentation method, device, computer equipment and storage medium | |
| CN114930401A (en) | Point cloud-based three-dimensional reconstruction method and device and computer equipment | |
| AU2004246071A1 (en) | Method for generating a three-dimensional terrain model | |
| CN109241855B (en) | Intelligent vehicle travelable area detection method based on stereoscopic vision | |
| CN113673274A (en) | Road boundary detection method, road boundary detection device, computer equipment and storage medium | |
| US8823555B2 (en) | Apparatus for displaying terrain on a display apparatus of an airborne vehicle | |
| Kühnl et al. | Visual ego-vehicle lane assignment using spatial ray features | |
| Griesbaum et al. | Direct local building inundation depth determination in 3-D point clouds generated from user-generated flood images | |
| KR102371852B1 (en) | Method and Apparatus for Updating Map Based on Point Cloud Information | |
| CN108227712A (en) | The avoidance running method and device of a kind of unmanned boat | |
| CN112559539A (en) | Method and device for updating map data | |
| CN115077563A (en) | Vehicle positioning accuracy evaluation method and device and electronic equipment | |
| CN115618602A (en) | Lane-level scene simulation method and system | |
| Shamaoma et al. | Extraction of flood-modelling related base-data from multi-source remote sensing imagery | |
| CN103337220A (en) | Picture data provision system |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: B4-006, maker Plaza, 338 East Street, Huilongguan town, Changping District, Beijing 100096 Patentee after: Beijing Idriverplus Technology Co.,Ltd. Address before: B4-006, maker Plaza, 338 East Street, Huilongguan town, Changping District, Beijing 100096 Patentee before: Beijing Idriverplus Technology Co.,Ltd. |