CN109993700A - Data processing method, device, electronic equipment and computer readable storage medium - Google Patents
Data processing method, device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN109993700A CN109993700A CN201910265528.4A CN201910265528A CN109993700A CN 109993700 A CN109993700 A CN 109993700A CN 201910265528 A CN201910265528 A CN 201910265528A CN 109993700 A CN109993700 A CN 109993700A
- Authority
- CN
- China
- Prior art keywords
- cloud
- track
- point cloud
- process points
- vehicle
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 17
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 207
- 238000012545 processing Methods 0.000 claims abstract description 110
- 230000004927 fusion Effects 0.000 claims abstract description 65
- 238000012795 verification Methods 0.000 claims description 63
- 230000015654 memory Effects 0.000 claims description 16
- 239000007787 solid Substances 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 10
- 238000007689 inspection Methods 0.000 claims description 9
- 230000005484 gravity Effects 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 5
- 230000002787 reinforcement Effects 0.000 claims description 5
- 238000007499 fusion processing Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 13
- 238000004422 calculation algorithm Methods 0.000 description 10
- 235000013399 edible fruits Nutrition 0.000 description 6
- 230000001419 dependent effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000000903 blocking effect Effects 0.000 description 4
- 230000032798 delamination Effects 0.000 description 4
- 238000002310 reflectometry Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Instructional Devices (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of data processing method, device, electronic equipment and computer readable storage medium.This method comprises: carrying out splicing and fusion treatment according to original point cloud, obtaining the first process points cloud；In the case where the first process points cloud is unsatisfactory for the first preset condition, the input operation of user is received；Wherein, input operation is for specifying the characteristic point of the same name in the first process points cloud；According to characteristic point of the same name, fusion treatment is carried out to the first process points cloud, obtains second processing point cloud；In the case where second processing point cloud meets the distance of the characteristic point of the same name in the first preset condition and second processing point cloud less than the first pre-determined distance, according to second processing point cloud, map producing Job Operations are executed.As it can be seen that can be met the requirements according to quality puts cloud to carry out the production of three-dimensional high-precision map, and compared with prior art, the embodiment of the present invention can effectively guarantee the quality of the map datum generated in the embodiment of the present invention.
Description
Technical field
The present embodiments relate to field of communication technology more particularly to a kind of data processing method, device, electronic equipment and
Computer readable storage medium.
Background technique
Three-dimensional high-precision map is to realize Vehicular automatic driving and the precondition that auxiliary drives, be automatic driving vehicle into
Row is accurately positioned and correct decisions provide main foundation.The processing of point cloud is a crucial ring in three-dimensional high-precision map producing
Section, it is to be understood that point cloud refers to the point data set on the product appearance surface obtained in reverse-engineering by measuring instrument,
Point cloud can also be referred to as point cloud data.
In the prior art, the point cloud used when three-dimensional high-precision map producing is likely that there are some quality problems, once have
The point cloud of quality problems flows into map producing sessions, then can interfere to the algorithm dependent on point cloud, such as to lane
Line modeling algorithm interferes, to reduce the quality of the map datum ultimately generated.
Summary of the invention
The embodiment of the present invention provides a kind of data processing method, device, electronic equipment and computer readable storage medium, with
It solves in the prior art when carrying out three-dimensional high-precision map producing, uses there are the point cloud of quality problems, cause to ultimately generate
The problem of quality of map datum reduces.
In order to solve the above-mentioned technical problem, the present invention is implemented as follows:
In a first aspect, the embodiment of the present invention provides a kind of data processing method, which comprises
According to original point cloud, splicing and fusion treatment are carried out, the first process points cloud is obtained；
In the case where the first process points cloud is unsatisfactory for the first preset condition, the input operation of user is received；Wherein,
Of the same name characteristic point of the input operation for specifying in the first process points cloud；
According to the characteristic point of the same name, fusion treatment is carried out to the first process points cloud, obtains second processing point cloud；
Meet first preset condition, and the feature of the same name in second processing point cloud in the second processing point cloud
In the case that the distance of point is less than the first pre-determined distance, according to the second processing point cloud, map producing Job Operations are executed.
Second aspect, the embodiment of the present invention provide a kind of data processing equipment, and described device includes:
First processing module, for carrying out splicing and fusion treatment, obtaining the first process points according to original point cloud
Cloud；
Receiving module, for receiving user's in the case where the first process points cloud is unsatisfactory for the first preset condition
Input operation；Wherein, of the same name characteristic point of the input operation for specifying in the first process points cloud；
Second processing module, for carrying out fusion treatment to the first process points cloud, obtaining according to the characteristic point of the same name
To second processing point cloud；
Execution module, for meeting first preset condition, and second processing point in the second processing point cloud
In the case that the distance of characteristic point of the same name in cloud is less than the first pre-determined distance, according to the second processing point cloud, map is executed
Production operation operation.
The third aspect, the embodiment of the present invention provide a kind of electronic equipment, including processor, memory, are stored in described deposit
On reservoir and the computer program that can run on the processor, the computer program are realized when being executed by the processor
The step of above-mentioned data processing method.
Fourth aspect, the embodiment of the present invention provide a kind of computer readable storage medium, the computer-readable storage medium
Computer program is stored in matter, the step of computer program realizes above-mentioned data processing method when being executed by processor.
In the embodiment of the present invention, in order to carry out the production of three-dimensional high-precision map, it can be spliced first according to original point cloud
Processing and fusion treatment, obtain the first process points cloud, next, whether the first preset condition is met according to the first process points cloud,
It can be determined that whether the quality of the first process points cloud meets the requirements.The case where requiring is unsatisfactory in the quality of the first process points cloud
Under, the characteristic point of the same name of the first process points cloud can be specified, in order to melt accordingly to the first process points cloud by manpower intervention
Conjunction processing, to obtain quality more preferably second processing point cloud.Later, it is pre- that first whether can be met according to second processing point cloud
If whether the distance of condition and the characteristic point of the same name in second processing point cloud determines second processing less than the first pre-determined distance
Whether the quality of point cloud meets the requirements.It, can be according to second processing in the case where the quality of second processing point cloud is met the requirements
Point cloud, executes map producing Job Operations.As it can be seen that in the embodiment of the present invention, the point Yun Laijin that can be met the requirements according to quality
The production of the three-dimensional high-precision map of row, in this way, the algorithm dependent on point cloud will not be interfered, therefore, compared with prior art, this
Inventive embodiments can effectively guarantee the quality of the map datum generated.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, needed in being described below to the embodiment of the present invention
Attached drawing to be used is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention,
For those of ordinary skill in the art, without any creative labor, it can also obtain according to these attached drawings
Take other attached drawings.
Fig. 1 is one of the flow chart of data processing method provided in an embodiment of the present invention；
Fig. 2 is the schematic diagram that the layering ratio of the first process points cloud is determined in the embodiment of the present invention；
Fig. 3 is the two of the flow chart of data processing method provided in an embodiment of the present invention；
Fig. 4 is the structural block diagram of data processing equipment provided in an embodiment of the present invention；
Fig. 5 is the structural schematic diagram of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, those of ordinary skill in the art's acquired every other implementation without creative efforts
Example, shall fall within the protection scope of the present invention.
Data processing method provided in an embodiment of the present invention is illustrated first below.
It should be noted that data processing method provided in an embodiment of the present invention is applied to electronic equipment.Specifically, electronics
Equipment can be server or the other equipment with data operation and processing function.In order to make it easy to understand, the present invention is implemented
It is illustrated in case where electronic equipment is server in example.
Referring to Fig. 1, the flow chart of data processing method provided in an embodiment of the present invention is shown in figure.As shown in Figure 1, should
Method includes the following steps:
Step 101, according to original point cloud, splicing and fusion treatment is carried out, the first process points cloud is obtained.
Before step 101, server needs first to obtain original point cloud.Specifically, original point cloud acquisition equipment (in order to
It is subsequent that the acquisition equipment of original point cloud is referred to as acquired into equipment convenient for explanation) it can be deployed in vehicle, server can be following
Carry acquisition equipment original point cloud collected.
In general, need the data volume of original point cloud to be used very huge when carrying out three-dimensional high-precision map generation,
Even across processing is vacuated, the data volume in a city can also reach TB rank；Wherein, TB is the unit of hard-disk capacity, 1TB
=1000GB=1000000MB.Therefore, when carrying out the downloading of original point cloud, multiple threads can be called, it is asynchronous to carry out batch
Downloading.It is understood that point cloud can be divided into three levels of organization, it is tile (i.e. 10 kilometers * 10 kilometers), node (i.e. 50 respectively
* 50 meters of rice), cell (i.e. 1 meter * 1 meter) once requests to download to obtain when each downloading request is using batch asynchronous downloading
The data of multiple node.In addition, acquisition equipment can use asynchronous response mode in order not to occlusion program.
Since server is downloaded to have obtained original point cloud, server is subsequent can to carry out splicing according to original point cloud
And fusion treatment, to obtain the first process points cloud.It should be noted that being carried out at splicing and fusion according to original point cloud
The specific implementation form multiplicity of reason, carries out citing introduction below.
In a kind of way of realization, according to original point cloud, splicing and fusion treatment are carried out, comprising:
According to original point cloud, intermediate point cloud is generated；Wherein, including the key message in original point cloud in intermediate point cloud；
Splicing and fusion treatment are carried out to intermediate point cloud.
In this way of realization, for the data of multiple node, garbage therein can be abandoned, such as will only be
Rgb (wherein, r represents red, and g represents green, and b the represents blue) value for showing and being arranged abandons, and really will be used for ground
The key message of figure production operation retains, these key messages may be constructed intermediate point cloud.Since the memory of server is limited
, after obtaining intermediate point cloud, intermediate point cloud can be written in caching, and construct index, carry out a cloud in order to subsequent
Lookup.
When needing to carry out the production of three-dimensional high-precision map, server can obtain intermediate point cloud, and centering from caching
Between point cloud carry out splicing and fusion treatment, to obtain the first process points cloud.It is understood that the fusion treatment of point cloud
Effect is: noise, layering and the redundancy of the point cloud of the multi-angle of view as caused by measurement error and matching error etc. overlapping region are eliminated, with
Establish that minutia is clear, the single layer point cloud model of surface smoothing.
As it can be seen that electronic equipment is only needed to the intermediate point including the key message in original point cloud in this way of realization
Cloud carries out splicing and fusion treatment, can efficiently reduce the operand for the treatment of process in this way, with improve processing speed and
Treatment effeciency.
Certainly, according to original point cloud, the way of realization for carrying out splicing and fusion treatment is not limited to above situation.
For example, after the original point cloud that downloading obtains acquisition equipment acquisition, server directly original point cloud can be written slow
In depositing, and construct index；When needing to carry out the production of three-dimensional high-precision map, server can directly obtain from caching original
Point cloud, and splicing and fusion treatment are carried out to original point cloud, to obtain the first process points cloud.
Step 102, in the case where the first process points cloud is unsatisfactory for the first preset condition, the input operation of user is received；
Wherein, input operation is for specifying the characteristic point of the same name in the first process points cloud.
Here, the first preset condition can be a foundation for judging some cloud qualities.
Specifically, if the first process points cloud meet the first preset condition, it is believed that the quality of the first process points cloud compared with
It is good, it can execute subsequent map directly according to the first process points cloud and generate Job Operations.
If the first process points cloud is unsatisfactory for the first preset condition, it is believed that the poor quality of the first process points cloud is
Avoid influencing the quality for the map datum being subsequently generated, server can be exported by modes such as voice, texts for table
The quality prompt information of problems of the first process points cloud is levied, and receives user and is operated according to the input that prompt information executes；
Wherein, input operation is for specifying the characteristic point of the same name in the first process points cloud.In general, existing in the first process points cloud
The characteristic point of the same name of substantial amounts, input operation can only specify part characteristic point of the same name in the first process points cloud, example
Characteristic point of the same name, the characteristic point of the same name on bar, the characteristic point of the same name on ground on such as specified board.
Step 103, according to characteristic point of the same name, fusion treatment is carried out to the first process points cloud, obtains second processing point cloud.
It in step 103, can be according to the characteristic point of the same name in the first specified process points cloud of input operation, to first
Process points cloud carries out further fusion treatment, further to eliminate the point of the multi-angle of view as caused by measurement error and matching error etc.
Noise, layering and the redundancy in cloud sector domain, to obtain for the first process points cloud quality more preferably second processing point cloud.
Step 104, meet the first preset condition, and characteristic point of the same name in second processing point cloud in second processing point cloud
In the case that distance is less than the first pre-determined distance, according to second processing point cloud, map producing Job Operations are executed.
After obtaining second processing point cloud, electronic equipment may determine that whether second processing point cloud meets the first default item
Part, and judge the distance of characteristic point of the same name in second processing point cloud whether less than the first pre-determined distance.Here, first is default
Condition is as a foundation for judging some cloud qualities, and characteristic point distance of the same name is as judging point cloud quality
Another foundation.
If second processing point cloud meets the first preset condition, and the distance of the characteristic point of the same name in second processing point cloud is small
In the first pre-determined distance, this explanation is according to above-mentioned for judging two kinds of foundations of some cloud qualities, the matter of second processing point cloud
Amount is preferable, and at this moment, server can execute subsequent map and generate Job Operations, in this way, subsequent according to second processing point cloud
The quality of the map datum of generation can effectively be guaranteed.
If second processing point cloud is unsatisfactory for the first preset condition, and/or, characteristic point of the same name in second processing point cloud
Distance is greater than or equal to the first pre-determined distance, this illustrates in two kinds of foundations according to above-mentioned for judging some cloud qualities extremely
Few one, there are problems for the quality of second processing point cloud, and at this moment, server can be exported by modes such as voice, texts and is used for
The quality prompt information of problems of second processing point cloud is characterized, and receives user and is grasped according to the input that the prompt information executes
Make；Wherein, input operation is for specifying the characteristic point of the same name in second processing point cloud.Later, server can be defeated according to this
Enter the specified characteristic point of the same name of operation, fusion treatment is carried out to second processing point cloud, subsequent process is referring to the first process points
The explanation for the step of executing after cloud progress fusion treatment, details are not described herein.
In the embodiment of the present invention, in order to carry out the production of three-dimensional high-precision map, it can be spliced first according to original point cloud
Processing and fusion treatment, obtain the first process points cloud, next, whether the first preset condition is met according to the first process points cloud,
It can be determined that whether the quality of the first process points cloud meets the requirements.The case where requiring is unsatisfactory in the quality of the first process points cloud
Under, the characteristic point of the same name of the first process points cloud can be specified, in order to melt accordingly to the first process points cloud by manpower intervention
Conjunction processing, to obtain quality more preferably second processing point cloud.Later, it is pre- that first whether can be met according to second processing point cloud
If whether the distance of condition and the characteristic point of the same name in second processing point cloud determines second processing less than the first pre-determined distance
Whether the quality of point cloud meets the requirements.It, can be according to second processing in the case where the quality of second processing point cloud is met the requirements
Point cloud, executes map producing Job Operations.As it can be seen that in the embodiment of the present invention, the point Yun Laijin that can be met the requirements according to quality
The production of the three-dimensional high-precision map of row, in this way, the algorithm dependent on point cloud will not be interfered, therefore, compared with prior art, this
Inventive embodiments can effectively guarantee the quality of the map datum generated.
Optionally, include the point cloud of different acquisition time acquisition in original point cloud, include corresponding to not in the first process points cloud
With the process points cloud of acquisition time；
In the case where the first process points cloud is unsatisfactory for the first preset condition, before the input operation for receiving user, the party
Method further include:
According to the process points cloud of corresponding different acquisition time, the spatial position of same object is determined respectively；
According to the distance of identified each spatial position, determine whether the first process points cloud meets the first preset condition.
It should be noted that object involved in the present embodiment can be any in board, bar or actual three-dimensional space
Fixed object.
When it is implemented, acquisition equipment can carry out the acquisition of a cloud periodically in the driving process of vehicle.Assuming that all
The point cloud of phase T1 acquisition is D1, and the point cloud that cycle T 2 acquires is D2, and the point cloud that cycle T 3 acquires is D3, the point cloud that cycle T 4 acquires
For D4, then, it may include D1, D2, D3 and D4 in original point cloud may include correspondingly corresponding T1 in the first process points cloud
D1 ', the D2 ' of corresponding T2, the D3 ' of corresponding T3, and corresponding T4 D4 '.
Next, the spatial position of same rod (such as bar G) can be determined respectively according to D1 ' to D4 '.Assuming that basis
The spatial position that D1 ' is determined is W1, is W2 according to the spatial position that D2 ' is determined, is according to the spatial position that D3 ' is determined
W3, the spatial position determined according to D4 ' are W4, it is possible to according to this distance between any two of W1 to W4, determine the
Whether one process points cloud meets the first preset condition.
Since in actual three-dimensional space, the spatial position of G is fixed and invariable, then, if W1 to W4 this two
The distance between two is very big, it may be considered that there are quality problems for the first process points cloud, can be determined that the first processing at this time
Point cloud is unsatisfactory for the first preset condition；On the contrary, can be determined that if this distance between any two of W1 to W4 is very small
First process points cloud meets the first preset condition.
As it can be seen that, by the judgement of spatial position distance, more convenient can be reliably determined out at first in the present embodiment
Whether reason point cloud meets the first preset condition.
Optionally, in the case where the first process points cloud is unsatisfactory for the first preset condition, the input for receiving user operates it
Before, this method further include:
Determine the target information of the first process points cloud；Wherein, target information includes reflective information, hierarchical information, dislocation letter
At least one of breath and block information；
According to target information, determine whether the first process points cloud meets the first preset condition.
Here, reflective information may include reflectivity；Hierarchical information may include layering ratio；The information that misplaces may include mistake
Bit rate；Block information may include shielding rate.According to target information, it is possible to determine that at least one of following: (1) the first process points cloud
Reflectivity whether meet the requirements；Whether the delamination in (2) first process points clouds is serious；In (3) first process points clouds
Whether misalignment is serious；Whether the circumstance of occlusion in (4) first process points clouds is serious.
It later, can be according to judgement as a result, judging the quality of the first process points cloud.Specifically, if the first processing
The reflectivity of point cloud meets the requirements, and delamination, misalignment and circumstance of occlusion be not serious, it may be considered that the first processing
The quality of point cloud is preferable, it is possible to determine that the first process points cloud meets the first preset condition.If the first process points cloud is anti-
It is undesirable to penetrate rate, and/or, at least one of delamination, misalignment and circumstance of occlusion are serious, it may be considered that the
There are quality problems for one process points cloud, it is possible to determine that the first process points cloud is unsatisfactory for the first preset condition.
As it can be seen that in the present embodiment, according to target information, more convenient the first process points cloud can be reliably determined out whether
Meet the first preset condition.
Optionally, the acquisition deployed with devices of original point cloud is in vehicle；
Determine the target information of the first process points cloud, comprising:
Obtain the first track of vehicle data；Wherein, the first track of vehicle data are corresponding with the first track of vehicle；
For each tracing point in M tracing point on the first track of vehicle, selected on its corresponding tangent line multiple
Checkpoint；Wherein, M is integer more than or equal to 1, the corresponding ray in each checkpoint, the corresponding ray in any checkpoint
Starting point is this checkpoint and direction is gravity direction；
It for each checkpoint, determines in the first process points cloud, the target in the corresponding solid region in this checkpoint
Point cloud；Wherein, the corresponding solid region in any checkpoint is using the corresponding ray in this checkpoint as center axis, and bottom surface radius is pre-
If the cylindrical region of radius；
According to the corresponding target point cloud in each checkpoint, the layering letter rate of the first process points cloud is determined.
Here, the value of M can be 1,2,3,4 or 5, the checkpoint selected on the corresponding tangent line of each tracing point
Number can be 2,3,4,5 perhaps 6 pre-set radius can be 0.1 meter, 0.12 meter or 0.15 meter, certainly, the value of M, every
The number of checkpoint and the value of pre-set radius selected on tangent line is not limited thereto, specifically can be according to practical feelings
Condition determines, herein will not enumerate.In addition, gravity direction may be considered Z axis negative direction.
In the present embodiment, in the driving process of vehicle, vehicle can call global positioning system (Global
Positioning System, GPS) it is positioned, to obtain the first track of vehicle data corresponding with the first track of vehicle.Vehicle
Obtained first track of vehicle data can be sent to server, in order to which server is according to the first track of vehicle number
According to obtaining the first track of vehicle.
Assuming that the first track of vehicle is the track 200 in Fig. 2, for this 3 tracks J10, J20 and J30 on track 200
Point can do the tangent line of track 200 respectively, to obtain tangent line Q1, tangent line Q2 and tangent line Q3；Wherein, Q1 is corresponding with J10, Q2 with
J20 is corresponding, and Q3 is corresponding with J30.Next, multiple checkpoints can be selected on Q1, Q2 and Q3 respectively, for Q1, Q2 and Q3
Any one of for, the spacing of adjacent checkpoint thereon can be identical, the spacing can be 0.4 meter, 0.5 meter, 0.6 meter
Deng.
Specifically, it is assumed that be directed to J10, selected five checkpoints, wherein checkpoint centered on J10, J11, J12,
J13, J14 are evenly arranged on the two sides J10, then, it for J11, can determine in the first process points cloud, be located at the corresponding three-dimensional area J11
Target point cloud D11 in domain；It for J12, can determine in the first process points cloud, the mesh in the corresponding solid region of J12
Punctuate cloud D12；It for J10, can determine in the first process points cloud, the target point cloud in the corresponding solid region of J10
D10；It for J13, can determine in the first process points cloud, the target point cloud D13 in the corresponding solid region of J13；For
J14 can determine in the first process points cloud, the target point cloud D14 in the corresponding solid region of J14.It should be noted that
The mode of the corresponding target point cloud in other checkpoints is determined referring to above description, details are not described herein.
Later, the layering ratio of the first process points cloud can be determined, below to true according to the corresponding target point cloud in each checkpoint
The specific implementation form of the layering ratio of fixed first process points cloud carries out citing introduction.
In a kind of way of realization, according to the corresponding target point cloud in each checkpoint, the layering ratio of the first process points cloud is determined,
Include:
It for each checkpoint, determines in its corresponding target point cloud, the point cloud positioned at ground；According to for each checkpoint
The point cloud determined, determines the layering ratio of the first process points cloud.
Here, server can carry out the semantic segmentation of a cloud, with according to semantic segmentation as a result, identification target point Yun Zhongwei
Point cloud in ground.Later, the layering ratio of the first process points cloud can be determined according only to the point cloud for being located at ground.It may be noted that
, according to semantic segmentation as a result, may recognize that the point cloud at tunnel, grade separation.
In this way of realization, determining can guarantee to determine in this way when layering ratio only with reference to the point cloud for being located at ground
As a result accuracy and efficiency.
In another way of realization, according to the corresponding target point cloud in each checkpoint, the layering of the first process points cloud is determined
Rate, comprising:
It for each checkpoint, calculates in its corresponding target point cloud, its except maximum height value and minimum height values
The average value being calculated is compared, according to obtained comparison result, really by the average value of reinforcement angle value with default average value
Whether the fixed corresponding target point cloud in this checkpoint is layered；Whether it is layered according to the corresponding target point cloud in each checkpoint,
Determine the layering ratio of the first process points cloud.
Continue the example in Fig. 2, is being directed to J10, is determining in the first process points cloud, be located at the corresponding solid region of J10
It, can be suitable according to size by the height value (it is it is also assumed that be the coordinate value of Z-direction) in D10 after interior target point cloud D10
Sequence is ranked up, to obtain the collating sequence of Z coordinate.Next, the maximum coordinate value among and minimum in collating sequence can be abandoned
Coordinate value, calculates the average value of other coordinate values in collating sequence, and by the average value being calculated and default average value into
Row compares.If the average value being calculated is greater than default average value, it may be considered that D10 is layered；Otherwise, can recognize
It is not layered for D10.
It should be noted that can also determine respectively whether D11 to D14 is layered using above-mentioned strategy.For
Checkpoint on the corresponding tangent line Q1 of J10, if it exceeds the corresponding target in checkpoint of certain proportion (such as 50%, 60% etc.)
Point cloud is layered, it may be considered that a cloud layering has occurred at J10.
Using aforesaid way, it can also determine a cloud layering whether has occurred at J20 and J30.Later, according to having occurred
The ratio of the tracing point of point cloud layering, can determine the layering ratio of the first process points cloud.Specifically, a cloud layering is having occurred
When the ratio of tracing point is 2%, it can determine that the layering ratio of the first process points cloud is 2%.
It should be noted that if the layering ratio of the first process points cloud is more than 2%, i.e. more than 2% in the first process points cloud
Point cloud there are delaminations, it may be considered that the first process points cloud is unsatisfactory for the first preset condition.
In this way of realization, in conjunction with Z coordinate value, more convenient layering ratio can be reliably determined out, also, determined
Maximum height value and minimum height values are eliminated in journey, can effectively reduce the error of definitive result in this way.
As it can be seen that in the present embodiment, in conjunction with track of vehicle information, very convenient the first process points cloud can be reliably determined out
Layering ratio information.
Optionally, the acquisition deployed with devices of original point cloud is in vehicle；
According to original point cloud, before carrying out splicing and fusion treatment, this method further include:
Obtain the second track of vehicle data；Wherein, the second track of vehicle data are corresponding with the second track of vehicle；
First verification is carried out to the second track of vehicle data；Wherein, the first verification includes completeness check, correctness verification
At least one of with precision checking；
According to original point cloud, splicing and fusion treatment are carried out, comprising:
In the case where the first verification to the second track of vehicle data passes through, according to original point cloud, splicing is carried out
And fusion treatment.
It should be noted that the acquisition modes of the second track of vehicle data are referring to the acquisition side to the first track of vehicle data
The explanation of formula, details are not described herein.
In general, the coordinate information in original point cloud is determined using the tracing point in the second track of vehicle as origin
, in the case where the first verification to the second track of vehicle data passes through, this second track of vehicle data of explanation is complete, quasi-
Really, reliably data according to original point cloud, carry out splicing and fusion treatment, after capable of preferably guaranteeing on this basis
The quality of the continuous map datum generated.
Optionally, the first verification includes completeness check；
First verification is carried out to the second track of vehicle data, comprising:
Correspond to a plurality of second track of vehicle in the second track of vehicle data, and be respectively present in a plurality of second track of vehicle with
In the case where the track of vehicle of every path matching in default map, the completeness check to the second track of vehicle data is determined
Pass through；Otherwise, it determines not passing through to the completeness check of the second track of vehicle data.
Here, default map can be two-dimensional map；Any track in default map, and in default map should
The track of vehicle of path matching may be considered identical track, can be matched using matching algorithm when carrying out the matching of track
Algorithm can use hidden Markov model.
In general, needing to carry out on every road in the default map original when carrying out the map generalization of high-precision ground
The acquisition of point cloud, also, when carrying out the acquisition of original point cloud, vehicle can call GPS simultaneously, carry out the acquisition of track data.
In this way, corresponding to a plurality of second track of vehicle in the second track of vehicle data, and there is default map in a plurality of second track of vehicle
In each track in the case where, it is believed that the second track of vehicle data be it is complete, completeness check passes through；Otherwise,
Determine that its completeness check does not pass through.
As it can be seen that in the present embodiment, based on default map, more convenient the second track of vehicle data can be reliably determined out
Completeness check whether pass through.
Optionally, the first verification includes that correctness verifies；
First verification is carried out to the second track of vehicle data, comprising:
Meet the second preset condition in the second track of vehicle data, and according to the second track of vehicle data, determines second
In track of vehicle, adjacent track point distance is greater than the first preset ratio, and adjacent track point less than the ratio of the second pre-determined distance
In the case that the ratio that distance is less than third pre-determined distance is equal to the second preset ratio, determine to the second track of vehicle data just
True property verification passes through；Otherwise, it determines the correctness verification to the second track of vehicle data does not pass through；
Wherein, third pre-determined distance is greater than the second pre-determined distance, and the second preset ratio is greater than the first preset ratio.
Here, the second track of vehicle data can exist with document form, and this document is referred to as EOUT.Second is default
Distance can be 5 meters, and the first preset ratio can be 99%, and third pre-determined distance can be 10 meters, and the second preset ratio can be with
It is 100%, certainly, the second pre-determined distance, the first preset ratio, the value of third pre-determined distance and the second preset ratio not office
It is limited to this, can specifically determines, will not enumerate herein according to the actual situation.
When it is implemented, correctness verification can refer to following information:
(1) format of EOUT is correct (i.e. the resolving of EOUT is correct)；
(2) timestamp of EOUT is continuous as unit of 0.05 orderly increases；
(3) both the start-stop end time difference of EOUT and start-stop end time difference of GPS were differed less than 5 seconds；
(4) the last timestamp that rises of EOUT includes point cloud and picture All Time stamp, that is to say, that is carried out a little in acquisition equipment
The acquisition of cloud, for camera when carrying out the shooting of image, GPS is also in the record for carrying out location information, in order to obtain corresponding vehicle
Track data；
(5) less than 5 meters accountings of adjacent two o'clock plan range (i.e. adjacent track point distance) are greater than or equal to 5 meters of accountings and are greater than
Or it is equal to 99%, and less than 10 meters accountings are equal to 100%；
Less than 0.25 meter accounting of (6) 0.1 seconds time interval track depth displacements is greater than or equal to 99%.
It should be noted that in the case that above-mentioned (1) is all satisfied to (3), it is believed that the second track of vehicle data
Meet the second preset condition, on this basis, if above-mentioned (4) to (6) are also all satisfied, can determine the second track of vehicle
The correctness verification of data passes through.If any one of above-mentioned (1) to (6) are unsatisfactory for, the second vehicle rail can be determined
The correctness verification of mark data does not pass through.
As it can be seen that in the present embodiment, using aforesaid way, more convenient the second track of vehicle data can be reliably determined out
Correctness verification whether pass through.
Optionally, the first verification includes precision checking；
First verification is carried out to the second track of vehicle data, comprising:
According to the second track of vehicle data, determine that the track hopping value of the second track of vehicle is less than default hop value, and
In the case that the vehicle coordinate difference that second track of vehicle and third track of vehicle correspond to same spatial location is less than preset difference value,
Determination passes through the precision checking of the second track of vehicle data；Otherwise, it determines not to the precision checkings of the second track of vehicle data
Pass through；
Wherein, third track of vehicle is in default map, with the matched track of the second track of vehicle.
Here, default hop value can be 15 centimetres, 20 centimetres or 25 centimetres, certainly, preset the value of hop value simultaneously
It is not limited to this, it can specifically determine according to the actual situation, the present embodiment does not do any restriction to this.
Here, default map can be two-dimensional map, in addition, third track of vehicle may be considered with the second track of vehicle
Identical track can use hidden Markov model using matching algorithm, matching algorithm when carrying out the matching of track.
When it is implemented, precision checking can refer to following information:
(1) same road different tracks difference in height is less than 2 meters；
(2) same road different tracks level error is less than 2 meters；
(3) single time tracing point jump is less than 20 centimetres.
It should be noted that in the case that above-mentioned (1) is all satisfied to (3), it is believed that the second track of vehicle data
Precision checking pass through；When in the ungratified situation in above-mentioned (1) at least one of (3), it is believed that the second vehicle rail
The precision checking of mark data does not pass through.
As it can be seen that in the present embodiment, using aforesaid way, more convenient the second track of vehicle data can be reliably determined out
Precision checking whether pass through.
Optionally, according to original point cloud, before carrying out splicing and fusion treatment, this method further include:
Second verification is carried out to original point cloud；Wherein, the second verification include in completeness check and precision checking at least
One；
According to original point cloud, splicing and fusion treatment are carried out, comprising:
In the case where the second verification to original point cloud passes through, according to original point cloud, carry out at splicing and fusion
Reason.
It should be noted that in the case where passing through to the second of original point cloud the verification, this illustrate original point cloud be it is complete,
Accurate data according to original point cloud, carry out splicing and fusion treatment, can preferably guarantee subsequent on this basis
The quality of the map datum of generation.
Optionally, according to original point cloud, before carrying out splicing and fusion treatment, this method further include:
Obtain three-dimensional bounding box；
Determine the corresponding store path of three-dimensional bounding box；
According to store path, original point cloud is obtained.
It should be noted that server can be by original point after the original point cloud that downloading obtains acquisition equipment acquisition
In cloud write-in caching, and index is constructed, may include pair between the three-dimensional bounding box of original point cloud and store path in index
It should be related to.In this way, subsequent it is to be understood that three-dimensional bounding box, corresponding store path can be determined according to index, and from the storage
Original point cloud is got in path, in order to carry out subsequent processing.As it can be seen that obtaining the operation of original point cloud in the present embodiment
Implement very convenient.
The specific implementation process of the present embodiment is described in detail with a specific example below with reference to Fig. 3.
As shown in figure 3, track data available first, and carry out the judgement of track data access.Here, track provides
Material data are equivalent to the second track of vehicle data above, and data access judgement in track is equivalent to above to the second vehicle rail
Mark data carry out the first verification, then, track data access determines the integrality for capableing of checkpoint cloud acquisition trajectories, and checks
The precision of point cloud acquisition track.
If data access judgement in track does not pass through, track data can be resurveyed.If track data access
Judgement passes through, and can carry out a cloud initial data access and determine.Here, the judgement of point cloud initial data access is equivalent to above right
Original point cloud carries out the first verification, then, point cloud initial data access determines to check the integrality of original point cloud, Yi Jijian
Look into the precision of original point cloud.
If the judgement of fruit dot cloud initial data access does not pass through, original point cloud can be resurveyed.Such as fruit dot cloud initial data
Access judgement passes through, and can successively carry out a cloud and point cloud merges automatically, being merged automatically by cloud and point cloud can
To obtain the first process points cloud.
Next, can carry out a cloud merges quasi- judgement out automatically.Here, point cloud merges quasi- judgement out automatically and is equivalent to
Judge whether the first process points cloud meets the first preset condition in text, then, point cloud merges quasi- judgement out automatically and can check: point
Whether cloud data reflectivity meets the requirements, whether point cloud data is layered, whether point cloud data misplaces and whether point cloud data is deposited
It is blocking.
Pass through as fruit dot cloud merges quasi- judgement out automatically, then map producing operation can be executed according to the first process points cloud
Operation, such as directly carry out lane line modeling.Do not pass through as fruit dot cloud merges quasi- judgement out automatically, then can manually adjust a cloud
Characteristic point, and a cloud artificial fusion is carried out, this is equivalent to above according to same in the first specified process points cloud of input operation
Name characteristic point carries out fusion treatment to the first process points cloud, obtains second processing point cloud.
Go out to determine next, cloud artificial fusion's standard can be carried out.Here, point cloud artificial fusion standard, which goes out, determines to be equivalent to
Judge whether second processing point cloud meets the distance of the first preset condition and the characteristic point of the same name in second processing point cloud in text
Whether less than the first pre-determined distance.
Determine not pass through as fruit dot cloud artificial fusion's standard goes out, then can continue to manually adjust a cloud characteristic point.Such as fruit dot cloud
Artificial fusion's standard, which goes out, to be determined to pass through, then can execute map producing Job Operations, such as directly carry out according to second processing point cloud
Lane line modeling.
By above-mentioned example it is found that in the present embodiment, the point cloud quality examination of systematization can be carried out, to guarantee for executing
The point cloud quality of map producing Job Operations is met the requirements.Checking process is specifically divided into three parts, is respectively: (1) to original
The inspection of data, the mainly inspection to point cloud acquisition track/cloud original document integrality and accuracy；Wherein, cloud is put
Acquisition trajectories are the second track of vehicle data, and point cloud initial data is original point cloud；(2) main to point cloud inspection after automatic fusion
If being characterized in the cloud of checkpoint with the presence or absence of layering/mistake/situations such as blocking and the board/bar extracted in fusion process etc.
It is no accurate, and whether distance is greater than threshold value after fusion；(3) to point cloud inspection after artificial fusion: being mainly in the cloud of checkpoint
It is no that there are layerings/mistake/situations such as blocking, and the same place distance being manually specified after fusion whether be greater than first it is default away from
From.
By experiment it is found that carrying out an inspection for cloud quality using above-mentioned strategy, after a cloud fusion can be efficiently controlled
The quality of data, guarantee that layering/dislocation/point cloud for blocking will not circulate to subsequent cargo handling operation, in this way can will be problematic
Point cloud be reduced to 1% from 10%, carry out the human cost that a cloud quality examination expends and drop to 1 people, and each tile from 5 people
Automatically produce the time control in 30 minutes.
It should be noted that the data volume due to cloud is often very big, when carrying out the inspection of a cloud, in order to accelerate to examine
Speed is looked into, a cloud can be divided into more parts, has adjusted multiple threads (specific number of threads is related to machine nucleus number), per thread
Check the corresponding point cloud data quality in one section of track.During the inspection process, it is related to a swapping in and out for cloud file, in order to guarantee
There are enough memories, needs to be arranged the maximum number of files stayed open in memory and minimum quantity of documents, here it is possible to using
First in first out (First Input First Output, FIFO) strategy needs to close earliest when being more than maximum number of files
It opens and currently without the file used, until quantity of documents is equal to minimum quantity of documents, accounts for memory using this kind of mode
With holding dynamic equilibrium
To sum up, compared with prior art, the present embodiment can effectively guarantee the quality of the map datum generated.
Data processing equipment provided in an embodiment of the present invention is illustrated below.
Referring to fig. 4, the structural block diagram of data processing equipment 400 provided in an embodiment of the present invention is shown in figure.Such as Fig. 4 institute
Show, data processing equipment 400 includes:
First processing module 401, for carrying out splicing and fusion treatment, obtaining the first processing according to original point cloud
Point cloud；
Receiving module 402, for receiving the defeated of user in the case where the first process points cloud is unsatisfactory for the first preset condition
Enter operation；Wherein, input operation is for specifying the characteristic point of the same name in the first process points cloud；
Second processing module 403 obtains for carrying out fusion treatment to the first process points cloud according to characteristic point of the same name
Two process points clouds；
Execution module 404, for meeting the first preset condition in second processing point cloud, and it is of the same name in second processing point cloud
In the case that the distance of characteristic point is less than the first pre-determined distance, according to second processing point cloud, map producing Job Operations are executed.
Optionally, include the point cloud of different acquisition time acquisition in original point cloud, include corresponding to not in the first process points cloud
With the process points cloud of acquisition time；
Data processing equipment 400 further include:
First determining module, for receiving user's in the case where the first process points cloud is unsatisfactory for the first preset condition
Before input operation, according to the process points cloud of corresponding different acquisition time, the spatial position of same object is determined respectively；
Second determining module determines whether the first process points cloud is full for the distance according to identified each spatial position
The first preset condition of foot.
Optionally, data processing equipment 400 further include:
Third determining module, for receiving user's in the case where the first process points cloud is unsatisfactory for the first preset condition
Before input operation, the target information of the first process points cloud is determined；Wherein, target information includes reflective information, hierarchical information, mistake
Position at least one of information and block information；
4th determining module, for determining whether the first process points cloud meets the first preset condition according to target information.
Optionally, the acquisition deployed with devices of original point cloud is in vehicle；
Third determining module, comprising:
Submodule is obtained, for obtaining the first track of vehicle data；Wherein, the first track of vehicle data and the first vehicle rail
Mark is corresponding；
Submodule is selected, each tracing point in M tracing point for being directed on the first track of vehicle is corresponding at its
Multiple checkpoints are selected on tangent line；Wherein, M is the integer more than or equal to 1, the corresponding ray in each checkpoint, any inspection
The starting point of the corresponding ray of point is this checkpoint and direction is gravity direction；
First determines submodule, for being directed to each checkpoint, determines in the first process points cloud, it is corresponding to be located at this checkpoint
Solid region in target point cloud；Wherein, the corresponding solid region in any checkpoint is to be with the corresponding ray in this checkpoint
Central axis, bottom surface radius are the cylindrical region of pre-set radius；
Second determines submodule, for determining the layering of the first process points cloud according to the corresponding target point cloud in each checkpoint
Information.
Optionally, it second determines submodule, is specifically used for:
It for each checkpoint, determines in its corresponding target point cloud, the point cloud positioned at ground；According to for each checkpoint
The point cloud determined, determines the hierarchical information of the first process points cloud；
Optionally, it second determines submodule, is specifically used for:
It for each checkpoint, calculates in its corresponding target point cloud, its except maximum height value and minimum height values
The average value being calculated is compared, according to obtained comparison result, really by the average value of reinforcement angle value with default average value
Whether the fixed corresponding target point cloud in this checkpoint is layered；Whether it is layered according to the corresponding target point cloud in each checkpoint,
Determine the layering ratio of the first process points cloud.
Optionally, first processing module 401, comprising:
Submodule is generated, for generating intermediate point cloud according to original point cloud；It wherein, include original point cloud in intermediate point cloud
In key message；
Submodule is handled, for carrying out splicing and fusion treatment to intermediate point cloud.
Optionally, the acquisition deployed with devices of original point cloud is in vehicle；
Data processing equipment 400 further include:
First obtains module, for before carrying out splicing and fusion treatment, obtaining the second vehicle according to original point cloud
Track data；Wherein, the second track of vehicle data are corresponding with the second track of vehicle；
First correction verification module, for carrying out the first verification to the second track of vehicle data；Wherein, the first verification includes complete
Property verification, correctness verification and at least one of precision checking；
First processing module 401, is specifically used for:
In the case where the first verification to the second track of vehicle data passes through, according to original point cloud, splicing is carried out
And fusion treatment.
Optionally, the first verification includes completeness check；
First correction verification module, is specifically used for:
Correspond to a plurality of second track of vehicle in the second track of vehicle data, and be respectively present in a plurality of second track of vehicle with
In the case where the track of vehicle of every path matching in default map, the completeness check to the second track of vehicle data is determined
Pass through；Otherwise, it determines not passing through to the completeness check of the second track of vehicle data.
Optionally, the first verification includes that correctness verifies；
First correction verification module, is specifically used for:
Meet the second preset condition in the second track of vehicle data, and according to the second track of vehicle data, determines second
In track of vehicle, adjacent track point distance is greater than the first preset ratio, and adjacent track point less than the ratio of the second pre-determined distance
In the case that the ratio that distance is less than third pre-determined distance is equal to the second preset ratio, determine to the second track of vehicle data just
True property verification passes through；Otherwise, it determines the correctness verification to the second track of vehicle data does not pass through；
Wherein, third pre-determined distance is greater than the second pre-determined distance, and the second preset ratio is greater than the first preset ratio.
Optionally, the first verification includes precision checking；
First correction verification module, is specifically used for:
According to the second track of vehicle data, determine that the track hopping value of the second track of vehicle is less than default hop value, and
In the case that the vehicle coordinate difference that second track of vehicle and third track of vehicle correspond to same spatial location is less than preset difference value,
Determination passes through the precision checking of the second track of vehicle data；Otherwise, it determines not to the precision checkings of the second track of vehicle data
Pass through；
Wherein, third track of vehicle is in default map, with the matched track of the second track of vehicle.
Optionally, data processing equipment 400 further include:
Second obtains module, for before carrying out splicing and fusion treatment, obtaining three-dimensional packet according to original point cloud
Enclose box；
5th determining module, for determining the corresponding store path of three-dimensional bounding box；
Third obtains module, for obtaining original point cloud according to store path.
In the embodiment of the present invention, in order to carry out the production of three-dimensional high-precision map, it can be spliced first according to original point cloud
Processing and fusion treatment, obtain the first process points cloud, next, whether the first preset condition is met according to the first process points cloud,
It can be determined that whether the quality of the first process points cloud meets the requirements.The case where requiring is unsatisfactory in the quality of the first process points cloud
Under, the characteristic point of the same name of the first process points cloud can be specified, in order to melt accordingly to the first process points cloud by manpower intervention
Conjunction processing, to obtain quality more preferably second processing point cloud.Later, it is pre- that first whether can be met according to second processing point cloud
If whether the distance of condition and the characteristic point of the same name in second processing point cloud determines second processing less than the first pre-determined distance
Whether the quality of point cloud meets the requirements.It, can be according to second processing in the case where the quality of second processing point cloud is met the requirements
Point cloud, executes map producing Job Operations.As it can be seen that in the embodiment of the present invention, the point Yun Laijin that can be met the requirements according to quality
The production of the three-dimensional high-precision map of row, in this way, the algorithm dependent on point cloud will not be interfered, therefore, compared with prior art, this
Inventive embodiments can effectively guarantee the quality of the map datum generated.
Electronic equipment provided in an embodiment of the present invention is illustrated below.
Referring to Fig. 5, the structural schematic diagram of electronic equipment 500 provided in an embodiment of the present invention is shown in figure.Such as Fig. 5 institute
Show, electronic equipment 500 includes: processor 501, memory 503, user interface 504 and bus interface.
Processor 501 executes following process for reading the program in memory 503:
According to original point cloud, splicing and fusion treatment are carried out, the first process points cloud is obtained；
In the case where the first process points cloud is unsatisfactory for the first preset condition, the input operation of user is received；Wherein, it inputs
Operation is for specifying the characteristic point of the same name in the first process points cloud；
According to characteristic point of the same name, fusion treatment is carried out to the first process points cloud, obtains second processing point cloud；
Meet the first preset condition in second processing point cloud, and the distance of the characteristic point of the same name in second processing point cloud is less than
In the case where first pre-determined distance, according to second processing point cloud, map producing Job Operations are executed.
In Fig. 5, bus architecture may include the bus and bridge of any number of interconnection, specifically be represented by processor 501
One or more processors and the various circuits of memory that represent of memory 503 link together.Bus architecture can be with
Various other circuits of such as peripheral equipment, voltage-stablizer and management circuit or the like are linked together, these are all these
Well known to field, therefore, it will not be further described herein.Bus interface provides interface.For different users
Equipment, user interface 504, which can also be, external the interface for needing equipment is inscribed, and the equipment of connection includes but is not limited to small key
Disk, display, loudspeaker, microphone, control stick etc..
Processor 501, which is responsible for management bus architecture and common processing, memory 503, can store processor 501 and is holding
Used data when row operation.
Optionally, include the point cloud of different acquisition time acquisition in original point cloud, include corresponding to not in the first process points cloud
With the process points cloud of acquisition time；
Processor 501, is also used to:
In the case where the first process points cloud is unsatisfactory for the first preset condition, before the input operation for receiving user, according to
The process points cloud of corresponding different acquisition time, determines the spatial position of same object respectively；
According to the distance of identified each spatial position, determine whether the first process points cloud meets the first preset condition.
Optionally, processor 501 are also used to:
In the case where the first process points cloud is unsatisfactory for the first preset condition, before the input operation for receiving user, determine
The target information of first process points cloud；Wherein, target information includes reflective information, hierarchical information, dislocation information and block information
At least one of；
According to target information, determine whether the first process points cloud meets the first preset condition.
Optionally, the acquisition deployed with devices of original point cloud is in vehicle；
Processor 501, is specifically used for:
Obtain the first track of vehicle data；Wherein, the first track of vehicle data are corresponding with the first track of vehicle；
For each tracing point in M tracing point on the first track of vehicle, selected on its corresponding tangent line multiple
Checkpoint；Wherein, M is integer more than or equal to 1, the corresponding ray in each checkpoint, the corresponding ray in any checkpoint
Starting point is this checkpoint and direction is gravity direction；
It for each checkpoint, determines in the first process points cloud, the target in the corresponding solid region in this checkpoint
Point cloud；Wherein, the corresponding solid region in any checkpoint is using the corresponding ray in this checkpoint as center axis, and bottom surface radius is pre-
If the cylindrical region of radius；
According to the corresponding target point cloud in each checkpoint, the layering ratio of the first process points cloud is determined.
Optionally, processor 501 are specifically used for:
It for each checkpoint, determines in its corresponding target point cloud, the point cloud positioned at ground；According to for each checkpoint
The point cloud determined, determines the layering ratio of the first process points cloud.
Optionally, processor 501 are specifically used for:
It for each checkpoint, calculates in its corresponding target point cloud, its except maximum height value and minimum height values
The average value being calculated is compared, according to obtained comparison result, really by the average value of reinforcement angle value with default average value
Whether the fixed corresponding target point cloud in this checkpoint is layered；Whether it is layered according to the corresponding target point cloud in each checkpoint,
Determine the layering ratio of the first process points cloud.
Optionally, processor 501 are specifically used for:
According to original point cloud, intermediate point cloud is generated；Wherein, including the key message in original point cloud in intermediate point cloud；
Splicing and fusion treatment are carried out to intermediate point cloud.
Optionally, the acquisition deployed with devices of original point cloud is in vehicle；
Processor 501, is specifically used for:
Obtain the second track of vehicle data；Wherein, the second track of vehicle data are corresponding with the second track of vehicle；
First verification is carried out to the second track of vehicle data；Wherein, the first verification includes completeness check, correctness verification
At least one of with precision checking；
According to original point cloud, splicing and fusion treatment are carried out, comprising:
In the case where the first verification to the second track of vehicle data passes through, according to original point cloud, splicing is carried out
And fusion treatment.
Optionally, the first verification includes completeness check；
Processor 501, is specifically used for:
Correspond to a plurality of second track of vehicle in the second track of vehicle data, and be respectively present in a plurality of second track of vehicle with
In the case where the track of vehicle of every path matching in default map, the completeness check to the second track of vehicle data is determined
Pass through；Otherwise, it determines not passing through to the completeness check of the second track of vehicle data.
Optionally, the first verification includes that correctness verifies；
Processor 501, is specifically used for:
Meet the second preset condition in the second track of vehicle data, and according to the second track of vehicle data, determines second
In track of vehicle, adjacent track point distance is greater than the first preset ratio, and adjacent track point less than the ratio of the second pre-determined distance
In the case that the ratio that distance is less than third pre-determined distance is equal to the second preset ratio, determine to the second track of vehicle data just
True property verification passes through；Otherwise, it determines the correctness verification to the second track of vehicle data does not pass through；
Wherein, third pre-determined distance is greater than the second pre-determined distance, and the second preset ratio is greater than the first preset ratio.
Optionally, the first verification includes precision checking；
Processor 501, is specifically used for:
According to the second track of vehicle data, determine that the track hopping value of the second track of vehicle is less than default hop value, and
In the case that the vehicle coordinate difference that second track of vehicle and third track of vehicle correspond to same spatial location is less than preset difference value,
Determination passes through the precision checking of the second track of vehicle data；Otherwise, it determines not to the precision checkings of the second track of vehicle data
Pass through；
Wherein, third track of vehicle is in default map, with the matched track of the second track of vehicle.
In the embodiment of the present invention, in order to carry out the production of three-dimensional high-precision map, it can be spliced first according to original point cloud
Processing and fusion treatment, obtain the first process points cloud, next, whether the first preset condition is met according to the first process points cloud,
It can be determined that whether the quality of the first process points cloud meets the requirements.The case where requiring is unsatisfactory in the quality of the first process points cloud
Under, the characteristic point of the same name of the first process points cloud can be specified, in order to melt accordingly to the first process points cloud by manpower intervention
Conjunction processing, to obtain quality more preferably second processing point cloud.Later, it is pre- that first whether can be met according to second processing point cloud
If whether the distance of condition and the characteristic point of the same name in second processing point cloud determines second processing less than the first pre-determined distance
Whether the quality of point cloud meets the requirements.It, can be according to second processing in the case where the quality of second processing point cloud is met the requirements
Point cloud, executes map producing Job Operations.As it can be seen that in the embodiment of the present invention, the point Yun Laijin that can be met the requirements according to quality
The production of the three-dimensional high-precision map of row, in this way, the algorithm dependent on point cloud will not be interfered, therefore, compared with prior art, this
Inventive embodiments can effectively guarantee the quality of the map datum generated.
Preferably, the embodiment of the present invention also provides a kind of electronic equipment, including processor 501, and memory 503 is stored in
On memory 503 and the computer program that can run on the processor 501, the computer program are executed by processor 501
Each process of the above-mentioned data processing method embodiment of Shi Shixian, and identical technical effect can be reached, to avoid repeating, here
It repeats no more.
The embodiment of the present invention also provides a kind of computer readable storage medium, and meter is stored on computer readable storage medium
Calculation machine program, the computer program realize each process of above-mentioned data processing method embodiment, and energy when being executed by processor
Reach identical technical effect, to avoid repeating, which is not described herein again.Wherein, the computer readable storage medium, such as only
Read memory (Read-Only Memory, abbreviation ROM), random access memory (Random Access Memory, abbreviation
RAM), magnetic or disk etc..
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the art
Under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very much
Form belongs within protection of the invention.
Claims (20)
1. a kind of data processing method, which is characterized in that the described method includes:
According to original point cloud, splicing and fusion treatment are carried out, the first process points cloud is obtained；
In the case where the first process points cloud is unsatisfactory for the first preset condition, the input operation of user is received；Wherein, described
Input operation is for specifying the characteristic point of the same name in the first process points cloud；
According to the characteristic point of the same name, fusion treatment is carried out to the first process points cloud, obtains second processing point cloud；
Meet first preset condition in the second processing point cloud, and the characteristic point of the same name in second processing point cloud
In the case that distance is less than the first pre-determined distance, according to the second processing point cloud, map producing Job Operations are executed.
2. the method according to claim 1, wherein including the acquisition of different acquisition time in the original point cloud
Cloud is put, includes the process points cloud of corresponding different acquisition time in the first process points cloud；
It is described in the case where the first process points cloud is unsatisfactory for the first preset condition, receive user input operation before,
The method also includes:
According to the process points cloud of corresponding different acquisition time, the spatial position of same object is determined respectively；
According to the distance of identified each spatial position, determine whether the first process points cloud meets the first preset condition.
3. the method according to claim 1, wherein described, in the first process points cloud to be unsatisfactory for first default
In the case where condition, before the input operation for receiving user, the method also includes:
Determine the target information of the first process points cloud；Wherein, the target information includes reflective information, hierarchical information, mistake
Position at least one of information and block information；
According to the target information, determine whether the first process points cloud meets the first preset condition.
4. according to the method described in claim 3, it is characterized in that, the acquisition deployed with devices of the original point cloud is in vehicle；
The target information of determination the first process points cloud, comprising:
Obtain the first track of vehicle data；Wherein, the first track of vehicle data are corresponding with the first track of vehicle；
For each tracing point in M tracing point on first track of vehicle, selected on its corresponding tangent line multiple
Checkpoint；Wherein, M is integer more than or equal to 1, the corresponding ray in each checkpoint, the corresponding ray in any checkpoint
Starting point is this checkpoint and direction is gravity direction；
It for each checkpoint, determines in the first process points cloud, the target in the corresponding solid region in this checkpoint
Point cloud；Wherein, the corresponding solid region in any checkpoint is using the corresponding ray in this checkpoint as center axis, and bottom surface radius is pre-
If the cylindrical region of radius；
According to the corresponding target point cloud in each checkpoint, the layering ratio of the first process points cloud is determined.
5. according to the method described in claim 4, it is characterized in that, described according to the corresponding target point cloud in each checkpoint, determination
The layering ratio of the first process points cloud, comprising:
It for each checkpoint, determines in its corresponding target point cloud, the point cloud positioned at ground；It is determined according to for each checkpoint
Point cloud out, determines the layering ratio of the first process points cloud.
6. according to the method described in claim 4, it is characterized in that, described according to the corresponding target point cloud in each checkpoint, determination
The layering ratio of the first process points cloud, comprising:
For each checkpoint, calculate in its corresponding target point cloud, its reinforcement except maximum height value and minimum height values
The average value being calculated is compared by the average value of angle value with default average value, according to obtained comparison result, determines this
Whether the corresponding target point cloud in checkpoint is layered；Whether it is layered, is determined according to the corresponding target point cloud in each checkpoint
The layering ratio of the first process points cloud.
7. the method according to claim 1, wherein described according to original point cloud, progress splicing and fusion
Processing, comprising:
According to original point cloud, intermediate point cloud is generated；Wherein, including the crucial letter in the original point cloud in the intermediate point cloud
Breath；
Splicing and fusion treatment are carried out to the intermediate point cloud.
8. the method according to claim 1, wherein the acquisition deployed with devices of the original point cloud is in vehicle；
It is described according to original point cloud, before carrying out splicing and fusion treatment, the method also includes:
Obtain the second track of vehicle data；Wherein, the second track of vehicle data are corresponding with the second track of vehicle；
First verification is carried out to the second track of vehicle data；Wherein, first verification includes completeness check, correctness
At least one of verification and precision checking；
It is described according to original point cloud, carry out splicing and fusion treatment, comprising:
In the case where the first verification to the second track of vehicle data passes through, according to original point cloud, splicing is carried out
And fusion treatment.
9. according to the method described in claim 8, it is characterized in that, first verification includes completeness check；
It is described that first verification is carried out to the second track of vehicle data, comprising:
A plurality of second track of vehicle is corresponded in the second track of vehicle data, and is deposited respectively in a plurality of second track of vehicle
In the case where the track of vehicle with every path matching in default map, determine to the complete of the second track of vehicle data
Whole property verification passes through；Otherwise, it determines not passing through to the completeness check of the second track of vehicle data.
10. according to the method described in claim 8, it is characterized in that, first verification includes that correctness verifies；
It is described that first verification is carried out to the second track of vehicle data, comprising:
Meet the second preset condition in the second track of vehicle data, and according to the second track of vehicle data, determines
In second track of vehicle, adjacent track point distance is greater than the first preset ratio, and phase less than the ratio of the second pre-determined distance
In the case that the ratio that adjacent tracing point distance is less than third pre-determined distance is equal to the second preset ratio, determine to second vehicle
The correctness verification of track data passes through；Otherwise, it determines the correctness verification to the second track of vehicle data does not pass through；
Wherein, the third pre-determined distance is greater than second pre-determined distance, and it is pre- that second preset ratio is greater than described first
If ratio.
11. according to the method described in claim 8, it is characterized in that, first verification includes precision checking；
It is described that first verification is carried out to the second track of vehicle data, comprising:
According to the second track of vehicle data, determine that the track hopping value of second track of vehicle is less than default jump
Value, and second track of vehicle and third track of vehicle correspond to the vehicle coordinate difference of same spatial location less than preset difference value
In the case where, determination passes through the precision checking of the second track of vehicle data；Otherwise, it determines to second track of vehicle
The precision checking of data does not pass through；
Wherein, the third track of vehicle is in default map, with the matched track of the second track of vehicle.
12. a kind of data processing equipment, which is characterized in that described device includes:
First processing module, for carrying out splicing and fusion treatment, obtaining the first process points cloud according to original point cloud；
Receiving module, for receiving the input of user in the case where the first process points cloud is unsatisfactory for the first preset condition
Operation；Wherein, of the same name characteristic point of the input operation for specifying in the first process points cloud；
Second processing module obtains for carrying out fusion treatment to the first process points cloud according to the characteristic point of the same name
Two process points clouds；
Execution module, for meeting first preset condition in the second processing point cloud, and in second processing point cloud
Characteristic point of the same name distance less than the first pre-determined distance in the case where, according to the second processing point cloud, execute map producing
Job Operations.
13. device according to claim 12, which is characterized in that include acquiring the different acquisition time in the original point cloud
Point cloud, include the process points cloud of corresponding different acquisition time in the first process points cloud；
Described device further include:
First determining module, for receiving user's in the case where the first process points cloud is unsatisfactory for the first preset condition
Before input operation, according to the process points cloud of corresponding different acquisition time, the spatial position of same object is determined respectively；
Second determining module determines whether the first process points cloud is full for the distance according to identified each spatial position
The first preset condition of foot.
14. device according to claim 12, which is characterized in that described device further include:
Third determining module, for receiving user's in the case where the first process points cloud is unsatisfactory for the first preset condition
Before input operation, the target information of the first process points cloud is determined；Wherein, the target information includes reflective information, divides
Layer information, dislocation at least one of information and block information；
4th determining module, for determining whether the first process points cloud meets the first default item according to the target information
Part.
15. device according to claim 14, which is characterized in that the acquisition deployed with devices of the original point cloud is in vehicle；
The third determining module, comprising:
Submodule is obtained, for obtaining the first track of vehicle data；Wherein, the first track of vehicle data and the first vehicle rail
Mark is corresponding；
Submodule is selected, each tracing point in M tracing point for being directed on first track of vehicle is corresponding at its
Multiple checkpoints are selected on tangent line；Wherein, M is the integer more than or equal to 1, the corresponding ray in each checkpoint, any inspection
The starting point of the corresponding ray of point is this checkpoint and direction is gravity direction；
First determines submodule, for being directed to each checkpoint, determines in the first process points cloud, it is corresponding to be located at this checkpoint
Solid region in target point cloud；Wherein, the corresponding solid region in any checkpoint is to be with the corresponding ray in this checkpoint
Central axis, bottom surface radius are the cylindrical region of pre-set radius；
Second determines submodule, for determining the layering of the first process points cloud according to the corresponding target point cloud in each checkpoint
Rate.
16. device according to claim 15, which is characterized in that described second determines submodule, is specifically used for:
It for each checkpoint, determines in its corresponding target point cloud, the point cloud positioned at ground；It is determined according to for each checkpoint
Point cloud out, determines the layering ratio of the first process points cloud.
17. device according to claim 15, which is characterized in that described second determines submodule, is specifically used for:
For each checkpoint, calculate in its corresponding target point cloud, its reinforcement except maximum height value and minimum height values
The average value being calculated is compared by the average value of angle value with default average value, according to obtained comparison result, determines this
Whether the corresponding target point cloud in checkpoint is layered；Whether it is layered, is determined according to the corresponding target point cloud in each checkpoint
The layering ratio of the first process points cloud.
18. device according to claim 12, which is characterized in that the acquisition deployed with devices of the original point cloud is in vehicle；
Described device further include:
First obtains module, for before carrying out splicing and fusion treatment, obtaining the second track of vehicle according to original point cloud
Data；Wherein, the second track of vehicle data are corresponding with the second track of vehicle；
First correction verification module, for carrying out the first verification to the second track of vehicle data；Wherein, it is described first verification include
At least one of completeness check, correctness verification and precision checking；
The first processing module, is specifically used for:
In the case where the first verification to the second track of vehicle data passes through, according to original point cloud, splicing is carried out
And fusion treatment.
19. a kind of electronic equipment, which is characterized in that including processor, memory is stored on the memory and can be described
The computer program run on processor realizes such as claim 1 to 11 when the computer program is executed by the processor
Any one of described in data processing method the step of.
20. 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 data processing side as described in any one of claims 1 to 11 when the computer program is executed by processor
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910265528.4A CN109993700B (en) | 2019-04-03 | 2019-04-03 | Data processing method, device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910265528.4A CN109993700B (en) | 2019-04-03 | 2019-04-03 | Data processing method, device, electronic equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109993700A true CN109993700A (en) | 2019-07-09 |
| CN109993700B CN109993700B (en) | 2023-07-04 |
Family
ID=67131331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910265528.4A Active CN109993700B (en) | 2019-04-03 | 2019-04-03 | Data processing method, device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109993700B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111553353A (en) * | 2020-05-11 | 2020-08-18 | 北京小马慧行科技有限公司 | Processing method and device of 3D point cloud, storage medium and processor |
| CN112455502A (en) * | 2019-09-09 | 2021-03-09 | 中车株洲电力机车研究所有限公司 | Train positioning method and device based on laser radar |
| CN112991162A (en) * | 2019-12-12 | 2021-06-18 | 北京初速度科技有限公司 | Point cloud data layering method and device |
| CN115047471A (en) * | 2022-03-30 | 2022-09-13 | 北京一径科技有限公司 | Method, device and equipment for determining laser radar point cloud layering and storage medium |
| CN115047472A (en) * | 2022-03-30 | 2022-09-13 | 北京一径科技有限公司 | Method, device and equipment for determining laser radar point cloud layering and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1780594A (en) * | 2002-11-07 | 2006-05-31 | 康复米斯公司 | Methods for determining meniscal size and shape and for devising treatment |
| CN104766302A (en) * | 2015-02-05 | 2015-07-08 | 武汉大势智慧科技有限公司 | Method and system for optimizing laser scanning point cloud data by means of unmanned aerial vehicle images |
| CN104794743A (en) * | 2015-04-27 | 2015-07-22 | 武汉海达数云技术有限公司 | Color point cloud producing method of vehicle-mounted laser mobile measurement system |
| CN105701478A (en) * | 2016-02-24 | 2016-06-22 | 腾讯科技（深圳）有限公司 | Method and device for extraction of rod-shaped ground object |
| CN106017320A (en) * | 2016-05-30 | 2016-10-12 | 燕山大学 | Bulk cargo stack volume measuring method based on image processing and system for realizing same |
| CN106017428A (en) * | 2016-05-19 | 2016-10-12 | 江苏省基础地理信息中心 | Method and device for generating three-dimensional data of river views |
| CN106296814A (en) * | 2015-05-26 | 2017-01-04 | 中国公路工程咨询集团有限公司 | Highway maintenance detection and virtual interactive interface method and system |
| CN106680798A (en) * | 2017-01-23 | 2017-05-17 | 辽宁工程技术大学 | Airborne LIDAR air strips overlay region redundancy identification and elimination method |
| CN107741233A (en) * | 2017-11-10 | 2018-02-27 | 邦鼓思电子科技（上海）有限公司 | A kind of construction method of the outdoor map of three-dimensional |
| CN107797129A (en) * | 2017-10-13 | 2018-03-13 | 重庆市勘测院 | Without the cloud data acquisition method and device under GNSS signal |
| CN107918753A (en) * | 2016-10-10 | 2018-04-17 | 腾讯科技（深圳）有限公司 | Processing Method of Point-clouds and device |
| CN108734654A (en) * | 2018-05-28 | 2018-11-02 | 深圳市易成自动驾驶技术有限公司 | It draws and localization method, system and computer readable storage medium |
| CN109064506A (en) * | 2018-07-04 | 2018-12-21 | 百度在线网络技术（北京）有限公司 | Accurately drawing generating method, device and storage medium |
| CN109282822A (en) * | 2018-08-31 | 2019-01-29 | 北京航空航天大学 | Construct storage medium, the method and apparatus of navigation map |
-
2019
- 2019-04-03 CN CN201910265528.4A patent/CN109993700B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1780594A (en) * | 2002-11-07 | 2006-05-31 | 康复米斯公司 | Methods for determining meniscal size and shape and for devising treatment |
| CN104766302A (en) * | 2015-02-05 | 2015-07-08 | 武汉大势智慧科技有限公司 | Method and system for optimizing laser scanning point cloud data by means of unmanned aerial vehicle images |
| CN104794743A (en) * | 2015-04-27 | 2015-07-22 | 武汉海达数云技术有限公司 | Color point cloud producing method of vehicle-mounted laser mobile measurement system |
| CN106296814A (en) * | 2015-05-26 | 2017-01-04 | 中国公路工程咨询集团有限公司 | Highway maintenance detection and virtual interactive interface method and system |
| CN105701478A (en) * | 2016-02-24 | 2016-06-22 | 腾讯科技（深圳）有限公司 | Method and device for extraction of rod-shaped ground object |
| CN106017428A (en) * | 2016-05-19 | 2016-10-12 | 江苏省基础地理信息中心 | Method and device for generating three-dimensional data of river views |
| CN106017320A (en) * | 2016-05-30 | 2016-10-12 | 燕山大学 | Bulk cargo stack volume measuring method based on image processing and system for realizing same |
| CN107918753A (en) * | 2016-10-10 | 2018-04-17 | 腾讯科技（深圳）有限公司 | Processing Method of Point-clouds and device |
| CN106680798A (en) * | 2017-01-23 | 2017-05-17 | 辽宁工程技术大学 | Airborne LIDAR air strips overlay region redundancy identification and elimination method |
| CN107797129A (en) * | 2017-10-13 | 2018-03-13 | 重庆市勘测院 | Without the cloud data acquisition method and device under GNSS signal |
| CN107741233A (en) * | 2017-11-10 | 2018-02-27 | 邦鼓思电子科技（上海）有限公司 | A kind of construction method of the outdoor map of three-dimensional |
| CN108734654A (en) * | 2018-05-28 | 2018-11-02 | 深圳市易成自动驾驶技术有限公司 | It draws and localization method, system and computer readable storage medium |
| CN109064506A (en) * | 2018-07-04 | 2018-12-21 | 百度在线网络技术（北京）有限公司 | Accurately drawing generating method, device and storage medium |
| CN109282822A (en) * | 2018-08-31 | 2019-01-29 | 北京航空航天大学 | Construct storage medium, the method and apparatus of navigation map |
Non-Patent Citations (4)
| Title |
|---|
| 吴海若: "融合车载扫描和航空影像数据的建筑物三维建模——以纽约布法罗为例", 《中国优秀硕士学位论文全文数据库基础科学辑》 * |
| 吴海若: "融合车载扫描和航空影像数据的建筑物三维建模——以纽约布法罗为例", 《中国优秀硕士学位论文全文数据库基础科学辑》, no. 01, 15 January 2014 (2014-01-15), pages 008 - 72 * |
| 郭世敏: "基于无人机航摄影像的大比例尺测图及三维建模研究", 《中国优秀硕士学位论文全文数据库基础科学辑》 * |
| 郭世敏: "基于无人机航摄影像的大比例尺测图及三维建模研究", 《中国优秀硕士学位论文全文数据库基础科学辑》, no. 01, 15 January 2018 (2018-01-15), pages 008 - 165 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112455502A (en) * | 2019-09-09 | 2021-03-09 | 中车株洲电力机车研究所有限公司 | Train positioning method and device based on laser radar |
| CN112991162A (en) * | 2019-12-12 | 2021-06-18 | 北京初速度科技有限公司 | Point cloud data layering method and device |
| CN112991162B (en) * | 2019-12-12 | 2023-09-19 | 北京魔门塔科技有限公司 | Layering method and device for point cloud data |
| CN111553353A (en) * | 2020-05-11 | 2020-08-18 | 北京小马慧行科技有限公司 | Processing method and device of 3D point cloud, storage medium and processor |
| CN111553353B (en) * | 2020-05-11 | 2023-11-07 | 北京小马慧行科技有限公司 | Processing method and device of 3D point cloud, storage medium and processor |
| CN115047471A (en) * | 2022-03-30 | 2022-09-13 | 北京一径科技有限公司 | Method, device and equipment for determining laser radar point cloud layering and storage medium |
| CN115047472A (en) * | 2022-03-30 | 2022-09-13 | 北京一径科技有限公司 | Method, device and equipment for determining laser radar point cloud layering and storage medium |
| CN115047471B (en) * | 2022-03-30 | 2023-07-04 | 北京一径科技有限公司 | Method, device, equipment and storage medium for determining laser radar point cloud layering |
| WO2023185927A1 (en) * | 2022-03-30 | 2023-10-05 | 北京一径科技有限公司 | Method, apparatus and device for determining layering of point cloud of lidar, and storage medium |
| WO2023185943A1 (en) * | 2022-03-30 | 2023-10-05 | 北京一径科技有限公司 | Method, apparatus and device for determining lidar point cloud layering, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109993700B (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109993700A (en) | Data processing method, device, electronic equipment and computer readable storage medium | |
| CN105589471B (en) | Unmanned plane during flying track method for drafting, device and system | |
| CN109669401A (en) | The building site data acquisition of unmanned vehicle auxiliary | |
| CN102779428B (en) | Guiding method and system of parking lot | |
| CN109612474A (en) | A kind of map road matching process, device, server and storage medium | |
| CN110329266A (en) | Can course continuation mileage determine method, apparatus, terminal and storage medium | |
| CN105758413B (en) | The method and apparatus of automation assessment yaw in navigation engine | |
| CN1965212A (en) | Map updating system | |
| CN102032910B (en) | Real-time self-investigation new path generating method of vehicle-mounted navigation map | |
| CN104866500A (en) | Method and device for displaying pictures in classified manner | |
| CN102142023A (en) | Map data, map data production method, storage medium and navigation apparatus | |
| CN110532276A (en) | Map updating method and updating device, vehicle | |
| CN108897724A (en) | Function schedule determines method and device | |
| CN108717796A (en) | A kind of geographical ramp self-learning method and system of vehicle | |
| CN108280995A (en) | Road condition data processing method, device and the computer equipment of car networking | |
| CN108288201A (en) | The method and device of stroke expense bill is provided in net about vehicle system for target user | |
| CN109947881A (en) | A kind of POI judging method, device, mobile terminal and computer readable storage medium | |
| FR2965911A1 (en) | METHOD AND DEVICE FOR DETERMINING ROAD INCLINATION INFORMATION | |
| CN110379165A (en) | A kind of road type prediction technique, device, equipment and storage medium | |
| CN109525946A (en) | A kind of safety prompt function method and device | |
| CN110060139A (en) | Accounting processing method and device | |
| CN105806347B (en) | A kind of true three-dimensional navigation method of gradient section and a kind of true three-dimensional navigation equipment | |
| CN110362640A (en) | A kind of method for allocating tasks and device based on electronic map data | |
| CN110363848A (en) | A kind of method for visualizing and device of the pore network model based on digital cores | |
| CN112632399B (en) | Topological relation obtaining method and device based on spatial position 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |