CN109635050A - Map accuracy estimating method and apparatus - Google Patents
Map accuracy estimating method and apparatus Download PDFInfo
- Publication number
- CN109635050A CN109635050A CN201811290711.1A CN201811290711A CN109635050A CN 109635050 A CN109635050 A CN 109635050A CN 201811290711 A CN201811290711 A CN 201811290711A CN 109635050 A CN109635050 A CN 109635050A
- Authority
- CN
- China
- Prior art keywords
- map
- evaluated
- region
- matching index
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Instructional Devices (AREA)
Abstract
The present invention provides a kind of map accuracy estimating method and apparatus.This method, it include: according to Reference Map and map to be evaluated, determine the Region Matching index and lines matching index of the map to be evaluated, the Region Matching index is used to indicate the Region Matching degree between the map to be evaluated and the Reference Map, and the lines matching index is used to indicate the lines matching degree between the map to be evaluated and the Reference Map;According to the Region Matching index and the lines matching index, the accuracy of the map to be evaluated is evaluated.It is compared with rate of precision in the prior art with recall rate, Region Matching index and lines matching index are better able to the difference of the map that reflection generates and true map, therefore, the accuracy of the map of generation is evaluated using Region Matching index and lines matching index, it is as a result relatively reliable.
Description
Technical field
The present invention relates to field of intelligent transportation technology more particularly to a kind of map accuracy estimating method and apparatus.
Background technique
With the intelligence of automotive engineering, pilotless automobile comes into being.Pilotless automobile is driven by interior intelligence
Instrument is sailed to realize unpiloted purpose.In pilotless automobile driving process, intelligent driving instrument can generate map, for row
Security standpoint is sailed, needs to be analyzed and evaluated the map of generation, to determine between the map and true map that generate
Difference, and then the map of generation is adjusted.
In the prior art, generally use the indexs such as rate of precision and recall rate common in semantic segmentation to the map of generation into
Row analysis and evaluation.However, this kind of metrics evaluation is the classification put, the accuracy of to map evaluation is not high.
Summary of the invention
The present invention provides a kind of map accuracy estimating method and apparatus, to improve cartographic evaluation accuracy.
In a first aspect, the present invention provides a kind of map accuracy estimating method, comprising:
According to Reference Map and map to be evaluated, determine that the Region Matching index of the map to be evaluated and lines matching refer to
Mark, the Region Matching index is used to indicate the Region Matching degree between the map to be evaluated and the Reference Map, described
Lines matching index is used to indicate the lines matching degree between the map to be evaluated and the Reference Map;
According to the Region Matching index and the lines matching index, the accuracy of the map to be evaluated is commented
Valence.
Optionally, the Region Matching index includes at least one of following index: the ratio in undermatching region or
Degree of overlapping with region;Wherein, the undermatching region is used to indicate on the map to be evaluated and fails and the Reference Map
The region of successful match, the matching area are used to indicate the area on the map to be evaluated with the Reference Map successful match
Domain.
Optionally, the lines matching index includes at least one of following index: the ratio of undermatching line, matched line
The average departure deviation of maximum distance difference or matched line.
Optionally, described according to Reference Map and map to be evaluated, determine the Region Matching index of the map to be evaluated
With lines matching index, comprising:
By each travelable region that the map to be evaluated is included and each travelable area that the Reference Map is included
Domain carries out matching primitives, obtains the Region Matching index;
By each lane line that the map to be evaluated is included and each lane line that the Reference Map is included progress
With calculating, the lines matching index is obtained.
Optionally, described according to the Region Matching index and the lines matching index, to the standard of the map to be evaluated
Exactness is evaluated, comprising:
According to the Region Matching index and the lines matching index, the map to be evaluated and the Reference Map are determined
Between difference;
According to the difference between the map to be evaluated and the Reference Map, to the accuracy of the map to be evaluated into
Row evaluation.
Optionally, the above method, further includes:
According to the difference between the map to be evaluated and the Reference Map, the map to be evaluated is adjusted.
Second aspect, the present invention provide a kind of map accuracy estimating device, comprising:
Determining module, for determining that the Region Matching of the map to be evaluated refers to according to Reference Map and map to be evaluated
Mark and lines matching index, the Region Matching index are used to indicate the region between the map to be evaluated and the Reference Map
Matching degree, the lines matching index are used to indicate the lines matching degree between the map to be evaluated and the Reference Map;
Evaluation module is used for according to the Region Matching index and the lines matching index, to the map to be evaluated
Accuracy is evaluated.
Optionally, the Region Matching index includes at least one of following index: the ratio in undermatching region or
Degree of overlapping with region;Wherein, the undermatching region is used to indicate on the map to be evaluated and fails and the Reference Map
The region of successful match, the matching area are used to indicate the area on the map to be evaluated with the Reference Map successful match
Domain.
Optionally, the lines matching index includes at least one of following index: the ratio of undermatching line, matched line
The average departure deviation of maximum distance difference or matched line.
Optionally, the determining module, specifically for each travelable region for being included by the map to be evaluated and institute
It states each travelable region that Reference Map is included and carries out matching primitives, obtain the Region Matching index;
By each lane line that the map to be evaluated is included and each lane line that the Reference Map is included progress
With calculating, the lines matching index is obtained.
Optionally, the evaluation module is specifically used for being determined according to the Region Matching index and the lines matching index
Difference between the map to be evaluated and the Reference Map;
According to the difference between the map to be evaluated and the Reference Map, to the accuracy of the map to be evaluated into
Row evaluation.
Optionally, above-mentioned map accuracy estimating device, further includes:
Module is adjusted, for according to the difference between the map to be evaluated and the Reference Map, to described to be evaluated
Map is adjusted.
The third aspect, the present invention provide a kind of computer readable storage medium, are stored thereon with computer program, the meter
Calculation machine program realizes above-mentioned map accuracy estimating method when being executed by processor.
Fourth aspect, the present invention provide a kind of electronic equipment, comprising:
Processor;And
Memory, for storing the executable instruction of the processor;
Wherein, the processor is configured to realize above-mentioned map accuracy estimating side via the executable instruction is executed
Method.
Map accuracy estimating method and apparatus provided by the invention, first according to Reference Map and map to be evaluated, really
The Region Matching index and lines matching index of the fixed map to be evaluated, are then based on the Region Matching index and the line
With index, the accuracy of the map to be evaluated is evaluated.It is compared with rate of precision in the prior art with recall rate, region
Matching index and lines matching index are better able to the map that reflection generates and therefore the difference of true map utilizes region
The accuracy of the map of generation is evaluated with index and lines matching index, it is as a result relatively reliable.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the system framework figure of map accuracy estimating method provided by the invention.
Fig. 2 is the flow diagram of the embodiment one of map accuracy estimating method provided by the invention;
Fig. 3 is the area schematic that map to be evaluated provided by the invention includes;
Fig. 4 is the area schematic that Reference Map provided by the invention includes;
Fig. 5 is the lane line schematic diagram that map to be evaluated provided by the invention includes;
Fig. 6 is the lane line schematic diagram that Reference Map provided by the invention includes;
Fig. 7 is another schematic diagram of Reference Map provided by the invention;
Fig. 8 is the flow diagram of the embodiment two of map accuracy estimating method provided by the invention;
Fig. 9 is the flow diagram of the embodiment three of map accuracy estimating method provided by the invention;
Figure 10 is the structural schematic diagram of map accuracy estimating device provided by the invention;
Figure 11 is the hardware structural diagram of electronic equipment provided by the invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
For unmanned vehicle, accurately map has vital work to the positioning of unmanned vehicle, navigation, control and safety
With.In the prior art, first with gyroscope, wheel range finder, global positioning system (Global Positioning
System, abbreviation GPS) and the sensors such as laser radar acquire data, then collected data fusion is generated ground
Figure, and then the map of generation is analyzed and evaluated using indexs such as rate of precision and recall rate common in semantic segmentation.So
And the indexs such as rate of precision and recall rate are the classifications for evaluation point, if evaluating the standard for generating map with the two indexs
It is not high that true property will cause evaluation result accuracy.
Based on above-mentioned technical problem, the present invention provides a kind of map accuracy estimating method and apparatus, after generating map,
Map and true map based on generation, the Region Matching index and lines matching for carrying out the map that matching primitives are generated refer to
Mark, and then according to the two indexs the accuracy of the map of generation is evaluated and rate of precision in the prior art and recalled
Rate is compared, and Region Matching index and lines matching index are better able to the map of reflection generation and the difference of true map, therefore,
The accuracy result that the map of generation is evaluated using Region Matching index and lines matching index is relatively reliable.
Fig. 1 is the system framework figure of map accuracy estimating method provided by the invention.As shown in Figure 1, the present invention provides
Map accuracy estimating method can be executed by corresponding map accuracy estimating device.Map accuracy estimating device difference
It is connected with map creation device and Reference Map storage device.
Wherein, map creation device can also be with gyroscope, wheel range finder, global positioning system (Global
Positioning System, abbreviation GPS) and the sensors connection such as laser radar, after sensor collects corresponding data
It is transferred to map creation device, map creation device merges the data of each sensor transmissions and generates map, and the map of generation is
For map to be evaluated, map to be evaluated is further sent to map accuracy estimating device by map creation device.
Wherein, Reference Map storage device is used for the Reference Map stored and map to be evaluated is compared.This is with reference to ground
Figure is true map.Such as: the Reference Map can be conditional electronic map, and Reference Map storage device can be any peace
Equipment equipped with conditional electronic map.The Reference Map of storage can be transferred to map accuracy estimating by Reference Map storage device
Device.
Wherein, map accuracy estimating device is in the map to be evaluated for receiving map creation device transmission, and reference
On the basis of the Reference Map of map storage device transmission, Reference Map and map to be evaluated can be subjected to matching primitives, thus
Two matching indexs of map to be evaluated are got, and then evaluation is made to map to be evaluated according to the two matching indexs, by
The difference between map to be evaluated and true map is reflected in above-mentioned two matching index, is made according to the two matching indexs
Evaluation result it is relatively reliable.
How figure accuracy estimating device as shown in Figure 1 is executed provided by the inventionly below with reference to specific embodiment
The process of figure accuracy estimating method is described in detail.These specific embodiments can be combined with each other below, for phase
Same or similar concept or process may repeat no more in certain embodiments.Below in conjunction with attached drawing, to implementation of the invention
Example is described.
Fig. 2 is the flow diagram of the embodiment one of map accuracy estimating method provided by the invention.The present embodiment mentions
The map accuracy estimating method of confession map accuracy estimating device can execute as shown in Figure 1, the map accuracy estimating device
It can be by arbitrary software and or hardware realization.As shown in Fig. 2, map accuracy estimating method provided in this embodiment, comprising:
S201, according to Reference Map and map to be evaluated, determine the Region Matching index and line of the map to be evaluated
With index.The Region Matching index is used to indicate the Region Matching degree between the map to be evaluated and the Reference Map,
The lines matching index is used to indicate the lines matching degree between the map to be evaluated and the Reference Map.
Wherein, Reference Map can be traditional electronic map.
Wherein, the region in Region Matching index refers to can travel region.Region Matching index may include referring to as follows
At least one of mark: the ratio in undermatching region or the degree of overlapping of matching area.
Specifically, the undermatching region refers to failing on the map to be evaluated and the Reference Map successful match
Region, the matching area refers to the region on the map to be evaluated with the Reference Map successful match.
Wherein, the line in lines matching index refers to can travel the lane line in region.Lines matching index may include as
At least one of lower index: the average departure deviation of the ratio of undermatching line, the maximum distance of matched line difference or matched line.
Specifically, the undermatching line refers to failing on the map to be evaluated and the Reference Map successful match
Lane line, the matched line refer to the lane line on the map to be evaluated with the Reference Map successful match.
Specifically, according to Reference Map and map to be evaluated determine the Region Matching index of the map to be evaluated can be real
Existing mode are as follows: by each travelable region that the map to be evaluated is included and each travelable area that the Reference Map is included
Domain carries out matching primitives, obtains the Region Matching index.
It is illustrated below by process of the citing to the degree of overlapping of the ratio and matching area that obtain undermatching region:
The process for the ratio for obtaining undermatching region is illustrated:
As shown in Figure 3, it is assumed that the travelable region on map to be evaluated includes: region 1, region 2, region 3,4 and of region
Region 5.As shown in figure 4, the travelable region in Reference Map includes: region 1, region 2 and region 3, then map to be evaluated
On fail region with the Reference Map successful match, i.e., undermatching region is region 4 and region 5, on map to be evaluated
With the region of the Reference Map successful match, as matching area is region 1, region 2 and region 3.Map to be evaluated is owed
The ratio of matching area are as follows: region sum=2/5 being related on undermatching areal/map to be evaluated and Reference Map.
The process for the degree of overlapping for obtaining matching area is illustrated:
Assuming that in Reference Map shown in geographic area that the region 1 on map to be evaluated shown in Fig. 3 is covered and Fig. 4
The geographic area covered in region 1 is identical, the geographic area and Fig. 4 that the region 2 on map to be evaluated shown in Fig. 3 is covered
The geographic area covered in the region 2 in shown Reference Map is different, and the region 3 on map to be evaluated shown in Fig. 3 is covered
The geographic area covered in the region 3 in Reference Map shown in the geographic area of lid and Fig. 4 is also different.Map so to be evaluated
In the upper region with the Reference Map successful match, only region 1 is overlapping, degree of overlapping=overlapping region of matching area
Number/matching area number=1/3.
Specifically, determining can be achieved for the lines matching index of the map to be evaluated according to Reference Map and map to be evaluated
Mode are as follows: match each lane line that the map to be evaluated is included and each lane line that the Reference Map is included
It calculates, obtains the lines matching index.
Below by citing to the average distance of the ratio of the undermatching line of acquisition, the maximum distance of matched line difference or matched line
The process of difference is illustrated:
The process for the ratio for obtaining undermatching line is illustrated:
As shown in fig. 5, it is assumed that the lane line on map to be evaluated includes: lane line 1, lane line 2 ... lane line 12.Such as
Shown in Fig. 6, the lane line in Reference Map includes: lane line 4, lane line 5 and lane line 6, then failing on map to be evaluated
With the lane line of the Reference Map successful match, i.e., undermatching line is lane line 1 to lane line 3 and lane line 7 to vehicle
Diatom 12, totally 9, undermatching line.With the line of the Reference Map successful match on map to be evaluated, i.e. matched line is lane
Line 4, lane line 5 and lane line 6.The ratio of the undermatching line of map to be evaluated are as follows: on the number of undermatching line/map to be evaluated
With lane line sum=9/12 being related in Reference Map.
The process of the average departure deviation of the maximum distance difference or matched line that obtain matched line is illustrated:
Assuming that joining on map to be evaluated with the lane line 4, lane line 5 and lane line 6 of the Reference Map successful match
The position on map is examined (to illustrate using dotted line) as shown in Figure 7.By lane line 4, lane line 5 and the lane line on map to be evaluated
After 6 project in Reference Map, calculate separately between the lane line 4 in the lane line 4 on map to be evaluated and Reference Map
Distance, the distance between the lane line 5 on lane line 5 and Reference Map on map to be evaluated, the lane on map to be evaluated
The distance between lane line 6 on line 6 and Reference Map, the maximum distance in three distances being calculated is matched line
Maximum distance is poor, and the average distance of three distances is the average departure deviation of matched line.
S202, according to the Region Matching index and the lines matching index, to the accuracy of the map to be evaluated into
Row evaluation.
Specifically, obtained in above-mentioned steps the ratio in undermatching region, the degree of overlapping of matching area, undermatching line ratio
After the average departure deviation of example, the maximum distance of matched line difference or matched line, these comprehensive indexs are to the accurate of map to be evaluated
Degree is evaluated.
In general, the ratio in undermatching region is bigger, show that the difference of map to be evaluated and Reference Map is bigger, it is to be evaluated
The accuracy of map is lower.
The degree of overlapping of matching area is bigger, shows that the difference of map to be evaluated and Reference Map is smaller, map to be evaluated
Accuracy is higher.
The ratio of undermatching line is bigger, shows that the difference of map to be evaluated and Reference Map is bigger, the standard of map to be evaluated
Exactness is lower.
The maximum distance difference of matched line is bigger, shows that the difference of map to be evaluated and Reference Map is bigger, map to be evaluated
Accuracy it is lower.
The average departure deviation of matched line is bigger, shows that the difference of map to be evaluated and Reference Map is bigger, map to be evaluated
Accuracy it is lower.
Map accuracy estimating method provided in this embodiment determines institute first according to Reference Map and map to be evaluated
The Region Matching index and lines matching index for stating map to be evaluated, are then based on the Region Matching index and the lines matching refers to
Mark, evaluates the accuracy of the map to be evaluated.It is compared with rate of precision in the prior art with recall rate, Region Matching
Index and lines matching index are better able to the map that reflection generates and therefore the difference of true map is referred to using Region Matching
Mark and lines matching index are relatively reliable come the accuracy result for evaluating the map of generation.
Below with reference to specific embodiment to the process evaluated in above-described embodiment the accuracy of map to be evaluated
It is described in detail.
Fig. 8 is the flow diagram of the embodiment two of map accuracy estimating method provided by the invention.As shown in figure 8,
Map accuracy estimating method provided in this embodiment, comprising:
S801, according to Reference Map and map to be evaluated, determine the Region Matching index and line of the map to be evaluated
With index.
Wherein, the specific implementation of this step can be found in the S201 in above-described embodiment, and details are not described herein by the present invention.
S802, according to the Region Matching index and the lines matching index, determine the map to be evaluated and the ginseng
Examine the difference between map.
S803, according to the difference between the map to be evaluated and the Reference Map, to the standard of the map to be evaluated
Exactness is evaluated.
Specifically, assuming that the index value of each evaluation index got through the foregoing embodiment is as shown in table 1
Evaluation index | Index value |
The ratio in undermatching region | A% |
The degree of overlapping of matching area | B% |
The ratio of undermatching line | C% |
The maximum distance of matched line is poor | D(m) |
The average departure deviation of matched line | E(m) |
Table 1
Wherein, the ratio in undermatching region and the degree of overlapping of matching area are Region Matching index.The ratio of undermatching line,
The maximum distance difference of matched line and the average departure deviation of matched line are lines matching index.
A kind of achievable mode of the difference between map to be evaluated and Reference Map is determined according to each index are as follows: to table
Evaluation index averaged in 1, which represents the difference between map to be evaluated and Reference Map, settable excellent
Good middle poor grade, the corresponding average value threshold value of each grade, when the average value sought meets the corresponding threshold value of certain grade
When range, then show that the accuracy of map to be evaluated is in the level of the grade.Such as: the average value sought meet " excellent " this
The corresponding threshold range of one grade then shows that the accuracy of map to be evaluated is " excellent ".
The achievable mode of another kind of the difference between map to be evaluated and Reference Map is determined according to each index are as follows: obtain
The weight for taking each evaluation index in Fig. 1 seeks weighted average to the evaluation index in table 1, the weighted average represent to
The difference between map and Reference Map is evaluated, the accuracy of map to be evaluated can be evaluated according to the weighted average.
Map accuracy estimating method provided in this embodiment is described according to Region Matching index and lines matching index,
To the achievable mode that the accuracy of map to be evaluated is evaluated, specifically, first according to the Region Matching index and institute
Lines matching index is stated, determines the difference between the map to be evaluated and the Reference Map;Then according to it is described to be evaluatedly
Difference between figure and the Reference Map, evaluates the accuracy of the map to be evaluated.Since evaluation procedure is based on
Evaluation index really reflect the difference between map to be evaluated and Reference Map, evaluation result is relatively reliable.
Fig. 9 is the flow diagram of the embodiment three of map accuracy estimating method provided by the invention, as shown in figure 9,
Map accuracy estimating method provided in this embodiment, comprising:
S901, according to Reference Map and map to be evaluated, determine the Region Matching index and line of the map to be evaluated
With index.
S902, according to the Region Matching index and the lines matching index, determine the map to be evaluated and the ginseng
Examine the difference between map.
S903, according to the difference between the map to be evaluated and the Reference Map, to the standard of the map to be evaluated
Exactness is evaluated.
Wherein, the implementation of S901-S903 can be found in above-described embodiment, and details are not described herein by the present invention.
S904, according to the difference between the map to be evaluated and the Reference Map, the map to be evaluated is carried out
Adjustment.
Ginseng as shown in figure 3 and figure 4, when the large percentage in region undermatching on map to be evaluated, and the overlapping of matching area
Spend it is smaller when, the geographical location that the region and each region that can included according to Reference Map in Fig. 4 be in, to shown in Fig. 3 to
Region on evaluation map is adjusted.
Similarly, shown in referring to figs. 5 and 6, when the large percentage of line undermatching on map to be evaluated, and the maximum of matched line
When the average departure deviation of range difference and matched line is also larger, the lane line that can included according to Reference Map shown in Fig. 6, and it is each
The geographical location that lane line is in is adjusted the lane line on map to be evaluated shown in Fig. 5.
Map accuracy estimating method provided in this embodiment, after the accuracy to map to be evaluated is evaluated, also
Map to be evaluated is adjusted according to evaluation result, so that map to be evaluated and true map are more nearly, improves nothing
People's driving driving safety.
Figure 10 is the structural schematic diagram of map accuracy estimating device provided by the invention.As shown in Figure 10, the present embodiment
The map accuracy estimating device of offer, comprising:
Determining module 1001, for determining the region of the map to be evaluated according to Reference Map and map to be evaluated
With index and lines matching index, the Region Matching index is used to indicate between the map to be evaluated and the Reference Map
Region Matching degree, the lines matching index are used to indicate the lines matching degree between the map to be evaluated and the Reference Map;
Evaluation module 1002, for according to the Region Matching index and the lines matching index, to it is described to be evaluatedly
The accuracy of figure is evaluated.
Optionally, the Region Matching index includes at least one of following index: the ratio in undermatching region or
Degree of overlapping with region;Wherein, the undermatching region is used to indicate on the map to be evaluated and fails and the Reference Map
The region of successful match, the matching area are used to indicate the area on the map to be evaluated with the Reference Map successful match
Domain.
Optionally, the lines matching index includes at least one of following index: the ratio of undermatching line, matched line
The average departure deviation of maximum distance difference or matched line.
Optionally, the determining module 1001, specifically for each travelable region for being included by the map to be evaluated
Each travelable region for being included with the Reference Map carries out matching primitives, obtains the Region Matching index;
By each lane line that the map to be evaluated is included and each lane line that the Reference Map is included progress
With calculating, the lines matching index is obtained.
Optionally, the evaluation module 1002 is specifically used for according to the Region Matching index and the lines matching index,
Determine the difference between the map to be evaluated and the Reference Map;
According to the difference between the map to be evaluated and the Reference Map, to the accuracy of the map to be evaluated into
Row evaluation.
Optionally, map accuracy estimating device provided in this embodiment, further includes:
Adjust module 1003, for according to the difference between the map to be evaluated and the Reference Map, to it is described to
Evaluation map is adjusted.
Map accuracy estimating device provided in this embodiment can be used for executing the map accuracy in any embodiment and comment
Valence method, it is similar that the realization principle and technical effect are similar, and details are not described herein.
Figure 11 is the hardware structural diagram of electronic equipment provided by the invention.As shown in figure 11, the electronics of the present embodiment
Equipment may include:
Memory 1101, for storing program instruction.
Processor 1102, for being performed the method for realizing any of the above-described embodiment description, tool in described program instruction
Body realization principle can be found in above-described embodiment, and details are not described herein again for the present embodiment.
The present invention provides a kind of computer readable storage medium, is stored thereon with computer program, the computer program
Map accuracy estimating method described in any of the above-described embodiment is realized when being executed by processor.
The present invention also provides a kind of program product, described program product includes computer program, and the computer program is deposited
In readable storage medium storing program for executing, at least one processor can read the computer program, institute from the readable storage medium storing program for executing for storage
State at least one processor execute the computer program make electronic equipment implement map described in any of the above-described embodiment standard
Exactness evaluation method.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or logical of device or unit
Letter connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) or processor (English: processor) execute this hair
The part steps of bright each embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory
(English: Read-Only Memory, abbreviation: ROM), random access memory (English: Random Access Memory, letter
Claim: RAM), the various media that can store program code such as magnetic or disk.
It should be understood that processor can be central processing unit (English: Central Processing Unit, referred to as:
CPU), it can also be other general processors, digital signal processor (English: Digital Signal Processor, letter
Claim: DSP), specific integrated circuit (English: Application Specific Integrated Circuit, referred to as: ASIC)
Deng.General processor can be microprocessor or the processor is also possible to any conventional processor etc..In conjunction with the application
The step of disclosed method, can be embodied directly in hardware processor and execute completion, or with the hardware and software in processor
Block combiner executes completion.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (10)
1. a kind of map accuracy estimating method characterized by comprising
According to Reference Map and map to be evaluated, the Region Matching index and lines matching index of the map to be evaluated, institute are determined
State the Region Matching degree that Region Matching index is used to indicate between the map to be evaluated and the Reference Map, the lines matching
Index is used to indicate the lines matching degree between the map to be evaluated and the Reference Map;
According to the Region Matching index and the lines matching index, the accuracy of the map to be evaluated is evaluated.
2. the method according to claim 1, wherein the Region Matching index include in following index at least
One: the ratio in undermatching region or the degree of overlapping of matching area;Wherein, the undermatching region is used to indicate described to be evaluated
Fail the region with the Reference Map successful match on map, the matching area be used to indicate on the map to be evaluated with
The region of the Reference Map successful match.
3. according to the method described in claim 2, it is characterized in that, the lines matching index includes at least one in following index
It is a: the average departure deviation of the ratio of undermatching line, the maximum distance of matched line difference or matched line.
4. method according to claim 1-3, which is characterized in that described according to Reference Map and to be evaluated
Figure, determines the Region Matching index and lines matching index of the map to be evaluated, comprising:
By each travelable region that the map to be evaluated is included and each travelable region that the Reference Map is included into
Row matching primitives obtain the Region Matching index;
Each lane line that the map to be evaluated is included and each lane line that the Reference Map is included are subjected to matching meter
It calculates, obtains the lines matching index.
5. according to the method described in claim 4, it is characterized in that, described according to the Region Matching index and the lines matching
Index evaluates the accuracy of the map to be evaluated, comprising:
According to the Region Matching index and the lines matching index, determine between the map to be evaluated and the Reference Map
Difference;
According to the difference between the map to be evaluated and the Reference Map, the accuracy of the map to be evaluated is commented
Valence.
6. according to the method described in claim 5, it is characterized by further comprising:
According to the difference between the map to be evaluated and the Reference Map, the map to be evaluated is adjusted.
7. a kind of map accuracy estimating device characterized by comprising
Determining module, for according to Reference Map and map to be evaluated, determine the map to be evaluated Region Matching index and
Lines matching index, the Region Matching index are used to indicate the Region Matching between the map to be evaluated and the Reference Map
Degree, the lines matching index are used to indicate the lines matching degree between the map to be evaluated and the Reference Map;
Evaluation module is used for according to the Region Matching index and the lines matching index, to the accurate of the map to be evaluated
Degree is evaluated.
8. device according to claim 7, which is characterized in that
The determining module, specifically for each travelable region for being included by the map to be evaluated and Reference Map institute
Each travelable region for including carries out matching primitives, obtains the Region Matching index;
Each lane line that the map to be evaluated is included and each lane line that the Reference Map is included are subjected to matching meter
It calculates, obtains the lines matching index.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program quilt
Processor realizes method described in any one of claims 1-6 when executing.
10. a kind of electronic equipment characterized by comprising
Processor;And
Memory, for storing the executable instruction of the processor;
Wherein, the processor is configured to described in any one of claims 1-6 to realize via the executable instruction is executed
Method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811290711.1A CN109635050A (en) | 2018-10-31 | 2018-10-31 | Map accuracy estimating method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811290711.1A CN109635050A (en) | 2018-10-31 | 2018-10-31 | Map accuracy estimating method and apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109635050A true CN109635050A (en) | 2019-04-16 |
Family
ID=66066983
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811290711.1A Pending CN109635050A (en) | 2018-10-31 | 2018-10-31 | Map accuracy estimating method and apparatus |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109635050A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111177290A (en) * | 2019-12-18 | 2020-05-19 | 浙江欣奕华智能科技有限公司 | Method and device for evaluating accuracy of three-dimensional map |
CN113360593A (en) * | 2021-06-30 | 2021-09-07 | 武汉四维图新科技有限公司 | Sensor data processing method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104361142A (en) * | 2014-12-12 | 2015-02-18 | 华北水利水电大学 | Detection method for rapid change in multi-source navigation electronic map vector road network |
CN106776996A (en) * | 2016-12-02 | 2017-05-31 | 百度在线网络技术(北京)有限公司 | Method and apparatus for testing the accuracy of high accuracy map |
CN107392219A (en) * | 2016-04-26 | 2017-11-24 | 大众汽车有限公司 | Compare the method and apparatus of two maps with the surface mark being stored therein |
CN108629795A (en) * | 2017-03-17 | 2018-10-09 | 高德软件有限公司 | A kind of mileage chart chip detection method and device |
-
2018
- 2018-10-31 CN CN201811290711.1A patent/CN109635050A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104361142A (en) * | 2014-12-12 | 2015-02-18 | 华北水利水电大学 | Detection method for rapid change in multi-source navigation electronic map vector road network |
CN107392219A (en) * | 2016-04-26 | 2017-11-24 | 大众汽车有限公司 | Compare the method and apparatus of two maps with the surface mark being stored therein |
CN106776996A (en) * | 2016-12-02 | 2017-05-31 | 百度在线网络技术(北京)有限公司 | Method and apparatus for testing the accuracy of high accuracy map |
CN108629795A (en) * | 2017-03-17 | 2018-10-09 | 高德软件有限公司 | A kind of mileage chart chip detection method and device |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111177290A (en) * | 2019-12-18 | 2020-05-19 | 浙江欣奕华智能科技有限公司 | Method and device for evaluating accuracy of three-dimensional map |
CN111177290B (en) * | 2019-12-18 | 2023-06-02 | 浙江欣奕华智能科技有限公司 | Evaluation method and device for accuracy of three-dimensional map |
CN113360593A (en) * | 2021-06-30 | 2021-09-07 | 武汉四维图新科技有限公司 | Sensor data processing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10900793B2 (en) | Vehicle path guiding apparatus and method | |
US10281279B2 (en) | Method and system for global shape matching a trajectory | |
WO2018221453A1 (en) | Output device, control method, program, and storage medium | |
JP2024050990A (en) | Judging device | |
CN103424112B (en) | A kind of motion carrier vision navigation method auxiliary based on laser plane | |
CN107449443A (en) | The integrity monitoring of radar altimeter | |
EP2144038A2 (en) | Inertial measurement using an imaging sensor and a digitized map | |
CN110082747A (en) | Increase the method for the reliability of determining vehicle location based on multiple test points | |
CN107223200A (en) | Navigation method, navigation device and terminal equipment | |
CN109937341A (en) | The estimation of the position of oneself | |
CN105182311A (en) | Omnidirectional radar data processing method and system | |
US20220113139A1 (en) | Object recognition device, object recognition method and program | |
CN109564095B (en) | Method and apparatus for using virtual probe points for routing or navigation purposes | |
CN108278994A (en) | A kind of underwater mapping method of miniature self-service ship and equipment | |
JP6119225B2 (en) | Intersection road boundary detection device and program | |
Sjanic | Navigation and SAR Auto-focusing in a Sensor Fusion Framework | |
CN109635050A (en) | Map accuracy estimating method and apparatus | |
CN106080397A (en) | Self-adaption cruise system and mobile unit | |
Liu et al. | Generating enhanced intersection maps for lane level vehicle positioning based applications | |
KR20210102970A (en) | Method for Adaptive Determination of Integrity Range of Parameter Estimation | |
Gustafsson et al. | Navigation and tracking of road-bound vehicles | |
Bhamidipati et al. | Set-valued shadow matching using zonotopes for 3D-map-aided GNSS localization | |
CN106556397A (en) | A kind of GNSS map-matching methods and device | |
CN106289281A (en) | A kind of double mode map-matching method theoretical based on three evidence DS | |
JP2020034451A (en) | Data structure, storage medium, and storage device |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |