CN109583392A - A kind of method for detecting parking stalls, device and storage medium - Google Patents
A kind of method for detecting parking stalls, device and storage medium Download PDFInfo
- Publication number
- CN109583392A CN109583392A CN201811477045.2A CN201811477045A CN109583392A CN 109583392 A CN109583392 A CN 109583392A CN 201811477045 A CN201811477045 A CN 201811477045A CN 109583392 A CN109583392 A CN 109583392A
- Authority
- CN
- China
- Prior art keywords
- parking stall
- vertex
- sample image
- network
- parking
- 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
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012549 training Methods 0.000 claims description 12
- 230000002776 aggregation Effects 0.000 claims description 9
- 238000004220 aggregation Methods 0.000 claims description 9
- 238000010438 heat treatment Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000004807 localization Effects 0.000 claims 1
- 238000013135 deep learning Methods 0.000 abstract description 3
- 238000010801 machine learning Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of method for detecting parking stalls, device and storage medium, obtains sample image, includes one or more parking stalls in the sample image, with the parking stall vertex in parking stall vertex positioning Network Recognition sample image；Parking stall vertex is matched two-by-two, to the part of parking stall vertex successful matching, its image block is intercepted, and image block is input in the sorter network of parking stall, the parking stall classification of parking stall sorter network includes one or more of invalid parking stall, vertical parking stall, horizontal parking stall, inclination parking stall；Sample image is inputted into parking stall sorter network, from parking stall of the parking stall sorter network output parking stall in a manner of machine learning or deep learning in classification samples image, method for detecting parking stalls proposed in this paper can support a variety of parking stall types under the several scenes such as right angle parking stall, oblique angle parking stall, tile floor, meadow, current most of parking stall types are met, and are all had verified that effectively.
Description
Technical field
The present invention relates to technical field of automotive electronics, more particularly to a kind of method for detecting parking stalls, device and storage medium.
Background technique
In recent years, the increase in demand with people to automatic Pilot, autonomous parking auxiliary system have become one and deeply grind
The project studied carefully, for this purpose, people it is in the urgent need to address how this problem of the system high efficiency vehicle positioning stop position of view-based access control model.
The problem of current parking stall measure technology is perfect not enough, missing inspection erroneous detection still has, while can not meet more
The parking stall of scene, polymorphic type.
Summary of the invention
In order to solve above-mentioned and other potential technical problems, the present invention provides a kind of method for detecting parking stalls, dress
It sets and storage medium, the parking stall in a manner of machine learning or deep learning in classification samples image, parking stall proposed in this paper
Detection method can support a variety of parking stall types under the several scenes such as right angle parking stall, oblique angle parking stall, tile floor, meadow, meet
Current most of parking stall types, and all have verified that effectively.
A kind of parking stall measure network training method, comprising the following steps:
Sample image is obtained, includes one or more parking stalls in the sample image, identifies the parking stall in sample image
Vertex；
Parking stall vertex is matched two-by-two, to the part of parking stall vertex successful matching, intercepts its image block, and by image
Block is input in the sorter network of parking stall, and the parking stall classification of parking stall sorter network includes invalid parking stall, vertical parking stall, level
One or more of parking stall, inclination parking stall；
Sample image is inputted into parking stall sorter network, is classified from parking stall sorter network output parking stall.
Further, the sample image includes underground garage scene, open-air garage scene, tile floor garage scene, meadow
Garage scene.
Further, when the interception image block, coordinate system is first established according to match point, with the coordinate points p1 of successful matching
Based on coordinate points p2, using (p1p2) extending direction as x-axis, the central point of (p1p2) is origin, takes a rectangular area R
As image block, obtained image block is considered as the Local map defined by p1 coordinate points and p2 coordinate points.
It further, further include that arrival line ROI is extracted, the parking stall vertex is matched two-by-two, all assembled schemes are obtained,
Wherein the arrival line of non-adjacent two vertex p1, p2 composition is invalid entry line, does not save invalid entry line, remaining non-adjacent
Two vertex be effective arrival line, effective arrival line is input to parking stall sorter network.
A kind of parking stall measure network, the parking stall measure network obtained with the parking stall measure network training method training.
A kind of method for detecting parking stalls, the mode for obtaining the positioning of parking stall vertex is that as described above repair is inputted with sample image
Parking stall measure network after just obtains.
A kind of parking stall measure corrective networks, to mark the parking stall that the parking stall of image is arrived with the parking stall measure network in advance
The gap of detection, then to parking stall measure e-learning to parking test results be modified.
Further, the loss function that the parking stall measure corrective networks use is Euclidean distance loss function
EuclideanLoss。
Further, the specific steps on the parking stall vertex in the identification sample image:
Sample image is obtained, includes one or more parking stalls in the sample image,
Sample image is input to parking stall vertex positioning network, the thermodynamic chart for characterizing parking stall vertex is obtained and obtains heat
The coordinate of heating power aggregation zone on trying hard to；
The coordinate of heating power aggregation zone on thermodynamic chart is obtained into parking stall vertex through screening, is to screen obtained parking stall vertex
Basis obtains the characteristic pattern comprising the parking stall vertex, then characteristic pattern input vertex is positioned network, and amendment obtains revised vehicle
Position vertex positions network, then with the parking stall vertex of parking stall vertex positioning network output sample image.
Further, the parking stall vertex is matched two-by-two, obtains all assembled schemes, wherein two non-adjacent vertex
The arrival line of p1, p2 composition is invalid entry line, remaining two non-adjacent vertex.
A kind of parking stall measure verification method, comprising the following steps:
By parking stall classification annotation on sample image, mark is recommended in the parking stall classification obtained on mark image；
Sample image block is input in parking stall measure network, and mark ratio is recommended into the parking stall of input and parking stall measure
Compared with acquisition verification result.
A kind of parking stall measure network training device, comprising:
Sample acquisition unit includes one or more parking stalls in the sample image for obtaining sample image；
Sample marks acquiring unit, for obtaining the sample image for having marked parking stall classification；
Parking stall vertex positions network, for being input with sample image, generates the parking stall vertex in sample image；
Arrival line ROI extraction unit, matches parking stall vertex, obtains all assembled schemes, wherein non-adjacent two
The arrival line of a vertex p1, p2 composition is invalid entry line, does not save invalid entry line, and remaining two non-adjacent vertex are to have
Arrival line is imitated, effective arrival line is input to parking stall sorter network；
Parking stall sorter network, for classifying to the parking stall in sample image,
Comparing unit is obtained by parking test results compared with the sample image marked in sample mark acquiring unit
Obtain comparison result；
Amending unit, for correcting parking stall measure network with comparison result.
A kind of parking stall measure system, comprising:
Sample acquisition unit includes one or more parking stalls in the sample image for obtaining sample image；
Sample marks acquiring unit, for obtaining the sample image for having marked parking stall classification；
Vertex positions network, and the thermodynamic chart for characterizing parking stall vertex is obtained after input sample image and obtains thermodynamic chart
On heating power aggregation zone coordinate；And parking stall vertex is obtained with this, by the figure around being obtained based on the parking stall vertex of acquisition
As block；
Arrival line ROI extraction unit, matches parking stall vertex, obtains all assembled schemes, wherein non-adjacent two
The arrival line of a vertex p1, p2 composition is invalid entry line, does not save invalid entry line, and remaining two non-adjacent vertex are to have
Arrival line is imitated, effective arrival line is input to parking stall sorter network；
Parking stall sorter network, for classifying to the parking stall in the image block in sample image.
As described above, of the invention has the advantages that
Parking stall in a manner of machine learning or deep learning in classification samples image, parking stall measure side proposed in this paper
Method can support a variety of parking stall types under the several scenes such as right angle parking stall, oblique angle parking stall, tile floor, meadow, meet big at present
Most parking stall types, and all have verified that effectively.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is shown as the flow chart of one embodiment of the invention.
Fig. 2 is shown as the schematic diagram on meadow parking stall of the present invention.
Fig. 3 is shown as the thermodynamic chart on meadow parking stall of the present invention.
Fig. 4 is shown as the thermodynamic chart of another embodiment of the present invention.
Fig. 5 is shown as the schematic diagram on tile floor parking stall of the present invention.
Fig. 6 is shown as the thermodynamic chart on tile floor parking stall of the present invention.
Fig. 7 is shown as the schematic diagram on tile floor parking space of the present invention vertex.
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be clear that this specification structure depicted in this specification institute accompanying drawings, ratio, size etc., only to cooperate specification to be taken off
The content shown is not intended to limit the invention enforceable qualifications so that those skilled in the art understands and reads, therefore
Do not have technical essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size are not influencing the present invention
Under the effect of can be generated and the purpose that can reach, it should all still fall in disclosed technology contents and obtain the model that can cover
In enclosing.Meanwhile cited such as "upper" in this specification, "lower", "left", "right", " centre " and " one " term, be also only
Convenient for being illustrated for narration, rather than to limit the scope of the invention, relativeness is altered or modified, in no essence
It changes under technology contents, when being also considered as the enforceable scope of the present invention.
Referring to FIG. 1 to FIG. 5,
A kind of parking stall measure network training method, comprising the following steps:
Sample image is obtained, includes one or more parking stalls in the sample image, identifies the parking stall in sample image
Vertex；
Parking stall vertex is matched two-by-two, to the part of parking stall vertex successful matching, intercepts its image block, and by image
Block is input in the sorter network of parking stall, and the parking stall classification of parking stall sorter network includes invalid parking stall, vertical parking stall, level
One or more of parking stall, inclination parking stall；
Sample image is inputted into parking stall sorter network, is classified from parking stall sorter network output parking stall.
Further, the sample image includes underground garage scene, open-air garage scene, tile floor garage scene, meadow
Garage scene.
Further, when the interception image block, coordinate system is first established according to match point, with the coordinate points p1 of successful matching
Based on coordinate points p2, using (p1p2) extending direction as x-axis, the central point of (p1p2) is origin, takes a rectangular area R
As image block, obtained image block is considered as the Local map defined by p1 coordinate points and p2 coordinate points.
It further, further include that arrival line ROI is extracted, the parking stall vertex is matched two-by-two, all assembled schemes are obtained,
Wherein the arrival line of non-adjacent two vertex p1, p2 composition is invalid entry line, does not save invalid entry line, remaining non-adjacent
Two vertex be effective arrival line, effective arrival line is input to parking stall sorter network.
A kind of parking stall measure network, the parking stall measure network obtained with the parking stall measure network training method training.
A kind of method for detecting parking stalls, the mode for obtaining the positioning of parking stall vertex is that as described above repair is inputted with sample image
Parking stall measure network after just obtains.
A kind of parking stall measure corrective networks, to mark the parking stall that the parking stall of image is arrived with the parking stall measure network in advance
The gap of detection, then to parking stall measure e-learning to parking test results be modified.
Further, the loss function that the parking stall measure corrective networks use is Euclidean distance loss function
EuclideanLoss。
Further, the specific steps on the parking stall vertex in the identification sample image:
Sample image is obtained, includes one or more parking stalls in the sample image,
Sample image is input to parking stall vertex positioning network, the thermodynamic chart for characterizing parking stall vertex is obtained and obtains heat
The coordinate of heating power aggregation zone on trying hard to；
The coordinate of heating power aggregation zone on thermodynamic chart is obtained into parking stall vertex through screening, is to screen obtained parking stall vertex
Basis obtains the characteristic pattern comprising the parking stall vertex, then characteristic pattern input vertex is positioned network, and amendment obtains revised vehicle
Position vertex positions network, then with the parking stall vertex of parking stall vertex positioning network output sample image.
Further, the parking stall vertex is matched two-by-two, obtains all assembled schemes, wherein two non-adjacent vertex
The arrival line of p1, p2 composition is invalid entry line, remaining two non-adjacent vertex.
A kind of parking stall measure verification method, comprising the following steps:
By parking stall classification annotation on sample image, mark is recommended in the parking stall classification obtained on mark image；
Sample image block is input in parking stall measure network, and mark ratio is recommended into the parking stall of input and parking stall measure
Compared with acquisition verification result.
A kind of parking stall measure network training device, comprising:
Sample acquisition unit includes one or more parking stalls in the sample image for obtaining sample image；
Sample marks acquiring unit, for obtaining the sample image for having marked parking stall classification；
Parking stall vertex positions network, for being input with sample image, generates the parking stall vertex in sample image；
Arrival line ROI extraction unit, matches parking stall vertex, obtains all assembled schemes, wherein non-adjacent two
The arrival line of a vertex p1, p2 composition is invalid entry line, does not save invalid entry line, and remaining two non-adjacent vertex are to have
Arrival line is imitated, effective arrival line is input to parking stall sorter network；
Parking stall sorter network, for classifying to the parking stall in sample image,
Comparing unit is obtained by parking test results compared with the sample image marked in sample mark acquiring unit
Obtain comparison result；
Amending unit, for correcting parking stall measure network with comparison result.
A kind of parking stall measure system, comprising:
Sample acquisition unit includes one or more parking stalls in the sample image for obtaining sample image；
Sample marks acquiring unit, for obtaining the sample image for having marked parking stall classification；
Vertex positions network, and the thermodynamic chart for characterizing parking stall vertex is obtained after input sample image and obtains thermodynamic chart
On heating power aggregation zone coordinate；And parking stall vertex is obtained with this, by the figure around being obtained based on the parking stall vertex of acquisition
As block；
Arrival line ROI extraction unit, matches parking stall vertex, obtains all assembled schemes, wherein non-adjacent two
The arrival line of a vertex p1, p2 composition is invalid entry line, does not save invalid entry line, and remaining two non-adjacent vertex are to have
Arrival line is imitated, effective arrival line is input to parking stall sorter network；
Parking stall sorter network for classifying to the parking stall in the image block in sample image, and obtains in each classification
Parking stall.
As a preferred embodiment, the present embodiment also provides a kind of terminal device, can such as execute the smart phone of program, put down
Plate computer, laptop, desktop computer, rack-mount server, blade server, tower server or cabinet-type service
Device (including server cluster composed by independent server or multiple servers) etc..The terminal device of the present embodiment is extremely
It is few to include but is not limited to: memory, the processor of connection can be in communication with each other by system bus.It should be pointed out that having group
The terminal device of part memory, processor can substitute it should be understood that being not required for implementing all components shown
Implementation is more or less component.
As a preferred embodiment, memory (i.e. readable storage medium storing program for executing) includes flash memory, hard disk, multimedia card, card-type storage
Device (for example, SD or DX memory etc.), random access storage device (RAM), static random-access memory (SRAM), read-only storage
Device (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read only memory (PROM), magnetic storage, magnetic
Disk, CD etc..In some embodiments, memory can be the internal storage unit of computer equipment, such as the computer is set
Standby 20 hard disk or memory.In further embodiments, memory is also possible to the External memory equipment of computer equipment, such as
The plug-in type hard disk being equipped in the computer equipment, intelligent memory card (Smart Media Card, SMC), secure digital
(Secure Digital, SD) card, flash card (Flash Card) etc..Certainly, memory can also both include computer equipment
Internal storage unit also include its External memory equipment.In the present embodiment, memory is installed on computer commonly used in storage
Operating system and types of applications software, such as the terrain detection program code based on radar in embodiment of equipment etc..In addition,
Memory can be also used for temporarily storing the Various types of data that has exported or will export.
Processor can be central processing unit (Central Processing Unit, CPU), control in some embodiments
Device, microcontroller, microprocessor or other data processing chips processed.The processor is total commonly used in control computer equipment
Gymnastics is made.In the present embodiment, program code or processing data of the processor for being stored in run memory, such as operation base
In the terrain detection program of radar, to realize the function of the terrain detection system in embodiment based on radar.
A kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that: the program is by processor
The step in above-mentioned method is realized when execution.
The present embodiment also provides a kind of computer readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory
(for example, SD or DX memory etc.), random access storage device (RAM), static random-access memory (SRAM), read-only memory
(ROM), electrically erasable programmable read-only memory (EEPROM), programmable read only memory (PROM), magnetic storage, magnetic
Disk, CD, server, App are stored thereon with computer program, phase are realized when program is executed by processor using store etc.
Answer function.The computer readable storage medium of the present embodiment is held for storing the terrain detection program based on radar by processor
The terrain detection method based on radar in embodiment is realized when row.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause
This, includes that institute is complete without departing from the spirit and technical ideas disclosed in the present invention for usual skill in technical field such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (11)
1. a kind of parking stall measure network training method, comprising the following steps:
Sample image is obtained, includes one or more parking stalls in the sample image, Network Recognition sample is positioned with parking stall vertex
Parking stall vertex in image；
Parking stall vertex is matched two-by-two, to the part of parking stall vertex successful matching, intercepts its image block, and image block is defeated
Enter into parking stall sorter network, the parking stall classification of parking stall sorter network includes invalid parking stall, vertical parking stall, horizontal vehicle
One or more of position, inclination parking stall；
Sample image is inputted into parking stall sorter network, exports parking stall from parking stall sorter network.
2. a kind of parking stall measure network, which is characterized in that with parking stall measure network training method described in the claims 1
The parking stall measure network that training obtains.
3. a kind of method for detecting parking stalls, which is characterized in that the mode for obtaining parking stall is to be inputted with sample image as aforesaid right is wanted
Revised parking stall measure network described in 2 is asked to obtain.
4. method for detecting parking stalls according to claim 3, which is characterized in that the sample image includes underground garage field
Scape, open-air garage scene, tile floor garage scene, meadow garage scene.
5. parking stall vertex according to claim 4 localization method, which is characterized in that it further include that arrival line ROI is extracted, it is described
Parking stall vertex is matched two-by-two, obtains all assembled schemes, wherein the arrival line that non-adjacent two vertex p1, p2 are formed is nothing
Arrival line is imitated, does not save invalid entry line, remaining two non-adjacent vertex are effective arrival line, and effective arrival line is input to
Parking stall sorter network.
6. method for detecting parking stalls according to claim 4, which is characterized in that when the interception image block, first according to pairing
Point establishes coordinate system, based on the coordinate points p1 of successful matching and coordinate points p2, using (p1p2) extending direction as x-axis,
(p1p2) central point is origin, takes a rectangular area R as image block, obtained image block is considered as by p1 coordinate points and p2
The Local map that coordinate points define.
7. a kind of parking stall measure verification method, comprising the following steps:
By parking stall classification annotation on sample image, mark is recommended in the parking stall classification obtained on mark image；
Sample image block is input in parking stall measure network described in power 2, and the parking stall of input and parking stall measure are recommended to mark
Note compares, and obtains verification result.
8. method for detecting parking stalls according to claim 1, which is characterized in that the parking stall top in the identification sample image
The specific steps of point:
Sample image is obtained, includes one or more parking stalls in the sample image,
Sample image is input to parking stall vertex positioning network, the thermodynamic chart for characterizing parking stall vertex is obtained and obtains thermodynamic chart
On heating power aggregation zone coordinate；
The coordinate of heating power aggregation zone on thermodynamic chart is obtained into parking stall vertex through screening, based on screening obtained parking stall vertex
The characteristic pattern comprising the parking stall vertex is obtained, then characteristic pattern input vertex is positioned into network, amendment obtains revised parking stall top
Point location network, then with the parking stall vertex of parking stall vertex positioning network output sample image.
9. a kind of parking stall measure network training device characterized by comprising
Sample acquisition unit includes one or more parking stalls in the sample image for obtaining sample image；
Sample marks acquiring unit, for obtaining the sample image for having marked parking stall classification；
Parking stall vertex positions network, for being input with sample image, generates the parking stall vertex in sample image；
Arrival line ROI extraction unit, matches parking stall vertex, obtains all assembled schemes, wherein non-adjacent two are pushed up
The arrival line of point p1, p2 composition is invalid entry line, does not save invalid entry line, and remaining two non-adjacent vertex are effectively to enter
Effective arrival line is input to parking stall sorter network by mouth line；
Parking stall sorter network, for classifying to the parking stall in sample image,
Comparing unit obtains ratio by parking test results compared with the sample image marked in sample mark acquiring unit
Relatively result；
Amending unit, for correcting parking stall measure network with comparison result, the amending unit is for correcting the positioning of parking stall vertex
Network.
10. a kind of parking stall measure system characterized by comprising
Sample acquisition unit includes one or more parking stalls in the sample image for obtaining sample image；
Sample marks acquiring unit, for obtaining the sample image for having marked parking stall classification；
Vertex positions network, and the thermodynamic chart for characterizing parking stall vertex is obtained after input sample image and is obtained on thermodynamic chart
The coordinate of heating power aggregation zone；And parking stall vertex is obtained with this, by the image block around being obtained based on the parking stall vertex of acquisition；
Arrival line ROI extraction unit, matches parking stall vertex, obtains all assembled schemes, wherein non-adjacent two are pushed up
The arrival line of point p1, p2 composition is invalid entry line, does not save invalid entry line, and remaining two non-adjacent vertex are effectively to enter
Effective arrival line is input to parking stall sorter network by mouth line；
Parking stall sorter network for classifying to the parking stall in the image block in sample image, and obtains the parking stall in each classification.
11. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that: the program is by processor
The step in the method as described in claim 1 to 8 any claim is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811477045.2A CN109583392A (en) | 2018-12-05 | 2018-12-05 | A kind of method for detecting parking stalls, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811477045.2A CN109583392A (en) | 2018-12-05 | 2018-12-05 | A kind of method for detecting parking stalls, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109583392A true CN109583392A (en) | 2019-04-05 |
Family
ID=65927435
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811477045.2A Pending CN109583392A (en) | 2018-12-05 | 2018-12-05 | A kind of method for detecting parking stalls, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109583392A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348297A (en) * | 2019-05-31 | 2019-10-18 | 纵目科技（上海）股份有限公司 | A kind of detection method, system, terminal and the storage medium of parking systems for identification |
| CN110515376A (en) * | 2019-07-26 | 2019-11-29 | 纵目科技（上海）股份有限公司 | A kind of track deduces evaluation method, terminal and the storage medium of correction |
| CN110706509A (en) * | 2019-10-12 | 2020-01-17 | 东软睿驰汽车技术（沈阳）有限公司 | Parking space and direction angle detection method, device, equipment and medium thereof |
| CN112016342A (en) * | 2019-05-28 | 2020-12-01 | 惠州市德赛西威汽车电子股份有限公司 | Learning type intelligent parking method and system |
| CN113205059A (en) * | 2021-05-18 | 2021-08-03 | 北京纵目安驰智能科技有限公司 | Parking space detection method, system, terminal and computer readable storage medium |
| CN113822834A (en) * | 2020-06-03 | 2021-12-21 | 富泰华工业（深圳）有限公司 | Article detection device, article detection method, and storage medium |
| CN113822156A (en) * | 2021-08-13 | 2021-12-21 | 北京易航远智科技有限公司 | Parking space detection processing method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105975941A (en) * | 2016-05-31 | 2016-09-28 | 电子科技大学 | Multidirectional vehicle model detection recognition system based on deep learning |
| CN108227912A (en) * | 2017-11-30 | 2018-06-29 | 北京市商汤科技开发有限公司 | Apparatus control method and device, electronic equipment, computer storage media |
| CN108875911A (en) * | 2018-05-25 | 2018-11-23 | 同济大学 | One kind is parked position detecting method |
| CN108898628A (en) * | 2018-06-21 | 2018-11-27 | 北京纵目安驰智能科技有限公司 | Three-dimensional vehicle object's pose estimation method, system, terminal and storage medium based on monocular |
-
2018
- 2018-12-05 CN CN201811477045.2A patent/CN109583392A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105975941A (en) * | 2016-05-31 | 2016-09-28 | 电子科技大学 | Multidirectional vehicle model detection recognition system based on deep learning |
| CN108227912A (en) * | 2017-11-30 | 2018-06-29 | 北京市商汤科技开发有限公司 | Apparatus control method and device, electronic equipment, computer storage media |
| CN108875911A (en) * | 2018-05-25 | 2018-11-23 | 同济大学 | One kind is parked position detecting method |
| CN108898628A (en) * | 2018-06-21 | 2018-11-27 | 北京纵目安驰智能科技有限公司 | Three-dimensional vehicle object's pose estimation method, system, terminal and storage medium based on monocular |
Non-Patent Citations (1)
| Title |
|---|
| 王马成;黎海涛;: "基于深度卷积神经网络的停车位检测", 电子测量技术, no. 21 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112016342A (en) * | 2019-05-28 | 2020-12-01 | 惠州市德赛西威汽车电子股份有限公司 | Learning type intelligent parking method and system |
| CN110348297A (en) * | 2019-05-31 | 2019-10-18 | 纵目科技（上海）股份有限公司 | A kind of detection method, system, terminal and the storage medium of parking systems for identification |
| CN110348297B (en) * | 2019-05-31 | 2023-12-26 | 纵目科技（上海）股份有限公司 | Detection method, system, terminal and storage medium for identifying stereo garage |
| CN110515376A (en) * | 2019-07-26 | 2019-11-29 | 纵目科技（上海）股份有限公司 | A kind of track deduces evaluation method, terminal and the storage medium of correction |
| CN110515376B (en) * | 2019-07-26 | 2023-11-28 | 纵目科技（上海）股份有限公司 | Evaluation method, terminal and storage medium for track deduction correction |
| CN110706509A (en) * | 2019-10-12 | 2020-01-17 | 东软睿驰汽车技术（沈阳）有限公司 | Parking space and direction angle detection method, device, equipment and medium thereof |
| CN113822834A (en) * | 2020-06-03 | 2021-12-21 | 富泰华工业（深圳）有限公司 | Article detection device, article detection method, and storage medium |
| CN113205059A (en) * | 2021-05-18 | 2021-08-03 | 北京纵目安驰智能科技有限公司 | Parking space detection method, system, terminal and computer readable storage medium |
| CN113205059B (en) * | 2021-05-18 | 2024-03-12 | 北京纵目安驰智能科技有限公司 | Parking space detection method, system, terminal and computer readable storage medium |
| CN113822156A (en) * | 2021-08-13 | 2021-12-21 | 北京易航远智科技有限公司 | Parking space detection processing method and device, electronic equipment and storage medium |
| CN113822156B (en) * | 2021-08-13 | 2022-05-24 | 北京易航远智科技有限公司 | Parking space detection processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109583392A (en) | A kind of method for detecting parking stalls, device and storage medium | |
| CN109614913A (en) | A kind of oblique parking stall recognition methods, device and storage medium | |
| CN110348297B (en) | Detection method, system, terminal and storage medium for identifying stereo garage | |
| CN107633209B (en) | Electronic device, the method for dynamic video recognition of face and storage medium | |
| CN109614914A (en) | Parking stall vertex localization method, device and storage medium | |
| CN107766807A (en) | Electronic installation, insure livestock recognition methods and computer-readable recording medium | |
| CN110148148A (en) | A kind of training method, model and the storage medium of the lower edge detection model based on target detection | |
| US20130185024A1 (en) | System for automatic object classification and tagging in an rf planning tool | |
| CN107633208B (en) | Electronic device, the method for face tracking and storage medium | |
| CN112036400B (en) | Method for constructing network for target detection and target detection method and system | |
| CN107247791B (en) | Parking lot map data generation method and device and machine-readable storage medium | |
| CN107844468A (en) | The cross-page recognition methods of form data, electronic equipment and computer-readable recording medium | |
| CN109299675B (en) | Electrical drawing based distribution box identification method and device | |
| WO2021147222A1 (en) | Ocr-based table layout restoration method and device, electronic apparatus, and storage medium | |
| CN110176017A (en) | A kind of Model for Edge Detection based on target detection, method and storage medium | |
| Baluyan et al. | Novel approach for rooftop detection using support vector machine | |
| CN116168351A (en) | Inspection method and device for power equipment | |
| CN107766322A (en) | Entity recognition method, electronic equipment and computer-readable recording medium of the same name | |
| CN103955713A (en) | Icon recognition method and device | |
| JP4967045B2 (en) | Background discriminating apparatus, method and program | |
| CN107844527A (en) | Web page address De-weight method, electronic equipment and computer-readable recording medium | |
| CN117007600A (en) | Defect detection method, device, equipment and computer readable storage medium | |
| CN110688995A (en) | Map query processing method, computer-readable storage medium and mobile terminal | |
| CN109918277A (en) | Electronic device, the evaluation method of system log cluster analysis result and storage medium | |
| CN109191379A (en) | A kind of semanteme marking method of panoramic mosaic, system, terminal 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 |