CN107704162A - One kind mark object control method - Google Patents
One kind mark object control method Download PDFInfo
- Publication number
- CN107704162A CN107704162A CN201610645264.1A CN201610645264A CN107704162A CN 107704162 A CN107704162 A CN 107704162A CN 201610645264 A CN201610645264 A CN 201610645264A CN 107704162 A CN107704162 A CN 107704162A
- Authority
- CN
- China
- Prior art keywords
- control point
- callout box
- mouse
- mouse position
- target control
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04842—Selection of displayed objects or displayed text elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/40—Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the invention discloses one kind to mark object control method, and method includes：After being labeled using callout box to the object in image, the control point of callout box is obtained, and establishes the corresponding relation of control point and object；If listening to the click event of mouse, mouse position is obtained；If judgement knows mouse position at least two callout box, target control point closest with mouse position at least two callout box, and the destination object according to corresponding to corresponding relation obtains target control point are obtained.The embodiment of the present invention obtains mouse position after the click event by monitoring mouse, calculate and the closest target control point of mouse position, and according to control point and the corresponding relation of object, obtain destination object corresponding to target control point, position determines destination object when can be clicked on according to mouse, reduce annotation tool and the interaction times of user so that annotation process is more simple, while saves label time.
Description
Technical field
The present embodiments relate to intelligent automobile technical field, and in particular to one kind mark object control method.
Background technology
Deepened continuously with the research of intelligent automobile, its intelligence degree improves constantly, in increasing intelligent automobile
Intelligent object is introduced, while driver driving experience is improved, disclosure satisfy that the personalized customization requirement of different drivers, therefore
Increasingly welcome by user.
Automatic Pilot sensing module is very important One function module in intelligent automobile, in car steering process
The object of middle automatic identification motor vehicle environment, including：People, car, barrier and building etc., it is directed to substantial amounts of deep learning
Algorithm, these deep learning algorithms need the substantial amounts of training sample marked, therefore, it is necessary to by marking in application program
Callout box is labeled to different objects.But existing method is during mark, when multiple callout box are overlapping, such as
When fruit user will select destination object corresponding to one of callout box, then need with mark application program repeatedly interact
It can determine that so that annotation process is relatively complicated, while expends the time.
During the embodiment of the present invention is realized, inventor has found existing method during mark, when multiple
The destination object to be selected just is can determine that, it is necessary to mark application program repeatedly interact so that mark when callout box is overlapping
Process is relatively complicated, while expends the time.
The content of the invention
Because existing method is during mark, when multiple callout box are overlapping, it is necessary to enter with mark application program
Repeatedly interaction just can determine that the destination object to be selected to row so that annotation process is relatively complicated, while time-consuming problem, this
Inventive embodiments propose a kind of mark object control method.
The embodiment of the present invention proposes a kind of mark object control method, including：
After being labeled using callout box to the object in image, the control point of the callout box is obtained, and described in foundation
Control point and the corresponding relation of the object；
If listening to the click event of mouse, mouse position is obtained；
If judge know the mouse position at least two callout box, obtain at least two callout box with
The closest target control point of the mouse position, and the mesh according to corresponding to the corresponding relation obtains the target control point
Mark object.
Preferably, the callout box is rectangle frame.
Preferably, the control point for obtaining the callout box includes：
4 summits and the midpoint on 4 sides of the rectangle frame are obtained, wherein, in 4 summits and 4 sides
Point is the control point of the rectangle frame.
Preferably, methods described also includes：
If judgement knows the mouse position in a callout box, object corresponding to the callout box is target pair
As.
Preferably, it is described to obtain target control point closest with the mouse position at least two callout box
Including：
Obtain each control point of at least two callout box；
The distance of the mouse position and each control point is calculated, obtains several distances；
Minimum range in several described distances of selection, and obtain target control point corresponding to the minimum range.
As shown from the above technical solution, mouse position is obtained after click event of the embodiment of the present invention by monitoring mouse,
Calculating and the closest target control point of the mouse position, and according to control point and the corresponding relation of the object, obtain
Destination object corresponding to the target control point, position determines destination object when can be clicked on according to mouse, and reducing mark should
With program and the interaction times of user so that annotation process is more simple, while saves label time.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these figures.
Fig. 1 is a kind of schematic flow sheet for mark object control method that one embodiment of the invention provides；
Fig. 2 is the result schematic diagram of object after a kind of mark that one embodiment of the invention provides；
Fig. 3 is the result schematic diagram of object after a kind of mark that another embodiment of the present invention provides；
Fig. 4 is a kind of structural representation for mark object control device that one embodiment of the invention provides；
Fig. 5 is a kind of logic diagram for mark object control terminal that one embodiment of the invention provides.
Embodiment
Below in conjunction with the accompanying drawings, the embodiment of invention is further described.Following examples are only used for more clear
Illustrate to Chu technical scheme, and can not be limited the scope of the invention with this.
Fig. 1 shows a kind of schematic flow sheet for mark object control method that the present embodiment provides, including：
S101, after being labeled using callout box to the object in image, the control point of the callout box is obtained, and established
The control point and the corresponding relation of the object；
Specifically, after the object in the mark application program identification image of terminal, using callout box to the object that is identified
It is labeled, obtains the control point in the callout box, and corresponding relation is established at each control point and the object identified.
Wherein, the mark application program is used to be labeled the object in image, with the spy in quick obtaining image
Determine object.
The object is the objects such as people, car, barrier and the building obtained in described image after image recognition.
After the callout box is the special object in identification image, figure that the special object region is labeled
Shape, so that follow-up intelligent automobile is during automatic Pilot, special object that can be in quick obtaining image.
The control point is to be used to control the point that the side of callout box moves in callout box.For example, when click callout box
Behind the control point on upper certain side, the side can be moved to optional position.
The corresponding relation for the object that the corresponding relation is marked by the callout box where each control point and the control point.
If S102, the click event for listening to mouse, obtain mouse position；
Specifically, the mark application program is monitored the Action Events of mouse, when the click thing for listening to mouse
After part, current mouse position is obtained.
If S103, judgement know the mouse position at least two callout box, at least two mark is obtained
The target control closest with mouse position point in frame, and the target control point pair is obtained according to the corresponding relation
The destination object answered.
Specifically, the mark application program obtains all callout box in described image, judges the mouse position successively
Put whether in each callout box, to know callout box of the mouse position in callout box；Judge when the mouse position exists
When at least two callout box, obtain all control points of at least two callout box, calculate successively the mouse position with
The distance at each control point, select minimum distance corresponding to control point be used as target control point, acquisition target control point, and according to
Control point and the corresponding relation of object, obtain destination object corresponding to target control point.
Wherein, the target control point is the control point nearest apart from mouse position.
The object that the destination object is marked by the callout box where target control point.
The present embodiment obtains mouse position after the click event by monitoring mouse, calculate with mouse position distance most
Near target control point, and according to control point and the corresponding relation of the object, obtain target corresponding to the target control point
Object, position determines destination object when can be clicked on according to mouse, reduces mark application program and the interaction times of user, makes
It is more simple to obtain annotation process, while saves label time.
Further, on the basis of above method embodiment, the callout box is rectangle frame.
The object of two images is shown using the result after rectangle frame is labeled for the present embodiment as shown in Figures 2 and 3
It is intended to, wherein, triangle is masked as mouse position, and oval frame is used to represent currently there is rectangle frame, in order to which user checks rectangle frame.
The object in image is labeled as callout box by using rectangle frame, not only annotation process is more convenient,
And it is easy to adjust.
Further, on the basis of above method embodiment, the control point bag of the callout box is obtained described in S101
Include：
4 summits and the midpoint on 4 sides of the rectangle frame are obtained, wherein, in 4 summits and 4 sides
Point is the control point of the rectangle frame.
Wherein, rectangle frame includes 4 summits and 4 sides, selects the midpoint on side to be conveniently adjusted single edge as control point
Position；Summit is selected to be easy to adjust the position on two sides being connected with the summit simultaneously as control point.
Further, on the basis of above method embodiment, methods described also includes：
If S104, judgement know the mouse position in a callout box, object corresponding to the callout box is mesh
Mark object.
Specifically, the mark application program judges to know the mouse position in a callout box, then it represents that without
Identification is currently needed for the callout box of operation, and object corresponding to the callout box is destination object.
Quantity by judging the callout box where mouse position then directly obtains target callout box, further for one
Destination object is obtained according to target callout box, the follow-up distance for calculating mouse position and control point can be avoided, when saving processing
Between.
Further, on the basis of above method embodiment, at least two callout box is obtained described in S103
In the target control point closest with the mouse position include：
S1031, each control point for obtaining at least two callout box；
Specifically, the mark application program obtains each control point of at least two callout box.
S1032, the mouse position and the distance at each control point are calculated, obtain several distances；
Specifically, the mark application program calculates the mouse position and the distance at each control point, obtains some
Individual distance.
Minimum range in S1033, several described distances of selection, and obtain target control corresponding to the minimum range
Point.
Specifically, the minimum range in several described distances of the mark application program selection, and obtain the minimum
Target control point corresponding to distance.
For example, the coordinate position at control point is represented using vectorial (x, y, id), and control point and corresponding objects
Corresponding relation.Wherein, x is the abscissa at control point, and y is the ordinate at control point, and id is the mark of object corresponding to control point
Number.
Assuming that mark application program judge know mouse click on when position M in callout box A and callout box B, callout box A
Control point include C1 (x1, y1, A), C2 (x2, y2, A), C3 (x3, y3, A), C4 (x4, y4, A), C5 (x5, y5, A), C6 (x6, y6,
A)、C7(x7, y7, A) and C8 (x8, y8, A), callout box B control point includes D1 (x9, y9, B), D2 (x10, y10, B), D3 (x11,
y11, B), D4 (x12, y12, B), D5 (x13, y13, B), D6 (x14, y14, B), D (x15, y15, B) and 7 and D8 (x16, y16, B).
Mouse position M and C1, C2, C3, C4, C5, C6, C7, C8, D1, D2, D3, D4, D5, D6, D7 and D8 are calculated respectively
Distance is MC1, MC2, MC3, MC4, MC5, MC6, MC7, MC8, MD1, MD2, MD3, MD4, MD5, MD6, MD7 and MD8.
Assuming that it is MC6 apart from minimum, then target control point is C6 (x6, y6, A), corresponding destination object is callout box A
The object marked.
By calculating the distance of mouse position and each control point successively, closest control point can be accurately known.
Fig. 4 shows a kind of structural representation for mark object control device that the present embodiment provides, and described device includes：
Control point acquisition module 401, mouse position acquisition module 402 and first object object acquisition module 403, wherein：
The control point acquisition module 401 is used for after being labeled using callout box to the object in image, described in acquisition
The control point of callout box, and establish the corresponding relation at the control point and the object；
If the mouse position acquisition module 402 is used for the click event for listening to mouse, mouse position is obtained；
If the first object object acquisition module 403 is used to judge to know the mouse position at least two callout box
In, then target control point closest with the mouse position at least two callout box is obtained, and according to described right
It should be related to obtain destination object corresponding to the target control point.
Specifically, after the control point acquisition module 401 is labeled using callout box to the object in image, institute is obtained
The control point of callout box is stated, and establishes the corresponding relation at the control point and the object；The mouse position acquisition module 402
If listening to the click event of mouse, mouse position is obtained；If the first object object acquisition module 403 judges to know institute
Mouse position is stated at least two callout box, then is obtained closest with the mouse position at least two callout box
Target control point, and the destination object according to corresponding to the corresponding relation obtains the target control point.
The present embodiment obtains mouse position after the click event by monitoring mouse, calculate with mouse position distance most
Near target control point, and according to control point and the corresponding relation of the object, obtain target corresponding to the target control point
Object, position determines destination object when can be clicked on according to mouse, reduces mark application program and the interaction times of user, makes
It is more simple to obtain annotation process, while saves label time.
Further, on the basis of said apparatus embodiment, the callout box is rectangle frame.
Further, on the basis of said apparatus embodiment, the control point acquisition module 401 is further used for obtaining
4 summits of the rectangle frame and the midpoint on 4 sides, wherein, the midpoint on 4 summits and 4 sides is the rectangle
The control point of frame.
Further, on the basis of said apparatus embodiment, described device also includes：
Second semantic object extraction module 404, if for judging to know the mouse position in a callout box, institute
It is destination object to state object corresponding to callout box.
Further, on the basis of said apparatus embodiment, the first object object acquisition module 403 is further
Including：
Control point acquiring unit 4031, for obtaining each control point of at least two callout box；
Metrics calculation unit 4032, for calculating the distance of the mouse position and each control point, obtain several
Distance；
Target control point acquiring unit 4033, for selecting the minimum range in several described distances, and described in acquisition
Target control point corresponding to minimum range.
Mark object control device described in the present embodiment can be used for performing above method embodiment, its principle and technology
Effect is similar, and here is omitted.
Fig. 5 shows the entity structure schematic diagram of mark object control terminal provided in an embodiment of the present invention, the terminal bag
Include：Processor (processor) 501, memory (memory) 502, communication interface (Communications Interface)
503 and bus 504, wherein, processor 501, memory 502, communication interface 503, completed by bus 504 mutual logical
Letter.The information transfer that communication interface 503 can be used between server and application program update process holding terminal.
The memory 502, for storing the corresponding relation at control point and object；
The processor 501 can call the control point in memory 502 and the corresponding relation of object, to perform such as lower section
Method：
After being labeled using callout box to the object in image, the control point of the callout box is obtained, and described in foundation
Control point and the corresponding relation of the object；
If listening to the click event of mouse, mouse position is obtained；
If judge know the mouse position at least two callout box, obtain at least two callout box with
The closest target control point of the mouse position, and the mesh according to corresponding to the corresponding relation obtains the target control point
Mark object.
In addition, the corresponding relation at the control point and object in above-mentioned memory 502 can pass through SFU software functional unit
Form is realized and is used as independent production marketing or in use, can be stored in a computer read/write memory medium.Base
In the part that such understanding, technical scheme substantially contribute to prior art in other words or the technical side
The part of case can be embodied in the form of software product, and the computer software product is stored in a storage medium, bag
Original picture is included to so that a computer equipment (can be personal computer, server, or network equipment etc.) performs sheet
Invent all or part of step of each embodiment methods described.And foregoing storage medium includes：It is USB flash disk, mobile hard disk, read-only
Memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or
Person's CD etc. is various can be with the medium of store program codes.
The present embodiment obtains mouse position after the click event by monitoring mouse, calculate with mouse position distance most
Near target control point, and according to control point and the corresponding relation of the object, obtain target corresponding to the target control point
Object, position determines destination object when can be clicked on according to mouse, reduces mark application program and the interaction times of user, makes
It is more simple to obtain annotation process, while saves label time.
Device embodiment described above is only schematical, wherein the unit illustrated as separating component can
To be or may not be physically separate, it can be as the part that unit is shown or may not be physics list
Member, you can with positioned at a place, or can also be distributed on multiple NEs.It can be selected according to the actual needs
In some or all of module realize the purpose of this embodiment scheme.Those of ordinary skill in the art are not paying creativeness
Work in the case of, you can to understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
Realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on such understanding, on
The part that technical scheme substantially in other words contributes to prior art is stated to embody in the form of software product, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including some fingers
Make to cause a computer equipment (can be personal computer, server, or network equipment etc.) to perform each implementation
Method described in some parts of example or embodiment.
It should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although reference
The present invention is described in detail previous embodiment, it will be understood by those within the art that：It still can be right
Technical scheme described in foregoing embodiments is modified, or carries out equivalent substitution to which part technical characteristic；And this
A little modifications are replaced, and the essence of appropriate technical solution is departed from the spirit and model of various embodiments of the present invention technical scheme
Enclose.
Claims (5)
1. one kind mark object control method, it is characterised in that including：
After being labeled using callout box to the object in image, the control point of the callout box is obtained, and establishes the control
The corresponding relation of point and the object；
If listening to the click event of mouse, mouse position is obtained；
If judge know the mouse position at least two callout box, obtain at least two callout box with it is described
The closest target control point of mouse position, and the target pair according to corresponding to the corresponding relation obtains the target control point
As.
2. according to the method for claim 1, it is characterised in that the callout box is rectangle frame.
3. according to the method for claim 2, it is characterised in that the control point for obtaining the callout box includes：
4 summits and the midpoint on 4 sides of the rectangle frame are obtained, wherein, the midpoint on 4 summits and 4 sides is
The control point of the rectangle frame.
4. according to the method for claim 1, it is characterised in that methods described also includes：
If judgement knows the mouse position in a callout box, object corresponding to the callout box is destination object.
5. according to the method for claim 1, it is characterised in that it is described obtain at least two callout box with the mouse
The closest target control point of cursor position includes：
Obtain each control point of at least two callout box；
The distance of the mouse position and each control point is calculated, obtains several distances；
Minimum range in several described distances of selection, and obtain target control point corresponding to the minimum range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610645264.1A CN107704162A (en) | 2016-08-08 | 2016-08-08 | One kind mark object control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610645264.1A CN107704162A (en) | 2016-08-08 | 2016-08-08 | One kind mark object control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107704162A true CN107704162A (en) | 2018-02-16 |
Family
ID=61168813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610645264.1A Withdrawn CN107704162A (en) | 2016-08-08 | 2016-08-08 | One kind mark object control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107704162A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109710148A (en) * | 2018-12-19 | 2019-05-03 | 广州文远知行科技有限公司 | Selection method, device, computer equipment and the storage medium of image labeling frame |
| CN110113651A (en) * | 2019-04-12 | 2019-08-09 | 北京奇艺世纪科技有限公司 | A kind of barrage answering method, device and electronic equipment |
| CN110210328A (en) * | 2019-05-13 | 2019-09-06 | 北京三快在线科技有限公司 | The method, apparatus and electronic equipment of object are marked in image sequence |
| CN111160402A (en) * | 2019-12-09 | 2020-05-15 | 武汉光庭信息技术股份有限公司 | Vehicle 2.5D image annotation method and device |
| CN111310667A (en) * | 2020-02-18 | 2020-06-19 | 北京小马慧行科技有限公司 | Method, device, storage medium and processor for determining whether annotation is accurate |
| CN113126866A (en) * | 2021-04-27 | 2021-07-16 | 北京百度网讯科技有限公司 | Object determination method and device, electronic equipment and storage medium |
| CN113392230A (en) * | 2020-03-13 | 2021-09-14 | 阿里巴巴集团控股有限公司 | Method for processing and operating labeled data, labeled platform and database |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101526877A (en) * | 2008-03-06 | 2009-09-09 | 日产自动车株式会社 | Display controller and item display method |
| US20100229128A1 (en) * | 2009-03-03 | 2010-09-09 | Funai Electric Co., Ltd. | Input Apparatus and Input System |
| CN107003792A (en) * | 2014-12-25 | 2017-08-01 | 爱信艾达株式会社 | Display control program, method and program |
-
2016
- 2016-08-08 CN CN201610645264.1A patent/CN107704162A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101526877A (en) * | 2008-03-06 | 2009-09-09 | 日产自动车株式会社 | Display controller and item display method |
| US20100229128A1 (en) * | 2009-03-03 | 2010-09-09 | Funai Electric Co., Ltd. | Input Apparatus and Input System |
| CN107003792A (en) * | 2014-12-25 | 2017-08-01 | 爱信艾达株式会社 | Display control program, method and program |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109710148A (en) * | 2018-12-19 | 2019-05-03 | 广州文远知行科技有限公司 | Selection method, device, computer equipment and the storage medium of image labeling frame |
| CN110113651A (en) * | 2019-04-12 | 2019-08-09 | 北京奇艺世纪科技有限公司 | A kind of barrage answering method, device and electronic equipment |
| CN110210328A (en) * | 2019-05-13 | 2019-09-06 | 北京三快在线科技有限公司 | The method, apparatus and electronic equipment of object are marked in image sequence |
| CN111160402A (en) * | 2019-12-09 | 2020-05-15 | 武汉光庭信息技术股份有限公司 | Vehicle 2.5D image annotation method and device |
| CN111160402B (en) * | 2019-12-09 | 2022-05-17 | 武汉光庭信息技术股份有限公司 | Vehicle 2.5D image annotation method and device |
| CN111310667A (en) * | 2020-02-18 | 2020-06-19 | 北京小马慧行科技有限公司 | Method, device, storage medium and processor for determining whether annotation is accurate |
| CN111310667B (en) * | 2020-02-18 | 2023-09-01 | 北京小马慧行科技有限公司 | Method, device, storage medium and processor for determining whether annotation is accurate |
| CN113392230A (en) * | 2020-03-13 | 2021-09-14 | 阿里巴巴集团控股有限公司 | Method for processing and operating labeled data, labeled platform and database |
| CN113126866A (en) * | 2021-04-27 | 2021-07-16 | 北京百度网讯科技有限公司 | Object determination method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107704162A (en) | One kind mark object control method | |
| CN111062495B (en) | Machine learning method and related device | |
| WO2021078027A1 (en) | Method and apparatus for constructing network structure optimizer, and computer-readable storage medium | |
| CN108764304B (en) | Scene recognition method and device, storage medium and electronic equipment | |
| CN108875045B (en) | Method of performing machine learning process for text classification and system thereof | |
| CN107690659A (en) | A kind of image identification system and image-recognizing method | |
| CN107704163A (en) | One kind mark object control device | |
| CN109801260A (en) | The recognition methods of livestock number and device | |
| EP4163822A1 (en) | Data annotation method and apparatus, and computer device and storage medium | |
| CN113939791A (en) | Image labeling method, device, equipment and medium | |
| US20230087292A1 (en) | Data annotation method and apparatus, and fine-grained recognition method and apparatus | |
| CN111259707B (en) | Training method of special linear lane line detection model | |
| CN106445915A (en) | New word discovery method and device | |
| CN108334805A (en) | The method and apparatus for detecting file reading sequences | |
| CN109544561A (en) | Cell mask method, system and device | |
| CN111652141B (en) | Question segmentation method, device, equipment and medium based on question numbers and text lines | |
| JP2022079509A (en) | Learning data creating device, method for creating learning data, and program | |
| CN114063858B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN105022843A (en) | Interaction method and system based on online handwriting | |
| CN115545145A (en) | Method for optimizing neural network model and neural network model processing system for executing method | |
| CN108769160B (en) | Service line recommended method, device and storage medium based on service | |
| CN109693244A (en) | The method and device of optimization dialogue robot | |
| CN113657370A (en) | Character recognition method and related equipment thereof | |
| CN111571567A (en) | Robot translation skill training method and device, electronic equipment and storage medium | |
| CN109241564A (en) | A kind of Photographing On-line method and apparatus of computer room assets |
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 | ||
| CB02 | Change of applicant information |
Address after: 511458 9, Nansha District Beach Road, Guangzhou, Guangdong, 9 Applicant after: Evergrande Faraday Future Smart Car (Guangdong) Co.,Ltd. Address before: 511458 9, Nansha District Beach Road, Guangzhou, Guangdong, 9 Applicant before: Rui Chi Intelligent Automobile (Guangzhou) Co.,Ltd. Address after: 100026 8 floor 909, 105 building 3, Yao Yuan Road, Chaoyang District, Beijing. Applicant after: Lexus Automobile (Beijing) Co.,Ltd. Address before: 100026 8 floor 909, 105 building 3, Yao Yuan Road, Chaoyang District, Beijing. Applicant before: FARADAY (BEIJING) NETWORK TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180907 Address after: 511458 9, Nansha District Beach Road, Guangzhou, Guangdong, 9 Applicant after: Rui Chi Intelligent Automobile (Guangzhou) Co.,Ltd. Address before: 100026 8 floor 909, 105 building 3, Yao Yuan Road, Chaoyang District, Beijing. Applicant before: Lexus Automobile (Beijing) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190311 Address after: 100015 Building No. 7, 74, Jiuxianqiao North Road, Chaoyang District, Beijing, 001 Applicant after: FAFA Automobile (China) Co.,Ltd. Address before: 511458 9, Nansha District Beach Road, Guangzhou, Guangdong, 9 Applicant before: Evergrande Faraday Future Smart Car (Guangdong) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180216 |
|
| WW01 | Invention patent application withdrawn after publication |