CN101607138A - Action identification method based on finite automata model - Google Patents
Action identification method based on finite automata model Download PDFInfo
- Publication number
- CN101607138A CN101607138A CNA2008100435135A CN200810043513A CN101607138A CN 101607138 A CN101607138 A CN 101607138A CN A2008100435135 A CNA2008100435135 A CN A2008100435135A CN 200810043513 A CN200810043513 A CN 200810043513A CN 101607138 A CN101607138 A CN 101607138A
- Authority
- CN
- China
- Prior art keywords
- action
- sub
- son
- finite automata
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention discloses a kind of action identification method, may further comprise the steps: the action of definition based on finite automata model; Motion operation is divided into the plurality of sub action, describes its sub-action sequence with the manual expression formula; The dynamic data of acceleration transducer collection are divided into the data subset of plurality of continuous, each data subset is judged as corresponding son action, obtain the sub-action sequence of dynamic data; Introduce finite automata model,, carry out action recognition according to the son action of dynamic data and the manual expression formula of motion operation.Action identification method of the present invention can be handled the input action data in real time, promotes action recognition efficient.
Description
Technical field
The present invention relates to the action induction technology, particularly a kind of action identification method based on finite automata model.
Background technology
Generally speaking, size according to movement range can be divided into two kinds to the action induction technology: the induction of small action and action induction significantly, the induction of common small action is just like flight simulator etc., if the small variation of handle can both be experienced in recreation; The electronic game machine Wii that common action induction was significantly issued just like Nintendo in 2006 etc., move as above significantly/down/left side/right side etc., arm has action usually.
The action induction The Application of Technology need realize in conjunction with relevant hardware, with the game paddle is example, for first kind of small action induction technology, need the gyroscope that to measure rotary speed in the handle, only need simply handle the angular velocity of rotation that gyroscope is measured getting final product at the software end.
For action induction technology significantly, relevant hardware needs to measure XYZ three axis linear acceleration at least, can also increase the gyroscope of measuring angular velocity of rotation on this basis.
The dynamic parser of action induction technology is to be input with 3 of dynamic handle or 5 axle acceleration sensor influence values significantly, goes out user's motion operation by the software algorithm final analysis.
Significantly dynamic at present parser also is in the starting stage, generally can only be some simple motion of identification, for example up, down, left, right, before and after etc.All need to spend the plenty of time and energy goes identification for the identification of some compound actions, and action of every interpolation is not always the case.And have a large amount of floating-point operations in the algorithm, have a strong impact on efficient, the delayed response time.
Summary of the invention
The technical problem to be solved in the present invention provides a kind of action identification method based on finite automata model, adopts this action induction method, can handle the input action data in real time, promotes action recognition efficient.
For solving the problems of the technologies described above, the action identification method based on finite automata model of the present invention may further comprise the steps:
(1) definition action;
(2) motion operation is divided into the plurality of sub action, describes its sub-action sequence with the manual expression formula;
(3) the dynamic data of acceleration transducer collection are divided into the data subset of plurality of continuous, each data subset is judged as corresponding son action, obtain the sub-action sequence of dynamic data;
(4) introduce finite automata model,, carry out action recognition according to the son action of dynamic data and the manual expression formula of motion operation.
The sub-action sequence of the dynamic data that step (3) obtains can carry out earlier carrying out step (4) again after the error shielding.
Space displacement amount, the average acceleration that can move according to the son of dynamic data are carried out the error shielding.
Action identification method based on finite automata model of the present invention is introduced finite automata (being called for short FA) model, can discern complicated action.For compound action, it is divided into the son action of plurality of continuous, represent the action of this reality with sub-action sequence.This sequence is input to FA one by one, and FA changes the output action result of determination according to the internal logic of oneself through certain state.Can handle the input action data in real time, promote action recognition efficient.
Description of drawings
Below in conjunction with the drawings and the specific embodiments the present invention is described in further detail.
Fig. 1 is the action identification method one embodiment flow chart based on finite automata model of the present invention;
Fig. 2 is a motion operation " circle clockwise " schematic diagram;
Fig. 3 is a sub-action definition mode example;
Fig. 4 is that a motion operation is divided son action example;
Fig. 5 is the two seeds action division methods example to " circle clockwise ".
The specific embodiment
Significantly action induction method one embodiment based on finite automata model of the present invention may further comprise the steps as shown in Figure 1:
(1) definition action;
(2) motion operation is divided into the plurality of sub action, in configuration file, describes its sub-action sequence with mathematic(al) representation;
(3) the dynamic data of the dynamic handle of acceleration transducer collection are divided into the data subset of plurality of continuous, each data subset is judged as corresponding son action, obtain the sub-action sequence of dynamic data;
(4) judging that according to dynamic data the sub-action sequence that obtains carries out the error shielding according to space displacement amount, the average acceleration of son action, to eliminate the error that dynamic handle state induction and small shake are brought;
(5) introduce finite automata model,, carry out action recognition according to the son action of dynamic data and the sub-action sequence of in configuration file, describing of motion operation with mathematic(al) representation.
Action identification method based on finite automata model of the present invention is introduced finite automata (being called for short FA) model, can discern complicated action.For compound action, it is divided into the son action of plurality of continuous, represent the action of this reality with sub-action sequence.This sequence is input to FA one by one, and FA changes the output action result of determination according to the internal logic of oneself through certain state.Can handle the input action data in real time, promote action recognition efficient.
No matter be 3 or 5 acceleration transducer, its action induction is to occur with the form of space 3 axle accelerations, and this just means that it does not have influence value when dynamic handle is made uniform motion in the space, is as good as when static at this moment.In the technical scheme of the present invention, can or have only the action of small induction to ignore non-inductive value.The present invention is applicable to the significantly action induction of 3 dimension spaces, but for the ease of accurately describing technology of the present invention, is example with " circle clockwise " in the 2 dimension action plane below, and technical scheme of the present invention is described.
1. definition action
In the plane, can define 8 son actions, be respectively " →
↑
←
↓
".But this is not unique definition, can be defined as 4,12 even more yet, mainly is by application program the different demands of motion operation accuracy to be decided.The various definitions mode of son action as shown in Figure 3.
For the action identification method based on finite automata model of the present invention, the son of definition action is many more, and is can recognized action just careful more, accurate more.But in actual implementation procedure, the dynamic handle of for example playing, because the error of dynamic handle hardware output parameter, and the restriction of the each side factors such as actual operation ability of PC, this accuracy will be affected.Thereby can not unrestrictedly too much define the son action.Here hypothesis is defined as 8.
2. motion operation is divided into the experimental process action
A fundamental issue of action induction technology is " how discerning motion operation ".In the present invention, based on defined son action in the 1st, the son that whole motion operation is divided into plurality of continuous moves.Again this sub-action sequence is mated at last.
A method in common of dividing motion operation is based on the time and divides, and suppose motion operation as shown in Figure 4, and the curve among Fig. 4 is represented the track of motion operation, and 2 dotted lines wherein are this division of operations 3 sections, promptly are divided into 3 sons and move.According to defined son action in the 1st, can 3 stages among Fig. 3 be judged to be successively " →
→ ".Pre-defined the leaving in the configuration file of manual expression formula that this motion operation is described, after the dynamic handle of user is done an action, the dynamic data of the dynamic handle that acceleration transducer is gathered can with predefined manual expression formula in the configuration file " →
→ " coupling, just being considered to the target action, application program just reads the description of manual expression formula in the configuration file, sets up FA then dynamicly, and then carries out action recognition, carries out corresponding logic function.Method of the present invention might not need motion operation consistent completely, and certain fault-tolerance is arranged in this process.
For example just can divide as shown in Figure 5 for the clockwise circle described in Fig. 2:
Two kinds of divisions are arranged among Fig. 5:
(1) left side: be divided into 4 son actions, can be identified as successively "
".
(2) the right: be divided into 4 son actions, can be identified as successively " → ↓ ← ↑ ".
These two kinds of zoned formats can be as the standard of identification.
But, it is not only these two kinds from motion operation " circle clockwise " itself.Can be refined as 4 types in fact for each top division:
(1)①→②→③→④
(2)②→③→④→①
(3)③→④→①→②
(4)④→①→②→③
So among Fig. 5 representative be exactly 8 seed action sequences.As long as the action of the dynamic handle of user can with one kind of coupling, that just can be identified as " circle clockwise " and move.These contents in actual development process all the available profile form present, and at the inner engine that needs to realize these action of configuration expression formulas of identification of program.
This action identification method of the present invention also has the another one advantage except discerning easily the compound action.Need now to suppose this operation of identification " n time round clockwise ", so only need simple modification action of configuration expression formula to get final product, for example can be expressed as " 1 → 2 → 3 → 4 → 1 → 2 → 3 → 4 " for " 2 times round clockwise ".
3. dynamic data are divided into the data subset of plurality of continuous
Two steps in front are to build analytical framework for analyzing motion operation in fact.From this step, just can carry out concrete data analysis and action recognition.
The identification for action has also been mentioned in the front, at first will carry out segmentation to the data based time of innervation.After the son action of dynamic data is judged in segmentation, the more continuous sub-action sequence of dynamic data is discerned.
The acceleration transducer of dynamic handle is at x for the output of action induction, y, and the acceleration on z three direction of principal axis is designated as that (ax, ay az), thereby at first need the point set of these data conversion for corresponding space motion path.
Suppose to be sampled as 100 times/S, son action split time is 50ms, needs 250ms if be used to finish " circle clockwise " this action, can be divided into the data subset of 5 son actions so.Then data acquisition system of each son action is carried out linear fit (linear because the son action in the above in second all is defined as, tool has great advantage on arithmetic speed).
4. shield the error that state induction and small shake are brought
Carry out in the motion operation process unavoidable some maloperation at dynamic handle, for example the user holds handle and keeps motionless, but in fact be difficult to guarantee static fully, acceleration transducer some influence value always more or less.Thereby be necessary for the processing of the error of this class.
Demand for action induction in some application programs is the action of type significantly, and the user also can be put into the scope of shielding if any a small amount of small-sized action so.
Also have a kind of situation in addition, when a motion operation finishes, from space motion path, be almost static.But the angle of theorem of kinetic energy from mechanics has a reverse impulse force that influence value is bigger during release, and what show in dynamic data is exactly the bigger values of a series of influence values.This also need deshield.
In the present invention, can carry out the error shielding, dual mode is roughly arranged according to the son action:
(1) the space displacement amount of son action
(2) average acceleration of son action
5. introduce finite automata (FA) Model Identification motion operation
Finite automata is in the computer theory, can handle a kind of model of complex state conversion logic rationally and effectively, following 5 parts of its formal definition: state set, alphabet, transfer function, initial state and final state.
Introduce in the present invention the finite automata model, compared following advantage with general action induction technology:
(1) processes in real time input.
Common action induction technology need to wait until that when processing the dynamic data of induction motion operation finishes The time, could process data. And in the present invention, greatly promote in the action recognition technology The real time data processing ability, the generation of each height action can be as the input of FA, in real time Change the internal state of FA.
(2) promote action recognition efficient.
The needed time of FA identification maneuver is depended on the quantity of son action. For example finish one moving Sense action need 250ms, be 50ms every sub-actuation time, will produce one every 50ms so Individual sub-actuating signal. For FA, can receive the sub-actuating signal of an input every 50ms, Thereby order about the variation of a series of states.
(3) effectively organize all kinds of motion operation.
For each motion operation, owing to itself there is a multiple situation, as mentioning in the 2nd " clockwise circle " this operation. Generally speaking, can mate one by one during identification. But at this Introduce the FA model in bright, just do not needed. Because " clockwise circle " this division of operations is 4 The son action so for the identification of this action, is exactly to be determined by sub-amount of action, is fixed as 4, There are several situations irrelevant with this operation.
(4) simplify development process.
In the specific implementation process, at first adopt manual expression formal description motion operation, it is namely described Sub-action sequence realize to make up the engine of FA then in inside. Application program at first reads the configuration literary composition For the manual expression form of the description of motion operation, the dynamic FA that sets up is subsequent then in the part Just can carry out action recognition.
When needs increase identification to new motion operation, only need in configuration file, add and to move The expression formula of doing is described and is got final product, and does not need to revise any module.
Claims (3)
1, a kind of action identification method based on finite automata model is characterized in that, may further comprise the steps:
(1) definition action;
(2) motion operation is divided into the plurality of sub action, describes its sub-action sequence with the manual expression formula;
(3) the dynamic data of acceleration transducer collection are divided into the data subset of plurality of continuous, each data subset is judged as corresponding son action, obtain the sub-action sequence of dynamic data;
(4) introduce finite automata model,, carry out action recognition according to the son action of dynamic data and the manual expression formula of motion operation.
2, the action identification method based on finite automata model according to claim 1 is characterized in that, the sub-action sequence of the dynamic data that step (3) is obtained carries out carrying out step (4) again after the error shielding.
3, the action identification method based on finite automata model according to claim 2 is characterized in that, carries out the error shielding according to space displacement amount, the average acceleration of the action of the son of dynamic data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008100435135A CN101607138B (en) | 2008-06-17 | 2008-06-17 | Action recognition method based on finite automata model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008100435135A CN101607138B (en) | 2008-06-17 | 2008-06-17 | Action recognition method based on finite automata model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101607138A true CN101607138A (en) | 2009-12-23 |
| CN101607138B CN101607138B (en) | 2013-11-20 |
Family
ID=41481146
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2008100435135A Active CN101607138B (en) | 2008-06-17 | 2008-06-17 | Action recognition method based on finite automata model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101607138B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218062A (en) * | 2013-04-24 | 2013-07-24 | 伍斌 | Man-machine interaction method and equipment based on acceleration sensor and motion recognition |
| CN109189218A (en) * | 2018-08-20 | 2019-01-11 | 广州市三川田文化科技股份有限公司 | A kind of method, apparatus of gesture identification, equipment and computer readable storage medium |
| CN113476833A (en) * | 2021-06-10 | 2021-10-08 | 深圳市腾讯网域计算机网络有限公司 | Game action recognition method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1153576A (en) * | 1995-05-10 | 1997-07-02 | 任天堂株式会社 | Operating device with analog joystick |
| CN1474424A (en) * | 1994-05-09 | 2004-02-11 | �ֹ��� | Controller unit for electronic device |
| CN1770064A (en) * | 2005-07-15 | 2006-05-10 | 中国海洋大学 | Interactive input device for computer |
| CN1996208A (en) * | 2007-01-15 | 2007-07-11 | 解晖 | Man-machine command input device and mapping method for motion information in the same |
-
2008
- 2008-06-17 CN CN2008100435135A patent/CN101607138B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1474424A (en) * | 1994-05-09 | 2004-02-11 | �ֹ��� | Controller unit for electronic device |
| CN1153576A (en) * | 1995-05-10 | 1997-07-02 | 任天堂株式会社 | Operating device with analog joystick |
| CN1770064A (en) * | 2005-07-15 | 2006-05-10 | 中国海洋大学 | Interactive input device for computer |
| CN1996208A (en) * | 2007-01-15 | 2007-07-11 | 解晖 | Man-machine command input device and mapping method for motion information in the same |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218062A (en) * | 2013-04-24 | 2013-07-24 | 伍斌 | Man-machine interaction method and equipment based on acceleration sensor and motion recognition |
| CN109189218A (en) * | 2018-08-20 | 2019-01-11 | 广州市三川田文化科技股份有限公司 | A kind of method, apparatus of gesture identification, equipment and computer readable storage medium |
| CN109189218B (en) * | 2018-08-20 | 2019-05-10 | 广州市三川田文化科技股份有限公司 | A kind of method, apparatus of gesture identification, equipment and computer readable storage medium |
| CN113476833A (en) * | 2021-06-10 | 2021-10-08 | 深圳市腾讯网域计算机网络有限公司 | Game action recognition method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101607138B (en) | 2013-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107368820B (en) | Refined gesture recognition method, device and equipment | |
| CN102246471A (en) | Testing apparatus and test method | |
| CN112506759B (en) | Automatic test method and device for servo system control software and storage medium | |
| CN110266552A (en) | Method, model training method and the device of Traffic anomaly detection | |
| CN113283082A (en) | Centroid trajectory generation method and device, computer readable storage medium and robot | |
| CN104460646A (en) | Testing Device For Real-Time Testing Of A Virtual Control Unit | |
| CN101607138B (en) | Action recognition method based on finite automata model | |
| CN101017374A (en) | Polypropylene melting index softsensoring instrument based on blind signal analysis and method thereof | |
| WO2022105023A1 (en) | Robot control method and apparatus, and computer readable storage medium, and robot | |
| CN102306054B (en) | Attitude sensing equipment and positioning method and device thereof and method and device for controlling mouse pointer | |
| CN114211491A (en) | Collision detection method and device, computer readable storage medium and robot | |
| CN101762252A (en) | Virtual three-coordinate measuring instrument and use method thereof | |
| CN100480973C (en) | Method and apparatus for detecting position of movable device | |
| CN109029459B (en) | Moving target track tracking system and calculation method based on same | |
| Mohandes et al. | Automation of the Arabic sign language recognition | |
| CN113001546B (en) | Method and system for improving motion speed safety of industrial robot | |
| CN113343458B (en) | Engine sensor selection method and device, electronic equipment and storage medium | |
| CN109408029A (en) | The method of car networking lower sensor generation random number | |
| CN114356494A (en) | Data processing method and device of neural network simulator and terminal | |
| CN109795592A (en) | Riding posture recognition methods and application apparatus | |
| CN107730712A (en) | A kind of interference positioning method and device | |
| CN116434324A (en) | Three-dimensional writing identification method and system for number-English full characters | |
| CN203191755U (en) | Multifunctional control instrument | |
| CN117406759B (en) | Pipeline robot crawling calibration method and system | |
| CN117833750A (en) | Real-time optimization method and system for motor running track |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20190228 Address after: 201203 7, 1 Lane 666 lane, Zhang Heng Road, Pudong New Area, Shanghai. Patentee after: SHANGHAI ZHANGMEN TECHNOLOGY CO., LTD. Address before: 201203 No. 356 GuoShoujing Road, Pudong New Area, Shanghai Patentee before: Shengle Information Technology (Shanghai) Co., Ltd. |
|
| TR01 | Transfer of patent right |