CN104239119A - Method and system for realizing electric power training simulation upon kinect - Google Patents
Method and system for realizing electric power training simulation upon kinect Download PDFInfo
- Publication number
- CN104239119A CN104239119A CN201410428230.8A CN201410428230A CN104239119A CN 104239119 A CN104239119 A CN 104239119A CN 201410428230 A CN201410428230 A CN 201410428230A CN 104239119 A CN104239119 A CN 104239119A
- Authority
- CN
- China
- Prior art keywords
- kinect
- emulation
- electric power
- training
- action
- 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
Abstract
The invention discloses a method and a system for realizing electric power training simulation upon kinect. The method comprises the following steps: acquiring the movement pose information of a trainee upon the kinect; dynamically recognizing the movement type of the trainee by adopting a method of combining template matching and dynamic programming; describing the movement type and the context of the electric power training simulation which corresponds to the movement type by adopting a finite-state machine, and finishing the transfer of a simulation state by taking the movement type of the trainee as a transfer function; describing the finite-state machine upon XML (extensive markup language) to control the logical change of a simulation behavior, and showing through the 3D virtual technology. According to the embodiments of the invention, through a method for enhancing electric power training experience by utilizing the kinect, the electric power training trainee can operate a virtual member in simulation through body movements, so that the trainee feels immersive.
Description
Technical field
The present invention relates to Simulating technique in Electric Power System field, be specifically related to a kind of method and system realizing training on electric power emulation based on kinect.
Background technology
The experience sense strengthening user is a direction of training on electric power emulation technology development always, start-up can be made now to roam in the three-dimensional scenics such as transformer station, but need constantly to move or click the mouse when training, or operation keyboard is to control effectively to computer, or need certain handheld device, these all reduce the experience sense of trainer.Along with the appearance of Kinect, the depth information of body sense technical limit spacing start-up can be utilized, by the identification to limbs joint, understand the action intention of start-up, thus electric analog system is effectively operated.
Kinect is a attitude sensing input equipment developed by Microsoft, and it is formed primarily of a main camera, a pair depth transducer, one group of microphone and a motor.Kinect possesses the several functions such as instant motion capture, image identification, microphone input, speech recognition, community interactive.In order to excavate the larger potentiality of Kinect, the PC that Microsoft has issued Kinect drives and programming SDK, thus has attracted more developer to carry out the game based on Kinect and application and development.Therefore the application of many novelties is arisen at the historic moment, as virtual mirror, robot manipulation, virtual guitar etc.Quite a few application is wherein had to combine virtual reality technology or augmented reality.These application have related to the various fields such as military affairs, medical treatment, amusement, education and training, but are not also employed in training on electric power emulation field, and its reason is that training on electric power relates to much equipment and the working specification of electric system.Given this, Kinect is applied in training on electric power emulation and also can runs into similar problem, so need the advantage in conjunction with playing Kinect technology in training on electric power to the emulation of working specification as far as possible.
Summary of the invention
Based on the deficiency of existing training on electric power analogue system, by with the use of some traditional algorithms (with the use of the method based on template as template matching method, dynamic programming; And with the use of the method based on grammer, as limited state machine technique etc.), make start-up have good experience sense.
The invention provides a kind of method realizing training on electric power emulation based on kinect, comprise the steps:
The movement posture information of start-up is obtained based on kinect;
The method adopting template matches and dynamic programming to combine carrys out the action classification that Dynamic Recognition goes out start-up;
Adopt finite state machine to be described by the context of the training on electric power emulation corresponding to action classification and action classification, complete the transfer of simulation status using the action classification of start-up as transfer function;
Describe the logic change of finite states machine control emulation behavior based on XML, and displayed by three dimensional virtual technique.
The described movement posture information based on kinect acquisition start-up comprises:
To the pre-service of the limbs nodal information that kinect obtains, segmentation, the extraction of boundary profile and the identification of limbs node, from continuous multiple frames, obtain position sequence information and the direction of motion vector of action.
The method adopting template matches and dynamic programming to combine is carried out the action classification that Dynamic Recognition goes out start-up and is comprised:
The pattern matching algorithm of dynamic time warping is adopted to carry out the identification of finger movement;
Obtain direction of motion from twice finger position, and direction of motion is normalized.
The context of the training on electric power emulation corresponding to action classification and action classification is described by described employing finite state machine, and the transfer step completing simulation status using the action classification of start-up as transfer function is specially:
Definition according to determining finite state machine: A
d=(S, ∑, δ, K, F), wherein:
S: the nonvoid set of state, refers to the state of start-up herein, and the execution of the emulation behavior of correspondence;
∑: corresponding character set, refers to emulation training human behavior herein, represent by three dimensional virtual technique;
The single-value mapping of δ: state transition function, S × ∑ → S;
δ (S
i, a)=S
j, S
i, S
j∈ S, refers to a behavior outcome of emulation training personnel herein, represents by three dimensional virtual technique; A ∈ ∑, refers to a certain behavior of emulation training personnel;
K: original state;
;
F: final state;
;
Transfer function δ includes the action of two legs and two-arm.
Accordingly, the embodiment of the present invention additionally provides a kind of system realizing training on electric power emulation based on kinect, comprising:
Movement posture information acquisition module, for obtaining the movement posture information of start-up based on kinect;
Action classification identification module, the method for adopting template matches and dynamic programming to combine carrys out the action classification that Dynamic Recognition goes out start-up;
Emulation shift module, for adopting finite state machine to be described by the context of the training on electric power emulation corresponding to action classification and action classification, completes the transfer of simulation status using the action classification of start-up as transfer function;
Emulation display module, for adopting XML language to describe the logic change of finite states machine control emulation behavior, and is displayed by three dimensional virtual technique.
Described movement posture identification module, for the pre-service to the limbs nodal information that kinect obtains, segmentation, the extraction of boundary profile and the identification of limbs node, obtains position sequence information and the direction of motion vector of action from continuous multiple frames.
The identification of described action classification identification module for adopting the pattern matching algorithm of dynamic time warping to carry out finger movement; And obtain direction of motion from twice finger position, and direction of motion is normalized.
In the feature that the embodiment of the present invention emulates in conjunction with training on electric power, typical template matches and dynamic programming algorithm is utilized to identify the action that kinect obtains, adopt finite state machine technology to control emulation behavior simultaneously, and by XML language, state machine is described in simulation scenario, not only increase the experience sense of training on electric power like this, also enhance the dirigibility of this Simulation Application.Utilize kinect to strengthen the method for training on electric power experience sense, the virtual member that training on electric power personnel come by limb action in operational simulation can be made, make start-up have sensation on the spot in person.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the method flow diagram realizing training on electric power emulation based on kinect in the embodiment of the present invention;
Fig. 2 is the method constitutional diagram strengthening training on electric power experience sense based on kinect in the embodiment of the present invention;
Fig. 3 is the system architecture schematic diagram realizing training on electric power emulation based on kinect in the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making other embodiments all obtained under creative work prerequisite, belong to the scope of protection of the invention.
In order to make full use of the body sense technology of Kinect in training on electric power emulation, need multiple intelligent identification technology to be combined.The present invention utilizes template matches and dynamic programming techniques to identify the action message that Kinect obtains, and according to the description of finite state machine in prediction scheme, the state of identified action control state machine is shifted, and completes the control to emulation behavior.
For achieving the above object, need the limbs nodal information obtained Kinect to carry out static segmentation and identification, then in conjunction with action continuity in time, utilize template matching method and be intended to the action identifying start-up in conjunction with dynamic programming techniques.These actions are applied in training, also need before emulation starts, in simulation scenario, utilize the everything intention of finite state machine to start-up to be described, when being controlled the action experience of start-up after simulation run by state machine.
Fig. 1 shows the method flow diagram realizing training on electric power emulation based on kinect in the embodiment of the present invention, comprises the steps:
S101, obtain the movement posture information of start-up based on kinect;
First static analysis is done to the limbs nodal information that kinect obtains, comprise pre-service, segmentation, the border wheel extraction of Guo and the identification of limbs node; Again according to the time course of action, from the continuous multiple frames that kinect obtains, obtain the position sequence information of action, thus sequence construct direction of motion vector.The method utilizing template matches and dynamic programming to combine finally by this direction of motion vector carrys out the action classification that Dynamic Recognition goes out start-up.
Fig. 2 shows the method constitutional diagram strengthening training on electric power experience sense based on kinect, according to the 3D position of the real-time bone node that Kinect forwindows sdk provides, the a certain moment can obtain the position of node, thus knows the angle between node and relative position.When catching in real time continuously, the motion vector of node can be obtained.The action instruction of start-up is identified again by the motion vector of articulation point.These identifyings comprise and identifying two legs, two-arm and two hands, but according to the needs of Simulated training, the identification of leg and arm only need be judged to lift leg, receives leg, carry arm, fall arm, left swing arm and right swing arm; The identification of palm is then comprised and changes hands, clench fist, stretch out the bending of the five fingers and each finger and stretch.
All be divided into following static state to the identification of above-mentioned limb action to identify and Dynamic Recognition two steps.For gesture identification, static identification key step comprises pre-service, Hand Gesture Segmentation, gestures detection, feature extraction; Dynamic process comprises seasonal effect in time series optimization and template matches etc.Pre-service based on Kinect dynamic hand gesture recognition refers to before dynamic gesture training with gesture identification, pre-service is carried out to the depth information flow data obtained from Kinect and bone nodal information flow data, split from whole data field needing the hand identified, to reduce follow-up calculated amount.After Hand Gesture Segmentation completes, then Border-Following algorithm is adopted to carry out contour detecting process to the picture split.
Border-Following algorithm concrete steps are first setpoint color threshold values, and when being less than this threshold value, this pixel is set to white.When being greater than this threshold value, this pixel is configured to predefined certain color (as redness).Then respectively each pixel in scanned picture successively from different directions, when two, the left and right adjoined with it pixel is different value, then this pixel is frontier point, thus finds out the profile of image.
Use K-curvature algorithm to distinguish finger tip again, by the point on image outline successively stored in array, utilize K-curvature algorithm to calculate the approximate curvature of any point.Namely to J point point (J) on any profile, whether within the specific limits vector between calculating point (J) and point (J-K) and angle vectorial between point (J) and point (J+K), thus judge whether it is finger tip.K gets 20 herein, judges that the scope of angle is between 0 to 55 degree.If selected angle is excessive, hand may be caused to be erroneously identified as finger tip near that section of arm; And if selected angle is too small, then make cannot be distinguished out when pointing shorter.
The frame per second of the depth information stream provided due to Kinect is 30FPS, even if so for the gesture of 2 seconds kind, the frame of catching in real time, close to 60 frames, constitutes a time series.To same gesture, different people or different time complete, and this seasonal effect in time series length is all not quite similar, and continue frame number simultaneously in a certain direction and are also not quite similar.This just cause training and identify difficulty increase, be thus necessary to be optimized this length of time series, remove unnecessary information, retain mark this gesture characteristic proper vector, namely to after filtering process after vector carry out sampling processing.
S102, the method adopting template matches and dynamic programming to combine carry out the action classification that Dynamic Recognition goes out start-up;
The process of dynamic hand gesture recognition is extract some feature to mate the action of gesture, and chosen position of the present invention and direction of motion vector are as characteristic quantity.Position feature be in gesture each point to the distance of starting point, direction vector is each point and the previous direction of motion vector (being generally normalized) formed, because position and speed are all scalar, the order of hands movement track correctly can not be described.And position is as in feature situation, same gesture, when actuating range varies in size, value is different, so be not very desirable selection.And speed is for same track, the speed that the time that different people is different waves is different, well can not mark gesture.Adopt direction of motion vector as eigenwert so final.
Template matching algorithm wherein the most simply realizes, and namely sets up a template, allows the characteristic of each action and template carry out classification, differentiate gesture by both similarities, and it is short that the time due to same gesture has length to have, and causes discrimination lower.Need to adopt dynamic time warping (DTW) algorithm for this reason, it is a kind of pattern matching algorithm with non-linear normalizing effect, elongate or shorten until consistent with the length of mode standard to characteristic signal, to make to mate better with template by adopting.Because application background of the present invention is the experience sense strengthening start-up, simply can fix the action of operation, therefore adopt DTW algorithm to carry out the identification of finger movement.
Obtain direction of motion from twice finger position, and be normalized direction of motion, the Y-coordinate that finger Y-coordinate is below less than previous finger represents upwards, and value is 1; The Y-coordinate that finger Y-coordinate is below greater than previous finger represents downward, and value is-1; Within the specific limits, then direction value is 0 to the Y-coordinate of twice finger position.Such one finger motion sequence be (0 ..., 1,1,1 ..., 1,0) or (0 ... ,-1 ,-1 ,-1 ... ,-1,0), then the former finger is upwards, and the latter represents that finger is downwards.If five fingers downwards simultaneously, then represent and clench fist; Upwards then represent simultaneously and stretch the palm.The motion sequence of arm be (0 ..., 1,1,1 ..., 1,0) and represent carry arm; For (0 ... ,-1 ,-1 ,-1 ... ,-1,0) represent and fall arm.The motion sequence of leg be (0 ..., 1,1,1 ..., 1,0) represent and lift leg; For (0 ... ,-1 ,-1 ,-1 ... ,-1,0) and represent that leg is upright.
The difference of the X-axis coordinate of same front and back two positions judges direction of motion, and for right arm, the X-coordinate that arm X-coordinate is below less than previous arm represents inwardly waves, and value is 1; The Y-coordinate that arm Y-coordinate is below greater than previous arm represents outwards waves, and value is-1; Within the specific limits, then direction value is 0 to the X-coordinate of twice arm position.The motion sequence of such right arm be (0 ..., 1,1, ..., 1,0) or (0 ... ,-1 ,-1 ,-1 ... ,-1,0), then the former right arm is inwardly waved, and the latter represents that right arm is outwards waved.Represent spinning movement with the wheel Guo area before and after the left hand palm, it is 1 that area diminishes, and area becomes greatly-1, and difference in areas is 0 within the specific limits, then motion sequence be (0 ..., 1,1,1 ..., 1,0) represent rotate, motion sequence be (0 ...-1 ,-1 ,-1, ,-1,0) temporarily without definition.
The context of the training on electric power emulation corresponding to action classification and action classification is described by S103, employing finite state machine, completes the transfer of simulation status using the action classification of start-up as transfer function;
This module combines the action intention that start-up understood in the context emulated, and advances the process of emulation according to this intention.Finite state machine is the powerful describing context grammer, and this module carrys out the transfer of completion status using the action of start-up as transfer function.
Definition according to determining finite state machine: A
d=(S, ∑, δ, K, F), wherein:
S: the nonvoid set of state, refers to the state of start-up herein, and the execution of the emulation behavior of correspondence;
∑: corresponding character set, refers to emulation training human behavior herein, represent by three dimensional virtual technique;
The single-value mapping of δ: state transition function, S × ∑ → S;
δ (S
i, a)=S
j, S
i, S
j∈ S, refers to a behavior outcome of emulation training personnel herein, represents by three dimensional virtual technique; A ∈ ∑, refers to a certain behavior of emulation training personnel;
K: original state;
;
F: final state;
;
Transfer function δ includes the action of two legs and two-arm, is specially and lifts leg, vertical leg, carry arm, falls arm, left swing arm and right swing arm; And two actions of hand, be specially and change hands, clench fist, stretch out the bending of the five fingers and each finger and stretch.
Character set ∑ is that the behavior of transfer function δ represents, and includes to move ahead, uprightly, squat down, turn round, bend over, carry arm, fall arm, change hands, clench fist, stretch out the bending of the five fingers and each finger and stretch.Transfer function δ is used to state of a control change, as controlled representing of start-up's behavior representated by ∑ with the left-hand rotation of arm or turn right, can represent that start-up turns left, or represent that start-up turns right with right-hand rotation arm with left-hand rotation arm.
For the overhaul of the equipments process in Fig. 2, start-up needs first to go to equipment place, includes to move ahead, turn, uprightly, squat down and the several state of operation.This limb action of " lifting leg " makes to move ahead and erectility all forwards forward traveling to; " arm translation " this limb action makes forward traveling forward turn condition to; " vertical leg " this limb action makes to move ahead or turn condition transfers to erectility; " arm moves down " this limb action makes erectility forward the state of squatting down to, and " arm moves " this limb action makes the state of squatting down forward erectility to; " changing hands, clench fist, stretch out the bending of the five fingers and each finger and stretch " these palm actions makes start-up enter job state, and till end.
S104, to describe the logic change of finite states machine control emulation behavior based on XML, and displayed by three dimensional virtual technique.
The operation of start-up is used as an artificial tasks in simulation scenario to describe, some action behaviors of start-up are related to when completing this operation, logical constitution between these a behaviors finite state machine, therefore this module describes the logic between this behavior by XML language in prediction scheme.
In emulation case, pre-XML describes the logic change of finite states machine control emulation behavior, is first described each job task:
< task > task name </ task >
The state set that this task agent contains is described as:
Wherein state name comprises: move ahead, uprightly, squat down, turn round, bend over, carry arm, fall arm, change hands, clench fist, stretch out the bending of the five fingers and each finger and stretch.Action name comprises: lift leg, vertical leg, carry arm, fall arm, left swing arm and right swing arm; And two the changing hands of hand, clench fist, stretch out the bending of the five fingers and each finger and stretch.
In simulation scenario, describe the job task representated by finite state machine with XML, the operation behaviour of start-up in emulation can be edited.
Accordingly, Fig. 3 also show the system architecture schematic diagram realizing training on electric power emulation based on kinect in the embodiment of the present invention, and this system comprises:
Movement posture information acquisition module, for obtaining the movement posture information of start-up based on kinect;
Action classification identification module, the method for adopting template matches and dynamic programming to combine carrys out the action classification that Dynamic Recognition goes out start-up;
Emulation shift module, for adopting finite state machine to be described by the context of the training on electric power emulation corresponding to action classification and action classification, completes the transfer of simulation status using the action classification of start-up as transfer function;
Emulation display module, for adopting XML language to describe the logic change of finite states machine control emulation behavior, and is displayed by three dimensional virtual technique.
It should be noted that, this movement posture identification module, for the pre-service to the limbs nodal information that kinect obtains, segmentation, the extraction of boundary profile and the identification of limbs node, obtains position sequence information and the direction of motion vector of action from continuous multiple frames.
It should be noted that, the identification of this action classification identification module for adopting the pattern matching algorithm of dynamic time warping to carry out finger movement; And obtain direction of motion from twice finger position, and direction of motion is normalized.Movement posture identification module first does static analysis to the limbs nodal information that kinect obtains, and comprises pre-service, segmentation, the extraction of boundary profile and the identification of limbs node; Again according to the time course of action, from the continuous multiple frames that kinect obtains, calculate the position sequence information of action, sequence construct goes out direction of motion vector thus, and its vector element is 0,1 and-1, represents motionless respectively, moves up or down; Because the number and the position of 0 element in vector and template that comprise 0 in this direction of motion vector are not quite similar, therefore have employed method that template matches and dynamic programming combine further to ignore the impact of above-mentioned 0 element, thus dynamically identify the action classification of start-up.Emulation shift module combines the action intention that start-up understood in the context emulated, and advances the operation of emulation according to this intention; It utilizes finite state machine to describe context grammer, carrys out the transfer of completion status using the action of start-up as transfer function.The information that action classification identification module utilizes kinect to obtain makes limbs node recognition, and from continuous print multiframe, obtain position sequence information and the direction of motion vector of action, because each responsiveness is all not quite similar, the number and the position of 0 element in vector and the template that comprise 0 in direction of motion vector are not quite similar, and the method that vector adopts template matches and dynamic programming to combine accordingly carrys out the action classification that Dynamic Recognition goes out start-up.In simulation scenario, describe the job task representated by finite state machine with XML in emulation display module, the operation behaviour of start-up in emulation can be edited.By obtaining the status information of start-up based on kinect, and in addition action recognition, thus realize emulation by finite state machine and transform, and be input in three-dimensional based on XML and shown, thus increase the body sensitivity of start-up.
To sum up, in the feature that the embodiment of the present invention emulates in conjunction with training on electric power, typical template matches and dynamic programming algorithm is utilized to identify the action that kinect obtains, adopt finite state machine technology to control emulation behavior simultaneously, and by XML language, state machine is described in simulation scenario, not only increase the experience sense of training on electric power like this, also enhance the dirigibility of this Simulation Application.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is that the hardware that can carry out instruction relevant by program has come, this program can be stored in a computer-readable recording medium, storage medium can comprise: ROM (read-only memory) (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), disk or CD etc.
Above to the embodiment of the present invention provide based on kinect realize training on electric power emulation method and system be described in detail, apply specific case herein to set forth principle of the present invention and embodiment, the explanation of above embodiment just understands method of the present invention and core concept thereof for helping; Meanwhile, for one of ordinary skill in the art, according to thought of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.
Claims (7)
1. realize a method for training on electric power emulation based on kinect, it is characterized in that, comprise the steps:
The movement posture information of start-up is obtained based on kinect;
The method adopting template matches and dynamic programming to combine carrys out the action classification that Dynamic Recognition goes out start-up;
Adopt finite state machine to be described by the context of the training on electric power emulation corresponding to action classification and action classification, complete the transfer of simulation status using the action classification of start-up as transfer function;
Describe the logic change of finite states machine control emulation behavior based on XML, and displayed by three dimensional virtual technique.
2. realize the method for training on electric power emulation as claimed in claim 1 based on kinect, it is characterized in that, the described movement posture information based on kinect acquisition start-up comprises:
To the pre-service of the limbs nodal information that kinect obtains, segmentation, the extraction of boundary profile and the identification of limbs node, from continuous multiple frames, obtain position sequence information and the direction of motion vector of action.
3. realize as claimed in claim 2 the method for training on electric power emulation based on kinect, it is characterized in that, the method adopting template matches and dynamic programming to combine is carried out the action classification that Dynamic Recognition goes out start-up and is comprised:
The pattern matching algorithm of dynamic time warping is adopted to carry out the identification of finger movement;
Obtain direction of motion from twice finger position, and direction of motion is normalized.
4. the method for training on electric power emulation is realized as claimed in claim 3 based on kinect, it is characterized in that, the context of the training on electric power emulation corresponding to action classification and action classification is described by described employing finite state machine, and the transfer step completing simulation status using the action classification of start-up as transfer function is specially:
Definition according to determining finite state machine: A
d=(S, ∑, δ, K, F), wherein:
S: the nonvoid set of state, refers to the state of start-up herein, and the execution of the emulation behavior of correspondence;
∑: corresponding character set, refers to emulation training human behavior herein, represent by three dimensional virtual technique;
The single-value mapping of δ: state transition function, S × ∑ → S;
δ (S
i, a)=S
j, S
i, S
j∈ S, refers to a behavior outcome of emulation training personnel herein, represents by three dimensional virtual technique; A ∈ ∑, refers to a certain behavior of emulation training personnel;
K: original state;
;
F: final state;
;
Transfer function δ includes the action of two legs and two-arm.
5. realize a system for training on electric power emulation based on kinect, it is characterized in that, comprising:
Movement posture information acquisition module, for obtaining the movement posture information of start-up based on kinect;
Action classification identification module, the method for adopting template matches and dynamic programming to combine carrys out the action classification that Dynamic Recognition goes out start-up;
Emulation shift module, for adopting finite state machine to be described by the context of the training on electric power emulation corresponding to action classification and action classification, completes the transfer of simulation status using the action classification of start-up as transfer function;
Emulation display module, for adopting XML language to describe the logic change of finite states machine control emulation behavior, and is displayed by three dimensional virtual technique.
6. the system of training on electric power emulation is realized as claimed in claim 5 based on kinect, it is characterized in that, described movement posture identification module, for the pre-service to the limbs nodal information that kinect obtains, segmentation, the extraction of boundary profile and the identification of limbs node, obtains position sequence information and the direction of motion vector of action from continuous multiple frames.
7. realize the system of training on electric power emulation as claimed in claim 6 based on kinect, it is characterized in that, described action classification identification module adopts the pattern matching algorithm of dynamic time warping to carry out the identification of finger movement; And obtain direction of motion from twice finger position, and direction of motion is normalized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410428230.8A CN104239119B (en) | 2014-08-27 | 2014-08-27 | A kind of method and system that training on electric power emulation is realized based on kinect |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410428230.8A CN104239119B (en) | 2014-08-27 | 2014-08-27 | A kind of method and system that training on electric power emulation is realized based on kinect |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104239119A true CN104239119A (en) | 2014-12-24 |
| CN104239119B CN104239119B (en) | 2017-11-21 |
Family
ID=52227254
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410428230.8A Active CN104239119B (en) | 2014-08-27 | 2014-08-27 | A kind of method and system that training on electric power emulation is realized based on kinect |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104239119B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104575150A (en) * | 2015-01-15 | 2015-04-29 | 广东电网有限责任公司教育培训评价中心 | Multi-user online cooperating method, device and system for power simulation training |
| CN104915011A (en) * | 2015-06-28 | 2015-09-16 | 合肥金诺数码科技股份有限公司 | Open environment gesture interaction game system |
| CN106607910A (en) * | 2015-10-22 | 2017-05-03 | 中国科学院深圳先进技术研究院 | Robot real-time simulation method |
| CN110221686A (en) * | 2019-04-29 | 2019-09-10 | 浙江大学 | A kind of gesture interaction system and method based on color image towards mine resources management |
| CN111028637A (en) * | 2019-12-27 | 2020-04-17 | 广东电网有限责任公司培训与评价中心 | Live-line work training method and system based on electric field visualization |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1924899A (en) * | 2006-09-26 | 2007-03-07 | 福建榕基软件开发有限公司 | Precise location method of QR code image symbol region at complex background |
| CN102163382A (en) * | 2011-04-29 | 2011-08-24 | 国网电力科学研究院武汉南瑞有限责任公司 | Live working helmet type simulation training system and method |
| CN103529944A (en) * | 2013-10-17 | 2014-01-22 | 合肥金诺数码科技股份有限公司 | Human body movement identification method based on Kinect |
-
2014
- 2014-08-27 CN CN201410428230.8A patent/CN104239119B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1924899A (en) * | 2006-09-26 | 2007-03-07 | 福建榕基软件开发有限公司 | Precise location method of QR code image symbol region at complex background |
| CN102163382A (en) * | 2011-04-29 | 2011-08-24 | 国网电力科学研究院武汉南瑞有限责任公司 | Live working helmet type simulation training system and method |
| CN103529944A (en) * | 2013-10-17 | 2014-01-22 | 合肥金诺数码科技股份有限公司 | Human body movement identification method based on Kinect |
Non-Patent Citations (1)
| Title |
|---|
| 鲁明等: "一种基于Kinect的虚拟现实姿态交互工具", 《系统仿真学报》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104575150A (en) * | 2015-01-15 | 2015-04-29 | 广东电网有限责任公司教育培训评价中心 | Multi-user online cooperating method, device and system for power simulation training |
| CN104575150B (en) * | 2015-01-15 | 2016-11-09 | 广东电网有限责任公司教育培训评价中心 | The method and apparatus of many people online cooperation and system for electric analog training |
| CN104915011A (en) * | 2015-06-28 | 2015-09-16 | 合肥金诺数码科技股份有限公司 | Open environment gesture interaction game system |
| CN106607910A (en) * | 2015-10-22 | 2017-05-03 | 中国科学院深圳先进技术研究院 | Robot real-time simulation method |
| CN106607910B (en) * | 2015-10-22 | 2019-03-22 | 中国科学院深圳先进技术研究院 | A kind of robot imitates method in real time |
| CN110221686A (en) * | 2019-04-29 | 2019-09-10 | 浙江大学 | A kind of gesture interaction system and method based on color image towards mine resources management |
| CN110221686B (en) * | 2019-04-29 | 2020-08-04 | 浙江大学 | Mine resource management-oriented gesture interaction system and method based on color images |
| CN111028637A (en) * | 2019-12-27 | 2020-04-17 | 广东电网有限责任公司培训与评价中心 | Live-line work training method and system based on electric field visualization |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104239119B (en) | 2017-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105868715B (en) | Gesture recognition method and device and gesture learning system | |
| Rautaray | Real time hand gesture recognition system for dynamic applications | |
| Wang et al. | Real-time hand-tracking with a color glove | |
| CN102222431B (en) | Computer implemented method for performing sign language translation | |
| US20130335318A1 (en) | Method and apparatus for doing hand and face gesture recognition using 3d sensors and hardware non-linear classifiers | |
| CN104239119A (en) | Method and system for realizing electric power training simulation upon kinect | |
| Badi et al. | Hand posture and gesture recognition technology | |
| CN116909407B (en) | Touch display screen panoramic interaction method and control system based on virtual reality | |
| Jais et al. | A review on gesture recognition using Kinect | |
| Salaris et al. | Robot choreography: The use of the kinetography Laban system to notate robot action and motion | |
| Singla et al. | Visual rendering of shapes on 2D display devices guided by hand gestures | |
| Boruah et al. | Development of a learning-aid tool using hand gesture based human computer interaction system | |
| Chu et al. | A Kinect-based handwritten digit recognition for TV remote controller | |
| Rehman et al. | Two hand gesture based 3d navigation in virtual environments | |
| Tran et al. | Easy-to-use virtual brick manipulation techniques using hand gestures | |
| Woo et al. | Sketch on dynamic gesture tracking and analysis exploiting vision-based 3D interface | |
| Ren et al. | Immersive and perceptual human-computer interaction using computer vision techniques | |
| KR101525011B1 (en) | tangible virtual reality display control device based on NUI, and method thereof | |
| Spanogianopoulos et al. | Human computer interaction using gestures for mobile devices and serious games: A review | |
| Bernardes Jr et al. | Design and implementation of a flexible hand gesture command interface for games based on computer vision | |
| Wang et al. | A Generative Human-Robot Motion Retargeting Approach Using a Single RGBD Sensor. | |
| Dhamanskar et al. | Human computer interaction using hand gestures and voice | |
| Jeong et al. | Hand gesture user interface for transforming objects in 3d virtual space | |
| Shin et al. | Deep Learning-based Hand Pose Estimation from 2D Image | |
| Sorel et al. | Dealing with variability when recognizing user's performance in natural 3D gesture interfaces |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C53 | Correction of patent of invention or patent application | ||
| CB02 | Change of applicant information |
Address after: 510000, No. two, 333, Guang Shan Road, Tianhe District, Guangdong, Guangzhou Applicant after: EDUCATION AND TRAINING ASSESSMENT CENTER, GUANGDONG POWER GRID CORP. Address before: 510000, No. two, 333, Guang Shan Road, Tianhe District, Guangdong, Guangzhou Applicant before: GPGC Training and Evaluation Center |
|
| COR | Change of bibliographic data |
Free format text: CORRECT: APPLICANT; FROM: GUANGDONG POWER GRID CORPORATION TRAINING AND EVALUATION CENTER TO: GUANGDONG POWER GRID LLC TRAINING AND EVALUATION CENTER |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |