CN108491066A - A kind of gesture interaction method and device - Google Patents

A kind of gesture interaction method and device Download PDF

Info

Publication number
CN108491066A
CN108491066A CN201810090288.4A CN201810090288A CN108491066A CN 108491066 A CN108491066 A CN 108491066A CN 201810090288 A CN201810090288 A CN 201810090288A CN 108491066 A CN108491066 A CN 108491066A
Authority
CN
China
Prior art keywords
finger
center point
interaction center
coordinate value
depth image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201810090288.4A
Other languages
Chinese (zh)
Inventor
胡明辉
马明飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Goertek Techology Co Ltd
Original Assignee
Goertek Techology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Goertek Techology Co Ltd filed Critical Goertek Techology Co Ltd
Priority to CN201810090288.4A priority Critical patent/CN108491066A/en
Publication of CN108491066A publication Critical patent/CN108491066A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input 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
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/017Gesture based interaction, e.g. based on a set of recognized hand gestures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input 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
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0487Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
    • G06F3/0488Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
    • G06F3/04883Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures for inputting data by handwriting, e.g. gesture or text
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/107Static hand or arm
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/107Static hand or arm
    • G06V40/117Biometrics derived from hands

Abstract

The invention discloses a kind of gesture interaction method and device, this method includes:Obtain the depth image of finger interactive action of the user on the projection interactive flat of smart projector;Depth image is handled to obtain the coordinate value of corresponding finger interaction center point, and judges whether finger interaction meets deliberate action condition according to the coordinate value of finger interaction center point, when meeting, row interpolation compensation is clicked through to finger interaction center;Report the coordinate value and interpolation of finger interaction center point so that according to the coordinate value and interpolation of finger interaction center point, finger sliding and the correspondence of predetermined registration operation in smart projector execute predetermined registration operation.The technical solution makes original discontinuous sliding interactive process become smooth, improves user-interaction experience, has expanded the application field of smart projector.

Description

A kind of gesture interaction method and device
Technical field
The present invention relates to smart projector technical fields, and in particular to a kind of gesture interaction method and device.
Background technology
Projecting apparatus is more common electronic equipment, currently, the development of projecting apparatus is more and more intelligent, have it is intelligent, The feature that can be interacted.But existing user gesture interaction, especially sliding interactive process is not smooth, and user-interaction experience is poor.
Invention content
The present invention provides a kind of gesture interaction method and devices, to solve or at least partly solve smart projector gesture Interactive process is not smooth, the poor problem of user experience.
To reach above-mentioned technical purpose, the technical proposal of the invention is realized in this way:
According to an aspect of the invention, there is provided a kind of gesture interaction method, this method include:
Obtain the depth image of finger interactive action of the user on the projection interactive flat of smart projector;
Depth image is handled to obtain the coordinate value of corresponding finger interaction center point, and according to the hand of depth image The coordinate value for referring to interaction center point judges whether finger interaction meets deliberate action condition, when meeting, to finger interaction center Click through row interpolation compensation;
Report the coordinate value and interpolation of finger interaction center point so that according to the coordinate value and interpolation of finger interaction center point It determines that finger interactive action slides for finger, and is executed according to finger sliding and the correspondence of predetermined registration operation in smart projector Predetermined registration operation.
According to another aspect of the present invention, a kind of gesture interaction device is provided, which includes:
Image acquisition unit, for obtaining finger interactive action of the user on the projection interactive flat of smart projector Depth image;
Image processing unit obtains the coordinate value of corresponding finger interaction center point for being handled depth image, And judge whether finger interaction meets deliberate action condition according to the coordinate value of the finger interaction center point of depth image, work as satisfaction When, row interpolation compensation is clicked through to finger interaction center;
Unit, coordinate value and interpolation for reporting finger interaction center point so that in being interacted according to finger are realized in interaction The coordinate value and interpolation of heart point determine that finger interactive action slides for finger, and are preset in smart projector according to finger sliding The correspondence of operation executes predetermined registration operation.
According to a further aspect of the invention, a kind of electronic equipment is provided, which includes:Memory and processing Device is communicated by internal bus between memory and processor and is connected, and memory is stored with the program that can be executed by processor Instruction, can realize the gesture interaction method of one aspect of the present invention when program instruction is executed by processor.
The beneficial effects of the invention are as follows:The gesture interaction method and device of implementation column of the present invention, by obtaining user in intelligence The depth image of finger interactive action on the projection interactive flat of energy projecting apparatus, is handled to obtain corresponding to depth image The coordinate value of finger interaction center point judges whether finger interaction is full according to the coordinate value of the finger interaction center point of depth image Sufficient deliberate action condition reports interpolation, in reporting finger to interact when meeting after clicking through row interpolation compensation to finger interaction center The coordinate value and interpolation of heart point so that the correspondence according to finger sliding and predetermined registration operation in smart projector executes default behaviour Make.Thus the embodiment of the present invention is directed to smart projector after identification finger sliding interaction, in being interacted to finger using interpolation method The heart clicks through row interpolation and compensates and report prediction coordinate points, so that original discontinuous sliding interactive process is become smooth, improves use The gesture interaction at family is experienced, and the application field and range of smart projector have been expanded.
Description of the drawings
Fig. 1 is the depth map signal of the user's finger interactive action obtained;
Fig. 2 is the depth map signal of the user's finger interactive action obtained;
Fig. 3 is a kind of flow chart of gesture interaction method of one embodiment of the invention;
Fig. 4 is a kind of sequence diagram of gesture interaction method of one embodiment of the invention;
Fig. 5 is the interpolation flow chart of one embodiment of the invention;
Fig. 6 is the depth map signal after the interpolation of one embodiment of the invention;
Fig. 7 is the principle schematic of the pre-determined distance threshold calculations of one embodiment of the invention;
Fig. 8 is the schematic diagram of the finger interaction center point of the click gesture interaction of one embodiment of the invention;
Fig. 9 is a kind of block diagram of gesture interaction device of one embodiment of the invention;
Figure 10 is the structure chart of the electronic equipment of one embodiment of the invention.
Specific implementation mode
Important structure there are two in smart projector, when upright projection module, second is that depth of field module.Upright projection mould Group can be connected with background operating system, can be on real desktop by upright projection module such as the Android system of mobile phone The content for delivering out mobile phone desktop, in there is provided the visible interactive windows of user.Depth of field module is by way of infrared scan (or other feasible distance measuring methods), obtain the distance of subpoint on the depth of field module to real desktop, with flat desktop phase Than if wherein adding hand body, the depth value that depth of field module is scanned to object will become smaller.In this way by being added before hand body The difference of data and data after addition hand body, can obtain the essential information of body in one's hands, including finger centre dot position information.
In order to effectively capture the information of user gesture interaction, the perspective plane of depth of field module needs to cover vertical throw The perspective plane of shadow module, that is, the area on the perspective plane of depth of field module is more than the perspective plane of upright projection module.For ease of understanding, Here the operation principle of depth of field module is illustrated, depth of field module is by emitting continuous near-infrared arteries and veins to target scene Then punching receives the light pulse being reflected back by object with sensor, the light by comparing light pulse is emitted and by object reflection The phase difference of pulse, the distance that can be calculated to obtain the transmission delay between light pulse and then obtain object relative to video camera, Finally obtain a width depth image.By the cooperation of above-mentioned two module, user can obtain as on smart mobile phone touch screen Carry out the similar impression of gesture interaction.
The inventor of the present application discovered that:Smart projector is when carrying out finger sliding interaction, due to the frame speed of depth of field module Rate is relatively low, generally 30FPS (frame number each second), i.e. 30 images of acquisition per second, and frame number each second is the more, and shown is dynamic Making will be more smooth, and 30FPS means that in gesture identification, the gesture interaction of certain speed can not be detected, and such as schemes 1, shown in Fig. 2,11 be palm, and 12 be finger interaction center point.The gesture that original user does is that a sliding from left to right is dynamic Make, but since depth of field module acquisition image data frame per second is relatively low, coherent movement originally becomes discontinuously.The interaction of user Experience is a card for originally smooth sliding, and poor user experience also limits the development of smart projector.
For this purpose, providing a kind of gesture interaction method in an implementation column of the invention, it is applied to smart projector, Fig. 3 is A kind of flow chart of gesture interaction method of one embodiment of the invention, referring to Fig. 3, this method includes the following steps:
Step S101 obtains the depth map of finger interactive action of the user on the projection interactive flat of smart projector Picture;
Step S102 handles the depth image to obtain the coordinate value of corresponding finger interaction center point, and root Judge whether finger interaction meets deliberate action condition according to the coordinate value of the finger interaction center point of depth image, when meeting, Row interpolation compensation is clicked through to the finger interaction center;
Step S103 reports the coordinate value and interpolation of the finger interaction center point so that in being interacted according to the finger The coordinate value and interpolation of heart point determine that the finger interactive action slides for finger, and according in finger sliding and smart projector The correspondence of predetermined registration operation executes predetermined registration operation.
As shown in Figure 3 it is found that the gesture interaction method of implementation column of the present invention, passes through the scape of acquisition user's finger interactive action Then deep image handles depth image to obtain the coordinate value of corresponding finger interaction center point, judge that finger interaction is full When sufficient deliberate action condition, reports the coordinate value of finger interaction center point and finger interaction center is clicked through on after row interpolation compensates Report interpolation;Determine that finger interactive action slides for finger by the coordinate value and interpolation of finger interaction center point again, and according to finger Sliding and the correspondence of predetermined registration operation in smart projector execute predetermined registration operation.
Here predetermined registration operation is, for example, page turning, wakes up the operations such as screen.
It is appreciated that when the gesture interaction method of the present embodiment is the finger interaction center point that can indicate slide After coordinate value is reported to system, system can realize predetermined registration operation according to the sliding of preservation and the correspondence of predetermined registration operation, this It is realized similar to the touch screen by smart mobile phone and touches interactive operation.
It should be noted that on the projection plane of smart projector, user can carry out gesture interaction, that is, Ke Yi It clicked, slided with finger on projection plane, relatively-stationary contact area that there are one fingers and projection plane meeting, and depth of field mould Group can be found out in the preset range according to the depth value in the depth image of acquisition in preset range (such as 1 cm range) The average value of depth value is then using average value as the coordinate value of finger interaction center point.In addition, the colour with acquisition color-values Image is different, the depth value of the collected target scene of depth image, and depth value characterizes certain point distance in projection scene and takes the photograph The distance of camera (i.e. depth of field module).
In order to improve the efficiency of the present embodiment algorithm, three independent thread parallel meters are used in one embodiment of the invention It calculates, that is to say, that step S101, S102, S103 in Fig. 3 are realized by three threads.
Fig. 4 is a kind of sequence diagram of gesture interaction method of one embodiment of the invention, referring to Fig. 4, downward arrow in Fig. 4 Head indicates time shaft, and the time of every Image Acquisition is uniform in the present embodiment, and the rate with depth of field module is that 30FPS is Example, the acquisition time of every image is about 40 milliseconds.Here it is illustrated with acquiring the action once slided, Fig. 4 intermediate cam shapes Label represents the finger interaction center point identified in depth image, and (each triangular marker comes from a width depth map Picture), position coordinate value of the circular mark representative to the finger interaction center point obtained after width depth image processing, five jiaos Shape label represents the coordinate value of the finger interaction center point reported and the prediction coordinate value (solid point as interpolation) of insertion.
Workflow in the present embodiment is substantially:After thread three gets the first width image data, image data enters The algoritic module of thread two, while thread three continues to obtain the image of depth of field module acquisition, realizes parallel mode.When in thread two Algorithm finger interaction center point be calculated postponed, thread one will start, and thread one will be in the interaction of obtained finger The position coordinates of heart point are reported to background system (Android system in such as mobile phone), background system to pass through front and back finger interaction center The position of point is slided and realizes corresponding operation with the correspondence of predetermined registration operation.
Fig. 5 is the interpolation flow chart of one embodiment of the invention, in the present embodiment, is sat from second finger interaction center point Mark proceeds by corresponding judgement.Deterministic process is as shown in Figure 5, and after meeting condition, one is obtained newly by interpolation method Point, such as the point 3 in Fig. 4.Start timer (since algorithm time interval substantially constant is 50 milliseconds) at this time, in the algorithm time When at the time of the half of interval, thread one is reported to the coordinate value for putting 3 in system, is equivalent to the point 2 and point realized in figure 6 A new point 3 is inserted between 4, to realize the continuity and fluency of sliding.
Referring to Fig. 5, flow starts, the condition in first judgment step 201, and whether Point (n-2) is null value;That is, first It first to determine in the n-th -2 width figure and not detect finger interaction point.Here n is, for example, 3.
Here Point (n)=(x (n), y (n)), the finger interaction center point detected for the n-th width depth image The coordinate of point, i.e. coordinate value are (x, y).Coordinate system is using the top left corner pixel of piece image point as coordinate origin, with width It is respectively reference axis structure with short transverse and obtains.
The condition of step 202 is that Point (n-1) is non-null value and single-point touch.
That is, the (n-1)th width figure detects finger interaction center point and only detects a finger interaction center point, If meeting above-mentioned 202 condition, it is equivalent to have obtained the point 1 in Fig. 4.
Step 203 is the detection with step 202 the same terms, that is, Point (n) is non-null value, and single-point touch, if step Rapid 203 condition is also met, and is equivalent to have obtained the point 2 in Fig. 4;
It is emphasized that here limitation single-point touch condition be due to:The algorithm of the present embodiment supports 10 touch-controls (such as Ten fingers contact projection plane), i.e., in same width figure, there can be ten finger interaction center points, may then generate The coordinate of Point (n) _ 1, Point (n) _ 2......Point (n) _ 100 point.And under usual conditions, sliding is all with one What finger carried out, the present embodiment is also for the slack problem of sliding process is improved, so by the gesture interaction of user It is limited to and slides under this scene, i.e., to exclude this non-slip exchange scenario of ten finger contact screens.
The condition of step 204 is that the absolute value of Point (n)-Point (n-1) is more than pre-determined distance threshold value.This condition It is the screening to the distance between two points being obtained in step 202 and step 203.
Here presetting at distance threshold isThis is because as shown in fig. 7, in general, on the contact surface of gesture interaction One button is composed of several coordinate points (dot in Fig. 7), and distance is 1 between two coordinate points, four coordinate points Square is constituted, then cornerwise distance is between coordinate points
It is emphasized that using the condition and threshold value of above-mentioned steps 202 to 204, can be very good to evade one other Interaction scenarios, finally navigate to sliding finger interact this scene.First, this algorithm be for single-point touch, this Which two central point just specify that range formula in step 204 applies is.Secondly, the condition of above-mentioned steps 202 to 204 is utilized Interference can be filtered out with threshold value.For example, Fig. 8 is the finger interaction center point of the click gesture interaction of one embodiment of the invention Schematic diagram, for finger interaction (i.e. finger in the of short duration time by interaction face) scene during the clicking of Fig. 8 signals It can be very good to filter out.Such case can still obtain a series of coordinate value, these coordinate values when carrying out finger identification The characteristics of be to be held essentially constant, and this slip gesture interaction scenarios that be apparently not the embodiment of the present invention be directed to, even if it can By the condition of step 202 and 203, can be also filtered in step 204, because of finger centre point in consecutive image at this time It sets and is basically unchanged, center position coordinate value is made the absolute value obtained after difference and (is not more than close to 0)。
In addition, can also be filtered out well to clicking interval in Fig. 8.It refers to that finger clicks end to click interval, then from Interaction page is opened, the process clicked again.Obviously, in Fig. 8 continuous solid dot be unsatisfactory for step 204 condition detection, And it is mingled with hollow dots between solid dot, and the detection of step 202 and step 203 cannot be met, then such situation also can be by It excludes, a kind of final only remaining this interaction scenario of sliding.
After having passed through the condition of step 201-204, the conclusion that user is being slided at this time is obtained, then subsequently will It can be inserted into system in particular moment and report finger interaction center point coordinates value.
Step 205 is namely executed, the timing since by step 204 has reached preset time threshold when the time When value, in the n-th width depth image finger interaction center point indicate position after be inserted into new finger interaction center point and on The coordinate value for reporting new finger interaction center point, n+1 is set to by n.
Preset time threshold calculates in this way:In conjunction with Fig. 4, the present embodiment will be realized to be noted between two points detected Enter an interpolation to improve the slack effect of sliding, and the time obtained between two finger interaction center points is about 50ms Algorithm in (millisecond), that is, thread two determines finger interaction center point the time it takes.Preferably, the present embodiment will be 20 milliseconds after each being reported by the finger interaction center point of condition report interpolation, such as on reporting a little 20ms after 2 Report the coordinate (that is, interpolation) of the point of prediction.
And interpolation calculates in this way:The coordinate of known Point (n-1) is (x (n)+x (n+1), y (n)+y (n+1)), The coordinate of Point (n) is (x (n), y (n)), then the coordinate of the intermediate point of the two isBy This it is found that the present embodiment is the prediction for carrying out subsequent point with linear interpolation method, can then obtain point coordinates below calculate it is public Formula isIt can be obtained after arrangement Then obtained new interpolation point and reported, the judgement of follow-up finger interaction center point and the calculating of interpolation and report will repeat The flow of step 203- steps 205.
It should be pointed out that in order to ensure the smooth effect of sliding, not using the end of sliding as exiting in the present embodiment The condition of interpolation after user slides that last point of end, still can be inserted into an interpolation point then according to this algorithm.Example Such as, referring to Fig. 4, it is assumed that point 4 is the point that the sliding judged terminates, then after sliding still according to the method for the present embodiment A point 5 so is inserted, this does not interfere with the impression of user, for sliding interaction, compensates the distance of several sliding points more, User is not aware of substantially.
Fig. 9 is a kind of block diagram of gesture interaction device of one embodiment of the invention, referring to Fig. 9, the gesture interaction device 900 are applied to smart projector, including:
Image acquisition unit 901, it is dynamic for obtaining finger interaction of the user on the projection interactive flat of smart projector The depth image of work;
Image processing unit 902 obtains the coordinate of corresponding finger interaction center point for being handled depth image Value, and judge whether finger interaction meets deliberate action condition according to the coordinate value of the finger interaction center point of depth image, when When meeting, row interpolation compensation is clicked through to finger interaction center;
Unit 903, coordinate value and interpolation for reporting finger interaction center point so that interacted according to finger are realized in interaction The coordinate value and interpolation of central point determine that finger interactive action slides for finger, and according to pre- in finger sliding and smart projector If the correspondence of operation executes predetermined registration operation.
In one embodiment of the invention, image processing unit 902 is specifically used for:In through the following steps after rule It is determined as finger interaction and meets deliberate action condition,
Step 201, the coordinate value of finger interaction center point is null value in the n-th -2 width depth image;
Step 202, the coordinate value of finger interaction center point is non-null value and finger interaction center in the (n-1)th width depth image Point is one;
Step 203, the coordinate value of finger interaction center point is non-null value and finger interaction center point in the n-th width depth image It is one;
Step 204, by hand in the coordinate value and the n-th width depth image of finger interaction center point in the (n-1)th width depth image The distance for referring to the calculated two fingers interaction center point of coordinate value of interaction center point is more than pre-determined distance threshold value.
In one embodiment of the invention, image processing unit 902, for the timing since by step 204, When the time having reached preset time threshold, inserted after the position that finger interaction center point indicates in the n-th width depth image Enter new finger interaction center point and report the coordinate value of new finger interaction center point, n is set to n+1.
In one embodiment of the invention, image processing unit 902, for utilizing linear interpolation method according to the n-th width scape In deep image in the coordinate value of finger interaction center point and the (n-1)th width depth image finger interaction center point coordinate value, really The coordinate value of fixed new finger interaction center point, and after the position that finger interaction center point indicates in the n-th width depth image It is inserted into.
In one embodiment of the invention, unit is realized in image acquisition unit 901, image processing unit 902 and interaction 903 three threads by starting in a parallel fashion execute respectively.
It should be noted that the course of work of the gesture interaction device of the present embodiment is the reality with aforementioned gesture interaction method Existing step is corresponding, therefore does not have the part of description to may refer to the explanation in previous embodiment in the present embodiment, herein no longer It repeats.
Figure 10 is the structure chart of the electronic equipment of one embodiment of the invention.As shown in Figure 10, which includes depositing Reservoir 1001 and processor 1002 are communicated by internal bus 1003 between memory 1001 and processor 1002 and are connected, storage Device 1001 is stored with the program instruction that can be executed by processor 1002, and program instruction can be realized when being executed by processor 1002 Above-mentioned gesture interaction method.
In addition, the logical order in above-mentioned memory 1001 can be realized and be used as by the form of SFU software functional unit Independent product sale in use, can be stored in a computer read/write memory medium.Based on this understanding, originally Substantially the part of the part that contributes to existing technology or the technical solution can be in other words for the technical solution of invention The form of software product embodies, which is stored in a storage medium, including some instructions to So that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation of the application The all or part of step of example method.And storage medium above-mentioned includes:USB flash disk, mobile hard disk, read-only memory (ROM, Read- Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with Store the medium of program code.
An alternative embodiment of the invention provides a kind of computer readable storage medium, computer-readable recording medium storage Computer instruction, computer instruction make computer execute above-mentioned method.
It should be understood by those skilled in the art that, the embodiment of the present invention can be provided as method, system or computer program Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention Apply the form of example.Moreover, the present invention can be used in one or more wherein include computer usable program code computer The computer program production implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) The form of product.
The present invention be with reference to according to the method for the embodiment of the present invention, the flow of equipment (system) and computer program product Figure and/or block diagram describe.It should be understood that can be realized by computer program instructions every first-class in flowchart and/or the block diagram The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided Instruct the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce A raw machine so that the instruction executed by computer or the processor of other programmable data processing devices is generated for real The dress for the function of being specified in a present flow of flow chart or a box or multiple boxes for multiple flows and/or block diagram It sets.
It should be noted that the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability Contain, so that the process, method, article or equipment including a series of elements includes not only those elements, but also includes Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device. In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element Process, method, article or equipment in there is also other identical elements.
In the specification of the present invention, numerous specific details are set forth.Although it is understood that the embodiment of the present invention can To put into practice without these specific details.In some instances, well known method, structure and skill is not been shown in detail Art, so as not to obscure the understanding of this description.Similarly, it should be understood that disclose in order to simplify the present invention and helps to understand respectively One or more of a inventive aspect, in the above description of the exemplary embodiment of the present invention, each spy of the invention Sign is grouped together into sometimes in single embodiment, figure or descriptions thereof.However, should not be by the method solution of the disclosure It releases and is intended in reflection is following:The feature that i.e. the claimed invention requirement ratio is expressly recited in each claim is more More features.More precisely, as the following claims reflect, inventive aspect is to be less than single reality disclosed above Apply all features of example.Therefore, it then follows thus claims of specific implementation mode are expressly incorporated in the specific implementation mode, Wherein each claim itself is as a separate embodiment of the present invention.
The above description is merely a specific embodiment, under the above-mentioned introduction of the present invention, those skilled in the art Other improvement or deformation can be carried out on the basis of the above embodiments.It will be understood by those skilled in the art that above-mentioned tool Body description only preferably explains that the purpose of the present invention, protection scope of the present invention are subject to the protection scope in claims.

Claims (11)

1. a kind of gesture interaction method, which is characterized in that this method includes:
Obtain the depth image of finger interactive action of the user on the projection interactive flat of smart projector;
The depth image is handled to obtain the coordinate value of corresponding finger interaction center point, and according to the hand of depth image The coordinate value for referring to interaction center point judges whether finger interaction meets deliberate action condition, when meeting, is interacted to the finger Central point carries out Interpolation compensation;
Report the coordinate value and interpolation of the finger interaction center point so that according to the coordinate value of the finger interaction center point and Interpolation determine the finger interactive action for finger slide, and according to finger sliding in smart projector predetermined registration operation it is corresponding Relationship executes predetermined registration operation.
2. according to the method described in claim 1, it is characterized in that, according to the coordinate value of the finger interaction center point of depth image Judge whether finger interaction meets deliberate action condition and include:
It is determined as finger interaction after rule in through the following steps and meets deliberate action condition,
Step 201, the coordinate value of finger interaction center point is null value in the n-th -2 width depth image;
Step 202, the coordinate value of finger interaction center point is non-null value in the (n-1)th width depth image and finger interaction center point is One;
Step 203, the coordinate value of finger interaction center point is non-null value in the n-th width depth image and finger interaction center point is one It is a;
Step 204, it is handed over by finger in the coordinate value and the n-th width depth image of finger interaction center point in the (n-1)th width depth image The distance of the calculated two fingers interaction center point of coordinate value of mutual central point is more than pre-determined distance threshold value.
3. according to the method described in claim 2, it is characterized in that, clicking through row interpolation compensation packet to the finger interaction center It includes:
Timing since by the step 204, when the time having reached preset time threshold, in the n-th width depth map It is inserted into new finger interaction center point after the position that finger interaction center point indicates as in and reports new finger interaction center The coordinate value of point, n+1 is set to by n.
4. according to the method described in claim 3, it is characterized in that, finger interaction center point indicates in the n-th width depth image Position after be inserted into new finger interaction center point and include:
Using linear interpolation method according to the coordinate value and the (n-1)th width depth map of finger interaction center point in the n-th width depth image The coordinate value of finger interaction center point, determines the coordinate value of new finger interaction center point, and in the n-th width depth image as in It is inserted into after the position of finger interaction center point instruction.
5. according to the method described in claim 1, it is characterized in that, this method includes:Start three threads difference in a parallel fashion It executes depth image to obtain, depth image processing, the coordinate value and interpolation of finger interaction center point report.
6. a kind of gesture interaction device, which is characterized in that the device includes:
Image acquisition unit, the depth of field for obtaining finger interactive action of the user on the projection interactive flat of smart projector Image;
Image processing unit obtains the coordinate value of corresponding finger interaction center point for being handled the depth image, And judge whether finger interaction meets deliberate action condition according to the coordinate value of the finger interaction center point of depth image, work as satisfaction When, row interpolation compensation is clicked through to the finger interaction center;
Unit, coordinate value and interpolation for reporting the finger interaction center point are realized in interaction so that are handed over according to the finger The coordinate value and interpolation of mutual central point determine that the finger interactive action slides for finger, and are projected with intelligence according to finger sliding The correspondence of predetermined registration operation executes predetermined registration operation on instrument.
7. device according to claim 6, which is characterized in that described image processing unit is specifically used for:When by following It is determined as finger interaction in step after rule and meets deliberate action condition,
Step 201, the coordinate value of finger interaction center point is null value in the n-th -2 width depth image;
Step 202, the coordinate value of finger interaction center point is non-null value in the (n-1)th width depth image and finger interaction center point is One;
Step 203, the coordinate value of finger interaction center point is non-null value in the n-th width depth image and finger interaction center point is one It is a;
Step 204, it is handed over by finger in the coordinate value and the n-th width depth image of finger interaction center point in the (n-1)th width depth image The distance of the calculated two fingers interaction center point of coordinate value of mutual central point is more than pre-determined distance threshold value.
8. device according to claim 7, which is characterized in that described image processing unit, for passing through the step certainly Beginning timing from when 204, when the time having reached preset time threshold, the finger interaction center point in the n-th width depth image It is inserted into new finger interaction center point after the position of instruction and reports the coordinate value of new finger interaction center point, n is set to n +1。
9. device according to claim 8, which is characterized in that
Described image processing unit, for the seat using linear interpolation method according to finger interaction center point in the n-th width depth image The coordinate value of finger interaction center point in scale value and the (n-1)th width depth image determines the coordinate of new finger interaction center point Value, and be inserted into after the position that finger interaction center point indicates in the n-th width depth image.
10. device according to claim 6, which is characterized in that described image acquiring unit, image processing unit and interaction Realize that unit is executed respectively by three threads started in a parallel fashion.
11. a kind of electronic equipment, which is characterized in that the electronic equipment includes:Memory and processor, the memory and institute It states to communicate by internal bus between processor and connect, the memory, which is stored with, to be referred to by the program that the processor executes It enables, described program instruction can realize claim 1-5 any one of them gesture interaction methods when being executed by the processor.
CN201810090288.4A 2018-01-30 2018-01-30 A kind of gesture interaction method and device Pending CN108491066A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810090288.4A CN108491066A (en) 2018-01-30 2018-01-30 A kind of gesture interaction method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810090288.4A CN108491066A (en) 2018-01-30 2018-01-30 A kind of gesture interaction method and device

Publications (1)

Publication Number Publication Date
CN108491066A true CN108491066A (en) 2018-09-04

Family

ID=63343955

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810090288.4A Pending CN108491066A (en) 2018-01-30 2018-01-30 A kind of gesture interaction method and device

Country Status (1)

Country Link
CN (1) CN108491066A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109683775A (en) * 2018-12-12 2019-04-26 歌尔科技有限公司 Exchange method, projection device and storage medium based on projection
CN112732162A (en) * 2021-03-30 2021-04-30 北京芯海视界三维科技有限公司 Projection interaction method, device and system and computer storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012234450A (en) * 2011-05-09 2012-11-29 Bluemouse Technology Co Ltd Character recognition device
US20130185671A1 (en) * 2012-01-13 2013-07-18 Fih (Hong Kong) Limited Electronic device and method for unlocking the electronic device
CN103488356A (en) * 2013-10-18 2014-01-01 武汉拓宝电子系统有限公司 Infrared camera three-dimensional imaging-based touch recognition method
US20150033194A1 (en) * 2013-07-25 2015-01-29 Yahoo! Inc. Multi-finger user identification
CN105589553A (en) * 2014-09-23 2016-05-18 上海影创信息科技有限公司 Gesture control method and system for intelligent equipment
CN105718878A (en) * 2016-01-19 2016-06-29 华南理工大学 Egocentric vision in-the-air hand-writing and in-the-air interaction method based on cascade convolution nerve network
CN107256083A (en) * 2017-05-18 2017-10-17 河海大学常州校区 Many finger method for real time tracking based on KINECT

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012234450A (en) * 2011-05-09 2012-11-29 Bluemouse Technology Co Ltd Character recognition device
US20130185671A1 (en) * 2012-01-13 2013-07-18 Fih (Hong Kong) Limited Electronic device and method for unlocking the electronic device
US20150033194A1 (en) * 2013-07-25 2015-01-29 Yahoo! Inc. Multi-finger user identification
CN103488356A (en) * 2013-10-18 2014-01-01 武汉拓宝电子系统有限公司 Infrared camera three-dimensional imaging-based touch recognition method
CN105589553A (en) * 2014-09-23 2016-05-18 上海影创信息科技有限公司 Gesture control method and system for intelligent equipment
CN105718878A (en) * 2016-01-19 2016-06-29 华南理工大学 Egocentric vision in-the-air hand-writing and in-the-air interaction method based on cascade convolution nerve network
CN107256083A (en) * 2017-05-18 2017-10-17 河海大学常州校区 Many finger method for real time tracking based on KINECT

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王晓峰等主编: "《数值逼近》", 31 December 2017 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109683775A (en) * 2018-12-12 2019-04-26 歌尔科技有限公司 Exchange method, projection device and storage medium based on projection
CN112732162A (en) * 2021-03-30 2021-04-30 北京芯海视界三维科技有限公司 Projection interaction method, device and system and computer storage medium

Similar Documents

Publication Publication Date Title
Memo et al. Head-mounted gesture controlled interface for human-computer interaction
US10664993B1 (en) System for determining a pose of an object
CN107466411B (en) Two-dimensional infrared depth sensing
CN104598915B (en) A kind of gesture identification method and device
CA3058821C (en) Touchless input
CN102999152B (en) A kind of gesture motion recognition methods and system
CN112823328A (en) Method for HMD camera calibration using synchronized images rendered on an external display
EP3316080B1 (en) Virtual reality interaction method, apparatus and system
CN106407875B (en) Target's feature-extraction method and device
US9665767B2 (en) Method and apparatus for pattern tracking
CN104317391A (en) Stereoscopic vision-based three-dimensional palm posture recognition interactive method and system
CN104240277B (en) Augmented reality exchange method and system based on Face datection
CN110413816A (en) Colored sketches picture search
US10338879B2 (en) Synchronization object determining method, apparatus, and system
SG181597A1 (en) Head recognition method
EP3345123B1 (en) Fast and robust identification of extremities of an object within a scene
CN107067031A (en) A kind of calligraphy posture automatic identifying method based on Wi Fi signals
CN103632126A (en) Human face tracking method and device
CN102799271A (en) Method and system for identifying interactive commands based on human hand gestures
CN105892668B (en) Apparatus control method and device
CN108491066A (en) A kind of gesture interaction method and device
CN105205786B (en) A kind of picture depth restoration methods and electronic equipment
CN110780734B (en) Gesture interaction AR projection method and device based on radar
KR20130017258A (en) Apparatus and method about implementation of augmented reality based on model with multiple-planes
CN107610173A (en) A kind of real-time location method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20180904

RJ01 Rejection of invention patent application after publication