CN205485915U - Wrist formula equipment - Google Patents
Wrist formula equipment Download PDFInfo
- Publication number
- CN205485915U CN205485915U CN201521139346.6U CN201521139346U CN205485915U CN 205485915 U CN205485915 U CN 205485915U CN 201521139346 U CN201521139346 U CN 201521139346U CN 205485915 U CN205485915 U CN 205485915U
- Authority
- CN
- China
- Prior art keywords
- camera head
- image
- wrist
- processor
- finger
- 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.)
- Expired - Fee Related
Links
- 210000000707 wrist Anatomy 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 claims description 32
- 210000004247 hand Anatomy 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 4
- 210000003811 finger Anatomy 0.000 description 65
- 238000006243 chemical reaction Methods 0.000 description 11
- 230000033001 locomotion Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 210000005224 forefinger Anatomy 0.000 description 4
- 230000005057 finger movement Effects 0.000 description 3
- 210000004932 little finger Anatomy 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- XUMBMVFBXHLACL-UHFFFAOYSA-N Melanin Chemical compound O=C1C(=O)C(C2=CNC3=C(C(C(=O)C4=C32)=O)C)=C2C4=CNC2=C1C XUMBMVFBXHLACL-UHFFFAOYSA-N 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005059 dormancy Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 210000001145 finger joint Anatomy 0.000 description 1
- 210000002478 hand joint Anatomy 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 210000003813 thumb Anatomy 0.000 description 1
- 230000002618 waking effect Effects 0.000 description 1
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
The utility model provides a wrist formula equipment, including the wrist strap, a camera device sets up on the wrist strap, the 2nd camera device sets up on the wrist strap and with a camera device is relative, and the 2nd camera device camera lens institute directive orientation with a camera device is the same, the treater, it is right to be used for a camera device with the hand image that the 2nd camera device gathered is handled.
Description
Technical field
This utility model relates to Intelligent worn device field, is specifically related to a wrist equipment.
Background technology
Along with the fast development of software and hardware relevant technical, wrist intelligent apparatus, such as intelligent watch, intelligence
The integrated level of bracelet etc. is more and more higher, and function is more and more abundanter, and the cell-phone function of significant proportion can lead to
Crossing intelligent watch, Intelligent bracelet realizes, and is greatly simplified user and receives and the method for transmission information.But and
Traditional intelligence mobile phone compares, and wrist intelligent apparatus is limited to small size display screen curtain, on the one hand, use
Person cannot utilize touch screen or button to complete the operation of correlation function in use well, easily causes by mistake
Operation, on the other hand, when intelligent watch be worn on one on hand time, operate on it, except
Waking up up, the simple operations such as dormancy need not outside the operation of another hands, and remaining complex operation is all
Another hands is had to complete, it is impossible to use one hand independently intelligent watch to be operated, therefore, intelligence hands
Table still suffers from the biggest defect on content shows and operates.
At present, more existing wrist equipment catch user's finger by the photographic head being arranged on equipment
Action, it is achieved be controlled equipment according to the action of finger, the photographic head of this kind equipment is generally arranged
Inside wrist, to the shooting finger-image in user's palm of the hand direction.But the environment residing for user
More complicated, when identifying the specific region such as finger or joint in the images, easily by ambient light and
The interference of the factors such as shooting background, finds the accuracy rate in region residing for finger relatively low the most in the images.
Utility model content
Therefore, seek in hand images during the technical problems to be solved in the utility model is prior art
The accuracy rate looking for region residing for finger is relatively low.
In view of this, this utility model provides a kind of wrist equipment, including: wrist strap;First shooting dress
Put, be arranged on described wrist strap;Second camera head, is arranged on described wrist strap and with described first
Camera head is relative, and the direction pointed by described second camera head lens images with described first
Device is identical;Processor, for gather described first camera head and described second camera head
Hand images processes.
Preferably, described first camera head for shooting the first image, institute along wrist to the back of the hand direction
Stating the second camera head for shooting the second image to palm of the hand direction along described wrist, described processor is used
In obtaining described first image and the second image, determine the direction residing for finger according to described first image,
The region that finger is residing in described second image is determined according to the direction residing for described finger.
Preferably, described wrist equipment is intelligent watch, and described processor is arranged in dial plate, described
First camera head is arranged and the second camera head is separately positioned at dial plate and on watchband, is arranged on table
Camera head on band is connected by the connection member being arranged in watchband with described processor.
Preferably, described connection member is flexible PCB.
This utility model also provides for another kind of wrist equipment, including: wrist strap;First camera head, if
Put on described wrist strap;Second camera head, is arranged on described wrist strap and fills with described first shooting
Put relatively, and the direction pointed by described second camera head lens and described first camera head phase
With;First processor, for processing the hand images of described first camera head collection;The
Two processors, are used for the result according to described first processor to described second camera head collection
Hand images process.
Preferably, described first camera head is for shooting the first image along wrist to the back of the hand direction;Institute
State the second camera head for shooting the second image along described wrist to palm of the hand direction;Described first processes
Device is for determining the direction residing for finger according to described first image;Described second processor is used for basis
Direction residing for described finger determines the region that finger is residing in described second image.
Preferably, described wrist equipment is intelligent watch, and described first processor and the second processor divide
Not being arranged at dial plate and on watchband, described first camera head and the second camera head are separately positioned on
At dial plate and on watchband, the processor being arranged on watchband and the processor being arranged in dial plate are by setting
Put the connection member in watchband to connect.
Preferably, described connection member is flexible PCB.
The wrist equipment that this utility model provides can utilize its 2 camera heads respectively along wearer's wrist
Gathering wearer's hand images to the palm of the hand and the back of the hand direction, its image gathered can show user's hands
The image in portion, then its processor 13 can be analyzed the process such as judgement to hand images, passes through hand
Image recognition goes out the gesture motion of user, and then can realize the control to equipment.
Accompanying drawing explanation
In order to be illustrated more clearly that this utility model detailed description of the invention or technical side of the prior art
Case, will make simply the accompanying drawing used required in detailed description of the invention or description of the prior art below
Introduce, it should be apparent that, the accompanying drawing in describing below is embodiments more of the present utility model, right
From the point of view of those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to according to
These accompanying drawings obtain other accompanying drawing.
The structural representation of the wrist equipment that Fig. 1 provides for this utility model embodiment 1;
One camera head of the wrist equipment that Fig. 2 provides by this utility model embodiment is collected
Hand images schematic diagram;
Fig. 3 is collected by another camera head of the wrist equipment that this utility model embodiment provides
Hand images schematic diagram;
The structural representation of the wrist equipment that Fig. 4 provides for this utility model embodiment 2;
The method determining region residing for finger in the picture that Fig. 5 provides for this utility model embodiment
Flow chart;
Fig. 6 is the side determining region residing for finger in the picture provided according to this utility model embodiment
The schematic diagram in direction residing for finger determined by method;
Fig. 7 is the side determining region residing for finger in the picture provided according to this utility model embodiment
Area schematic residing for finger determined by method;
Fig. 8 is the scene schematic diagram in direction residing for a concrete determination finger;
The device determining region residing for finger in the picture that Fig. 9 provides for this utility model embodiment
Structural representation.
Detailed description of the invention
Below in conjunction with accompanying drawing, the technical solution of the utility model is clearly and completely described, aobvious
So, described embodiment is a part of embodiment of this utility model rather than whole embodiments.
Based on the embodiment in this utility model, those of ordinary skill in the art are not making creative work
The every other embodiment obtained under premise, broadly falls into the scope of this utility model protection.
In description of the present utility model, it should be noted that term " " center ", " on ", D score,
Orientation or the position relationship of the instruction such as "left", "right", " vertically ", " level ", " interior ", " outward " are
Based on orientation shown in the drawings or position relationship, it is for only for ease of description this utility model and simplification is retouched
State rather than indicate or imply that the device of indication or element must have specific orientation, with specifically
Azimuth configuration and operation, therefore it is not intended that to restriction of the present utility model.Additionally, term " the
One ", " second ", " the 3rd " are only used for describing purpose, and it is not intended that instruction or imply relatively heavy
The property wanted.
In description of the present utility model, it should be noted that unless otherwise clearly defined and limited,
Term " is installed ", " being connected ", " connection " should be interpreted broadly, for example, it may be fixing even
Connect, it is also possible to be to removably connect, or be integrally connected;Can be to be mechanically connected, it is also possible to be electricity
Connect;Can be to be joined directly together, it is also possible to be indirectly connected to by intermediary, it is also possible to be two units
Connection within part, can be wireless connections, it is also possible to be wired connection.Common for this area
For technical staff, above-mentioned term concrete meaning in this utility model can be understood with concrete condition.
Additionally, technical characteristic involved in this utility model difference embodiment disclosed below is only
The conflict of not constituting each other just can be combined with each other.
Embodiment 1
This utility model embodiment provides a kind of wrist equipment, and this device includes as shown in Figure 1: wrist strap 10,
First camera head 11 and the second camera head 12;Wherein, the first camera head 11 and the second shooting
Device 12 is arranged on wrist strap 10, and the first camera head 11 is relative with the second camera head 12 to be set
Put, and the two pointed direction is identical.
After user wears, the first camera head 11 can be along wearer's wrist to the back of the hand direction shooting hand
Image, the second camera head 12 can be along wearer's wrist to palm of the hand direction shooting hand images.For
Different types of wrist equipment, the set-up mode of camera head is different, but its angle with wearer's arm
Degree is that comparison is fixed.The first camera head 11 arranged in this way and the second camera head 12 can
Collect hand images as shown in Figures 2 and 3 respectively.
Processor 13, is connected, for right with described first camera head 11 and the second camera head 12
The hand images that described first camera head 11 and described second camera head 12 gather processes.
Processor 13 can carry out multiple process to image, identifies hand motion the most in the picture, according to figure
Equipment is controlled by the hand motion as reflecting, specifically will carry out in subsequent embodiment in detail
Introduce.
The said equipment can utilize its 2 camera heads respectively along wearer's wrist to the palm of the hand and the back of the hand direction
Gathering wearer's hand images, its image gathered can show the image of user's hand, then its
Processor 13 can be analyzed judgement etc. and process hand images, identifies user's by hand images
Gesture motion, and then the control to equipment can be realized.
Above-mentioned wrist equipment can be intelligent watch, and when user wears wrist-watch, dial plate is usually located at wrist
Outside, watchband is around wrist, and therefore the first camera head 11 may be provided at dial plate, the second shooting dress
Put 12 and may be provided on watchband, thus the first camera head 11 be arranged on this towards hand, its angle
Just the back of the hand can be photographed with direction;Second camera head 12 is arranged on watchband (near such as bracelet clasp
Or on bracelet clasp) towards hand, its angle and direction can photograph the palm of the hand and finger just, and this structure is not
User is needed to adjust the position of camera head, it is simple to user wears.Further, by above-mentioned 2 photographic head
To carry out exchanging also be feasible in position.Processor 13, as the process core of intelligent watch, can be arranged
At dial plate, the second camera head 12 is arranged in watchband with the connection member of processor 13, and this is even
Relay part can be flexible PCB.
Embodiment 2
This utility model embodiment provides a kind of wrist equipment, and this device includes as shown in Figure 4: wrist strap
20, the first camera head 21 and the second camera head 22;Wherein, the first camera head 21 and second
Camera head 22 is arranged on wrist strap 20, the first camera head 21 and the second camera head 22 phase
Identical to setting and the two pointed direction.
The first camera head 21 arranged in this way and the second camera head 22 can be adopted collection respectively and arrive such as
Hand images shown in Fig. 2 and Fig. 3.
First processor 23, is connected with the first camera head 21, for adopting the first camera head 21
The hand images of collection processes;
Second processor 24, is connected with the second camera head 22, for according to first processor 23
The hand images that second camera head 22 is gathered by result processes.
The image being respectively received can be carried out many by first processor 23 and the second processor 24 respectively
Kind processing, the hand motion identify hand motion the most in the picture, reflecting according to image is to equipment
It is controlled, specifically will describe in detail in subsequent embodiment.
The said equipment can utilize its 2 camera heads respectively along wearer's wrist to the palm of the hand and the back of the hand direction
Gathering wearer's hand images, its image gathered can show the image of user's hand, then its 2
Individual processor can be analyzed judgement etc. respectively and process hand images, identifies use by hand images
The gesture motion at family, and then the control to equipment can be realized.
Above-mentioned wrist equipment can be intelligent watch, the first camera head 21 and the second camera head 22
Being separately positioned at dial plate and on watchband, corresponding processor can be arranged nearby, such as can be by first
Camera head 21 and first processor 23 are arranged at dial plate, and the second camera head 22 and second processes
Device 24 is arranged on watchband the position close to bracelet clasp, the processor being arranged on watchband be arranged on table
Processor in dish is connected by the connection member being arranged in watchband, and connection member is preferably flexible electrical
Road plate.In the example depicted in fig. 4, first processor 23 and the second discrete setting of processor 24,
But it is not limited to this, it is also possible to the two processor is set together.
Embodiment 3
This utility model embodiment provides a kind of method determining region residing for finger in the picture, the party
Method can be by the processor 13 in embodiment 1 or the first processor in embodiment 2 23 and second
Reason device 24 performs, as it is shown in figure 5, the method comprises the steps:
S1, obtains the first image and the second image, wherein the first image figure the most as shown in Figure 2
Picture, the second image image the most as shown in Figure 3.
S2, determines the direction residing for finger according to the first image, it should be noted that wear under normality
The palm of person is that nature curves inwardly (shape of partly clenching fist), and therefore the first camera head 11 generally will not
Collect finger-image, the simply direction estimated in this step according to image shown in Fig. 2
Information.
Specifically, image as shown in Figure 2 shows the image in wearer's the back of the hand portion, by this
Image is analyzed and processes available such as the back of the hand profile, the angle of inclination of picture material, hand closes
The characteristic informations such as the heeling condition of joint, the most then can estimate wearer's hands according to features described above information
Refer to the orientation at place.It will be understood by those skilled in the art that residing for finger, direction is the most vertical
Edge under image, due to the impact of the factor such as state of user's wearing state and hand joint, as
Shown in arrow in Fig. 6, the direction generally has a certain degree along shape under image.
S3, determines, according to the direction residing for finger, the region that finger is residing in the second image, wherein,
Region residing for finger is finger tip, the region at finger-joint place.Under normality, the second camera head 12 can
To collect the image including finger, so then can be according to the direction estimated in step S2 at figure
Image shown in 3 is found the position of finger tip.Specifically can be according to a default length and above-mentioned side
To determining region in the picture.Further, by arranging predeterminable range, it may be determined that such as finger tip
With the more specifically region such as joint.One is can determine that such as according to said method as a example by fingertip area
The region that there may be finger tip shown in Fig. 7;Or can also be according to default ratio value and above-mentioned side
Divide an image into multistage to information, then determine that one or more snippets region wherein.
For the region in addition to region residing for above-mentioned finger, can directly ignore, or give relatively low
Weights, identify finger movement time, can preferentially in the above-mentioned region determined searching specific part,
Thus can reduce the amount of calculation identifying operation.
According to such scheme, by the image shot to the back of the hand direction along wrist is analyzed, can obtain
To the direction residing for finger, then according to the direction along wrist in the image that palm of the hand direction shoots it is being
Can determine that the region at finger place, and then the activity of finger, final basis can be judged in this region
The activity of finger specific part realizes various control and operates.Program identification finger specific part is utilized to live
It is not required to time dynamic in whole image find specific part, only need to find finger in the region determined special
Determining position, thus the program can improve the efficiency finding region residing for finger in the picture, thus
The efficiency of finger movement identification operation can be improved.
As one preferred embodiment, above-mentioned steps S2 may include that
S21, identifies at least two in forefinger, middle finger, the third finger and little finger in the first image
With the summit connecting joint of the back of the hand, specifically can be identified according to the hand shape facility in image,
The mode finding the position with obvious characteristic from image has multiple, utilizes existing feature identification to calculate
Method is all feasible.Thus can identify forefinger as shown in Figure 8, middle finger, nameless and little thumb
Referring to the summit in these 4 joints, the present embodiment is preferably used summit, 4 joints and carries out subsequent treatment, by
This result obtained is the most accurate.But this utility model is not limited to use 4 summits, use 2 or 3
Individual summit fitting a straight line is all feasible.
S22, utilizes the summit fitting a straight line in each joint, utilizes the algorithm of some fitting a straight line to have multiple,
It is all feasible for utilizing existing algorithm;
S23, using become predetermined angular with described straight line direction as the direction residing for described finger.Due to
Finger is necessarily in the downwardly direction of summit, joint, therefore can determine that angled with this straight line to
Under direction be the direction residing for finger, wherein predetermined angle can be 90 degree.Above-mentioned preferred version
Determining finger orientation according to joint position, its accuracy rate is higher.
As it has been described above, the mode finding the position with obvious characteristic from image has multiple, as one
Individual preferred embodiment, above-mentioned steps S21 may include that
S211, removes prospect and/or background image from the first image.Prospect and the back of the body is determined from image
The method of scape image has multiple, owing to the skin color data of human body have certain numerical range, institute
With in the picture, the rgb value of the pixel of hand region all should be the most permissible within a certain range
According to default rgb value scope, the content in image is judged, target image and the back of the body can be filtered out
Scape image;According to the sharpness value of image or depth value, the content in image can also be judged and goes
Removing, existing background removal approach is all feasible.
S212, the first image after eliminating prospect and/or background image identifies forefinger, middle finger,
The nameless profile connecting joint with at least two in little finger with the back of the hand, eliminates background image
After hand images in only remain with skin area, it is believed that this region is the region of hands.In order to know
Other finger part, needs to differentiate according to the morphological characteristic of finger.Thus, Canny operator can be used
Extract the edge contour of hand region.Canny operator by signal to noise ratio with location product estimate,
Approached by optimization method, obtain marginal information.
Specific address, it is necessary first to image is carried out gaussian filtering smoothed image noise, to reduce noise
Impact on testing result, gaussian kernel function is as follows:
Then calculate the gradient of image intensity value, i.e. do the first-order difference of both direction.Calculate each picture
The gradient amplitude of vegetarian refreshments and direction.
Corresponding intensity with direction is:
θ [x, y]=arctan (Gx(x, y)/Gy(x, y));
Obtain, in whole image after the gradient amplitude of each point and direction, calculating local maximum, retain
Corresponding pixel.Finally, the pixel that retain is calculated according to dual threshold, for retain
Pixel carries out boundary tracking, completes edge extracting.
S213, identifies the summit in joint according to the curvature of profile, after obtaining the back of the hand edge, and can be in order to
The extraction of joint boss is carried out by the back of the hand form.By the analysis for joint bossing form
It is recognised that joint raised brim has the situation of curvature mutation, i.e. joint projection both sides lines trend
More consistent, and raised line degree of crook is relatively big, and close to turning through 180 degree.
Based on above-mentioned characteristic, first image border is carried out dyad quantization image border line of sampling, with shape
The characteristic curve becoming to have length and move towards statistics.During vector quantization, seek distance according to the position between pixel
And first-order difference obtains direction trend.Then, calculate the dot product result of these vectors, obtain vector
Corner dimension between line.Then, (the most flat for all of more straight straightway of all verge searchings
All angles are not more than 25 degree).Arrange these straightways in order, calculate walking of straightway half interval contour section
To change, such as, it is more than 140 degree by moving towards change, and distance is more than certain threshold value, then be judged to phase
The joint answered.Remove corresponding noise and reproducible results, it is determined that for joint boss.
As one preferred embodiment, above-mentioned steps S211 may include that
S2111a, carries out color space conversion process to the first image;Human body skin is by skin corium and covers
Cover relatively thin epidermal area thereon to constitute, light in epidermal area by melanin absorption, and in skin corium
Occur to absorb and scattering the most simultaneously.The colour of skin difference of Different Individual mainly shows as by black in epidermal area
The brightness flop caused by concentration difference of element, its skin corium optical characteristics is the most essentially identical, Er Qietong
The individual colour of skin of race has stronger general character, and is clearly distinguishable from most of background color, in color
Space forms one little and clustering of compacting.Thus, the detection carrying out skin based on color is feasible
's.
Carry out Face Detection to need to select appropriate color space, colour of skin energy cluster, poly-in this space
It is combined, and to lack as far as possible with the lap of the non-colour of skin.The image of camera collection is RGB
Image, in RGB color space, the colour of skin is more with the lap of the non-colour of skin, and can be by brightness
Impact is serious;HSV color space well separates due to tone, color saturation and brightness, with
Overlapping less of non-colour of skin point;On CbCr subspace in YCbCr color space, the colour of skin is good
In the range of being gathered in a class ellipse, and concentration is also compared in the distribution on Cb, Cr component.Therefore,
By rgb space, hand images is converted to YCbCr color space or HSV color space is all feasible.
The conversion formula of RGB to HSV is:
The conversion formula of RGB to YCbCr is:
Y=0.257R '+0.504G '+0.098B '+16
Cb=-0.148R '-0.291G '+0.439B '+128
Cr=0.439R '-0.368G '-0.071B '+128.
S2112a, carries out binary conversion treatment, warp to the first image after color space conversion process
Cross conversion, the lines figure of only two kinds of colors of black and white can be converted the image into;
S2113a, removes prospect and/or background image in the first image after binary conversion treatment.
Above-mentioned preferred version can improve the accuracy identifying operation further.
As another preferred embodiment, above-mentioned steps S211 may include that
S2111b, obtains the depth value of each pixel in the first image
S2112b, compares the depth value of each pixel described with predetermined depth value range, with
Finger-image, prospect and/or background image is determined in from described first image.Due to wrist equipment
Particularity, need the partial distance camera head of imaging to be about about 10-15cm, therefore camera head
Focusing can be fixing, it is only necessary to ensures the focusing in 10-15cm clearly;Meanwhile, when lifting
During wrist operation, the generally distance hand of other objects (foreground and background) in areas imaging is more closely or relatively
Far, not in 10-15cm distance range, therefore foreground and background is out of focus, by the algorithm of fuzziness
Can readily differentiate front background.
S212b, removes prospect and/or background image, wherein the nearest interior of distance the first camera head 11
Holding is foreground image, and distance the first camera head 11 content too far is background image.
Foreground and background image is all got rid of by above-mentioned preferred version according to depth of view information, only retains the back of the hand
Anterior scene, then can identify joint in this scene further, thus can further improve identification
Efficiency.
Embodiment 4
This utility model embodiment provides a kind of device determining region residing for finger in the picture, such as Fig. 9
Shown in include:
Acquiring unit 91, for obtaining the first image and the second image, wherein said first image is edge
The image that wrist shoots to the back of the hand direction, described second image is to shoot along described wrist to palm of the hand direction
Image;
Direction-determining unit 92, for determining the direction residing for finger according to described first image;
According to the direction residing for described finger, area determination unit 93, for determining that finger is described second
Region residing in image.
According to such scheme, by the image shot to the back of the hand direction along wrist is analyzed, can obtain
To the direction residing for finger, then according to the direction along wrist in the image that palm of the hand direction shoots it is being
Can determine that the region at finger place, and then the activity of finger specific part can be judged in this region,
Finally realize various control according to the activity of finger specific part to operate.Utilize program identification finger special
Determine to be not required to during the activity of position in whole image find specific part, only need to seek in the region determined
Looking for finger specific part, thus the program can improve and finds the effect in region residing for finger in the picture
Rate, thus the efficiency of finger movement identification operation can be improved.
Preferably, described direction-determining unit 92 includes:
Summit determines unit, for identify in described first image forefinger, middle finger, the third finger and
At least two in little finger and the summit connecting joint of the back of the hand;
Fitting unit, for utilizing the summit fitting a straight line in each described joint;
Angle direction determines unit, and the direction being used for become predetermined angular with described straight line is as described hands
Direction residing for finger.
Above-mentioned preferred version determines finger orientation according to joint position, and its accuracy rate is higher.
Preferably, described summit determines that unit includes:
Background removal unit, for removing background image from described first image;
Outline identification unit, identifies each hands in the first image after eliminating background image
Refer to the profile connecting joint with the back of the hand;
Vertex recognition unit, for identifying the summit in joint according to the curvature of described profile.
Preferably, described background removal unit includes:
Color space converting unit, for carrying out color space conversion process to described first image;
Binary conversion treatment unit, for carrying out two to the first image after color space conversion process
Value processes;
Background process unit, for removing background image in the first image after binary conversion treatment.
Above-mentioned preferred version can improve the accuracy identifying operation further.
Preferably, described summit determines that unit includes:
Image determination unit, for according in described first image each pixel depth value and
Predetermined depth value range determines the figure connecting joint of each finger and the back of the hand from described first image
Picture, prospect and/or background image;
Image removal unit, is used for removing described prospect and/or background image;
Outline identification unit, identifies in the first image after eliminating prospect and/or background image
Go out the profile connecting joint of each finger and the back of the hand;
Vertex recognition unit, for identifying the summit in joint according to the curvature of described profile.
Foreground and background image is all got rid of by above-mentioned preferred version according to depth of view information, only retains the back of the hand
Anterior scene, then can identify joint in this scene further, thus can further improve identification
Efficiency.
Obviously, above-described embodiment is only for clearly demonstrating example, and not to embodiment party
The restriction of formula.For those of ordinary skill in the field, the most also may be used
To make other changes in different forms.Here without also all of embodiment being given
With exhaustive.And the obvious change thus extended out or variation are created still in this utility model
Protection domain among.
Claims (8)
1. a wrist equipment, it is characterised in that including:
Wrist strap;
First camera head, is arranged on described wrist strap;
Second camera head, is arranged on described wrist strap and relative with described first camera head, and
Direction pointed by described second camera head lens is identical with described first camera head;
Processor, for the hand figure gathering described first camera head and described second camera head
As processing.
Wrist equipment the most according to claim 1, it is characterised in that described first camera head
For shooting the first image along wrist to the back of the hand direction, described second camera head is for along described wrist
Shoot the second image to palm of the hand direction, described processor is used for obtaining described first image and the second image,
Determine the direction residing for finger according to described first image, determine hands according to the direction residing for described finger
Refer to region residing in described second image.
Wrist equipment the most according to claim 1 and 2, it is characterised in that described wrist equipment
For intelligent watch, described processor is arranged in dial plate, and described first camera head is arranged to be taken the photograph with second
As device is separately positioned at dial plate and on watchband, the camera head being arranged on watchband and described process
Device is connected by the connection member being arranged in watchband.
Wrist equipment the most according to claim 3, it is characterised in that described connection member is soft
Property circuit board.
5. a wrist equipment, it is characterised in that including:
Wrist strap;
First camera head, is arranged on described wrist strap;
Second camera head, is arranged on described wrist strap and relative with described first camera head, and
Direction pointed by described second camera head lens is identical with described first camera head;
First processor, for processing the hand images of described first camera head collection;
Second processor, for the result according to described first processor to described second shooting dress
The hand images putting collection processes.
Wrist equipment the most according to claim 5, it is characterised in that
Described first camera head is for shooting the first image along wrist to the back of the hand direction;
Described second camera head is for shooting the second image along described wrist to palm of the hand direction;
Described first processor is for determining the direction residing for finger according to described first image;
According to the direction residing for described finger, described second processor is for determining that finger is at described second figure
Region residing in Xiang.
7. according to the wrist equipment described in claim 5 or 6, it is characterised in that described wrist equipment
It is separately positioned at dial plate and on watchband for intelligent watch, described first processor and the second processor,
Described first camera head and the second camera head are separately positioned at dial plate and on watchband, are arranged on table
Processor on band is connected by the connection member being arranged in watchband with the processor being arranged in dial plate
Connect.
Wrist equipment the most according to claim 7, it is characterised in that described connection member is soft
Property circuit board.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201521139346.6U CN205485915U (en) | 2015-12-31 | 2015-12-31 | Wrist formula equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201521139346.6U CN205485915U (en) | 2015-12-31 | 2015-12-31 | Wrist formula equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN205485915U true CN205485915U (en) | 2016-08-17 |
Family
ID=56663229
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201521139346.6U Expired - Fee Related CN205485915U (en) | 2015-12-31 | 2015-12-31 | Wrist formula equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN205485915U (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017113793A1 (en) * | 2015-12-31 | 2017-07-06 | 北京体基科技有限公司 | Method and apparatus for determining area of finger in image, and a wrist-type device |
CN107450672A (en) * | 2017-09-19 | 2017-12-08 | 曾泓程 | A kind of wrist intelligent apparatus of high discrimination |
CN114451641A (en) * | 2022-01-05 | 2022-05-10 | 云码智能(海南)科技有限公司 | Intelligent bracelet, auxiliary welding device and method |
-
2015
- 2015-12-31 CN CN201521139346.6U patent/CN205485915U/en not_active Expired - Fee Related
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017113793A1 (en) * | 2015-12-31 | 2017-07-06 | 北京体基科技有限公司 | Method and apparatus for determining area of finger in image, and a wrist-type device |
CN106933341A (en) * | 2015-12-31 | 2017-07-07 | 北京体基科技有限公司 | It is a kind of to determine the method in region, device and wrist equipment residing for finger in the picture |
CN106933341B (en) * | 2015-12-31 | 2024-04-26 | 北京体基科技有限公司 | Method and device for determining region of finger in image and wrist type equipment |
CN107450672A (en) * | 2017-09-19 | 2017-12-08 | 曾泓程 | A kind of wrist intelligent apparatus of high discrimination |
CN107450672B (en) * | 2017-09-19 | 2024-03-29 | 曾泓程 | Wrist type intelligent device with high recognition rate |
CN114451641A (en) * | 2022-01-05 | 2022-05-10 | 云码智能(海南)科技有限公司 | Intelligent bracelet, auxiliary welding device and method |
CN114451641B (en) * | 2022-01-05 | 2022-10-14 | 云码智能(海南)科技有限公司 | Intelligent bracelet, auxiliary welding device and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106933340B (en) | Gesture motion recognition method, control method and device and wrist type equipment | |
CN107949863B (en) | Authentication device and authentication method using biometric information | |
CN106133752B (en) | Eye gaze tracking | |
CN107438854B (en) | System and method for performing fingerprint-based user authentication using images captured by a mobile device | |
KR100847136B1 (en) | Method and Apparatus for Shoulder-line detection and Gesture spotting detection | |
EP3225154A2 (en) | Gaze detection apparatus and gaze detection method | |
CN109829446A (en) | Eye fundus image recognition methods, device, electronic equipment and storage medium | |
CN107004114A (en) | Blood-vessel image filming apparatus and individual authentication system | |
CN103324284A (en) | Mouse control method based on face and eye detection | |
KR20180138300A (en) | Electronic device for providing property information of external light source for interest object | |
CN102402680A (en) | Hand and indication point positioning method and gesture confirming method in man-machine interactive system | |
CN101271517A (en) | Face region detecting device, method, and computer readable recording medium | |
CN205485072U (en) | Wear -type display device | |
CN205485915U (en) | Wrist formula equipment | |
JP2007272435A (en) | Face feature extraction device and face feature extraction method | |
CN111563435A (en) | Sleep state detection method and device for user | |
CN106933341B (en) | Method and device for determining region of finger in image and wrist type equipment | |
CN104966300A (en) | Bearing roller image detection system, method and image detection device | |
CN102662470B (en) | A kind of method and system realizing eye operation | |
CN104484654B (en) | Anti- drowned recognition methods based on pattern-recognition and fingerprint matching location algorithm | |
CN104808776A (en) | Device and method for detecting continuous attaching of head-wearing intelligent device on human body | |
CN108520221B (en) | Method, apparatus, storage medium and the terminal device of figure identification | |
CN104809371A (en) | Device and method for determining validity of authentication information of head-wearing intelligent device | |
CN205608659U (en) | Wrist formula equipment | |
CN110598635B (en) | Method and system for face detection and pupil positioning in continuous video frames |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160817 |