CN108549878A - Hand detection method based on depth information and system - Google Patents
Hand detection method based on depth information and system Download PDFInfo
- Publication number
- CN108549878A CN108549878A CN201810391268.0A CN201810391268A CN108549878A CN 108549878 A CN108549878 A CN 108549878A CN 201810391268 A CN201810391268 A CN 201810391268A CN 108549878 A CN108549878 A CN 108549878A
- Authority
- CN
- China
- Prior art keywords
- hand
- depth image
- normalized
- image
- selection area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 32
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 28
- 238000012805 post-processing Methods 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 14
- 230000001629 suppression Effects 0.000 claims abstract description 10
- 238000010606 normalization Methods 0.000 claims description 6
- 230000036544 posture Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 230000010339 dilation Effects 0.000 claims description 3
- 230000003628 erosive effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 description 4
- 230000001537 neural effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a kind of hand detection method and system based on depth information.Including：Obtain the current depth image of human body；According to current depth image, initial position co-ordinates of the hand in current depth image are marked；Current depth image is normalized；According to the current depth image after normalized, it is based on preset multilayer convolutional neural networks model, obtains including each selection area that hand detects；Non-maxima suppression operation is carried out according to each selection area, obtains optimal selection area；Post processing of image is carried out to optimal selection area, obtains final position coordinate of the hand in current depth image.The hand detection method based on depth information of the present invention, the related depth map detection hand method of tradition is eliminated to limit hand in the condition of camera forefront, the position of hand can accurately be found again simultaneously, by non-maxima suppression operation and post processing of image, the positional precision in the hand centre of the palm can be further promoted.
Description
Technical field
The present invention relates to hand detection technique field, more particularly to a kind of hand detection method and one based on depth information
Hand detecting system of the kind based on depth information.
Background technology
With the continuous development of new interaction technique and application, especially AR (augmented reality) and VR's (virtual reality) is fast
Speed development, gesture the relevant technologies are considered as next-generation new most representative interaction technique.It may be implemented contactless long-range
Human-computer interaction.In smart home field, intelligent appliance or robot can be controlled and be ordered by gesture；It is adjacent in VR and AR
Real experiences true to nature can be reached in domain, playing in teaching process, greatly enhancing user experience etc..All hands
Gesture interaction technique is directed to hand detection algorithm.It is enterprising that general common hand detection algorithm is mainly based upon 2D cromograms
It is hand position that row, which detects or finds closest approach region acquiescence by traditional image processing method on depth map,
Or these methods are completely dependent on Pixel Information, poor anti jamming capability or there is certain limitation to hand position region.
When human hand scope of activities is larger, often detect inaccurate.
Invention content
The present invention is directed at least solve one of the technical problems existing in the prior art, it is proposed that one kind being based on depth information
Hand detection method and a kind of hand detecting system based on depth information.
To achieve the goals above, the first aspect of the present invention provides a kind of hand detection side based on depth information
Method, including：
Step S120, the current depth image of human body is obtained；
Step S130, according to the current depth image, initial bit of the hand in the current depth image is marked
Set coordinate；
Step S140, the current depth image is normalized；
Step S150, according to the current depth image after normalized, it is based on preset multilayer convolutional neural networks mould
Type, obtain include hand detection each selection area；
Step S160, non-maxima suppression operation is carried out according to each selection area, obtains optimal selection area；
Step S170, post processing of image is carried out to the optimal selection area, obtains hand in the current depth figure
Final position coordinate as in.
Optionally, the method further includes：
S110：The step of updating preset multilayer convolutional neural networks model.
Optionally, the step S110 includes：
Obtain each depth image of the hand of human body, wherein each depth image includes the depth map of the various postures of hand
Picture；
According to each depth image, initial position co-ordinates of the hand in corresponding each depth image are marked；
Each depth image is normalized；
Each depth image after normalized is inputted into convolutional neural networks model, is trained, until meeting iteration
Number or loss convergence, complete to update the preset multilayer convolutional neural networks model.
Optionally, described the step of each depth image is normalized, includes：
Normalized is made in preset depth bounds [- 1,1] or [0,1] to each depth image.
Optionally, described to include to the optimal selection area progress post processing of image：
At least one of smothing filtering, dilation erosion and contour detecting.
The second aspect of the present invention provides a kind of hand detecting system based on depth information, including：
Acquisition module, the current depth image for obtaining human body；
Mark module, for according to the current depth image, it is first in the current depth image to mark hand
Beginning position coordinates；
Module is normalized, for the current depth image to be normalized；
Chosen module, for according to the current depth image after normalized, being based on preset multilayer convolutional Neural net
Network model, obtain include hand detection each selection area；
Assessment module obtains optimal selection area for carrying out non-maxima suppression operation according to each selection area；
Image processing module obtains hand and works as described for carrying out post processing of image to the optimal selection area
Final position coordinate in preceding depth image.
Optionally, further include：
Update module, for updating preset multilayer convolutional neural networks model.
Optionally, the acquisition module is additionally operable to obtain each depth image of the hand of human body, wherein each depth map
As the depth image of the various postures including hand；
The mark module is additionally operable to, according to each depth image, it is first in corresponding each depth image to mark hand
Beginning position coordinates；
The normalization module is additionally operable to that each depth image is normalized；
The update module is carried out for each depth image after normalized to be inputted convolutional neural networks model
Training is completed to update the preset multilayer convolutional neural networks model until meeting iterations or loss convergence.
Optionally, the normalization module is used for each depth image in preset depth bounds [- 1,1]
Or make normalized in [0,1].
Optionally, the acquisition module includes depth camera or depth cameras.
The hand detection method based on depth information of the present invention eliminates the related depth map detection hand method pair of tradition
Hand must be limited in the condition of camera forefront, while can accurately find the position (including both hands) of hand again, by non-
Maximum inhibits operation and post processing of image, can further promote the positional precision in the hand centre of the palm.
The hand detecting system based on depth information of the present invention eliminates the related depth map detection hand method pair of tradition
Hand must be limited in the condition of camera forefront, while can accurately find the position (including both hands) of hand again, by non-
Maximum inhibits operation and post processing of image, can further promote the positional precision in the hand centre of the palm.
Description of the drawings
Attached drawing is to be used to provide further understanding of the present invention, an and part for constitution instruction, with following tool
Body embodiment is used to explain the present invention together, but is not construed as limiting the invention.In the accompanying drawings：
Fig. 1 is the flow chart of the hand detection method based on depth information in first embodiment of the invention；
Fig. 2 is the structural schematic diagram of the hand detecting system based on depth information in second embodiment of the invention.
Reference sign
100：Hand detecting system based on depth information；
110：Acquisition module；
120：Mark module；
130：Normalize module；
140：Chosen module；
150：Assessment module；
160：Image processing module
170：Update module.
Specific implementation mode
The specific implementation mode of the present invention is described in detail below in conjunction with attached drawing.It should be understood that this place is retouched
The specific implementation mode stated is merely to illustrate and explain the present invention, and is not intended to restrict the invention.
With reference to figure 1, the first aspect of the present invention is related to a kind of hand detection method S100 based on depth information, including：
Step S120, the current depth image of human body is obtained.
Specifically, in this step, depth camera or depth cameras even depth vision facilities can be utilized to obtain
The current depth image of human body.
Step S130, according to the current depth image, initial bit of the hand in the current depth image is marked
Set coordinate.
It should be noted that for how to mark initial position co-ordinates of the hand in the current depth image not
Specific restriction is made, for example, can be determined by the depth information of each pixel in depth image.It is, of course, also possible to
The calibration to hand position coordinate is realized according to other modes.
Step S140, the current depth image is normalized.
Step S150, according to the current depth image after normalized, it is based on preset multilayer convolutional neural networks mould
Type, obtain include hand detection each selection area.
It should be noted that preset multilayer convolutional neural networks model roughly corresponds to sorter model, can incite somebody to action
Current depth image after normalized substitutes into preset multilayer convolutional neural networks model, that is, is equivalent to substitution
In sorter model, for the current depth image, each of hand detection can be determined according to the output result of sorter model
Selection area.
Step S160, non-maxima suppression operation is carried out according to each selection area, obtains optimal selection area.
Step S170, post processing of image is carried out to the optimal selection area, obtains hand in the current depth figure
Final position coordinate as in.
In this step, the final position coordinate of the hand obtained is compared with the initial position co-ordinates of hand, most final position
Setting coordinate can be more accurate.
The hand detection method S100 based on depth information in the present embodiment eliminates the related depth map detection hand of tradition
Portion's method must limit hand in the condition of camera forefront, while the position that can accurately find hand again is (including double
Hand), by non-maxima suppression operation and post processing of image, it can further promote the positional precision in the hand centre of the palm.
Optionally, as shown in Figure 1, the method further includes：
S110：The step of updating preset multilayer convolutional neural networks model.
Specifically, step S110 includes：
Obtain each depth image of the hand of human body, wherein each depth image includes the depth map of the various postures of hand
Picture.
According to each depth image, initial position co-ordinates of the hand in corresponding each depth image are marked.
Each depth image is normalized.
Each depth image after normalized is inputted into convolutional neural networks model, is trained, until meeting iteration
Number or loss convergence, complete to update the preset multilayer convolutional neural networks model.
The hand detection method S100 based on depth information in the present embodiment, can be to preset multilayer convolutional Neural net
Network model is updated, that is to say, that can be trained to preset multilayer convolutional neural networks model, so as into one
Step accurately finds the position (including both hands) of hand, and then can further promote the positional precision in the hand centre of the palm.
Optionally, described the step of each depth image is normalized, includes：
Normalized is made in preset depth bounds [- 1,1] or [0,1] to each depth image.Certainly,
It can also be normalized in other preset depth bounds according to actual needs.
The hand detection method S100 based on depth information in the present embodiment, further can accurately find the position of hand
(including both hands), and then can further promote the positional precision in the hand centre of the palm.
Optionally, described to include to the optimal selection area progress post processing of image：
At least one of smothing filtering, dilation erosion and contour detecting.
The second aspect of the present invention is wrapped as shown in Fig. 2, providing a kind of hand detecting system 100 based on depth information
It includes：
Acquisition module 110, the current depth image for obtaining human body；
Mark module 120, for according to the current depth image, marking hand in the current depth image
Initial position co-ordinates；
Module 130 is normalized, for the current depth image to be normalized；
Chosen module 140, for according to the current depth image after normalized, being based on preset multilayer convolutional Neural
Network model, obtain include hand detection each selection area；
Assessment module 150 obtains optimal selected area for carrying out non-maxima suppression operation according to each selection area
Domain；
Image processing module 160 obtains hand described for carrying out post processing of image to the optimal selection area
Final position coordinate in current depth image.
The hand detecting system 100 based on depth information in the present embodiment eliminates the related depth map detection hand of tradition
Portion's method must limit hand in the condition of camera forefront, while the position that can accurately find hand again is (including double
Hand), by non-maxima suppression operation and post processing of image, it can further promote the positional precision in the hand centre of the palm.
Optionally, further include：
Update module 170, for updating preset multilayer convolutional neural networks model.
Optionally, the acquisition module 110 is additionally operable to obtain each depth image of the hand of human body, wherein each depth
Image includes the depth image of the various postures of hand；
The mark module 120 is additionally operable to, according to each depth image, mark hand in corresponding each depth image
Initial position co-ordinates；
The normalization module 130, is additionally operable to that each depth image is normalized；
The update module 170, for each depth image after normalized to be inputted convolutional neural networks model, into
Row training is completed to update the preset multilayer convolutional neural networks model until meeting iterations or loss convergence.
The hand detecting system 100 based on depth information in the present embodiment, can be to preset multilayer convolutional Neural net
Network model is updated, that is to say, that can be trained to preset multilayer convolutional neural networks model, so as into one
Step accurately finds the position (including both hands) of hand, and then can further promote the positional precision in the hand centre of the palm.
Optionally, the normalization module 130, for each depth image preset depth bounds [- 1,
1] or in [0,1] make normalized.
Optionally, the acquisition module 110 includes depth camera or depth cameras.
It is understood that the principle that embodiment of above is intended to be merely illustrative of the present and the exemplary implementation that uses
Mode, however the present invention is not limited thereto.For those skilled in the art, in the essence for not departing from the present invention
In the case of refreshing and essence, various changes and modifications can be made therein, these variations and modifications are also considered as protection scope of the present invention.
Claims (10)
1. a kind of hand detection method based on depth information, which is characterized in that including：
Step S120, the current depth image of human body is obtained；
Step S130, it according to the current depth image, marks initial position of the hand in the current depth image and sits
Mark；
Step S140, the current depth image is normalized；
Step S150, according to the current depth image after normalized, it is based on preset multilayer convolutional neural networks model, is obtained
To each selection area detected including hand；
Step S160, non-maxima suppression operation is carried out according to each selection area, obtains optimal selection area；
Step S170, post processing of image is carried out to the optimal selection area, obtains hand in the current depth image
Final position coordinate.
2. hand detection method according to claim 1, which is characterized in that the method further includes：
S110：The step of updating preset multilayer convolutional neural networks model.
3. hand detection method according to claim 2, which is characterized in that the step S110 includes：
Obtain each depth image of the hand of human body, wherein each depth image includes the depth image of the various postures of hand；
According to each depth image, initial position co-ordinates of the hand in corresponding each depth image are marked；
Each depth image is normalized；
Each depth image after normalized is inputted into convolutional neural networks model, is trained, until meeting iterations
Or loss convergence, it completes to update the preset multilayer convolutional neural networks model.
4. hand detection method according to claim 3, which is characterized in that described that place is normalized to each depth image
The step of reason includes：
Normalized is made in preset depth bounds [- 1,1] or [0,1] to each depth image.
5. hand detection method as claimed in any of claims 1 to 4, which is characterized in that described to described optimal
Selection area carry out post processing of image include：
At least one of smothing filtering, dilation erosion and contour detecting.
6. a kind of hand detecting system based on depth information, which is characterized in that including：
Acquisition module, the current depth image for obtaining human body；
Mark module, for according to the current depth image, marking initial bit of the hand in the current depth image
Set coordinate；
Module is normalized, for the current depth image to be normalized；
Chosen module, for according to the current depth image after normalized, being based on preset multilayer convolutional neural networks mould
Type, obtain include hand detection each selection area；
Assessment module obtains optimal selection area for carrying out non-maxima suppression operation according to each selection area；
Image processing module obtains hand in the current depth for carrying out post processing of image to the optimal selection area
Spend the final position coordinate in image.
7. hand detecting system according to claim 6, which is characterized in that further include：
Update module, for updating preset multilayer convolutional neural networks model.
8. hand detecting system according to claim 7, which is characterized in that
The acquisition module is additionally operable to obtain each depth image of the hand of human body, wherein each depth image includes each of hand
The depth image of kind posture；
The mark module is additionally operable to mark initial bit of the hand in corresponding each depth image according to each depth image
Set coordinate；
The normalization module is additionally operable to that each depth image is normalized；
The update module, for by each depth image input convolutional neural networks model after normalized, being trained,
Until meeting iterations or loss convergence, complete to update the preset multilayer convolutional neural networks model.
9. hand detecting system according to claim 8, which is characterized in that the normalization module, for described each
Depth image makees normalized in preset depth bounds [- 1,1] or [0,1].
10. the hand detecting system according to any one of claim 6 to 9, which is characterized in that the acquisition module packet
Include depth camera or depth cameras.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810391268.0A CN108549878B (en) | 2018-04-27 | 2018-04-27 | Depth information-based hand detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810391268.0A CN108549878B (en) | 2018-04-27 | 2018-04-27 | Depth information-based hand detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108549878A true CN108549878A (en) | 2018-09-18 |
| CN108549878B CN108549878B (en) | 2020-03-24 |
Family
ID=63512809
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810391268.0A Active CN108549878B (en) | 2018-04-27 | 2018-04-27 | Depth information-based hand detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108549878B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109243248A (en) * | 2018-09-29 | 2019-01-18 | 南京华捷艾米软件科技有限公司 | A kind of virtual piano and its implementation based on 3D depth camera mould group |
| CN109696958A (en) * | 2018-11-28 | 2019-04-30 | 南京华捷艾米软件科技有限公司 | A kind of gestural control method and system based on depth transducer gesture identification |
| CN111462548A (en) * | 2019-01-21 | 2020-07-28 | 北京字节跳动网络技术有限公司 | Paragraph point reading method, device, equipment and readable medium |
| CN111459443A (en) * | 2019-01-21 | 2020-07-28 | 北京字节跳动网络技术有限公司 | Character point-reading method, device, equipment and readable medium |
| CN111462234A (en) * | 2020-03-27 | 2020-07-28 | 北京华捷艾米科技有限公司 | Position determination method and device |
| WO2021098666A1 (en) * | 2019-11-20 | 2021-05-27 | Oppo广东移动通信有限公司 | Hand gesture detection method and device, and computer storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999152A (en) * | 2011-09-09 | 2013-03-27 | 康佳集团股份有限公司 | Method and system for gesture recognition |
| US20160260260A1 (en) * | 2014-10-24 | 2016-09-08 | Usens, Inc. | System and method for immersive and interactive multimedia generation |
| CN106648103A (en) * | 2016-12-28 | 2017-05-10 | 歌尔科技有限公司 | Gesture tracking method for VR headset device and VR headset device |
| CN106778435A (en) * | 2016-11-30 | 2017-05-31 | 上海正雅齿科科技有限公司 | Feature extracting method based on Image neighborhood structure tensor equation |
| CN107292904A (en) * | 2016-03-31 | 2017-10-24 | 北京市商汤科技开发有限公司 | A kind of palm tracking and system based on depth image |
-
2018
- 2018-04-27 CN CN201810391268.0A patent/CN108549878B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999152A (en) * | 2011-09-09 | 2013-03-27 | 康佳集团股份有限公司 | Method and system for gesture recognition |
| US20160260260A1 (en) * | 2014-10-24 | 2016-09-08 | Usens, Inc. | System and method for immersive and interactive multimedia generation |
| CN107292904A (en) * | 2016-03-31 | 2017-10-24 | 北京市商汤科技开发有限公司 | A kind of palm tracking and system based on depth image |
| CN106778435A (en) * | 2016-11-30 | 2017-05-31 | 上海正雅齿科科技有限公司 | Feature extracting method based on Image neighborhood structure tensor equation |
| CN106648103A (en) * | 2016-12-28 | 2017-05-10 | 歌尔科技有限公司 | Gesture tracking method for VR headset device and VR headset device |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109243248A (en) * | 2018-09-29 | 2019-01-18 | 南京华捷艾米软件科技有限公司 | A kind of virtual piano and its implementation based on 3D depth camera mould group |
| CN109696958A (en) * | 2018-11-28 | 2019-04-30 | 南京华捷艾米软件科技有限公司 | A kind of gestural control method and system based on depth transducer gesture identification |
| CN111462548A (en) * | 2019-01-21 | 2020-07-28 | 北京字节跳动网络技术有限公司 | Paragraph point reading method, device, equipment and readable medium |
| CN111459443A (en) * | 2019-01-21 | 2020-07-28 | 北京字节跳动网络技术有限公司 | Character point-reading method, device, equipment and readable medium |
| WO2021098666A1 (en) * | 2019-11-20 | 2021-05-27 | Oppo广东移动通信有限公司 | Hand gesture detection method and device, and computer storage medium |
| CN111462234A (en) * | 2020-03-27 | 2020-07-28 | 北京华捷艾米科技有限公司 | Position determination method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108549878B (en) | 2020-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108549878A (en) | Hand detection method based on depth information and system | |
| CN109255813B (en) | Man-machine cooperation oriented hand-held object pose real-time detection method | |
| US10043308B2 (en) | Image processing method and apparatus for three-dimensional reconstruction | |
| CN105930767B (en) | A kind of action identification method based on human skeleton | |
| CN103226387B (en) | Video fingertip localization method based on Kinect | |
| CN105389539B (en) | A kind of three-dimension gesture Attitude estimation method and system based on depth data | |
| CN107103613B (en) | A kind of three-dimension gesture Attitude estimation method | |
| JP5877053B2 (en) | Posture estimation apparatus and posture estimation method | |
| CN106055091A (en) | Hand posture estimation method based on depth information and calibration method | |
| CN103544472B (en) | A kind of processing method and processing unit based on images of gestures | |
| CN112001859B (en) | Face image restoration method and system | |
| CN104035557B (en) | Kinect action identification method based on joint activeness | |
| CN107813310A (en) | One kind is based on the more gesture robot control methods of binocular vision | |
| CN103679175A (en) | Fast 3D skeleton model detecting method based on depth camera | |
| CN112200771B (en) | Height measurement method, device, equipment and medium | |
| CN105930795A (en) | Walking state identification method based on space vector between human body skeleton joints | |
| CN106808472A (en) | Location of workpiece posture computing device and handling system | |
| CN101393497A (en) | Multi-point touch method based on binocular stereo vision | |
| CN113393524B (en) | Target pose estimation method combining deep learning and contour point cloud reconstruction | |
| WO2022174594A1 (en) | Multi-camera-based bare hand tracking and display method and system, and apparatus | |
| CN111178170B (en) | Gesture recognition method and electronic equipment | |
| CN103942524A (en) | Gesture recognition module and gesture recognition method | |
| JP6075888B2 (en) | Image processing method, robot control method | |
| CN104123562A (en) | Human body face expression identification method and device based on binocular vision | |
| CN113971835A (en) | Control method and device of household appliance, storage medium and terminal 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Hand detection method and system based on depth information Effective date of registration: 20220311 Granted publication date: 20200324 Pledgee: Industrial Bank Co.,Ltd. Beijing West Railway Station sub branch Pledgor: BeiJing Hjimi Technology Co.,Ltd. Registration number: Y2022110000054 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PP01 | Preservation of patent right |
Effective date of registration: 20231101 Granted publication date: 20200324 |
|
| PP01 | Preservation of patent right |