CN109948435A - Sitting posture prompting method and device - Google Patents

Sitting posture prompting method and device Download PDF

Info

Publication number
CN109948435A
CN109948435A CN201910101151.9A CN201910101151A CN109948435A CN 109948435 A CN109948435 A CN 109948435A CN 201910101151 A CN201910101151 A CN 201910101151A CN 109948435 A CN109948435 A CN 109948435A
Authority
CN
China
Prior art keywords
sitting posture
target
image
texture image
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
CN201910101151.9A
Other languages
Chinese (zh)
Inventor
胡正
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.)
Shenzhen Orbbec Co Ltd
Original Assignee
Shenzhen Orbbec 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 Shenzhen Orbbec Co Ltd filed Critical Shenzhen Orbbec Co Ltd
Priority to CN201910101151.9A priority Critical patent/CN109948435A/en
Publication of CN109948435A publication Critical patent/CN109948435A/en
Pending legal-status Critical Current

Links

Abstract

The present invention provides a kind of sitting posture prompting method, includes the following steps: the texture image and depth image that acquire target;Judge whether the target is in learning state according to the texture image and/or depth image;When the target is in learning state, the texture image and/or depth image are handled to obtain the sitting posture of the target;Judge whether the sitting posture complies with standard sitting posture, when the sitting posture is not inconsistent standardization sitting posture, issues related prompting or execute relevant operation.The present invention also provides corresponding sitting posture reminders, and target is carried out sitting posture identification and reminded to be effectively improved health problem caused by incorrect sitting-pose using depth image, texture image.

Description

Sitting posture prompting method and device
Technical field
The present invention relates to posture alignment technique field more particularly to a kind of sitting posture prompting method and devices.
Background technique
Studies have shown that current student that must be near-sighted is more and more, the basic reason for causing child's myopia is to be chronically at In incorrect sitting-pose.Do not rectify for example, child during doing the homework, can usually generate sitting posture, writing posture is incorrect, sighting distance It crosses close, visual angle not just, the problem of vision chronic fatigue, if things go on like this will result in the consequence of myopia, brought to study, life all It is how inconvenient and worried, in addition, being chronically in the state of incorrect sitting-pose, also easily causes spinal curvature or lateral bending to deform, cause Crookback seriously affects psychosomatic development.
And in real life, achieve the purpose that form outside healthy sitting posture habit except through artificially observing and correcting, also Have and compares typical method and have based on wearable device method, based on artificial intelligence approach and based on the method for range image analysis. But otherwise cost is very high, however effect is undesirable, otherwise it is inconvenient to use, it is difficult to effectively promote.
Therefore, a kind of effective sitting posture prompting method and device is also lacked, in the prior art with effective protection student Eyesight and health.
Summary of the invention
To solve the above problems, the present invention proposes a kind of sitting posture prompting method, comprising: acquire the texture image and depth of target Spend image;Judge whether the target is in learning state according to the texture image and/or depth image;At the target When learning state, the texture image and/or depth image are handled to obtain the sitting posture of the target;Described in judgement Whether sitting posture complies with standard sitting posture, when the sitting posture is not inconsistent standardization sitting posture, issues related prompting or executes relevant operation.
In one of the embodiments, the sitting posture include body posture, movement, sighting distance, expression, in hand motion extremely Few one kind.
The judgement of the learning state includes persistently coagulating to learning object to the target in one of the embodiments, It is detected between apparent time.
In one of the embodiments, the method further includes: calculate preset time period in each at times in The ratio of the sitting posture total quantity of the target in the quantity and the preset time period of the sitting posture for not being inconsistent standardization sitting posture, with The sitting posture for obtaining target changes with time trend within a preset period of time.
In one of the embodiments, the method further includes: between the sitting posture to current goal and standard sitting posture Difference current sitting posture is evaluated as Appreciation gist.
In one of the embodiments, the method further includes: according to the texture image and/or depth image pair Desktop article is identified to judge messy degree.
The present invention also proposes a kind of sitting posture reminder, comprising: acquisition equipment, for acquiring the texture image and depth of target Spend image;Output equipment is reminded for issuing;Processor is connected with the acquisition equipment, output equipment, receives the texture Image and/or the depth image, and judge whether the target is according to the texture image and/or the depth image Learning state;And when the target is in learning state, the texture image and/or depth image are handled to obtain Take the sitting posture of the target;Judge whether the sitting posture complies with standard sitting posture, when the sitting posture is not inconsistent standardization sitting posture, issues Relevant operation is reminded or executed to correlation.
In one of the embodiments, the sitting posture include body posture, movement, sighting distance, expression, in hand motion extremely Few one kind.
The judgement of the learning state includes persistently coagulating to learning object to the target in one of the embodiments, It is detected between apparent time.
The processor further executes in one of the embodiments: not meeting mark described in calculating in preset time period The ratio of the sitting posture total quantity of the target in the quantity of the sitting posture of quasi- sitting posture and the preset time period, to obtain the seat of target Appearance changes with time trend.
The processor further executes in one of the embodiments: to the sitting posture of current goal and standard sitting posture it Between difference current sitting posture is evaluated as Appreciation gist.
The processor further executes in one of the embodiments: according to the texture image and/or depth image Desktop article is identified to judge messy degree.
Sitting posture prompting method and device provided by the invention, by the texture information and/or depth information of acquisition to target Sitting posture be monitored, when the sitting posture of target is not inconsistent standardization sitting posture, target is reminded in time, is avoided when target exists Do not have under personal monitoring for a long time in incorrect sitting-pose, to affect vision and health.In addition, sitting posture prompting side provided by the invention Whether method and device are in learning state first with the image information identification active user of acquisition, if so, again to the sitting posture of target It is identified, it can be to avoid the false alert as caused by the abnormal sitting postures such as rest.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of sitting posture reminder in one embodiment of the invention;
Fig. 2 is the structural schematic diagram of sitting posture reminder in another embodiment of the present invention;
Fig. 3 is the structural schematic diagram of sitting posture prompting system in one embodiment of the invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention In attached drawing, technical solution in the embodiment of the present invention is explicitly described, it is clear that described embodiment is the present invention A part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not having Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
Fig. 1 is please referred to, Fig. 1 is the structural schematic diagram of sitting posture reminder 10 in one embodiment of the invention.Device 10 wraps Acquisition equipment 100, output equipment 110 are included, and the processor 120 being connected respectively with acquisition equipment 100, output equipment 110.Dress It can also include some supporting structures, functional module etc. that 10, which are set, according to its form difference, such as in some embodiments, device 10 can be the desk lamp with sitting posture prompting function, desk, robot etc..
Acquisition equipment 100 is used to acquire the depth image and texture image of target.Wherein, acquisition equipment 100 can be base In structure light, binocular, TOF (time flight algorithm) technology depth camera, in one embodiment, acquisition equipment 100 include Structure light depth camera and texture camera, with sampling depth image and texture image.The acquisition frequency of depth image and texture image Rate can be the same or different, and be set accordingly according to specific functional requirement, for example be adopted with the frequency translation of 60FPS Collect depth image and texture image, finally obtains the depth image and texture image of 30FPS respectively.Texture image includes visible Light image and black light image, it is seen that light image includes color image, White-light image;Black light image includes near-infrared figure Picture, thermal infrared images, radioscopic image etc..
In one embodiment, the 100 collected depth image of institute of acquisition equipment is further registrated with texture image, i.e., Find the corresponding relationship in depth image and texture image between each pixel by registration Algorithm, with eliminate therebetween due to Parallax caused by the difference of spatial position.Registration can be completed by application specific processor in acquisition equipment 100, can also be by outside Processor is completed, for example is completed by processor 120.Multiple functions may be implemented in depth image and texture image after registered, For example object detection and identification can be accelerated.In one embodiment, object detection first can be carried out to texture image, recycled Pixel corresponding relationship directly orients the object in depth image, once calculates the object detection of depth image it is possible thereby to reduce Method;In one embodiment, it first can carry out object detection by the texture image to previous frame, carry out depth image in next frame and adopt When collection, the depth value of the pixel on object position is only obtained, i.e., the depth image of object parts is only exported, to reduce depth Image zooming-out algorithm calculation amount is spent, while reducing data transfer bandwidth.Conversely, object detection first can also be carried out to depth image Or identification, recycle pixel corresponding relationship to accelerate detection or identification to object in texture image.
Processor 120 is used to receive the depth image and/or texture image that acquisition equipment 100 acquires, and according to the line Reason image and/or depth image judge whether target is in learning state, when the target is in learning state, to the line Reason image and/or depth image are further processed to obtain the sitting posture of the target, secondly judge whether the sitting posture accords with Standardization sitting posture then issues related prompting or executes relevant operation when the sitting posture is not inconsistent standardization sitting posture.Optionally, exist In one embodiment, processor 120 can first identify the facial expression of target according to texture image, with the learning state to target Tentatively judged.When determining that target is in learning state, processor 120 is calculated and is handled to depth image again, with It obtains the sitting posture of the target and judges whether the sitting posture complies with standard sitting posture, when the sitting posture is not inconsistent standardization sitting posture, Prompting instruction is then executed, such as in one embodiment, processor 120 generates related remind and instructs and by the output equipment 110 output alerting signals are to remind the target.
In some embodiments, the judgement that processor 120 carries out learning state includes: Face datection, recognition of face, sight Detection, learning object detection and etc..For example whether human eye sight is persistently stared within a certain period of time where learning object Region detected, if continue gaze duration be more than a certain threshold value, then it is assumed that be in learning state.Learning object can be book The equipment such as sheet, e-book, computer, plate are also possible in the study such as presented learning Content, such as text, picture, video Hold.In one embodiment, it can also include the identification and judgement to target expression that processor 120, which carries out the judgement of learning state, Deng.
In some embodiments, it includes the inspection to intended body posture and/or movement that processor 120, which carries out the judgement of sitting posture, It surveys and identification further includes in one embodiment the detection and identification to human eye and learning object distance (sighting distance).In a reality Apply in example, to the detection of body posture and movement and identification can based on texture image and/or depth image to Whole Body or Person's upper part of the body artis (skeleton) detects, and according to the relative positional relationship pair in framework information between head part and trunk Current sitting posture is identified, further, detection and knowledge to movement then may be implemented to variation of the posture in time series Not.It is understood that in some cases, when body integrally leans forward or swings back, although the opposite position on head and trunk Set correct, but sight is close to or far from learning object, therefore, it is necessary to further be detected to sighting distance, in conjunction with body posture, Sighting distance can more accurately reflect whether the sitting posture of current goal is correct.It is understood that in some embodiments, sitting posture is also It may include other features, such as human face expression, hand motion etc. except body posture, sighting distance.
The sitting posture for the target that processor 120 further will acquire is compared with standard sitting posture, when the sitting posture of monitoring objective In preset standard sitting posture threshold range, then standard sitting posture is regarded as, otherwise, issues related prompting or execute relevant operation, Such as it generates dependent instruction and the target is reminded by the output equipment 110.
Optionally, in one embodiment, output equipment can be in display panel, buzzer, microphone or loudspeaker One or more.For example, processor 120 can be generated related remind and instruct when the sitting posture of target is not inconsistent standardization sitting posture, To control the display panel the related prompting of display, or control buzzer, microphone or loudspeaker issue related voice to remind target Sitting posture is adjusted, the combination of a variety of alerting patterns is also possible to.
In addition, reminding instruction other than it can be directly output to current goal, can also be held according to sitting posture testing result The some other relevant operations of row, for example export to cloud, other terminals to perform corresponding processing, for example data save, statistics And real time monitoring etc..
It is understood that processor 120 can be the single processor (such as ARM, CPU) in device 10 The combination of various processor be can be (such as while comprising embedded microprocessor (MPU) and embedded microcontroller (MCU)), it is also possible to the (not shown)s such as the cloud processor being independently arranged with device 10.
Referring to figure 2., device 10 can also include the memory being connected with processor 120 in one of the embodiments, 130.Memory 130 is used to store the sitting posture of target.In this way, processor 120 can be calculated according to the sitting posture of stored target Change with time trend to its sitting posture, or calculate in preset time period the quantity of the sitting posture for not being inconsistent standardization sitting posture with The ratio of the sitting posture total quantity of the target in the preset time period, to obtain " fraction defective " of the sitting posture of target.It can be with Fraction defective is calculated according to each " fraction defective " at times in default total period to change with time trend.For example, The quantity and target of the sitting posture for not being inconsistent standardization sitting posture in each small period can be calculated with 1 hour for a period Sitting posture total quantity ratio, changed with time trend with obtaining the sitting posture of target, and further judged according to variation tendency The learning state of target.It is understood that memory 130 can be located in device 10, it is also possible to cloud memory.
Optionally, in one embodiment, processor 120 can also in real time to the sitting posture of current goal and standard sitting posture it Between difference (such as marking) is evaluated to current sitting posture as Appreciation gist.For example, it is assumed that standard sitting posture is set as 10 points, When the sitting posture of current goal is in preset standard sitting posture threshold range, then 10 scores are made to current sitting posture, and sit according to current Appearance and the deviation size of standard sitting posture carry out corresponding deduction, it is to be understood that deviation is bigger, and score is lower.In addition, processing Device 120 can remind target evaluation result (i.e. score) by output equipment, for example, passing through display panel for score Show or carries out voice reminder by voice device (microphone, loudspeaker);Or statistics certain time (such as daily) Evaluation result in section is changed with time trend with monitoring sitting posture, to further obtain the learning state of target.
Optionally, in one embodiment, when occurring more people in scene, processor 120 will be identified from depth image Multiple human bodies, and according to the obtained depth information of calculating, choose nearest people with a distance from acquisition equipment as identification object or Person is using the people of field of view center as identification object.
Referring to figure 3., the present invention also provides a kind of sitting posture prompting systems 30 comprising sitting posture reminder 10 and with it is described The connected mobile terminal 20 of the communication of sitting posture reminder 10, the mobile terminal 20 is for receiving the sitting posture reminder transmission Data, to realize long-range monitoring to target.Wherein, device 10 can pass through interface (not shown) and mobile terminal 20 Carry out it is connected, to further realize transmission of data, such as I/O interface, network interface, USB interface, WIFI interface etc..
It is understood that the processor 120 in device 10 can adopt various monitoring data, such as acquisition equipment 100 The depth image and/or texture image of collection are sent to mobile terminal 20, can also not be inconsistent standardization for described in preset time period The ratio of the sitting posture total quantity of the monitoring objective is sent to mobile terminal in the sitting posture quantity and the preset time period of sitting posture 20, or the data such as the evaluation result evaluated current sitting posture can also be sent to mobile terminal 20, to realize to institute State the long-range monitoring of monitoring objective.
Optionally, in one embodiment, when acquisition the continuous N frame of equipment 100 acquisition image in all do not recognize mesh Mark, then judge that target has been moved off, at this point, processor 120 can be according to the depth image and/or texture image received to table Face article is identified to judge messy degree, and counts time departure, when article is messy is more than certain time, is then sent and is mentioned It wakes up, such as sends short message, mail, CRBT waits until on mobile terminal, to realize the long-range monitoring to the monitoring objective.
Optionally, in one embodiment, mobile terminal can be in mobile phone, tablet computer or intelligent wearable device It is at least one.
Sitting posture prompting method and device provided by the invention, by the texture information of acquisition and depth information to the seat of target Appearance is monitored, and when the sitting posture of target is not inconsistent standardization sitting posture, is reminded in time target, is avoided when target is not having Under personal monitoring for a long time be in sitting posture, thus affect vision and health.In addition, sitting posture prompting method provided by the invention and dress It sets, whether learning state is in first with the texture information identification active user of acquisition, if so, knowing again to the sitting posture of target It not, can be to avoid the false alert as caused by the abnormal sitting postures such as rest.
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be said that Specific implementation of the invention is only limited to these instructions.For those skilled in the art to which the present invention belongs, it is not taking off Under the premise of from present inventive concept, several equivalent substitute or obvious modifications can also be made, and performance or use is identical, all answered When being considered as belonging to protection scope of the present invention.

Claims (10)

1. a kind of sitting posture prompting method, which comprises the steps of:
Acquire the texture image and depth image of target;
Judge whether the target is in learning state according to the texture image and/or depth image;
When the target is in learning state, the texture image and/or depth image are handled to obtain the mesh Target sitting posture;
Judge whether the sitting posture complies with standard sitting posture, when the sitting posture is not inconsistent standardization sitting posture, issues related prompting or hold Row relevant operation.
2. sitting posture prompting method according to claim 1, which is characterized in that the sitting posture includes body posture, movement, view Away from, at least one of expression, hand motion.
3. sitting posture prompting method according to claim 1, which is characterized in that the judgement of the learning state includes to described Target detects the lasting gaze duration of learning object.
4. sitting posture prompting method according to claim 1, which is characterized in that the method also includes:
Calculate in preset time period the quantity of each sitting posture for not being inconsistent standardization sitting posture at times and it is described each The ratio of the sitting posture total quantity of the target, is changed with time within a preset period of time at times with obtaining the sitting posture of target Trend;
Or,
Difference between sitting posture to current goal and standard sitting posture evaluates current sitting posture as Appreciation gist.
5. sitting posture prompting method according to claim 1, which is characterized in that the method also includes:
Desktop article is identified according to the texture image and/or depth image to judge messy degree.
6. a kind of sitting posture reminder characterized by comprising
Equipment is acquired, for acquiring the texture image and depth image of target;
Output equipment is reminded for issuing;
Processor is connected with the acquisition equipment, output equipment, is used for: receiving the texture image and/or the depth map Picture, and judge whether the target is in learning state according to the texture image and/or the depth image;And
When the target is in learning state, the texture image and/or depth image are handled to obtain the mesh Target sitting posture;
Judge whether the sitting posture complies with standard sitting posture, when the sitting posture is not inconsistent standardization sitting posture, issues related prompting or hold Row relevant operation.
7. sitting posture reminder according to claim 6, which is characterized in that the sitting posture includes body posture, movement, view Away from, at least one of expression, hand motion.
8. sitting posture reminder according to claim 6, which is characterized in that the judgement of the learning state includes to described Target detects the lasting gaze duration of learning object.
9. sitting posture reminder according to claim 6, which is characterized in that the processor further includes executing:
Calculate the quantity with the target in the preset time period of the sitting posture for not being inconsistent standardization sitting posture in preset time period Sitting posture total quantity ratio, changed with time trend with obtaining the sitting posture of target;
Or,
Difference between sitting posture to current goal and standard sitting posture evaluates current sitting posture as Appreciation gist.
10. sitting posture reminder according to claim 6, which is characterized in that the processor further executes:
Desktop article is identified according to the texture image and/or depth image to judge messy degree.
CN201910101151.9A 2019-01-31 2019-01-31 Sitting posture prompting method and device Pending CN109948435A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910101151.9A CN109948435A (en) 2019-01-31 2019-01-31 Sitting posture prompting method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910101151.9A CN109948435A (en) 2019-01-31 2019-01-31 Sitting posture prompting method and device

Publications (1)

Publication Number Publication Date
CN109948435A true CN109948435A (en) 2019-06-28

Family

ID=67006734

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910101151.9A Pending CN109948435A (en) 2019-01-31 2019-01-31 Sitting posture prompting method and device

Country Status (1)

Country Link
CN (1) CN109948435A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110648509A (en) * 2019-09-25 2020-01-03 珠海格力电器股份有限公司 Method, device and system for generating prompt message
CN110889322A (en) * 2019-10-09 2020-03-17 深圳市九洲电器有限公司 Method for preventing sedentary sitting and related product
CN111515957A (en) * 2020-05-13 2020-08-11 暨南大学 Desktop robot system and desktop robot for sitting posture detection and language chat
CN111601088A (en) * 2020-05-27 2020-08-28 大连成者科技有限公司 Sitting posture monitoring system based on monocular camera sitting posture identification technology
WO2021138964A1 (en) * 2020-01-10 2021-07-15 鄢家厚 Read/write distance identification method based on smart watch
CN113591522A (en) * 2020-04-30 2021-11-02 百度在线网络技术(北京)有限公司 Image processing method, device and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107169483A (en) * 2017-07-12 2017-09-15 深圳奥比中光科技有限公司 Tasks carrying based on recognition of face
CN107609383A (en) * 2017-10-26 2018-01-19 深圳奥比中光科技有限公司 3D face identity authentications and device
CN109117705A (en) * 2018-06-14 2019-01-01 浙江凯耀照明股份有限公司 A kind of system and method carrying out sitting posture identification by desk lamp

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107169483A (en) * 2017-07-12 2017-09-15 深圳奥比中光科技有限公司 Tasks carrying based on recognition of face
CN107609383A (en) * 2017-10-26 2018-01-19 深圳奥比中光科技有限公司 3D face identity authentications and device
CN109117705A (en) * 2018-06-14 2019-01-01 浙江凯耀照明股份有限公司 A kind of system and method carrying out sitting posture identification by desk lamp

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110648509A (en) * 2019-09-25 2020-01-03 珠海格力电器股份有限公司 Method, device and system for generating prompt message
CN110889322A (en) * 2019-10-09 2020-03-17 深圳市九洲电器有限公司 Method for preventing sedentary sitting and related product
WO2021138964A1 (en) * 2020-01-10 2021-07-15 鄢家厚 Read/write distance identification method based on smart watch
CN113591522A (en) * 2020-04-30 2021-11-02 百度在线网络技术(北京)有限公司 Image processing method, device and storage medium
CN111515957A (en) * 2020-05-13 2020-08-11 暨南大学 Desktop robot system and desktop robot for sitting posture detection and language chat
CN111601088A (en) * 2020-05-27 2020-08-28 大连成者科技有限公司 Sitting posture monitoring system based on monocular camera sitting posture identification technology
CN111601088B (en) * 2020-05-27 2021-12-21 大连成者科技有限公司 Sitting posture monitoring system based on monocular camera sitting posture identification technology

Similar Documents

Publication Publication Date Title
CN109948435A (en) Sitting posture prompting method and device
Angelopoulos et al. Event based, near eye gaze tracking beyond 10,000 hz
US10635900B2 (en) Method for displaying gaze point data based on an eye-tracking unit
CN103838378B (en) A kind of wear-type eyes control system based on pupil identification positioning
CN102520796B (en) Sight tracking method based on stepwise regression analysis mapping model
CN105022981B (en) A kind of method, device and mobile terminal detecting human eye health state
CN108171218A (en) A kind of gaze estimation method for watching network attentively based on appearance of depth
CN104793741A (en) Imaging system and method for guiding eyeballs to trace virtual reality
CN102456137B (en) Sight line tracking preprocessing method based on near-infrared reflection point characteristic
CN103955272A (en) Terminal equipment user posture detecting system
CN104952221B (en) Myopia-proof intelligent desk lamp
US10843299B2 (en) Object recognition and presentation for the visually impaired
KR20120060978A (en) Method and Apparatus for 3D Human-Computer Interaction based on Eye Tracking
CN105095885B (en) A kind of detection method and detection device of human eye state
CN106981183A (en) Correcting sitting posture method and system
CN107260506B (en) 3D vision training system, intelligent terminal and head-mounted device based on eye movement
CN109766007A (en) A kind of the blinkpunkt compensation method and compensation device, display equipment of display equipment
CN109522887A (en) A kind of Eye-controlling focus method, apparatus, equipment and storage medium
CN110263691A (en) Head movement detection method based on android system
CN112232128B (en) Eye tracking based method for identifying care needs of old disabled people
CN102508551B (en) Sight capturing method and man-machine interaction method adopting sight capturing
CN107346178A (en) A kind of vision protection device and method
CN109194952A (en) Wear-type eye movement tracing equipment and its eye movement method for tracing
JP2010112979A (en) Interactive signboard system
CN112183200A (en) Eye movement tracking method and system based on video image

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
CB02 Change of applicant information

Address after: 11-13 / F, joint headquarters building, high tech Zone, 63 Xuefu Road, Yuehai street, Nanshan District, Shenzhen, Guangdong 518000

Applicant after: Obi Zhongguang Technology Group Co., Ltd

Address before: 12 / F, joint headquarters building, high tech Zone, 63 Xuefu Road, Nanshan District, Shenzhen, Guangdong 518000

Applicant before: SHENZHEN ORBBEC Co.,Ltd.

CB02 Change of applicant information