CN105139447A - Sitting posture real-time detection method based on double cameras - Google Patents
Sitting posture real-time detection method based on double cameras Download PDFInfo
- Publication number
- CN105139447A CN105139447A CN201510486671.8A CN201510486671A CN105139447A CN 105139447 A CN105139447 A CN 105139447A CN 201510486671 A CN201510486671 A CN 201510486671A CN 105139447 A CN105139447 A CN 105139447A
- Authority
- CN
- China
- Prior art keywords
- camera
- sitting posture
- human eye
- image
- human
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000011897 real-time detection Methods 0.000 title claims abstract description 18
- 238000001514 detection method Methods 0.000 claims abstract description 14
- 230000009977 dual effect Effects 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 9
- 239000007787 solid Substances 0.000 claims description 5
- 230000001105 regulatory effect Effects 0.000 claims description 4
- 238000013519 translation Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 abstract description 2
- 210000000887 face Anatomy 0.000 abstract 1
- 230000036544 posture Effects 0.000 description 25
- 210000003128 head Anatomy 0.000 description 8
- 208000001491 myopia Diseases 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 230000004379 myopia Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 208000000875 Spinal Curvatures Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000007630 basic procedure Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 201000007094 prostatitis Diseases 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 210000001747 pupil Anatomy 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a sitting posture real-time detection method based on double cameras. The method comprises the following steps of calibrating internal and external parameters of cameras; acquiring a human body sitting posture stereo image through a binocular camera; performing stereo matching for the acquired stereo image, keeping a point cloud in a set range as a potential human body part point cloud; projecting the segmented human body part point cloud in the acquired image to perform image-based human face and human eye detection; judging whether the human faces are detected; judging whether an image rotation angle is greater than a set threshold value; judging whether the human eyes are detected; calling rotation transformation R2 of a calibrated camera coordinate system relative to a vertical plane, and calculating out vertical distance between the human eyes and the cameras through a three-dimensional point cloud nearby the human eyes; adding the set distance between the binocular camera and a desk surface and the distance between the human eyes and the cameras together to obtain the vertical distance between the human eyes and the desk surface; and judging whether the vertical distance between the human eyes and the desk surface is greater than a set vertical distance threshold value. The sitting posture real-time detection method based on double cameras automatically detects human body sitting posture in real time and judges whether the sitting posture is correct or not.
Description
Technical field
The present invention relates to a kind of sitting posture real-time detection method.Particularly relate to a kind of technology such as binocular solid coupling, three-dimensional reconstruction and recognition of face that utilize and whether the sitting posture real-time detection method based on dual camera providing automatic discrimination is rectified to human body sitting posture.
Background technology
The rate of myopia of adolescents in China occupy prostatitis, the world throughout the year, investigation according to the Ministry of Education of the state, the Ministry of Public Health shows: there is A nearsighted person more than 400,000,000 in China at present, wherein teenager becomes " severely afflicated area ": in pupil, rate of myopia is more than 30%, and middle school student reach 70%, and university student reaches 90%." writing posture is incorrect, long between using at the moment " is the major reason causing myopia.Meanwhile, writing posture is incorrect, also can cause the problems such as spinal curvature.According to " Xicheng District of Beijing, 14, Shijingshan District primary school student body health detection analysis report " (seeing table) that 2012 issue, in nearly ten thousand students of investigation, writing posture problem number ratio reaches 77.6%.
At present on upper market, relevant human body sitting posture detects and normally utilizes ultrasonic sensor, the distance of probing head and sensor, if be too near to, desk lamp gives a warning correcting sitting postures.But this scheme exists inborn shortcoming, such as: have radiation to human body, the angle that head departs from health axis can not be measured, and sensor is easily blocked.
Summary of the invention
Technical matters to be solved by this invention is, provides a kind of defect that can make up conventional ultrasound ranging technology, and antijamming capability is strong, differentiates the sitting posture real-time detection method based on dual camera that accuracy is high.
The technical solution adopted in the present invention is: a kind of sitting posture real-time detection method based on dual camera, is to process the image gathered by two binocular camera formed with money camera arranged on the table, specifically comprises the steps:
1) demarcation of camera inside and outside parameter is carried out;
2) human body sitting posture stereo-picture is gathered by binocular camera;
3) Stereo matching is carried out to the stereo pairs gathered, site space point cloud is rebuild according to the camera inside and outside parameter of having demarcated and matching result, and according to setup parameter, to the on-the-spot three-dimensional point cloud rebuild, retain the some cloud of setting range as potential human body parts point cloud;
4) by step 3) the human body point cloud that is partitioned into projects to step 2) in the image that gathers, determine people region in the picture, and the face carried out in described region based on image and human eye detection;
5) judge whether face to be detected, then do not return step 2), have, enter step 6);
6) judge whether image rotation angle is greater than setting threshold value, if image rotation angle is greater than setting threshold value, then head part does not rectify, and is judged to be attitude mistake, returns step 2), otherwise enter step 7);
7) judge whether human eye to be detected, detect, enter step 8), otherwise the human face region central point that setting detects is position of human eye, enters step 8);
8) call in the camera coordinate system demarcated relative to the rotational transform R2 of vertical plane, by the three-dimensional point cloud near human eye, calculate the vertical range of human eye to camera;
9) distance of the binocular camera of setting to desktop is added with the distance of human eye to camera, draws the vertical range of human eye to desktop;
10) determining step 9) whether the human eye that calculates be greater than the vertical range threshold value of human eye to desktop of setting to the vertical range of desktop, judge that attitude is correct, return step 2), otherwise judge that human eye is too near to desktop distance, attitude mistake then output error result, returns step 2).
Two described cameras are spaced apart 8.5 ~ 11.5cm between two cameras on the table by support level is fixing, and the elevation angle regulating camera is human body sitting posture to be positioned at the angle in the middle part of image.
Step 1) described in camera calibration, comprising:
(1) gridiron pattern scaling board is set at 0.5m ~ 2m place, camera front;
(2) binocular camera sync pulse jamming some groups of gridiron pattern scaling board images are utilized, utilize the binocular solid calibration algorithm based on plane, calibrate Intrinsic Matrix K1 and K2 of two cameras, and the outer parameter i.e. translation T1 of second relative first camera of camera and rotational transform R1, the outer parameter of setting first camera is unit matrix I and (0,0,0)
t, then the outer parameter of second camera is R1 and T1;
(3) utilizing the first camera to take the gridiron pattern scaling board vertically put, based on demarcating intrinsic parameter K1 and K2 by PnP algorithm, calibrating the rotational transform R2 of camera coordinate system relative to vertical plane;
(4) all parameters calibrated are stored in system file.
Step 3) described in setup parameter, comprising: setting people and camera between distance range be 0.5 ~ 1.5m; Human body parts point cloud scope, namely length, width and height are within the scope of the cube of 0.7m; Camera position is to the distance of desktop.
Step 4) in when carrying out based on the face of image and human eye detection, in order to detect head part's askew status, when image can't detect face, by image spacing 5 ~ 10 degree of left rotation and right rotation, until face detected, or image spacing left rotation and right rotation angle is greater than till 90 degree.
Step 4) described in face and human eye detection, be carry out pattern match complete by calling the waterfall cascade classifier cascade trained.
Step 8) described in calculate the vertical range of human eye to camera, due under reconstruction point cloud is based upon camera coordinate system, utilize the rotational transform of camera and vertical plane will put Cloud transform to plumbness, some cloud coordinate is vertically the distance of human eye to camera.
Sitting posture real-time detection method based on dual camera of the present invention, by combining based on binocular stereo vision, three-dimensional reconstruction, face and eye detection algorithm, the information of comprehensive utilization two dimensional image and three dimensions point cloud, and image rotation, can to askew head common in sitting posture, eyes from books (desktop) too close to etc. wrong attitude detect in real time, the sitting posture of automatic human body, provides judgement to the correctness of sitting posture.Algorithm robust, real-time, equipment is simple, and antijamming capability is strong, differentiates that accuracy is high.After initial alignment, testing process automatically completes, without the need to any man-machine interactively.And can be regulated by parameter threshold, meet the use of the different height people such as children and adult.
Accompanying drawing explanation
The installation of Fig. 1 camera and the signal of shooting scaling board;
Wherein: 1: support 2: camera 3: gridiron pattern scaling board
Fig. 2 is the basic procedure that sitting posture detects in real time.
Embodiment
Below in conjunction with embodiment and accompanying drawing, the sitting posture real-time detection method based on dual camera of the present invention is described in detail.
As shown in Figure 2, sitting posture real-time detection method based on dual camera of the present invention, that the image gathered by two binocular camera formed with money camera arranged on the table is processed, two described cameras are fixing on the table by support level, 8.5 ~ 11.5cm is spaced apart between two cameras, the elevation angle regulating camera is human body sitting posture can be positioned at the angle in the middle part of image, even if human body parts is placed in the middle as far as possible in image.Described process comprises the steps:
1) demarcation of camera inside and outside parameter is carried out;
Described camera calibration, shown in beginning Fig. 1, comprising:
(1) gridiron pattern scaling board is set at 0.5m ~ 2m place, camera front;
(2) binocular camera sync pulse jamming some groups of gridiron pattern scaling board images are utilized, utilize the binocular solid calibration algorithm based on plane, calibrate Intrinsic Matrix K1 and K2 of two cameras, and the outer parameter i.e. translation T1 of second relative first camera of camera and rotational transform R1, the outer parameter of setting first camera is unit matrix I and (0,0,0)
t, then the outer parameter of second camera is R1 and T1;
(3) utilizing the first camera to take the gridiron pattern scaling board vertically put, based on demarcating intrinsic parameter K1 and K2 by PnP algorithm, calibrating the rotational transform R2 of camera coordinate system relative to vertical plane;
(4) all parameters calibrated are stored in system file.
Then as shown in Figure 2:
2) human body sitting posture stereo-picture is gathered by binocular camera;
The camera fixed is put the correct position in desktop, and it is right that distance people is about 0.5m first, and the people sat up straight imaging in camera is positioned in the middle of image as far as possible.
3) Stereo matching is carried out to the stereo pairs gathered, site space point cloud is rebuild according to the camera inside and outside parameter of having demarcated and matching result, and according to setup parameter, the scene point cloud rebuild is processed, retain the some cloud of setting range as potential human body parts point cloud; Described setup parameter, comprising: the distance range between setting people and camera is 0.5 ~ 1.5m; Human body parts point cloud scope, namely length, width and height are within the scope of the cube of 0.7m; Camera position is to the distance of desktop.
Dual camera real-time synchronization gathers sitting posture image, and supposing that first, second camera takes image is respectively I1, I2.Utilize has demarcated parameter K1, K2, T1, R1, binocular solid coupling is carried out to the stereogram of collection, obtains the matching relationship of I1, I2 two between width image pixel.Utilize matching relationship and parameter K1, K2, T1, R1 carry out three-dimensional reconstruction, here the imaging model projection matrix of the first camera is K1 [I|0], the imaging model projection matrix of the first camera is K2 [R1|T1], therefore under reconstruction point cloud is based upon the first camera coordinate system.Utilize the scope i.e. distance threshold of distance camera of the human body parts point cloud set, in reconstruction point cloud, be partitioned into the some cloud of human body parts.
4) by step 3) the human body parts point cloud that is partitioned into projects to step 2) in the image that gathers, determine people region in the picture, and the face carried out in described region based on image and human eye detection, human body parts point cloud is instead thrown back in the first camera shot image I1 by projection matrix K1 [I|0].Expansive working is carried out to cloud subpoint in the picture, determines the image-region F that a cloud covers.In F, utilize Face datection algorithm and eye detection algorithm to carry out the detection of face and eyes.
Described Face datection algorithm and eye detection algorithm carry out pattern match complete by calling the waterfall cascade classifier cascade trained.
When carrying out based on the face of image and human eye detection, in order to detect the outer tiltedly state of head part, when image can't detect face, by image spacing 5 ~ 10 degree rotation, until face detected, or image spacing first right rotation angle is greater than till 90 degree.
5) judge whether information face and eye being detected, if face do not detected, then cannot judge, then return step 2), have, enter step 6);
6) if face detected, judge whether image rotation angle is greater than setting threshold value, if image rotation angle is greater than setting threshold value (as 30 degree), then head part does not rectify, head is crooked, is judged to be attitude mistake, exports attitude error message, return step 2), otherwise enter step 7);
7) judge whether human eye to be detected, detect, enter step 8), otherwise the human face region center that setting detects is position of human eye, enters step 8);
8) call in the camera coordinate system demarcated relative to the rotational transform R2 of vertical plane, by the three-dimensional point cloud near human eye, calculate the vertical range of human eye to camera; Described calculates the vertical range of human eye to camera, due under reconstruction point cloud is based upon camera coordinate system, utilize the rotational transform of camera and vertical plane will put Cloud transform to plumbness, some cloud coordinate is vertically the distance of human eye to camera.Namely, utilize image and the corresponding relation putting cloud, in ocular vicinity search from its nearest reconstruction point, and utilize the rotational transform R2 of the first camera and the vertical plane demarcated by this point transformation to vertical direction, then after conversion, the y-axis coordinate figure of some cloud is the vertical range at the first camera center.If eyes do not detected, then position of human eye is thought at human face region center, by from the nearest reconstruction point in this position after R2 conversion, obtain its vertical range to the first camera center equally.
9) distance of the binocular camera of setting to desktop is added with the distance of human eye to camera, draws the vertical range of human eye to desktop;
10) determining step 9) whether the human eye that calculates be greater than the vertical range threshold value of human eye to desktop of setting to the vertical range of desktop, judge that attitude is correct, return step 2), otherwise judge that human eye is too near to desktop distance, attitude mistake then output error result, returns step 2).That is, to the vertical range at the first camera center, human eye is added that camera arrives the distance of frame bottom (i.e. desktop), then obtain the vertical range L of eyes to desktop.Be greater than the threshold value of setting as crossed L, then judge that sitting posture is correct, otherwise, judge sitting posture mistake; Return continuation to detect next time.
Claims (7)
1. based on a sitting posture real-time detection method for dual camera, it is characterized in that, be that the image gathered by two binocular camera formed with money camera arranged on the table is processed, specifically comprise the steps:
1) demarcation of camera inside and outside parameter is carried out;
2) human body sitting posture stereo-picture is gathered by binocular camera;
3) Stereo matching is carried out to the stereo pairs gathered, site space point cloud is rebuild according to the camera inside and outside parameter of having demarcated and matching result, and according to setup parameter, to the on-the-spot three-dimensional point cloud rebuild, retain the some cloud of setting range as potential human body parts point cloud;
4) by step 3) the human body point cloud that is partitioned into projects to step 2) in the image that gathers, determine people region in the picture, and the face carried out in described region based on image and human eye detection;
5) judge whether face to be detected, then do not return step 2), have, enter step 6);
6) judge whether image rotation angle is greater than setting threshold value, if image rotation angle is greater than setting threshold value, then head part does not rectify, and is judged to be attitude mistake, returns step 2), otherwise enter step 7);
7) judge whether human eye to be detected, detect, enter step 8), otherwise the human face region central point that setting detects is position of human eye, enters step 8);
8) call in the camera coordinate system demarcated relative to the rotational transform R2 of vertical plane, by the three-dimensional point cloud near human eye, calculate the vertical range of human eye to camera;
9) distance of the binocular camera of setting to desktop is added with the distance of human eye to camera, draws the vertical range of human eye to desktop;
10) determining step 9) whether the human eye that calculates be greater than the vertical range threshold value of human eye to desktop of setting to the vertical range of desktop, judge that attitude is correct, return step 2), otherwise judge that human eye is too near to desktop distance, attitude mistake then output error result, returns step 2).
2. the sitting posture real-time detection method based on dual camera according to claim 1, it is characterized in that, two described cameras are fixing on the table by support level, be spaced apart 8.5 ~ 11.5cm between two cameras, the elevation angle regulating camera is human body sitting posture to be positioned at the angle in the middle part of image.
3. the sitting posture real-time detection method based on dual camera according to claim 1, is characterized in that, step 1) described in camera calibration, comprising:
(1) gridiron pattern scaling board is set at 0.5m ~ 2m place, camera front;
(2) binocular camera sync pulse jamming some groups of gridiron pattern scaling board images are utilized, utilize the binocular solid calibration algorithm based on plane, calibrate Intrinsic Matrix K1 and K2 of two cameras, and the outer parameter i.e. translation T1 of second relative first camera of camera and rotational transform R1, the outer parameter of setting first camera is unit matrix I and (0,0,0)
t, then the outer parameter of second camera is R1 and T1;
(3) utilizing the first camera to take the gridiron pattern scaling board vertically put, based on demarcating intrinsic parameter K1 and K2 by PnP algorithm, calibrating the rotational transform R2 of camera coordinate system relative to vertical plane;
(4) all parameters calibrated are stored in system file.
4. the sitting posture real-time detection method based on dual camera according to claim 1, is characterized in that, step 3) described in setup parameter, comprising: setting people and camera between distance range be 0.5 ~ 1.5m; Human body parts point cloud scope, namely length, width and height are within the scope of the cube of 0.7m; Camera position is to the distance of desktop.
5. the sitting posture real-time detection method based on dual camera according to claim 1, it is characterized in that, step 4) in when carrying out based on the face of image and human eye detection, in order to detect head part's askew status, when image can't detect face, by image spacing 5 ~ 10 degree of left rotation and right rotation, until face detected, or image spacing left rotation and right rotation angle is greater than till 90 degree.
6. the sitting posture real-time detection method based on dual camera according to claim 1, is characterized in that, step 4) described in face and human eye detection, be carry out pattern match complete by calling the waterfall cascade classifier cascade trained.
7. the sitting posture real-time detection method based on dual camera according to claim 1, it is characterized in that, step 8) described in calculate the vertical range of human eye to camera, due under reconstruction point cloud is based upon camera coordinate system, utilize the rotational transform of camera and vertical plane will put Cloud transform to plumbness, some cloud coordinate is vertically the distance of human eye to camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510486671.8A CN105139447B (en) | 2015-08-07 | 2015-08-07 | Sitting posture real-time detection method based on dual camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510486671.8A CN105139447B (en) | 2015-08-07 | 2015-08-07 | Sitting posture real-time detection method based on dual camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105139447A true CN105139447A (en) | 2015-12-09 |
| CN105139447B CN105139447B (en) | 2018-09-11 |
Family
ID=54724779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510486671.8A Expired - Fee Related CN105139447B (en) | 2015-08-07 | 2015-08-07 | Sitting posture real-time detection method based on dual camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105139447B (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022304A (en) * | 2016-06-03 | 2016-10-12 | 浙江大学 | Binocular camera-based real time human sitting posture condition detection method |
| CN106022378A (en) * | 2016-05-23 | 2016-10-12 | 武汉大学 | Camera and pressure sensor based cervical spondylopathy identification method |
| CN107491751A (en) * | 2017-08-14 | 2017-12-19 | 成都伞森科技有限公司 | Sitting posture analysis method and device |
| CN107545609A (en) * | 2017-09-29 | 2018-01-05 | 竹蜻蜓博轩（天津）科技有限公司 | A kind of office management system with monitoring function |
| CN108460707A (en) * | 2018-03-12 | 2018-08-28 | 林为庆 | A kind of the operation intelligent supervision method and its system of student |
| CN108877166A (en) * | 2018-07-23 | 2018-11-23 | 广东小天才科技有限公司 | Sitting posture reminding device |
| CN109523755A (en) * | 2018-12-17 | 2019-03-26 | 石家庄爱赛科技有限公司 | Stereoscopic vision sitting posture reminder and based reminding method |
| CN109685007A (en) * | 2018-12-21 | 2019-04-26 | 深圳市康康网络技术有限公司 | Method for early warning, user equipment, storage medium and the device being accustomed to eye |
| CN110287864A (en) * | 2019-06-24 | 2019-09-27 | 火石信科(广州)科技有限公司 | A kind of intelligent identification of read-write scene read-write element |
| CN110298284A (en) * | 2019-06-24 | 2019-10-01 | 火石信科(广州)科技有限公司 | A kind of recognition methods for reading and writing scene and read and write position |
| CN110309750A (en) * | 2019-06-24 | 2019-10-08 | 火石信科(广州)科技有限公司 | A method of scene is read and write based on monocular camera automatic identification |
| CN110440697A (en) * | 2019-08-08 | 2019-11-12 | 肖乐 | Correcting sitting postures intelligence system and method |
| CN110757477A (en) * | 2019-10-31 | 2020-02-07 | 昆山市工研院智能制造技术有限公司 | Height and orientation self-adaptive adjusting method of accompanying robot and accompanying robot |
| CN111027517A (en) * | 2019-12-26 | 2020-04-17 | 陈欣然 | Sitting posture correction reminding system and method based on vision and application |
| CN111243742A (en) * | 2020-01-14 | 2020-06-05 | 中科海微(北京)科技有限公司 | Intelligent glasses capable of analyzing eye habits of children |
| CN112329642A (en) * | 2020-11-06 | 2021-02-05 | 重庆第二师范学院 | Supervised learning detection method, system, electronic device and medium |
| CN113051991A (en) * | 2020-11-08 | 2021-06-29 | 泰州市出彩网络科技有限公司 | Abnormal state dual detection platform and method |
| CN113129374A (en) * | 2021-04-20 | 2021-07-16 | 四川写正智能科技有限公司 | Method and device for assisting reading and writing posture judgment by laser point cloud face recognition |
| CN113312939A (en) * | 2020-02-26 | 2021-08-27 | 北京君正集成电路股份有限公司 | System for preventing false alarm generated when no target exists in front of detector in sitting posture detection |
| CN113312938A (en) * | 2020-02-26 | 2021-08-27 | 北京君正集成电路股份有限公司 | Method and system for preventing false alarm generated when no target exists in front of detector in sitting posture detection |
| CN114963109A (en) * | 2022-06-18 | 2022-08-30 | 中山市鸿旭科技有限公司 | Method for correcting body posture by using subconscious behaviors and desk lamp |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202534119U (en) * | 2012-04-11 | 2012-11-14 | 上海渐华科技发展有限公司 | Camera sitting posture correcting device |
| CN102956090A (en) * | 2011-08-26 | 2013-03-06 | 陈仕国 | Double-lens image sensing myopia-preventing reminder |
| CN103065289A (en) * | 2013-01-22 | 2013-04-24 | 清华大学 | Four-ocular video camera front face reconstruction method based on binocular stereo vision |
| CN103729981A (en) * | 2014-01-03 | 2014-04-16 | 东南大学 | Child sitting posture monitoring intelligent terminal |
| CN103908063A (en) * | 2014-04-03 | 2014-07-09 | 安徽海聚信息科技有限责任公司 | Intelligent desk with sitting posture correcting function and correcting method implemented by intelligent desk |
-
2015
- 2015-08-07 CN CN201510486671.8A patent/CN105139447B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102956090A (en) * | 2011-08-26 | 2013-03-06 | 陈仕国 | Double-lens image sensing myopia-preventing reminder |
| CN202534119U (en) * | 2012-04-11 | 2012-11-14 | 上海渐华科技发展有限公司 | Camera sitting posture correcting device |
| CN103065289A (en) * | 2013-01-22 | 2013-04-24 | 清华大学 | Four-ocular video camera front face reconstruction method based on binocular stereo vision |
| CN103729981A (en) * | 2014-01-03 | 2014-04-16 | 东南大学 | Child sitting posture monitoring intelligent terminal |
| CN103908063A (en) * | 2014-04-03 | 2014-07-09 | 安徽海聚信息科技有限责任公司 | Intelligent desk with sitting posture correcting function and correcting method implemented by intelligent desk |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022378A (en) * | 2016-05-23 | 2016-10-12 | 武汉大学 | Camera and pressure sensor based cervical spondylopathy identification method |
| CN106022378B (en) * | 2016-05-23 | 2019-05-10 | 武汉大学 | Sitting posture judgment method and based on camera and pressure sensor cervical spondylosis identifying system |
| CN106022304B (en) * | 2016-06-03 | 2019-11-29 | 浙江大学 | A kind of real-time body's sitting posture situation detection method based on binocular camera |
| CN106022304A (en) * | 2016-06-03 | 2016-10-12 | 浙江大学 | Binocular camera-based real time human sitting posture condition detection method |
| CN107491751A (en) * | 2017-08-14 | 2017-12-19 | 成都伞森科技有限公司 | Sitting posture analysis method and device |
| CN107491751B (en) * | 2017-08-14 | 2020-06-09 | 成都伞森科技有限公司 | Sitting posture analysis method and device |
| CN107545609A (en) * | 2017-09-29 | 2018-01-05 | 竹蜻蜓博轩（天津）科技有限公司 | A kind of office management system with monitoring function |
| CN108460707A (en) * | 2018-03-12 | 2018-08-28 | 林为庆 | A kind of the operation intelligent supervision method and its system of student |
| CN108877166A (en) * | 2018-07-23 | 2018-11-23 | 广东小天才科技有限公司 | Sitting posture reminding device |
| CN108877166B (en) * | 2018-07-23 | 2020-11-03 | 广东小天才科技有限公司 | Sitting posture reminding device |
| CN109523755A (en) * | 2018-12-17 | 2019-03-26 | 石家庄爱赛科技有限公司 | Stereoscopic vision sitting posture reminder and based reminding method |
| CN109685007A (en) * | 2018-12-21 | 2019-04-26 | 深圳市康康网络技术有限公司 | Method for early warning, user equipment, storage medium and the device being accustomed to eye |
| CN110309750A (en) * | 2019-06-24 | 2019-10-08 | 火石信科(广州)科技有限公司 | A method of scene is read and write based on monocular camera automatic identification |
| CN110298284A (en) * | 2019-06-24 | 2019-10-01 | 火石信科(广州)科技有限公司 | A kind of recognition methods for reading and writing scene and read and write position |
| CN110287864A (en) * | 2019-06-24 | 2019-09-27 | 火石信科(广州)科技有限公司 | A kind of intelligent identification of read-write scene read-write element |
| CN110440697A (en) * | 2019-08-08 | 2019-11-12 | 肖乐 | Correcting sitting postures intelligence system and method |
| CN110757477A (en) * | 2019-10-31 | 2020-02-07 | 昆山市工研院智能制造技术有限公司 | Height and orientation self-adaptive adjusting method of accompanying robot and accompanying robot |
| CN111027517A (en) * | 2019-12-26 | 2020-04-17 | 陈欣然 | Sitting posture correction reminding system and method based on vision and application |
| CN111243742A (en) * | 2020-01-14 | 2020-06-05 | 中科海微(北京)科技有限公司 | Intelligent glasses capable of analyzing eye habits of children |
| CN111243742B (en) * | 2020-01-14 | 2023-08-25 | 中科海微(北京)科技有限公司 | Intelligent glasses capable of analyzing eye habit of children |
| CN113312938A (en) * | 2020-02-26 | 2021-08-27 | 北京君正集成电路股份有限公司 | Method and system for preventing false alarm generated when no target exists in front of detector in sitting posture detection |
| CN113312939A (en) * | 2020-02-26 | 2021-08-27 | 北京君正集成电路股份有限公司 | System for preventing false alarm generated when no target exists in front of detector in sitting posture detection |
| CN113312938B (en) * | 2020-02-26 | 2024-10-15 | 北京君正集成电路股份有限公司 | Method and system for preventing false alarm generated when no target exists in front of detector in sitting posture detection |
| CN112329642A (en) * | 2020-11-06 | 2021-02-05 | 重庆第二师范学院 | Supervised learning detection method, system, electronic device and medium |
| CN113051991A (en) * | 2020-11-08 | 2021-06-29 | 泰州市出彩网络科技有限公司 | Abnormal state dual detection platform and method |
| CN113129374A (en) * | 2021-04-20 | 2021-07-16 | 四川写正智能科技有限公司 | Method and device for assisting reading and writing posture judgment by laser point cloud face recognition |
| CN114963109A (en) * | 2022-06-18 | 2022-08-30 | 中山市鸿旭科技有限公司 | Method for correcting body posture by using subconscious behaviors and desk lamp |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105139447B (en) | 2018-09-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105139447A (en) | Sitting posture real-time detection method based on double cameras | |
| CN106022304B (en) | A kind of real-time body's sitting posture situation detection method based on binocular camera | |
| CN106168853B (en) | A kind of free space wear-type gaze tracking system | |
| CN103729981B (en) | A kind of child sitting gesture monitoring intelligent terminal | |
| CN104732191B (en) | The devices and methods therefor of virtual display Eye-controlling focus is realized using Cross ration invariability | |
| CN106461983B (en) | Method for determining at least one parameter of personal visual behaviour | |
| CN103908063A (en) | Intelligent desk with sitting posture correcting function and correcting method implemented by intelligent desk | |
| CN105094300B (en) | A kind of sight line tracking system and method based on standardization eye image | |
| CN105354825B (en) | The intelligent apparatus of reading matter position and its application in automatic identification read-write scene | |
| CN109523755A (en) | Stereoscopic vision sitting posture reminder and based reminding method | |
| CN103971408A (en) | Three-dimensional facial model generating system and method | |
| CN103099602A (en) | Constitution detecting method and constitution detecting system based on optical identification | |
| CN102596005A (en) | Method and device for automatically measuring at least one refractive characteristic of both eyes of person | |
| CN105354822B (en) | The intelligent apparatus of read-write element position and application in automatic identification read-write scene | |
| CN104581113B (en) | Adaptive holographic display methods and holographic display based on viewing angle | |
| CN104146681A (en) | Eye ground retina OCT image correction method | |
| CN103908064A (en) | Intelligent desk with sitting posture correcting function and correcting method implemented by intelligent desk | |
| CN105741375A (en) | Large-visual-field binocular vision infrared imagery checking method | |
| CN106840112A (en) | A kind of space geometry measuring method of utilization free space eye gaze point measurement | |
| US20190196221A1 (en) | System and Method of Obtaining Fit and Fabrication Measurements for Eyeglasses Using Simultaneous Localization and Mapping of Camera Images | |
| CN111012353A (en) | Height detection method based on face key point recognition | |
| CN105335699B (en) | Read-write scene is read and write intelligent identification and the application thereof of element three-dimensional coordinate | |
| CN110251070A (en) | It is a kind of to use eye health condition monitoring method and system | |
| CN107452032A (en) | Human body back depth image preprocess method | |
| CN115409774A (en) | Eye detection method based on deep learning and strabismus screening system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230330 Address after: Room 524, Automation Building, No. 95, Zhongguancun East Road, Haidian District, Beijing, 100080 Patentee after: BEIJING ZHONGZI SCIENCE AND TECHNOLOGY BUSINESS INCUBATOR CO.,LTD. Address before: 300309 building 7, Jinghu Science Park, Dongli District, Tianjin Patentee before: TIANJIN INTELLIGENT TECH. INSTITUTE OF CASIA Co.,Ltd. |
|
| 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: 20180911 |