CN111401382A - Method for automatically detecting camera range and desk lamp using same - Google Patents
Method for automatically detecting camera range and desk lamp using same Download PDFInfo
- Publication number
- CN111401382A CN111401382A CN201911227879.2A CN201911227879A CN111401382A CN 111401382 A CN111401382 A CN 111401382A CN 201911227879 A CN201911227879 A CN 201911227879A CN 111401382 A CN111401382 A CN 111401382A
- Authority
- CN
- China
- Prior art keywords
- camera
- user
- desk lamp
- range
- human body
- 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
Images
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
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D3/00—Control of position or direction
- G05D3/12—Control of position or direction using feedback
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for automatically detecting the range of a camera, which comprises the following steps: s1: collecting an image; s2: extracting the collected images by using a human body posture recognition algorithm to obtain human body posture data, and if the extraction is successful, performing step S4; if the extraction fails, go to step S3; s3: sending a prompt to prompt the user to sit upright, and performing the step S1 again; s4: and detecting the included angle between the two shoulders and the horizontal plane and the position of the neck in the image according to the human body posture data extracted in the step of S2, so as to judge the position of the camera relative to the user. The invention also discloses a desk lamp using the method, which eliminates the parallax problem of the monocular camera, solves the difficulty of judging the position relationship between the camera and the user and reminds the user of correcting the posture; and then, the distance parameter between the camera and the user is preliminarily determined by matching with the skull size of the user, so that the approximate position shown by the eyes of the user is searched, and the reading and the light tracing of the user are realized by matching with the desk lamp body provided with the adjusting part.
Description
Technical Field
The invention relates to the technical field of intelligent electrical appliances, in particular to a method for automatically detecting the range of a camera and a desk lamp using the method.
Background
In recent years, parents pay more attention to children's education, and the time for young students to learn the education is relatively increased. The current market has a sitting posture recognition desk lamp based on the human posture of a monocular camera, and the human sitting posture recognition algorithm of the monocular camera can refer to a text of sitting posture vision recognition method research based on discriminant deep learning published by Huangxu, Hunan university, the classification number of the text is as follows: TP391.41 and TP18, and the combination mode that a binocular camera matches with a user to set the camera consciously and manually is adopted by most of the prior table lamps to solve the problem, for example, the combination mode that the binocular camera is matched with the user to set the camera is adopted by the monocular camera in the application, the publication number of the binocular camera is 'CN 204305177U' disclosed in Chinese patent document, the binocular camera comprises a base, a first camera twistable shaping supporting rod and a second camera twistable shaping supporting rod are arranged at the top of the base, the top of the first camera supporting rod is provided with the camera, the top of the second camera supporting rod is provided with a variable-focus camera, the middle of the second camera supporting rod is provided with a microphone, the upper part of the second camera supporting rod is provided with the table lamp, one side of the base is provided with a wire control switch panel, the zoom button is arranged on the camera, the other side of the base is provided with a USB interface connected with a lead, the binocular camera realizes 180-degree adjustable azimuth monitoring shooting and video chatting. However, the cost is greatly increased by using the binocular camera, and the conscious manual setting requires the user to have vision-related cognition, so that the use complexity of the user is increased.
Disclosure of Invention
Aiming at the following problems in the prior art: 1. the relative position difficulty of the monocular camera and a user is judged due to parallax; 2. although the binocular camera desk lamp can avoid parallax, the problems of high cost and inconvenient adjustment exist, the invention designs a method for automatically detecting the camera range based on a monocular camera and a desk lamp using the same.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for automatically detecting the range of a camera comprises the following steps:
s1: collecting an image; s2: extracting the collected images by using a human body posture recognition algorithm to obtain human body posture data, and if the extraction is successful, performing step S4; if the extraction fails, go to step S3; s3: sending a prompt to prompt the user to sit upright, and performing the step S1 again; s4: and detecting the included angle between the two shoulders and the horizontal plane and the position of the neck in the image according to the human body posture data extracted in the step of S2, so as to judge the position of the camera relative to the user. The camera captures one frame of image in the camera range and performs distortion correction on the image, and ignores the distortion correction of the software if the camera module has been subjected to distortion processing, at which point step S1 is completed. Next, this frame of image is analyzed, key points of the human body, including main key points of eyes, nose, ears, shoulders, arms, etc., are extracted by using a human body posture recognition algorithm, and if the key points are not extracted, that is, if the position mark of the table lamp relative to the human is not generated, step S3 is performed. And step S3, the program sends out a prompt to remind the user to keep the posture correction for 2-3 seconds, then the steps S1-S2 are repeated until the key point information of the human body is successfully extracted, and then the step S4 is carried out. Step S4, a, determining whether the camera is positioned right in front, left in front or right in front of the user according to the included angle between the two shoulders and the horizontal direction; b. meanwhile, the rotation direction of the camera and the table lamp body is judged according to the position of the neck of the user in the image. Step a is used for confirming the relative position of the camera and the user, and step b is used for confirming the adjustment direction of the camera and preparing for subsequent work.
Preferably, S2.1: the human body posture data comprises information of human body key points, wherein the human body key points comprise characteristics and position information of eyes, a nose, ears, shoulders and arms; the position information of the user eyes is a core parameter, and other parameters are auxiliary parameters for helping the camera to confirm the relative positions of the user eyes in the environment. S2.2: the information of the human body key points also comprises skull size information. Since human skull parameters do not change much after 16 years of age, the skull size information can be used to roughly confirm the distance parameters between the camera and the user.
Preferably, when the height of the camera is lower than the height of shoulders of the user:
s4.1: after the included angle between the two shoulders and the horizontal direction is detected, if the detection result is near 0 degrees and does not exceed the range of a preset value, the camera is judged to be arranged right in front of the user; if the left shoulder height is lower than the again-seen height and exceeds the preset value range, the camera is judged to be arranged in front of the left of the user; and if the left shoulder height is higher than the re-seeing height and exceeds the range of the preset value as a detection result, judging that the camera is arranged in the front right of the user. After the height relation between the shoulders of the user and the camera is determined, the relative position relation between the camera and the user can be obtained by detecting the included angle between the connecting line of the two shoulders and the horizontal direction, namely the camera is positioned at the left front, the right front or the right front of the user.
S4.2: after the position of the neck in the image is detected, if the detection result shows that the neck is in the middle of the image, the camera is judged to be over against the user; if the detection result is that the neck is at the right part of the image, the camera rotates rightwards; and if the detection result shows that the neck is at the left part of the image, the camera rotates leftwards. The position of the neck position of the user in the image indicates the condition that the camera deviates from the user, and the parameter is used for adjusting the subsequent camera to face the user so as to facilitate the prepositive work for the subsequent work.
The invention also discloses a desk lamp using the method for automatically detecting the camera range, which comprises a desk lamp body, wherein the desk lamp body comprises an adjusting part, an illuminating part arranged at the top end of the adjusting part and a control part arranged at the bottom end of the adjusting part, the adjusting part is provided with a camera, and the control part comprises a control module, a reminding module and a control module: wherein
The camera is fixed at the position, close to the control part, of the adjusting part of the desk lamp body and used for collecting user images in a preset area and sending a collection result to the control module;
a control module: the device comprises a camera, a prompting module, a display module and a prompting module, wherein the prompting module is used for receiving a user image acquired by the camera, processing picture data, extracting information of key points of a human body in the picture, wherein the key points of the human body comprise characteristics and position information of eyes, a nose, ears, shoulders and arms;
a manipulation module: after the position of the camera relative to the user is judged, the adjusting part is started to operate the position parameters of the desk lamp body and the camera in the horizontal direction and the vertical direction, so that the irradiation range of the desk lamp body can be automatically adjusted according to the position of the user.
The image that desk lamp accessible control module gathered the camera is handled to obtain camera and desk lamp body and user's positional relation, rethread control module starts the manipulation module and carries out the spatial position adjustment to the desk lamp body, makes desk lamp automatic coordination user position throw light on, ensures simultaneously that the camera can be towards the user, lays the basis for work such as position of sitting correction later.
Preferably, the lighting part is hinged with the top end of the adjusting part, and the bottom end of the adjusting part is hinged with the control part. The top end of the adjusting part is hinged with the illuminating part, the bottom end of the adjusting part is hinged with the control part, two electric motors are arranged at two hinged points respectively, and when the control module starts adjusting parameters to the control module, the control module can start the electric motors to adjust the position of the adjusting part or the illuminating part.
Preferably, the camera is a monocular camera. The automatic detection and judgment of the position relation between the user and the camera, which can be realized only by a binocular camera in the traditional technology, are realized through the monocular camera, and the manufacturing cost of the camera assembly is effectively reduced.
Preferably, the control part is arranged at the lower part of the desk lamp body, and the control module detects included angles between two shoulders of the user and the horizontal plane and the position of the neck in the picture according to the picture data and judges the position of the desk lamp body relative to the user according to the included angles. The control part arranged at the lower part of the desk lamp body can effectively detect the human body information of the user through the camera lower than the heights of the two shoulders of the user, the aim of automatically detecting the range of the camera is achieved, and then the placing position information of the desk lamp body and the camera is obtained, wherein the information is a predetermined condition of a sitting posture recognition algorithm of the human body posture based on the monocular camera.
Preferably, the control module further extracts the size information of the human skull in the picture, and judges the distance between the desk lamp body and the eyes of the user according to the information, and the control module corrects the adjustment result of the adjusting part according to the distance information until the irradiation range of the illuminating part falls within the visual range of the eyes of the user. The relative position relation between the camera and the user can be obtained through the included angle between the two shoulder connecting lines and the horizontal direction, the position of the neck of the user indicates the condition that the camera deviates from the user in an image, the rotation direction and the rotation angle of the desk lamp body and the camera can be determined through the cooperation of the two shoulder connecting lines and the horizontal direction, the distance information is matched, the adjusting portion can continuously rotate the illumination portion to the rotation direction for a certain angle according to calculation and bend downwards, the illumination portion can enable the illumination range to fall within the range shown by the eyes of the user, and the desk lamp body can be helped to achieve the function of reading and tracing the light of the user.
Therefore, the invention has the following beneficial effects: (1) the camera is used for identifying an included angle between a connecting line of two shoulders of a user and the horizontal direction to detect the relative position relation between the user and the camera, so that the relative position detection is realized quickly and accurately; (2) identifying the position of the neck of the user in the image by using the camera so as to determine the rotation direction of the camera, so that the camera can face the user; (3) the distance parameter between the camera and the user is preliminarily determined by detecting the size of the skull of the user, so that the approximate position shown by the eyes of the user is searched, and the reading and the light tracing of the user are realized by matching with the desk lamp body provided with the adjusting part; (4) the problem that the camera and the user position relation is judged is solved through the monocular camera, the parallax problem is eliminated, the detection accuracy is high, the safety and the reliability are realized, and the monocular camera can be matched with the reminding module to correct the sitting posture of the user.
Drawings
Fig. 1 is a schematic structural view of a table lamp body according to the present invention.
Fig. 2 is a side view of the body of the desk lamp of fig. 1.
FIG. 3 is a flowchart of the detection procedure in example 1.
In the figure: 1. the desk lamp comprises a desk lamp body, 2, an illumination part, 3, an adjusting part, 31, a camera, 4 and a control part.
Detailed Description
The invention is further described with reference to the following detailed description and accompanying drawings. Examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
In the description of the present invention, it is to be understood that the terms "center", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used only for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, should not be construed as limiting the present invention.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Examples
As shown in fig. 1, a desk lamp using a method for automatically detecting a camera range includes a desk lamp body, the desk lamp body includes a lighting part, an adjusting part and a control part, the control part includes a camera, a control module, a reminding module and a control module: wherein
The camera is fixed at a position, close to the base, of the adjusting part of the desk lamp body and used for collecting user images of a preset area and sending a collection result to the control module;
a control module: the image processing device is used for receiving a user image acquired by a camera, processing image data, extracting information of key points of a human body in the image, wherein the key points of the human body comprise characteristics and position information of eyes, nose, ears, shoulders and arms;
a manipulation module: after the position of the camera relative to the user is judged, the adjusting part is started to operate the position parameters of the desk lamp body and the camera in the horizontal direction and the vertical direction, so that the irradiation range of the desk lamp body can be automatically adjusted according to the position of the user.
In this embodiment, the camera setting is fixing and is being close to the base position at desk lamp body regulating part, and during normal use, the camera height is less than two shoulder heights of user. As shown in FIG. 2, the detection steps of the present invention are as follows: the desk lamp can process images collected by the camera through the control module, and the processor of the control module mainly identifies the images through the following method: utilize human key point of MBH to mark technique to human upper part of the body, including the top of the head, the nose point, eyes (pupil), the auricle, the mouth angle, the shoulder joint, the elbow, the wrist, the hand point, key points such as neck and clavicle intersect, ensure that control module fixes a position user's profile, there is the angle in the positive and camera of user probably appearing when considering that the monocular camera carries out image acquisition, consequently, it only needs eyes (pupil) at first to detect camera position mark after the camera starts, the nose point, the auricle, the shoulder joint, elbow information acquisition succeeds in carrying out initial data discernment, promptly: a. determining whether the camera is positioned right in front, left in front or right in front of the user according to the included angle between the two shoulders and the horizontal direction; b. meanwhile, the rotation direction of the camera and the table lamp body is judged according to the position of the neck of the user in the image. Step a is used for confirming the relative position of the camera and the user, and step b is used for confirming the adjustment direction of the camera and preparing for subsequent work. If the preliminary information acquisition fails, the sitting posture of the user is not in accordance with the basic image acquisition standard, and at the moment, the control module starts the reminding module to remind the user to keep sitting posture for 2-3 seconds so as to ensure that the information acquisition is successful next time. The detection in the step a and the detection in the step b can be carried out simultaneously, and the relative position of the camera and the user can be judged quickly.
In the step a, after the included angle between the two shoulders and the horizontal direction is detected, if the detection result is near 0 degree and does not exceed the range of a preset value, the camera is judged to be arranged right in front of the user, and the preset value is 0 +/-3.5 degrees in the embodiment; if the left shoulder height is lower than the again-seen height and exceeds the preset value range, the camera is judged to be arranged in front of the left of the user; and if the left shoulder height is higher than the re-seeing height and exceeds the range of the preset value as a detection result, judging that the camera is arranged in the front right of the user. After the height relation between the shoulders of the user and the camera is determined, the relative position relation between the camera and the user can be obtained by detecting the included angle between the connecting line of the two shoulders and the horizontal direction, namely the camera is positioned at the left front, the right front or the right front of the user.
In step b: after the position of the neck in the image is detected, if the detection result shows that the neck is in the middle of the image, the camera is judged to be over against the user; if the detection result is that the neck is at the right part of the image, the camera is required to rotate rightwards; if the detection result is that the neck is at the left part of the image, the camera should rotate leftwards, the position of the neck of the user in the image indicates the condition that the camera deviates from the user, and the parameter is used for adjusting the subsequent camera to face the user so as to realize the predetermined condition of the subsequent sitting posture identification and correction function.
If the rotation of camera needs to be realized, the control part and the adjusting part of the desk lamp body need to be matched together for realization. Control the module through control module start and carry out spatial position adjustment to the desk lamp body, regulating part is the cylinder structure, the regulating part lower extreme is articulated with the control part, the regulating part upper end is articulated with the illumination portion, when the camera need turn to the right, as shown in fig. 3, control module gives an instruction, and the control module turns into the space coordinate parameter with the instruction, and the drive motor M1 and M2 and the setting on the regulating part top of regulating part bottom are at motor M3 and M4, M1 is used for controlling the regulating part and carries out the ascending rotation of Z axle direction, M2 is used for controlling the regulating part and rotates around the Y axle, and is corresponding, M3 is used for controlling the illumination portion and rotates around the Z axle, M4 is used for controlling the illumination portion and rotates around the Y axle. And controlling the four motors to adjust the upper end and the lower end of the hinge joint according to the space coordinate parameter control module, so that the camera can adjust the position along with the adjusting part. The control module can also extract the size information of the human skull in the picture, and the data show that the size of the human skull is basically not changed after the age of 16 years, and the head circumference of a normal adult is about 54-58 cm. The distance between the desk lamp body and the eyes of the user can be calculated by comparing the collected normal distance information of the user and the desk lamp with the skull size of the user in the image, and then the previous space coordinate parameter adjustment result is corrected by the adjusting part until the irradiation range of the lighting part of the desk lamp body falls into the range seen by the eyes of the user.
The relative position relation between the camera and the user can be obtained through the included angle between the connecting line of the two shoulders and the horizontal direction, the position of the neck of the user indicates the condition that the camera deviates from the user in the image, the rotation direction and the rotation angle of the camera can be determined through the cooperation of the two shoulder connecting lines and the horizontal direction, the distance information is matched, the adjusting part can continuously rotate the illumination part for a certain angle towards the rotation direction according to calculation, after the angle of the illumination part is adjusted to the horizontal direction range shown by the eyes of the user, the upper end hinge of the adjusting part is continuously adjusted, the illumination range error of the illumination part in the vertical direction is further corrected, the illumination range approximately falls to the visual area of the eyes of the user, and the desk lamp body can be helped to realize the light tracing function of the reading area of. When the sitting posture of the user changes, the included angle between the connecting line of the two shoulders and the horizontal direction changes or the position of the neck in the image changes, the control part can control the adjusting part to adjust the illuminating part, so that the high-quality illumination range of the illuminating part always falls within the range seen by the eyes of the user.
Example 2
Compared with the embodiment 1, the desk lamp body in the embodiment can not only provide the reading light following function realized by following the eyesight of the user, but also realize the function of reminding the user of bad sitting posture. The gesture of the user can be monitored at intervals by using an MBH human key point calibration technology in the image acquisition process, however, the premise is that the relative position of the camera and the user still needs to be adjusted by the steps in the embodiment 1, after the camera faces the user, if the position information of the human key point of the user still exceeds the basic detection range, the situation that the position of the user changes to a greater extent when the image is acquired for the first time is detected, if the situation that the whole position of the user is away from the detection range of the camera is detected, the situation that the user still uses the desk lamp but the position of the user changes to a greater extent is detected, at the moment, the reminding module is started by the control module, and the user is reminded of correcting the gesture.
The camera is a monocular camera. The automatic detection and judgment of the position relation between the user and the camera, which can be realized only by a binocular camera in the traditional technology, are realized through the monocular camera, and the manufacturing cost of the camera assembly is effectively reduced. The control part is arranged on the lower portion of the desk lamp body, and the control module detects included angles between two shoulders of a user and the horizontal plane and positions of necks in the picture according to the picture data and judges the position of the desk lamp body relative to the user. The control part arranged at the lower part of the desk lamp body can effectively detect the human body information of the user through the camera lower than the heights of the two shoulders of the user, the aim of automatically detecting the range of the camera is achieved, and then the placing position information of the desk lamp body and the camera is obtained, wherein the information is a predetermined condition of a sitting posture recognition algorithm of the human body posture based on the monocular camera.
In addition to the above embodiments, the technical features of the present invention can be re-selected and combined to form new embodiments within the scope of the claims and the specification of the present invention, which are all realized by those skilled in the art without creative efforts, and thus, the embodiments of the present invention which are not described in detail should be regarded as the specific embodiments of the present invention and are within the protection scope of the present invention.
Claims (8)
1. A method for automatically detecting the range of a camera is characterized by comprising the following steps:
s1: collecting an image;
s2: extracting the collected images by using a human body posture recognition algorithm to obtain human body posture data, and if the extraction is successful, performing step S4; if the extraction fails, go to step S3;
s3: sending a prompt to prompt the user to sit upright, and performing the step S1 again;
s4: and detecting the included angle between the two shoulders and the horizontal direction and the position of the neck of the user in the picture according to the human body posture data extracted in the step of S2, so as to judge the position of the camera relative to the user.
2. The method of claim 1, wherein the camera range is automatically detected,
s2.1: the human body posture data comprises information of human body key points, wherein the human body key points comprise characteristics and position information of eyes, a nose, ears, shoulders and arms;
s2.2: the information of the human body key points also comprises skull size information.
3. The method of claim 1, wherein if the height of the camera is lower than the height of the shoulders of the user:
s4.1: after the included angle between the two shoulders and the horizontal direction is detected, if the detection result is near 0 degrees and does not exceed the range of a preset value, the camera is judged to be arranged right in front of the user; if the left shoulder height is lower than the again-seen height and exceeds the preset value range, the camera is judged to be arranged in front of the left of the user; if the left shoulder height is higher than the re-seeing height and exceeds the range of a preset value, judging that the camera is arranged in front of the right of the user;
s4.2: after the position of the neck in the picture is detected, if the detection result shows that the neck is in the middle of the picture, the camera is judged to be over against the user; if the detection result is that the neck is at the right part of the picture, the camera rotates rightwards; and if the detection result shows that the neck is at the left part of the picture, the camera rotates leftwards.
4. A desk lamp using a method for automatically detecting the range of a camera according to claims 1-3, comprising a desk lamp body (1), wherein the desk lamp body (1) comprises an adjusting part (3), a lighting part (2) arranged at the top end of the adjusting part (3) and a control part (4) arranged at the bottom end of the adjusting part (3), the camera (31) is arranged on the adjusting part (3), and the control part (4) comprises a control module, a reminding module and a control module: wherein
The camera (31) is fixed at the position, close to the control part (4), of the adjusting part (3) of the desk lamp body (1) and used for collecting user images of a preset area and sending a collection result to the control module;
a control module: the image processing device is used for receiving a user image acquired by the camera (31), processing image data, extracting information of key points of a human body in the image, wherein the key points of the human body comprise the characteristics and position information of eyes, nose, ears, shoulders and arms, and if the information in the image cannot be identified, judging that the sitting posture of the user is not standard and starting a reminding module to remind the user of correcting the sitting posture;
a manipulation module: after the position of the camera (31) relative to the user is judged, the operation adjusting part (3) and the camera (31) are started to adjust in the horizontal direction and the vertical direction.
5. The desk lamp using the method for automatically detecting the camera range according to claim 4, wherein the illuminating part (2) is hinged with the top end of the adjusting part (4), and the bottom end of the adjusting part (4) is hinged with the control part (4).
6. The desk lamp using the method for automatically detecting the camera range according to claim 4, wherein the camera (31) is a monocular camera.
7. The desk lamp using the method for automatically detecting the camera range according to claim 4, wherein the control part (4) is arranged at the lower part of the desk lamp body (1), and the control module detects the included angle between the shoulders and the horizontal plane and the position of the neck in the picture according to the picture data and judges the position of the desk lamp body (1) relative to the user.
8. The desk lamp using the method for automatically detecting the camera range according to claim 4, wherein the control module further extracts the size information of the human skull in the picture and judges the distance between the desk lamp body (1) and the eyes of the user according to the information, and the control module corrects the adjustment result of the adjusting part (3) according to the distance information until the illumination range of the illuminating part (2) falls within the range seen by the eyes of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911227879.2A CN111401382B (en) | 2019-12-04 | 2019-12-04 | Method for automatically detecting camera range and table lamp using same |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911227879.2A CN111401382B (en) | 2019-12-04 | 2019-12-04 | Method for automatically detecting camera range and table lamp using same |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111401382A true CN111401382A (en) | 2020-07-10 |
| CN111401382B CN111401382B (en) | 2023-05-26 |
Family
ID=71432489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911227879.2A Active CN111401382B (en) | 2019-12-04 | 2019-12-04 | Method for automatically detecting camera range and table lamp using same |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111401382B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112989961A (en) * | 2021-02-22 | 2021-06-18 | 广州铁路职业技术学院（广州铁路机械学校） | Sitting posture identification method and desk lamp |
| CN113506132A (en) * | 2021-07-06 | 2021-10-15 | 树蛙信息科技(南京)有限公司 | Method and device for determining offline attention degree |
| CN113587386A (en) * | 2021-07-13 | 2021-11-02 | 青岛海信日立空调***有限公司 | Indoor unit of air conditioner |
| CN114842617A (en) * | 2021-02-02 | 2022-08-02 | 深圳慧安康科技有限公司 | Safety early warning method and device based on desk lamp, desk lamp and storage medium |
| CN114938556A (en) * | 2022-04-29 | 2022-08-23 | 中国科学院半导体研究所 | Automatic adjusting method and device for light of desk lamp, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103423657A (en) * | 2013-08-21 | 2013-12-04 | 步步高教育电子有限公司 | Intelligent lamp and intelligent reminding method thereof |
| JP2015231121A (en) * | 2014-06-04 | 2015-12-21 | シャープ株式会社 | Imaging apparatus, bioinstrumentation booth, imaging apparatus control method, program, and recording medium |
| CN105792480A (en) * | 2016-04-13 | 2016-07-20 | 惠州Tcl移动通信有限公司 | Intelligent desk lamp and lamp switching control method thereof |
| CN106981183A (en) * | 2017-05-04 | 2017-07-25 | 湖北工程学院 | Correcting sitting posture method and system |
| CN209012875U (en) * | 2018-12-27 | 2019-06-21 | 中科院合肥技术创新工程院 | Desk lamp with sitting posture arbitration functions |
| CN209495180U (en) * | 2018-12-28 | 2019-10-15 | 浙江凯耀照明股份有限公司 | A kind of sitting posture identification table lamp system based on machine vision |
| CN110458010A (en) * | 2019-07-05 | 2019-11-15 | 武汉迈格驷友科技有限公司 | A kind of intelligent desk lamp, a kind of sitting posture detecting method and a kind of electronic equipment |
-
2019
- 2019-12-04 CN CN201911227879.2A patent/CN111401382B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103423657A (en) * | 2013-08-21 | 2013-12-04 | 步步高教育电子有限公司 | Intelligent lamp and intelligent reminding method thereof |
| JP2015231121A (en) * | 2014-06-04 | 2015-12-21 | シャープ株式会社 | Imaging apparatus, bioinstrumentation booth, imaging apparatus control method, program, and recording medium |
| CN105792480A (en) * | 2016-04-13 | 2016-07-20 | 惠州Tcl移动通信有限公司 | Intelligent desk lamp and lamp switching control method thereof |
| CN106981183A (en) * | 2017-05-04 | 2017-07-25 | 湖北工程学院 | Correcting sitting posture method and system |
| CN209012875U (en) * | 2018-12-27 | 2019-06-21 | 中科院合肥技术创新工程院 | Desk lamp with sitting posture arbitration functions |
| CN209495180U (en) * | 2018-12-28 | 2019-10-15 | 浙江凯耀照明股份有限公司 | A kind of sitting posture identification table lamp system based on machine vision |
| CN110458010A (en) * | 2019-07-05 | 2019-11-15 | 武汉迈格驷友科技有限公司 | A kind of intelligent desk lamp, a kind of sitting posture detecting method and a kind of electronic equipment |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114842617A (en) * | 2021-02-02 | 2022-08-02 | 深圳慧安康科技有限公司 | Safety early warning method and device based on desk lamp, desk lamp and storage medium |
| CN112989961A (en) * | 2021-02-22 | 2021-06-18 | 广州铁路职业技术学院（广州铁路机械学校） | Sitting posture identification method and desk lamp |
| CN113506132A (en) * | 2021-07-06 | 2021-10-15 | 树蛙信息科技(南京)有限公司 | Method and device for determining offline attention degree |
| CN113587386A (en) * | 2021-07-13 | 2021-11-02 | 青岛海信日立空调***有限公司 | Indoor unit of air conditioner |
| CN114938556A (en) * | 2022-04-29 | 2022-08-23 | 中国科学院半导体研究所 | Automatic adjusting method and device for light of desk lamp, electronic equipment and storage medium |
| CN114938556B (en) * | 2022-04-29 | 2023-11-24 | 中国科学院半导体研究所 | Automatic adjusting method and device for light of desk lamp, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111401382B (en) | 2023-05-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111401382A (en) | Method for automatically detecting camera range and desk lamp using same | |
| US8902303B2 (en) | Apparatus connectable to glasses | |
| CN104202865B (en) | A kind of Intelligent lightening device | |
| CN112483924B (en) | AI eye-protecting desk lamp with sitting posture correction reminding function and implementation method thereof | |
| CN103908063A (en) | Intelligent desk with sitting posture correcting function and correcting method implemented by intelligent desk | |
| TWI362005B (en) | ||
| CN106060514A (en) | Device and method for controlling pose of television in multi-vision mode | |
| CN103908065A (en) | Intelligent desk with sitting posture correcting function and correcting method implemented by intelligent desk | |
| CN110290349B (en) | Lamp and method for detecting sitting posture state of user | |
| CN204807842U (en) | Intelligence glasses | |
| CN106600915B (en) | The method, apparatus and system that body correction is reminded | |
| CN110934591A (en) | Sitting posture detection method and device | |
| TW201205469A (en) | Display device and method for adjusting display orientation thereof | |
| CN114938556B (en) | Automatic adjusting method and device for light of desk lamp, electronic equipment and storage medium | |
| CN109785592A (en) | Desk lamp and its control method, computer storage medium | |
| CN205938439U (en) | Adjustable lazy people's support of intelligence distance and control system thereof | |
| CN110135321A (en) | A kind of device and method suitable for outdoor recognition of face | |
| CN103908066A (en) | Intelligent desk with sitting posture correcting function and correcting method implemented by intelligent desk | |
| CN214619150U (en) | Table lamp for monitoring sitting posture | |
| CN107329570A (en) | A kind of method that display device angle is automatically adjusted according to individual beholder position | |
| CN107775658A (en) | Adapt to human comfort automatically adjust screen and face apart from robot | |
| CN111144327B (en) | Method for improving recognition efficiency of face recognition camera of self-service equipment | |
| CN112617398A (en) | Self-adaptive adjusting table and table control system | |
| CN210344844U (en) | Face recognition device and electric adjusting device thereof | |
| CN214510023U (en) | Self-adaptive adjusting table and table control system |
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 |