CN118072345B - Interest capturing-based display method and system - Google Patents
Interest capturing-based display method and system Download PDFInfo
- Publication number
- CN118072345B CN118072345B CN202311567077.2A CN202311567077A CN118072345B CN 118072345 B CN118072345 B CN 118072345B CN 202311567077 A CN202311567077 A CN 202311567077A CN 118072345 B CN118072345 B CN 118072345B
- Authority
- CN
- China
- Prior art keywords
- information
- target
- interest
- head
- conductive metal
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000000007 visual effect Effects 0.000 claims abstract description 20
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 230000000694 effects Effects 0.000 claims abstract description 6
- 239000007788 liquid Substances 0.000 claims description 33
- 239000002184 metal Substances 0.000 claims description 33
- 238000007789 sealing Methods 0.000 claims description 26
- 238000012544 monitoring process Methods 0.000 claims description 21
- 230000007246 mechanism Effects 0.000 claims description 16
- 230000008859 change Effects 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 12
- 238000003384 imaging method Methods 0.000 claims description 11
- 238000001802 infusion Methods 0.000 claims description 11
- 238000012512 characterization method Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 210000005069 ears Anatomy 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 3
- 238000005034 decoration Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 210000003128 head Anatomy 0.000 description 43
- 230000036544 posture Effects 0.000 description 8
- 230000000875 corresponding effect Effects 0.000 description 7
- 238000007405 data analysis Methods 0.000 description 3
- 230000004424 eye movement Effects 0.000 description 3
- 239000000047 product Substances 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 206010014357 Electric shock Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013329 compounding Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
- G01L5/0028—Force sensors associated with force applying means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L1/00—Measuring force or stress, in general
- G01L1/20—Measuring force or stress, in general by measuring variations in ohmic resistance of solid materials or of electrically-conductive fluids; by making use of electrokinetic cells, i.e. liquid-containing cells wherein an electrical potential is produced or varied upon the application of stress
- G01L1/22—Measuring force or stress, in general by measuring variations in ohmic resistance of solid materials or of electrically-conductive fluids; by making use of electrokinetic cells, i.e. liquid-containing cells wherein an electrical potential is produced or varied upon the application of stress using resistance strain gauges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
-
- 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
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The application discloses a display method and a system based on interest capture, wherein the display method comprises the following steps: acquiring group image information of a plurality of targets in a demonstration scene, wherein the group image information is acquired at a overlook angle; identifying the group image data to obtain head characteristic information of each target; analyzing the predefined symmetrical characteristic in the head characteristic information to obtain the face horizontal orientation information of the target; acquiring the posture information of each target head; performing visual orientation estimation according to the face horizontal orientation information and the gesture information to obtain visual orientation information; based on the visual orientation information, the head position of the target and the predefined standard visual attention position, judging whether interest attention is carried out, if so, recording corresponding time, and obtaining attention duration. The application has the effects of reducing the implementation cost of automatic analysis of the interest points of the user group and being more beneficial to product popularization and technical application.
Description
Technical Field
The application relates to the technical field of multimedia interaction, in particular to a display method and a display system based on interest capturing.
Background
Compared with the traditional pure-structure black/green board, the intelligent blackboard integrates the functions of the black/green board, the projector, the white board, the teaching integrated machine and other teaching facilities, and has better teaching experience and interaction characteristics.
In the scene of training infants, preschool children (early education) interests and common sense in the form of videos and animations, there are such problems: when facing a plurality of children, the content of broadcast presentation is mostly relevant personnel, unified screening matching of mechanism, and receives regional, living background or other factor's influence, and the degree that different children are interesting to same thing is different, and this leads to unified arrangement planning's content suitability not good, and later stage is through the manual work to each group child continuously observe, investigation analysis, and the content of the corresponding adjustment broadcast presentation of again is consuming time and power relatively again.
Currently, patent publication No. CN113506027a discloses a course quality assessment and improvement method based on visual attention and teacher behavior of students, the attention information of the teacher of the students is obtained through an eye movement instrument, the teacher class is recorded through a photographing device, the distance between an eye tracking point and a wearer is obtained in real time by using a measuring method combining TensorFlow API frame target detection and the eye movement instrument, so as to obtain real-time gazing information of the user, and the video content is analyzed and correlated with the eye movement coordinates, so that the relationship between the attention information of the students and the teacher behavior and the key content of the class is obtained.
Above-mentioned technical scheme can help the teacher convenient understanding student's interest point in course, but: at present, equipment cost required for realizing accurate eye tracking is high, more eye tracking is applied to intelligent glasses used by monomers such as VR glasses, and under the scene, especially when the number of users is large, the interference is large, the data size is large, the analysis difficulty is large, and popularization and application are limited.
Disclosure of Invention
In order to reduce the implementation cost of automatic analysis of interest points of a user group, and facilitate product popularization and technical application, the application provides a display method and a display system based on interest capture.
In a first aspect, the present application provides a display method based on interest capturing, which adopts the following technical scheme:
A display method based on interest capture, comprising:
Acquiring group image information of a plurality of targets in a demonstration scene, wherein the group image information is acquired at a overlook angle;
identifying the group image data to obtain head characteristic information of each target;
Analyzing the predefined symmetrical characteristic in the head characteristic information to obtain the face horizontal orientation information of the target;
Acquiring the posture information of each target head; wherein the gesture information is detected through intelligent wearing decorations worn on the heads of the targets in advance;
Performing visual orientation estimation according to the face horizontal orientation information and the gesture information to obtain visual orientation information;
Judging whether interest attention is carried out or not based on the visual orientation information, the head position of the target and the predefined standard visual attention position, if so, recording corresponding time to obtain attention duration, continuously monitoring pressure information of a target bearing surface in a demonstration scene in the process, and recording based on a time axis;
correcting the concerned duration of each target according to the change of the pressure information on the time axis;
updating the concerned time length of each target, counting the total concerned time length of the past demonstration and calculating the concerned time length mean value;
And sequencing each presentation content based on the total attention duration and the attention duration mean value, and adjusting the presentation activities of the later time according to the sequencing.
Optionally, the gesture information is collected through an IMU unit, and if the face horizontal orientation information is obtained for the first time in any field of demonstration process, then the predefined symmetric features in the head taking feature information are analyzed with a preset frequency T;
And updating the face horizontal orientation information of the target according to the gesture information between any two times of analysis of the predefined symmetrical characteristic in the head taking characteristic information.
Optionally, the analyzing the symmetry features predefined in the header feature information includes:
the predefined symmetry feature is the ear;
connecting the upper auricles of two ears of the same head to obtain a head width line;
Drawing a perpendicular bisector based on the head width direction line;
the direction of the perpendicular bisector similar to the front outline of the upper ear is the face horizontal orientation information of the target.
Optionally, the collecting mode of the group image information collected at the overlook angle includes:
arranging mirror surfaces on the tops of a plurality of targets in advance;
and acquiring imaging of a plurality of targets on the mirror surface to obtain group image information.
Optionally, the characterization of each smart pendant is differentiated, and the head position of the target is calculated by the following ways:
Identifying each target based on the characterization of the smart pendant;
Calculating the imaging position of the head characteristic information of the target relative to the group image information;
the imaging position is defined as the head position of the subject.
In a second aspect, the present application provides a display system based on interest capture, which adopts the following technical scheme:
An interest capture based display system comprising a control module arranged to load and execute a computer program for an interest capture based display method as any one of the above.
Optionally, the intelligent pendant comprises an intelligent pendant for gesture detection, a camera for collecting group image information under a overlooking view angle, and a pressure monitoring mechanism for monitoring the pressure of a target bearing surface in a demonstration scene.
Optionally, the pressure monitoring mechanism includes:
A base plate laid in the presentation scene;
the buffer box is arranged around the edge of the bottom plate and is surrounded by a medium groove;
the flexible panel is arranged above the bottom plate, is adapted to the cross section of the medium groove and has an upper surface lower than the height of the inner cavity of the buffer box;
A sealing tube, one end of which is fixed to the flexible panel and the other end of which is sealed;
The conductive metal sheets are arranged in the sealing pipes, and two conductive metal sheets which are parallel to each other are arranged in each sealing pipe;
The plurality of resistance blocks are distributed along the length direction of a certain conductive metal sheet;
a permanent magnet for bringing the two conductive metal sheets together;
the medium tank is filled with medium liquid, and an opening at the lower part of the side wall of the buffer box is communicated with the inner cavity and the medium tank; the bottom plate is provided with a groove, and the lower end of the sealing tube extends into the groove vertically;
One end of one conductive metal sheet is fixed at the upper end of the sealing tube, the lower end is a free end, a resistance block is arranged on one surface of the other conductive metal sheet facing the free end, and a soft magnetic sheet is fixed on one surface of the other conductive metal sheet facing away from the free end; the permanent magnet is fixed on the side wall of the groove, and one surface of the resistor block, which faces to the conductive metal sheet with both ends fixed, is an inclined surface and is inclined downwards;
The sealing pipes are uniformly distributed below the flexible panel and are divided into a plurality of groups, and the conductive metal sheets in the sealing pipes in the same group are mutually connected in parallel.
Optionally, the control module is electrically connected with a liquid level sensing unit and an infusion pump, the liquid level sensing unit is used for detecting the liquid level in the buffer box, the infusion pump is used for communicating the buffer box with the medium liquid storage container through a pipeline, and the buffer box is communicated with the atmosphere; the control module is configured to: when the pressure information fed back by the pressure monitoring mechanism accords with an unmanned scene, if the liquid level value fed back by the liquid level sensing unit is lower than a preset standard liquid level, the control module controls the infusion pump to supplement medium liquid into the buffer box.
Optionally, the control module is configured to: if the pressure change information of a certain target is larger than a preset first threshold value and the duration t is larger than a preset second threshold value in one demonstration process, the deleting amount in the time of the attention duration correction is restored, and the attention duration of the corresponding target is updated.
In summary, the present application includes at least one of the following beneficial technical effects: the method can identify, track and record the concerned duration of each target on the demonstration content, estimate the interests of each target according to the concerned duration, facilitate the user to adjust the display content of the intelligent blackboard and the like, and the implementation cost of the automatic analysis of the interest points of the user group is relatively low because the head images of the targets are matched with the intelligent pendant capable of carrying out the head gesture detection; and because the time length of attention can be corrected by utilizing the pressure change of the target on the target bearing surface in the demonstration scene, the product popularization and the technology application are facilitated, and the analysis is also more accurate.
Drawings
FIG. 1 is a schematic flow chart of the method of the present application;
FIG. 2 is a schematic diagram of a pressure monitoring mechanism according to the present application;
FIG. 3 is an enlarged schematic view of portion A of FIG. 2;
fig. 4 is a system block diagram of the system of the present application.
Reference numerals illustrate: 1. a bottom plate; 11. a groove; 2. a buffer box; 3. a medium tank; 41. a liquid level sensing unit; 42. an infusion pump; 5. a flexible panel; 6. sealing the tube; 7. a conductive metal sheet; 71. soft magnetic sheets; 8. a resistor block; 9. permanent magnets.
Detailed Description
The application is described in further detail below with reference to fig. 1-4.
The embodiment of the application discloses a display method based on interest capture, which is more used for scenes facing infants and preschool children as audience main bodies, and the difficulty of manually researching and analyzing to know interest points is further increased because the group has limited expression capability.
Referring to fig. 1, the interest capture-based display method includes:
group image information of a plurality of targets in a demonstration scene which can be early education and preschool education class scenes is acquired, wherein the targets are children in class. In the process of collecting images by a camera, the method is distinguished in that:
Arranging mirror surfaces on the tops of a plurality of targets in advance; i.e. mounting a mirror on top of the room;
and acquiring imaging of a plurality of targets on the mirror surface to obtain group image information.
The existing intelligent blackboard can be integrally provided with a camera for collecting images, but the shooting angle of the camera is inclined downward, and under the shooting angle, if a plurality of people exist in a scene, the characteristics of certain targets are easily shielded by the others, so that the implementation of the method is influenced; if the mode is adopted, imaging is acquired from the mirror surface, and group image information is acquired, the situation can be avoided; because the image at the overlook angle is already imaged on the mirror surface, and the mirror surface is flat and is not blocked, the imaging is acquired at this time, and a group image which is relatively not blocked can be obtained for data analysis.
On the basis of the above, the group image data is identified, and head characteristic information of each target is obtained.
Because image recognition (human body recognition) is the prior art, the description is omitted; in this embodiment, the features that need to be identified from the image are: head features, ear features, foot features, etc.; it can be understood that children are in sitting postures in early education and other scenes, so that the foot characteristics and other characteristic information of the front and back of the human body can be clearly obtained from the overlooking view.
Analyzing the predefined symmetrical characteristic in the head characteristic information to obtain the face level orientation information of the target
It is known that the features of the human head such as ears, eyes, etc. are normally symmetrical structures; in this embodiment, the symmetrical feature is taken as an ear as an example, and the analyzing the symmetrical feature predefined in the head characteristic information includes:
connecting the upper auricles of two ears of the same head to obtain a head width line;
Drawing a perpendicular bisector based on the head width direction line;
the direction of the perpendicular bisector similar to the front outline of the upper ear is the face horizontal orientation information of the target.
Because there is still a difference in the characteristic profile of the ear from the top view, such as: the width of the front outline is larger than the thickness of the rear outline, so that besides drawing a midrange pointing to the front and rear of a human body by utilizing the symmetrical characteristic of ears, the contour characteristic of ears can be further utilized to determine which end of the midrange is the front side of the human body, and the face horizontal orientation information is obtained.
The method further comprises the following steps: and acquiring the posture information of each target head.
In the method, the head posture of the target mainly refers to the inclination angle, but:
1) The method does not continue to analyze the head gesture by using the image; because only the group target image in the overlooking view cannot obtain information about how much the head is lifted and lowered;
2) The method does not adopt a gyroscope, but collects attitude information by means of an IMU unit (sensor); although the gyroscope can obtain the posture change information when the head is lifted and lowered, the movement parameters of the head cannot be calculated based on the feedback of the gyroscope, and the interest analysis of the method actually needs to continuously track the head of the target, so that if the gyroscope is the gyroscope, the image data analysis needs to be continuously carried out in the implementation process of the method, and the operation pressure of a computer, a server and the like is greatly increased. If the IMU unit is adopted to collect the head posture information, after the face horizontal orientation information is obtained for the first time, the face horizontal orientation information is obtained only by updating according to the three-dimensional rotation quantity fed back by the IMU, and then the data analysis quantity in the implementation process of the method is greatly reduced.
The exemplary illustration, the IMU may be integrated on a smart pendant, such as: the battery and the circuit structure with the wireless communication unit are correspondingly arranged in the head ring and the hairpin so as to achieve the data return function.
Based on the setting, if face horizontal orientation information is obtained for the first time in any one presentation process, then the symmetrical characteristic predefined in the head taking characteristic information is analyzed according to a preset frequency T;
and updating the face horizontal orientation information of the target according to the gesture information before analyzing the predefined symmetrical characteristic in the head characteristic information for any two times.
At this time, the horizontal orientation of the image analysis face at the frequency T may be cross-compared with the result updated based on the IMU feedback, to verify whether the image analysis is normal or not, and whether the sensor is normal or not.
Because the IMU unit collects three-dimensional posture (change) information, that is, rotation information when the head is lifted and lowered can be obtained in addition to horizontal rotation information of the head, the method can perform visual orientation estimation according to the horizontal orientation information and posture information of the face to obtain visual orientation information.
For example: assuming that the face horizontal orientation is 30 ° north-east, the IMU unit feedback data analyzed a 30 ° counterclockwise rotation, the estimated view angle orientation is 30 ° north-east and 30 ° head-up.
Subsequently, the method comprises the following steps: based on the visual orientation information, the head position of the target, and the predefined standard visual attention position, it is determined whether interest attention is being conducted.
For example: and establishing a three-dimensional coordinate system, marking the head position of the target and the predefined standard visual attention position in the coordinate system, drawing a line representing the sight line according to the visual angle direction, and detecting whether the line intersects with a coordinate point (a coordinate point set) corresponding to the predefined standard visual attention position or not, so as to judge whether interest attention is carried out.
If the judgment result is yes, corresponding time is recorded, the concerned duration is obtained, pressure information of the target bearing surface in the demonstration scene is continuously monitored in the process, and recording is carried out based on a time axis.
The time length of interest of each target is corrected based on the change in the pressure information on the time axis (in the present method, it is considered that the continuous movement of the target affects the concentration, and the movement of the target causes the pressure change, so correction is performed as necessary).
And updating the concerned time length of each target, counting the total concerned time length of the past demonstration and calculating the concerned time length mean value.
And sequencing each presentation content based on the total attention duration and the attention duration mean value, and adjusting the presentation activities of the later time according to the sequencing.
According to the setting, the method can identify, track and record the concerned time length of each target on the demonstration content, and estimate the interest of each target according to the concerned time length, so that the user can conveniently adjust the display content of an intelligent blackboard and the like, and the implementation cost of the automatic analysis of the interest points of the user group is relatively low because the head images of the targets are matched with the intelligent pendant capable of carrying out head gesture detection; and because the time length of attention can be corrected by utilizing the pressure change of the target on the target bearing surface in the demonstration scene, the product popularization and the technology application are facilitated, and the analysis is also more accurate.
In one embodiment of the method, the characterization of each smart pendant is differentiated, for example: when the intelligent pendant is a hairpin, distinguishing the smart pendant by different patterns and colors; or a plurality of LED lamps are configured, so that the LEDs are lightened in different lamp colors and different flicker frequencies; at this time, the head position of the target is calculated by:
Identifying each target based on the characterization of the smart pendant;
Calculating the imaging position of the head characteristic information of the target relative to the group image information;
the imaging position is defined as the head position of the subject.
According to the setting, the difficulty of image recognition and distinguishing when the method continuously tracks each target can be effectively reduced.
The embodiment of the application also discloses a display system based on interest capture.
Referring to fig. 4, the interest capture based display system includes a control module, which may be a control motherboard integrated into a smart blackboard, configured to load and execute a computer program for any of the interest capture based display methods described above.
The system also comprises an intelligent pendant for gesture detection, a camera for collecting group image information under a overlooking view angle and a pressure monitoring mechanism for monitoring the pressure of a target bearing surface in a demonstration scene.
The structure of the intelligent pendant and the installation and use mode of the camera are already described in the embodiment of the method, so that the description is omitted; the following explains the pressure monitoring mechanism implemented by the compounding method: the pressure monitoring mechanism may be a plurality of membrane pressure sensors that are deployed in the demonstration scene.
Referring to fig. 2 and 3, in another embodiment of the present system, to further reduce cost, the pressure monitoring mechanism includes:
A base plate 1 laid in a presentation scene;
a buffer box 2 which is arranged around the edge of the bottom plate 1 and is surrounded by a medium groove 3;
a flexible panel 5 disposed above the bottom plate 1 and adapted to the cross section of the medium tank 3;
a seal tube 6 having one end fixed to the flexible panel 5 and the other end sealed;
a conductive metal thin plate 7 provided in the sealing pipes 6 and having two conductive metal thin plates 7 parallel to each other in each sealing pipe 6;
a plurality of resistance blocks 8 arranged along the longitudinal direction of one of the conductive metal thin plates 7;
a permanent magnet 9 for bringing the two conductive metal sheets 7 close to each other.
The medium groove 3 is filled with medium liquid which can be oily medium so as to reduce electric shock risk; the lower opening of the side wall of the buffer box 2 is communicated with the inner cavity and the medium groove 3; the bottom plate 1 is provided with a groove 11, the sealing tube 6 is vertical, and the lower end of the sealing tube extends into the groove 11. One end of one conductive metal sheet 7 is fixed to the upper end of the sealing tube 6, the lower end is a free end, and the surface facing the other conductive metal sheet 7 is provided with a resistor block 8, and the surface facing away from the other conductive metal sheet 7 is provided with a soft magnetic sheet 71. The permanent magnet 9 is fixed to the side wall of the recess 11. The surface of the resistor block 8 facing the conductive metal sheet 7 with both ends fixed is an inclined surface and is inclined downward.
The plurality of sealing tubes 6 are uniformly distributed below the flexible panel 5 and divided into a plurality of groups, for example: 36 are marked as a group according to the specification of 6*6; the conductive metal sheets 7 in the same set of sealed tubes 6 are connected in parallel with each other.
According to the setting, the current/voltage sampling is carried out on each group during use, so as to achieve the monitoring purpose.
When the target (child) does not enter the demonstration scene, the flexible panel 5 floats under the action of the buoyancy, and at this time, each group of sealing tubes 6 corresponds to one current/voltage parameter.
When a certain object is stepped on, the sealing tube 6 is sunk, and at the moment, the permanent magnet 9 is matched with the soft magnetic sheet 71 on the conductive metal sheet 7 with one free end, so that the conductive metal sheet 7 is close to the other conductive metal sheet 7, namely, the resistor block 8 is contacted with the other conductive metal sheet 7. At this time, the group of structures has another corresponding current/voltage parameter after being powered on.
If the target shakes in the above area and the like, the position of the soft magnetic sheet 71 relative to the permanent magnet 9 is changed due to the lifting of the part of the sealing tube 6, so that the thrust generated by the permanent magnet 9 is changed, the number of the connected resistor blocks 8 is changed, the total resistance value is changed, and the current/voltage is changed, so that the current/voltage change information can be equivalent to the pressure change information, and the application can be used for evaluating whether the target shakes, moves and the like.
The inclined surface of the resistor block 8 can be used for matching with the thrust generated when the sealing tube 6 is lifted to different positions relative to the permanent magnet 9, so that the resistor blocks 8 with various heights can be better connected into a circuit.
According to the arrangement, the pressure monitoring mechanism is soft to step on, so that the pressure monitoring mechanism can also protect children when being applied to early education and other scenes, and is not only used for detecting whether each target is moving or not.
In one embodiment of the present application, it is considered that the time when the pressure change information (i.e., the current/voltage information change frequency/amplitude) is greater than the preset threshold value is distraction, and thus the corresponding stop record is the time of interest, i.e., the time of interest correction is performed.
In one embodiment of the application, each target is considered to have habit of focusing on itself, so the control module is set to:
If the pressure change information of a certain target in one demonstration process is larger than a preset first threshold value and the duration t is larger than a preset second threshold value, the target is considered to be not distraction, but habit thereof, so that the pruning amount in the correction of the concerned duration is recovered.
Referring to fig. 2 and 4, it can be understood that, in order to allow the medium liquid between the bottom plate 1 and the flexible panel 5 not only to prop the flexible panel 5 for rotation, the buffer box 2 needs to be communicated with the atmosphere, i.e. the medium liquid can be extruded in the buffer box 2 to rise; the medium liquid is communicated with the atmosphere, which leads to water volatilization, etc., and the liquid level is lowered after long-term use, thus affecting the use effect of the pressure monitoring mechanism, therefore, in one embodiment of the system, a liquid level sensing unit 41 (a floating ball liquid level meter) is arranged in the buffer box 2, and the buffer box 2 is communicated with an infusion pump 42 through a pipeline, and the infusion pump 42 is communicated with a container storing the medium liquid. The liquid level sensing unit 41 and the infusion pump 42 are electrically connected to the control module, respectively.
When the pressure information fed back by the pressure monitoring mechanism accords with the unmanned scene, if the liquid level value fed back by the liquid level sensing unit 41 is lower than the preset standard liquid level, the control module controls the infusion pump 42 to supplement the medium liquid into the buffer box 2 until the standard liquid level is reached.
The above embodiments are not intended to limit the scope of the present application, so: all equivalent changes in structure, shape and principle of the application should be covered in the scope of protection of the application.
Claims (10)
1. A display method based on interest capture, comprising:
Acquiring group image information of a plurality of targets in a demonstration scene, wherein the group image information is acquired at a overlook angle;
identifying the group image data to obtain head characteristic information of each target;
Analyzing the predefined symmetrical characteristic in the head characteristic information to obtain the face horizontal orientation information of the target;
Acquiring the posture information of each target head; wherein the gesture information is detected through intelligent wearing decorations worn on the heads of the targets in advance;
Performing visual orientation estimation according to the face horizontal orientation information and the gesture information to obtain visual orientation information;
Judging whether interest attention is carried out or not based on the visual orientation information, the head position of the target and the predefined standard visual attention position, if so, recording corresponding time to obtain attention duration, continuously monitoring pressure information of a target bearing surface in a demonstration scene in the process, and recording based on a time axis;
correcting the concerned duration of each target according to the change of the pressure information on the time axis;
updating the concerned time length of each target, counting the total concerned time length of the past demonstration and calculating the concerned time length mean value;
And sequencing each presentation content based on the total attention duration and the attention duration mean value, and adjusting the presentation activities of the later time according to the sequencing.
2. The interest-capture-based display method of claim 1, wherein: the attitude information is acquired through an IMU unit, and if the face horizontal orientation information is obtained for the first time in any one field of demonstration process, the predefined symmetrical features in the head taking feature information are analyzed at a preset frequency T;
And updating the face horizontal orientation information of the target according to the gesture information between any two times of analysis of the predefined symmetrical characteristic in the head taking characteristic information.
3. The interest-capture-based display method of claim 1, wherein: analyzing the symmetry features predefined in the header feature information, which comprises the following steps:
the predefined symmetry feature is the ear;
connecting the upper auricles of two ears of the same head to obtain a head width line;
Drawing a perpendicular bisector based on the head width direction line;
the direction of the perpendicular bisector similar to the front outline of the upper ear is the face horizontal orientation information of the target.
4. The interest-capture-based display method of claim 1, wherein: the group image information acquired at the overlook angle is acquired by the following steps:
arranging mirror surfaces on the tops of a plurality of targets in advance;
and acquiring imaging of a plurality of targets on the mirror surface to obtain group image information.
5. The interest-capture-based display method of claim 4, wherein: distinguishing the characterization of each intelligent pendant, wherein the head position of the target is calculated by the following steps:
Identifying each target based on the characterization of the smart pendant;
Calculating the imaging position of the head characteristic information of the target relative to the group image information;
the imaging position is defined as the head position of the subject.
6. A display system based on interest capture, characterized by: comprising a control module arranged to load and execute a computer program of the interest capture based display method of any of claims 1 to 3.
7. The interest-based display system of claim 6, wherein: the intelligent pendant comprises an intelligent pendant for gesture detection, a camera for collecting group image information under a overlooking view angle and a pressure monitoring mechanism for monitoring the pressure of a target bearing surface in a demonstration scene.
8. The interest-based display system of claim 7, wherein: the pressure monitoring mechanism includes:
a base plate (1) laid in a presentation scene;
the buffer box (2) is arranged around the edge of the bottom plate (1) and is surrounded by a medium groove (3);
A flexible panel (5) which is arranged above the bottom plate (1), is adapted to the cross section of the medium groove (3) and has an upper surface lower than the height of the inner cavity of the buffer box (2);
a sealing tube (6) having one end fixed to the flexible panel (5) and the other end sealed;
a conductive metal sheet (7) disposed in the sealing pipes (6) and having two conductive metal sheets (7) parallel to each other in each sealing pipe (6);
a plurality of resistance blocks (8) which are arranged along the length direction of one conductive metal sheet (7);
a permanent magnet (9) for bringing the two conductive metal sheets (7) together;
the medium tank (3) is filled with medium liquid, and an opening at the lower part of the side wall of the buffer box (2) is communicated with the inner cavity and the medium tank (3); a groove (11) is formed in the bottom plate (1), and the sealing tube (6) extends vertically and the lower end of the sealing tube extends into the groove (11);
One end of one conductive metal sheet (7) is fixed at the upper end of the sealing tube (6), the lower end is a free end, a resistor block (8) is arranged on one surface of the other conductive metal sheet (7), and a soft magnetic sheet (71) is fixed on one surface of the other conductive metal sheet (7) facing away from the other conductive metal sheet; the permanent magnet (9) is fixed on the side wall of the groove (11), and one surface of the resistor block (8) facing the conductive metal sheet (7) with both ends fixed is an inclined surface and is inclined downwards;
the sealing pipes (6) are uniformly distributed below the flexible panel (5) and are divided into a plurality of groups, and the conductive metal sheets (7) in the sealing pipes (6) of the same group are mutually connected in parallel.
9. The interest-based display system of claim 8, wherein: the control module is electrically connected with a liquid level sensing unit (41) and an infusion pump (42), the liquid level sensing unit (41) is used for detecting the liquid level in the buffer box (2), the infusion pump (42) is used for communicating the buffer box (2) with a medium liquid storage container through a pipeline, and the buffer box (2) is communicated with the atmosphere; the control module is configured to: when the pressure information fed back by the pressure monitoring mechanism accords with an unmanned scene, if the liquid level value fed back by the liquid level sensing unit (41) is lower than a preset standard liquid level, the control module controls the infusion pump (42) to supplement medium liquid into the buffer box (2).
10. The interest-based display system of claim 6, wherein: the control module is configured to: if the pressure change information of a certain target is larger than a preset first threshold value and the duration t is larger than a preset second threshold value in one demonstration process, the deleting amount in the time of the attention duration correction is restored, and the attention duration of the corresponding target is updated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311567077.2A CN118072345B (en) | 2023-11-22 | 2023-11-22 | Interest capturing-based display method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311567077.2A CN118072345B (en) | 2023-11-22 | 2023-11-22 | Interest capturing-based display method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118072345A CN118072345A (en) | 2024-05-24 |
| CN118072345B true CN118072345B (en) | 2024-07-26 |
Family
ID=91096108
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311567077.2A Active CN118072345B (en) | 2023-11-22 | 2023-11-22 | Interest capturing-based display method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118072345B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111563449A (en) * | 2020-04-30 | 2020-08-21 | 上海交通大学 | Real-time classroom attention detection method and system |
| CN112465249A (en) * | 2020-12-04 | 2021-03-09 | 黄河水利职业技术学院 | Human resource distribution system based on interestingness |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110308790A (en) * | 2019-06-04 | 2019-10-08 | 宁波视睿迪光电有限公司 | The image adjusting device and system of teaching demonstration |
| EP3970060A1 (en) * | 2019-06-10 | 2022-03-23 | Huawei Technologies Co., Ltd. | Driver attention detection using heat maps |
| WO2022224173A1 (en) * | 2021-04-21 | 2022-10-27 | Cipia Vision Ltd. | Systems and methods for determining driver control over a vehicle |
| CN112906633B (en) * | 2021-03-18 | 2021-11-02 | 南通师范高等专科学校 | Teaching optimization method based on student attention |
| CN113449192A (en) * | 2021-07-07 | 2021-09-28 | 中国银行股份有限公司 | Education resource recommendation method based on mobile banking and related device |
| WO2023002496A1 (en) * | 2021-07-18 | 2023-01-26 | Doshi Payal | Smart e-learning system using adaptive video lecture delivery based on attentiveness of the viewer |
| CN114187611A (en) * | 2021-12-08 | 2022-03-15 | 北京大学 | Attention analysis method, attention analysis system, electronic equipment and storage medium |
| CN115600922A (en) * | 2022-10-09 | 2023-01-13 | 厦门优优汇联信息科技股份有限公司（Cn） | Multidimensional intelligent teaching quality assessment method and system |
-
2023
- 2023-11-22 CN CN202311567077.2A patent/CN118072345B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111563449A (en) * | 2020-04-30 | 2020-08-21 | 上海交通大学 | Real-time classroom attention detection method and system |
| CN112465249A (en) * | 2020-12-04 | 2021-03-09 | 黄河水利职业技术学院 | Human resource distribution system based on interestingness |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118072345A (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109284737A (en) | A kind of students ' behavior analysis and identifying system for wisdom classroom | |
| CN103729981B (en) | A kind of child sitting gesture monitoring intelligent terminal | |
| CN107609516B (en) | Adaptive eye movement method for tracing | |
| CN107247511A (en) | A kind of across object exchange method and device based on the dynamic seizure of eye in virtual reality | |
| CN108257137A (en) | A kind of angle measurement method and system of the automatic interpretation of view-based access control model hot spot | |
| CN105578044A (en) | Panoramic view adaptive teacher image analysis method | |
| CN109084350A (en) | A kind of kitchen ventilator and oil smoke concentration detection method having filtering functions vision-based detection module | |
| CN111273232B (en) | Indoor abnormal condition judging method and system | |
| CN111399634B (en) | Method and device for recognizing gesture-guided object | |
| CN112016492A (en) | Teaching attention monitoring system and method based on vision | |
| CN118072345B (en) | Interest capturing-based display method and system | |
| EP4354401A1 (en) | Method and system of detecting obstacle elements with a visual aid device | |
| CN107094232A (en) | Panoramic video direct broadcast service device | |
| TWI478099B (en) | Learning-based visual attention prediction system and mathod thereof | |
| CN109089032A (en) | A kind of smog vision imaging device | |
| CN107172383A (en) | A kind of Obj State detection method and device | |
| CN109028225A (en) | A kind of kitchen ventilator and oil smoke concentration detection method of the fixed vision detection system of band | |
| CN110081828A (en) | Machine vision gap of the shield tail detection image grid search-engine point reliability filter method | |
| JP2020140336A (en) | Structure detection device, structure detection method, and structure detection program | |
| CN115719464A (en) | Water meter durability device water leakage monitoring method based on machine vision | |
| CN110738109B (en) | Method, device and computer storage medium for detecting user standing | |
| KR101502683B1 (en) | Instructor Tracing System Using 3 Dimensional Sensing Module | |
| CN209013297U (en) | A kind of kitchen ventilator of the fixed vision detection system of band | |
| KR101192300B1 (en) | Water level detection method using k-means clustering | |
| CN209013288U (en) | A kind of kitchen ventilator having filtering functions vision-based detection module |
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 |