Painting concentration detection method and system

Abstract

The invention relates to the technical field of video image recognition, in particular to a drawing concentration detection method and system.The drawing video stream of each student is collected in real time, a plurality of feature frame images of the drawing video stream are obtained, and each feature frame image is divided into a plurality of drawing areas; newly-added drawing sub-regions are screened according to the image difference of the drawing regions in the adjacent feature frames, the drawing personality category of the student is determined according to the feature set degree of the newly-added drawing sub-regions, and the time window and the feature weight of drawing concentration detection are determined according to the drawing personality category of the student; whether the drawing concentration of the student is abnormal or not is judged based on the feature weight of the concentration detection of the student, so that a personalized concentration evaluation mode is formulated for the students with different drawing habits, and the accuracy of a concentration evaluation result is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of video image recognition, and in particular to a method and system for detecting concentration in painting. Background Art

[0002] In the field of education, the assessment of students' concentration has always been an important research direction. Traditionally, the detection of concentration during the painting process mainly relies on the subjective observation of teachers. Teachers rely on their own experience to roughly judge students' concentration by observing whether students look around while painting, whether they frequently fiddle with objects unrelated to painting, and whether the painting process is coherent. However, this method has many limitations. On the one hand, teachers' observations are easily affected by subjective factors, and different students have different behavioral habits, so the evaluation results lack consistency and accuracy. On the other hand, manual observation is difficult to comprehensively and accurately record and analyze the various performances of students in the painting process, and some abnormal moments of concentration are easy to be missed. Therefore, it is a technical problem that needs to be solved urgently to develop personalized concentration assessment methods for students with different habits to avoid misjudgments caused by a single assessment model.

[0003] For example, China Patent Application Publication No.: CN117197880A, the invention discloses a concentration monitoring method and system, including the following steps: 1. Collect image information of the person to be tested and the equipment using an image acquisition device; 2. Micro-behavior recognition detection; 3. Obtain the line of sight trajectory of the person to be tested on the display screen, and compare the similarity between the two in combination with the attention heat map of the display screen; 4. Analyze the movement trend of the line of sight trajectory to determine whether it is consistent with prior knowledge; 5. Detect the eye features of the person to be tested, obtain the blinking frequency of the person to be tested, and determine whether it is normal; 6. Combining the above test results and through weighted calculation, determine whether the person to be tested is in a working state.

[0004] The prior art still has the following problems:

[0005] The existing technology does not take into account the different drawing habits of students, which will affect the accuracy of drawing concentration detection. The existing technology cannot formulate personalized concentration assessment methods for students with different drawing habits, which affects the accuracy of the concentration assessment results. Summary of the invention

[0006] To this end, the present invention provides a method and system for detecting concentration in drawing, so as to overcome the problem that the prior art cannot formulate a personalized concentration assessment method for students with different drawing habits, which affects the accuracy of the concentration assessment results.

[0007] To achieve the above object, the present invention provides a method for detecting concentration in painting, comprising:

[0008] Collect the painting video streams of each student in real time, obtain a number of feature frame images of the painting video stream at a preset time interval, and divide each feature frame image into a number of painting areas;

[0009] Screen for new painting sub-areas based on the image differences of the painting areas in adjacent feature frames, and determine the painting personality category of the student according to the feature aggregation degree of the new painting sub-areas;

[0010] Determine the time window and feature weights for painting concentration detection according to the painting personality category of the student, including,

[0011] Based on the area ratio of the newly added painting pixel points in adjacent frame images of the painting video stream within a preset feature monitoring period, determine whether the student enters the window feature stage. Based on the determination result, determine the first time window, and determine the first feature weight according to the number of overwriting times within the first time window;

[0012] Or, determine whether the painting area of the student has switched based on the area ratio of the newly added painting pixel points in adjacent frame images. Based on the determination result, determine the second time window, and obtain the brush stroke speed parameter within the second time window to determine the second feature weight;

[0013] Based on the feature weights of the student's concentration detection, determine whether there is an abnormality in the student's painting concentration.

[0014] Furthermore, the process of screening for new painting sub-areas includes,

[0015] If the image difference of the painting area in adjacent feature frames meets the new area condition, then screen the painting area as a new painting sub-area;

[0016] The new area condition is that there are newly added pixel points within the painting area.

[0017] Furthermore, the process of determining the painting personality category of the student includes,

[0018] Calculate the area overlap degree of the new painting sub-areas corresponding to adjacent frames, and determine the area overlap degree as the feature aggregation degree;

[0019] If the feature aggregation degree of the student meets the overall painting condition, then the painting personality category of the student is determined as the first painting personality category;

[0020] If the feature aggregation degree of the student does not meet the overall painting condition, then the painting personality category of the student is determined as the second painting personality category;

[0021] Among them, the overall painting condition is that the feature aggregation degree is not zero.

[0022] Furthermore, the process of determining the time window and feature weights for painting concentration detection includes,

[0023] If the painting personality category of the student is determined to be the first painting personality category, then it is determined whether the student enters the window feature stage based on the area ratio of the newly added painting pixel points in adjacent frame images within a preset feature monitoring period, a first time window is determined based on the determination result, and a first feature weight is determined according to the number of scribbling times within the first time window;

[0024] If the painting personality category of the student is determined to be the second painting personality category, then it is determined whether the painting area of the student has switched based on the area ratio of the newly added painting pixel points in adjacent frame images, a second time window is determined based on the determination result, and a brush stroke speed parameter within the second time window is obtained to determine a second feature weight.

[0025] Further, the process of determining whether the student enters the window feature stage and determining the first time window includes,

[0026] Obtain the area ratio of the newly added painting pixel points in several adjacent frame images within the feature monitoring period;

[0027] If several area ratios within the feature monitoring period meet the first window determination condition, it is determined that the student enters the window feature stage, and the feature monitoring period is determined as the first time window;

[0028] Among them, the first window determination condition is that the area ratios obtained by several calculations do not exceed a preset detailed area ratio threshold.

[0029] Further, the process of determining the first feature weight includes,

[0030] Obtain the number of scribbling times within the first time window, calculate the ratio of the window duration of the first time window to the number of scribbling times, and determine the ratio as the first feature weight.

[0031] Further, the process of determining whether the painting area of the student has switched and determining the second time window includes,

[0032] Calculate the area ratio of the newly added painting pixel points in adjacent frame images;

[0033] If the area ratio of the adjacent frames meets the second window determination condition, it is determined that the painting area of the student has switched, and a second time window with a preset duration is determined based on the latter frame of the adjacent frames as the reference moment, and the second time window includes the reference moment;

[0034] Among them, the second window determination condition is that the area ratio exceeds a preset switching area threshold.

[0035] Furthermore, the process of determining the second feature weight includes:

[0036] The pen stroke velocity parameters corresponding to several moments in the second time window are obtained, the variance of the pen stroke velocity parameters corresponding to the several moments is calculated, and the variance is determined as the second feature weight.

[0037] Furthermore, the process of determining whether the student's drawing concentration is abnormal includes:

[0038] If the first feature weight of the student does not meet the first normal concentration condition, or the second feature weight does not meet the second normal concentration condition, it is determined that the student's painting concentration is abnormal;

[0039] Among them, the first normal concentration condition is that the first feature weight does not exceed a preset first feature weight reference value, and the second normal concentration condition is that the second feature weight does not exceed a preset second feature weight reference value.

[0040] Furthermore, the present invention also provides a painting concentration detection system, comprising:

[0041] A feature extraction module, which includes an image acquisition unit and an image information processing unit;

[0042] The image acquisition unit is used to collect the painting video stream of each student in real time;

[0043] The image information processing unit is used to obtain a number of feature frame images of the painting video stream, divide each feature frame image into a number of painting areas, screen a newly added painting sub-area, determine the student's painting personality category according to the feature aggregation degree of the newly added painting sub-area, and obtain the area ratio of the newly added painting pixel points of adjacent frame images;

[0044] A concentration monitoring module, which is connected to the feature extraction module and includes a concentration recognition unit and a behavior monitoring unit;

[0045] The concentration recognition unit is used to determine the time window and feature weight of the painting concentration detection, and the behavior monitoring unit is used to obtain the number of corrections made by the student and the stroke speed parameter of the student;

[0046] A determination module is connected to the feature extraction module and the concentration monitoring module to determine whether there is any abnormality in the student's painting concentration.

[0047] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention collects the painting video stream of each student in real time, obtains several feature frame images of the painting video stream, divides each feature frame image into several painting areas, screens new painting sub-areas according to the image differences of the painting areas in adjacent feature frames, and determines the student's painting personality category according to the feature aggregation degree of the new painting sub-areas, determines the time window and feature weight of the painting concentration detection according to the student's painting personality category, and determines whether the student's painting concentration is abnormal based on the feature weight of the student's concentration detection, thereby realizing the formulation of personalized concentration assessment methods for students with different painting habits, and improving the accuracy of the concentration assessment results.

[0048] In particular, the present invention divides students' painting personality categories according to the feature aggregation degree of the newly added painting sub-area. It can be understood that the feature aggregation degree can represent the students' painting habits. The smaller the feature aggregation degree, the more likely the students will first draw the overall outline and then fill in the local details during the painting process. The larger the feature aggregation degree, the more likely the students will complete a certain area before painting the next area during the painting process. Students with different painting habits face different timings and expressions of painting concentration defects during the painting process. Students who draw the overall framework first have an advantage in grasping the overall proportion and layout, but are prone to distraction when going into details. Students who draw a certain area first focus on painting the local area, and are prone to distraction when connecting between areas. The present invention divides students' painting personality categories by the feature aggregation degree of the newly added painting sub-area, thereby realizing classification processing according to the students' own painting habits and improving the accuracy of concentration assessment results.

[0049] In particular, under the condition that the student's painting personality category is the first painting personality category, the present invention determines whether the student has entered the window feature stage according to several area ratios within the feature monitoring period, determines the first time window based on the determination result, and determines the first feature weight according to the number of alterations corresponding to the first time window. It can be understood that the students of the first painting personality category first paint the whole and then paint the local details when painting. From drawing the overall framework to filling in the details, it is a process of shifting attention from macro to micro. Students with high concentration can quickly adapt to the requirements of detail drawing, and can reduce alterations caused by attention shift when filling in the details, while students with low concentration cannot focus on the details well and need to make constant alterations to adjust. The present invention uses the student entering the window feature stage as the first time window, obtains the number of alterations corresponding to the first time window to determine the first feature weight, and then realizes the formulation of personalized concentration assessment methods for students with different painting habits, thereby improving the accuracy of the concentration assessment results.

[0050] In particular, under the condition that the painting personality category of the trainee is the second painting personality category, the present invention determines whether the trainee's painting has a region switch based on the area ratio of the newly added painting pixel points in adjacent frame images, determines the second time window based on the determination result, and obtains the brush stroke speed parameter according to the second time window to determine the second feature weight. It can be understood that after the trainee with the second painting personality category finishes painting a certain region and then proceeds to paint the next region, the switching of the painting region means that the trainee needs to shift their attention from a completed region to a new region to be painted. Trainees with high concentration can quickly adjust the brush stroke speed before and after the region switch to a state suitable for painting the new region without significant speed changes. Trainees with low concentration need time to refocus, and the brush stroke speed will have significant fluctuations before and after the region switch. The present invention uses a period of time before and after the region switch as the second time window, obtains the brush stroke speed parameter corresponding to the second time window to determine the second feature weight, and further realizes a personalized concentration assessment method for trainees with different painting habits, improving the accuracy of the concentration assessment result.

[0051] In particular, the present invention determines that the painting concentration of the trainee is abnormal according to the fact that the first feature weight of the trainee does not meet the first normal concentration condition, or the second feature weight does not meet the second normal concentration condition. It can be understood that the larger the first feature weight, the higher the modification frequency of the trainee, the lower the painting concentration of the trainee, and there is an abnormal phenomenon in the painting concentration. The larger the second feature weight, the greater the fluctuation of the brush stroke speed when the trainee switches the painting region, the lower the painting concentration of the trainee, and there is an abnormal phenomenon in the painting concentration. Furthermore, a personalized concentration assessment method for trainees with different painting habits is realized, improving the accuracy of the concentration assessment result. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a step diagram of the painting concentration detection method according to an embodiment of the present invention;

[0053] Figure 2 is a logic flow diagram for screening newly added painting sub-regions according to an embodiment of the present invention;

[0054] Figure 3 is a logic flow diagram for determining the time window and feature weight of painting concentration detection and a structural block diagram of a painting concentration detection system according to an embodiment of the present invention;

[0055] Figure 4 is a structural block diagram of a painting concentration detection system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] To make the objectives and advantages of the present invention more clearly understood, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only for explaining the present invention and are not used to limit the present invention.

[0057] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0058] It should be noted that in the description of the present invention, the terms indicating the direction or positional relationship such as "upper", "lower", "inner", "outer", etc. are based on the direction or positional relationship shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0059] In addition, it should also be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installation" and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0060] Please refer to Figure 1 as shown, which is the step diagram of the painting concentration detection method in the embodiment of the present invention. A painting concentration detection method of the present invention includes:

[0061] Step S100, collecting the painting video streams of each student in real time, obtaining a plurality of feature frame images of the painting video stream at a preset time interval, and dividing each feature frame image into a plurality of painting areas;

[0062] Specifically, the preset time interval for obtaining the feature frame images can be set by those skilled in the art according to the accuracy requirements of painting concentration detection. The higher the accuracy requirements, the shorter the time interval. Preferably, the time interval can be 1 min.

[0063] Specifically, the size of the divided painting areas can be set by those skilled in the art according to the actual painting type. Preferably, when the painting type is realistic painting, the size of the divided painting areas can be 5 cm × 5 cm.

[0064] Step S200, screening for new added painting sub-areas according to the image differences of the painting areas in adjacent feature frames, and determining the painting personality categories of the students according to the feature aggregation degree of the new added painting sub-areas;

[0065] Step S300, determine the time window and feature weights for the painting concentration detection according to the painting personality category of the trainee, including:

[0066] Based on the area ratio of the newly added painting pixel points in adjacent frame images within a preset feature monitoring period of the painting video stream, determine whether the trainee enters the window feature stage, determine the first time window according to the determination result, and determine the first feature weight according to the number of scribbles within the first time window;

[0067] Or, determine whether there is a regional switch in the trainee's painting according to the area ratio of the newly added painting pixel points in adjacent frame images, determine the second time window according to the determination result, and obtain the brush stroke speed parameter within the second time window to determine the second feature weight;

[0068] Specifically, the preset feature monitoring period can be set by those skilled in the art according to the accuracy requirements of the concentration detection. The higher the accuracy requirements, the longer the preset feature monitoring period. Preferably, the feature monitoring period can be 5 minutes.

[0069] Step S400, determine whether there is an abnormality in the painting concentration of the trainee based on the feature weights of the trainee's concentration detection.

[0070] Specifically, please refer to Figure 2 As shown, it is the logical flowchart for screening newly added painting sub-regions in the embodiment of the present invention. The process of screening newly added painting sub-regions includes:

[0071] If the image difference of the painting area in adjacent feature frames meets the new area condition, then screen the painting area as a newly added painting sub-region;

[0072] If the image difference of the painting area in adjacent feature frames does not meet the new area condition, then do not screen the painting area;

[0073] The new area condition is that there are newly added pixel points in the painting area.

[0074] Specifically, the image difference of the painting area in adjacent feature frames can be obtained by using an image processing library to extract the color values of the pixel points corresponding to the painting area, and calculate the differences in the pixel values of the R, G, and B channels of the pixel points corresponding to the painting area in adjacent feature frames respectively. The difference is the image difference of the painting area in adjacent feature frames. This is the prior art and will not be elaborated here.

[0075] Specifically, the process of determining the painting personality category of the trainee includes:

[0076] Calculate the regional coincidence degree of the newly added painting sub-regions corresponding to adjacent frames, and determine the regional coincidence degree as the feature set degree;

[0077] If the student's characteristic aggregation degree meets the overall drawing condition, the student's drawing personality category is determined to be the first drawing personality category;

[0078] If the student's characteristic aggregation does not meet the overall drawing conditions, the student's drawing personality category is determined to be the second drawing personality category;

[0079] The overall painting condition is that the feature aggregation degree is not zero.

[0080] Specifically, the present invention divides students' painting personality categories according to the feature aggregation degree of newly added painting sub-areas. It can be understood that the feature aggregation degree can represent the students' painting habits. The smaller the feature aggregation degree, the more it represents that the students first draw the overall outline and then fill in the local details during the painting process. The larger the feature aggregation degree, the more it represents that the students complete the painting of a certain area before painting the next area during the painting process. Students with different painting habits face different timings and expressions of painting concentration defects during the painting process. Students who draw the overall framework first have an advantage in grasping the overall proportion and layout, but are prone to distraction when going into details. Students who draw a certain area first focus on painting the local area, and are prone to distraction when connecting between areas. The present invention divides students' painting personality categories by the feature aggregation degree of newly added painting sub-areas, thereby realizing classification processing according to students' own painting habits and improving the accuracy of concentration assessment results.

[0081] Specifically, see Figure 3 As shown, it is a logic flow chart of determining the time window and feature weight of painting concentration detection according to an embodiment of the present invention. The process of determining the time window and feature weight of painting concentration detection includes:

[0082] If the student's painting personality category is determined to be the first painting personality category, whether the student has entered the window feature stage is determined based on the area ratio of newly added painting pixels in adjacent frame images of the painting video stream within a preset feature monitoring period, a first time window is determined based on the determination result, and a first feature weight is determined according to the number of alterations within the first time window;

[0083] If the student's painting personality category is determined to be the second painting personality category, it is determined whether area switching occurs in the student's painting based on the area ratio of the newly added painting pixels in adjacent frame images, and the second time window is determined based on the determination result. The brush stroke speed parameters within the second time window are obtained to determine the second feature weight.

[0084] Specifically, under the condition that the painting personality category of the student is the first painting personality category, the present invention determines whether the student enters the window feature stage according to a number of area ratios within the feature monitoring period, determines the first time window based on the determination result, and determines the first feature weight according to the number of scribbles corresponding to the first time window. It can be understood that students with the first painting personality category first paint the whole picture and then paint the local details. From drawing the overall framework to filling in the details, it is a process of the attention shifting from the macroscopic to the microscopic. Students with high concentration can quickly adapt to the requirements of detail drawing and reduce scribbles caused by the shift of attention when filling in the details, while students with low concentration cannot focus well on the details and need to constantly scribble to adjust. The present invention takes the stage when the student enters the window feature as the first time window, obtains the number of scribbles corresponding to the first time window to determine the first feature weight, and further realizes a personalized concentration evaluation method for students with different painting habits, improving the accuracy of the concentration evaluation result.

[0085] Specifically, under the condition that the painting personality category of the student is the second painting personality category, the present invention determines whether the student's painting has a region switch according to the area ratio of the newly added painting pixel points in adjacent frame images, determines the second time window based on the determination result, and obtains the brush stroke speed parameter according to the second time window to determine the second feature weight. It can be understood that after a student with the second painting personality category finishes painting a certain region, they then paint the next region. The switch of the painting region means that the student needs to shift their attention from a completed region to a new region to be painted. Students with high concentration can quickly adjust the brush stroke speed before and after the region switch to a state suitable for painting the new region without significant speed changes, while students with low concentration need time to refocus their attention and the brush stroke speed will have large fluctuations before and after the region switch. The present invention takes a period of time before and after the region switch as the second time window, obtains the brush stroke speed parameter corresponding to the second time window to determine the second feature weight, and further realizes a personalized concentration evaluation method for students with different painting habits, improving the accuracy of the concentration evaluation result.

[0086] Specifically, the process of determining whether the student enters the window feature stage and determining the first time window includes

[0087] Obtaining the area ratio of the newly added painting pixel points in a number of adjacent frame images within the feature monitoring period;

[0088] If a number of area ratios within the feature monitoring period meet the first window determination condition, it is determined that the student enters the window feature stage, and the feature monitoring period is determined as the first time window;

[0089] If a number of area ratios within the characteristic monitoring period do not meet the first window determination condition, it is determined that the student has not entered the window characteristic stage;

[0090] The first window determination condition is that the area ratios obtained by several calculations do not exceed a preset detail area ratio threshold.

[0091] Specifically, the process of obtaining the area ratio is to calculate the area ratio of the area of the newly added painting pixel points to the area of the current painting pixel points several times according to adjacent frame images within a preset feature monitoring period in the painting video stream.

[0092] Specifically, the preset detail area ratio threshold may be set by a person skilled in the art according to the accuracy requirement of concentration detection. The higher the accuracy requirement, the smaller the detail area ratio threshold. Preferably, the detail area ratio threshold may be 5%.

[0093] Specifically, the process of determining the first feature weight includes:

[0094] The number of alterations within the first time window is obtained, a ratio of the window duration of the first time window to the number of alterations is calculated, and the ratio is determined as the first feature weight.

[0095] Specifically, the process of determining whether the student's drawing has region switching and determining the second time window includes:

[0096] Calculate the area ratio of newly added drawing pixels in adjacent frame images;

[0097] Specifically, the process of calculating the area ratio of newly added painting pixels in adjacent frame images is to obtain two adjacent frames in the time sequence of the painting video stream, determine the previous frame in the time sequence as the first key frame, and determine the next frame in the time sequence as the second key frame, and calculate the area ratio of the newly added painting pixel to the area of the current painting pixel based on the image difference between the first key frame image and the second key frame image.

[0098] If the area ratio of the adjacent frames meets the second window determination condition, it is determined that the student's painting area is switched, and a second time window of a preset length is determined with the next frame of the adjacent frames as the reference time, and the second time window includes the reference time;

[0099] If the area ratio of the adjacent frames does not meet the second window determination condition, it is determined that no area switching occurs in the student's drawing;

[0100] The second window determination condition is that the area ratio exceeds a preset switching area threshold.

[0101] Specifically, the preset switching area ratio threshold can be set by those skilled in the art according to the accuracy requirements of concentration detection. The higher the accuracy requirements, the larger the switching area ratio threshold. Preferably, the detailed area ratio threshold can be 15%.

[0102] Specifically, the process of determining the second feature weight includes

[0103] obtaining the stroke speed parameters corresponding to several moments within the second time window, calculating the variance of the stroke speed parameters corresponding to several moments, and determining the variance as the second feature weight.

[0104] Specifically, the process of determining whether there is an abnormality in the student's painting concentration includes

[0105] If the first feature weight of the student does not meet the first normal concentration condition, or the second feature weight does not meet the second normal concentration condition, it is determined that there is an abnormality in the student's painting concentration;

[0106] If the first feature weight of the student meets the first normal concentration condition and the second feature weight meets the second normal concentration condition, it is determined that there is no abnormality in the student's painting concentration;

[0107] Among them, the first normal concentration condition is that the first feature weight does not exceed the preset first feature weight reference value, and the second normal concentration condition is that the second feature weight does not exceed the preset second feature weight reference value.

[0108] Specifically, the preset first feature weight reference value can be set by those skilled in the art according to the accuracy requirements of concentration detection. The higher the accuracy requirements, the smaller the preset first feature weight reference value. Preferably, the first feature weight reference value can be 3 times / minute.

[0109] Specifically, the preset second feature weight reference value can be set by those skilled in the art according to the actual painting type. Preferably, when the painting type is realistic painting, the second feature weight reference value can be 0.8.

[0110] Specifically, according to the present invention, if the first characteristic weight of a student does not meet the first normal concentration condition, or the second characteristic weight does not meet the second normal concentration condition, it is determined that the student's painting concentration is abnormal. It can be understood that the greater the first characteristic weight, the higher the frequency of the student's scribbling and the lower the student's painting concentration, indicating an abnormal painting concentration. The greater the second characteristic weight, the greater the fluctuation of the brush stroke speed when the student switches the painting area and the lower the student's painting concentration, indicating an abnormal painting concentration. Furthermore, a personalized concentration evaluation method is developed for students with different painting habits, improving the accuracy of the concentration evaluation results.

[0111] Specifically, please refer to Figure 4 As shown in the figure, it is a structural block diagram of the painting concentration detection system according to an embodiment of the present invention. The present invention also provides a painting concentration detection system, including:

[0112] A feature extraction module, which includes an image acquisition unit and an image information processing unit;

[0113] Among them, the image acquisition unit is used to collect the painting video streams of each student in real time;

[0114] The image information processing unit is used to obtain a number of feature frame images of the painting video stream, divide each feature frame image into a number of painting areas, screen for newly added painting sub-areas, determine the painting personality category of the student according to the feature aggregation degree of the newly added painting sub-areas, and obtain the area ratio of the newly added painting pixel points of adjacent frame images;

[0115] Specifically, the present invention does not limit the specific structure of the image acquisition unit. Preferably, it can be a camera. A high-definition network camera is installed on the ceiling of the painting classroom, and its field of view covers the students' painting desks to collect the painting video streams of each student in real time, which will not be elaborated here.

[0116] Specifically, the present invention does not limit the specific structure of the image information processing unit. Preferably, it can be implemented by an embedded image processor in cooperation with a microprocessor, used to divide the painting area, screen for newly added painting sub-areas, determine the painting personality category of the student, and extract the pixel points in the image to determine the image difference between adjacent frame images, which will not be elaborated here.

[0117] A concentration monitoring module, which is connected to the feature extraction module and includes a concentration recognition unit and a behavior monitoring unit;

[0118] The concentration recognition unit is used to determine the time window and characteristic weight for painting concentration detection, and the behavior monitoring unit is used to obtain the number of times the student scribbles and obtain the brush stroke speed parameter of the student;

[0119] Specifically, the present invention does not limit the specific structure of the concentration recognition unit. Preferably, it can be a microprocessor for selecting the time window and feature weights for detecting painting concentration, which will not be elaborated here.

[0120] Specifically, the present invention does not limit the specific structure of the behavior monitoring unit. Preferably, it can be realized by an intelligent paintbrush with an in-built acceleration sensor and gyroscope in cooperation with a touch sensor. The acceleration and angle change data of the paintbrush are collected in real time by the sensors, and these data are converted into stroke speed information through an algorithm. By installing a touch sensor at the edge of the painting table, the touch sensor detects signal changes and records the number of times of modification, which will not be elaborated here.

[0121] A determination module, which is connected to the feature extraction module and the concentration monitoring module, for determining whether there is an abnormality in the painting concentration of the student.

[0122] Specifically, the present invention does not limit the specific structure of the determination module. Preferably, it can be a processor used in a computer for determining whether there is an abnormality in the painting concentration of the student, which will not be elaborated here.

[0123] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or replacements to the relevant technical features, and the technical solutions after these changes or replacements will fall within the protection scope of the present invention.

[0124] The above are only the preferred embodiments of the present invention and are not used to limit the present invention; for those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for detecting painting concentration, characterized in that, include: Collect the painting video stream of each student in real time, obtain a number of feature frame images of the painting video stream at a preset time interval, and divide each feature frame image into a number of painting areas; Screening a new painting sub-region according to the image difference of the painting regions in adjacent feature frames, and determining the student's painting personality category according to the feature aggregation degree of the new painting sub-region; Determine the time window and feature weight for drawing concentration detection based on the student's drawing personality category. include, Determine whether the student has entered the window feature stage based on the area ratio of newly added painting pixels in adjacent frame images of the painting video stream within a preset feature monitoring period, determine a first time window based on the determination result, and determine a first feature weight according to the number of alterations within the first time window; Or, judging whether the student's painting area switching occurs according to the area ratio of newly added painting pixels in adjacent frame images, determining a second time window based on the judgment result, and obtaining a brush stroke speed parameter within the second time window to determine a second feature weight; Based on the feature weight of the student's concentration detection, it is determined whether the student's painting concentration is abnormal.

2. The painting concentration detection method according to claim 1, wherein The process of screening the newly added painting sub-areas includes: If the image difference of the painting area in the adjacent feature frames meets the condition of adding a new area, the painting area is selected as a new painting sub-area; The newly added area condition is that there are newly added pixels in the drawing area.

3. The painting concentration detection method according to claim 2, wherein The process of determining the student's drawing personality category includes, Calculating the region overlap of newly added painting sub-regions corresponding to adjacent frames, and determining the region overlap as the feature set degree; If the student's characteristic aggregation degree meets the overall drawing condition, the student's drawing personality category is determined to be the first drawing personality category; If the student's characteristic aggregation does not meet the overall drawing conditions, the student's drawing personality category is determined to be the second drawing personality category; The overall painting condition is that the feature aggregation degree is not zero.

4. The painting concentration detection method according to claim 3, characterized in that, The process of determining the time window and feature weights for painting concentration detection includes: If the student's painting personality category is determined to be the first painting personality category, whether the student has entered the window feature stage is determined based on the area ratio of newly added painting pixels in adjacent frame images of the painting video stream within a preset feature monitoring period, a first time window is determined based on the determination result, and a first feature weight is determined according to the number of alterations within the first time window; If the student's painting personality category is determined to be the second painting personality category, it is determined whether area switching occurs in the student's painting based on the area ratio of the newly added painting pixels in adjacent frame images, and the second time window is determined based on the determination result. The brush stroke speed parameters within the second time window are obtained to determine the second feature weight.

5. The painting concentration detection method according to claim 4, wherein The process of determining whether the trainee has entered the window characteristic stage and determining the first time window includes: Obtaining the area ratio of newly added drawing pixel points of a number of adjacent frame images within the feature monitoring period; If a number of area ratios within the characteristic monitoring period meet the first window determination condition, it is determined that the trainee has entered the window characteristic stage, and the characteristic monitoring period is determined as the first time window; Among them, the first window determination condition is that the area ratios obtained from several calculations do not exceed a preset detailed area ratio threshold.

6. The painting concentration detection method according to claim 5, characterized in that The process of determining the first feature weight includes obtaining the number of times of modification within the first time window, calculating the ratio of the window duration of the first time window to the number of times of modification, and determining the ratio as the first feature weight.

7. The painting concentration detection method according to claim 4, wherein The process of determining whether the student's painting has a region switch and determining the second time window includes calculating the area ratio of the newly added painting pixel points of adjacent frame images; if the area ratio of the adjacent frames meets the second window determination condition, it is determined that the student's painting has a region switch, and a second time window with a preset duration is determined based on the latter frame of the adjacent frames. The second time window includes the reference time; Among them, the second window determination condition is that the area ratio exceeds a preset switching area threshold.

8. The painting concentration detection method according to claim 7, wherein The process of determining the second feature weight includes obtaining the brush stroke speed parameters corresponding to several moments within the second time window, calculating the variance of the brush stroke speed parameters corresponding to several moments, and determining the variance as the second feature weight.

9. The painting concentration detection method according to claim 8, wherein The process of determining whether there is an abnormality in the painting concentration of the student includes if the first feature weight of the student does not meet the first normal concentration condition, or the second feature weight does not meet the second normal concentration condition, it is determined that there is an abnormality in the painting concentration of the student; Among them, the first normal concentration condition is that the first feature weight does not exceed a preset first feature weight reference value, and the second normal concentration condition is that the second feature weight does not exceed a preset second feature weight reference value.

10. A painting concentration detection system for performing the painting concentration detection method according to any one of claims 1-9 above, characterized in that, including: a feature extraction module, which includes an image acquisition unit and an image information processing unit; Among them, the image acquisition unit is used to collect the painting video stream of each student in real time; The image information processing unit is used to obtain several feature frame images of the painting video stream, divide each feature frame image into several painting regions, screen the newly added painting sub-regions, determine the painting personality category of the student according to the feature aggregation degree of the newly added painting sub-regions, and obtain the area ratio of the newly added painting pixel points of adjacent frame images; a concentration monitoring module, which is connected to the feature extraction module and includes a concentration recognition unit and a behavior monitoring unit; The concentration recognition unit is used to determine the time window and feature weight for painting concentration detection, and the behavior monitoring unit is used to obtain the number of times of modification of the student and obtain the brush stroke speed parameter of the student; a determination module, which is connected to the feature extraction module and the concentration monitoring module, and is used to determine whether there is an abnormality in the painting concentration of the student.

Images