Multi-point touch positioning method and system for display screen

Abstract

The invention relates to the technical field of touch screens, and particularly discloses a display screen multi-point touch positioning method and system.The method comprises the steps that shielded light path data on a display screen are obtained, and a plurality of initial touch areas are determined according to the shielded light path data on the display screen; acquiring a central point coordinate of a central point of the initial touch area and corresponding infrared signal intensity, calculating touch trueness of the initial touch area according to the central point coordinate and the corresponding infrared signal intensity, and determining a real touch point according to the touch trueness; and obtaining a moving track of the real touch point, screening out an effective track in the moving track, and determining a corresponding sliding instruction according to the effective track. According to the method, the real touch points on the display screen can be accurately identified, and the accuracy of multi-touch-point identification is improved.

Description

Technical Field

[0001] The present application relates to the field of touch screen technology, and more specifically, to a method and system for multi-touch positioning of a display screen. Background Art

[0002] Touch technology has become an integral part of our daily lives, from small touchscreen phones and tablets to large-scale smart conference systems and video wall displays. Its intuitive and convenient performance has enabled it to be applied to every aspect of production and life. In the field of large-scale touchscreens, the more mature touch technologies currently include infrared tube scanning, camera optical positioning, and ultrasonic positioning. In infrared tube scanning technology, an infrared touch screen is equipped with an infrared touch frame densely packed with infrared emitting tubes and receiving tubes. The emitting tubes transmit infrared light, while the receiving tubes receive it, forming an infrared detection network on the display surface. This infrared detection network continuously scans to see if any infrared light is blocked by a touch object. Based on the missing infrared light, it calculates the touch position of the touch object and generates touch point data, thus enabling touch recognition on the infrared touch screen.

[0003] However, in the prior art, when scanning the infrared emitting tube and the infrared receiving tube, if multi-touch occurs during the touch action, it is difficult to accurately identify the exact coordinate position of the touch action, resulting in low multi-touch recognition accuracy. Summary of the Invention

[0004] The present invention provides a display screen multi-touch positioning method and system to solve the problem of low accuracy of display screen multi-touch recognition in the prior art, including: Obtain light path data that is blocked on the display screen, and determine several initial touch areas based on the light path data that is blocked on the display screen; obtain the center point coordinates of the center point of the initial touch area and the corresponding infrared signal strength, calculate the touch authenticity of the initial touch area based on the center point coordinates and the corresponding infrared signal strength, and determine the real touch point based on the touch authenticity; obtain the movement trajectory of the real touch point, filter out the valid trajectory in the movement trajectory, and determine the corresponding sliding instruction based on the valid trajectory.

[0005] Furthermore, the touch authenticity of the initial touch area is calculated based on the center point coordinates and the corresponding infrared signal strength, including: obtaining the edge contour point of the initial touch area corresponding to the center point, and determining the contour point coordinates and the corresponding infrared signal strength based on the edge contour point of the initial touch area; obtaining the touch point position of the center point, determining the touch confidence of the center point based on the touch point position of the center point, and determining the touch authenticity of the initial touch area based on the coordinates and infrared signal strength of the center point and the edge contour point combined with the touch confidence.

[0006] Further, the method further comprises: determining the touch authenticity of the initial touch area according to the coordinates of the center point and the edge contour points, the infrared signal intensity, and the touch confidence; and determining the touch authenticity of the initial touch area according to a touch authenticity calculation formula, wherein the touch authenticity calculation formula is,

[0007] wherein, is the touch authenticity, is the touch confidence of the center point of the initial touch area, is the number of all edge contour points in the initial touch area, is the Euclidean distance from the i-th edge contour point to the center point, is the infrared signal intensity of the i-th edge contour point, is the infrared signal intensity of the center point, is the standard deviation of the Euclidean distance between each edge contour point and the center point in the initial touch area, is the standard deviation of the infrared signal intensity between each edge contour point and the center point in the initial touch area,

[0008] Further, the method further comprises: obtaining the touch probability of each touch point position in the historical display screen touch data, clustering each touch point position according to the touch probability; determining the cluster center of each touch point position according to the clustering result, and determining the touch confidence of the corresponding touch point position according to the cluster center of the touch point position.

[0009] Further, the method further comprises: establishing a sample data set according to the touch probability of each touch point position in the historical display screen touch data, and randomly selecting k initial cluster centers of the sample data set; calculating the Euclidean distance from the sample data in the sample data set to the initial cluster center, and dividing each photovoltaic module area into a corresponding cluster according to the Euclidean distance from the sample data in the sample data set to the initial cluster center; calculating the average value of the sample data in each cluster, and recalculating the cluster center according to the average value of the sample data in each cluster; repeating the above steps until the cluster center no longer changes or the number of iterations reaches a preset maximum number of iterations, to obtain the clustering result of the touch point position.

[0010] ​​Further, the determining the real touch point according to the touch reality degree comprises: acquiring a preset touch reality degree interval, judging whether the touch reality degree of the initial touch area is in the preset touch reality degree interval; if the touch reality degree of the initial touch area is in the preset touch reality degree interval, setting the initial touch area as the real touch point; if the touch reality degree of the initial touch area is not in the preset touch reality degree interval, setting the initial touch area as the invalid touch point.

[0011] Further, the screening the effective trajectory in the moving trajectory comprises: determining the moving speed, the moving direction and the moving distance of the real touch point according to the moving trajectory of the real touch point, and counting the moving speed of the real touch point within a preset moving distance; judging whether the moving speed of the real touch point within the preset moving distance is greater than a first preset threshold, if the moving speed of the real touch point within the preset moving distance is greater than the first preset threshold, setting the moving trajectory as the invalid trajectory; if the moving speed of the real touch point within the preset moving distance is less than or equal to the first preset threshold, setting the moving trajectory as the effective trajectory.

[0012] Further, the determining the corresponding sliding instruction according to the effective trajectory comprises: determining the historical touch point moving trajectory and the corresponding sliding instruction according to the historical display screen touch data, preprocessing the historical touch point moving trajectory to obtain the preprocessed historical touch point moving trajectory and the corresponding sliding instruction; establishing a training sample set according to the preprocessed historical touch point moving trajectory and the corresponding sliding instruction, establishing an initial sliding instruction evaluation model according to the training sample set and training the initial sliding instruction evaluation model to obtain a trained sliding instruction evaluation model; inputting the current effective trajectory into the trained sliding instruction evaluation model to obtain the corresponding sliding instruction evaluation result.

[0013] Further, the preprocessing the historical touch point moving trajectory comprises: vectorizing the moving speed, the moving direction and the moving distance of each touch point in the historical touch point moving trajectory, sorting the vectorized moving speed, the moving direction and the moving distance of each touch point in the historical touch point moving trajectory according to the time sequence to obtain a feature sequence of the historical touch point moving trajectory, and taking the feature sequence as the preprocessed historical touch point moving trajectory.

[0014] In order to achieve the above purpose, the application further provides a display screen multi-point touch positioning system, comprising: The detection module is configured to acquire light path data blocked on the display screen, and determine a plurality of initial touch control areas according to the light path data blocked on the display screen.

[0015] The present application has the following advantages: By applying the above technical solution, the present application can accurately calculate the touch control reality of each touch control area by combining the coordinate data of the touch control area and the infrared signal strength, thereby screening out the real touch control points, accurately identifying the real touch control points on the display screen, and effectively improving the accuracy of multi-touch point recognition. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0017] Figure 1 The overall flowchart of the display screen multi-point touch control positioning method proposed by the embodiment of the present application is shown. Figure 2 The structural schematic diagram of the display screen multi-point touch control positioning system proposed by the embodiment of the present application is shown. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0019] The present application provides a display screen multi-point touch control positioning method, as shown in Figure 1 The present application provides a display screen multi-point touch control positioning method, as shown in S101, acquiring light path data blocked on the display screen, and determining a plurality of initial touch control areas according to the light path data blocked on the display screen. In the embodiment, infrared emitting tubes and infrared receiving tubes are installed on the outer frame of the touch screen of the display screen, infrared rays are emitted from the infrared emitting tubes to the infrared receiving tubes, and an infrared detection network is formed on the surface of the touch screen. When an object touches the display screen, the infrared rays passing through the touch point position are blocked, thereby forming an initial touch control area.

[0020] In S102, the center point coordinates of the center point of the initial touch control area and the corresponding infrared signal intensity are obtained, the touch control authenticity of the initial touch control area is calculated according to the center point coordinates and the corresponding infrared signal intensity, and the real touch point is determined according to the touch control authenticity. In some embodiments of the present application, the calculation of the touch control authenticity of the initial touch control area according to the center point coordinates and the corresponding infrared signal intensity comprises: obtaining the edge contour points of the initial touch control area corresponding to the center point, determining the contour point coordinates and the corresponding infrared signal intensity according to the edge contour points of the initial touch control area; obtaining the touch point position where the center point is located, determining the touch control confidence of the center point according to the touch point position where the center point is located, and determining the touch control authenticity of the initial touch control area according to the coordinates and the infrared signal intensity of the center point and the edge contour points in combination with the touch control confidence.

[0021] In some embodiments of the present application, the determination of the touch control authenticity of the initial touch control area according to the coordinates and the infrared signal intensity of the center point and the edge contour points in combination with the touch control confidence comprises: determining the touch control authenticity of the initial touch control area based on a touch control authenticity calculation formula, wherein the touch control authenticity calculation formula is,

[0022] wherein, the touch control authenticity is, the touch control confidence of the center point of the initial touch control area is, the number of all edge contour points in the initial touch control area is, the Euclidean distance of the i-th edge contour point to the center point is, the infrared signal intensity of the i-th edge contour point is, the infrared signal intensity of the center point is, the standard deviation of the Euclidean distance between each edge contour point and the center point in the initial touch control area is, , the standard deviation of the infrared signal intensity between each edge contour point and the center point in the initial touch control area is, .

[0023] In the real touch operation, when the touch object (such as a finger) completely covers the infrared light path, the infrared light path of the center point is completely blocked, and the infrared signal strength detected by the receiving tube tends to zero. At the edge of the touch area, due to the incomplete shielding of the light path by the arc surface of the finger or other real touch objects, the infrared intensity at the edge of the touch area is higher than that at the center point. At the same time, the shape data of the touch object can be calculated by the coordinate distance between the center point and the edge point. Therefore, the touch authenticity of the initial touch area can be accurately calculated by combining the coordinates of the center point and the edge contour point with the touch confidence. Through the formula, the touch authenticity of the initial touch area can be calculated, and even if there are multiple touch areas, the real touch point can also be accurately selected.

[0024] In some embodiments of the present application, the touch confidence of the center point is determined according to the touch point position where the center point is located, including: obtaining the touch probability of each touch point position in the historical display screen touch data, and clustering each touch point position according to the touch probability; determining the cluster center of each touch point position according to the clustering result, and determining the touch confidence of the corresponding touch point position according to the cluster center of the touch point position.

[0025] In the present embodiment, the display screen is divided into a plurality of touch point positions according to a preset grid, the touch times of each touch point position are determined through historical display screen touch data, the ratio of the touch times of the touch point position to the total touch times is calculated, thereby calculating the touch probability, each touch point position is clustered through the touch probability, a touch probability-confidence mapping table is established, the touch confidence of the touch point position is determined through the touch probability of the cluster center corresponding to the touch point position, and the range of the touch confidence is [0, 1]. The higher the touch probability, the greater the touch confidence.

[0026] In some embodiments of the present application, the clustering of each touch point position according to the touch probability includes: establishing a sample data set according to the touch probability of each touch point position in the historical display screen touch data, and randomly selecting k initial cluster centers of the sample data set; calculating the Euclidean distance of the sample data in the sample data set to the initial cluster center, and dividing each photovoltaic module region to the corresponding cluster according to the Euclidean distance of the sample data in the sample data set to the initial cluster center; calculating the average value of the sample data in each cluster, and recalculating the cluster center according to the average value of the sample data in each cluster; repeating the above steps until the cluster center no longer changes or the iteration number reaches the preset maximum iteration number, and obtaining the clustering result of the touch point position.

[0027] In the present embodiment, the value of k is set to 5, and the k-means clustering algorithm is used to cluster each touch point position to calculate the touch confidence of the touch point position.

[0028] In some embodiments of the present application, the determining the real touch point according to the touch reality includes: obtaining a preset touch reality interval, judging whether the touch reality of the initial touch area is in the preset touch reality interval; if the touch reality of the initial touch area is in the preset touch reality interval, setting the initial touch area as the real touch point; if the touch reality of the initial touch area is not in the preset touch reality interval, setting the initial touch area as the invalid touch point.

[0029] In the present embodiment, the initial touch area closest to the real touch operation is screened out through the preset touch reality interval, and the area is set as the real touch point, and the invalid touch point is screened out.

[0030] In the present embodiment, the initial touch area closest to the real touch operation is screened out through the preset touch reality interval, and the area is set as the real touch point, and the invalid touch point is screened out.

[0031] In some embodiments of the present application, the screening the effective trajectory in the moving trajectory includes: determining the moving speed, the moving direction and the moving distance of the real touch point according to the moving trajectory of the real touch point, and counting the moving speed of the real touch point within a preset moving distance; judging whether the moving speed of the real touch point within the preset moving distance is greater than a first preset threshold, if the moving speed of the real touch point within the preset moving distance is greater than the first preset threshold, setting the moving trajectory as the invalid trajectory; if the moving speed of the real touch point within the preset moving distance is less than or equal to the first preset threshold, setting the moving trajectory as the effective trajectory.

[0032] In the present embodiment, the invalid trajectory with too fast speed is screened out through the moving speed of the real touch point within the preset moving distance, which effectively prevents the false touch operation and improves the accuracy of touch operation recognition.

[0033] In some embodiments of the present application, the determining the corresponding sliding instruction according to the effective trajectory includes: determining the historical touch point moving trajectory and the corresponding sliding instruction according to the historical display screen touch data, preprocessing the historical touch point moving trajectory to obtain the preprocessed historical touch point moving trajectory and the corresponding sliding instruction; establishing a training sample set according to the preprocessed historical touch point moving trajectory and the corresponding sliding instruction, establishing an initial sliding instruction evaluation model according to the training sample set and training the initial sliding instruction evaluation model to obtain a trained sliding instruction evaluation model; inputting the current effective trajectory into the trained sliding instruction evaluation model to obtain the corresponding sliding instruction evaluation result.

[0034] In some embodiments of the present application, the preprocessing of the historical touch point movement trajectory includes: vectorizing the movement speed, movement direction and movement distance of each touch point in the historical touch point movement trajectory, sorting the movement speed, movement direction and movement distance of each touch point in the historical touch point movement trajectory after vectorization according to the chronological order to obtain a feature sequence of the historical touch point movement trajectory, and taking the feature sequence as the preprocessed historical touch point movement trajectory.

[0035] In the present embodiment, a training sample set is established according to the feature sequence of the historical touch point movement trajectory and the corresponding sliding instruction, the feature sequence in the training sample set is taken as an input variable, the sliding instruction is taken as an output variable, a deep learning neural network model is established, the network structure of which is ResNet50, 80% of the training sample set is taken as a training set and 20% is taken as a test set, a mean square error loss function is used, the optimizer uses Adam, and a trained sliding instruction evaluation model is finally obtained through training, so as to output the sliding instruction evaluation result corresponding to the current effective trajectory. In the present embodiment, the effective trajectory input into the model can be multiple trajectories in the same time period, and more accurate sliding instructions can be obtained through comprehensive analysis of multiple trajectories, thereby improving the accuracy of multi-touch point recognition.

[0036] Based on the same technical concept, as shown in Figure 2 The present application also provides a display screen multi-point touch positioning system, which comprises: a detection module for acquiring occluded light path data on the display screen and determining a plurality of initial touch areas according to the occluded light path data on the display screen; a positioning module for acquiring center point coordinates of center points of the initial touch areas and corresponding infrared signal intensities, calculating touch real degrees of the initial touch areas according to the center point coordinates and the corresponding infrared signal intensities, and determining real touch points according to the touch real degrees; and a trajectory module for acquiring movement trajectories of the real touch points, screening out effective trajectories in the movement trajectories, and determining corresponding sliding instructions according to the effective trajectories.

[0037] By applying the above technical solutions, the present application can accurately identify real touch points on the display screen and improve the accuracy of multi-touch point recognition.

[0038] Those skilled in the art can clearly understand the present application through the description of the foregoing embodiments that the present application can be realized by hardware or by means of software and necessary universal hardware platform. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.), and includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in various implementation scenarios of the present application.

[0039] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacement for some technical features thereof; and these modifications or replacements do not drive the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A multi-touch positioning method for a display screen, characterized in that, The method comprises: Obtaining light path data blocked on the display screen, and determining a number of initial touch areas based on the light path data blocked on the display screen; Obtaining the center point coordinates of the center point of the initial touch area and the corresponding infrared signal strength, calculating the touch authenticity of the initial touch area based on the center point coordinates and the corresponding infrared signal strength, and determining the actual touch point based on the touch authenticity; Obtain the movement trajectory of the actual touch point, filter out the valid trajectory in the movement trajectory, and determine the corresponding sliding instruction based on the valid trajectory.

2. The method of claim 1, wherein, The step of calculating the touch authenticity of the initial touch area according to the center point coordinates and the corresponding infrared signal strength includes: Obtaining the edge contour point of the initial touch area corresponding to the center point, and determining the contour point coordinates and the corresponding infrared signal strength according to the edge contour point of the initial touch area; The touch point position of the center point is obtained, the touch confidence of the center point is determined based on the touch point position of the center point, and the touch authenticity of the initial touch area is determined based on the coordinates of the center point and the edge contour point and the infrared signal strength combined with the touch confidence.

3. The method of claim 2, wherein, The step of determining the touch authenticity of the initial touch area according to the coordinates of the center point and the edge contour points and the infrared signal strength in combination with the touch confidence level includes: The touch authenticity of the initial touch area is determined based on the touch authenticity calculation formula, and the touch authenticity calculation formula is: wherein, is a touch reality, is a touch confidence of the center point of the initial touch area, is a number of all edge contour points in the initial touch area, is a Euclidean distance from the i-th edge contour point to the center point, is an infrared signal intensity of the i-th edge contour point, is an infrared signal intensity of the center point, is a standard deviation of the Euclidean distance between each edge contour point and the center point in the initial touch area, , is a standard deviation of the infrared signal intensity between each edge contour point and the center point in the initial touch area, .

4. The method of claim 2, wherein, Determining the touch confidence of the center point according to the touch point position of the center point includes: Obtain the touch probability of each touch point in the historical display screen touch data, and cluster the touch points according to the touch probability; The cluster center of each touch point is determined according to the clustering result, and the touch confidence of the corresponding touch point is determined according to the cluster center of the touch point.

5. The method of claim 4, wherein, Clustering the touch points according to the touch probability includes: A sample data set is established based on the touch probability of each touch point in the historical display screen touch data, and k initial cluster centers of the sample data set are randomly selected; Calculate the Euclidean distance between the sample data in the sample data set and the initial cluster center, and divide each photovoltaic module area into a corresponding cluster according to the Euclidean distance between the sample data in the sample data set and the initial cluster center; Calculate the average value of the sample data in each cluster, and recalculate the cluster center based on the average value of the sample data in each cluster; Repeat the above steps until the cluster center no longer changes or the number of iterations reaches the preset maximum number of iterations, and obtain the clustering result of the touch points.

6. The method of claim 1, wherein, Determining the real touch point according to the touch realism includes: Obtaining a preset touch realism range, and determining whether the touch realism of the initial touch area is within the preset touch realism range; If the touch realism of the initial touch area is within the preset touch realism range, the initial touch area is set as the real touch point; If the touch fidelity of the initial touch area is not within the preset touch fidelity range, the initial touch area is set as an invalid touch point.

7. The method of claim 1, wherein, The filtering out of valid trajectories in the movement trajectory includes: Determine the moving speed, moving direction and moving distance of the real touch point according to the moving trajectory of the real touch point, and count the moving speed of the real touch point within the preset moving distance; determining whether a moving speed of the actual touch point within a preset moving distance is greater than a first preset threshold, and if the moving speed of the actual touch point within the preset moving distance is greater than the first preset threshold, setting the moving trajectory as an invalid trajectory; If the moving speed of the actual touch point within the preset moving distance is less than or equal to the first preset threshold, the moving trajectory is set as a valid trajectory.

8. The method of claim 1, wherein, The determining of the corresponding sliding instruction according to the valid trajectory includes: Determine the historical touch point movement trajectory and the corresponding sliding instruction according to the historical display screen touch data, pre-process the historical touch point movement trajectory, and obtain the pre-processed historical touch point movement trajectory and the corresponding sliding instruction; Establishing a training sample set based on the pre-processed historical touch point movement trajectory and the corresponding sliding instructions, establishing an initial sliding instruction evaluation model based on the training sample set, and training the initial sliding instruction evaluation model to obtain a trained sliding instruction evaluation model; The current valid trajectory is input into the trained sliding command evaluation model to obtain the corresponding sliding command evaluation result.

9. The method of claim 8, wherein, The pre-processing of the historical touch point movement trajectory includes: The moving speed, moving direction and moving distance of each touch point in the historical touch point movement trajectory are vectorized, and the moving speed, moving direction and moving distance of each touch point in the historical touch point movement trajectory after vectorization are sorted in chronological order to obtain a feature sequence of the historical touch point movement trajectory, and the feature sequence is used as the preprocessed historical touch point movement trajectory.

10. A multi-touch positioning system for a display screen, characterized by include: A detection module, configured to obtain light path data blocked on the display screen, and determine a number of initial touch areas based on the light path data blocked on the display screen; A positioning module is used to obtain the center point coordinates of the center point of the initial touch area and the corresponding infrared signal strength, calculate the touch authenticity of the initial touch area based on the center point coordinates and the corresponding infrared signal strength, and determine the actual touch point based on the touch authenticity; The trajectory module is used to obtain the movement trajectory of the real touch point, filter out the valid trajectory in the movement trajectory, and determine the corresponding sliding instruction based on the valid trajectory.

Images