CN116129798A - LED lamp bead brightness control method and device based on artificial intelligence algorithm - Google Patents

Abstract

The invention provides an LED lamp bead brightness control method and device based on an artificial intelligence algorithm, wherein the method comprises the following steps: shooting a plurality of images of the lamp beads in the process of increasing the working current of the LED display screen, and correlating the current value corresponding to the shooting time of the images with the images; establishing a brightness control model of the lamp beads according to the images and the current values; face distribution data of a front area of the LED display screen are determined; determining position relation data between each face and the LED display screen according to the face distribution data; dividing a display area of the LED display screen into a plurality of subareas according to the position relation data, and setting brightness display parameters for each subarea; determining a plurality of lamp bead groups corresponding to the subareas; and respectively adjusting the brightness of each lamp bead group according to the brightness control model and the brightness display parameters. According to the scheme, the brightness of the lamp beads is adjusted according to the character distribution condition in front of the LED display screen by establishing the brightness control model of the lamp beads, so that the LED display screen is more intelligent and efficient.

Description

LED lamp bead brightness control method and device based on artificial intelligence algorithm

Technical Field

The invention relates to the technical field of display control, in particular to an LED lamp bead brightness control method and device based on an artificial intelligence algorithm.

Background

With the development of display technology, LED displays play an increasingly important role in life nowadays, and the personalized demands of users on LED displays are becoming finer, which requires finer and intelligent control of the light beads of LED displays. The current LED lamp bead brightness control scheme cannot meet the actual requirements.

Disclosure of Invention

Based on the problems, the invention provides an LED lamp bead brightness control method and device based on an artificial intelligence algorithm, which can automatically adjust the brightness of the lamp bead, and is more intelligent and efficient.

In view of the above, an aspect of the present invention provides an LED lamp bead brightness control method based on an artificial intelligence algorithm, which is applied to an LED display screen, and includes:

connecting each lamp bead with a first switch and a second switch, wherein when all the first switches are communicated and all the second switches are disconnected, all the lamp beads are in a serial state;

switching on the power supply of the LED display screen, keeping all the first switches connected and the second switches disconnected, and gradually and linearly increasing the working current passing through the lamp beads of the LED display screen;

Synchronously shooting a plurality of images of the lamp beads in the process of increasing the working current, and correlating the current value corresponding to the shooting time of the images with the images;

establishing a brightness control model of the lamp beads according to the image and the current magnitude value;

acquiring character data of the front area of the LED display screen, identifying face data from the character data by utilizing an artificial intelligent face recognition algorithm, and determining face distribution data;

determining position relation data between each face and the LED display screen according to the face distribution data;

dividing a display area of the LED display screen into a plurality of subareas according to the position relation data, and setting brightness display parameters for each subarea;

controlling the connection and disconnection of the first switch and the second switch of each lamp bead according to a plurality of subareas so as to obtain a plurality of lamp bead groups corresponding to the subareas;

and respectively adjusting the brightness of each lamp bead group according to the brightness control model and the brightness display parameters of each subarea.

Preferably, the step of establishing a brightness control model of the lamp bead according to the image and the current magnitude value includes:

Graying the image to obtain first image data;

sequentially performing Gaussian filtering, gradient calculation, non-maximum value suppression, double-threshold selection and edge inspection on the first image data to obtain second image data;

filling the edge outline of the lamp bead displayed in the second image data with pixels with gray values of 255 to obtain third image data;

a first right-angle coordinate system is established by taking one point in the third image data as an origin of coordinates and taking the unit length of a pixel as the unit lengths of an X axis and a Y axis, and a first coordinate value of a lamp bead pixel point corresponding to each lamp bead is obtained according to the third image data;

and determining the central coordinate value of the central point of each lamp bead according to the first coordinate value.

Preferably, after the step of determining the central coordinate value of the central point of each of the lamp beads according to the first coordinate value, the method further includes:

for each lamp bead, determining a square area by taking the central coordinate value as the center and taking N pixel unit lengths as side lengths;

extracting gray values of M pixel points in each square area;

Calculating a weighted average value of the M gray values to obtain an average gray value of each square area, namely a brightness value of each corresponding lamp bead;

establishing a brightness control model of the lamp beads according to the brightness value and the current value;

wherein N, M is a positive integer.

Preferably, the step of acquiring the character data of the front area of the LED display screen, identifying the face data from the character data by using an artificial intelligent face recognition algorithm, and determining the face distribution data includes:

acquiring image data in a preset angle range of a front area of the LED display screen;

human body detection is carried out on the image data by utilizing a pre-trained artificial intelligent human body detection algorithm to obtain human body detection data;

determining the character data according to the human body detection data, wherein the character data at least comprises human body images, the number of human bodies and the position relationship among the human bodies;

extracting the human body image from the character data;

performing face recognition on the personnel images by using a face recognition algorithm to recognize a first human body with all or part of all the faces facing the LED display screen;

Determining the position relation of S first human bodies according to the position relation of the human bodies, and obtaining the face distribution data;

wherein S is the number of the first human bodies, and S is a positive integer.

Preferably, the step of determining positional relationship data between each face and the LED display screen according to the face distribution data includes:

a three-dimensional coordinate system is established by taking the center of the LED display screen as a coordinate origin O, taking a horizontal line passing through the coordinate origin as a U axis, taking a vertical line passing through the coordinate origin as a V axis, and taking a straight line passing through the coordinate origin and being vertical to the U axis and the V axis as a W axis;

selecting one of the S first human bodies as a punctuation person;

calculating the distance and angle from the coordinate origin O to the punctuation personnel;

calculating punctuation coordinate values of the punctuation personnel in the three-dimensional coordinate system according to the distance and the angle;

determining coordinate values of other S-1 faces according to the punctuation coordinate values and the face distribution data;

and determining the position relation data between all the S human faces and the LED display screen according to the punctuation coordinate values and the coordinate values of the other S-1 human faces.

Another aspect of the present invention provides an artificial intelligence algorithm-based LED bead brightness control device, applied to an LED display screen, including: the lamp beads are provided with a first switch and a second switch, and the acquisition module and the processing control module are used for acquiring current data and image data; wherein,,

The process control module is configured to:

switching on the power supply of the LED display screen, keeping all the first switches connected and the second switches disconnected, and gradually and linearly increasing the working current of the lamp beads passing through the LED display screen, wherein when all the first switches are connected and the second switches are disconnected, all the lamp beads are in a serial state;

synchronously shooting a plurality of images of the lamp beads in the process of increasing the working current, and correlating the current value corresponding to the shooting time of the images with the images;

establishing a brightness control model of the lamp beads according to the image and the current magnitude value;

acquiring character data of the front area of the LED display screen, identifying face data from the character data by utilizing an artificial intelligent face recognition algorithm, and determining face distribution data;

determining position relation data between each face and the LED display screen according to the face distribution data;

dividing a display area of the LED display screen into a plurality of subareas according to the position relation data, and setting brightness display parameters for each subarea;

controlling the connection and disconnection of the first switch and the second switch of each lamp bead according to a plurality of subareas so as to obtain a plurality of lamp bead groups corresponding to the subareas;

And respectively adjusting the brightness of each lamp bead group according to the brightness control model and the brightness display parameters of each subarea.

Preferably, in the step of establishing a brightness control model of the lamp bead according to the image and the current magnitude value, the processing control module is specifically configured to:

graying the image to obtain first image data;

sequentially performing Gaussian filtering, gradient calculation, non-maximum value suppression, double-threshold selection and edge inspection on the first image data to obtain second image data;

filling the edge outline of the lamp bead displayed in the second image data with pixels with gray values of 255 to obtain third image data;

a first right-angle coordinate system is established by taking one point in the third image data as an origin of coordinates and taking the unit length of a pixel as the unit lengths of an X axis and a Y axis, and a first coordinate value of a lamp bead pixel point corresponding to each lamp bead is obtained according to the third image data;

and determining the central coordinate value of the central point of each lamp bead according to the first coordinate value.

Preferably, after the step of determining the central coordinate value of the central point of each of the lamp beads according to the first coordinate value, the process control module is specifically configured to:

For each lamp bead, determining a square area by taking the central coordinate value as the center and taking N pixel unit lengths as side lengths;

extracting gray values of M pixel points in each square area;

calculating a weighted average value of the M gray values to obtain an average gray value of each square area, namely a brightness value of each corresponding lamp bead;

establishing a brightness control model of the lamp beads according to the brightness value and the current value;

wherein N, M is a positive integer.

Preferably, in the step of acquiring the person data in the front area of the LED display screen, and identifying the face data from the person data and determining the face distribution data by using an artificial intelligence face recognition algorithm, the processing control module is specifically configured to:

the acquisition module is controlled to acquire image data within a preset angle range of the front area of the LED display screen;

human body detection is carried out on the image data by utilizing a pre-trained artificial intelligent human body detection algorithm to obtain human body detection data;

determining the character data according to the human body detection data, wherein the character data at least comprises human body images, the number of human bodies and the position relationship among the human bodies;

Extracting the human body image from the character data;

performing face recognition on the personnel images by using a face recognition algorithm to recognize a first human body with all or part of all the faces facing the LED display screen;

determining the position relation of S first human bodies according to the position relation of the human bodies, and obtaining the face distribution data;

wherein S is the number of the first human bodies, and S is a positive integer.

Preferably, in the step of determining positional relationship data between each face and the LED display screen according to the face distribution data, the processing control module is specifically configured to: :

a three-dimensional coordinate system is established by taking the center of the LED display screen as a coordinate origin O, taking a horizontal line passing through the coordinate origin as a U axis, taking a vertical line passing through the coordinate origin as a V axis, and taking a straight line passing through the coordinate origin and being vertical to the U axis and the V axis as a W axis;

selecting one of the S first human bodies as a punctuation person;

calculating the distance and angle from the coordinate origin O to the punctuation personnel;

calculating punctuation coordinate values of the punctuation personnel in the three-dimensional coordinate system according to the distance and the angle;

Determining coordinate values of other S-1 faces according to the punctuation coordinate values and the face distribution data;

and determining the position relation data between all the S human faces and the LED display screen according to the punctuation coordinate values and the coordinate values of the other S-1 human faces.

By adopting the technical scheme, each lamp bead is connected with the first switch and the second switch, and when all the first switches are communicated and all the second switches are disconnected, all the lamp beads are in a serial state; switching on the power supply of the LED display screen, keeping all the first switches connected and the second switches disconnected, and gradually and linearly increasing the working current passing through the lamp beads of the LED display screen; synchronously shooting a plurality of images of the lamp beads in the process of increasing the working current, and correlating the current value corresponding to the shooting time of the images with the images; establishing a brightness control model of the lamp beads according to the image and the current magnitude value; acquiring character data of the front area of the LED display screen, identifying face data from the character data by utilizing an artificial intelligent face recognition algorithm, and determining face distribution data; determining position relation data between each face and the LED display screen according to the face distribution data; dividing a display area of the LED display screen into a plurality of subareas according to the position relation data, and setting brightness display parameters for each subarea; controlling the connection and disconnection of the first switch and the second switch of each lamp bead according to a plurality of subareas so as to obtain a plurality of lamp bead groups corresponding to the subareas; and respectively adjusting the brightness of each lamp bead group according to the brightness control model and the brightness display parameters of each subarea. According to the scheme provided by the invention, the brightness control model of the lamp beads is built firstly, and then the brightness of the lamp beads is regulated according to the character distribution condition in front of the LED display screen, so that the lamp beads are more intelligent and efficient.

Drawings

FIG. 1 is a flowchart of a method for controlling the brightness of LED lamp beads based on an artificial intelligence algorithm according to an embodiment of the invention;

fig. 2 is a schematic block diagram of an LED light bead brightness control device based on an artificial intelligence algorithm according to another embodiment of the present invention.

Detailed Description

In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced otherwise than as described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.

The terms first, second and the like in the description and in the claims of the present application and in the above-described figures, are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

An LED light bead brightness control method and apparatus based on an artificial intelligence algorithm according to some embodiments of the present invention are described below with reference to fig. 1 to 2.

As shown in fig. 1, an embodiment of the present invention provides a method for controlling brightness of LED lamp beads based on an artificial intelligence algorithm, which is applied to an LED display screen, and includes:

connecting each lamp bead with a first switch and a second switch, wherein when all the first switches are communicated and all the second switches are disconnected, all the lamp beads are in a serial state;

switching on the power supply of the LED display screen, keeping all the first switches connected and the second switches disconnected, and gradually and linearly increasing the working current passing through the lamp beads of the LED display screen;

Synchronously shooting a plurality of images of the lamp beads in the process of increasing the working current, and correlating the current value corresponding to the shooting time of the images with the images;

establishing a brightness control model of the lamp beads according to the image and the current magnitude value;

acquiring character data of the front area of the LED display screen, identifying face data from the character data by utilizing an artificial intelligent face recognition algorithm, and determining face distribution data;

determining position relation data between each face and the LED display screen according to the face distribution data;

dividing a display area of the LED display screen into a plurality of subareas according to the position relation data, and setting brightness display parameters for each subarea;

controlling the connection and disconnection of the first switch and the second switch of each lamp bead according to a plurality of subareas so as to obtain a plurality of lamp bead groups corresponding to the subareas;

and respectively adjusting the brightness of each lamp bead group according to the brightness control model and the brightness display parameters of each subarea.

It will be appreciated that in order to provide a refined bead control scheme, at least a first switch and a second switch are configured for each bead, and by controlling the connection and disconnection states of the first switch and the second switch, the serial/parallel relationship between each bead and other beads can be controlled, in this embodiment, when all the first switches are connected and the second switches are disconnected, all the beads are in a serial state. After the power supply of the LED display screen is connected, all the first switches are kept connected and all the second switches are disconnected, at the moment, all the lamp beads are connected in series in a circuit, the passing current is consistent, and when the working current of the lamp beads passing through the LED display screen is gradually and linearly increased, the brightness of the lamp beads can be changed; synchronously shooting a plurality of images of the lamp beads in the process of increasing the working current, so as to obtain sample image data of the brightness of the lamp beads, and correlating the current value corresponding to the shooting time of the images with the images; and establishing a brightness control model of the lamp bead according to the image and the current magnitude value.

It should be noted that, when the positions of the people in front of the LED display screen are different, the viewing angles are different, the display effects seen by the human eyes may be different, and the display brightness perceived by the human body may be different, so that the brightness of the display area of the LED display screen needs to be divided according to the distribution of the people, and each sub-area needs to be adjusted separately. In this embodiment, image data (such as three-dimensional character image data with depth information obtained by a point cloud shooting device) of the front area of the LED display screen is collected, and identification and calculation are performed on the image data to obtain character data of the front area of the LED display screen; combining an artificial intelligent face recognition algorithm and an image measurement technology, recognizing face data from the character data, and acquiring information such as the number, the size, the position, the relative distance and the like of the faces to determine face distribution data; then, determining position relation data between each face and the LED display screen according to the face distribution data by means of a three-dimensional coordinate system, a distance measurement technology and the like; dividing a display area of the LED display screen into a plurality of subareas according to the position relation data, and setting brightness display parameters for each subarea; controlling the connection and disconnection of the first switch and the second switch of each lamp bead according to a plurality of subareas so as to obtain a plurality of lamp bead groups corresponding to the subareas; and respectively adjusting the brightness of each lamp bead group according to the brightness control model and the brightness display parameters of each subarea.

By adopting the scheme of the embodiment of the invention, each lamp bead is connected with the first switch and the second switch, and when all the first switches are communicated and all the second switches are disconnected, all the lamp beads are in a serial state; switching on the power supply of the LED display screen, keeping all the first switches connected and the second switches disconnected, and gradually and linearly increasing the working current passing through the lamp beads of the LED display screen; synchronously shooting a plurality of images of the lamp beads in the process of increasing the working current, and correlating the current value corresponding to the shooting time of the images with the images; establishing a brightness control model of the lamp beads according to the image and the current magnitude value; acquiring character data of the front area of the LED display screen, identifying face data from the character data by utilizing an artificial intelligent face recognition algorithm, and determining face distribution data; determining position relation data between each face and the LED display screen according to the face distribution data; dividing a display area of the LED display screen into a plurality of subareas according to the position relation data, and setting brightness display parameters for each subarea; controlling the connection and disconnection of the first switch and the second switch of each lamp bead according to a plurality of subareas so as to obtain a plurality of lamp bead groups corresponding to the subareas; and respectively adjusting the brightness of each lamp bead group according to the brightness control model and the brightness display parameters of each subarea. According to the scheme provided by the invention, the brightness control model of the lamp beads is built firstly, and then the brightness of the lamp beads is regulated according to the character distribution condition in front of the LED display screen, so that the lamp beads are more intelligent and efficient.

In some possible embodiments of the present invention, the step of establishing a brightness control model of the lamp bead according to the image and the current magnitude value includes:

graying the image to obtain first image data;

sequentially performing Gaussian filtering, gradient calculation, non-maximum value suppression, double-threshold selection and edge inspection on the first image data to obtain second image data;

filling the edge outline of the lamp bead displayed in the second image data with pixels with gray values of 255 to obtain third image data;

a first right-angle coordinate system is established by taking one point in the third image data as an origin of coordinates and taking the unit length of a pixel as the unit lengths of an X axis and a Y axis, and a first coordinate value of a lamp bead pixel point corresponding to each lamp bead is obtained according to the third image data;

and determining the central coordinate value of the central point of each lamp bead according to the first coordinate value.

It can be understood that, in this embodiment, in order to obtain accurate brightness sample values of the respective lamp beads, the image is first grayed to obtain first image data; sequentially performing image processing operations such as Gaussian filtering, gradient calculation, non-maximum value suppression, double-threshold selection, edge inspection and the like on the first image data to obtain second image data; filling the edge outline of the lamp bead displayed in the second image data with pixels with gray values of 255 to obtain third image data; a first right-angle coordinate system is established by taking one point in the third image data as an origin of coordinates and taking the unit length of a pixel as the unit lengths of an X axis and a Y axis, and a first coordinate value of a lamp bead pixel point corresponding to each lamp bead is obtained according to the third image data; and calculating the central coordinate value of the central point of each lamp bead according to the first coordinate value so as to determine the position of each lamp bead.

In some possible embodiments of the present invention, after the step of determining the central coordinate value of the central point of each of the beads according to the first coordinate value, the method further includes:

for each lamp bead, determining a square area by taking the central coordinate value as the center and taking N pixel unit lengths as side lengths;

extracting gray values of M pixel points in each square area;

calculating a weighted average value of the M gray values to obtain an average gray value of each square area, namely a brightness value of each corresponding lamp bead;

establishing a brightness control model of the lamp beads according to the brightness value and the current value;

wherein N, M is a positive integer.

It can be understood that, because the image of each bead includes a plurality of pixels, and the brightness values of the pixels are not completely the same, in order to ensure accuracy and high efficiency of brightness control, in this embodiment, for each bead, a square area is determined by taking the central coordinate value as the center and taking N number of unit lengths of the pixels as side lengths, where the value of N is determined according to actual measurement or big data experience values, and the determined square area is all pixel points covered by the bead; in order to calculate the brightness sample value of each lamp bead, calculating the brightness value of each square region independently, namely respectively extracting the gray values of M pixel points in each region, and calculating a weighted average value of the M gray values to obtain the average gray value of each square region, namely the brightness value of each corresponding lamp bead; and establishing a brightness control model of the lamp bead according to the brightness value and the current value.

In some possible embodiments of the present invention, the step of obtaining the character data of the front area of the LED display screen, and using an artificial intelligence face recognition algorithm to identify the face data from the character data, and determining the face distribution data includes:

acquiring image data in a preset angle range of a front area of the LED display screen;

human body detection is carried out on the image data by utilizing a pre-trained artificial intelligent human body detection algorithm to obtain human body detection data;

determining the character data according to the human body detection data, wherein the character data at least comprises human body images, the number of human bodies and the position relationship among the human bodies;

extracting the human body image from the character data;

performing face recognition on the personnel images by using a face recognition algorithm to recognize a first human body with all or part of all the faces facing the LED display screen;

determining the position relation of S first human bodies according to the position relation of the human bodies, and obtaining the face distribution data;

wherein S is the number of the first human bodies, and S is a positive integer.

It may be appreciated that there are various ways of acquiring the character data in the front area of the LED display screen, in this embodiment of the present invention, image data (such as three-dimensional character image data acquired by the point cloud capturing device) within a preset angle (such as 120 degrees) of the front area of the LED display screen is acquired, then human body detection is performed on the image data (such as recognition performed by a pre-trained human body detection algorithm based on artificial intelligence) to obtain human body detection data, and further human body data including at least human body images, the number of human bodies, the size of human bodies, the positional relationship among the human bodies, and the like is obtained through three-dimensional image data recognition and calculation. When the human body faces away from the LED display screen, the requirement that the corresponding person does not watch the displayed content is described, and the character data is noise data and needs to be removed to improve the precision. In this embodiment, by acquiring the human body image and performing face recognition on the human body image, it is recognized that all or part of the human face (for example, more than a certain preset proportion) faces the first human body of the LED display screen; and determining the position relation of S first human bodies according to the position relation of the first human bodies, and obtaining the face distribution data. It should be noted that, in this embodiment, it may further include: identifying human eye data from the human face data, and determining the human face data of the audience with the sight concentrated on the LED display screen according to the human eye data; and determining the face distribution data according to the face data of the audience. By the scheme, the face of the person not watching the LED display screen can be removed, so that the scheme is more accurate.

In some possible embodiments of the present invention, the step of determining positional relationship data between each face and the LED display screen according to the face distribution data includes:

a three-dimensional coordinate system is established by taking the center of the LED display screen as a coordinate origin O, taking a horizontal line passing through the coordinate origin as a U axis, taking a vertical line passing through the coordinate origin as a V axis, and taking a straight line passing through the coordinate origin and being vertical to the U axis and the V axis as a W axis;

selecting one of the S first human bodies as a punctuation person;

calculating the distance and angle from the coordinate origin O to the punctuation personnel;

calculating punctuation coordinate values of the punctuation personnel in the three-dimensional coordinate system according to the distance and the angle;

determining coordinate values of other S-1 faces according to the punctuation coordinate values and the face distribution data;

and determining the position relation data between all the S human faces and the LED display screen according to the punctuation coordinate values and the coordinate values of the other S-1 human faces.

It can be understood that, in order to determine the positional relationship between the viewer and the display screen more efficiently and accurately, in this embodiment, the distance between the S face and the origin 0 of coordinates, the included angle between each plane, the coordinate values of the S face, and the like are calculated by establishing a three-dimensional coordinate system and adopting a distance measurement algorithm or the like, so as to obtain positional relationship data between all the S faces and the LED display screen.

In some possible embodiments of the present invention, dividing the display area of the LED display screen into a plurality of sub-areas according to the positional relationship data includes:

s vectors from the origin O to the S faces respectively are determined according to the position relation data;

calculating the included angle between the projection of each of the S vectors on the plane UOW and/or the plane VOW and the W axis to obtain S first included angle values on the plane UOW and/or S second included angle values on the plane VOW;

calculating first distribution data and/or second distribution data of the S first included angle values and/or the S second included angle values;

and dividing the LED display screen into a plurality of subareas in the vertical direction and/or the horizontal direction according to the first distribution data and/or the second distribution data.

It can be understood that, in order to more accurately and efficiently adjust the brightness of the light beads of the LED display screen according to the character data, in this embodiment, the position relationship data of the viewer and the LED display screen is determined by means of a three-dimensional coordinate system, S vectors from the origin O to the S face are determined according to the position relationship data, then the angle between the vector projection and the W axis is calculated, finally, a preset angle distribution and a subarea division plan (for example, the LED display screen is divided into six equal parts in the vertical direction in two areas of 60-90 degrees, 30-60 degrees and 0-30 degrees in the plane UOW) are utilized by using a mathematical statistics method, and the LED display screen is divided into a plurality of subareas in the vertical direction and/or the horizontal direction according to the distribution data of the angle. Preferably, more accurate sub-region division can be performed by combining data such as the length of a line segment, the vector size and the like corresponding to the vector projection.

Referring to fig. 2, another embodiment of the present invention provides an LED bead brightness control device based on an artificial intelligence algorithm, which is applied to an LED display screen, and includes: the lamp beads are provided with a first switch and a second switch, and the acquisition module and the processing control module are used for acquiring current data and image data; wherein,,

the process control module is configured to:

switching on the power supply of the LED display screen, keeping all the first switches connected and the second switches disconnected, and gradually and linearly increasing the working current of the lamp beads passing through the LED display screen, wherein when all the first switches are connected and the second switches are disconnected, all the lamp beads are in a serial state;

synchronously shooting a plurality of images of the lamp beads in the process of increasing the working current, and correlating the current value corresponding to the shooting time of the images with the images;

establishing a brightness control model of the lamp beads according to the image and the current magnitude value;

acquiring character data of the front area of the LED display screen, identifying face data from the character data by utilizing an artificial intelligent face recognition algorithm, and determining face distribution data;

Determining position relation data between each face and the LED display screen according to the face distribution data;

dividing a display area of the LED display screen into a plurality of subareas according to the position relation data, and setting brightness display parameters for each subarea;

controlling the connection and disconnection of the first switch and the second switch of each lamp bead according to a plurality of subareas so as to obtain a plurality of lamp bead groups corresponding to the subareas;

and respectively adjusting the brightness of each lamp bead group according to the brightness control model and the brightness display parameters of each subarea.

It will be appreciated that in order to provide a refined bead control scheme, at least a first switch and a second switch are configured for each bead, and by controlling the connection and disconnection states of the first switch and the second switch, the serial/parallel relationship between each bead and other beads can be controlled, in this embodiment, when all the first switches are connected and the second switches are disconnected, all the beads are in a serial state. After the power supply of the LED display screen is connected, all the first switches are kept connected and all the second switches are disconnected, at the moment, all the lamp beads are connected in series in a circuit, the passing current is consistent, and when the working current of the lamp beads passing through the LED display screen is gradually and linearly increased, the brightness of the lamp beads can be changed; synchronously shooting a plurality of images of the lamp beads in the process of increasing the working current, so as to obtain sample image data of the brightness of the lamp beads, and correlating the current value corresponding to the shooting time of the images with the images; and establishing a brightness control model of the lamp bead according to the image and the current magnitude value.

It should be noted that, when the positions of the people in front of the LED display screen are different, the viewing angles are different, the display effects seen by the human eyes may be different, and the display brightness perceived by the human body may be different, so that the brightness of the display area of the LED display screen needs to be divided according to the distribution of the people, and each sub-area needs to be adjusted separately. In this embodiment, image data (such as three-dimensional character image data with depth information obtained by a point cloud shooting device) of the front area of the LED display screen is collected, and identification and calculation are performed on the image data to obtain character data of the front area of the LED display screen; combining an artificial intelligent face recognition algorithm and an image measurement technology, recognizing face data from the character data, and acquiring information such as the number, the size, the position, the relative distance and the like of the faces to determine face distribution data; then, determining position relation data between each face and the LED display screen according to the face distribution data by means of a three-dimensional coordinate system, a distance measurement technology and the like; dividing a display area of the LED display screen into a plurality of subareas according to the position relation data, and setting brightness display parameters for each subarea; controlling the connection and disconnection of the first switch and the second switch of each lamp bead according to a plurality of subareas so as to obtain a plurality of lamp bead groups corresponding to the subareas; and respectively adjusting the brightness of each lamp bead group according to the brightness control model and the brightness display parameters of each subarea.

By adopting the scheme of the embodiment of the invention, each lamp bead is connected with the first switch and the second switch, and when all the first switches are communicated and all the second switches are disconnected, all the lamp beads are in a serial state; switching on the power supply of the LED display screen, keeping all the first switches connected and the second switches disconnected, and gradually and linearly increasing the working current passing through the lamp beads of the LED display screen; synchronously shooting a plurality of images of the lamp beads in the process of increasing the working current, and correlating the current value corresponding to the shooting time of the images with the images; establishing a brightness control model of the lamp beads according to the image and the current magnitude value; acquiring character data of the front area of the LED display screen, identifying face data from the character data by utilizing an artificial intelligent face recognition algorithm, and determining face distribution data; determining position relation data between each face and the LED display screen according to the face distribution data; dividing a display area of the LED display screen into a plurality of subareas according to the position relation data, and setting brightness display parameters for each subarea; controlling the connection and disconnection of the first switch and the second switch of each lamp bead according to a plurality of subareas so as to obtain a plurality of lamp bead groups corresponding to the subareas; and respectively adjusting the brightness of each lamp bead group according to the brightness control model and the brightness display parameters of each subarea. According to the scheme provided by the invention, the brightness control model of the lamp beads is built firstly, and then the brightness of the lamp beads is regulated according to the character distribution condition in front of the LED display screen, so that the lamp beads are more intelligent and efficient.

It should be noted that the block diagram of the LED lamp bead brightness control device based on the artificial intelligence algorithm shown in fig. 2 is only schematic, and the number of the illustrated modules does not limit the protection scope of the present invention.

In some possible embodiments of the present invention, in the step of establishing the brightness control model of the lamp bead according to the image and the current magnitude value, the processing control module is specifically configured to:

graying the image to obtain first image data;

sequentially performing Gaussian filtering, gradient calculation, non-maximum value suppression, double-threshold selection and edge inspection on the first image data to obtain second image data;

filling the edge outline of the lamp bead displayed in the second image data with pixels with gray values of 255 to obtain third image data;

a first right-angle coordinate system is established by taking one point in the third image data as an origin of coordinates and taking the unit length of a pixel as the unit lengths of an X axis and a Y axis, and a first coordinate value of a lamp bead pixel point corresponding to each lamp bead is obtained according to the third image data;

and determining the central coordinate value of the central point of each lamp bead according to the first coordinate value.

It can be understood that, in this embodiment, in order to obtain accurate brightness sample values of the respective lamp beads, the image is first grayed to obtain first image data; sequentially performing image processing operations such as Gaussian filtering, gradient calculation, non-maximum value suppression, double-threshold selection, edge inspection and the like on the first image data to obtain second image data; filling the edge outline of the lamp bead displayed in the second image data with pixels with gray values of 255 to obtain third image data; a first right-angle coordinate system is established by taking one point in the third image data as an origin of coordinates and taking the unit length of a pixel as the unit lengths of an X axis and a Y axis, and a first coordinate value of a lamp bead pixel point corresponding to each lamp bead is obtained according to the third image data; and calculating the central coordinate value of the central point of each lamp bead according to the first coordinate value so as to determine the position of each lamp bead.

In some possible embodiments of the present invention, after the step of determining the central coordinate value of the central point of each of the beads according to the first coordinate value, the process control module is specifically configured to:

For each lamp bead, determining a square area by taking the central coordinate value as the center and taking N pixel unit lengths as side lengths;

extracting gray values of M pixel points in each square area;

calculating a weighted average value of the M gray values to obtain an average gray value of each square area, namely a brightness value of each corresponding lamp bead;

establishing a brightness control model of the lamp beads according to the brightness value and the current value;

wherein N, M is a positive integer.

It can be understood that, because the image of each bead includes a plurality of pixels, and the brightness values of the pixels are not completely the same, in order to ensure accuracy and high efficiency of brightness control, in this embodiment, for each bead, a square area is determined by taking the central coordinate value as the center and taking N number of unit lengths of the pixels as side lengths, where the value of N is determined according to actual measurement or big data experience values, and the determined square area is all pixel points covered by the bead; in order to calculate the brightness sample value of each lamp bead, calculating the brightness value of each square region independently, namely respectively extracting the gray values of M pixel points in each region, and calculating a weighted average value of the M gray values to obtain the average gray value of each square region, namely the brightness value of each corresponding lamp bead; and establishing a brightness control model of the lamp bead according to the brightness value and the current value.

In some possible embodiments of the present invention, in the step of obtaining the person data in the front area of the LED display screen, and identifying the face data from the person data by using an artificial intelligence face recognition algorithm, and determining the face distribution data, the processing control module is specifically configured to:

the acquisition module is controlled to acquire image data within a preset angle range of the front area of the LED display screen;

human body detection is carried out on the image data by utilizing a pre-trained artificial intelligent human body detection algorithm to obtain human body detection data;

determining the character data according to the human body detection data, wherein the character data at least comprises human body images, the number of human bodies and the position relationship among the human bodies;

extracting the human body image from the character data;

performing face recognition on the personnel images by using a face recognition algorithm to recognize a first human body with all or part of all the faces facing the LED display screen;

determining the position relation of S first human bodies according to the position relation of the human bodies, and obtaining the face distribution data;

wherein S is the number of the first human bodies, and S is a positive integer.

It may be appreciated that there are various ways of acquiring the character data in the front area of the LED display screen, in this embodiment of the present invention, image data (such as three-dimensional character image data acquired by the point cloud capturing device) within a preset angle (such as 120 degrees) of the front area of the LED display screen is acquired, then human body detection is performed on the image data (such as recognition performed by a pre-trained human body detection algorithm based on artificial intelligence) to obtain human body detection data, and further human body data including at least human body images, the number of human bodies, the size of human bodies, the positional relationship among the human bodies, and the like is obtained through three-dimensional image data recognition and calculation. When the human body faces away from the LED display screen, the requirement that the corresponding person does not watch the displayed content is described, and the character data is noise data and needs to be removed to improve the precision. In this embodiment, by acquiring the human body image and performing face recognition on the human body image, it is recognized that all or part of the human face (for example, more than a certain preset proportion) faces the first human body of the LED display screen; and determining the position relation of S first human bodies according to the position relation of the first human bodies, and obtaining the face distribution data. It should be noted that, in this embodiment, it may further include: identifying human eye data from the human face data, and determining the human face data of the audience with the sight concentrated on the LED display screen according to the human eye data; and determining the face distribution data according to the face data of the audience. By the scheme, the face of the person not watching the LED display screen can be removed, so that the scheme is more accurate.

In some possible embodiments of the present invention, in the step of determining positional relationship data between each face and the LED display screen according to the face distribution data, the processing control module is specifically configured to: :

a three-dimensional coordinate system is established by taking the center of the LED display screen as a coordinate origin O, taking a horizontal line passing through the coordinate origin as a U axis, taking a vertical line passing through the coordinate origin as a V axis, and taking a straight line passing through the coordinate origin and being vertical to the U axis and the V axis as a W axis;

selecting one of the S first human bodies as a punctuation person;

calculating the distance and angle from the coordinate origin O to the punctuation personnel;

calculating punctuation coordinate values of the punctuation personnel in the three-dimensional coordinate system according to the distance and the angle;

determining coordinate values of other S-1 faces according to the punctuation coordinate values and the face distribution data;

and determining the position relation data between all the S human faces and the LED display screen according to the punctuation coordinate values and the coordinate values of the other S-1 human faces.

It can be understood that, in order to determine the positional relationship between the viewer and the display screen more efficiently and accurately, in this embodiment, the distance between the S face and the origin 0 of coordinates, the included angle between each plane, the coordinate values of the S face, and the like are calculated by establishing a three-dimensional coordinate system and adopting a distance measurement algorithm or the like, so as to obtain positional relationship data between all the S faces and the LED display screen.

In some possible embodiments of the present invention, dividing the display area of the LED display screen into a plurality of sub-areas according to the positional relationship data includes:

s vectors from the origin O to the S faces respectively are determined according to the position relation data;

calculating the included angle between the projection of each of the S vectors on the plane UOW and/or the plane VOW and the W axis to obtain S first included angle values on the plane UOW and/or S second included angle values on the plane VOW;

calculating first distribution data and/or second distribution data of the S first included angle values and/or the S second included angle values;

and dividing the LED display screen into a plurality of subareas in the vertical direction and/or the horizontal direction according to the first distribution data and/or the second distribution data.

It can be understood that, in order to more accurately and efficiently adjust the brightness of the light beads of the LED display screen according to the character data, in this embodiment, the position relationship data of the viewer and the LED display screen is determined by means of a three-dimensional coordinate system, S vectors from the origin O to the S face are determined according to the position relationship data, then the angle between the vector projection and the W axis is calculated, finally, a preset angle distribution and a subarea division plan (for example, the LED display screen is divided into six equal parts in the vertical direction in two areas of 60-90 degrees, 30-60 degrees and 0-30 degrees in the plane UOW) are utilized by using a mathematical statistics method, and the LED display screen is divided into a plurality of subareas in the vertical direction and/or the horizontal direction according to the distribution data of the angle. Preferably, more accurate sub-region division can be performed by combining data such as the length of a line segment, the vector size and the like corresponding to the vector projection.

It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, such as the above-described division of units, merely a division of logic functions, and there may be additional manners of dividing in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, or may be in electrical or other forms.

The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units described above, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the above-mentioned method of the various embodiments of the present application. And the aforementioned memory includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Those of ordinary skill in the art will appreciate that all or a portion of the steps in the various methods of the above embodiments may be implemented by a program that instructs associated hardware, and the program may be stored in a computer readable memory, which may include: flash disk, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk.

The foregoing has outlined rather broadly the more detailed description of embodiments of the present application, wherein specific examples are provided herein to illustrate the principles and embodiments of the present application, the above examples being provided solely to assist in the understanding of the methods of the present application and the core ideas thereof; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

Although the present invention is disclosed above, the present invention is not limited thereto. Variations and modifications, including combinations of the different functions and implementation steps, as well as embodiments of the software and hardware, may be readily apparent to those skilled in the art without departing from the spirit and scope of the invention.

Claims (10)

1. An LED lamp bead brightness control method based on an artificial intelligence algorithm is applied to an LED display screen and is characterized by comprising the following steps:

connecting each lamp bead with a first switch and a second switch, wherein when all the first switches are communicated and all the second switches are disconnected, all the lamp beads are in a serial state;

switching on the power supply of the LED display screen, keeping all the first switches connected and the second switches disconnected, and gradually and linearly increasing the working current passing through the lamp beads of the LED display screen;

synchronously shooting a plurality of images of the lamp beads in the process of increasing the working current, and correlating the current value corresponding to the shooting time of the images with the images;

establishing a brightness control model of the lamp beads according to the image and the current magnitude value;

acquiring character data of the front area of the LED display screen, identifying face data from the character data by utilizing an artificial intelligent face recognition algorithm, and determining face distribution data;

determining position relation data between each face and the LED display screen according to the face distribution data;

dividing a display area of the LED display screen into a plurality of subareas according to the position relation data, and setting brightness display parameters for each subarea;

Controlling the connection and disconnection of the first switch and the second switch of each lamp bead according to a plurality of subareas so as to obtain a plurality of lamp bead groups corresponding to the subareas;

and respectively adjusting the brightness of each lamp bead group according to the brightness control model and the brightness display parameters of each subarea.

2. The method of claim 1, wherein the step of establishing a brightness control model of the lamp beads according to the image and the current magnitude value comprises:

graying the image to obtain first image data;

sequentially performing Gaussian filtering, gradient calculation, non-maximum value suppression, double-threshold selection and edge inspection on the first image data to obtain second image data;

filling the edge outline of the lamp bead displayed in the second image data with pixels with gray values of 255 to obtain third image data;

a first right-angle coordinate system is established by taking one point in the third image data as an origin of coordinates and taking the unit length of a pixel as the unit lengths of an X axis and a Y axis, and a first coordinate value of a lamp bead pixel point corresponding to each lamp bead is obtained according to the third image data;

And determining the central coordinate value of the central point of each lamp bead according to the first coordinate value.

3. The method of claim 2, further comprising, after the step of determining the center coordinate value of the center point of each of the beads according to the first coordinate value:

for each lamp bead, determining a square area by taking the central coordinate value as the center and taking N pixel unit lengths as side lengths;

extracting gray values of M pixel points in each square area;

calculating a weighted average value of the M gray values to obtain an average gray value of each square area, namely a brightness value of each corresponding lamp bead;

establishing a brightness control model of the lamp beads according to the brightness value and the current value;

wherein N, M is a positive integer.

4. The method for controlling the brightness of LED lamp beads based on the artificial intelligence algorithm according to claim 3, wherein the step of acquiring the character data of the front area of the LED display screen, identifying the face data from the character data by using the artificial intelligence face recognition algorithm, and determining the face distribution data comprises the steps of:

Acquiring image data in a preset angle range of a front area of the LED display screen;

human body detection is carried out on the image data by utilizing a pre-trained artificial intelligent human body detection algorithm to obtain human body detection data;

determining the character data according to the human body detection data, wherein the character data at least comprises human body images, the number of human bodies and the position relationship among the human bodies;

extracting the human body image from the character data;

performing face recognition on the personnel images by using a face recognition algorithm to recognize a first human body with all or part of all the faces facing the LED display screen;

determining the position relation of S first human bodies according to the position relation of the human bodies, and obtaining the face distribution data;

wherein S is the number of the first human bodies, and S is a positive integer.

5. The method for controlling the brightness of LED lamp beads based on the artificial intelligence algorithm according to claims 1 to 4, wherein the step of determining positional relationship data between each face and the LED display screen according to the face distribution data comprises:

a three-dimensional coordinate system is established by taking the center of the LED display screen as a coordinate origin O, taking a horizontal line passing through the coordinate origin as a U axis, taking a vertical line passing through the coordinate origin as a V axis, and taking a straight line passing through the coordinate origin and being vertical to the U axis and the V axis as a W axis;

Selecting one of the S first human bodies as a punctuation person;

calculating the distance and angle from the coordinate origin O to the punctuation personnel;

calculating punctuation coordinate values of the punctuation personnel in the three-dimensional coordinate system according to the distance and the angle;

determining coordinate values of other S-1 faces according to the punctuation coordinate values and the face distribution data;

and determining the position relation data between all the S human faces and the LED display screen according to the punctuation coordinate values and the coordinate values of the other S-1 human faces.

6. LED lamp pearl brightness control device based on artificial intelligence algorithm is applied to LED display screen, its characterized in that includes: the lamp beads are provided with a first switch and a second switch, and the acquisition module and the processing control module are used for acquiring current data and image data; wherein,,

the process control module is configured to:

switching on the power supply of the LED display screen, keeping all the first switches connected and the second switches disconnected, and gradually and linearly increasing the working current of the lamp beads passing through the LED display screen, wherein when all the first switches are connected and the second switches are disconnected, all the lamp beads are in a serial state;

Synchronously shooting a plurality of images of the lamp beads in the process of increasing the working current, and correlating the current value corresponding to the shooting time of the images with the images;

establishing a brightness control model of the lamp beads according to the image and the current magnitude value;

acquiring character data of the front area of the LED display screen, identifying face data from the character data by utilizing an artificial intelligent face recognition algorithm, and determining face distribution data;

determining position relation data between each face and the LED display screen according to the face distribution data;

dividing a display area of the LED display screen into a plurality of subareas according to the position relation data, and setting brightness display parameters for each subarea;

controlling the connection and disconnection of the first switch and the second switch of each lamp bead according to a plurality of subareas so as to obtain a plurality of lamp bead groups corresponding to the subareas;

and respectively adjusting the brightness of each lamp bead group according to the brightness control model and the brightness display parameters of each subarea.

7. The LED light bead brightness control device based on the artificial intelligence algorithm of claim 6, wherein in the step of establishing the brightness control model of the light bead from the image and the current magnitude value, the process control module is specifically configured to:

Graying the image to obtain first image data;

sequentially performing Gaussian filtering, gradient calculation, non-maximum value suppression, double-threshold selection and edge inspection on the first image data to obtain second image data;

filling the edge outline of the lamp bead displayed in the second image data with pixels with gray values of 255 to obtain third image data;

a first right-angle coordinate system is established by taking one point in the third image data as an origin of coordinates and taking the unit length of a pixel as the unit lengths of an X axis and a Y axis, and a first coordinate value of a lamp bead pixel point corresponding to each lamp bead is obtained according to the third image data;

and determining the central coordinate value of the central point of each lamp bead according to the first coordinate value.

8. The LED light bead brightness control device of claim 7, wherein after the step of determining the center coordinate value of the center point of each of the light beads according to the first coordinate value, the process control module is specifically configured to:

for each lamp bead, determining a square area by taking the central coordinate value as the center and taking N pixel unit lengths as side lengths;

Extracting gray values of M pixel points in each square area;

calculating a weighted average value of the M gray values to obtain an average gray value of each square area, namely a brightness value of each corresponding lamp bead;

establishing a brightness control model of the lamp beads according to the brightness value and the current value;

wherein N, M is a positive integer.

9. The LED lamp bead luminance control device based on the artificial intelligence algorithm of claim 8, wherein in the step of obtaining the character data of the front area of the LED display screen, and identifying the face data from the character data by using the artificial intelligence face recognition algorithm, and determining the face distribution data, the processing control module is specifically configured to:

the acquisition module is controlled to acquire image data within a preset angle range of the front area of the LED display screen;

human body detection is carried out on the image data by utilizing a pre-trained artificial intelligent human body detection algorithm to obtain human body detection data;

determining the character data according to the human body detection data, wherein the character data at least comprises human body images, the number of human bodies and the position relationship among the human bodies;

Extracting the human body image from the character data;

performing face recognition on the personnel images by using a face recognition algorithm to recognize a first human body with all or part of all the faces facing the LED display screen;

determining the position relation of S first human bodies according to the position relation of the human bodies, and obtaining the face distribution data;

wherein S is the number of the first human bodies, and S is a positive integer.

10. The LED light bead brightness control device based on the artificial intelligence algorithm according to claims 6-9, wherein in the step of determining positional relationship data between each face and the LED display screen according to the face distribution data, the processing control module is specifically configured to: :

a three-dimensional coordinate system is established by taking the center of the LED display screen as a coordinate origin O, taking a horizontal line passing through the coordinate origin as a U axis, taking a vertical line passing through the coordinate origin as a V axis, and taking a straight line passing through the coordinate origin and being vertical to the U axis and the V axis as a W axis;

selecting one of the S first human bodies as a punctuation person;

calculating the distance and angle from the coordinate origin O to the punctuation personnel;

calculating punctuation coordinate values of the punctuation personnel in the three-dimensional coordinate system according to the distance and the angle;

Determining coordinate values of other S-1 faces according to the punctuation coordinate values and the face distribution data;

and determining the position relation data between all the S human faces and the LED display screen according to the punctuation coordinate values and the coordinate values of the other S-1 human faces.

Images