WO2024060447A1 - 动态画面检测方法、装置、显示器及存储介质 - Google Patents

动态画面检测方法、装置、显示器及存储介质 Download PDF

Info

Publication number
WO2024060447A1
WO2024060447A1 PCT/CN2022/142037 CN2022142037W WO2024060447A1 WO 2024060447 A1 WO2024060447 A1 WO 2024060447A1 CN 2022142037 W CN2022142037 W CN 2022142037W WO 2024060447 A1 WO2024060447 A1 WO 2024060447A1
Authority
WO
WIPO (PCT)
Prior art keywords
optical flow
detected
image
preset
target
Prior art date
Application number
PCT/CN2022/142037
Other languages
English (en)
French (fr)
Inventor
刘伟明
武洁
Original Assignee
深圳创维－Rgb电子有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳创维－Rgb电子有限公司 filed Critical 深圳创维－Rgb电子有限公司
Publication of WO2024060447A1 publication Critical patent/WO2024060447A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G06T7/248—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving reference images or patches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence

Definitions

  • the present application relates to the field of image display technology, and in particular to a dynamic picture detection method, device, display and storage medium.
  • OLED Organic Light-Emitting Diode (organic light-emitting diode) display screen
  • It can improve the contrast and make the display better.
  • the problem of screen burn-in may occur.
  • OLED display The screen itself needs to detect whether the current screen is a static screen every once in a while. If it is a static screen, it needs to shift the pixels of the OLED display or enter the screen saver screen.
  • the TV's mouse or remote control operations can be used as event triggers and determined as dynamic images.
  • the mouse on the external device will The operation is a video signal and cannot be detected as an event trigger, so it cannot be judged as a dynamic picture. Therefore, the screen saver screen may be entered during the user's use, affecting the user experience.
  • the main purpose of this application is to provide a dynamic picture detection method, device, display and storage medium, aiming to solve the technical problem of low detection accuracy of dynamic pictures in the prior art.
  • the dynamic picture detection method includes:
  • the display picture is a dynamic picture.
  • the dynamic picture detection device is applied to dynamic picture detection equipment.
  • the dynamic picture detection device includes:
  • An acquisition module configured to acquire at least two images to be detected corresponding to the display screen of the display
  • a detection module used to detect moving targets in the image to be detected according to a preset dense optical flow algorithm
  • the determination module is used to determine that the displayed picture is a dynamic picture if a moving target is detected in the image to be detected.
  • This application also provides a display, which is a physical device.
  • the display includes: a memory, a processor, and a program of the dynamic picture detection method stored on the memory and executable on the processor.
  • the program of the dynamic picture detection method is executed by the processor, the steps of the dynamic picture detection method as described above can be implemented.
  • the storage medium is a computer-readable storage medium.
  • the computer-readable storage medium stores a program for implementing a dynamic picture detection method.
  • the program for the dynamic picture detection method is executed by a processor.
  • the present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned dynamic picture detection method when executed by a processor.
  • This application provides a dynamic picture detection method, device, display and storage medium.
  • the display picture output and displayed on the display is obtained, and then through According to the preset dense optical flow algorithm, the moving target in the image to be detected is detected, thereby realizing the detection of whether there is a moving target in the display screen, and then if the moving target is detected in the image to be detected, Then it is determined that the displayed picture is a dynamic picture, which realizes the detection and accurate determination of whether the input image information is a dynamic picture on the display side.
  • the detection process does not rely on the change or detection of the signal, but is only based on whether the picture itself changes, avoiding
  • the dynamic screen is misjudged as a static screen. This improves the accuracy of dynamic screen detection and overcomes the problem of the relatively low detection accuracy of dynamic screen in the existing technology. Low technical issues.
  • Figure 1 is a schematic scene diagram of an implementable manner in the dynamic picture detection method of the present application
  • Figure 2 is a schematic diagram of a display structure of the hardware operating environment involved in the dynamic picture detection method in the embodiment of the present application;
  • Figure 3 is a schematic flow chart of an embodiment of the dynamic picture detection method of the present application.
  • Figure 4 is a schematic flow chart of another embodiment of the dynamic picture detection method of the present application.
  • Figure 5 is a schematic structural diagram of the device involved in the dynamic picture detection method in the embodiment of the present application.
  • OLED Organic Light-Emitting Diode (organic light-emitting diode) display screen
  • OLED Organic Light-Emitting Diode
  • the OLED display cannot rely on the screen saver of the host. It needs to detect whether the current screen is a static screen every once in a while. If it is a static screen, the OLED display pixels need to be shifted or enter the screen saver screen. wait.
  • the TV's mouse or remote control operations can be used as event triggers and determined as dynamic images.
  • the mouse on the external device will The operation is a video signal and cannot be detected as an event trigger, so it cannot be judged as a dynamic picture, so the screen saver screen may be entered during the user's use.
  • Figure 1 is a schematic diagram of an implementable manner of the dynamic picture detection method of the present application.
  • the computer transmits the computer picture to a TV with an OLED screen for output through a high-definition cable.
  • the TV may Because no dynamic picture is detected, the OLED display is controlled to enter the screen saver screen. However, for the user, the operation does not actually stop at this time. That is, there is no need to enter the screen saver screen at this time, and the user's computer screen is interrupted. The display process affects the user experience.
  • FIG 2 is a schematic diagram of a display structure of the hardware operating environment involved in the dynamic picture detection method in the embodiment of the present application.
  • Displays in embodiments of the present disclosure may include, but are not limited to, OLED displays, LCD (Liquid Crystal Display, liquid crystal display), LED (light-emitting diode, light-emitting diode) displays, etc.
  • the display also includes: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a network interface 1003, and a memory 1004.
  • a processor 1001 such as a central processing unit (Central Processing Unit, CPU)
  • a communication bus 1002 is used to realize connection communication between these components.
  • the network interface 1003 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (WI-FI) interface).
  • the memory 1004 may be a high-speed random access memory (Random Access Memory (RAM) memory, or stable non-volatile memory (Non-Volatile Memory, NVM), such as disk memory.
  • RAM Random Access Memory
  • NVM non-Volatile Memory
  • the memory 1004 may optionally be a storage device independent of the aforementioned processor 1001.
  • the terminal may also include a camera, RF (Radio Frequency, radio frequency) circuits, sensors, audio circuits, WiFi modules, etc.
  • sensors such as light sensors, motion sensors and other sensors.
  • the light sensor may include an ambient light sensor and a proximity sensor.
  • the ambient light sensor may adjust the brightness of the display screen according to the brightness of the ambient light.
  • the proximity sensor may turn off the display screen and/or when the mobile terminal moves to the ear. Backlight.
  • the gravity acceleration sensor can detect the magnitude of acceleration in various directions (usually three axes).
  • the mobile terminal can detect the magnitude and direction of gravity when stationary, and can be used to identify applications such as mobile terminal posture (such as horizontal and vertical screen switching, Related games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tapping), etc.; of course, the mobile terminal can also be equipped with other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc., here No longer.
  • mobile terminal posture such as horizontal and vertical screen switching, Related games, magnetometer attitude calibration
  • vibration recognition related functions such as pedometer, tapping
  • the mobile terminal can also be equipped with other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc., here No longer.
  • FIG. 2 does not constitute a limitation on the operating device, and may include more or fewer components than shown, or a combination of certain components, or a different arrangement of components.
  • the memory 1004 as a storage medium may include an operating system, a data storage module, a network communication module, and a dynamic picture detection program.
  • the network interface 1003 is mainly used for data communication with other devices.
  • the processor 1001 and the memory 1004 in the running device of this application can be set in the running device.
  • the running device calls the dynamic picture detection program stored in the memory 1004 through the processor 1001 and performs the following operations:
  • the display picture is a dynamic picture.
  • processor 1001 can call the dynamic picture detection program stored in the memory 1004, and also perform the following operations:
  • a target optical flow vector whose optical flow mode length is greater than the preset optical flow mode length threshold is detected, it is determined that there is a moving target in the image to be detected.
  • processor 1001 can call the dynamic picture detection program stored in the memory 1004, and also perform the following operations:
  • optical flow mode length and optical flow direction of the optical flow vector are determined.
  • the moving target present in the image to be detected is determined.
  • processor 1001 can call the dynamic picture detection program stored in the memory 1004, and also perform the following operations:
  • the moving target present in the to-be-detected image is determined.
  • processor 1001 can call the dynamic picture detection program stored in the memory 1004, and also perform the following operations:
  • processor 1001 can call the dynamic picture detection program stored in the memory 1004, and also perform the following operations:
  • the preset dense optical flow algorithm determine the initial vector corresponding to each pixel in the image to be detected
  • the module length of the first target initial vector whose module length is greater than the preset first module length is adjusted to the preset first module length, and in each of the initial vectors, the module length is smaller than the preset module length.
  • the module length of the second target initial vector of the first module length is processed by median filtering and adjusted to the second module length to obtain the intermediate vector;
  • processor 1001 can call the dynamic picture detection program stored in the memory 1004, and also perform the following operations:
  • An embodiment of the present application provides a dynamic picture detection method.
  • the dynamic picture detection method is applied to a display and includes the following steps:
  • Step S10 obtaining at least two images to be detected corresponding to the display screen of the display;
  • the dynamic picture detection method is applied to a display.
  • the display may include but is not limited to an OLED display, an LCD, an LED display, etc., and the display passes HDMI (High Definition Multimedia Interface, High Definition Interface). Multimedia interface), VGA (Video Graphics Array, video graphics array) interface or DP (DisplayPort, display interface), etc., are linearly connected with the user equipment, and then receive and output the video signal transmitted by the display user equipment, wherein the user equipment includes Laptops, computers, tablets, mobile phones and other portable terminal devices.
  • images to be detected corresponding to the display screen of the display at at least two different times are obtained, wherein the display screen can be a dynamic screen or a static screen, and the image to be detected is the display screen at a certain time.
  • the time interval between the time ranges corresponding to the images to be detected can be determined according to the actual situation. This embodiment does not limit this.
  • the images to be detected can be directly captured by taking screenshots or taking photos.
  • the acquired image may also be an image obtained by taking a screenshot or taking a photo, and then preprocessing using image processing technology.
  • the method of obtaining at least two images to be detected corresponding to the display screen of the display may be to use the MT9950 platform and obtain once every 1.5 seconds through the screenshot interface of the Android system.
  • openCV An open source computer vision library
  • the step of obtaining at least two images to be detected corresponding to the display screen of the display includes:
  • Step S11 take at least two screenshots of the display screen of the monitor to obtain at least two screenshot images
  • screenshots are taken of the display screen of the display at at least two different times to obtain at least two screenshot images.
  • Step S12 Perform specification adjustment and grayscale conversion on each of the screenshot images to obtain at least two images to be detected.
  • the specifications of each of the screenshot images are adjusted, and the adjusted screenshot images are converted into grayscale images to obtain at least two grayscale images to be detected.
  • the specification adjustment method is to reduce the resolution of the screenshot image.
  • the specification adjustment method is to intercept the portion corresponding to the area to be detected in the screenshot image, wherein the area to be detected can be determined according to actual needs.
  • the area to be detected can be determined according to the information.
  • the position of the prompt pop-up window when it appears on the screen is determined, and such information prompt pop-up windows usually appear in the peripheral edge areas of the screen. Therefore, the area to be detected can be a part of the center of the screenshot image, or it can be The area above the nth row of pixels from bottom to top in the screenshot image, etc.
  • a pop-up window with a message prompt may appear.
  • Such message prompts usually have nothing to do with whether the user's device is operated by someone.
  • the display will determine the screen due to the message prompt.
  • the screen saver screen may be re-entered after a period of time, that is, the screen saver screen is raised due to a message prompt.
  • the process is essentially an invalid operation, and will also consume the computing power and power of the device.
  • the calculation amount of subsequent moving target detection can be effectively reduced, thereby improving the detection efficiency of dynamic picture detection.
  • Step S20 Detect the moving target in the image to be detected according to the preset dense optical flow algorithm
  • the pixels in the two images to be detected are compared one by one to determine whether there is a moving target in the image to be detected, wherein,
  • the dense optical flow algorithm is an image registration method that performs point-by-point matching of images. By calculating the offset of all points on the image, a dense optical flow field is formed. The method determines whether the image to be detected is To detect the existence of moving targets, you can determine the existence of moving targets in the two images to be detected based on the offset between the two images to be detected. You can also set the offset threshold or offset pixel number threshold according to the actual situation.
  • Step S30 If a moving target is detected in the image to be detected, it is determined that the display screen is a dynamic screen.
  • the display screen is a dynamic picture in the time range corresponding to each image to be detected; if in the image to be detected If no moving target is detected, it is determined that the display picture is a static picture in the time range corresponding to each of the images to be detected.
  • the following steps are also included: starting timing, and returning to the execution step: obtaining at least two images to be detected corresponding to the displayed image of the display; if no dynamic image is detected within a preset time range, outputting a display screen saver image.
  • the display screen output and displayed on the monitor is obtained, and then the said display screen is obtained according to the preset dense optical flow algorithm.
  • Detecting the moving target in the image to be detected realizes the detection of whether there is a moving target in the display screen, and then determines that the display screen is a dynamic screen if the moving target is detected in the image to be detected, thus realizing
  • the display side detects and accurately determines whether the input image information is a dynamic picture.
  • the detection process does not rely on the change or detection of the signal, but is only based on whether the picture itself changes. This avoids the inability to detect when the display picture is input as a video signal.
  • the accuracy of dynamic picture detection is improved and the technical problem of low detection accuracy of dynamic pictures in the prior art is overcome.
  • the step of identifying the message notification area in each initial screen projection image frame includes:
  • Step S21 determine the optical flow vector corresponding to each pixel in the image to be detected according to the preset dense optical flow algorithm
  • the pixels in the two images to be detected are compared one by one to obtain the optical flow offset of the moving target, and each pixel can be determined.
  • the light corresponding to each pixel point in the image to be detected can be determined. Modulus length and direction of the flow vector.
  • the step of determining the optical flow vector corresponding to each pixel in the image to be detected according to a preset dense optical flow algorithm includes:
  • Step S211 determine the initial vector corresponding to each pixel point in the image to be detected according to the preset dense optical flow algorithm
  • the pixels in the two images to be detected are compared one by one to obtain the optical flow offset of the moving target, and each pixel can be determined.
  • the initial value corresponding to each pixel point in the image to be detected can be determined.
  • Step S212 Adjust the module length of the first target initial vector whose module length is greater than the preset first module length in each of the initial vectors to the preset first module length, and adjust the module length of each of the initial vectors.
  • the module length of the second target initial vector that is smaller than the preset first module length is processed by median filtering and adjusted to the second module length to obtain the intermediate vector;
  • all or part of the initial vectors within a certain range are sorted according to the size of the module length, for example, each row of initial vectors is sorted, each column of initial vectors is sorted, etc., and the module length is greater than
  • the initial vector with the preset first module length is used as the first target initial vector, and the module length of each first target initial vector is adjusted to the preset first module length; the module length is smaller than the initial vector with the preset first module length.
  • the module length of each second target initial vector is brought into the preset median filter algorithm, the second module length is calculated, and the module length of each second target initial vector is adjusted to the desired value.
  • the second module length is set; the initial vector whose module length is equal to the preset first module length remains unchanged. After modulus length adjustment is performed on all initial vectors, intermediate vectors corresponding to each initial vector are obtained.
  • the method of sorting each of the initial vectors may be bubble sorting or the like.
  • Step S213 Divide the modulus of each intermediate vector by its corresponding maximum modulus to obtain an optical flow vector.
  • the optical flow vector is obtained by dividing the modulus length of each intermediate vector by its corresponding maximum modulus length, where the maximum modulus length corresponding to each of the intermediate vectors is
  • the maximum module length among the initial vectors that are sorted together. For example, if all the initial vectors are sorted according to the module length, then the maximum module length corresponding to each intermediate vector The module lengths are the same and are the maximum module lengths among all initial vectors.
  • each row of initial vectors can determine a maximum module length, and the corresponding maximum module lengths of the intermediate vectors in each row
  • the module length is the maximum module length determined for the row in which it is located.
  • the maximum module lengths corresponding to the intermediate vectors located in different rows may be the same or different.
  • the mode length of each optical flow vector is smoothed by median filtering and dividing by the maximum mode length, thereby reducing detection noise and improving the anti-noise capability of the dynamic picture detection method. .
  • Step S22 If in each of the optical flow vectors, a target optical flow vector whose optical flow mode length is greater than the preset optical flow mode length threshold is detected, it is determined that there is a moving target in the image to be detected.
  • each optical flow vector it is determined whether the optical flow mode length of each optical flow vector is greater than a preset optical flow mode length threshold. If in each of the optical flow vectors, it is detected that the optical flow mode length is greater than the preset optical flow mode length. If the target optical flow vector has an optical flow mode length threshold, it is determined that there is a moving target in the image to be detected; if in each of the optical flow vectors, no target with an optical flow mode length greater than the preset optical flow mode length threshold is detected.
  • the preset optical flow mode length threshold can be determined based on big data, actual test results, etc., for example, the preset optical flow mode length threshold It can be 0, or a minimum value can be determined based on noise or error values, which is not limited in this embodiment.
  • steps also include:
  • Step S221 if in each of the optical flow vectors, a target optical flow vector whose optical flow mode length is greater than the preset optical flow mode length threshold is detected, count the total number of each of the target optical flow vectors;
  • Step S222 If the total number of target optical flow vectors exceeds the preset total threshold, it is determined that there is a moving target in the image to be detected;
  • Step S223 If the total number of target optical flow vectors does not exceed a preset total threshold, it is determined that there is no moving target in the image to be detected.
  • the total number of each of the target optical flow vectors is counted. , determine whether the total number of target optical flow vectors exceeds the preset total threshold. If the total number of target optical flow vectors exceeds the preset total threshold, it is determined that there is a moving target in the image to be detected; if the target optical flow If the total number of vectors does not exceed the preset total threshold, it is determined that there is no moving target in the image to be detected.
  • the noise interference can be reduced and the accuracy of detection can be improved.
  • the step of determining whether a moving target exists in the image to be detected includes:
  • Step S221 if in each of the optical flow vectors, a target optical flow vector whose optical flow mode length is greater than the preset optical flow mode length threshold is detected, then determine based on the optical flow mode length and optical flow direction of the optical flow vector.
  • the optical flow modulus of each of the optical flow vectors is greater than a preset optical flow modulus threshold. If, in each of the optical flow vectors, no target optical flow vector with an optical flow modulus greater than the preset optical flow modulus threshold is detected, it is determined that there is no moving target in the image to be detected; if, in each of the optical flow vectors, a target optical flow vector with an optical flow modulus greater than the preset optical flow modulus threshold is detected, the polar coordinates corresponding to the optical flow vector are determined based on the optical flow modulus and the optical flow direction of the optical flow vector.
  • Step S222 generating an optical flow image according to the polar coordinates corresponding to each of the optical flow vectors
  • each optical flow vector can be determined based on the polar diameter and polar angle of the polar coordinates corresponding to each optical flow vector, using the polar angle as hue information and the polar diameter as saturation information.
  • the corresponding color of the HSV color space and then based on the conversion relationship between the HSV color space and the RGB color space, an optical flow image represented by the RGB color space is obtained.
  • the polar diameters of the parts without motion are almost the same, showing The colors are almost the same and can be used as the background color of the optical flow image.
  • the moving parts due to their different movement speeds, show different colors, and a corresponding moving image can be formed on the background color.
  • optical flow vectors whose polar diameters are smaller than a preset polar diameter threshold can be represented as black in the optical flow image.
  • Step S223 If a moving image is detected in the optical flow image, determine the moving target present in the image to be detected.
  • image recognition technology is used to identify moving images in the optical flow image. If a moving image is detected in the optical flow image, it is determined whether the moving image exists in the image to be detected. Moving target, if no moving image is detected in the optical flow image, it is determined that the moving target does not exist in the image to be detected, wherein the moving image is made of a background color different from that of the optical flow image. Regular or irregular graphics composed of colors.
  • the method of identifying moving images in the optical flow image can be to detect whether there is a color different from the background color in the optical flow image, or to identify the light Contours in streaming images, etc.
  • the step of determining the moving target present in the image to be detected includes:
  • Step S2231 if a moving image is detected in the optical flow image, determine the circumscribed contour of the moving image in the optical flow image according to a preset contour discovery algorithm;
  • Step S2232 Based on the position of the circumscribed contour, determine whether each of the moving images is located in the area to be detected on the display screen;
  • Step S2233 If at least one of the moving images is detected in the to-be-detected area of the display screen, determine the moving target present in the to-be-detected image.
  • image recognition technology is used to identify moving images in the optical flow image. If no moving image is detected in the optical flow image, it is determined that there is no moving image in the image to be detected.
  • the positional relationship between the areas to be detected on the screen is used to determine whether each of the moving images is located in the area to be detected on the display screen. If at least one of the moving images is detected in the area to be detected on the display screen, then Determine whether the moving target exists in the image to be detected. If the moving image is not detected in the area to be detected in the display screen, determine whether the moving target does not exist in the image to be detected.
  • a pop-up window with a message prompt may also appear.
  • Such message prompts usually have nothing to do with whether the user device is operated by someone. If the display screen detects that the static picture enters the screen saver screen, The monitor determines that the screen is a dynamic screen due to a message prompt and exits the screen saver screen. At this time, since the screen saver screen is not released due to user operation, it may re-enter the screen saver screen after a period of time, that is, due to the message prompt The process of proposing a screen saver screen is essentially an invalid operation, and will also consume the computing power and battery of the device. By limiting the area to be detected, the above-mentioned invalid exit of the screen saver screen can be effectively avoided.
  • the embodiment of the present application also provides a dynamic picture detection device.
  • the dynamic picture detection device is applied to dynamic picture detection equipment.
  • the dynamic picture detection device includes:
  • the acquisition module 10 is used to acquire at least two images to be detected corresponding to the display screen of the display;
  • the detection module 20 is used to detect moving targets in the image to be detected according to the preset dense optical flow algorithm
  • the determination module 30 is configured to determine that the display picture is a dynamic picture if a moving target is detected in the image to be detected.
  • the detection module 20 is also used to:
  • the preset dense optical flow algorithm determine the optical flow vector corresponding to each pixel in the image to be detected
  • a target optical flow vector whose optical flow mode length is greater than the preset optical flow mode length threshold is detected, it is determined that there is a moving target in the image to be detected.
  • the detection module 20 is also used to:
  • optical flow mode length and optical flow direction of the optical flow vector are determined.
  • the moving target present in the image to be detected is determined.
  • the detection module 20 is also used to:
  • the moving target present in the to-be-detected image is determined.
  • the detection module 20 is also used to:
  • the detection module 20 is also used to:
  • the preset dense optical flow algorithm determine the initial vector corresponding to each pixel in the image to be detected
  • the module length of the first target initial vector whose module length is greater than the preset first module length is adjusted to the preset first module length, and in each of the initial vectors, the module length is smaller than the preset module length.
  • the module length of the second target initial vector of the first module length is processed by median filtering and adjusted to the second module length to obtain the intermediate vector;
  • the acquisition module 10 is also used to:
  • the dynamic picture detection device provided by this application adopts the dynamic picture detection method in the above embodiment to solve the technical problem of low detection accuracy of dynamic pictures in the prior art.
  • the beneficial effects of the dynamic picture detection device provided by the embodiments of the present application are the same as those of the dynamic picture detection method provided by the above-mentioned embodiments, and other technical features of the dynamic picture detection device are the same as those of the above-mentioned embodiments.
  • the features disclosed by the methods are the same and will not be described again here.
  • the present application also provides a computer program product, including a computer program that implements the steps of the dynamic picture detection method as described above when executed by a processor.
  • the computer program product provided by this application solves the technical problem of low detection accuracy of dynamic pictures in the prior art.
  • the beneficial effects of the computer program product provided by the embodiments of the present application are the same as the beneficial effects of the dynamic picture detection method provided by the above embodiments, and will not be described again here.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)

Abstract

本申请公开了一种动态画面检测方法、装置、显示器及存储介质，所述动态画面检测方法包括：获取所述显示器的显示画面对应的至少两张待检测图像；根据预设的稠密光流算法，对所述待检测图像中的运动目标进行检测；若在所述待检测图像中检测到运动目标，则判定所述显示画面为动态画面。

Description

动态画面检测方法、装置、显示器及存储介质
本申请要求于2022年9月21日申请的、申请号为202211153920.8的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及图像显示技术领域，尤其涉及一种动态画面检测方法、装置、显示器及存储介质。
 背景技术
随着广播电视事业的飞速发展、数字化进程的不断加快，OLED（Organic Light-Emitting Diode，有机发光二极管）显示屏应运而生，它能提升对比度，使显示画面更好，但OLED显示屏长期处于静态画面时，可能会出现烧屏的问题，为了解决烧屏的问题，OLED显示屏自身需要每隔一段时间去检测当前画面是否处于静态画面，如果是静态画面，需要对OLED显示屏像素进行移位操作或者进入屏幕保护画面等。对于OLED显示屏的电视机来说，电视机的鼠标或者遥控等操作可以作为事件触发，判定为动态画面，但是当OLED显示屏的图像内容是由外接设备输入时，此时外接设备上的鼠标等操作为视频信号，而无法被检测为事件触发，故而无法被判定为动态画面，故而可能在用户使用过程中进入屏幕保护画面，影响用户体验。
 技术问题
本申请的主要目的在于提供一种动态画面检测方法、装置、显示器及存储介质，旨在解决现有技术动态画面的检测准确性较低的技术问题。
 技术解决方案
为实现上述目的，本申请提供一种动态画面检测方法，所述动态画面检测方法包括：
获取所述显示器的显示画面对应的至少两张待检测图像；
根据预设的稠密光流算法，对所述待检测图像中的运动目标进行检测；
若在所述待检测图像中检测到运动目标，则判定所述显示画面为动态画面。
本申请还提供一种动态画面检测装置，所述动态画面检测装置应用于动态画面检测设备，所述动态画面检测装置包括：
获取模块，用于获取所述显示器的显示画面对应的至少两张待检测图像；
检测模块，用于根据预设的稠密光流算法，对所述待检测图像中的运动目标进行检测；
判定模块，用于若在所述待检测图像中检测到运动目标，则判定所述显示画面为动态画面。
本申请还提供一种显示器，所述显示器为实体设备，所述显示器包括：存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的所述动态画面检测方法的程序，所述动态画面检测方法的程序被处理器执行时可实现如上述的动态画面检测方法的步骤。
本申请还提供一种存储介质，所述存储介质为计算机可读存储介质，所述计算机可读存储介质上存储有实现动态画面检测方法的程序，所述动态画面检测方法的程序被处理器执行时实现如上述的动态画面检测方法的步骤。
本申请还提供一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现如上述的动态画面检测方法的步骤。
 有益效果
本申请提供了一种动态画面检测方法、装置、显示器及存储介质，通过获取所述显示器的显示画面对应的至少两张待检测图像，实现了对显示器上输出显示的显示画面的获取，进而通过根据预设的稠密光流算法，对所述待检测图像中的运动目标进行检测，实现了对显示画面中是否存在运动目标的检测，进而通过若在所述待检测图像中检测到运动目标，则判定所述显示画面为动态画面，实现了显示器端对输入的图像信息是否为动态画面的检测和准确判定，检测过程不依赖于信号的变化或检测，仅基于画面本身是否发生变化，避免了当显示画面作为视频信号输入时，由于无法检测到事件触发，而将动态画面误判为静态画面的情况，提高了动态画面检测的准确性，克服了解决现有技术动态画面的检测准确性较低的技术问题。
 附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本申请的实施例，并与说明书一起用于解释本申请的原理。
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，对于本领域普通技术人员而言，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本申请动态画面检测方法中一种可实施方式的场景示意图；
图2为本申请实施例中动态画面检测方法涉及的硬件运行环境的显示器结构示意图；
图3为本申请动态画面检测方法一实施例的流程示意图；
图4为本申请动态画面检测方法另一实施例的流程示意图；
图5为本申请实施例中动态画面检测方法涉及的装置结构示意图。
本申请目的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
 本发明的实施方式
为使本申请的上述目的、特征和优点能够更加明显易懂，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述。显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动的前提下所获得的所有其它实施例，均属于本申请保护的范围。
随着广播电视事业的飞速发展、数字化进程的不断加快，OLED（Organic Light-Emitting Diode，有机发光二极管）显示屏应运而生，它能提升对比度，使显示画面更好，但OLED显示屏长期处于静态画面时，可能会出现烧屏的问题，为了解决烧屏的问题，OLED显示屏无法依赖于主机的屏幕保护程序，其自身就需要每隔一段时间去检测当前画面是否处于静态画面，如果是静态画面，需要对OLED显示屏像素进行移位操作或者进入屏幕保护画面等。
对于OLED显示屏的电视机来说，电视机的鼠标或者遥控等操作可以作为事件触发，判定为动态画面，但是当OLED显示屏的图像内容是由外接设备输入时，此时外接设备上的鼠标等操作为视频信号，而无法被检测为事件触发，故而无法被判定为动态画面，故而可能在用户使用过程中进入屏幕保护画面。在一种可实施的方式中，参照图1，图1为本申请动态画面检测方法中一种可实施方式的场景示意图，电脑通过高清线，将电脑画面传输到具有OLED屏的电视机上进行输出显示，此时，即使用户在电脑上进行操作，由于电脑上的鼠标等操作为视频信号，而无法被检测为事件触发，故而无法被判定为动态画面，故而可能在用户使用过程中，电视机会由于未检测到动态画面，而控制OLED显示屏进入屏幕保护画面，而此时对于用户而言，实际并未停止操作，也即，此时并不需要进入屏幕保护画面，又中断了用户电脑画面的展示过程，影响了用户体验。
参照图2，图2为本申请实施例中动态画面检测方法涉及的硬件运行环境的显示器结构示意图。本公开实施例中的显示器可以包括但不限于OLED显示器、LCD（Liquid Crystal Display，液晶显示器）、LED（light-emitting diode，发光二极管）显示器等。
如图2所示，所述显示器还包括：处理器1001，例如中央处理器（Central Processing Unit，CPU），通信总线1002，网络接口1003，存储器1004。其中，通信总线1002用于实现这些组件之间的连接通信。网络接口1003可选的可以包括标准的有线接口、无线接口（如无线保真（Wireless-Fidelity，WI-FI）接口）。存储器1004可以是高速的随机存取存储器（Random Access Memory，RAM）存储器，也可以是稳定的非易失性存储器（Non-Volatile Memory，NVM），例如磁盘存储器。存储器1004可选的还可以是独立于前述处理器1001的存储装置。
在一实施例中，终端还可以包括摄像头、RF（Radio Frequency，射频）电路，传感器、音频电路、WiFi模块等等。其中，传感器比如光传感器、运动传感器以及其他传感器。具体地，光传感器可包括环境光传感器及接近传感器，其中，环境光传感器可根据环境光线的明暗来调节显示屏的亮度，接近传感器可在移动终端移动到耳边时，关闭显示屏和/或背光。作为运动传感器的一种，重力加速度传感器可检测各个方向上（一般为三轴）加速度的大小，静止时可检测出重力的大小及方向，可用于识别移动终端姿态的应用（比如横竖屏切换、相关游戏、磁力计姿态校准）、振动识别相关功能（比如计步器、敲击）等；当然，移动终端还可配置陀螺仪、气压计、湿度计、温度计、红外线传感器等其他传感器，在此不再赘述。
本领域技术人员可以理解，图2中示出的结构并不构成对运行设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
如图2所示，作为一种存储介质的存储器1004中可以包括操作***、数据存储模块、网络通信模块以及动态画面检测程序。
在图2所示的运行设备中，网络接口1003主要用于与其他设备进行数据通信。本申请运行设备中的处理器1001、存储器1004可以设置在运行设备中，所述运行设备通过处理器1001调用存储器1004中存储的动态画面检测程序，并执行以下操作：
获取所述显示器的显示画面对应的至少两张待检测图像；
根据预设的稠密光流算法，对所述待检测图像中的运动目标进行检测；
若在所述待检测图像中检测到运动目标，则判定所述显示画面为动态画面。
进一步地，处理器1001可以调用存储器1004中存储的动态画面检测程序，还执行以下操作：
根据预设的稠密光流算法，确定所述待检测图像中各个像素点对应的光流矢量；
若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则判定所述待检测图像中存在运动目标。
进一步地，处理器1001可以调用存储器1004中存储的动态画面检测程序，还执行以下操作：
若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则根据所述光流矢量的光流模长和光流方向，确定所述光流矢量对应的极坐标；
根据各所述光流矢量对应的极坐标，生成光流图像；
若在所述光流图像中检测到运动图像，则判定所述待检测图像中存在的运动目标。
进一步地，处理器1001可以调用存储器1004中存储的动态画面检测程序，还执行以下操作：
若在所述光流图像中检测到运动图像，则根据预设的轮廓发现算法确定所述光流图像中的运动图像的外接轮廓；
根据所述外接轮廓的位置，判断各所述运动图像是否位于所述显示画面的待检测区域；
若在所述显示画面的待检测区域中检测到至少一个所述运动图像，则判定所述待检测图像中存在的运动目标。
进一步地，处理器1001可以调用存储器1004中存储的动态画面检测程序，还执行以下操作：
若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则统计各所述目标光流矢量的总数；
若所述目标光流矢量的总数超过预设总数阈值，则判定所述待检测图像中存在运动目标；
若所述目标光流矢量的总数不超过预设总数阈值，则判定所述待检测图像中不存在运动目标。
进一步地，处理器1001可以调用存储器1004中存储的动态画面检测程序，还执行以下操作：
根据预设的稠密光流算法，确定所述待检测图像中各个像素点对应的初始矢量；
将各所述初始矢量中，模长大于预设第一模长的第一目标初始矢量的模长，调整为预设第一模长，并将各所述初始矢量中，模长小于预设第一模长的第二目标初始矢量的模长，进行中值滤波处理，调整为第二模长，得到中间矢量；
将各所述中间矢量的模长除以各自对应的最大模长，得到光流矢量。
进一步地，处理器1001可以调用存储器1004中存储的动态画面检测程序，还执行以下操作：
对所述显示器的显示画面进行至少两次截屏，得到至少两张截屏图像；
对各所述截屏图像进行规格调整和灰度转换，得到至少两张待检测图像。
本申请实施例提供一种动态画面检测方法，在本申请动态画面检测方法的第一实施例中，参照图3，所述动态画面检测方法应用于显示器，包括以下步骤：
步骤S10，获取所述显示器的显示画面对应的至少两张待检测图像；
在本实施例中，需要说明的是，所述动态画面检测方法应用于显示器，所述显示器可以包括但不限于OLED显示器、LCD、LED显示器等，所述显示器通过HDMI（High Definition Multimedia Interface、高清多媒体接口）、VGA（Video Graphics Array，视频图形阵列）接口或DP（DisplayPort，显示接口）等，与用户设备线性连接，进而接收并输出显示用户设备传输的视频信号，其中，所述用户设备包括笔记本电脑、计算机、平板电脑、手机等可移动式终端设备。
具体地，获取所述显示器的显示画面在至少两个不同的时刻对应的待检测图像，其中，所述显示画面可以为动态画面或静态画面，所述待检测图像为所述显示画面在某一时刻的静态图像，各所述待检测图像对应的时间范围之间的时间间隔可以根据实际情况进行确定，本实施例对此不加以限制，所述待检测图像可以为通过截屏或拍照等方式直接获取到的图像，也可以为在通过截屏或拍照等方式之后，再采用图像处理技术进行预处理得到的图像。
在一种可实施的方式中，所述获取所述显示器的显示画面对应的至少两张待检测图像的方式可以为，采用MT9950平台，通过Android（安卓）***的截屏接口，每1.5秒获取一次当前画面的图像数据，即可获取到bitmap（位图） RGBA_8888数据，选取四通道图像数据中的R（红色）、G（绿色）、B（蓝色）三通道数据作为数据源，移植openCV（一个开源的计算机视觉库）到MT9950平台的HAL（Hardware Abstraction Layer，硬件抽象层），将bitmap数据转换成openCV可用的BGR数据，再转换成mat对象进行操作，即打通了MTK9950的HAL与openCV之间的数据通路，以使得后续可以通过openCV进行运动目标的检测。
在一实施例中，所述获取所述显示器的显示画面对应的至少两张待检测图像的步骤包括：
步骤S11，对所述显示器的显示画面进行至少两次截屏，得到至少两张截屏图像；
在本实施例中，具体地，在至少两个不同的时刻，对所述显示器的显示画面进行截屏，得到至少两张截屏图像。
步骤S12，对各所述截屏图像进行规格调整和灰度转换，得到至少两张待检测图像。
在本实施例中，具体地，对各所述截屏图像的规格进行调整，将规格调整后的截屏图像转化成灰度图像，得到至少两张灰度化的待检测图像。
在一种可实施的方式中，所述规格调整的方式为减小所述截屏图像的分辨率。
在一种可实施的方式中，所述规格调整的方式为截取所述截屏图像中待检测区域对应的部分，其中，所述待检测区域可以根据实际需要进行确定，示例性地，可以根据信息提示弹窗在屏幕上出现时的位置进行确定，而此类信息提示弹窗通常出现在屏幕的四周边缘区域，故而，所述待检测区域可以为所述截屏图像中心的部分区域，也可以为所述截屏图像中从下往上第n行像素点以上的区域等。当用户设备无人操作时，也可能会出现消息提示的弹窗，此类消息提示通常与用户设备是否有人操作无关，若显示屏检测到静态画面进入屏幕保护画面之后，显示器因消息提示判定画面为动态画面，而退出屏幕保护画面，此时，由于屏幕保护画面的解除并非是由于用户操作，可能在一段时间之后又会重新进入屏幕保护画面，也即，因消息提示而提出屏幕保护画面的过程实质上是无效操作，且还会消耗设备的算力和电量，通过截取待检测区域的方式，将可能引起误操作的区域预先去除，不仅可以减小后续进行运动目标检测的计算量，还可以有效避免上述无效退出屏幕保护画面的情况。
在本实施例中，通过规格调整和灰度调整，可以有效减小后续运动目标检测的运算量，进而提高动态画面检测的检测效率。
步骤S20，根据预设的稠密光流算法，对所述待检测图像中的运动目标进行检测；
在本实施例中，具体地，根据预设的稠密光流算法，对两张待检测图像中的像素点一一进行比对，判断所述待检测图像中是否存在运动目标，其中，所述稠密光流算法是一种针对图像进行逐点匹配的图像配准方法，通过计算图像上所有的点的偏移量，从而形成一个稠密的光流场，所述判断所述待检测图像中是否存在运动目标的方式，可以根据两张待检测图像之间存在偏移量，判定两张待检测图像中存在运动目标，也可以根据实际情况设定偏移量阈值或偏移像素点数量阈值，当偏移量超过偏移量阈值时，或者当偏移像素点数量超过偏移像素点数量阈值时，判定两张待检测图像中存在运动目标，所述稠密光流算法的具体算法内容与现有技术相近，在此不过多赘述。
步骤S30，若在所述待检测图像中检测到运动目标，则判定所述显示画面为动态画面。
在本实施例中，具体地，若在所述待检测图像中检测到运动目标，则判定所述显示画面在各所述待检测图像对应的时间范围为动态画面；若在所述待检测图像中未检测到运动目标，则判定所述显示画面在各所述待检测图像对应的时间范围为静态画面。
在一种可实施的方式中，所述判定所述显示画面为静态画面的步骤之后，还包括以下步骤：开始计时，并返回执行步骤：获取所述显示器的显示画面对应的至少两张待检测图像；若在预设时间范围内，未检测到动态画面，则输出显示屏幕保护画面。
在本实施例中，通过获取所述显示器的显示画面对应的至少两张待检测图像，实现了对显示器上输出显示的显示画面的获取，进而通过根据预设的稠密光流算法，对所述待检测图像中的运动目标进行检测，实现了对显示画面中是否存在运动目标的检测，进而通过若在所述待检测图像中检测到运动目标，则判定所述显示画面为动态画面，实现了显示器端对输入的图像信息是否为动态画面的检测和准确判定，检测过程不依赖于信号的变化或检测，仅基于画面本身是否发生变化，避免了当显示画面作为视频信号输入时，由于无法检测到事件触发，而将动态画面误判为静态画面的情况，提高了动态画面检测的准确性，克服了解决现有技术动态画面的检测准确性较低的技术问题。
进一步地，在本申请动态画面检测方法的另一实施例中，参照图4，所述对各所述初始投屏图像帧中的消息通知区域进行识别的步骤包括：
步骤S21，根据预设的稠密光流算法，确定所述待检测图像中各个像素点对应的光流矢量；
在本实施例中，具体地，根据预设的稠密光流算法，对两张待检测图像中的像素点一一进行比对，得到运动目标的光流偏移量，即可确定每个像素点在x方向的光流分量和y方向的光流分量，基于x方向的光流分量和y方向的光流分量的大小和方向，即可确定所述待检测图像中各个像素点对应的光流矢量的模长和方向。
在一实施例中，所述根据预设的稠密光流算法，确定所述待检测图像中各个像素点对应的光流矢量的步骤包括：
步骤S211，根据预设的稠密光流算法，确定所述待检测图像中各个像素点对应的初始矢量；
在本实施例中，具体地，根据预设的稠密光流算法，对两张待检测图像中的像素点一一进行比对，得到运动目标的光流偏移量，即可确定每个像素点在x方向的光流分量和y方向的光流分量，基于x方向的光流分量和y方向的光流分量的大小和方向，即可确定所述待检测图像中各个像素点对应的初始矢量的模长和方向。
步骤S212，将各所述初始矢量中，模长大于预设第一模长的第一目标初始矢量的模长，调整为预设第一模长，并将各所述初始矢量中，模长小于预设第一模长的第二目标初始矢量的模长，进行中值滤波处理，调整为第二模长，得到中间矢量；
在本实施例中，具体地，将全部或一定范围内的部分初始矢量按照模长的大小进行排序，例如，将每一行初始矢量进行排序、将每一列初始矢量进行排序等，将模长大于预设第一模长的初始矢量作为第一目标初始矢量，将各所述第一目标初始矢量的模长调整为预设第一模长；将模长小于预设第一模长的初始矢量作为第二目标初始矢量，将各所述第二目标初始矢量的模长带入预设中值滤波算法，计算得到第二模长，将各所述第二目标初始矢量的模长调整为所述第二模长；将模长等于预设第一模长的初始矢量保持不变。对全部初始矢量进行模长调整之后，得到各所述初始矢量各自对应的中间矢量。其中，对各所述初始矢量进行排序的方式可以为冒泡排序等。
步骤S213，将各所述中间矢量的模长除以各自对应的最大模长，得到光流矢量。
在本实施例中，具体地，将各所述中间矢量的模长除以各自对应的最大模长，得到光流矢量，其中，各所述中间矢量各自对应的最大模长，为各所述中间矢量对应的初始矢量在按照模长排序时，共同进行排序的初始矢量中的最大模长，例如，若将全部初始矢量按照模长的大小进行排序，则各所述中间矢量各自对应的最大模长相同，均为全部初始矢量中的最大模长，若将每行初始矢量按照模长的大小进行排序，则每行初始矢量均可以确定一个最大模长，每行中间矢量各自对应的最大模长，为其所在的行确定的最大模长，位于不同行的中间矢量各自对应的最大模长可能相同或不同。
在本实施例中，通过中值滤波和除以最大模长的方式，对各所述光流矢量的模长进行平滑处理，进而减小检测噪声，提高所述动态画面检测方法的抗噪声能力。
步骤S22，若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则判定所述待检测图像中存在运动目标。
在本实施例中，具体地，判断各所述光流矢量的光流模长是否大于预设光流模长阈值，若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则判定所述待检测图像中存在运动目标；若在各所述光流矢量中，未检测到光流模长大于预设光流模长阈值的目标光流矢量，则判定所述待检测图像中不存在运动目标，其中，所述预设光流模长阈值可以根据大数据、实际测试结果等进行确定，例如所述预设光流模长阈值可以为0，也可以根据噪声或误差值确定一个极小值，本实施例对此不加以限制。
在一实施例中，所述若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则判定所述待检测图像中存在运动目标的步骤，还包括：
步骤S221，若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则统计各所述目标光流矢量的总数；
步骤S222，若所述目标光流矢量的总数超过预设总数阈值，则判定所述待检测图像中存在运动目标；
步骤S223，若所述目标光流矢量的总数不超过预设总数阈值，则判定所述待检测图像中不存在运动目标。
在本实施例中，具体地，若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则统计各所述目标光流矢量的总数，判断所述目标光流矢量的总数是否超过预设总数阈值，若所述目标光流矢量的总数超过预设总数阈值，则判定所述待检测图像中存在运动目标；若所述目标光流矢量的总数不超过预设总数阈值，则判定所述待检测图像中不存在运动目标。
在本实施例中，由于稠密光流算法的检测过程可能存在一定的噪声，通过设置光流模长阈值或总数阈值的方式，可以减小噪声干扰，提高检测的准确性。
在一实施例中，所述若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则判定所述待检测图像中存在运动目标的步骤包括：
步骤S221，若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则根据所述光流矢量的光流模长和光流方向，确定所述光流矢量对应的极坐标；
在本实施例中，具体地，判断各所述光流矢量的光流模长是否大于预设光流模长阈值，若在各所述光流矢量中，未检测到光流模长大于预设光流模长阈值的目标光流矢量，则判定所述待检测图像中不存在运动目标；若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则根据所述光流矢量的光流模长和光流方向，确定所述光流矢量对应的极坐标。
步骤S222，根据各所述光流矢量对应的极坐标，生成光流图像；
在本实施例中，具体地，根据各所述光流矢量对应的极坐标的极径和极角，将极角作为色调信息，极径作为饱和度信息，即可确定各所述光流矢量对应的HSV颜色空间的颜色，进而根据HSV颜色空间与RGB颜色空间的转换关系，得到RGB颜色空间表示的光流图像，在所述光流图像中，没有运动的部分极径几乎相同，呈现出的颜色也就几乎相同，可以作为所述光流图像的底色，而运动的部分，由于其运动速度的不同，呈现出不同的颜色，即可在底色上形成对应的运动图像。
在一种可实施的方式中，为了增加光流图像的区分度，可以将极径小于预设极径阈值的光流矢量，在光流图像中均以黑色表示。
步骤S223，若在所述光流图像中检测到运动图像，则判定所述待检测图像中存在的运动目标。
在本实施例中，具体地，采用图像识别技术，对所述光流图像中的运动图像进行识别，若在所述光流图像中检测到运动图像，则判定所述待检测图像中存在的运动目标，若在所述光流图像中未检测到运动图像，则判定所述待检测图像中不存在的运动目标，其中，所述运动图像是由与所述光流图像底色颜色不同的颜色组成的规则或不规则图形，所述对所述光流图像中的运动图像进行识别的方式，可以为检测所述光流图像中是否存在与底色不同的颜色，也可以识别所述光流图像中的轮廓等。
在一实施例中，所述若在所述光流图像中检测到运动图像，则判定所述待检测图像中存在的运动目标的步骤包括：
步骤S2231，若在所述光流图像中检测到运动图像，则根据预设的轮廓发现算法确定所述光流图像中的运动图像的外接轮廓；
步骤S2232，根据所述外接轮廓的位置，判断各所述运动图像是否位于所述显示画面的待检测区域；
步骤S2233，若在所述显示画面的待检测区域中检测到至少一个所述运动图像，则判定所述待检测图像中存在的运动目标。
在本实施例中，具体地，采用图像识别技术，对所述光流图像中的运动图像进行识别，若在所述光流图像中未检测到运动图像，则判定所述待检测图像中不存在的运动目标；若在所述光流图像中检测到运动图像，则根据预设的轮廓发现算法确定所述光流图像中的运动图像的外接轮廓，根据所述外接轮廓的位置所述显示画面的待检测区域之间的位置关系，判断各所述运动图像是否位于所述显示画面的待检测区域中，若在所述显示画面的待检测区域中检测到至少一个所述运动图像，则判定所述待检测图像中存在的运动目标，若在所述显示画面的待检测区域中未检测到所述运动图像，则判定所述待检测图像中不存在的运动目标。
在本实施例中，当用户设备无人操作时，也可能会出现消息提示的弹窗，此类消息提示通常与用户设备是否有人操作无关，若显示屏检测到静态画面进入屏幕保护画面之后，显示器因消息提示判定画面为动态画面，而退出屏幕保护画面，此时，由于屏幕保护画面的解除并非是由于用户操作，可能在一段时间之后又会重新进入屏幕保护画面，也即，因消息提示而提出屏幕保护画面的过程实质上是无效操作，且还会消耗设备的算力和电量，通过限定待检测区域的方式，可以有效避免上述无效退出屏幕保护画面的情况。
进一步地，本申请实施例还提供一种动态画面检测装置，参照图5，所述动态画面检测装置应用于动态画面检测设备，所述动态画面检测装置包括：
获取模块10，用于获取所述显示器的显示画面对应的至少两张待检测图像；
检测模块20，用于根据预设的稠密光流算法，对所述待检测图像中的运动目标进行检测；
判定模块30，用于若在所述待检测图像中检测到运动目标，则判定所述显示画面为动态画面。
在一实施例中，所述检测模块20，还用于：
根据预设的稠密光流算法，确定所述待检测图像中各个像素点对应的光流矢量；
若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则判定所述待检测图像中存在运动目标。
在一实施例中，所述检测模块20，还用于：
若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则根据所述光流矢量的光流模长和光流方向，确定所述光流矢量对应的极坐标；
根据各所述光流矢量对应的极坐标，生成光流图像；
若在所述光流图像中检测到运动图像，则判定所述待检测图像中存在的运动目标。
在一实施例中，所述检测模块20，还用于：
若在所述光流图像中检测到运动图像，则根据预设的轮廓发现算法确定所述光流图像中的运动图像的外接轮廓；
根据所述外接轮廓的位置，判断各所述运动图像是否位于所述显示画面的待检测区域；
若在所述显示画面的待检测区域中检测到至少一个所述运动图像，则判定所述待检测图像中存在的运动目标。
在一实施例中，所述检测模块20，还用于：
若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则统计各所述目标光流矢量的总数；
若所述目标光流矢量的总数超过预设总数阈值，则判定所述待检测图像中存在运动目标；
若所述目标光流矢量的总数不超过预设总数阈值，则判定所述待检测图像中不存在运动目标。
在一实施例中，所述检测模块20，还用于：
根据预设的稠密光流算法，确定所述待检测图像中各个像素点对应的初始矢量；
将各所述初始矢量中，模长大于预设第一模长的第一目标初始矢量的模长，调整为预设第一模长，并将各所述初始矢量中，模长小于预设第一模长的第二目标初始矢量的模长，进行中值滤波处理，调整为第二模长，得到中间矢量；
将各所述中间矢量的模长除以各自对应的最大模长，得到光流矢量。
在一实施例中，所述获取模块10，还用于：
对所述显示器的显示画面进行至少两次截屏，得到至少两张截屏图像；
对各所述截屏图像进行规格调整和灰度转换，得到至少两张待检测图像。
本申请提供的动态画面检测装置，采用上述实施例中的动态画面检测方法，解决了解决现有技术动态画面的检测准确性较低的技术问题。与现有技术相比，本申请实施例提供的动态画面检测装置的有益效果与上述实施例提供的动态画面检测方法的有益效果相同，且该动态画面检测装置中的其他技术特征与上述实施例方法公开的特征相同，在此不做赘述。
进一步地，本申请还提供一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现如上述的动态画面检测方法的步骤。
本申请提供的计算机程序产品解决了解决现有技术动态画面的检测准确性较低的技术问题。与现有技术相比，本申请实施例提供的计算机程序产品的有益效果与上述实施例提供的动态画面检测方法的有益效果相同，在此不做赘述。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利处理范围内。

Claims (15)

  1. 一种动态画面检测方法，其中，所述动态画面检测方法应用于显示器，包括以下步骤：
    获取所述显示器的显示画面对应的至少两张待检测图像；
    根据预设的稠密光流算法，对所述待检测图像中的运动目标进行检测；
    若在所述待检测图像中检测到运动目标，则判定所述显示画面为动态画面。
  2. 如权利要求1所述动态画面检测方法，其中，所述根据预设的稠密光流算法，对所述待检测图像中的运动目标进行检测的步骤包括：
    根据预设的稠密光流算法，确定所述待检测图像中各个像素点对应的光流矢量；
    若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则判定所述待检测图像中存在运动目标。
  3. 如权利要求2所述动态画面检测方法，其中，所述若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则判定所述待检测图像中存在运动目标的步骤包括：
    若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则根据所述光流矢量的光流模长和光流方向，确定所述光流矢量对应的极坐标；
    根据各所述光流矢量对应的极坐标，生成光流图像；
    若在所述光流图像中检测到运动图像，则判定所述待检测图像中存在的运动目标。
  4. 如权利要求3所述动态画面检测方法，其中，所述若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则判定所述待检测图像中存在运动目标的步骤包括：
    若在各所述光流矢量中，未检测到光流模长大于预设光流模长阈值的目标光流矢量，则判定所述待检测图像中不存在运动目标。
  5. 如权利要求3所述动态画面检测方法，其中，所述根据各所述光流矢量对应的极坐标，生成光流图像的步骤包括：
    根据各所述光流矢量对应的极坐标的极径和极角，将极角作为色调信息，极径作为饱和度信息，即可确定各所述光流矢量对应的HSV颜色空间的颜色，进而根据HSV颜色空间与RGB颜色空间的转换关系，得到RGB颜色空间表示的光流图像。
  6. 如权利要求3所述动态画面检测方法，其中，所述若在所述光流图像中检测到运动图像，则判定所述待检测图像中存在的运动目标的步骤包括：
    若在所述光流图像中检测到运动图像，则根据预设的轮廓发现算法确定所述光流图像中的运动图像的外接轮廓；
    根据所述外接轮廓的位置，判断各所述运动图像是否位于所述显示画面的待检测区域；
    若在所述显示画面的待检测区域中检测到至少一个所述运动图像，则判定所述待检测图像中存在的运动目标。
  7. 如权利要求3所述动态画面检测方法，其中，所述若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则根据所述光流矢量的光流模长和光流方向，确定所述光流矢量对应的极坐标的步骤包括：
    若在各所述光流矢量中，检测到光流模长大于预设光流模长阈值的目标光流矢量，则统计各所述目标光流矢量的总数；
    若所述目标光流矢量的总数超过预设总数阈值，则判定所述待检测图像中存在运动目标；
    若所述目标光流矢量的总数不超过预设总数阈值，则判定所述待检测图像中不存在运动目标。
  8. 如权利要求2所述动态画面检测方法，其中，所述根据预设的稠密光流算法，确定所述待检测图像中各个像素点对应的光流矢量的步骤包括：
    根据预设的稠密光流算法，确定所述待检测图像中各个像素点对应的初始矢量；
    将各所述初始矢量中，模长大于预设第一模长的第一目标初始矢量的模长，调整为预设第一模长，并将各所述初始矢量中，模长小于预设第一模长的第二目标初始矢量的模长，进行中值滤波处理，调整为第二模长，得到中间矢量；
    将各所述中间矢量的模长除以各自对应的最大模长，得到光流矢量。
  9. 如权利要求8所述动态画面检测方法，其中，将各所述初始矢量中，模长大于预设第一模长的第一目标初始矢量的模长，调整为预设第一模长，并将各所述初始矢量中，模长小于预设第一模长的第二目标初始矢量的模长，进行中值滤波处理，调整为第二模长，得到中间矢量的步骤，之前还包括：将全部或一定范围内的部分初始矢量按照模长的大小进行排序。
  10. 如权利要求1所述动态画面检测方法，其中，所述获取所述显示器的显示画面对应的至少两张待检测图像的步骤包括：
    对所述显示器的显示画面进行至少两次截屏，得到至少两张截屏图像；
    对各所述截屏图像进行规格调整和灰度转换，得到至少两张待检测图像。
  11. 如权利要求1所述动态画面检测方法，其中，所述动态画面检测方法还包括：
    若在所述待检测图像中未检测到运动目标，则判定所述显示画面在各所述待检测图像对应的时间范围为静态画面。
  12. 如权利要求11所述动态画面检测方法，其中，所述若在所述待检测图像中未检测到运动目标，则判定所述显示画面在各所述待检测图像对应的时间范围为静态画面的步骤之后，还包括：
    开始计时，并返回执行步骤：
    获取所述显示器的显示画面对应的至少两张待检测图像；
    若在预设时间范围内，未检测到动态画面，则输出显示屏幕保护画面。
  13. 一种动态画面检测装置，其中，所述动态画面检测装置应用于显示器，包括：
    获取模块，用于获取所述显示器的显示画面对应的至少两张待检测图像；
    检测模块，用于根据预设的稠密光流算法，对所述待检测图像中的运动目标进行检测；
    判定模块，用于若在所述待检测图像中检测到运动目标，则判定所述显示画面为动态画面。
  14. 一种显示器，其中，所述显示器包括：
    至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1至12中任一项所述的动态画面检测方法的步骤。
  15. 一种存储介质，其中，所述存储介质为计算机可读存储介质，所述计算机可读存储介质上存储有实现动态画面检测方法的程序，所述实现动态画面检测方法的程序被处理器执行以实现如权利要求1至12中任一项所述动态画面检测方法的步骤。
PCT/CN2022/142037 2022-09-21 2022-12-26 动态画面检测方法、装置、显示器及存储介质 WO2024060447A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211153920.8 2022-09-21
CN202211153920.8A CN115423794A (zh) 2022-09-21 2022-09-21 动态画面检测方法、装置、显示器及存储介质

Publications (1)

Publication Number Publication Date
WO2024060447A1 true WO2024060447A1 (zh) 2024-03-28

Family

ID=84204429

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/142037 WO2024060447A1 (zh) 2022-09-21 2022-12-26 动态画面检测方法、装置、显示器及存储介质

Country Status (2)

Country Link
CN (1) CN115423794A (zh)
WO (1) WO2024060447A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115423794A (zh) * 2022-09-21 2022-12-02 深圳创维－Rgb电子有限公司 动态画面检测方法、装置、显示器及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150125091A1 (en) * 2013-11-01 2015-05-07 Nvidia Corporation System, method, and computer program product for performing fast, non-rigid registration for high dynamic range image stacks
CN114399539A (zh) * 2022-01-14 2022-04-26 合肥英睿***技术有限公司 运动目标的检测方法、设备以及存储介质
CN115423794A (zh) * 2022-09-21 2022-12-02 深圳创维－Rgb电子有限公司 动态画面检测方法、装置、显示器及存储介质

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150125091A1 (en) * 2013-11-01 2015-05-07 Nvidia Corporation System, method, and computer program product for performing fast, non-rigid registration for high dynamic range image stacks
CN114399539A (zh) * 2022-01-14 2022-04-26 合肥英睿***技术有限公司 运动目标的检测方法、设备以及存储介质
CN115423794A (zh) * 2022-09-21 2022-12-02 深圳创维－Rgb电子有限公司 动态画面检测方法、装置、显示器及存储介质

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
KURNIANGGORO LAKSONO; SHAHBAZ AJMAL; JO KANG-HYUN: "Dense optical flow in stabilized scenes for moving object detection from a moving camera", 2016 16TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS (ICCAS), INSTITUTE OF CONTROL, ROBOTICS AND SYSTEMS - ICROS, 16 October 2016 (2016-10-16), pages 704 - 708, XP033051643, DOI: 10.1109/ICCAS.2016.7832395 *
SHEN SHIHAO, CAI YILIN, QIU JIAYI, LI GUANGZHAO: "Dynamic Dense RGB-D SLAM using Learning-based Visual Odometry", ARXIV (CORNELL UNIVERSITY), 12 May 2022 (2022-05-12), Ithaca, XP093150444, Retrieved from the Internet <URL:https://arxiv.org/pdf/2205.05916v1.pdf> DOI: 10.48550/arxiv.2205.05916 *
ZHANG TIANWEI, ZHANG HUAYAN, YANG LI, NAKAMURA YOSHIHIKO, ZHANG LEI: "FlowFusion: Dynamic Dense RGB-D SLAM Based on Optical Flow", ARXIV (CORNELL UNIVERSITY), 11 March 2020 (2020-03-11), Ithaca, XP093150446, Retrieved from the Internet <URL:https://arxiv.org/pdf/2003.05102.pdf> DOI: 10.48550/arxiv.2003.05102 *

Also Published As

Publication number Publication date
CN115423794A (zh) 2022-12-02

Similar Documents

Publication Publication Date Title
CN111486950B (zh) 环境光检测方法、装置、电子设备及存储介质
US20160350940A1 (en) Automatic Recognition And Calibration Method Of Medical Color And Grayscale Images
CN107293265B (zh) 显示屏画面调整方法、显示终端及可读存储介质
WO2024060448A1 (zh) 静帧检测方法、电子设备及存储介质
US20220268567A1 (en) Screen display control method and electronic device
US10237454B2 (en) Method for detecting terminal static layer information, terminal and television
WO2020056744A1 (zh) 拖影评价、改善方法和电子设备
CN112017577B (zh) 屏幕显示校准方法及装置
US20130271667A1 (en) Video processing apparatus and video processing method
WO2023045884A1 (zh) 屏幕光检测模型训练方法、环境光检测方法及装置
US11495183B2 (en) Method and device for controlling backlight brightness, and display device
US9640142B2 (en) Apparatus for detecting region of interest and method thereof
WO2024060447A1 (zh) 动态画面检测方法、装置、显示器及存储介质
CN113990263B (zh) 显示屏的背光处理方法、装置、存储介质及电子设备
US20140247275A1 (en) Information processing method and electronic device
CN114119431A (zh) 图像处理方法、装置、电子设备及存储介质
US11302294B2 (en) Display device, and control method, control apparatus and control system therefor
US20100220244A1 (en) Eletronic device, display device, and method of controlling audio/video output of an electronic device
CN111145151A (zh) 一种运动区域确定方法及电子设备
US20210280150A1 (en) Display apparatus, display method, image processing device and computer program product for image processing
CN114489549B (zh) 投屏图像处理方法、装置、电子设备及存储介质
US9232201B2 (en) Dynamic projected image color correction based on projected surface coloration
CN114647468A (zh) 投屏图像显示方法、装置、电子设备及存储介质
WO2023142370A1 (zh) 投屏显示方法、装置、电子设备及可读存储介质
TW201917455A (zh) 背光模組之功耗管理裝置與功耗管理方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22959445

Country of ref document: EP

Kind code of ref document: A1