Intelligent screen projection control system based on image processing technology

Abstract

The invention relates to the technical field of screen projection control, and discloses an intelligent screen projection control system based on an image processing technology, which comprises an image acquisition module, an image preprocessing module, an image feature extraction module, an image projection module, a parameter detection module, an intelligent control module and a man-machine interaction module, through the arrangement of the parameter detection module and the intelligent control module, corresponding intelligent control is performed by detecting whether the quality of the image is reduced in the playing process and sending a corresponding instruction signal to the intelligent control module based on the detection result, and after the quality is reduced, picture control parameters are adjusted; according to the technical scheme, the image quality is guaranteed, luminosity compensation is carried out at the same time, and therefore when the image is projected in the screen projection process, the image quality can be improved, image quality reduction caused by image distortion is prevented, the projected image is restored, meanwhile, the definition and chromaticity of the image are improved, and the stability of the image quality in the playing process is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of screen projection control technology, and more specifically to an intelligent screen projection control system based on image processing technology. Background Art

[0002] With the development of science and technology, projection equipment has been widely used in education, business, entertainment and other fields; multimedia content on the screen of the device to be projected is projected onto large screens such as TVs and projectors to share information with others; after the existing smart projection system projects the content of the projection device, it can intelligently adjust the parameters of the projected screen to ensure the clarity and color of the projected screen; it enhances the viewing experience and improves the user experience.

[0003] However, when existing smart projection screens project images, image distortion is prone to occur during the projection restoration and playback process, which reduces the user's viewing experience. Therefore, there is a need for a smart projection screen control system based on image processing technology to highly restore the projected image and improve the clarity and stability of the projected image. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides an intelligent screen projection control system based on image processing technology to solve the problems existing in the above-mentioned background technology.

[0005] The present invention provides the following technical solutions: an intelligent screen projection control system based on image processing technology, comprising an image acquisition module, an image preprocessing module, an image feature extraction module, an image projection module, a parameter detection module, an intelligent control module and a human-computer interaction module; The image acquisition module is used to acquire the screen image on the projection device in real time and transmit it to the image preprocessing module; The image preprocessing module is used to preprocess the screen image collected by the image acquisition module to obtain image data that can be directly used; The image feature extraction module is used to extract features from the screen image based on the data preprocessed by the image preprocessing module; The image projection module is used to receive data from the image feature extraction module and project the received image information to form a projection screen; The parameter detection module is used to evaluate the image quality of the image after being projected by the image projection module, and detect whether the image quality is reduced, and send a corresponding command signal to the intelligent control module according to the detection result; The intelligent control module is used to receive the command signal of the parameter detection module and perform corresponding intelligent control; The human-computer interaction module is used to perform human-computer interaction display on the data.

[0006] Preferably, the image feature extraction module uses SIFT feature extraction algorithm to extract features from the screen image; the formula is expressed as: ; Where x and y are pixel points on the image, L(x, y, σ) is the result of convolution of the image and the Gaussian kernel function, i.e., the Gaussian scale space of the image; I is the screen image to be projected, G(x, y, σ) is the Gaussian kernel function; σ is the scale space factor; the Gaussian kernel function is expressed as: .

[0007] Preferably, the specific manner in which the parameter detection module performs image quality assessment is: Step S01: record the projection screen image as I´, divide the projection screen into P frames, and record the i-th projection screen image as I´ i , the image to be projected is recorded as I, the projected image is divided into the same P frames, and the i-th frame of the image to be projected is recorded as I i , respectively calculate the first quality index and the second quality index of each frame of the projection screen; i=1, 2, 3, ..., P; Step S02: Calculate the first quality index of the i-th projection screen image: , where ZLA i is the first quality index of the i-th frame projection screen image, M and N are the number of pixel rows and columns of the projection image respectively, m and n are the image pixels, m=1, 2, 3, ..., M; n=1, 2, 3, ..., N; Step S03: Calculate the second quality index of the i-th frame projection screen image: , where ZLB i is the second quality index of the i-th frame projection screen image, M and N are the number of pixel rows and columns of the projection image respectively, m and n are the image pixels, m=1, 2, 3, ..., M; n=1, 2, 3, ..., N; Step S04: Combining the data of step S02 and step S03, image quality assessment is performed, and the calculation formula is expressed as: , among which ZL i is the comprehensive quality evaluation index of the i-th frame projection screen image, λ1 and λ2 are the weight factors of the first quality index and the second quality index respectively, satisfying 0<λ1<1, 0<λ2<1.

[0008] Preferably, the specific process of the parameter detection module detecting whether the image quality is degraded is: Get the comprehensive quality index ZL of the i-th frame projection image i, record the picture control parameters at this time, the picture control parameters include but are not limited to contrast, brightness, resolution, etc.; if there is a comprehensive quality evaluation index ZL of the i+1th frame image i+1 , so that ZL i+1 >ZL i , the detection result is that it has not decreased, and a first command signal is sent to the intelligent control module; if there is a comprehensive quality evaluation index ZL of the i+1th frame image i+1 <ZL i , the detection result is decreasing, and a second command signal is sent to the intelligent control module; Wherein, i=1, 2, 3, …, P, and P is the total number of frames of the projection screen.

[0009] Preferably, after receiving the first command signal, the intelligent control module records the picture control parameters corresponding to the i+1th frame image, replacing the last recorded picture control parameters. If the picture control parameters corresponding to the i-th frame image are respectively contrast a1, brightness a2 and resolution a3, then ZL i >UI, record the contrast a1, brightness a2 and resolution a3 at this time, the image control parameters corresponding to the image of the i+1th frame are contrast b1, brightness b2 and resolution b3, ZL i+1 >ZL i When the contrast b1, brightness b2 and resolution b3 at that time are recorded, the contrast a1, brightness a2 and resolution a3 are replaced.

[0010] Preferably, after receiving the second instruction signal, the intelligent control module performs photometric compensation on the image and adjusts the picture control parameters to be consistent with the recorded picture control parameters; , where Y´ i is the compensation image of the i-th frame projection screen image, B θ is the photometric compensation expression, θ is the learnable network parameter, T is the spectral reflectance feature, , where L is the loss function.

[0011] Preferably, the Gaussian scale space is constructed to detect feature points that exist at different scales, and Gaussian Laplace operator is approximately calculated by Gaussian difference when detecting feature points; the calculation formula of Gaussian difference is expressed as: ; where k is the scale factor of the scale difference between two adjacent layers. Assuming that each group has S layers, then ; and the bottom-level image of the previous set of images is obtained by downsampling the images with a scale of 2σ in the next set.

[0012] Technical effects and advantages of the present invention: The present invention is provided with a parameter detection module and an intelligent control module, which is conducive to evaluating the image quality of the image after being projected by the image projection module, and obtaining a comprehensive quality evaluation index based on the calculation of the first quality index and the second quality index, so as to detect whether the image quality is degraded during the playback process, and send a corresponding command signal to the intelligent control module based on the detection result. The intelligent control module performs corresponding intelligent control based on the corresponding command signal. After the quality is degraded, the picture control parameters are adjusted to ensure the quality of the picture image, and light compensation is performed at the same time, so that when the image is projected during the projection process, the image quality can be improved, the image quality degradation caused by image distortion can be prevented, and the clarity and color of the image can be improved while restoring the projected image, so as to ensure the stability of the image quality during the playback process. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a structural diagram of the intelligent screen projection control system based on image processing technology of the present invention. DETAILED DESCRIPTION

[0014] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely illustrative. The smart projection control system based on image processing technology involved in the present invention is not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0015] like Figure 1 As shown, the present invention provides an intelligent screen projection control system based on image processing technology, including an image acquisition module, an image preprocessing module, an image feature extraction module, an image projection module, a parameter detection module, an intelligent control module and a human-computer interaction module; The image acquisition module is used to acquire the screen image on the projection device in real time and transmit it to the image preprocessing module; The image preprocessing module is used to preprocess the screen image collected by the image acquisition module to obtain image data that can be directly used; the preprocessing includes but is not limited to operations such as cleaning and noise reduction; The image feature extraction module is used to extract features of the screen image from the data preprocessed by the image preprocessing module, including but not limited to features such as texture, color and shape of the image; The image projection module is used to receive data from the image feature extraction module and project the received image information to form a projection screen; The parameter detection module is used to evaluate the image quality of the image after being projected by the image projection module, and detect whether the image quality is reduced, and send a corresponding command signal to the intelligent control module according to the detection result; The intelligent control module is used to receive the command signal of the parameter detection module and perform corresponding intelligent control; The human-computer interaction module is used to perform human-computer interaction display on the data.

[0016] In this embodiment, it should be specifically explained that the image feature extraction module uses SIFT feature extraction algorithm to extract features from the screen image; The SIFT feature extraction algorithm constructs the scale space mainly in the form of an image pyramid, that is, the original image is first convolved with a Gaussian function, and then the processed image is downsampled. After downsampling, a series of images with decreasing sizes are obtained. Images of different sizes form groups in the pyramid. For each image of different sizes, convolution is performed with a Gaussian kernel function of different sizes to form different layers in each group. The Gaussian scale space of a frame of the image on the screen image to be projected can be obtained by convolving the image with different Gaussian kernel functions; the SIFT feature extraction algorithm performs key detection at different scales, which is conducive to extracting feature points with different scale detail features in the image and improving the accuracy of subsequent image restoration; The formula is: ; Where x and y are pixel points on the image, L(x, y, σ) is the result of convolution of the image and the Gaussian kernel function, i.e., the Gaussian scale space of the image; I is the screen image to be projected, G(x, y, σ) is the Gaussian kernel function; σ is the scale space factor; the Gaussian kernel function is expressed as: ; The purpose of constructing the Gaussian scale space is to detect feature points that exist at different scales. When detecting feature points, the Gaussian difference method is used to approximate the Gaussian Laplace operator. The calculation formula of the Gaussian difference is expressed as: The response image of Gaussian difference is obtained by subtracting the images of two adjacent Gaussian spaces, where k is the proportional factor of the scale difference between two adjacent layers. Assuming that each group has S layers, then ; and the bottom image of the previous group of images is obtained by downsampling the images with a scale of 2σ in the next group; after the Gaussian pyramid is constructed, the Gaussian difference pyramid is obtained by subtracting adjacent Gaussian pyramids; After constructing the Gaussian difference pyramid, the extreme points in the scale space are found. Each pixel in the image is compared with its adjacent points in the image and the adjacent points in the adjacent scale space. If there is a point with the largest value among all 26 adjacent points, then this point is the maximum point. After obtaining the discrete extreme points in the image, in order to improve the stability of the feature points, the sub-pixel interpolation method is used to obtain the extreme points in the continuous space, that is, the obtained feature points.

[0017] In this embodiment, it should be specifically explained that the specific manner in which the parameter detection module performs image quality assessment is: Step S01: record the projection screen image as I´, divide the projection screen into P frames, and record the i-th projection screen image as I´ i , the image to be projected is recorded as I, the projected image is divided into the same P frames, and the i-th frame of the image to be projected is recorded as I i , respectively calculate the first quality index and the second quality index of each frame of the projection screen; i=1, 2, 3, ..., P; Step S02: Calculate the first quality index of the i-th projection screen image: , where ZLA i is the first quality index of the i-th frame projection screen image, M and N are the number of pixel rows and columns of the projection image respectively, m and n are the image pixels, m=1, 2, 3, ..., M; n=1, 2, 3, ..., N; Step S03: Calculate the second quality index of the i-th frame projection screen image: , where ZLB i is the second quality index of the i-th frame projection screen image, M and N are the number of pixel rows and columns of the projection image respectively, m and n are the image pixels, m=1, 2, 3, ..., M; n=1, 2, 3, ..., N; Step S04: Combining the data of step S02 and step S03, image quality assessment is performed, and the calculation formula is expressed as: , among which ZL i is the comprehensive quality evaluation index of the i-th frame projection screen image, λ1 and λ2 are the weight factors of the first quality index and the second quality index respectively, satisfying 0<λ1<1, 0<λ2<1; Comprehensive quality evaluation index ZL i The larger the value is, the better the quality of the i-th frame projection image is, the clearer the image is, and the higher the color restoration is.

[0018] In this embodiment, it should be specifically explained that the specific process of the parameter detection module detecting whether the image quality is degraded is as follows: Get the comprehensive quality index ZL of the i-th frame projection image i, record the picture control parameters at this time, the picture control parameters include but are not limited to contrast, brightness, resolution, etc.; if there is a comprehensive quality evaluation index ZL of the i+1th frame image i+1 , so that ZL i+1 >ZL i , the detection result is that it has not decreased, and a first command signal is sent to the intelligent control module; if there is a comprehensive quality evaluation index ZL of the i+1th frame image i+1 <ZL i , the detection result is decreasing, and a second command signal is sent to the intelligent control module.

[0019] In this embodiment, it should be specifically explained that after receiving the first command signal, the intelligent control module records the picture control parameters corresponding to the i+1th frame image, replacing the last recorded picture control parameters. For example, if the picture control parameters corresponding to the i-th frame image are respectively contrast a1, brightness a2 and resolution a3, then ZL i >UI, record the contrast a1, brightness a2 and resolution a3 at this time, the image control parameters corresponding to the image of the i+1th frame are contrast b1, brightness b2 and resolution b3, ZL i+1 >ZL i When the contrast a1, brightness a2 and resolution a3 are replaced by the contrast b1, brightness b2 and resolution b3 at this time, only the picture control parameters of the image corresponding to the maximum value of the comprehensive quality evaluation index are recorded; After receiving the second command signal, the intelligent control module performs photometric compensation on the image and adjusts the picture control parameters to be consistent with the recorded picture control parameters; thereby ensuring that the quality of the projected image is always at the best value; the projection process will be affected by many factors such as the color texture and material of the projection surface, ambient light, etc., which may cause the image quality to be inconsistent, and may cause problems such as color distortion, so the image is photometrically compensated to maintain the image quality; , where Y´ i is the compensation image of the i-th frame projection screen image, B θ is the photometric compensation expression, θ is the learnable network parameter, T is the spectral reflectance feature, , where L is the loss function, which can make the compensated projection screen image as close as possible to the image to be projected, thereby improving the image quality of the projection screen.

[0020] In this embodiment, it should be specifically explained that a method for implementing an intelligent screen projection control system based on image processing technology includes the following steps: Step A1: collect the screen image on the projection device in real time and perform preprocessing operations, including but not limited to cleaning and denoising the image. Step A2: Extract features from the preprocessed image data. The formula is: ; Where x and y are pixel points on the image, L(x, y, σ) is the result of convolution of the image and the Gaussian kernel function, i.e., the Gaussian scale space of the image; I is the screen image to be projected, G(x, y, σ) is the Gaussian kernel function; σ is the scale space factor; the Gaussian kernel function is expressed as: ; Step A3: based on the extracted image data features, restore the image to be projected and project it onto the screen surface to form a projection screen; Step A4: Divide the projection screen into P frames, evaluate the image quality of each frame, and detect whether the image quality of the projection screen is consistent during playback and whether the image quality is degraded; The projection screen image is recorded as I´, the projection screen is divided into P frames, and the i-th frame projection screen image is recorded as I´ i , the image to be projected is recorded as I, the projected image is divided into the same P frames, and the i-th frame of the image to be projected is recorded as I i , respectively calculate the first quality index and the second quality index of each frame of the projection screen; i=1, 2, 3, ..., P; The calculation formula of the first quality index is expressed as: , where ZLA i is the first quality index of the i-th frame projection screen image, M and N are the number of pixel rows and columns of the projection image respectively, m and n are the image pixels, m=1, 2, 3, ..., M; n=1, 2, 3, ..., N; The calculation formula of the second quality index is expressed as: , where ZLB i is the second quality index of the i-th frame projection screen image, M and N are the number of pixel rows and columns of the projection image respectively, m and n are the image pixels, m=1, 2, 3, ..., M; n=1, 2, 3, ..., N; Image quality is evaluated based on the first quality index and the second quality index, and the calculation formula is expressed as: , among which ZL i is the comprehensive quality evaluation index of the i-th frame projection screen image, λ1 and λ2 are the weight factors of the first quality index and the second quality index respectively, satisfying 0<λ1<1, 0<λ2<1; Step A5: Based on the detection result of the image quality in step A4, a corresponding instruction signal is sent, and corresponding intelligent control is performed based on the instruction signal; Get the comprehensive quality index ZL of the i-th frame projection image i , record the picture control parameters at this time, the picture control parameters include but are not limited to contrast, brightness, resolution, etc.; if there is a comprehensive quality evaluation index ZL of the i+1th frame image i+1 , so that ZL i+1 >ZL i , the detection result is that it has not decreased, and a first command signal is sent to the intelligent control module; if there is a comprehensive quality evaluation index ZL of the i+1th frame image i+1 <ZL i , the detection result is decreasing, and a second command signal is sent to the intelligent control module; After receiving the first command signal, the image control parameters corresponding to the i+1th frame image are recorded to replace the last recorded image control parameters. For example, if the image control parameters corresponding to the i-th frame image are respectively contrast a1, brightness a2 and resolution a3, then ZL i >UI, record the contrast a1, brightness a2 and resolution a3 at this time, the image control parameters corresponding to the image of the i+1th frame are contrast b1, brightness b2 and resolution b3, ZL i+1 >ZL i When the contrast a1, brightness a2 and resolution a3 are replaced by the contrast b1, brightness b2 and resolution b3 at this time, only the picture control parameters of the image corresponding to the maximum value of the comprehensive quality evaluation index are recorded; After receiving the second command signal, the image is photometrically compensated, and the picture control parameters are adjusted to be consistent with the recorded picture control parameters, thereby ensuring that the quality of the projected image is always at an optimal value.

[0021] In the present embodiment, it should be specifically explained that the difference between the present embodiment and the prior art lies mainly in that the present embodiment is provided with a parameter detection module and an intelligent control module, which is conducive to evaluating the image quality of the image after being projected by the image projection module, and obtaining a comprehensive quality evaluation index based on the calculation of the first quality index and the second quality index, so as to detect whether the image quality has declined during the playback process, and send a corresponding command signal to the intelligent control module based on the detection result. The intelligent control module performs corresponding intelligent control based on the corresponding command signal. When the quality has declined, the picture control parameters are adjusted to ensure the quality of the picture image, and luminosity compensation is performed at the same time, so that when the image is projected during the projection process, the image quality can be improved, and the image quality decline caused by image distortion can be prevented. While restoring the projected image, the clarity and color of the image are improved, and the stability of the image quality during the playback process is guaranteed.

[0022] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0023] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent screen projection control system based on image processing technology, characterized in that: It includes image acquisition module, image preprocessing module, image feature extraction module, image projection module, parameter detection module, intelligent control module and human-computer interaction module; The image acquisition module is used to acquire the screen image on the projection device in real time and transmit it to the image preprocessing module; The image preprocessing module is used to preprocess the screen image collected by the image acquisition module to obtain image data that can be directly used; The image feature extraction module is used to extract features from the screen image based on the data preprocessed by the image preprocessing module; The image projection module is used to receive data from the image feature extraction module and project the received image information to form a projection screen; The parameter detection module is used to evaluate the image quality of the image after being projected by the image projection module, and detect whether the image quality is reduced, and send a corresponding command signal to the intelligent control module according to the detection result; The intelligent control module is used to receive the command signal of the parameter detection module and perform corresponding intelligent control; The human-computer interaction module is used to perform human-computer interaction display on the data.

2. According to claim 1, the intelligent screen projection control system based on image processing technology is characterized in that: The image feature extraction module uses SIFT feature extraction algorithm to extract features from the screen image; the formula is expressed as: ; Where x and y are pixel points on the image, L(x, y, σ) is the result of convolution of the image and the Gaussian kernel function, i.e., the Gaussian scale space of the image; I is the screen image to be projected, G(x, y, σ) is the Gaussian kernel function; σ is the scale space factor; the Gaussian kernel function is expressed as: .

3. According to claim 1, the intelligent screen projection control system based on image processing technology is characterized in that: The specific method of the parameter detection module for image quality assessment is as follows: Step S01: record the projection screen image as I´, divide the projection screen into P frames, and record the i-th projection screen image as I´ i , the image to be projected is recorded as I, the projected image is divided into the same P frames, and the i-th frame of the image to be projected is recorded as I i , respectively calculate the first quality index and the second quality index of each frame of the projection screen; i=1, 2, 3, ..., P; Step S02: Calculate the first quality index of the i-th projection screen image: , where ZLA i is the first quality index of the i-th frame projection screen image, M and N are the number of rows and columns of pixels of the projection image, respectively, m and n are the image pixels, m=1, 2, 3, ..., M; n=1, 2, 3, ..., N; Step S03: Calculate the second quality index of the i-th frame projection screen image: , where ZLB i is the second quality index of the i-th frame projection screen image, M and N are the number of pixel rows and columns of the projection image respectively, m and n are the image pixels, m=1, 2, 3, ..., M; n=1, 2, 3, ..., N; Step S04: Combining the data of step S02 and step S03, image quality assessment is performed, and the calculation formula is expressed as: , among which ZL i is the comprehensive quality evaluation index of the i-th frame projection screen image, λ1 and λ2 are the weight factors of the first quality index and the second quality index respectively, satisfying 0<λ1<1, 0<λ2<1.

4. According to claim 1, the intelligent screen projection control system based on image processing technology is characterized in that: The specific process of the parameter detection module detecting whether the image quality is reduced is as follows: Get the comprehensive quality index ZL of the i-th frame projection image i , record the picture control parameters at this time, the picture control parameters include contrast, brightness, and resolution; if there is a comprehensive quality evaluation index ZL of the i+1th frame image i+1 , so that ZL i+1 >ZL i , then the detection result is that it has not dropped, and a first command signal is sent to the intelligent control module; If there is a comprehensive quality evaluation index ZL of the i+1th frame image i+1 <ZL i , the detection result is decreasing, and a second command signal is sent to the intelligent control module; Wherein, i=1, 2, 3, …, P, and P is the total number of frames of the projection screen.

5. According to claim 1, the intelligent screen projection control system based on image processing technology is characterized in that: After receiving the first command signal, the intelligent control module records the picture control parameters corresponding to the i+1th frame image, replacing the last recorded picture control parameters. If the picture control parameters corresponding to the i-th frame image are respectively contrast a1, brightness a2 and resolution a3, then ZL i >UI, record the contrast a1, brightness a2 and resolution a3 at this time, the image control parameters corresponding to the image of the i+1th frame are contrast b1, brightness b2 and resolution b3, ZL i+1 >ZL i When the contrast b1, brightness b2 and resolution b3 at that time are recorded, the contrast a1, brightness a2 and resolution a3 are replaced.

6. The intelligent screen projection control system based on image processing technology according to claim 1, characterized in that: After receiving the second command signal, the intelligent control module performs photometric compensation on the image and adjusts the picture control parameters to be consistent with the recorded picture control parameters; , where Y´ i is the compensation image of the i-th frame projection screen image, B θ is the photometric compensation expression, θ is the learnable network parameter, T is the spectral reflectance feature, , where L is the loss function.

7. The intelligent screen projection control system based on image processing technology according to claim 2, characterized in that: The Gaussian scale space is constructed to detect feature points that exist at different scales. When detecting feature points, the Gaussian difference is used to approximate the Gaussian Laplace operator. The calculation formula of the Gaussian difference is expressed as: ; where k is the scale factor of the scale difference between two adjacent layers. Assuming that each group has S layers, then ; and the bottom-level image of the previous set of images is obtained by downsampling the images with a scale of 2σ in the next set.

Images