A display method based on an LCD projector and an LCD projector

Abstract

A display method based on an LCD projector and an LCD projector, relating to the field of projectors. The method includes: identifying an occluding object in the projection area of the LCD projector; performing face recognition on the occluding object, and if the occluding object contains a face, determining the occluding object as an occluding person; performing facial recognition on the occluding person to obtain facial expressions, and performing gesture recognition on the occluding person to obtain body movements; detecting the staying time of the occluding person in the projection area, and if the staying time is greater than a preset time threshold, identifying whether the occluding person is a target person according to the facial expressions and body movements; if it is a target person, determining the position of the human body contour in the projection area and determining the occluded projection area occupied; adjusting the projection parameters of the occluded projection area so that the visibility of the occluded projection area is higher than a preset visibility threshold. Implementing this method can improve the demonstration effect of the LCD projector.

Description

Technical Field

[0001] This application relates to the field of projectors, and particularly to a display method and an LCD projector based on an LCD projector. Background Art

[0002] With the continuous development of display technology, LCD projectors have been widely used in scenarios such as conference rooms and classrooms due to their advantages such as high definition and large-size display. The LCD projector projects an image onto a wall or a screen to achieve the effect of large-screen display.

[0003] In the related art, LCD projectors generally adopt an adjustable projection parameter system and a simple occlusion processing function. For occlusion processing, some projectors use technologies based on infrared or ultrasonic sensors to detect whether there is an object in the projection area. When occlusion is detected, the system will emit a prompt sound or display a warning message on the screen.

[0004] However, this method still causes the speaker to be blocked by the displayed content during a speech, and the audience cannot clearly see the speaker's expressions and movements. Due to the reason of the projector display, the speaker's expressions and movements cannot convey information to the audience, resulting in a poor demonstration effect of the LCD projector. Summary of the Invention

[0005] This application provides a display method and an LCD projector based on an LCD projector, which are used to improve the demonstration effect of the LCD projector.

[0006] In a first aspect, this application provides a display method based on an LCD projector, which is applied to an LCD projector. The method includes: detecting the projection area of the LCD projector and identifying the occluding object in the projection area; performing face recognition on the occluding object, and if the occluding object contains a face, determining the occluding object as an occluding person; performing facial recognition on the occluding person to obtain the facial expression of the occluding person, and performing gesture recognition on the occluding person to obtain the body movements of the occluding person; detecting the residence time of the occluding person in the projection area, and if the residence time is greater than a preset time threshold, identifying whether the occluding person is a target person according to the facial expression and the body movements; if it is a target person, determining the human contour position of the target person in the projection area and determining the occluding projection area occupied by the human contour position; adjusting the projection parameters of the occluding projection area so that the visibility of the occluding projection area is higher than a preset visibility threshold.

[0007] By adopting the above technical solution, the LCD projector detects the projection area, identifies the occluding object and determines the occluding person, performs face and pose recognition on the occluding person, and obtains information such as facial expressions and body movements. Then, by detecting the staying time of the occluding person and combining multi-modal information such as facial expressions and body movements, the target person is accurately identified. Once the target person is determined, the position of the human body contour and the occluding projection area are determined, and then the projection parameters of this area are adjusted to improve visibility, ensuring that the occluding area where the target person is located is clearly visible, enabling the viewer to see the target person, and avoiding the problem of poor demonstration effect caused by the traditional projector's inability to distinguish the identity of the occluding person.

[0008] Combined with some embodiments of the first aspect, in some embodiments, the step of identifying whether the occluding person is the target person according to the facial expression and the body movement specifically includes: inputting the facial expression into the expression feature extraction module in the preset multi-modal feature fusion model to obtain a facial expression feature vector; inputting the body movement into the body movement feature extraction module in the preset multi-modal feature fusion model to obtain a body movement feature vector; performing feature fusion on the facial expression feature vector and the body movement feature vector to obtain a fused feature vector; inputting the fused feature vector into a preset target person classifier to obtain a target person probability score; if the target person probability score is greater than a preset threshold, it is determined that the occluding person is the target person.

[0009] By adopting the above technical solution, the facial expression is input into the expression feature extraction module of the preset multi-modal feature fusion model to obtain a facial expression feature vector, the body movement is input into the body movement feature extraction module to obtain a body movement feature vector, then feature fusion is performed to obtain a fused feature vector, and finally the fused feature vector is input into the preset target person classifier to obtain a target person probability score, so as to determine whether the occluding person is the target person. This multi-modal feature fusion method makes full use of various information such as facial expressions and body movements, making the recognition of the target person more accurate and comprehensive.

[0010] In some embodiments in combination with some embodiments of the first aspect, the step of adjusting the projection parameters of the occluded projection area so that the visibility of the occluded projection area is higher than a preset visibility threshold specifically includes: obtaining the current brightness value and contrast value of the occluded projection area; calculating the current visibility of the occluded projection area according to the current brightness value and the current contrast value; if the current visibility is lower than the preset visibility threshold, increasing the brightness value of the occluded projection area to obtain an optimized brightness value, and increasing the contrast value of the occluded projection area to obtain an optimized contrast value; calculating the optimized visibility of the occluded projection area according to the optimized brightness value and the optimized contrast value; if the optimized visibility is not lower than the preset visibility threshold, taking the optimized brightness value and the optimized contrast value as the new projection parameters of the occluded projection area, and adjusting the projection settings of the LCD projector according to the new projection parameters.

[0011] By adopting the above technical solution, first, the current brightness value and contrast value of the occluded projection area are obtained, and the current visibility is calculated. If the current visibility is lower than the preset threshold, the brightness value and contrast value are increased to obtain the optimized brightness value and contrast value, and the optimized visibility is calculated. If the optimized visibility is not lower than the preset threshold, the optimized brightness value and contrast value are used as the new projection parameters to adjust the projection settings of the projector, which can dynamically adjust the projection parameters according to the actual situation, ensure that the visibility of the occluded projection area is always higher than the preset visibility threshold, and make the human body in the occluded projection area clearly visible.

[0012] In some embodiments in combination with some embodiments of the first aspect, after the step of adjusting the projection parameters of the occluded projection area so that the visibility of the occluded projection area is higher than a preset visibility threshold, the method further includes: performing real-time monitoring on the occluded projection area, and obtaining the real-time brightness value and real-time contrast value of the occluded projection area; calculating the real-time visibility of the occluded projection area according to the real-time brightness value and the real-time contrast value; if it is detected that the real-time visibility is lower than the preset visibility threshold, obtaining the current ambient light intensity of the LCD projector; dynamically adjusting the preset visibility threshold according to the current ambient light intensity to obtain an adjusted visibility threshold; comparing the real-time visibility with the adjusted visibility threshold; if the real-time visibility is still lower than the adjusted visibility threshold, re-executing the step of adjusting the projection parameters of the occluded projection area until the real-time visibility is greater than or equal to the adjusted visibility threshold.

[0013] By adopting the above technical solution, the occluded projection area is monitored in real time, the real-time brightness value and the real-time contrast value are obtained, and the real-time visibility is calculated. If the real-time visibility is lower than the preset visibility threshold, the current ambient light intensity of the LCD projector is obtained, and the preset visibility threshold is dynamically adjusted to obtain the adjusted visibility threshold. The real-time visibility is compared with the adjusted visibility threshold. If the real-time visibility is still lower than the adjusted visibility threshold, the step of adjusting the projection parameters of the occluded projection area is re-executed until the real-time visibility is greater than or equal to the adjusted visibility threshold, so that the visibility of the occluded projection area can be optimized in a timely manner according to the change of the ambient light, ensuring a clear projection effect under different environmental conditions and enhancing the environmental adaptability and stability of the LCD projector.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the steps of determining the human body contour position of the target person in the projection area and determining the occluded projection area occupied by the human body contour position, the method further includes: determining the position ratio of the occluded projection area in the projection area, and determining the screen position in the current screen played by the LCD projector according to the position ratio; detecting whether there is text content or graphic content at the screen position; if so, adjusting the projection parameters of the occluded projection area so that the visibility of the occluded projection area is higher than the preset visibility threshold.

[0015] By adopting the above technical solution, the position ratio of the occluded projection area in the projection area is determined, the screen position in the current screen played by the LCD projector is determined according to the position ratio, and then it is detected whether there is text content or graphic content at the screen position. If so, the projection parameters of the occluded projection area are adjusted so that the visibility of the occluded projection area is higher than the preset visibility threshold, which can prevent the human body of the target person from being blocked by text and the demonstration effect is better.

[0016] In combination with some embodiments of the first aspect, in some embodiments, the steps of determining the position ratio of the occluded projection area in the projection area and determining the screen position in the current screen played by the LCD projector according to the position ratio specifically include: obtaining the boundary coordinates of the occluded projection area, the boundary coordinates of the projection area, and the resolution of the current screen played by the LCD projector; calculating the horizontal position ratio and the vertical position ratio of the occluded projection area in the projection area according to the boundary coordinates of the occluded projection area and the boundary coordinates of the projection area; calculating the screen pixel coordinate range corresponding to the occluded projection area according to the horizontal position ratio, the vertical position ratio, and the resolution; and determining the screen position corresponding to the occluded projection area in the current played screen according to the screen pixel coordinate range.

[0017] By adopting the above technical solution, the boundary coordinates of the occluded projection area, the boundary coordinates of the projection area, and the resolution of the current playback screen of the LCD projector are obtained. Based on these coordinates, the horizontal position ratio and vertical position ratio of the occluded projection area in the projection area are calculated. Then, according to the ratio and the resolution, the corresponding picture pixel coordinate range of the occluded projection area is calculated. Finally, based on this range, the corresponding picture position of the occluded projection area is determined in the current playback screen, which can accurately find the corresponding position of the occluded area in the playback screen, making the processing of the occluded projection area more accurate and effective.

[0018] Combined with some embodiments of the first aspect, in some embodiments, after the step of adjusting the projection parameters of the occluded projection area so that the visibility of the occluded projection area is higher than a preset visibility threshold, the method further includes: if the occluding object is identified as a non-human occluding object, performing shape analysis and size measurement on the non-human occluding object to obtain the contour information and size data of the non-human occluding object; according to the contour information and size data, determining whether the non-human occluding object is a movable object; if it is determined to be a movable object, sending a removal instruction to the user, and the removal instruction is in the form of an audio or visual prompt.

[0019] By adopting the above technical solution, when the occluding object is identified as a non-human occluding object, the system will perform shape analysis and size measurement on it, so as to obtain the contour information and size data of the non-human occluding object. Then, based on this contour information and size data, it can be determined whether the non-human occluding object is a movable object. If it is determined to be a movable object, a removal instruction is sent to the user, and the instruction is conveyed to the user in the form of an audio or visual prompt. The user can receive a prompt about the occlusion of the movable object in a timely manner, so as to take corresponding measures to remove the object, reduce the influence of the non-human occluding object on the projection screen, and improve the integrity and clarity of the projection screen.

[0020] In a second aspect, an embodiment of the present application provides an LCD projector, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, and the computer program code includes computer instructions. The one or more processors call the computer instructions to cause the LCD projector to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product containing instructions. When the above computer program product runs on an LCD projector, it causes the above LCD projector to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0022] Fourthly, an embodiment of the present application provides a computer-readable storage medium, including instructions that, when running on an LCD projector, cause the LCD projector to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0023] It can be understood that the LCD projector provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be elaborated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0025] 1. In the present application, the projection area is detected by an LCD projector, the occluding object is identified and the occluding person is determined, and face and pose recognition are performed on the occluding person to obtain information such as facial expressions and body movements. Then, by detecting the staying time of the occluding person and combining multi-modal information such as facial expressions and body movements, the target person is accurately identified. Once the target person is determined, the position of the human body contour and the occluded projection area are determined, and then the projection parameters of this area are adjusted to improve visibility, ensuring that the occluded area where the target person is located is clearly visible, enabling the viewer to see the target person, and avoiding the problem of poor demonstration effect caused by the traditional projector being unable to distinguish the identity of the occluding person.

[0026] 2. In the present application, the current brightness value and contrast value of the occluded projection area are first obtained, and the current visibility is calculated. If the current visibility is lower than the preset threshold, the brightness value and contrast value are increased to obtain the optimized brightness value and contrast value, and the optimized visibility is calculated. If the optimized visibility is not lower than the preset threshold, the optimized brightness value and contrast value are used as the new projection parameters to adjust the projection settings of the projector, which can dynamically adjust the projection parameters according to the actual situation, ensuring that the visibility of the occluded projection area is always higher than the preset visibility threshold, making the human body in the occluded projection area clearly visible.

[0027] 3. In the present application, the position ratio of the occluded projection area in the projection area is determined, and the picture position in the current picture played by the LCD projector is determined according to this position ratio. Then, it is detected whether there is text content or graphic content at this picture position. If there is, the projection parameters of the occluded projection area are adjusted to make the visibility of the occluded projection area higher than the preset visibility threshold, which can prevent the human body of the target person from being blocked by text and result in a better demonstration effect. Description of the Drawings

[0028] Figure 1 is a scene diagram of the display method based on an LCD projector in the embodiments of the present application;

[0029] Figure 2 is a schematic flowchart of a display method based on an LCD projector in an embodiment of the present application;

[0030] Figure 3 is another schematic flowchart of a display method based on an LCD projector in an embodiment of the present application;

[0031] Figure 4 is a schematic structural diagram of a physical device of an LCD projector in an embodiment of the present application. Detailed implementation manners

[0032] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application, the singular forms "a", "an", "the above", "the" and "this" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations including one or more of the listed items.

[0033] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0034] For ease of understanding, the application scenarios of the embodiments of the present application are introduced below, such as Figure 1 , Figure 1 is a scene diagram of a display method based on an LCD projector in an embodiment of the present application.

[0035] In Figure 1 , the LCD projector projects an image onto a screen. There are occluding objects and target persons in the projection area. By detecting the occluding objects in the projection area, it is identified whether there is a human face, so as to determine the occluding person. For the identified person, the system further performs recognition of facial expressions and postures to obtain their facial expressions and body movements. If the staying time of the occluding person in the projection area exceeds a preset threshold, the system will judge whether it is a target person according to their expressions and movements. The "target person" is identified and located within the projection area. At the same time, non-human occluding objects are also detected. By adjusting the projection parameters of the occluding area, it is ensured that the visibility of the area where the target person is located is higher than a preset value, so that the audience can clearly see the face and body of the target person without affecting the demonstration effect of the target person.

[0036] The following describes the process of the method provided in this embodiment in combination with the above scenarios. Please refer to Figure 2 , which is a schematic flowchart of a display method based on an LCD projector in an embodiment of the present application.

[0037] S201. Detect the projection area of the LCD projector and identify the occluding objects in the projection area.

[0038] Among them, the LCD projector refers to a projection device using liquid crystal display technology, which is used to project images or videos onto a screen or wall. The projection area refers to the entire picture range projected by the LCD projector, usually in a rectangular shape. Occluding objects refer to any objects that appear in the projection area and cause occlusion or interference to the projection image, including people, animals, furniture, etc.

[0039] Specifically, after the LCD projector starts working and projects an image, the system continuously monitors the entire projection area. This step uses image analysis technology to perform real-time scanning and analysis of the projection area to identify any occluding objects present. The system uses a camera or other sensors to capture real-time images of the projection area, and then analyzes these images through computer vision algorithms to detect any object contours or moving objects that are different from the background, thereby identifying the occluding objects.

[0040] In some embodiments, the detection of the projection area and the identification of occluding objects are achieved in multiple ways: scanning the entire projection area with a depth camera; then, analyzing the obtained depth data to identify areas with significant depth differences from the background plane; finally, marking these areas as occluding objects. Optionally, capture the background image of the projection area when there are no occluding objects; then, capture the image of the projection area in real time and perform a pixel-level comparison with the background image; finally, identify the significantly different areas as occluding objects. In addition, there are other implementation methods, which are not limited here.

[0041] S202. Perform face recognition on the occluding object. If the occluding object contains a face, the occluding object is determined as an occluding person.

[0042] Among them, face recognition refers to using computer vision technology to detect and identify human faces in images or videos. Occluding persons refer to occluding objects identified as containing human faces, that is, occluding objects determined to be human. Specifically, after identifying the occluding objects, the system further analyzes each occluding object, especially performs face recognition. If a human face is detected in the occluding object, the system marks the occluding object as an occluding person.

[0043] In some embodiments, face recognition of occluded objects is achieved in multiple ways: Optionally, the image of the occluded object is input into a pre-trained convolutional neural network; then, the network outputs the region containing the face and its confidence; finally, according to a preset confidence threshold, it is determined whether there is a face. Optionally, the system uses traditional feature point detection methods for face recognition. The specific steps include: First, preprocess the image of the occluded object, such as grayscale conversion and histogram equalization; then, use a Haar cascade classifier or a similar algorithm to detect the face region; finally, search for key feature points such as eyes, nose, mouth, etc. within the detected region, and if enough feature points are found, it is recognized as a face. In addition, there are other implementation methods, which are not limited here.

[0044] S203. Perform face recognition on the occluded person to obtain the facial expression of the occluded person, and perform pose recognition on the occluded person to obtain the body movements of the occluded person.

[0045] Among them, face recognition refers to the process of analyzing and interpreting human faces using computer vision technology. Facial expression refers to the emotional state shown on a person's face, such as smiling, frowning, surprise, etc. Pose recognition refers to the technology of understanding human poses by analyzing the positions and movements of various parts of the human body. Body movement is used to represent the movement states of the human limbs and torso, such as waving, nodding, shaking the head, etc.

[0046] Specifically, the system performs fine-grained recognition on the face of the occluded person, extracts facial features, and analyzes facial expressions. This process usually involves locating facial key points, such as eyes, mouth, eyebrows, etc., and then judging facial expressions based on the relative positions and changes of these key points. At the same time, the system also performs recognition on the overall pose of the occluded person, which includes analyzing the bone structure, joint positions, and relative movements of the limbs of the human body, so as to obtain information on body movements.

[0047] In some embodiments, facial expression recognition and pose recognition can be achieved in multiple ways: Optionally, use a pre-trained convolutional neural network to extract facial features; then, input the extracted features into an expression classifier; finally, output the expression category and its confidence, detect the key points of the human body (such as shoulders, elbows, wrists, etc.); then, analyze the relative positions and movement trajectories of these key points; finally, match the current body movement according to a predefined pose pattern library. Optionally, construct 3D models of the human face and body; then, map the real-time captured 2D images onto the 3D models; finally, recognize facial expressions and body movements by analyzing the deformation of the 3D models. It can be understood that other methods can also be used for implementation, which are not limited here.

[0048] S204. Detect the residence time of the occluding person in the projection area. If the residence time is greater than a preset time threshold, identify whether the occluding person is the target person based on the facial expression and body movement.

[0049] Among them, the residence time refers to the length of time that the occluding person continuously exists in the projection area. The preset time threshold represents a time standard preset by the system for determining whether the occluding person is worthy of further analysis. The target person refers to the person that the system determines the occluding person to be in line with the target person who is giving a speech. The facial expression and body movement of the target person have the characteristics of giving a speech.

[0050] Specifically, the system will start a timer to record the residence time of the occluding person in the projection area. At this time, the system will use a preset algorithm or model to determine whether this occluding person conforms to the characteristics of the target person through facial expression and body movement information.

[0051] In some embodiments, the detection of the residence time and the identification of the target person can be achieved in various ways: Optionally, the system can adopt a target tracking method based on computer vision. The specific steps include: First, assign a unique ID to each detected occluding person; then, continuously track the position of each ID using a target tracking algorithm (such as a Kalman filter); finally, record the cumulative time of each ID in the projection area and compare it with the preset threshold. Optionally, the system can use a multi-modal feature fusion method to identify the target person. The specific steps include: First, extract the facial expression feature vector and the body movement feature vector; then, use a pre-trained feature fusion model to combine these feature vectors into a comprehensive feature representation; finally, input this comprehensive feature into the target person classifier to obtain a judgment result on whether it is the target person. It can be understood that other ways can also be adopted to achieve the residence time detection and the target person identification, such as combining environmental context information or using a deep learning model with a spatio-temporal attention mechanism, which is not limited here.

[0052] S205. If it is the target person, determine the body contour position of the target person in the projection area and determine the occluding projection area occupied by the body contour position.

[0053] Among them, the target person refers to a specific person that the system identifies as needing special attention or processing. The body contour position represents the outer boundary line of the target person in the projection area. The occluding projection area refers to the part of the projection screen covered or occluded by the body contour of the target person. The projection area is used to represent the entire screen range projected by the LCD projector.

[0054] Specifically, first, the system precisely locates the position of the target person in the entire projection area. Then, it uses image processing algorithms to extract the human body contour of the target person, which usually includes the outer boundaries of the head, torso, and limbs. Next, the system calculates the specific position and size of this human body contour in the projection area. Finally, based on the position and size of this human body contour, the system determines the occluded projection area, that is, the part of the projection screen covered by the human body contour.

[0055] In some embodiments, the determination of the human body contour position of the target person and the determination of the occluded projection area can be achieved in various ways: Optionally, the system can adopt a deep learning-based human body segmentation method. The specific steps include: First, use a pre-trained semantic segmentation model to process the image of the projection area to obtain a pixel-level human body segmentation result; then, post-process the segmentation result, such as edge smoothing and small area removal, to obtain a more accurate human body contour; finally, align the human body contour with the coordinate system of the projection area to calculate the precise position and size of the occluded projection area. Optionally, the system can use a bone detection-based method to determine the human body contour. The specific steps include: First, use a human pose estimation algorithm to detect the key bone points of the target person; then, construct a rough human body model based on these bone points; finally, expand the rough model into a complete human body contour through interpolation and fitting methods, and calculate the occluded projection area. It can be understood that other methods can also be used to determine the human body contour position and the occluded projection area, such as combining 3D reconstruction technology of multi-view images or using a thermal imaging camera for auxiliary positioning, which are not limited here.

[0056] S206. Adjust the projection parameters of the occluded projection area to make the visibility of the occluded projection area higher than the preset visibility threshold.

[0057] Among them, the projection parameters refer to various settings that control the display effect of the projection screen, including brightness, contrast, color saturation, etc. Visibility refers to the clarity and recognizability of the projection screen under occlusion. The preset visibility threshold refers to the lowest acceptable visibility standard preset by the system.

[0058] Specifically, this step is immediately executed after the occluded projection area is determined. The system first evaluates the visibility of the current occluded projection area, usually by calculating indicators such as contrast and clarity within the area through image processing algorithms. If it is found that the visibility is lower than the preset threshold, the system will start to adjust the projection parameters. The adjustment process is usually iterative. The system will gradually change parameters such as brightness and contrast, and re-evaluate the visibility after each adjustment.

[0059] In some embodiments, the adjustment of the projection parameters for the occluded projection area can be achieved in various ways: Optionally, the system can adopt a method based on image enhancement. The specific steps include: First, apply a contrast enhancement algorithm, such as histogram equalization or adaptive contrast enhancement, to the occluded projection area; Then, adjust the brightness within the area, where it is necessary to increase the overall brightness to offset the shadow caused by occlusion; Finally, fine-tune the color saturation to ensure that the enhanced image maintains a natural appearance. Optionally, the system can use an adaptive adjustment method based on artificial intelligence. The specific steps include: First, use a machine learning model to analyze the characteristics of the occluded projection area, such as the degree of occlusion, ambient light, etc.; Then, based on the analysis results, predict the optimal parameter adjustment scheme; Finally, gradually apply the predicted parameters and monitor the effect in real time, and make fine-tuning if necessary. It can be understood that other methods can also be adopted, which are not limited here.

[0060] The following is a further and more specific process description of the method provided in this embodiment. Please refer to Figure 2 , which is another schematic flowchart of the display method based on an LCD projector in the embodiments of the present application.

[0061] S301. Detect the projection area of the LCD projector and identify the occluding object in the projection area.

[0062] It can be understood that this step is similar to step S101 and will not be elaborated here.

[0063] S302. Perform face recognition on the occluding object. If a face is included in the occluding object, the occluding object is determined as an occluding person.

[0064] It can be understood that this step is similar to step S102 and will not be elaborated here.

[0065] S303. Perform face recognition on the occluding person to obtain the facial expression of the occluding person, and perform pose recognition on the occluding person to obtain the body movements of the occluding person.

[0066] It can be understood that this step is similar to step S103 and will not be elaborated here.

[0067] S304. Detect the residence time of the occluding person in the projection area. If the residence time is greater than a preset time threshold, determine whether the occluding person is a target person according to the facial expression and the body movements.

[0068] This step specifically includes:

[0069] Input the facial expression into the expression feature extraction module in the preset multi-modal feature fusion model to obtain a facial expression feature vector;

[0070] Input the limb movement into the limb movement feature extraction module in the preset multi-modal feature fusion model to obtain the limb movement feature extraction module;

[0071] Fuse the facial expression feature vector and the limb movement feature vector to obtain a fused feature vector;

[0072] Input the fused feature vector into the preset target person classifier to obtain the target person probability score;

[0073] If the target person probability score is greater than the preset threshold, determine that the occluded person is the target person.

[0074] In these steps, the facial expression refers to the emotional state shown on a person's face, such as smiling, frowning, etc. The limb movement represents the movement state of a person's limbs and torso, such as waving, nodding, etc. The preset multi-modal feature fusion model refers to a machine learning model that has been pre-trained and can process multiple different types of input data. The feature vector is used to represent the mathematical representation form obtained by converting the original data. The fused feature vector refers to a new comprehensive feature representation formed by combining multiple feature vectors. The preset target person classifier refers to an algorithm model that has been pre-trained and is used to determine whether the input data belongs to the target person category. The target person probability score represents the likelihood that the input data is classified as the target person. The preset threshold refers to the judgment criterion preset by the system for determining whether to classify the occluded person as the target person.

[0075] Specifically, after obtaining the facial expression and limb movement information of the occluded person, immediately start to execute this series of steps. First, input the facial expression data into the expression feature extraction module of the preset multi-modal feature fusion model to extract key features and convert them into vectors. At the same time, input the limb movement data into the limb movement feature extraction module of the same model, and also extract features and convert them into vectors. Next, use the feature fusion algorithm to combine these two feature vectors into a more comprehensive fused feature vector. Then, input this fused feature vector into the preset target person classifier to calculate a probability score, indicating the likelihood that the current occluded person is the target person. Finally, compare this probability score with the preset threshold. If the score exceeds the threshold, determine that the occluded person is the target person, otherwise consider it not to be the target person.

[0076] In some embodiments, multi-modal feature fusion and target person recognition can be achieved in various ways: using a multi-modal feature fusion method based on an attention mechanism, including processing data using a pre-trained visual model, applying a cross-attention mechanism, and finally performing weighted summation to obtain a fused feature vector; using an ensemble learning method to improve the accuracy of target person recognition, including training multiple different classifiers, inputting the fused feature vector into each classifier, and finally synthesizing the prediction results to obtain the final target person probability score. It can be understood that other ways can also be adopted to achieve multi-modal feature fusion and target person recognition, such as using a graph neural network or adopting an online learning method, which are not limited here.

[0077] S305. If it is the target person, determine the position of the human body contour of the target person in the projection area, and determine the occluded projection area occupied by the position of the human body contour.

[0078] It can be understood that this step is similar to step S205 and will not be elaborated here.

[0079] S306. Adjust the projection parameters of the occluded projection area so that the visibility of the occluded projection area is higher than a preset visibility threshold.

[0080] This step specifically includes:

[0081] Obtain the current brightness value and contrast value of the occluded projection area;

[0082] Calculate the current visibility of the occluded projection area according to the current brightness value and the current contrast value;

[0083] If the current visibility is lower than the preset visibility threshold, increase the brightness value of the occluded projection area to obtain an optimized brightness value, and increase the contrast value of the occluded projection area to obtain an optimized contrast value;

[0084] Calculate the optimized visibility of the occluded projection area according to the optimized brightness value and the optimized contrast value;

[0085] If the optimized visibility is not lower than the preset visibility threshold, use the optimized brightness value and the optimized contrast value as the new projection parameters of the occluded projection area, and adjust the projection settings of the LCD projector according to the new projection parameters.

[0086] Specifically, the occluded projection area refers to the part of the projected image blocked by the human body. The brightness value represents the light and dark degree of the projected image. The contrast value is used to represent the difference degree between the brightest part and the darkest part of the image. Visibility refers to the clarity and recognizability of the projected image when it is occluded. The preset visibility threshold represents the lowest acceptable visibility standard preset by the system. The optimized brightness value and the optimized contrast value refer to the new brightness and contrast parameters after adjustment. The new projection parameters are used to represent the adjusted projection settings, including the optimized brightness value and contrast value. The LCD projector refers to a projection device that uses liquid crystal display technology.

[0087] Specifically, when the system detects that the projection area is occluded, it immediately starts to execute this series of steps. First, the system obtains the current brightness value and contrast value of the occluded projection area, which is usually achieved through built-in optical sensors or image processing algorithms. Then, the system uses a predefined algorithm to calculate the current visibility based on these values. Next, the system compares the calculated visibility with the preset threshold. If it is lower than the threshold, the system gradually increases the brightness value and contrast value, recalculating the visibility after each increase until it reaches or exceeds the preset threshold. During this process, the system may use complex optimization algorithms to balance the increase in brightness and contrast to achieve the best effect. Finally, when the optimized visibility meets the requirements, the system sets the new brightness value and contrast value as the new projection parameters for the occluded projection area and adjusts the settings of the LCD projector accordingly.

[0088] In some embodiments, the parameter optimization and visibility improvement of the occluded projection area can be achieved in various ways: Optionally, the system can adopt an adaptive optimization method based on machine learning. The specific steps include: First, use a pre-trained neural network model to input parameters such as the current brightness value, contrast value, and ambient light, and predict the optimal parameter adjustment direction; then, according to the prediction results, gradually adjust the brightness and contrast, and calculate the new visibility using an image quality evaluation algorithm after each adjustment; finally, when the visibility reaches the preset threshold or the number of adjustments reaches the upper limit, stop the optimization process and apply the optimal parameters. Optionally, the system can use a multi-region segmented optimization strategy. The specific steps include: First, divide the occluded projection area into multiple sub-regions, and optimize the parameters of each sub-region separately; then, apply different degrees of brightness and contrast enhancement to each sub-region, while considering the smooth transition between adjacent regions; finally, comprehensively evaluate the visibility of all sub-regions. If the overall visibility reaches the preset threshold, apply the optimized parameters, otherwise continue to adjust. It can be understood that other methods can also be used to optimize the parameters of the occluded projection area, such as using a genetic algorithm to search for the optimal parameter combination, or combining a human eye visual characteristic model to optimize the parameters, which are not limited here.

[0089] S307. Monitor the occluded projection area in real time to obtain the real-time brightness value and real-time contrast value of the occluded projection area.

[0090] Real-time monitoring means continuously detecting and tracking the target area. The occluded projection area refers to the part of the area where the human body occludes the projection area of the LCD projector. The real-time brightness value is the numerical value of the brightness and darkness degree of the occluded projection area at the current moment. The real-time contrast value is the numerical value of the difference degree between the bright part and the dark part of the occluded projection area at the current moment. Obtaining the real-time brightness value and real-time contrast value is to analyze the image of the occluded projection area through an image processing algorithm and extract the corresponding brightness and contrast features.

[0091] Specifically, the system will continuously use a camera or sensor to collect and analyze images of the occluded projection area, and extract the brightness value and contrast value of the occluded projection area in units of a certain time interval (for example, every 100 ms). This can be achieved by calculating the histogram distribution, gray-level statistics, etc. of each collected image. The system will immediately update these brightness and contrast values to reflect the latest state of the occluded projection area. Continuously monitoring the occluded projection area and obtaining its real-time parameters is the key step to achieve subsequent dynamic adjustment.

[0092] S308. Calculate the real-time visibility of the occluded projection area according to the real-time brightness value and the real-time contrast value.

[0093] Real-time visibility refers to the clear and recognizable degree of the occluded projection area at the current moment. Calculating the real-time visibility according to the real-time brightness value and real-time contrast value means using brightness and contrast parameters to evaluate the visible state of the occluded area through a specific algorithm.

[0094] Specifically, the system will input the obtained real-time brightness value and real-time contrast value of the occluded projection area into a preset algorithm for calculating visibility. This algorithm can calculate a numerical visibility score or parameter based on the brightness value and contrast value, combined with factors such as ambient light and image quality evaluation model. The calculated numerical value of the real-time visibility can quantitatively represent the quality of the visual effect of the current occluded projection area. The system will immediately update this visibility value. Calculating the real-time visibility is the key step to achieve dynamic optimization.

[0095] S309. If it is detected that the real-time visibility is lower than the preset visibility threshold, obtain the current ambient light intensity of the LCD projector.

[0096] The preset visibility threshold is the minimum acceptable visibility standard for the occluded projection area pre-set by the system. The current ambient light intensity is the real-time lighting condition of the environment where the LCD projector is located, such as indoor / outdoor, bright / dark, etc. Detecting that the real-time visibility is lower than the threshold and then obtaining the current light intensity is an operation to obtain environmental parameters for dynamic adjustment when the visibility of the occluded projection area is recognized as insufficient.

[0097] Specifically, the system will immediately compare the calculated real-time visibility of the occluded projection area with the preset visibility threshold. If the visibility is lower than the threshold, the detection of the ambient light intensity is triggered. This can be achieved by collecting data through the photosensitive sensor built in the LCD projector or by using a camera to obtain an image for analysis. After obtaining the data of the current light intensity, the system can dynamically adjust relevant parameters according to the lighting conditions to improve the visibility of the occluded area.

[0098] S310. Dynamically adjust the preset visibility threshold according to the current ambient light intensity to obtain an adjusted visibility threshold.

[0099] The current ambient light intensity is the real-time lighting condition of the environment where the LCD projector is located. The preset visibility threshold is the minimum acceptable visibility standard for the occluded projection area pre-set by the system. Adjusting the preset visibility threshold is to appropriately modify the originally set visibility standard according to the current lighting conditions. The adjusted visibility threshold is a new visibility standard that has been dynamically optimized.

[0100] Specifically, the system will dynamically adjust the originally set preset visibility threshold according to the detected current ambient light intensity data. In a strong light environment, due to the limited projection brightness, the visibility standard can be appropriately reduced; while in a low light environment, the visibility standard can be increased. This adjustment process can be achieved based on a preset mapping curve or a machine learning model. The new adjusted visibility threshold will replace the original preset value for subsequent visibility judgment, thus achieving adaptive optimization.

[0101] S311. Compare the real-time visibility with the adjusted visibility threshold.

[0102] The real-time visibility is the visible state of the current occluded projection area. Comparing the real-time visibility with the adjusted visibility threshold is an operation to determine whether the optimized visibility standard is met.

[0103] Specifically, the system will compare the real-time visibility value of the already calculated occluded projection area with the new visibility threshold adjusted in the previous step to see if the current real-time visibility is higher than the new threshold. If it is higher, it means that the current visibility has met the requirements; if it is still lower than the new threshold, parameters need to be further adjusted to improve the visibility. This comparison process can be carried out immediately to determine whether the effect of parameter adjustment meets the requirements.

[0104] S312. If the real-time visibility is still lower than the adjusted visibility threshold, re-execute the step of adjusting the projection parameters of the occluded projection area until the real-time visibility is greater than or equal to the adjusted visibility threshold.

[0105] The adjustment of projection parameters refers to changing parameters such as the brightness and contrast of the occluded projection area. What this step means is that if it is found through comparison that the real-time visibility is still lower than the adjusted threshold requirement, the system needs to re-execute the process of adjusting the projection parameters and continue to adjust until the real-time visibility is improved and meets the new threshold requirement.

[0106] Specifically, if the visibility comparison result is that the real-time visibility is still lower than the new threshold, the system will re-execute the process of adjusting the parameters of the occluded projection area. This usually includes continuing to increase the brightness, contrast, etc. in order to further improve the visibility. The adjustment process is a closed-loop control. After each adjustment, the real-time visibility is calculated and compared again, and the iteration continues until the standard is reached. The implementation method can be to gradually increase the adjustment amplitude or use a search algorithm to find the optimal parameter combination. When the visibility meets the new threshold requirement, the adjustment is completed; otherwise, a new round of adjustment continues, and so on in a cycle.

[0107] S313. Determine the position ratio of the occluded projection area in the projection area, and determine the picture position in the current picture played by the LCD projector according to this position ratio;

[0108] This step specifically includes:

[0109] Obtain the boundary coordinates of the occluded projection area, the boundary coordinates of the projection area, and the resolution of the current picture played by the LCD projector;

[0110] According to the boundary coordinates of the occluded projection area and the boundary coordinates of the projection area, calculate the horizontal position ratio and vertical position ratio of the occluded projection area in the projection area

[0111] According to the horizontal position ratio, the vertical position ratio, and the resolution, calculate the range of picture pixel coordinates corresponding to the occluded projection area;

[0112] According to the range of picture pixel coordinates, determine the picture position corresponding to the occluded projection area in the current played picture.

[0113] Among these steps, the occluded projection area refers to the part of the projected image that is occluded by an object. The boundary coordinates represent the location and extent of a certain area in space. The projection area refers to the entire area where the projector can project an image. The resolution is used to represent the number of pixels in a digital image, usually expressed as the number of horizontal pixels multiplied by the number of vertical pixels. The horizontal position ratio and the vertical position ratio refer to the relative position of the occluded area in the entire projection area. The range of the picture pixel coordinates represents the pixel positions in the digital image corresponding to the occluded area. The currently playing picture refers to the image content being displayed by the projector.

[0114] Specifically, when the system detects that the projection area is occluded, it immediately starts to execute this series of steps. First, the system obtains the boundary coordinates of the occluded projection area and the entire projection area, which may be achieved through optical sensors or image processing algorithms. At the same time, the system also obtains the resolution information of the currently playing picture. Next, the system uses mathematical calculation methods to calculate the relative position of the occluded area in the entire projection area based on the boundary coordinates of these two areas, obtaining the position ratios in the horizontal and vertical directions. This calculation process may involve coordinate system conversion and normalization processing. Then, the system combines these position ratios with the current picture resolution and, through ratio conversion, obtains the range of pixel coordinates in the digital image corresponding to the occluded area. This step may need to consider factors such as projection distortion and correction. Finally, the system accurately locates the picture position corresponding to the occluded area in the currently playing digital image according to the calculated range of pixel coordinates. This positioning process may also need to consider factors such as image scaling and cropping to ensure the accuracy of the positioning.

[0115] In some embodiments, the positioning and mapping of the occluded area can be achieved in various ways: Optionally, the system can adopt a three-dimensional space mapping method based on a depth camera. The specific steps include: First, use the depth camera to capture the three-dimensional point cloud data of the projection area, including the occluding object and the projection surface; then, identify the contour of the occluding object through a point cloud segmentation algorithm and calculate its exact position and shape in three-dimensional space; finally, use the projection matrix to map the occluded area in three-dimensional space to the two-dimensional image plane to obtain the corresponding range of pixel coordinates. Optionally, the system can use a real-time tracking method based on computer vision. The specific steps include: First, embed invisible marker points or feature patterns in the projection picture; then, use a high-speed camera to capture the projection picture in real time and detect the position changes of these marker points through image processing algorithms; finally, infer the exact position and range of the occluded area based on the deformation and occlusion of the marker points. It can be understood that other methods can also be used to achieve the positioning and mapping of the occluded area, such as using a collaborative positioning system of multiple projectors and cameras, or combining a human pose estimation algorithm for more accurate occlusion prediction, which is not limited here.

[0116] S314. Detect whether there is text content or graphic content at this screen position.

[0117] The screen position refers to the position corresponding to the occluded projection area in the screen played by the LCD projector. Text content refers to the text or characters existing at this screen position. Graphic content refers to the graphic or picture elements at this screen position. Detecting whether there is text or graphic content at the screen position means analyzing the display content at this position to determine whether it contains text or graphic information.

[0118] Specifically, the system will first determine the pixel area of the corresponding screen position according to the position ratio of the occluded projection area in the entire projected screen. Then, use image processing algorithms to analyze this screen position and detect whether this area contains text or graphic information. For example, use OCR technology to recognize text, and use edge detection, feature matching, etc. to judge graphic elements. Finally, if text or graphics are detected at the screen position, it is confirmed that this position needs to be ensured to be clearly visible with priority.

[0119] S315. If there is, adjust the projection parameters of this occluded projection area so that the visibility of this occluded projection area is higher than the preset visibility threshold.

[0120] Projection parameter adjustment means changing parameters such as the brightness and contrast of the occluded projection area. Improving visibility makes the image in the occluded area clearer and recognizable. The preset visibility threshold is the defined minimum acceptable visibility level.

[0121] If text or graphic content is detected at the screen position, the system will start the process of adjusting the parameters of the occluded projection area, with the goal of making the visibility of this area higher than the preset visibility threshold. The adjustment process includes gradually increasing the brightness and contrast of the occluded area while calculating the visibility of this area. When the visibility reaches or exceeds the preset threshold, the adjustment process ends. This can ensure that the occluded projection area where the text or graphic content is located achieves a clear and recognizable display effect. The specific implementation method can be to use image enhancement algorithms to optimize for text and graphics, or use machine learning models to predict the best parameter combination.

[0122] In some embodiments, after step S215, it further includes: if the occluding object is identified as a non-human occluding object, perform shape analysis and size measurement on the non-human occluding object to obtain the contour information and size data of the non-human occluding object;

[0123] According to the contour information and size data, judge whether the non-human occluding object is a movable object.

[0124] If it is determined that the object is a movable object, a removal instruction is sent to the user, and the removal instruction is in the form of an audio or visual prompt.

[0125] Specifically, the contour information refers to the outer boundary of the non-human occluding object obtained through image analysis. The size data refers to the size parameters of the occluding object measured. A movable object refers to an object whose position can be changed by human effort. Determining whether it is movable is to infer its moving possibility based on the object characteristics.

[0126] Specifically, the system first extracts the contour of the occluding object and measures its length, width, height and other data. Then, based on these contour and size information, combined with the object database, the category of the non-human occluding object is judged. For light or small-volume items, the system can infer that they have the possibility of moving. On the contrary, for fixed or oversized objects, it is judged as immovable. The contour and size characteristics support judging the moving attribute of the object.

[0127] If it is determined that the object is a movable object, a removal instruction is sent to the user, and the removal instruction is in the form of an audio or visual prompt.

[0128] The removal instruction is a prompt message to remind the user to move the occluding object away. The audio prompt can be a voice broadcast. The visual prompt can be text, icons, etc. displayed on the screen. This step means that if it is judged that the occluding object can be removed, the system will notify the user in the form of a prompt sound or a screen prompt to remove the movable occluding object.

[0129] Specifically, when it is judged that the occluding object can be moved away, the system sends a removal prompt to the user who is using it. This can be a voice prompt of "Please move the occluding object away", or a text or icon prompt that suddenly appears above the screen. The purpose is to attract the user's attention and remind to remove the movable object to eliminate the projected occlusion. The prompt method should be prominent and not interrupt the user experience. Sending the removal prompt can effectively prompt the user to actively eliminate the projected block and improve the projection effect.

[0130] The following describes the LCD projector in the embodiment of the present invention application from the perspective of hardware processing. Please refer to Figure 4 , which is a schematic structural diagram of an entity device of the LCD projector in the embodiment of the present application.

[0131] It should be noted that Figure 4 The structure of the LCD projector shown is only an example and should not bring any limitations to the functions and usage scope of the embodiments of the present invention.

[0132] Such as Figure 4As shown, the LCD projector includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the Read-Only Memory (ROM) 402 or the program loaded from the storage section 408 into the Random Access Memory (RAM) 403, such as executing the method described in the above embodiments. In the RAM 403, various programs and data required for system operation are also stored. The CPU 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An Input / Output (I / O) interface 405 is also connected to the bus 404.

[0133] The following components are connected to the I / O interface 405: an input section 406 including an audio input device, a button switch, etc.; an output section 407 including a Liquid Crystal Display (LCD), an audio output device, an indicator light, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read from it can be installed into the storage section 408 as needed.

[0134] Specifically, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication section 409, and / or installed from the removable medium 411. When the computer program is executed by the Central Processing Unit (CPU) 401, various functions defined in the present invention are executed.

[0135] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fibers, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0136] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings.

[0137] Specifically, the LCD projector in this embodiment includes a processor and a memory. A computer program is stored on the memory. When the computer program is executed by the processor, the display method based on the LCD projector provided in the above embodiment is implemented.

[0138] On the other hand, the present invention also provides a computer-readable storage medium. This storage medium can be included in the LCD projector described in the above embodiment; or it can exist independently and not be assembled into the LCD projector. The above storage medium carries one or more computer programs. When the one or more computer programs are executed by a processor of the LCD projector, the LCD projector implements the display method based on the LCD projector provided in the above embodiment.

[0139] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the various embodiments of the present application.

[0140] As used in the foregoing embodiments, depending on the context, the term "when" may be construed to mean "if" or "after" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "when determining" or "if (the stated condition or event) is detected" may be construed to mean "if determined" or "in response to determining" or "when (the stated condition or event) is detected" or "in response to detecting (the stated condition or event)".

[0141] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented. The processes can be completed by relevant hardware instructed by a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the foregoing method embodiments. The foregoing storage media include: various media such as ROM or random access memory RAM, magnetic disks, or optical discs that can store program code.

Claims

1. A display method based on an LCD projector, characterized in that, Applied to an LCD projector, the method includes: Detect the projection area of the LCD projector and identify the occluding object in the projection area; Perform face recognition on the occluding object. If a face is included in the occluding object, determine the occluding object as an occluding person; Perform facial recognition on the occluding person to obtain the facial expression of the occluding person, and perform gesture recognition on the occluding person to obtain the body movements of the occluding person; Detect the staying time of the occluding person in the projection area. If the staying time is greater than a preset time threshold, determine whether the occluding person is a target person according to the facial expression and the body movements. The step of determining whether the occluding person is a target person according to the facial expression and the body movements specifically includes: input the facial expression into the expression feature extraction module in a preset multi-modal feature fusion model to obtain a facial expression feature vector; input the body movements into the body movement feature extraction module in the preset multi-modal feature fusion model to obtain a body movement feature extraction module; fuse the facial expression feature vector and the body movement feature vector to obtain a fused feature vector; input the fused feature vector into a preset target person classifier to obtain a target person probability score; if the target person probability score is greater than a preset threshold, determine the occluding person as a target person; If it is a target person, determine the body contour position of the target person in the projection area and determine the occluding projection area occupied by the body contour position; Adjust the projection parameters of the occluding projection area so that the visibility of the occluding projection area is higher than a preset visibility threshold. The step of adjusting the projection parameters of the occluding projection area so that the visibility of the occluding projection area is higher than a preset visibility threshold specifically includes: Obtain the current brightness value and contrast value of the occluding projection area; Calculate the current visibility of the occluding projection area according to the current brightness value and the contrast value; If the current visibility is lower than the preset visibility threshold, increase the brightness value of the occluding projection area to obtain an optimized brightness value, and increase the contrast value of the occluding projection area to obtain an optimized contrast value; Calculate the optimized visibility of the occluding projection area according to the optimized brightness value and the optimized contrast value; If the optimized visibility is not lower than the preset visibility threshold, use the optimized brightness value and the optimized contrast value as the new projection parameters of the occluding projection area and adjust the projection settings of the LCD projector according to the new projection parameters.

2. The method according to claim 1, characterized in that, After the step of adjusting the projection parameters of the occluding projection area so that the visibility of the occluding projection area is higher than a preset visibility threshold, the method further includes: Perform real-time monitoring on the occluding projection area and obtain the real-time brightness value and real-time contrast value of the occluding projection area; Calculate the real-time visibility of the occluding projection area according to the real-time brightness value and the real-time contrast value; If it is detected that the real - time visibility is lower than the preset visibility threshold, obtain the current ambient light intensity of the LCD projector; According to the current ambient light intensity, dynamically adjust the preset visibility threshold to obtain an adjusted visibility threshold; Compare the real - time visibility with the adjusted visibility threshold; If the real - time visibility is still lower than the adjusted visibility threshold, re - execute the step of adjusting the projection parameters of the occluded projection area until the real - time visibility is greater than or equal to the adjusted visibility threshold.

3. The method according to claim 1, wherein After the step of determining the human body contour position of the target person in the projection area and determining the occluded projection area occupied by the human body contour position, the method further includes: Determine the position ratio of the occluded projection area in the projection area, and determine the picture position in the current picture played by the LCD projector according to the position ratio; Detect whether there is text content or graphic content at the picture position; If there is, adjust the projection parameters of the occluded projection area so that the visibility of the occluded projection area is higher than the preset visibility threshold.

4. The method according to claim 3, wherein The step of determining the position ratio of the occluded projection area in the projection area and determining the picture position in the current picture played by the LCD projector according to the position ratio specifically includes: Obtain the boundary coordinates of the occluded projection area, the boundary coordinates of the projection area, and the resolution of the current picture played by the LCD projector; According to the boundary coordinates of the occluded projection area and the boundary coordinates of the projection area, calculate the horizontal position ratio and the vertical position ratio of the occluded projection area in the projection area; According to the horizontal position ratio, the vertical position ratio, and the resolution, calculate the range of picture pixel coordinates corresponding to the occluded projection area; According to the range of picture pixel coordinates, determine the picture position corresponding to the occluded projection area in the current played picture.

5. The method according to claim 4, wherein After the step of adjusting the projection parameters of the occluded projection area so that the visibility of the occluded projection area is higher than the preset visibility threshold, the method further includes: If the occluding object is identified as a non - human occluding object, perform shape analysis and size measurement on the non - human occluding object to obtain the contour information and size data of the non - human occluding object; According to the contour information and size data, determine whether the non - human occluding object is a movable object; If it is determined to be a movable object, send a removal instruction to the user, and the removal instruction is in the form of an audio or visual prompt.

6. An LCD projector, characterized in that, The LCD projector includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the LCD projector to execute the method according to any one of claims 1 - 5.

7. A computer-readable storage medium, comprising instructions, characterized in that, When the instruction runs on the LCD projector, the LCD projector is caused to execute the method according to any one of claims 1-5.

8. A computer program product, characterized in that, When the computer program product runs on the LCD projector, the LCD projector is caused to execute the method according to any one of claims 1-5.

Images