Projection equipment and anti-eye-shooting projection method

Abstract

The invention provides projection equipment and an anti-eye-shooting projection method, and the method comprises the steps: marking a pixel point corresponding to a figure region in a target image as a target pixel point when the projection equipment obtains the target image, and generating a target enclosing rectangle according to an image region formed by the target pixel point, and obtaining a minimum height coordinate and a maximum height coordinate according to the first vertex angle point and the second vertex angle point of the target bounding rectangle, thereby calculating the head height of the figure area according to the image height of the target image, a preset constant, the minimum height coordinate and the maximum height coordinate. And determining a head area corresponding to the figure area in the target enclosing rectangle according to the head height, and reducing the brightness of projection content projected to the head area by the light emitting assembly. According to the method and the device, the pixel points in the target image are classified, so that the head area of a person is identified in the low-resolution target image, the brightness of the projection content corresponding to the head area is adjusted, and the face of a user is prevented from being irradiated by strong light.

Description

Technical Field

[0001] The present application relates to the technical field of projection equipment, and in particular to a projection equipment and an anti-eyeballing projection method. Background Art

[0002] Projection equipment is a device that can project images, videos and other information onto a screen or white wall through an optical system. It can be used for movie playback, video display, image projection and other scenes. Projection equipment can project large-screen images at a long distance so that users can watch clearer images.

[0003] When the projection device is working, it will convert digital image information into light signals, and then convert the light signals into light sources and project them into the projection area. When the user enters the projection area, the light source emitted by the projection device will directly hit the user's eyes, causing damage to the user's vision. For this reason, the projection device can be provided with an anti-eye function, that is, when the user enters the projection area, the projection device will identify the user's head area, thereby reducing the brightness of the light source in the head area and reducing the impact of strong light on the user's vision.

[0004] Identifying the user's head area requires the use of specific recognition algorithms, which require obtaining a high-resolution image of the display area, so as to recognize the user's head area in the high-resolution image of the display area. However, for low-end projection devices, it is impossible to obtain a high-resolution image of the display area through a high-resolution sensor, which results in the low-end projection device being unable to determine the user's head area through a specific recognition algorithm, and thus being unable to apply the anti-glare function. Summary of the invention

[0005] The present application provides a projection device and an anti-eyeballing projection method to solve the problem that a low-resolution projection device cannot apply an anti-eyeballing function when a user enters a projection area.

[0006] In a first aspect, some embodiments of the present application provide a projection device, including:

[0007] A light emitting component is configured to project projection content onto a projection surface;

[0008] A camera configured to capture a target image of the projection surface;

[0009] The controller is configured as:

[0010] When acquiring the target image, marking the pixel points corresponding to the person area in the target image as target pixel points;

[0011] Generate a target circumscribed rectangle according to the image area formed by the target pixel points;

[0012] Determine a first vertex point of the circumscribed rectangle and a second vertex point diagonally opposite the first vertex point, wherein the ordinate of the first vertex point is the minimum height coordinate, and the ordinate of the second vertex point is the maximum height coordinate;

[0013] Calculating the head height of the character area according to the image height of the target image, a preset constant, the minimum height coordinate and the maximum height coordinate, wherein the head height is the product of the height difference calculated between the maximum height coordinate and the minimum height coordinate and the preset constant;

[0014] Determine a head area corresponding to the person area in the target circumscribed rectangle according to the head height;

[0015] The brightness of the projection content projected by the light emitting component onto the head area is reduced.

[0016] The above technical solution has the following beneficial effects or advantages: by performing pixel classification on the acquired target image, the target pixel points corresponding to the human area in the target image are separated, and a target circumscribed rectangle is generated in the image area formed by the target pixel points, so as to determine the height of the head area through the target circumscribed rectangle. In the head area corresponding to the head height, the projection device reduces the brightness of the projection content projected by the light emitting component to realize the radiant eye function. In this embodiment, by identifying the human head in the low-resolution target image, the projection brightness can be reduced through the identified head area in the case of low resolution, thereby protecting the user's eyes from being exposed to strong light when the user enters the projection area.

[0017] In some embodiments, the controller performs the step of marking the pixel points corresponding to the person area in the target image as the target pixel points, which is specifically configured as follows:

[0018] In response to a power-on instruction, controlling the camera to capture a reference image;

[0019] Acquire reference pixel points in the reference image;

[0020] According to the reference pixel point, obtaining an initial distance value representing the distance between the camera and the projection surface;

[0021] If the difference between the initial distance value and the distance value of a pixel point in the target image is greater than the determination threshold, the pixel point is marked as a target pixel point.

[0022] The above technical solution has the following beneficial effects or advantages: when the projection device is turned on, the reference image is collected by the camera as a reference, and when the user enters the projection area, if the difference between the initial distance value and the distance value of the pixel point of the target image collected by the camera in real time is greater than the determination threshold, the pixel point is marked as the target pixel point. Therefore, this part of the pixel points can be marked as the target pixel points, thereby improving the efficiency of obtaining the target pixel points.

[0023] In some embodiments, the step of marking the pixel points corresponding to the person area in the target image as the target pixel points is specifically configured as follows:

[0024] Performing encoding on the target image by the encoder to obtain target image encoding;

[0025] Input the target image code into the decoder corresponding to the encoder for decoding to obtain an image decoding result;

[0026] The pixel points whose binary classification results in the image decoding result are the same as the preset classification results are marked as target pixel points, and the binary classification results are the probability results that the pixel points of the image decoding result are the target pixel points or the probability results that the pixel points of the image decoding result are the non-target pixel points.

[0027] The above technical solution has the following beneficial effects or advantages: by inputting the target image acquired in real time into the encoder for encoding to extract the pixel features in the target image, the target image code is obtained, and the target image code is decoded by the corresponding decoder to obtain the image decoding result, and the pixel points whose binary classification results in the image decoding result are the same as the preset classification results are marked as target pixel points, thereby improving the accuracy of obtaining the target pixel points.

[0028] In some embodiments, before the step of generating a target circumscribed rectangle according to the image area formed by the target pixels, the controller is further configured to:

[0029] Obtaining a region boundary point in the target pixel point;

[0030] Adjacent region boundary points are connected in sequence to obtain the image region.

[0031] The above technical solution has the following beneficial effects or advantages: the projection device can obtain the area boundary points in the target pixel points to determine the boundary of the person area in the projection area, thereby connecting adjacent area boundary points in sequence to obtain the image area of ​​the person entering the projection area.

[0032] In some embodiments, the step of obtaining the region boundary point in the target pixel point is specifically configured as follows:

[0033] Traversing the pixel points adjacent to the target pixel point;

[0034] If the adjacent pixel points include at least one non-target pixel point, the target pixel point is marked as a region boundary point.

[0035] The above technical solution has the following beneficial effects or advantages: the region boundary point should be consistent with the target pixel point and the non-target pixel point at the same time. To this end, the projection device can traverse the adjacent pixel points of the target pixel point. If the adjacent pixel points include at least one non-target pixel point, the target pixel point is marked as a region boundary point, and the image area is determined based on the region boundary point.

[0036] In some embodiments, the preset constant includes a target constant and a natural constant, and the step of calculating the head height of the character area according to the image height of the target image, the preset constant, the minimum height coordinate, and the maximum height coordinate is specifically configured as follows:

[0037] Calculate the height difference between the maximum height coordinate and the minimum height coordinate;

[0038] Calculate the height ratio of the height difference value to the image height;

[0039] The height of the head is obtained by calculating the product of the height difference, the target constant and a hyperbolic tangent function with the height ratio as the exponent of the natural constant.

[0040] The above technical solution has the following beneficial effects or advantages: the height difference between the maximum height coordinate and the minimum height coordinate is calculated, so that when the person in the detection image is higher, that is, the person is closer to the projection device, the proportion of the head should be larger, and then the height ratio of the height difference to the image height is calculated, and the maximum circumscribed rectangle height is normalized to 0-1. Finally, the head height is calculated according to the product of the height difference, the preset constant and the hyperbolic tangent function.

[0041] In some embodiments, the step of determining the head area corresponding to the person area in the target circumscribed rectangle according to the head height is specifically configured as follows:

[0042] Calculate the difference between the image height and the head height to determine the height of the area to be cropped;

[0043] According to the height of the area to be cropped, cropping is performed on the target circumscribed rectangle to obtain a remaining rectangle after cropping;

[0044] The target pixel points in the remaining rectangle are marked as the head area.

[0045] The above technical solution has the following beneficial effects or advantages: through the difference between the image height and the head height, the height of the area to be cropped is determined, and the torso area of ​​the character area is cropped according to the height of the area to be cropped to retain the head area of ​​the character area, thereby determining the projection area whose brightness needs to be reduced.

[0046] In some embodiments, the step of reducing the brightness of the projection content projected by the light emitting component to the head area is specifically configured as follows:

[0047] Obtaining the image size of the head area in the target image;

[0048] According to the mapping relationship between the light emitting component and the camera calibration, the image size is mapped to the area size of the light emitting component to obtain a target processing area;

[0049] The brightness of the projection content projected by the light emitting component onto the target processing area is reduced.

[0050] The above technical solution has the following beneficial effects or advantages: in the above embodiment, the obtained head area is the image size. In order to map the image size to the projection size of the light emitting component, the projection device can obtain the image size of the head area in the target image, and then map the image size to the resolution size of the camera according to the mapping relationship between the light emitting component and the camera calibration, complete the conversion of the mapping relationship between the image size and the projection size, and obtain the target processing area.

[0051] In some embodiments, after the step of reducing the brightness of the projection content projected by the light emitting component to the head area, the controller is further configured to:

[0052] Extracting regional feature points of the target processing area;

[0053] Obtaining a target processing region of a next target image by identifying the regional feature points in a next target image of the current target image;

[0054] The brightness of the projection content of the light emitting component projected onto the target processing area of ​​the next target image is reduced.

[0055] The above technical solution has the following beneficial effects or advantages: the target processing area is the head area of ​​the person. By obtaining the regional feature points of the head area of ​​the person, when the projection device obtains the next target image, it can be determined whether the position of the head area has changed based on the identification regional feature points, thereby determining the target processing area of ​​the next target image based on the changed position of the head area, and reducing the brightness of the projection content projected to the target processing area of ​​the next target image under the light emitting component.

[0056] In a second aspect, some embodiments of the present application further provide an anti-eyeballing projection method, which is applied to the projection device described in the first aspect, wherein the projection device includes a light output component configured to project projection content onto a projection surface; a camera configured to capture a target image of the projection surface; and a controller; the method includes:

[0057] When acquiring the target image, marking the pixel points corresponding to the person area in the target image as target pixel points;

[0058] Generate a target circumscribed rectangle according to the image area formed by the target pixel points;

[0059] Determine a first vertex point of the circumscribed rectangle and a second vertex point diagonally opposite the first vertex point, wherein the ordinate of the first vertex point is the minimum height coordinate, and the ordinate of the second vertex point is the maximum height coordinate;

[0060] Calculating the head height of the character area according to the image height of the target image, a preset constant, the minimum height coordinate and the maximum height coordinate, wherein the head height is the product of the height difference calculated between the maximum height coordinate and the minimum height coordinate and the preset constant;

[0061] Determine a head area corresponding to the person area in the target circumscribed rectangle according to the head height;

[0062] The brightness of the projection content projected by the light emitting component onto the head area is reduced.

[0063] It can be seen from the above technical scheme that the present application provides a projection device and an anti-eye projection method. When the projection device acquires a target image, the method marks the pixel points corresponding to the character area in the target image as target pixel points, and generates a target circumscribed rectangle according to the image area formed by the target pixel points, and obtains the minimum height coordinate and the maximum height coordinate according to the first vertex point and the second vertex point of the target circumscribed rectangle, thereby calculating the head height of the character area according to the image height of the target image, a preset constant, the minimum height coordinate and the maximum height coordinate, and determining the head area corresponding to the character area in the target circumscribed rectangle according to the head height, and reducing the brightness of the projection content projected by the light emitting component to the head area. The present application classifies the pixel points in the target image, thereby identifying the head area of ​​the character in the low-resolution target image, and adjusting the brightness of the projection content corresponding to the head area to avoid strong light irradiating the user's face. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0065] Figure 1 A schematic diagram of the projection state of a projection device provided in some embodiments of the present application;

[0066] Figure 2 A schematic diagram of the structure of a projection device provided in some embodiments of the present application;

[0067] Figure 3 A schematic diagram of the optical-mechanical architecture of a projection device provided in some embodiments of the present application;

[0068] Figure 4 A schematic diagram of the optical path of a projection device provided in some embodiments of the present application;

[0069] Figure 5 A schematic diagram of the system framework of a projection device provided in some embodiments of the present application;

[0070] Figure 6 A flowchart of a projection device that performs an anti-eye-shooting projection method provided in some embodiments of the present application;

[0071] Figure 7 A timing diagram of a projection device implementing an anti-eye-shooting projection method provided in some embodiments of the present application;

[0072] Figure 8 A schematic diagram of a projection device capturing a target image provided in some embodiments of the present application;

[0073] Fig. 9 A flowchart of a first embodiment of a projection device marking a target pixel point provided in some embodiments of the present application;

[0074] Fig.10 A flowchart of a second embodiment of a projection device marking target pixels provided in some embodiments of the present application;

[0075] Fig.11 A schematic diagram of the boundary points of the projection device marking area provided in some embodiments of the present application;

[0076] Fig.12 A schematic diagram of a projection device cutting out a head area rectangle provided in some embodiments of the present application;

[0077] Fig.13 A schematic diagram of a projection device providing some embodiments of the present application to reduce the projection brightness in the head area. DETAILED DESCRIPTION

[0078] In order to make the purpose and implementation method of the present application clearer, the exemplary implementation method of the present application will be clearly and completely described below in conjunction with the drawings in the exemplary embodiments of the present application. Obviously, the described exemplary embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0079] It should be noted that the brief description of terms in this application is only for the convenience of understanding the embodiments described below, and is not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their ordinary and common meanings.

[0080] The terms "first", "second", "third", etc. in the specification and claims of this application and the above drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances.

[0081] The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0082] The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0083] The embodiments of the present application can be applied to various types of projection devices. The following will take a projector as an example to explain the projection device and the automatic focusing method.

[0084] A projector is a device that can project images or videos onto a screen. It can be connected to computers, broadcasting networks, the Internet, VCD (Video Compact Disc), DVD (Digital Versatile Disc Recordable), game consoles, DV, etc. through different interfaces to play corresponding video signals. Projectors are widely used in homes, offices, schools, and entertainment venues.

[0085] Figure 1 The figure shows a schematic diagram of the placement of a projection device according to an embodiment of the present application. Figure 2 A schematic diagram of the optical path of a projection device according to an embodiment of the present application is shown.

[0086] In some embodiments, reference Figure 1-2A projection device provided in the present application includes a projection screen 1 and a projection device 2. The projection screen 1 is fixed at a first position, and the projection device 2 is placed at a second position, so that the picture projected by it coincides with the projection screen 1. The projection device includes a laser light source 100, a light output component 200, a lens 300, and a projection surface 400. Among them, the laser light source 100 provides illumination for the light output component 200, the light output component 200 modulates the light source beam, and outputs it to the lens 300 for imaging, and projects it to the projection surface 400 to form a projection picture. Since the laser light source 100, the light output component 200, and the lens 300 are jointly used to emit projection light to project a projection picture, in some embodiments of the present application, the laser light source 100, the light output component 200, and the lens 300 are collectively referred to as a light output component.

[0087] In some embodiments, the laser light source 100 of the projection device includes a laser component and an optical lens component. The light beam emitted by the laser component can pass through the optical lens component to provide lighting for the light output component. For example, the optical lens component requires a higher level of environmental cleanliness and airtightness; while the chamber where the laser component is installed can be sealed with a lower level of dustproofness to reduce the sealing cost.

[0088] In some embodiments, the light emitting assembly 200 of the projection device may be implemented to include a blue light engine, a green light engine, a red light engine, and may also include a heat dissipation system, a circuit control system, etc. It should be noted that in some embodiments, the light emitting component of the projector may also be implemented by an LED light source.

[0089] Figure 3 A schematic diagram of the circuit architecture of a projection device according to an embodiment of the present application is shown. In some embodiments, the projection device may include a display control circuit 10, a laser light source 20, at least one laser driving component 30, and at least one brightness sensor 40. The laser light source 20 may include at least one laser corresponding to the at least one laser driving component 30. The at least one refers to one or more, and the multiple refers to two or more.

[0090] Based on the circuit architecture, the projection device can achieve adaptive adjustment. For example, by setting a brightness sensor 40 in the light output path of the laser light source 20, the brightness sensor 40 can detect a first brightness value of the laser light source and send the first brightness value to the display control circuit 10.

[0091] The display control circuit 10 can obtain the second brightness value corresponding to the driving current of each laser, and when it is determined that the difference between the second brightness value of the laser and the first brightness value of the laser is greater than the difference threshold, it is determined that a COD fault occurs in the laser; the display control circuit can adjust the current control signal of the laser driving component corresponding to the laser until the difference is less than or equal to the difference threshold, thereby eliminating the COD fault of the blue laser; the projection device can eliminate the COD fault of the laser in time, reduce the damage rate of the laser, and improve the image display effect of the projection device.

[0092] Figure 4 A schematic structural diagram of a projection device according to an embodiment of the present application is shown.

[0093] In some embodiments, the laser light source 20 in the projection device may include independently arranged blue laser 201, red laser 202 and green laser 203. The projection device may also be called a three-color projection device. The blue laser 201, the red laser 202 and the green laser 203 are all modular lightweight (Mirai Console Loader, MCL) packaged lasers, which are small in size and conducive to the compact arrangement of the optical path.

[0094] In some embodiments, the controller includes at least one of a central processing unit (CPU), a video processor, an audio processor, a graphics processing unit (GPU), a RAM Random Access Memory (RAM), a ROM (Read-Only Memory, ROM), a first interface to an nth interface for input / output, a communication bus (Bus), etc.

[0095] In some embodiments, the projection device may be configured with a camera for cooperating with the projection device to achieve adjustment and control of the projection process. For example, the camera configured with the projection device may be specifically implemented as a 3D camera or a binocular camera; when the camera is implemented as a binocular camera, it specifically includes a left camera and a right camera; the binocular camera may obtain the image and playback content presented by the screen corresponding to the projection device, that is, the projection surface, and the image or playback content is projected by the light emitting component built into the projection device.

[0096] When the projection device moves, its projection angle and distance to the projection surface change, causing the projected image to deform. The projected image will appear as a trapezoidal image or other deformed image. The projection device controller can achieve automatic trapezoidal correction based on the image captured by the camera by coupling the angle between the projection surfaces and the correct display of the projection image.

[0097] Figure 5A schematic diagram of a system framework for realizing display control of a projection device according to an embodiment of the present application is shown.

[0098] In some embodiments, the projection device has the characteristics of a telephoto micro-projector, and its controller can control the display of the projection light image through a preset algorithm to achieve functions such as automatic trapezoidal correction of the display screen, automatic screen entry, automatic obstacle avoidance, automatic focusing, and anti-eye-shooting.

[0099] In some embodiments, the projection device is configured with a gyroscope sensor; when the device is moving, the gyroscope sensor can sense the position movement and actively collect displacement signals; the collected data is then sent to the application service layer through the system framework layer to support the application data required during user interface interaction and application interaction. The collected data can also be used for data calls by the controller in the algorithm service implementation.

[0100] In some embodiments, the projection device is configured with a time-of-flight sensor. After the time-of-flight sensor collects corresponding data, the data will be sent to the corresponding time-of-flight service of the service layer; after the above-mentioned time-of-flight service obtains the data, it will send the collected data to the application service layer through the process communication framework, and the data will be used for interactive use such as controller data calls, user interfaces, and program applications.

[0101] In some embodiments, the projection device is configured with a camera for capturing images, and the camera can be implemented as a binocular camera, a depth camera, a 3D camera, etc.; the camera capture data will be sent to the camera service, and then the camera service will send the captured target image to the process communication framework, and / or the projection device correction service; the projection device correction service can receive the camera capture data sent by the camera service, and the controller can call the corresponding control algorithm in the algorithm library according to the different functions to be implemented.

[0102] In some embodiments, data is interacted with the application service through a process communication framework, and then the calculation results are fed back to the correction service through the process communication framework; the correction service sends the obtained calculation results to the projection device operating system to generate control signals, and sends the control signals to the light emitting component control driver to control the working condition of the light emitting component and realize automatic correction of the displayed image.

[0103] In some embodiments, the projection device can project a large screen image at a longer distance so that the user can view a clearer picture. When the projection device is working, it can convert the received digital image information into light signals. These light signals carry the image information to be displayed. The projection device can convert the light signals into light sources and project them into the projection area to display the received digital image, i.e., the projection screen, in the projection area. The digital image can be a single-frame fixed image or one frame of a video media asset. Different digital images can be projected according to the changes in the video frames uploaded in real time by the video media asset.

[0104] The projection surface 400 may be the projection area in the above embodiment, and the projection surface 400 may be a plane area such as a wall or a screen that can present a projection image. For this reason, the projection surface 400 may be used as the projection area. Since the projection area is illuminated by the light source emitted by the projection device, when the user enters the projection area and faces the projection device, the light source will directly shine into the user's eyes, causing damage to the user's vision.

[0105] In order to improve the safety of the projection device to the user's eyesight, the projection device can be equipped with an anti-glare function, and the projection device can collect the target image of the projection area in real time through the camera. When the user enters the projection area, the projection device can identify the head area of ​​the person area in the target image, thereby reducing the brightness of the light source in the head area, reducing the impact of strong light on the user's eyesight, and protecting the user's eyesight.

[0106] The projection device needs to use specific recognition algorithms to recognize the user's head area, such as machine learning algorithms, deep learning target detection or segmentation algorithms, or template matching algorithms, etc. These algorithms need to be based on the clear and obvious head features of the person in the target image for recognition. To this end, the cameras of these projection devices with anti-glare functions include high-resolution image sensors that can obtain high-resolution target images to meet the recognition algorithm's requirements for performing recognition based on clear head features.

[0107] For low-end projection devices, the cameras configured in these projection devices are not equipped with high-resolution sensors. Therefore, the projection devices cannot identify clear human head features in the target images captured by the low-resolution cameras. This causes the low-end projection devices to be unable to determine the user's head area through specific recognition algorithms, and thus are unable to apply the anti-glare function.

[0108] In order to solve the problem that low-resolution projection devices cannot apply the anti-eye function when the user enters the projection area, some embodiments of the present application provide a projection device, wherein the projection device includes a light output component 200, a camera and a controller, wherein the light output component 200 is configured to project projection content onto a projection surface 400, wherein the area corresponding to the projection surface 400 can be referred to as a projection area, and the camera is configured to capture a target image projected onto the projection surface 200. Figure 6 A flowchart of a projection device performing an anti-eye-shooting projection method provided in an embodiment of the present application. Figure 7 The timing diagram of the projection device according to the embodiment of the present application performing the anti-eye projection method. Figure 7 The timing relationships shown implement the anti-eye projection method. Figure 6 and Figure 7 , the controller is configured to:

[0109] S100: When acquiring the target image, mark the pixel points corresponding to the person area in the target image as target pixel points.

[0110] In order to determine whether there is a person entering the projection area, the projection device can use the camera to capture the target image of the projection surface after it is turned on. The target image is not the target image corresponding to the projection screen, but the target image obtained by shooting and capturing the projection area. When no user enters the projection area, the image content in the target image should be the same as the projection content. At this time, the projection device does not need to apply the anti-eye function. Figure 8 As shown, when a user enters the projection area, the user should be located between the projection device and the projection surface 400 and block the light beam emitted by the light output component 200. At this time, in the target image obtained by the projection device, since part of the light beam is blocked by the user, the pixel points corresponding to the blocked light beam are obviously different from the pixel points projected onto the projection surface 400. Figure 8 In the target image, each grid in the array represents a pixel, where the pixel marked as 0 is the pixel corresponding to the projection image, and the other pixel points marked with the number other than 0 are used to represent the pixel points collected after being blocked by the user.

[0111] In order to distinguish the pixels of the target image projected onto the projection surface 400 from the pixels of the target image projected onto the user, the present embodiment may mark the pixels corresponding to the character area in the target image as target pixels. It is understandable that the user may adjust the interval length of the camera collecting the target image corresponding to the projection area in the setting menu of the projection device in advance. For example, the camera may obtain the target image once every 1 second or once every 5 seconds. In this way, the projection device may automatically control the camera to collect the target image of the projection area according to the interval length preset by the user after it is turned on.

[0112] Each time the target image of the projection area is captured, the controller can identify the pixel points corresponding to the character area in the target image, and mark these pixel points to obtain the target pixel points. In order to improve the accuracy of identifying the target pixel points, the projection device can identify the target pixel points in at least two ways. The following two embodiments illustrate the methods of identifying the target pixel points.

[0113] Embodiment 1:

[0114] The projection device can respond to the power-on instruction and control the camera to capture a reference image after powering on. The reference image is an image captured by the camera when the projection device is not projecting the projection content. It should be noted that when capturing the reference image, it should be ensured that there are no objects blocking the projection surface 400 in the projection area. To this end, the projection device can perform object detection on the projection area when capturing the reference image. If an object blocking the projection surface 400 is detected in the projection area, a prompt message can be generated to prompt the user to move the object out of the projection area.

[0115] The reference image includes reference pixels, and the projection device can obtain the initial distance value between the camera and the projection surface 400 based on these reference pixels, that is, when there is no obstruction, the distance value of the pixel points corresponding to the projection picture projected by the projection device should be the initial distance value.

[0116] However, when the user enters the projection area, the projection image projected by the projection device will be blocked by the user, resulting in the distance value of the blocked pixel point in the target image being smaller than the initial distance value. Based on the above scenario, the projection device can set a determination threshold for determining the target pixel point. Fig. 9 As shown, the projection device can calculate the difference between the initial distance value and the distance value of the pixel in the target image each time the target image of the projection area is collected. When the difference is greater than the determination threshold, it means that there are pixels in the target image that are blocked by the user, which causes the distance value of the pixel to become smaller, so that the difference between the initial distance value and the distance value of the pixel in the target image increases and exceeds the determination threshold. Therefore, in the target image, the pixel whose difference is greater than the determination threshold can be marked as the target pixel.

[0117] In another implementation of Example 1, the target pixel point can also be determined by comparing the size of the pixel value. It should be understood that when a pixel point is blocked by the user, the position displayed by the pixel point is closer to the light emitting component 200 relative to the projection surface 400. For this reason, the pixel value of the pixel point will increase due to the reduction in the projection distance. Based on the above scenario, the controller can also obtain the initial pixel value of each pixel point in the reference image, and calculate the difference between the pixel value of the target image obtained in real time and the initial pixel value. If the difference is greater than the pixel value threshold, the pixel point is marked as a target pixel point.

[0118] Embodiment 2:

[0119] The projection device can also identify target pixels in the target image in the form of a convolutional neural network. To this end, when the controller acquires the target image through the camera, it can input the target image into the convolutional neural network. The convolutional neural network may include an encoder and a decoder, wherein the encoder is used to perform encoding on the target image to obtain the target image encoding. Fig.10 As shown, the encoder may include a plurality of hierarchical structures formed by convolution operation modules to perform encoding operations on the target image layer by layer. For example, when the encoder includes a first convolution operation module, a second convolution operation module, and a third convolution operation module, after the target image is input into the encoder, the first convolution operation module will perform the first encoding on the target image to extract the pixel features in the target image through encoding and output the first encoding result. The first encoding result output by the first convolution operation module is then input into the second convolution operation module to extract the pixel features again and output the second encoding result. The second encoding result is then input into the third convolution operation module to complete the encoding and output the target image encoding.

[0120] In some embodiments, the convolution operation module may include a convolution operation unit, a linear integration unit, a depth-separable convolution operation, a linear integration unit and a convolution operation unit in sequence. When the convolution operation module performs encoding on the target image, the operations may be performed in sequence according to the above unit structure.

[0121] After the encoding is completed, the output target image code can be input into the decoder corresponding to the encoder for decoding to obtain the image decoding result. Fig.10 The decoder includes a plurality of hierarchical structures formed by transposed convolution operation modules. During the decoding process, the target image encoding can be directly decoded through the transposed convolution operation module. During the encoding process, the encoding result output by the convolution operation module can be added to the input of the next convolution operation module through matrix addition, and then input into the transposed convolution operation module for decoding.

[0122] In some embodiments, the convolution operation module may include a transposed convolution operation unit, a linear integration unit, a depth-separable convolution operation, a linear integration unit and a convolution operation unit in sequence. When the transposed convolution operation module performs encoding on the target image, the operations may be performed in sequence according to the above unit structure.

[0123] Exemplarily, when the projection device performs a convolution operation, the output image output may be an array matrix consisting of i rows and j columns, and the input image input may be an array matrix consisting of m rows and n columns and a convolution kernel kernel. Therefore, the output image may be expressed as follows:

[0124] output(i,j)=∑ M ∑ N input(m,n)×kernel(im,jn);

[0125] For the linear integration unit, it means that all the pixels in the intermediate operation matrix undergo a nonlinear calculation. For the linear integration unit, its nonlinear function is:

[0126] f(x)=max(0,x);

[0127] Among them, x is the pixel value corresponding to the input pixel point.

[0128] In some embodiments, other nonlinear functions may be used instead of the linear integration unit, such as a sigmoid function, a tanh function, etc.

[0129] In some embodiments, the convolution operation module is sequentially executed by convolution calculation, linear integration unit, depth-separable convolution operation, linear integration unit, and convolution operation, and the calculation process is regarded as a process of encoding or decoding the input image into abstract features.

[0130] In some embodiments, the convolutional neural network needs to predict the binary classification results of each pixel in the target image. Based on the above scenario, the convolutional neural network in this embodiment can be a neural network that has not been trained, or a neural network that has been pre-trained with sample images of the same resolution and including target pixels and non-target pixels. For the neural network participating in the training, the training loss can be obtained by cross entropy calculation, that is:

[0131]

[0132] In the above formula, a is the resolution of the sample image, b is used to determine the resolution of the label corresponding to the image result, and σ is the Sigmoid function:

[0133] The final trained convolutional neural network model will make the output i*j matrix value between 0 and 1 in the cross entropy calculation involving the Sigmoid function. At this time, a threshold can be set to change the final output matrix of the convolutional neural network into a distribution of 0 and 1. For example, when the output is 1, the binary classification result is the first classification result, and the pixel point is the target pixel point. When the output is 0, the binary classification result is the second classification result, and the pixel point is a non-target pixel point. The binary classification result is the probability result of the pixel point of the image decoding result being the target pixel point or the probability result of the pixel point being a non-target pixel point.

[0134] S200: Generate a target circumscribed rectangle according to the image area formed by the target pixels.

[0135] After identifying the target pixels in the target image, the image area formed by the target pixels is the person area. Therefore, the projection device needs to identify the head area in the person area to reduce the projection brightness of the head area. However, in the scenario of using a low-resolution camera, the projection device cannot perform recognition on the head area through the recognition algorithm. Therefore, after acquiring the target image, the projection device generates a target bounding rectangle in the graphic area formed by the target pixels, and the target bounding rectangle includes all the target pixels.

[0136] In some embodiments, the projection device needs to determine the region boundary points of the image region formed by the target pixel points. To facilitate the determination of the region boundary points, the projection device may mark the pixel points in the target image according to the target pixel points and the non-target pixel points, for example, Fig.10 As shown, the projection device can mark the target pixel in the target image as 1 and the non-target pixel as 0. The region boundary point is the target pixel that forms the boundary of the character region. Therefore, the region boundary point should be adjacent to both the target pixel and the non-target pixel. For this purpose, the projection device can traverse the adjacent pixels of the target pixel. If all the adjacent pixels of the target pixel are target pixels, it means that the target pixel is located at the center of the character region and is not a target pixel that forms the region boundary.

[0137] If the neighboring pixels of the target pixel include at least one non-target pixel, it means that the target pixel is a target pixel forming a region boundary, and the projection device can mark the target pixel as a region boundary point. Fig.11 , Fig.11, the pixel points in the shaded part are the region boundary points. The projection device can use the first traversed region boundary point as the boundary starting point. After obtaining the boundary starting point, the projection device takes the boundary starting point as the center point, traverses the adjacent pixel points of the boundary starting point, and uses the first adjacent pixel point obtained through the traversal as the next target pixel point to be detected, and repeats the detection process of the adjacent pixel points containing at least one non-target pixel point for the target pixel point, until all the region boundary points in the target circumscribed rectangle are obtained.

[0138] After acquiring the region boundary points, the projection device can connect all the region boundary points. In the process of connecting the region boundary points, the projection device can determine the region boundary point that is currently closest to the region boundary point to be connected, thereby sequentially connecting the adjacent region boundary points. After the connection is completed, the region boundary points and other target pixel points located inside the region formed by the region boundary points together form an image region.

[0139] In some embodiments, the projection area may also include multiple image areas, that is, there are at least two users entering the projection area. Taking two users entering the projection area as an example, at this time, the target image acquired by the projection device may include two closed image areas. Therefore, the projection device may generate a target bounding rectangle based on two different image areas, that is, generate a first target bounding rectangle for the first image area, and generate a second target bounding rectangle for the second image area. The area boundary points of the first image area and the area boundary points of the second image area can be expressed as:

[0140] {[(x 1 ,y 1 ),(x 2 ,y 2 ),(x 3 ,y 3 )……(x n ,y n )],[(x 1 ,y 1 ),(x 2 ,y 2 ),(x 3 ,y 3 )……(x m ,y m )]};

[0141] Among them, [(x 1 ,y 1 ),(x 2 ,y 2 ),(x 3 ,y 3 )……(x n ,y n)] is the region boundary point in the first image region, [(x 1 ,y 1 ),(x 2 ,y 2 ),(x 3 ,y 3 )……(x m ,y m )] is the region boundary point in the second image region.

[0142] S300: Determine a first vertex point of the target circumscribed rectangle and a second vertex point diagonally opposite to the first vertex point.

[0143] In the process of generating the target circumscribed rectangle, the projection device can traverse the maximum horizontal coordinate, the minimum horizontal coordinate, the maximum vertical coordinate and the minimum vertical coordinate of all target pixel points in the image area, and then determine the first vertex point according to the maximum horizontal coordinate and the minimum vertical coordinate, and determine the second vertex point according to the minimum horizontal coordinate and the maximum vertical coordinate, and the second vertex point is the diagonal point of the first vertex point. The vertical coordinate of the first vertex point is the minimum height coordinate, and the vertical coordinate of the second vertex point is the maximum height coordinate, so that the target circumscribed rectangle is generated with the first vertex point and the second vertex point as the two vertices of the target circumscribed rectangle.

[0144] In some embodiments, the order of determining the first vertex point and the second vertex point can be reversed. For example, the first vertex point is determined based on the minimum horizontal coordinate and the maximum vertical coordinate, and the second vertex point is determined based on the maximum horizontal coordinate and the minimum vertical coordinate. At this time, the vertical coordinate of the first vertex point is the maximum height coordinate, and the vertical coordinate of the second vertex point is the minimum height coordinate.

[0145] This embodiment is illustratively described by taking the ordinate of the first vertex point as the minimum height coordinate and the ordinate of the second vertex point as the maximum height coordinate as an example.

[0146] S400: Calculating the head height of the character area according to the image height of the target image, a preset constant, the minimum height coordinate and the maximum height coordinate.

[0147] The head height is the product of the height difference between the maximum height coordinate and the minimum height coordinate and a preset constant. In the process of calculating the head height, the projection data can obtain the image height and the preset constant of the target image, where the preset constant can include a natural constant and a preset constant, and the preset constant is a preset constant, for example, 0.5. After obtaining the image height and the preset constant, the head height in the target image can be calculated by combining the minimum height coordinate and the maximum height coordinate using the following formula:

[0148]

[0149] Among them, headh is the height of the head area in the target image, that is, the head height, K is a preset constant, y 2 is the maximum height coordinate, y 1 is the minimum height coordinate, e is a natural constant, and H is the image height.

[0150] In the above formula, the projection device can calculate the height difference between the maximum height coordinate and the minimum height coordinate, and calculate the height ratio between the height difference and the image height, so as to normalize the height of the target bounding rectangle to 0-1. Then, the height ratio is used as input to the hyperbolic tangent function, that is, Since the height of the target bounding rectangle is normalized to 0-1, it can be ensured that when x∈[0,1], this function takes the value [0,0.76], which is a proportional function. In the hyperbolic tangent function, the height ratio is used as the exponent of the natural constant e. Finally, the product of the height difference, the preset constant, and the hyperbolic tangent function with the height ratio as the exponent of the natural constant is calculated to obtain the head height.

[0151] S500: Determine a head region corresponding to the person region in the target circumscribed rectangle according to the head height.

[0152] In order to reduce the interference of the image area outside the head area on the acquisition of the head area, the projection device can perform cropping based on the image area outside the head area. To this end, the projection device can calculate the difference between the image height and the head height to determine the height of the area to be cropped, and the area to be cropped is the other image area outside the head area.

[0153] After determining the height to be cut, Fig.12 As shown, the target circumscribed rectangle can be cropped according to the area to be cropped, and the rectangular area outside the head area, such as the rectangle of the torso and leg area, can be removed to obtain the remaining rectangle after cropping, wherein the head area of ​​the user entering the projection area is inside the remaining rectangle. The projection device can traverse the target pixel points in the remaining rectangle. Since the target pixel points form the pixel points of the character area, after cropping the area outside the head area, the target pixel points in the remaining rectangle are the target pixel points that form the head area, and the projection device can mark the target pixel points in the remaining rectangle as the head area.

[0154] In some embodiments, in order to improve the accuracy of obtaining the head region, the projection device can also identify the regional boundary points of the head region in the remaining rectangle, that is, traverse the adjacent pixel points of the target pixel point in the remaining rectangle. When at least one adjacent pixel point is a non-target pixel point, the target pixel point is the regional pixel point of the head region. After determining the regional pixel point, the projection device can also generate a circumscribed rectangle for the regional pixel point again, that is, a head circumscribed rectangle, so as to determine the head region according to the head circumscribed rectangle.

[0155] S600: reducing the brightness of the projection content projected by the light emitting component onto the head area.

[0156] like Fig.13 As shown, after determining the head area, the projection device can reduce the brightness of the projection content projected by the light emitting component to the head area, so that when the user enters the projection area, the impact of strong light on the user's vision can be reduced. Since the size of the head area in the target image is different from the size actually projected by the projection device, the projection device needs to convert the head area into the area actually projected by the projection device after obtaining the head area of ​​the target image. To this end, in some embodiments, the projection device can obtain the image size of the head area in the target image, and then obtain the mapping relationship between the light emitting component 200 and the camera calibration, so that according to the mapping relationship, the image size of the target image captured by the camera is mapped to the area size of the light emitting component 200 to obtain the target processing area, which is the projection area where the head area in the target image captured by the camera is mapped to the corresponding position projected by the light emitting component 200. The projection device thus reduces the brightness of the projection content projected by the light emitting component 200 to the target processing area, reducing the impact on the user's vision.

[0157] In some embodiments, if the user keeps moving in the projection area, the head area will also keep moving accordingly. Therefore, if the projection device reduces the brightness of the projection content of the user in the target processing area, when the user moves, the strong light in other projection areas outside the current target processing area will still damage the user's eyesight. To this end, after determining the target processing area, the projection device extracts the regional feature points of the target processing area, thereby obtaining the head features of the user entering the projection area. After determining the regional feature points, when the projection device obtains the next target image of the current target image through the camera, it identifies the regional feature points in the next target image, thereby determining the position of the user's head area in the next target image, that is, the target processing area. If the position of the target processing area of ​​the next target image is the same as the position where the projection device first obtains the target processing area, it means that the user has not moved during the time interval for obtaining the target image, so there is no need to change the position of reducing the brightness of the projection content.

[0158] If the target processing area position of the next target image is different from the position where the projection device first acquires the target processing area, it means that the user has moved to other positions during the time interval for acquiring the target image. Therefore, it is necessary to reduce the brightness of the projected content according to the user's movement trajectory and the target processing area as the trajectory width, so as to follow the user's head area according to the user's movement path, so as to protect the user's eyesight in real time when moving in the projection area.

[0159] In some embodiments, the projection device may also use a target tracking algorithm to determine the position of the user in the projection area. The target tracking algorithm refers to an algorithm that determines the head area based on the head area coordinates of the data for continuous target images. The target tracking algorithm may be an IoU tracking algorithm, or a trained Deep-SORT tracking algorithm, etc.

[0160] Some embodiments of the present application also provide an anti-eyeballing projection method, which is applied to a projection device. To facilitate the execution of the method, the projection device should at least include a light emitting component 200, which is configured to project projection content onto a projection surface; a machine, which is configured to collect a target image of the projection surface; and a controller. The method includes:

[0161] S100: When acquiring the target image, mark the pixel points corresponding to the person area in the target image as target pixel points.

[0162] S200: Generate a target circumscribed rectangle according to the image area formed by the target pixels.

[0163] S300: Determine a first vertex point of the circumscribed rectangle and a second vertex point diagonally opposite to the first vertex point, wherein the ordinate of the first vertex point is the minimum height coordinate, and the ordinate of the second vertex point is the maximum height coordinate.

[0164] S400: Calculating the head height of the character area according to the image height of the target image, a preset constant, the minimum height coordinate and the maximum height coordinate.

[0165] The head height is the product of the height difference between the maximum height coordinate and the minimum height coordinate and a preset constant.

[0166] S500: Determine a head region corresponding to the person region in the target circumscribed rectangle according to the head height.

[0167] S600: reducing the brightness of the projection content projected by the light emitting component onto the head area.

[0168] The present application provides a projection device and an anti-eyeballing projection method. When the projection device acquires a target image, the method marks the pixel points corresponding to the character area in the target image as target pixel points, generates a target circumscribed rectangle according to the image area formed by the target pixel points, acquires the minimum height coordinate and the maximum height coordinate according to the first vertex point and the second vertex point of the target circumscribed rectangle, thereby calculating the head height of the character area according to the image height of the target image, a preset constant, the minimum height coordinate and the maximum height coordinate, determines the head area corresponding to the character area in the target circumscribed rectangle according to the head height, reduces the brightness of the projection content projected by the light emitting component to the head area. The present application classifies the pixel points in the target image, thereby identifying the head area of ​​the character in the low-resolution target image, thereby adjusting the brightness of the projection content corresponding to the head area to avoid strong light irradiating the user's face.

[0169] Similar parts between the embodiments provided in this application can be referenced to each other. The specific implementation methods provided above are only a few examples under the general concept of this application and do not constitute a limitation on the protection scope of this application. For those skilled in the art, any other implementation methods expanded based on the scheme of this application without creative work belong to the protection scope of this application.

Claims

1. A projection device, characterized in that: include: A light emitting component is configured to project projection content onto a projection surface; A camera configured to capture a target image of the projection surface; The controller is configured as: When acquiring the target image, marking the pixel points corresponding to the person area in the target image as target pixel points; Generate a target circumscribed rectangle according to the image area formed by the target pixel points; Determine a first vertex point of the target circumscribed rectangle and a second vertex point diagonally opposite the first vertex point, wherein the ordinate of the first vertex point is the minimum height coordinate, and the ordinate of the second vertex point is the maximum height coordinate; Calculating the head height of the character area according to the image height of the target image, a preset constant, the minimum height coordinate and the maximum height coordinate, wherein the head height is the product of the height difference calculated between the maximum height coordinate and the minimum height coordinate and the preset constant; Determine a head area corresponding to the person area in the target circumscribed rectangle according to the head height; The brightness of the projection content projected by the light emitting component onto the head area is reduced.

2. The projection device according to claim 1, characterized in that: The controller performs the step of marking the pixel points corresponding to the person area in the target image as target pixel points, and is specifically configured as follows: In response to a power-on instruction, controlling the camera to capture a reference image; Acquire reference pixel points in the reference image; According to the reference pixel point, obtaining an initial distance value representing the distance between the camera and the projection surface; If the difference between the initial distance value and the distance value of a pixel point in the target image is greater than the determination threshold, the pixel point is marked as a target pixel point.

3. The projection device according to claim 1, characterized in that: The controller performs the step of marking the pixel points corresponding to the person area in the target image as target pixel points, and is specifically configured as follows: Performing encoding on the target image by the encoder to obtain target image encoding; Input the target image code into the decoder corresponding to the encoder for decoding to obtain an image decoding result; The pixel points whose binary classification results in the image decoding result are the same as the preset classification results are marked as target pixel points, and the binary classification results are the probability results that the pixel points of the image decoding result are the target pixel points or the probability results that the pixel points of the image decoding result are the non-target pixel points.

4. The projection device according to claim 1, characterized in that: Before the step of generating a target circumscribed rectangle according to the image area formed by the target pixel points, the controller is further configured to: Obtaining a region boundary point in the target pixel point; Adjacent region boundary points are connected in sequence to obtain the image region.

5. The projection device according to claim 4, characterized in that: The controller performs the step of acquiring the region boundary point in the target pixel point, and is specifically configured as follows: Traversing the pixel points adjacent to the target pixel point; If the adjacent pixel points include at least one non-target pixel point, the target pixel point is marked as a region boundary point.

6. The projection device according to claim 1, characterized in that: The preset constant includes a target constant and a natural constant, and the controller performs the step of calculating the head height of the character area according to the image height of the target image, the preset constant, the minimum height coordinate, and the maximum height coordinate, and is specifically configured as follows: Calculate the height difference between the maximum height coordinate and the minimum height coordinate; Calculate the height ratio of the height difference value to the image height; The height of the head is obtained by calculating the product of the height difference, the target constant and a hyperbolic tangent function with the height ratio as the exponent of the natural constant.

7. The projection device according to claim 1, characterized in that: The controller performs the step of determining the head area corresponding to the person area in the target circumscribed rectangle according to the head height, and is specifically configured as follows: Calculate the difference between the image height and the head height to determine the height of the area to be cropped; According to the height of the area to be cropped, cropping is performed on the target circumscribed rectangle to obtain a remaining rectangle after cropping; The target pixel points in the remaining rectangle are marked as the head area.

8. The projection device according to claim 1, characterized in that: The controller performs the step of reducing the brightness of the projection content projected by the light emitting component to the head area, and is specifically configured as follows: Obtaining the image size of the head area in the target image; According to the mapping relationship between the light emitting component and the camera calibration, the image size is mapped to the area size of the light emitting component to obtain a target processing area; The brightness of the projection content projected by the light emitting component onto the target processing area is reduced.

9. The projection device according to claim 8, characterized in that: After the controller executes the step of reducing the brightness of the projection content projected by the light emitting component onto the head area, the controller is further configured to: Extracting regional feature points of the target processing area; Obtaining a target processing region of a next target image by identifying the regional feature points in a next target image of the current target image; The brightness of the projection content of the light emitting component projected onto the target processing area of ​​the next target image is reduced.

10. An anti-eye projection method, characterized in that: The projection device as claimed in any one of claims 1 to 9, wherein the projection device comprises a light emitting component configured to project projection content onto a projection surface; A camera configured to capture a target image of the projection surface; Controller; the method comprising: When acquiring the target image, marking the pixel points corresponding to the person area in the target image as target pixel points; Generate a target circumscribed rectangle according to the image area formed by the target pixel points; Determine a first vertex point of the circumscribed rectangle and a second vertex point diagonally opposite the first vertex point, wherein the ordinate of the first vertex point is the minimum height coordinate, and the ordinate of the second vertex point is the maximum height coordinate; Calculating the head height of the character area according to the image height of the target image, a preset constant, the minimum height coordinate and the maximum height coordinate, wherein the head height is the product of the height difference calculated between the maximum height coordinate and the minimum height coordinate and the preset constant; Determine a head area corresponding to the person area in the target circumscribed rectangle according to the head height; The brightness of the projection content projected by the light emitting component onto the head area is reduced.

Images