Pet display system and pet display method

Abstract

This invention proposes a pet display system and a pet display method. The system includes a display panel and a computing circuit. The computing circuit receives an input image and determines whether the system is in pet mode. If not in pet mode, the computing circuit transmits the input image to the display panel for display. If in pet mode, the computing circuit reduces the red component of the input image to obtain a converted image, and transmits the converted image to the display panel for display.

Description

Technical Field

[0001] This disclosure relates to a display system and display method suitable for pet vision. Prior Technology

[0002] With changes in social structure and family patterns, pets are playing an increasingly important role in modern families and are gradually being regarded as family members. Many pet owners not only focus on their pets' health and nutrition, but also value their emotional needs and quality of life. As a result, more and more products and services related to pet interaction have emerged, ranging from food and toys to wearable devices, audio-visual content, and interactive devices, all aimed at improving pet welfare and the human-pet interaction experience.

[0003] However, existing display devices (such as televisions, tablets, and mobile phone screens) are designed for color and brightness based on human visual characteristics, without considering the differences in visual perception between common pets such as dogs and cats. Research shows that the color vision systems of animals like dogs and cats differ from those of humans. The content presented on traditional display devices may not provide clear or attractive visual stimulation for pets, thus reducing their engagement and interest in interaction. Summary of the Invention

[0004] This disclosure proposes a pet display system, comprising a display panel and a computing circuit. The computing circuit receives an input image and determines whether it is in pet mode. If not in pet mode, the computing circuit transmits the input image to the display panel for display. If in pet mode, the computing circuit reduces the red component of the input image to obtain a converted image, and transmits the converted image to the display panel for display.

[0005] In one embodiment of this disclosure, the above-described computing circuit is used to calculate multiple values ​​of the input image in the L*a*b* color space and reduce the value in the a* channel.

[0006] In one embodiment of this disclosure, the above-described calculation circuit is used to calculate the value of the b* channel.

[0007] In one embodiment of this disclosure, the above-described calculation circuit is used to multiply the values ​​in the L*a*b* color space by a transformation matrix, thereby reducing the values ​​in the a* channel and increasing the values ​​in the b* channel.

[0008] In one embodiment of this disclosure, the input image contains multiple pixels, each containing a corresponding numerical value. The computing circuit groups these pixels to obtain multiple groups, obtains representative pixels of the first group, multiplies the numerical value contained in the representative pixel by a transformation matrix to obtain multiple transformed numerical values, and replaces the pixels of the first group with the transformed numerical values.

[0009] In one embodiment of this disclosure, the pet display system further includes an image capturing device for acquiring multiple pet images. The computing circuit calculates the gaze time based on the pet images and determines the transformation matrix based on the gaze time.

[0010] In one embodiment of this disclosure, a computing circuit obtains a set of preset variables for the transformation matrix and sets multiple sets of perturbation variables. The computing circuit adds each set of perturbation variables to the preset variables to generate multiple sets of test variables, and applies each set of test variables to the input image to obtain the corresponding gaze duration. The computing circuit adjusts the preset variables according to the gaze duration.

[0011] In one embodiment of this disclosure, the above-described computing circuit is used to set a reward positively correlated with gaze time and adjust a preset variable according to the following mathematical formula.

[0012] in For preset variables, Where is the learning rate and N is the number of perturbation variables. To correspond to the standard deviation of the disturbance variable, Let i be the group of disturbance variables. This represents the reward corresponding to the i-th group of perturbation variables.

[0013] In one embodiment of this disclosure, the above-described computing circuit is used to set a reward according to the following mathematical formula, wherein Let T be the gaze duration corresponding to the i-th test variable, where T is a real number.

[0014] In one embodiment of this disclosure, the pet display system further includes an image capturing device and an interactive device. The image capturing device acquires a pet image. The interactive device is electrically connected to a computing circuit. The computing circuit determines whether the pet image belongs to a preset category; if so, it activates the interactive device.

[0015] From another perspective, embodiments of the present invention propose a pet display method executed by a computing circuit. This pet display method includes: receiving an input image; determining whether the device is in pet mode; if not in pet mode, transmitting the input image to a display panel for display; and if in pet mode, reducing the red component of the input image to obtain a converted image, and transmitting the converted image to the display panel for display.

[0016] To make the above features and advantages of the present invention more apparent and understandable, specific embodiments are described below in conjunction with the accompanying drawings for detailed explanation. Simple Explanation of the Diagram

[0017] Figure 1 is a schematic diagram illustrating a pet display system according to one embodiment. Figure 2 is a block diagram illustrating a pet display system according to one embodiment. Figure 3 is a flowchart illustrating a pet display method according to one embodiment. Figure 4 is an example diagram illustrating the transformation of an input image according to one embodiment. Implementation

[0018] Some embodiments of the present invention will now be described in detail with reference to the accompanying drawings. Component symbols used in the following description are considered identical or similar when they appear in different drawings. These embodiments are only a part of the present invention and do not disclose all possible implementations of the invention. More precisely, these embodiments are merely examples of systems and methods within the scope of the present invention's patent application.

[0019] The terms "first," "second," etc., used in this article do not specifically refer to order or sequence; they are merely used to distinguish elements or operations described using the same technical terms.

[0020] Figure 1 is a schematic diagram illustrating a pet display system according to one embodiment. Referring to Figure 1, the pet display system includes a display device 110, an image capturing device 120, and an interactive device 130. This scenario applies to a pet 140, which in this example is a dog, but in other embodiments it could be a cat, bird, or other animal.

[0021] Display device 110 has multiple modes, one of which is called pet mode. In other modes (such as normal mode, movie mode, game mode, etc.), the images displayed by display device 110 are primarily for human viewing, and therefore the colors presented conform to human vision. However, in pet mode, the images displayed by display device 110 are primarily for the pet 140 to view, and therefore the colors presented conform to the pet 140's vision. For example, dogs primarily perceive colors including blue and yellow, but have a weaker ability to distinguish red. Therefore, in pet mode, the red component can be reduced, thereby allowing the pet 140 to distinguish the content displayed by display device 110. Interactive device 130 and electronic device 150 will be described in the following paragraphs.

[0022] Figure 2 is a block diagram illustrating a pet display system according to one embodiment. Referring to Figure 2, the pet display system 200 includes a computing circuit 210, a display panel 220, an image capturing device 120, and an interactive device 130. In this embodiment, the computing circuit 210 and the display panel 220 are integrated into a single display device 110, but in other embodiments, the computing circuit 210 may be another device (e.g., a television box). In this embodiment, the image capturing device 120 and the display device 110 are different devices, but in other embodiments, the image capturing device 120 may be integrated with the display device 110.

[0023] The computing circuit 210 may include a central processing unit, microprocessor, microcontroller, image processing chip, deep-learning processing unit (DPU), neural network processing unit (NPU), tensor processing unit (TPU), application-specific integrated circuits (ASIC), or programmable logic device (PLD). In this embodiment, the computing circuit 210 is a time controller in the display device 110, but in other embodiments it may be other circuits with computing capabilities. The display panel 220 may be a liquid crystal display panel, an organic light-emitting diode panel, or an electronic paper panel. The image capturing device 120 may include a charge-coupled device (CCD) sensor, a complementary metal-oxide-semiconductor (CMOS) sensor, or other suitable photosensitive elements. In some embodiments, the image capturing device 120 may also include dual cameras, a structured light sensing device, a laser, or any element capable of sensing scene depth. Image capturing device 120 can be electrically connected to computing circuit 210 via wired or wireless means. Interactive device 130 can be an automatic pet feeder, pet button, toy, or other device that allows interaction with a pet. Similarly, interactive device 130 can be electrically connected to computing circuit 210 via wired or wireless means. Electronic device 150 is communicatively connected to computing circuit 210. Electronic device 150 is, for example, a mobile phone, laptop, personal computer, or other device with computing capabilities.

[0024] Figure 3 is a flowchart illustrating a pet display method according to an embodiment. Referring to Figures 1 to 3, steps 301 to 304 are executed by the computing circuit 210, and will not be described again below. In step 301, an input image is received. This input image is an image prepared for display on the display panel 220, and the present invention does not limit the content of the input image.

[0025] In step 302, it is determined whether the user is in pet mode. In some embodiments, the user can select one of multiple modes via an on-screen display. If the user selects pet mode, step 302 determines that the user is in pet mode; if the user selects another mode, step 302 determines that the user is not in pet mode. In other words, the computing circuit 210 can determine whether the user is currently in pet mode based on the mode selected by the user. In other embodiments, the user 160 can remotely transmit a command to the computing circuit 210 via the electronic device 150 to specify pet mode. In some embodiments, the image capturing device 120 captures environmental images, and then the computing circuit 210 can detect whether there are pets and people in the environmental images. If there are only pets, the user enters pet mode; otherwise, the user enters another mode.

[0026] If not in pet mode, proceed to step 303 to transmit the input image to display panel 220, where the input image is displayed. In other words, the input image is displayed according to preset color settings (conforming to human visual perception).

[0027] In pet mode, step 304 is performed to reduce the red component of the input image to obtain a converted image, which is then transmitted to the display panel 220 for display. Figure 4 is an example diagram illustrating the converted input image according to one embodiment. Referring to Figure 4, the input image 410 conforms to human vision, and after conversion in step 304, a converted image 420 is obtained, which conforms to the pet's vision.

[0028] The input image may belong to color spaces such as RGB, YUV, and XYZ. A color space conversion is performed first, followed by reducing the red component. For example, the input image can be converted to the L*a*b* color space. The L*a*b* color space includes L*, a*, and b* channels, each with corresponding values. In such an embodiment, for each pixel of the input image, the value in the a* channel can be reduced to obtain the converted image. There are several ways to reduce the a* channel value, such as subtracting a fixed value from the original value; if the original a* channel value is greater than 0, it can be multiplied by -1 or set to 0.

[0029] In some embodiments, decreasing the value of the a* channel simultaneously increases the value of the b* channel to maintain constant pixel brightness. In some embodiments, the amount by which the a* channel is decreased is the same as the amount by which the b* channel is increased. In other embodiments, the amount by which the a* channel is decreased may be greater than or less than the amount by which the b* channel is increased.

[0030] In some embodiments, when the input image belongs to the RGB color space, the value of the red channel can be directly reduced without color space conversion. Alternatively, the values ​​of the green and blue channels can be increased simultaneously to maintain constant brightness.

[0031] In some embodiments, in order to reduce the red component, the values ​​in the L*a*b* color space can be multiplied by a transformation matrix, and this calculation is expressed as the following mathematical formula 1. [Mathematical Expression 1]

[0032] Where X is a vector containing three values ​​of a pixel in the L*a*b* color space. M is a transformation matrix of size 3*3. Y is the transformed vector, and the values ​​contained in this vector are called the transformed values. After performing the calculation of Equation 1 for each pixel, the transformed image can be obtained. The transformation matrix can be designed so that the values ​​of the a* channel decrease and the values ​​of the b* channel increase after transformation.

[0033] Performing the mathematical equation (Equation 1) calculation for every pixel would consume too many computational resources. Therefore, some implementations can employ speed-up methods. For example, vector quantization can be used, where multiple representative vectors are pre-defined. Then, each pixel in the input image is calculated to determine which representative vector it is closest to, thus classifying the pixel into the corresponding representative vector. The representative vector has a length of 3, representing the values ​​of the L*, a*, and b* channels. The representative vector is then processed using Equation 1 to obtain the transformed vector, and all pixels classified into the same category will use this transformed vector.

[0034] In some embodiments, all pixels in the input image can be clustered to obtain multiple groups. Unsupervised learning clustering algorithms (such as the K-homogeneous algorithm) can be used here, and the present invention does not limit the number of groups. Then, a representative pixel is obtained for each group; for example, the centroid of the group can be taken as the representative pixel. The values ​​contained in the representative pixel are then multiplied by a transformation matrix to obtain the transformed values, and all pixels within this group are replaced with the transformed values. When the number of groups is small, more computation can be saved, but more original pixel information is lost; conversely, when the number of groups is large, more pixel information can be retained, but less computation is saved. In some embodiments, the number of groups can be determined based on hardware resources.

[0035] The values ​​in the aforementioned transformation matrix M can be preset. In some embodiments, the values ​​in the transformation matrix M can also be dynamically changed during execution. For example, referring to Figures 1 and 2, multiple pet images can be acquired through the image capturing device 120. The calculation circuit 210 can calculate a gaze duration based on these pet images. The calculation circuit 210 can first detect the pupils of the pet 140, determine the gaze position based on the pupil position, and then calculate the time the gaze position remains on the display device 110 as the gaze duration.

[0036] Next, the transformation matrix can be determined based on the gaze duration. Specifically, first, a set of preset variables for the transformation matrix is ​​obtained, denoted as... Then, multiple sets of perturbation variables are set, represented as... , representing the i-th perturbation variable, this perturbation variable It is a vector of length 9. In some embodiments, the perturbation variable can be sampled according to a Gaussian distribution with a mean of 0 and a standard deviation of . Next, each perturbation variable is added to the above preset variables to obtain multiple sets of test variables, expressed as the following mathematical formula 2. [Mathematical Expression 2]

[0037] Where N is a positive integer representing the number of all perturbation variables. Let be the variable for the i-th test group. Represents the i-th group of perturbation variables. Each group of test variables All of these can form a transformation matrix M. Next, each set of test variables... All of these are applied to the input image (such as the transformation in mathematical formula 1) to obtain the transformed image. After displaying the transformed image, the corresponding gaze duration is calculated using the pupil detection method described above. For example, each set of test variables can be set. Each test was conducted for 10 minutes, and then the variables for each test group were calculated. The corresponding gaze duration; if the gaze duration is longer, it indicates that the corresponding test variable... It better matches the current visual perception of pets.

[0038] The gaze duration can be used to adjust the aforementioned preset variables. In some embodiments, the computing circuit 210 may set a reward positively correlated with the gaze duration. For example, the reward may be set according to the following mathematical formula 3. [Mathematical Expression 3]

[0039] in Let T be the gaze duration corresponding to the i-th test variable. T is a real number. Let T be the reward corresponding to the i-th test variable. In other words, when the gaze duration is less than or equal to a real number T, the reward is... The reward is 0. When the gaze duration is greater than a real number T, the reward is... Greater than 0. Next, the preset variables mentioned above can be adjusted according to the following mathematical formula 4. . [Mathematical Expression 4]

[0040] in This is the learning rate. This represents the standard deviation of multiple sets of perturbation variables. Therefore, when a certain set of test variables causes a longer gaze duration, the preset variable... This will be adjusted to closely approximate the test variable. Through this method, the transformation matrix M (i.e., the adjusted preset variable) can be dynamically determined. When facing different pets, the transformation matrix M can be determined according to the gaze time to match the pet's vision.

[0041] On the other hand, after acquiring pet images through the image capturing device 120, the pet's emotions, actions, etc., can also be identified through these images. When the computing circuit 210 determines that the pet image belongs to a preset category, it activates the interactive device 130. This preset category can represent hunger or boredom, and the interactive device 130 can be a toy or an automatic feeder. For example, when the pet image is detected to belong to the hunger category, the computing circuit 210 can actively activate the automatic feeder. Or when the pet image is detected to belong to the boredom category, the computing circuit 210 can actively activate the toy.

[0042] In other embodiments, the pet display system 200 may also include a microphone for capturing sound signals. The computing circuitry 210 can determine whether the pet is bored or hungry based on the sound signals and the pet image.

[0043] In some embodiments, user 160 can receive images captured by image capturing device 120 via electronic device 150. Electronic device 150 can also capture images of user 160, which can be transmitted to display device 110. In other words, user 160 can have video calls with pet via display device 110 and electronic device 150.

[0044] In some embodiments, the user 160 can also remotely control the interactive device 130 via the electronic device 150 to interact with the pet 140. For example, the interactive device is a feeder, and the user 160 can send a message to the computing circuit 210 via the electronic device 150, which will then activate the interactive device 130.

[0045] In some embodiments, the interactive device 130 is a button, and the content displayed on the display panel 220 is about a game. The pet can watch the game screen and play the game by pressing the button. Because the content displayed on the display panel 220 in this embodiment is visually compatible with the pet, the pet can have a better gaming experience.

[0046] Although the present invention has been disclosed above by way of embodiments, it is not intended to limit the present invention. Anyone skilled in the art can make some modifications and refinements without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0047] 110: Display device 120: Image capturing device 130: Interactive Installation 140: Pets 150: Electronic devices 160: Users 200: Pet Display System 210: Computational Circuits 220: Display panel 301~304: Steps 410: Input Image 420: Converted image

Claims

1. A pet display system, comprising: a display panel; a computing circuit for receiving at least one input image and determining whether it is in a pet mode; an image capturing device for acquiring a pet image; and an interactive device electrically connected to the computing circuit, wherein if not in pet mode, the computing circuit transmits the at least one input image to the display panel for display; if in pet mode, the computing circuit reduces a red component of the at least one input image to obtain at least one converted image, and transmits the at least one converted image to the display panel for display, wherein the computing circuit determines whether the pet image belongs to a preset category, and if so, activates the interactive device.

2. The pet display system as claimed in claim 1, wherein the computing circuitry is configured to calculate a plurality of values ​​of the at least one input image in an L*a*b* color space, and reduce the value of the at least one input image in an a* channel.

3. The pet display system as claimed in claim 2, wherein the computing circuitry is used to increase the value of the values ​​in a b* channel.

4. The pet display system as claimed in claim 3, wherein the computing circuitry is used to multiply the values ​​in the L*a*b* color space by a transformation matrix, thereby reducing the value in the a* channel and increasing the value in the b* channel.

5. The pet display system of claim 4, wherein the at least one input image comprises a plurality of pixels, each of the pixels comprising corresponding values, wherein the computing circuit is configured to group the pixels to obtain a plurality of groups, obtain a representative pixel of a first group of the groups, multiply the values ​​contained in the representative pixel by the transformation matrix to obtain a plurality of transformed values, and replace the pixels of the first group with the transformed values.

6. The pet display system as described in claim 5, further comprising: An image capturing device is used to acquire multiple pet images, wherein the computing circuit is used to calculate a gaze time based on the pet images and determine a transformation matrix based on the gaze time.

7. The pet display system of claim 6, wherein the computing circuit is configured to obtain a set of preset variables of the transformation matrix and set multiple sets of perturbation variables, wherein the computing circuit is configured to add each of the multiple sets of perturbation variables to the set of preset variables to generate multiple sets of test variables, and apply each of the multiple sets of test variables to the at least one input image to obtain the corresponding gaze time, wherein the computing circuit is configured to adjust the set of preset variables according to the gaze times.

8. The pet display system as claimed in claim 7, wherein the computing circuitry is configured to set a reward positively correlated with the gaze duration and adjust the set of preset variables according to the following mathematical formula, wherein is the set of preset variables, is a learning rate, N is the number of the plurality of perturbation variables, is a standard deviation corresponding to the plurality of perturbation variables, is the i-th perturbation variable in the plurality of perturbation variables, and is the reward corresponding to the i-th perturbation variable.

9. The pet display system as claimed in claim 8, wherein the computing circuitry is configured to set the reward according to the following mathematical formula, where is the gaze time corresponding to the i-th test variable, and T is a real number.

10. A pet display method, executed by a computing circuit, the pet display method comprising: receiving at least one input image; determining whether it is in a pet mode; if not in a pet mode, transmitting the at least one input image to a display panel for displaying the at least one input image; if in a pet mode, reducing a red component of the at least one input image to obtain at least one converted image, transmitting the at least one converted image to the display panel for displaying the at least one converted image; acquiring a pet image through an image capturing device; and determining whether the pet image belongs to a preset category, and if so, activating an interactive device.

11. The pet display method as described in claim 10, further comprising: Calculate multiple values ​​of the at least one input image in an L*a*b* color space, and reduce the value of the a* channel among these values.

12. The pet display method as described in claim 11 further includes: Increase the value in one of the b* channels.

13. The pet display method as described in claim 12 further includes: The values ​​in the L*a*b* color space are multiplied by a transformation matrix, thereby reducing the value in the a* channel and increasing the value in the b* channel.

14. The pet display method as claimed in claim 13, wherein the at least one input image comprises a plurality of pixels, each of the pixels comprising corresponding values, the pet display method further comprising: The pixels are grouped to obtain multiple groups. A representative pixel of the first group is obtained. The values ​​contained in the representative pixel are multiplied by the transformation matrix to obtain multiple transformed values. The pixels of the first group are replaced with the transformed values.

15. The pet display method as described in claim 14, further comprising: Multiple pet images are acquired through an image capturing device; a gaze duration is calculated based on the pet images, and a transformation matrix is ​​determined based on the gaze duration.

16. The pet display method as described in claim 15, further comprising: Obtain a set of preset variables for the transformation matrix, and set multiple sets of perturbation variables; Add each of the multiple sets of perturbation variables to the set of preset variables to generate multiple sets of test variables, and apply each of the multiple sets of test variables to the at least one input image to obtain the corresponding gaze time; and adjust the set of preset variables according to the gaze times.

17. The pet display method as described in claim 16, further comprising: Set a reward positively correlated with the gaze duration, and adjust the set of preset variables according to the following mathematical formula, where is the set of preset variables, is a learning rate, N is the number of the multiple sets of perturbation variables, is a standard deviation corresponding to the multiple sets of perturbation variables, is the i-th perturbation variable in the multiple sets of perturbation variables, and is the reward corresponding to the i-th perturbation variable.

18. The pet display method as described in claim 17, further comprising: The reward is set according to the following mathematical formula, where is the gaze time corresponding to the i-th test variable, and T is a real number.

Images