A reading light based on artificial intelligence

Abstract

The present invention discloses a reading lamp based on artificial intelligence, belonging to the field of smart home technology, including a lamp head, a lamp pole, a lamp holder and a plurality of sensing control modules, wherein the lamp head is connected to the end of the lamp pole through a connecting assembly, and the lamp head can rotate around a first axis and / or a second axis through the connecting assembly, and the first axis, the second axis and the central axis of the lamp pole are perpendicular to each other; the plurality of sensing control modules include an eye tracking module, a lighting control module, a data processing module and a communication module. The reading lamp provided by the present invention can simultaneously capture the user's gaze point and obtain the user's perception of brightness by setting an eye tracking function, can adjust the brightness of the reading lamp according to the user's perception of brightness and adjust the area illuminated by the reading lamp at the same time, and irradiate the light above or to the side of the gaze area to ensure that the light does not directly shine on the book or the eyes to avoid reflection and glare problems.

Description

Technical Field

[0001] The present invention relates to the field of smart home technology, and in particular to a reading lamp based on artificial intelligence. Background Art

[0002] In our daily study and work, we often need auxiliary light sources to cope with poor ambient light or study and work at night. If the reading light is not suitable, it will easily affect the reading experience and cause vision loss. Healthy lighting fixtures need to meet the following basic conditions: 1. The color temperature is not higher than 4000K, preferably around 4000K; 2. The light is evenly distributed. That is, the illumination at the working distance is >300lx (A grade) or >500lx (AA grade); 3. No blue light hazard (RG0 grade); 4. The color rendering index Ra>90, the spectrum is close to natural light; 5. Good light shielding, no glare.

[0003] When the brightness is too low or too high, it will cause eye discomfort and affect vision. Brightness is the level of light falling on the eyes when reading. Although the light bulbs in the room produce enough lumens, the surface of the book may still not have the required brightness. Ordinary reading lights only consider keeping the intensity of the light they emit within a suitable range, and do not consider the brightness of the visual focus area under multiple light sources. They cannot adapt to the complex lighting conditions of multiple light sources. When the user adjusts the brightness and color temperature by himself, since the user can only rely on physical sensation and does not have the corresponding eye knowledge, the set light environment does not always meet the needs.

[0004] To this end, we propose an artificial intelligence-based reading light to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to solve the problem in the prior art that there is no optimization of lighting under multiple light sources, and to propose a reading light based on artificial intelligence.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] An artificial intelligence-based reading lamp comprises a lamp body, wherein the lamp body comprises a lamp head, a lamp pole, a lamp holder and a plurality of induction control modules, wherein the lamp head is connected to the end of the lamp pole through a connecting assembly, and the lamp head can rotate around a first axis and / or a second axis through the connecting assembly, and the first axis, the second axis and the central axis of the lamp pole are perpendicular to each other;

[0008] The multiple sensing control modules include an eye tracking module, a lighting control module, a data processing module, and a communication module;

[0009] The eye tracking module includes at least one camera and an infrared sensor, wherein the infrared sensor is configured to detect the position of the user, and the camera is configured to capture the user's head image and eye image;

[0010] The lighting control module is configured to adjust the lighting area, lighting brightness and light color temperature of the reading light;

[0011] The data processing module is configured to process the data collected by the eye tracking module to obtain the user's pupil changes and gaze point position, and feed the results back to the lighting control module;

[0012] The communication module is used for information exchange between the lamp and other smart devices.

[0013] Preferably, the connecting assembly includes a socket and a spherical limit body, one of the socket and the spherical limit body is connected to the lamp pole, and the other is connected to the lamp head, the socket has a spherical groove, the spherical limit body is limited in the spherical groove, and can be universally rotated in the spherical groove by a micro-motor drive or manual adjustment by the user.

[0014] Preferably, the eye tracking module monitors the change of the user's pupil diameter and records the eye movement and the position of the gaze point through the following steps: the infrared sensor emits infrared light, captures the human body temperature information, and confirms the user's location and distance from the lamp body; using a camera or sensor, the reading light can track the reader's head or eye position, and the intelligent control unit adjusts the direction and focus of the light according to the tracking data to ensure that the light in the reading area is always uniform. Through eye tracking technology, the reading light can adjust the light focus and brightness in real time to ensure that the user's eyes are always in the most comfortable light environment when reading.

[0015] The camera captures the human eye image and transmits the human eye image information to the data processing module after preliminary processing.

[0016] Preferably, the data processing module obtains the pupil gaze point information of the human eye by the following steps: using image processing technology to identify the pupil and corneal reflection;

[0017] By comparing the positions of the pupil and corneal reflection in consecutive frames, gaze movement, i.e., the movement of the eye in the horizontal and vertical directions, is calculated;

[0018] The user's gaze point coordinates are calculated based on gaze movement and the position information of the user's head.

[0019] Preferably, the image processing technology comprises the following steps:

[0020] Gaussian filtering is applied to the image to reduce noise; the brightness changes of the image in the horizontal and vertical directions are detected by calculating the horizontal and vertical gradients of the image, the edges in the image are detected, and the pupil and corneal reflections are identified. The specific formula is as follows:

[0021] Horizontal gradient:

[0022] Vertical gradient:

[0023] Edge Strength:

[0024] Edge direction: θ = arctan2(G y ,G x )

[0025] Among them, K x,ij is the horizontal gradient kernel, I ij is the pixel value of the smoothed image at position (i, j), K y,ij is the vertical gradient kernel, G x is the horizontal gradient, G y is the vertical gradient.

[0026] Preferably, the gaze movement can be expressed as:

[0027] Δx=x n -x n-1

[0028] Δy=y n -y n-1

[0029] Among them, (x n ,y n ) is the center position of the pupil or corneal reflection in the current frame, (x n-1 ,y n-1 ). is the position in the previous frame.

[0030] Preferably, the calculated gaze point position information is obtained by calculating the following formula:

[0031] (X,Y)=(X ref +asinθ)·(X′-x ref ),(Y ref +bcos(θ)·(Y′-y ref ))

[0032] Among them, (x, y) is the image coordinate of the pupil center, (X, Y) is the gaze point coordinate, (x′, y′) is the image coordinate of the corneal reflection, (X′, Y′) is the gaze point coordinate of the corneal reflection, (x ref ,yref ) is the image coordinate of the reference point, (X ref ,Y ref ) is the gaze point coordinate of the reference point, a, b, θ are the long axis, short axis and the angle between the main axis and the horizontal direction of the preset eyeball model respectively.

[0033] Preferably, after the gaze point position information is fed back to the lighting control module, the lighting control module adjusts the angle of the lamp head so that the light is irradiated above or to the side of the gaze point position. By determining the user's line of sight fixation area, the light is irradiated above or to the side of the line of sight fixation area to ensure that the light does not directly shine on the book or the eyes to avoid reflection and glare problems.

[0034] Preferably, the data processing module also processes the brightness information through the change in the user's pupil diameter identified by the eye tracking module; including the following situations: whether the user's eyes need to be frequently adjusted to adapt to the light, and if so, determining the change in the user's pupil; when the user's pupil is dilated, it means that the brightness is too low, and the information is fed back to the lighting control module to increase the brightness; when the user's pupil is constricted, it means that the brightness is too high, and the information is fed back to the lighting control module to decrease the brightness.

[0035] Preferably, the communication module is one or more combinations of a 4G module, a 5G module, a low-power Bluetooth module, a WiFi module, a NB-IOT module and a GPRS / GSM module.

[0036] In summary, the artificial intelligence-based reading light provided by the present invention has at least the following beneficial effects: by setting the eye tracking function, it is possible to simultaneously capture the user's gaze point and obtain the user's perception of brightness, and can adjust the brightness of the reading light according to the user's perception of brightness and adjust the area illuminated by the reading light at the same time; by determining the user's gaze area, the light is irradiated above or to the side of the gaze area to ensure that the light does not directly shine on the book or the eyes to avoid reflection and glare problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a structural schematic diagram of the present invention;

[0038] Figure 2 It is a schematic diagram of the modules in the present invention.

[0039] In the figure: 100, lamp holder; 110, connecting assembly; 111, spherical limiting body; 112, spherical notch; 200, lamp pole; 300, lamp holder. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0041] Example 1

[0042] like Figure 1 As shown, an artificial intelligence-based reading lamp includes a lamp body, wherein the lamp body includes a lamp head 100, a lamp pole 200, a lamp holder 300 and a plurality of induction control modules, wherein the lamp head 100 is connected to the end of the lamp pole 200 through a connecting assembly 110, and the lamp head 100 can rotate around a first axis and / or a second axis through the connecting assembly 110, and the first axis, the second axis and the central axis of the lamp pole 200 are perpendicular to each other;

[0043] The multiple sensing control modules include an eye tracking module, a lighting control module, a data processing module, and a communication module;

[0044] In this embodiment, the eye tracking module includes at least one camera and an infrared sensor, the infrared sensor is configured to detect the user's position, and the camera is configured to capture the user's head image and eye image; using the camera or sensor, the reading light can track the reader's head or eye position, and the lighting control module adjusts the direction and focus of the light according to the tracking data to ensure that the light in the reading area is always uniform. Through eye tracking technology, the reading light can adjust the focus and brightness of the light in real time to ensure that the user's eyes are always in the most comfortable light environment when reading.

[0045] The lighting control module is configured to adjust the lighting area, lighting brightness and light color temperature of the reading light;

[0046] The data processing module is configured to process the data collected by the eye tracking module to obtain the user's pupil changes and gaze point position, and feed the results back to the lighting control module;

[0047] The communication module is used for information exchange between the lamp and other smart devices.

[0048] The connecting assembly 110 includes a socket and a spherical limiting body 111, one of which is connected to the lamp pole 200, and the other is connected to the lamp holder 100. The socket has a spherical groove 112, and the spherical limiting body 111 is limited in the spherical groove 112, and can be driven by a micro motor or manually adjusted by the user to rotate universally in the spherical groove 112.

[0049] The eye tracking module monitors the changes in the user's pupil diameter and records the eye movement and gaze point position through the following steps: the infrared sensor emits infrared light, captures human body temperature information, and confirms the user's location and distance from the lamp body; the camera captures the human eye image, and transmits the human eye image information to the data processing module after preliminary processing.

[0050] The data processing module obtains the pupil gaze point information of the human eye by the following steps: using image processing technology to identify the pupil and corneal reflection;

[0051] By comparing the positions of the pupil and corneal reflection in consecutive frames, gaze movement, i.e., the movement of the eye in the horizontal and vertical directions, is calculated;

[0052] The user's gaze point coordinates are calculated based on gaze movement and the position information of the user's head.

[0053] The image processing technique comprises the following steps:

[0054] Gaussian filtering is applied to the image to reduce noise; the brightness changes of the image in the horizontal and vertical directions are detected by calculating the horizontal and vertical gradients of the image, the edges in the image are detected, and the pupil and corneal reflections are identified. The specific formula is as follows:

[0055] Horizontal gradient:

[0056] Vertical gradient:

[0057] Edge Strength:

[0058] Edge direction: θ = arctan2(G y ,G x )

[0059] Among them, K x,ij is the horizontal gradient kernel, I ij is the pixel value of the smoothed image at position (i, j), K y,ij is the vertical gradient kernel, G x is the horizontal gradient, G y is the vertical gradient.

[0060] The gaze movement can be expressed as:

[0061] Δx=x n -x n-1

[0062] Δy=y n -y n-1

[0063] Among them, (x n ,y n ) is the center position of the pupil or corneal reflection in the current frame, (x n-1 ,y n-1 ). is the position in the previous frame.

[0064] The calculated gaze point position information is obtained by the following formula:

[0065] (X,Y)=(X ref +asinθ)·(X′-x ref ),(Y ref +bcos(θ)·(Y′-y ref ))

[0066] Among them, (x, y) is the image coordinate of the pupil center, (X, Y) is the gaze point coordinate, (x′, y′) is the image coordinate of the corneal reflection, (X′, Y′) is the gaze point coordinate of the corneal reflection, (x ref ,y ref ) is the image coordinate of the reference point, (X ref ,Y ref ) is the gaze point coordinate of the reference point, a, b, θ are the long axis, short axis and the angle between the main axis and the horizontal direction of the preset eyeball model respectively.

[0067] After the gaze point position information is fed back to the lighting control module, the lighting control module adjusts the angle of the lamp head so that the light is irradiated above or to the side of the gaze point position. By determining the user's line of sight fixation area, the light is irradiated above or to the side of the line of sight fixation area to ensure that the light does not directly shine on the book or the eyes to avoid reflection and glare problems.

[0068] The data processing module also obtains brightness information through the change in the user's pupil diameter identified by the eye tracking module; including the following situations: whether the user's eyes need to adjust frequently to adapt to the light, and if so, determining the change in the user's pupil; when the user's pupil is dilated, it means that the brightness is low, and feedback information is sent to the lighting control module to increase the brightness; when the user's pupil is constricted, it means that the brightness is high, and feedback information is sent to the lighting control module to lower the brightness.

[0069] The communication module is one or more combinations of 4G module, 5G module, low-power Bluetooth module, WiFi module, NB-IOT module and GPRS / GSM module. When connected to a smart phone or smart speaker, the switch, brightness adjustment and color temperature adjustment functions of the reading light can be controlled by voice control or mobile phone APP.

[0070] The technical solutions in the above-mentioned embodiments of the present application have at least the following technical effects or advantages: by setting the eye tracking function, it is possible to simultaneously capture the user's gaze point and obtain the user's perception of brightness, and can adjust the brightness of the reading light and the area illuminated by the reading light according to the user's perception of brightness. By determining the user's gaze area, light is irradiated above or to the side of the gaze area to ensure that the light does not directly shine on the book or the eyes to avoid reflection and glare problems.

[0071] Example 2

[0072] The embodiment of the present application also provides an artificial intelligence-based reading light. As shown in the figure, this embodiment completes eye tracking through an infrared sensor, including pupil monitoring and corneal reflection detection.

[0073] Pupil detection: The pupil is a dark circular area in the eye that is very sensitive to light. Infrared eye tracking systems work by emitting infrared light to illuminate the eye and using a camera to capture an image of the pupil.

[0074] Corneal reflection detection: The corneal reflection is the light reflected on the cornea of ​​the eye, which is located around the pupil. By analyzing the position and shape of the corneal reflection, the position of the pupil can be determined.

[0075] By analyzing the positions of the pupil and corneal reflection in the continuous frames, the movement of the eyeball in the horizontal and vertical directions is calculated to obtain the gaze movement. The subsequent steps are consistent with those in Example 1 and will not be described in detail here.

[0076] The technical solutions in the above-mentioned embodiments of the present application have at least the following technical effects or advantages: when the ambient light is insufficient, the camera cannot capture a sufficiently clear image of the user's eyes to complete eye tracking. At this time, the infrared sensor is used to emit infrared light that is invisible to the human eye, which can avoid excessive eye tracking errors caused by environmental factors.

[0077] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A reading lamp based on artificial intelligence, comprising a lamp body, characterized in that: The lamp body comprises a lamp head, a lamp pole, a lamp holder and a plurality of induction control modules, wherein the lamp head is connected to the end of the lamp pole through a connecting assembly, and the lamp head can rotate around a first axis and / or a second axis through the connecting assembly, and the first axis, the second axis and the central axis of the lamp pole are perpendicular to each other; The multiple sensing control modules include an eye tracking module, a lighting control module, a data processing module, and a communication module; The eye tracking module includes at least one camera and an infrared sensor, wherein the infrared sensor is configured to detect the position of the user, and the camera is configured to capture the user's head image and eye image; The lighting control module is configured to adjust the lighting area, lighting brightness and light color temperature of the reading light; The data processing module is configured to process the data collected by the eye tracking module to obtain the user's pupil changes and gaze point position, and feed the results back to the lighting control module; The communication module is used for information exchange between the lamp and other smart devices; The data processing module obtains the pupil gaze point information of the human eye by the following steps: using image processing technology to identify the pupil and corneal reflection; By comparing the positions of the pupil and corneal reflection in consecutive frames, gaze movement, i.e., the movement of the eye in the horizontal and vertical directions, is calculated; The user's gaze point position coordinates are calculated through gaze movement and the user's head position information; The image processing technique comprises the following steps: Gaussian filtering is applied to the image to reduce noise; the brightness changes of the image in the horizontal and vertical directions are detected by calculating the horizontal and vertical gradients of the image, the edges in the image are detected, and the pupil and corneal reflections are identified. The specific formula is as follows: Horizontal gradient: Vertical gradient: Edge Strength: Edge direction: θ = arctan2(G y ,G x ) Among them, K x,ij is the horizontal gradient kernel, I ij is the pixel value of the smoothed image at position (i, j), K y,ij is the vertical gradient kernel, G x is the horizontal gradient, G y is the vertical gradient; The gaze movement can be expressed as: Δx=x n -x n-1 Δy=y n -y n-1 Among them, (x n ,y n ) is the center position of the pupil or corneal reflection in the current frame, (x n-1 ,y n-1 ) is the position in the previous frame; The gaze point position information is calculated using the following formula: (X,Y)=(X ref +asinθ)·(Xx ref ),(AND ref +b cos(θ)·(Yy ref )) Among them, (x, y) is the image coordinate of the pupil center, (X, Y) is the gaze point coordinate, (x′, y′) is the image coordinate of the corneal reflection, (X′, Y′) is the gaze point coordinate of the corneal reflection, (x ref ,y ref ) is the image coordinate of the reference point, (X ref ,Y ref ) is the gaze point coordinate of the reference point, a, b, θ are the long axis, short axis and the angle between the main axis and the horizontal direction of the preset eyeball model respectively.

2. The artificial intelligence-based reading light according to claim 1, characterized in that: The connecting assembly includes a socket and a spherical limiting body, one of which is connected to the lamp pole and the other is connected to the lamp head, the socket has a spherical notch, the spherical limiting body is limited in the spherical notch, and can be driven by a micro motor or manually adjusted by the user to allow the spherical limiting body to rotate in all directions in the spherical notch.

3. The artificial intelligence-based reading light according to claim 1, characterized in that: The eye tracking module monitors the changes in the user's pupil diameter and records the eye movement and gaze point position through the following steps: the infrared sensor emits infrared light, captures the body temperature information, and confirms the user's location and distance from the lamp body; The camera captures the human eye image and transmits the human eye image information to the data processing module after preliminary processing.

4. The artificial intelligence-based reading light according to claim 1, characterized in that: After the gaze point position information is fed back to the lighting control module, the lighting control module adjusts the angle of the lamp head so that the light is irradiated above or to the side of the gaze point position.

5. The artificial intelligence-based reading light according to claim 1, characterized in that: The data processing module also processes the changes in the user's pupil diameter identified by the eye tracking module to obtain brightness information; including the following situations: whether the user's eyes need to adjust frequently to adapt to the light, and if so, determining the changes in the user's pupils; when the user's pupils are dilated, it means that the brightness is low, and feedback information is sent to the lighting control module to increase the brightness; When the user's pupils shrink, it means that the brightness is too high, and the information is fed back to the lighting control module to lower the brightness.

6. The artificial intelligence-based reading light according to claim 1, characterized in that: The communication module is one or more combinations of a 4G module, a 5G module, a low-power Bluetooth module, a WiFi module, a NB-IOT module, and a GPRS / GSM module.

Images