Architectural illumination brightness adaptive adjustment system and method based on target perception

Abstract

According to the invention, the system comprises an information collection module, an analysis and evaluation module, a connection module, a driving unit, a processing module and an illumination unit, can autonomously capture face image information, starts different illumination environments according to the information, and achieves the self-adaptive adjustment of the illumination brightness of the building. According to the invention, people can be intelligently identified so as to control the brightness of lamps at different positions of a room, the filtering and gain amplification circuit of the signal acquisition circuit can be automatically adjusted according to the physiological characteristics and physiological signal characteristics of an acquired object, accurate acquisition of physiological signals can be realized, and the face state can be identified by using a neural network based on deep learning. The state of a human face target is obtained by comparing the collected information, so that the on-off state of the lighting device by the lighting module is called, the interaction between the lighting light and the target is achieved, more possibilities are provided for the creation of the space atmosphere of the smart building, the lighting light of the smart building has interaction and immersive interaction experience, and the interestingness of the smart building is improved. And the device is more energy-saving and environment-friendly.

Description

Technical Field

[0001] The present invention relates to the technical field of landscape architecture, and particularly to a building lighting brightness adaptive adjustment system and method based on target perception. Background Art

[0002] A smart building refers to optimizing the combination of the building's structure, systems, services, and management according to user needs to provide users with an efficient, comfortable, and convenient humanized building environment. A smart building is the product of integrating modern scientific and technological achievements, and its technical foundation mainly consists of modern building technology, modern computer technology, modern communication technology, and modern control technology. It is mainly applicable to new construction, expansion, or renovation projects such as office buildings, commercial comprehensive buildings, culture, media, schools, stadiums, hospitals, transportation, industrial buildings, and residential communities. By equipping the building with intelligent functions, the goals of high efficiency, safety, energy conservation, comfort, environmental protection, and sustainable development can be achieved.

[0003] The existing lighting control of smart buildings generally relies on sound, ambient light, and human induction for switching and brightness adjustment, and cannot adapt to factors such as different movement trajectories of the human body in the building space and the attributes of the space areas passed by the movement trajectories, so as to achieve an adaptive response in lighting switching and brightness adjustment. This not only causes waste of electrical energy but also cannot meet the diverse needs of users, and the interaction feeling is weak. Most lighting controls rely on manual control by personnel. Although many projects consider group and time-sharing control during the design period, and even some set up multiple control methods such as induction control, during the actual operation and management after the project is completed and put into use, it is actually manually controlled by humans. And many companies save operating costs, with very few management personnel and lacking technical function training (not understanding operation or being lazy, etc.), or directly turn off the lighting sources to save electricity and the lamp replacement cycle, only using 25% of the lamp sources to maintain the basic illumination requirements, or not caring about the power supply due to laziness. This causes problems such as insufficient illumination or excessive waste of illumination, which not only affects people's line of sight and recognition, but also the uneven illumination will result in a situation of bright and dark areas, and the comfort level is very poor. Therefore, in view of the current situation, it is necessary to improve it.

[0004] The existing lighting adjustment only adjusts the lighting in a specific environment and is mostly applied to voice-activated lights. There are certain technical difficulties in the case of multiple application scenarios, such as the lighting adjustment scenario during PPT presentation, the lighting adjustment scenario during a meeting, and the lighting adjustment scenario during cleaning. For the lighting adjustment in such multiple scenarios, manual control is often used, resulting in very low flexibility. Moreover, the existing lighting adjustment rarely involves image processing and voice recognition for lighting adjustment, and the intelligent recognition through the image artificial interaction scenario needs to be strengthened urgently. Summary of the Invention

[0005] The object of the present invention is to overcome the above-mentioned defects in the prior art. The present invention provides a building lighting brightness adaptive adjustment system and method based on target perception. By identifying the status information of the target person, the function of adjustable light brightness can be realized, ensuring that the output light source has a rich enough output to respond to different states, achieving the purpose of improving user experience and comfort, and effectively solving the problem that the existing intelligent building lighting control generally relies on sound, ambient light, and human induction for switching and brightness adjustment, and cannot adapt to factors such as different movement trajectories of the human body in the building space and the attributes of the space areas passed by the movement trajectories, realizing adaptive response in lighting switching and brightness adjustment, resulting in waste of electrical energy while also not meeting the diverse needs of users and having a weak sense of interaction.

[0006] The building lighting brightness adaptive adjustment system based on target perception includes an information acquisition module 1, an analysis and evaluation module 2, a connection module 3, a processing module 4, and a lighting unit 5;

[0007] The information acquisition module 1 is used to collect the information of the users in the environment in real time, preprocess the collected information, and send the preprocessed information to the analysis and evaluation module 2;

[0008] The analysis and evaluation module 2 is used to receive the preprocessed information of the users, input the histogram of oriented gradients features into a convolutional neural network to analyze and identify the information of the users, extract the facial information of the users, and judge the status information of the users in various situations. The status information is the physiological state of the users, and / or indicates that the users are in a waking state or in a sleeping state;

[0009] The connection module 3 is used to send the status information judged by the analysis and evaluation module 2 to the processing module 4;

[0010] The processing module 4 is used to receive the status information sent by the analysis and evaluation module 2 and generate light adjustment output information according to the judged current physiological state of the users;

[0011] The lighting unit 5 is used to receive the output information of the processing module and control the lamp to emit corresponding light brightness and hue according to a preset value.

[0012] In one embodiment, the analysis and evaluation module 2 is set at the local end that realizes a local area network connection with the information acquisition module 1; or the analysis and evaluation module 2 is set at the server end that realizes a remote connection with the information acquisition module 1.

[0013] In one embodiment, the information acquisition module 1 includes a camera unit 11, and the camera unit 11 is used to collect the image signal of the user's face.

[0014] In one embodiment, the analysis and evaluation module 2 includes an image processing unit 21, which is used to parse the current status information of the user from the image signal by using a physiological prediction neural network model and output it in the status information.

[0015] In one embodiment, it includes a driving unit 6. The driving unit 6 is signal-connected to the lighting unit 5. The driving unit 6 includes:

[0016] A waveform generation module 61, which is used to generate a pulse modulation signal;

[0017] A waveform adjustment module 62, which is signal-connected to the waveform generation module 61 and is used to adjust the duty cycle of the pulse modulation signal.

[0018] A method for adaptively adjusting the brightness of building lighting based on target perception, including the system for adaptively adjusting the brightness of building lighting based on target perception according to any one of the above, includes the following steps:

[0019] Collect the status information of the user in real time, preprocess the collected status information, and send the preprocessed status information to the analysis and evaluation module;

[0020] The analysis and evaluation module receives the preprocessed status information of the user, uses the histogram of oriented gradients features to input a convolutional neural network to parse and identify the user's information, extracts the user's facial information, judges the status information of the user in various situations, and sends the judged status information to the monitoring and feedback module;

[0021] Receive the status information, and generate light adjustment output information according to the judged current physiological state of the user;

[0022] Receive the output information of the processing module, and control the lamp to emit corresponding light brightness and hue according to a preset value.

[0023] In one embodiment, using the histogram of oriented gradients features to input a convolutional neural network includes parsing the current status information of the user from the image signal by using a physiological prediction neural network model and outputting it in the status information.

[0024] In one embodiment, using the physiological prediction neural network model includes:

[0025] Collect the original modeling data, select the indicators of the detected facial features, facial movement features, and head movement features as the input values in the model training stage, and select the corresponding expression values of the input quantities as the expected output values in the model training stage;

[0026] Construct a BP neural network model according to the selected input quantity and the desired output quantity. The BP neural network model includes a three-layer feedforward neural network structure, namely an input layer, a hidden layer, and an output layer. The input index of the input layer is the selected input quantity, and the output index of the output layer is the desired output quantity. Set the desired error E according to the actual prediction accuracy requirement.

[0027] Train the BP neural network model with the current training data.

[0028] According to the currently measured data, apply the model and use the BP neural network model to confirm the state information.

[0029] Among them, the input layer, the hidden layer, and the output layer all include nodes corresponding to the types of expressions. When there are M types of expressions, the input layer has M + 5 nodes, the output layer has M nodes, and the hidden layer has M + 7 nodes.

[0030] The activation function of the hidden layer adopts the Relu function, and the activation function of the output layer adopts a linear function.

[0031] In one embodiment, training the BP neural network model includes:

[0032] Take a sample P i , Q j , and input P i into the network.

[0033] Calculate the error measure E i and the actual output O i ;

[0034] Repeat adjusting the weights until ∑E i < ε;

[0035] Calculate the difference between the actual output O p and the ideal output Q i ;

[0036] Adjust the output layer weight matrix through the error of the output layer.

[0037] Estimate the error of the previous layer of the output layer through the error of the output layer, so as to obtain the error estimates of other layers.

[0038] Modify the weight matrix through error estimation.

[0039] Among them, the error calculation formula is

[0040] In one embodiment, the controlling the lamp to emit corresponding light brightness according to a preset value includes adjusting the illumination brightness:

[0041] The driving unit generates a pulse modulation signal to drive the lighting unit to light up;

[0042] Increase or decrease the duty cycle of the pulse modulation signal to adjust the brightness of the lighting unit;

[0043] When the duty cycle of the pulse modulation signal increases but does not reach 100%, if the duty cycle of the pulse modulation signal continues to increase, the lighting time of the lighting unit continues to increase and the brightness continues to increase;

[0044] When the duty cycle of the pulse modulation signal increases to 100%, if the duty cycle of the pulse modulation signal continues to increase, the lighting time of the lighting unit does not increase and the brightness does not increase;

[0045] When the duty cycle of the pulse modulation signal is lower than the set lower limit value, the lighting unit starts to alternate between bright and dark and flickers;

[0046] When the duty cycle of the pulse modulation signal decreases to 0, the lighting time of the lighting unit is 0 and the lighting unit goes out.

[0047] Beneficial effects: Due to the above technical solutions, this building lighting brightness adaptive adjustment system and method based on target perception of the present invention can autonomously capture face images, can turn on different lighting environments for the user's face, intelligently "recognize people" to control the brightness of lamps at different positions in the room, can automatically adjust the filtering and gain amplification circuits of the signal acquisition circuit according to the physiological characteristics and physiological signal characteristics of the collected object, achieve accurate acquisition of physiological signals, identify the face state through a neural network based on deep learning, and mobilize the lighting module to control the on / off state of the lighting equipment by comparing the collected information with the face target state. By recognizing the face state, the present invention realizes the control of the brightness of the corresponding lighting module, thereby regulating the lighting light according to the target state to soothe the psychology, achieving the purpose of improving the user experience and comfort. Thus, the lighting light interacts with the target, provides more possibilities for creating the spatial atmosphere of the smart building, enables the smart building lighting to have interactive and immersive interactive experiences, and is more energy-saving and environmentally friendly, realizing adaptive responses in lighting switching and brightness adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will discuss the drawings required for use in the description of the embodiments or the prior art. Obviously, the technical solutions described in conjunction with the drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other embodiments and their drawings can be obtained based on these embodiments shown in the drawings.

[0049] Figure 1 It is a schematic structural diagram of the building lighting brightness adaptive adjustment system based on target perception of the present invention;

[0050] Figure 2 It is a schematic flowchart of the method for adaptive adjustment of building lighting brightness based on target perception of the present invention. Specific embodiments

[0051] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0052] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0053] Next, the present invention will be further described in conjunction with the accompanying drawings and specific embodiments, but it is not a limitation of the present invention.

[0054] The following is combined with the specification appendix Figure 1 , Figure 2 , and the structural design of this device will be described in detail.

[0055] Referring to Figure 1 , Figure 2 , the building lighting brightness adaptive adjustment system based on target perception includes an information collection module 1, an analysis and evaluation module 2, a connection module 3, a processing module 4, and a lighting unit 5;

[0056] The information collection module 1 is used to collect the information of users in the environment in real time, preprocess the collected information, and send the preprocessed information to the analysis and evaluation module 2;

[0057] The analysis and evaluation module 2 is used to receive the preprocessed information of the user, use the histogram of oriented gradients features to input a convolutional neural network to parse and identify the information of the user, extract the facial information of the user, and judge the status information of the user in various situations. The status information is the physiological state of the user, and / or indicates that the user is in a waking state or in a sleeping state;

[0058] The connection module 3 is used to send the status information judged by the analysis and evaluation module 2 to the processing module 4. The connection module 3 includes any one or a combination of WIFI, Zigbee, NB-loT, eMTC, Z-wave, LoRa, SigFox, RF radio frequency, and Bluetooth. Specifically, WIFI and mobile data have different signal frequency bands. According to the different signals in the user's environment, it is possible to switch between WIFI and mobile data at will. Sometimes, if the Wifi network is unstable or disconnected, and the mobile network was enabled previously, then the mobile network will be used by default;

[0059] The processing module 4 is used to receive the status information sent by the analysis and evaluation module 2 and generate lighting adjustment output information according to the judged current physiological state of the user;

[0060] The lighting unit 5 is used to receive the output information of the processing module and control the lamp to emit corresponding light brightness and hue according to a preset value. The lighting unit 5 includes an LED lamp. The LED lamp has no stroboscopic effect and operates in pure direct current, eliminating the visual fatigue caused by the stroboscopic effect of traditional light sources. At the same time, it is convenient for the present invention to control the operation of the LED lamp through a pulse modulation signal with an adjustable duty cycle.

[0061] Further, in a preferred embodiment of the building lighting brightness adaptive adjustment system based on target perception of the present invention, the analysis and evaluation module 2 is arranged at the local end that realizes a local area network connection with the information collection module 1; or the analysis and evaluation module 2 is arranged at the server end that realizes a remote connection with the information collection module 1.

[0062] Further, in a preferred embodiment of the building lighting brightness adaptive adjustment system based on target perception of the present invention, the information collection module 1 includes a camera unit 11. The camera unit 11 is used to collect the image signal of the user's face. The camera unit 11 is used to collect the image signal of the user. Specifically, the camera unit 11 is an array camera. The sensing distance of the array camera is 1-6m, the vertical sensing angle is 45°, and the horizontal sensing angle is 135°. In this way, when measuring the physiological signal state of the user, the array camera can basically cover the entire room for measurement without rotation.

[0063] Further, in a preferred embodiment of the building lighting brightness adaptive adjustment system based on target perception of the present invention, the analysis and evaluation module 2 includes an image processing unit 21, which is used to analyze and obtain the current status information of the user from the image signal by using a physiological prediction neural network model and output it in the status information.

[0064] Further, in a preferred embodiment of a building lighting brightness adaptive adjustment system based on target perception according to the present invention, it includes a driving unit 6, and the driving unit 6 is signal-connected to the lighting unit 5. The driving unit 6 includes:

[0065] A waveform generating module 61 for generating a pulse modulation signal;

[0066] A waveform adjusting module 62, signal-connected to the waveform generating module 61, for adjusting the duty cycle of the pulse modulation signal.

[0067] When adjusting the brightness of the lighting unit 5, the signal frequency of the pulse modulation signal remains unchanged. What changes is the time of the high level of the pulse of the pulse modulation signal, that is, the conduction time of the lighting unit 5. This signal to adjust the brightness is equivalent to the average current of the lighting unit 5, so the current will change. Therefore, the change in the duty cycle of the pulse modulation signal can change the power of the lighting unit 5;

[0068] The waveform generating module 61 generates a pulse width modulation signal. PWM is pulse width modulation, that is, a pulse waveform with a variable duty cycle. The PWM waveform controls the conduction and cutoff of semiconductor switching devices, so that a series of pulses with equal amplitudes but unequal widths are obtained at the output end, and these pulses are used to replace a sine wave or other required waveforms. Modulating the widths of the pulses according to certain rules can change both the magnitude of the output voltage of the inverter circuit and the output frequency. The current tracking type PWM converter circuit is to adopt current tracking control for the converter circuit. That is, instead of modulating the carrier wave with a signal wave, the desired output current is used as the command signal, and the actual current is used as the feedback signal. By comparing the instantaneous values of the two, the on and off of each power device in the inverter circuit are determined, so that the actual output tracks the change of the current. The frequency of the PWM waveform remains unchanged, and the width of the pulse is directly changed, that is, the conduction time of the switching element is controlled; for example, if it is currently conducting at a high level, then the larger A and the smaller B of the square wave, the longer the conduction time; otherwise, it is shorter.

[0069] An electronic device, comprising: a memory and one or more processors;

[0070] Wherein, the memory is communicatively connected to the one or more processors, and the memory stores instructions executable by the one or more processors. When the instructions are executed by the one or more processors, the electronic device is configured to implement the method as described in any one of the above.

[0071] Specifically, the processor and the memory can be connected through a bus or other means. Taking the connection through the bus as an example, the processor can be a Central Processing Unit (CPU). The processor can also be other general-purpose processors, Digital Signal Processors (DSPs), Application-Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., in the form of chips, or combinations of the above types of chips.

[0072] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules. The processor executes various functional applications and data processing of the processor by running the non-transitory software programs / instructions and functional modules stored in the memory.

[0073] The memory can include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created by the processor, etc. In addition, the memory can include high-speed random access memory and can also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory optionally includes a memory remotely set relative to the processor, and these remote memories can be connected to the processor through a network (such as through a communication interface). Examples of the above networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0074] A computer-readable storage medium, on which computer-executable instructions are stored. When the computer-executable instructions are executed by a computing device, they can be used to implement the method described in any one of the above.

[0075] The foregoing computer-readable storage mediums include physical volatile and non-volatile, removable and non-removable media implemented in any way or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Specifically, the computer-readable storage mediums include, but are not limited to, USB flash drives, external hard drives, read-only memory (ROM), random access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other solid-state memory technologies, CD-ROM, digital versatile disk (DVD), HD-DVD, Blu-ray or other optical storage devices, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the required information and can be accessed by a computer.

[0076] Although the subject matter described herein is provided in the general context of execution in conjunction with the execution of an operating system and applications on a computer system, those skilled in the art will recognize that other implementations may be performed in conjunction with other types of program modules. In general, program modules include routines, programs, components, data structures, and other types of structures that perform specific tasks or implement specific abstract data types. Those skilled in the art will understand that the subject matter described herein may be practiced using other computer system configurations, including handheld devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, minicomputers, mainframe computers, etc., and may also be used in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0077] Those of ordinary skill in the art can realize that the units and method steps of the examples described in conjunction with the embodiments of the present application herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0078] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the original technology, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application.

[0079] A method for adaptively adjusting the brightness of building lighting based on target perception, including the system for adaptively adjusting the brightness of building lighting based on target perception according to any one of the above, includes the following steps:

[0080] Collect the status information of the user in real time, preprocess the collected status information, and send the preprocessed status information to the analysis and evaluation module;

[0081] The analysis and evaluation module receives the preprocessed status information of the user, uses the histogram of oriented gradients features to input into a convolutional neural network to analyze and identify the user's information, extracts the user's facial information, judges the status information of the user in various situations, and sends the judged status information to the monitoring and feedback module;

[0082] Receive the status information, and generate lighting adjustment output information according to the judged current physiological state of the user;

[0083] Receive the output information of the processing module, and control the lamp to emit corresponding light brightness and hue according to the preset value.

[0084] Furthermore, in a preferred embodiment of a method for adaptively adjusting the brightness of building lighting based on target perception according to the present invention, using the histogram of oriented gradients features to input into a convolutional neural network includes using a physiological prediction neural network model to parse the current status information of the user from the image signal and output it in the status information.

[0085] Furthermore, in a preferred embodiment of a method for adaptively adjusting the brightness of building lighting based on target perception according to the present invention, using a physiological prediction neural network model includes:

[0086] Collect the original modeling data, select the indicators of the detected facial features, facial action features, and head action features as the input values in the model training stage, and select the corresponding expression values of the input quantities as the expected output values in the model training stage;

[0087] Construct a BP neural network model according to the selected input quantity and the desired output quantity. The BP neural network model includes a three-layer feedforward neural network structure, namely an input layer, a hidden layer, and an output layer. The input index of the input layer is the selected input quantity, and the output index of the output layer is the desired output quantity. Set the desired error E according to the actual prediction accuracy requirement.

[0088] Train the BP neural network model with the current training data.

[0089] According to the currently measured data, apply the model and use the BP neural network model to confirm the state information.

[0090] Among them, the input layer, the hidden layer, and the output layer all include nodes corresponding to the types of expressions. When there are M types of expressions, the input layer has M + 5 nodes, the output layer has M nodes, and the hidden layer has M + 7 nodes.

[0091] The activation function of the hidden layer adopts the Relu function, and the activation function of the output layer adopts the linear function.

[0092] In a specific embodiment, in terms of expression prediction, a BP neural network with an input layer of 5 nodes, an output layer of 1 node, and a hidden layer of 15 nodes can be constructed. Replace P1 to P5 in the input layer with the following values in its aspects:

[0093] P1: The type of detected expression;

[0094] P2: The time when the expression is detected;

[0095] P3: Facial features;

[0096] P4: Facial action features;

[0097] P5: Head action features;

[0098] And the output O1 can be replaced with the type of expression predicted in the nth time period. The activation function of the hidden layer in this model adopts the Relu function, and the activation function of the output layer adopts the linear function.

[0099] Furthermore, in a preferred embodiment of a method for adaptively adjusting the brightness of building lighting based on target perception according to the present invention, training the BP neural network model includes:

[0100] Take a sample P from the metrics i , Q j , and input P i into the network;

[0101] Calculate the error measure E i and the actual output Q i ;

[0102] Adjust the weights repeatedly until ∑E i <ε;

[0103] Calculate the actual output O p and the ideal output Q i difference;

[0104] Adjust the weight matrix of the output layer through the error of the output layer;

[0105] Estimate the error of the previous layer of the output layer through the error of the output layer, so as to obtain the error estimates of other layers;

[0106] Modify the weight matrix through error estimation;

[0107] wherein, the error calculation formula is

[0108] The BP neural network adopted in this project obtains a suitable linear or non-linear relationship between the input and the output through the event of "training". The "training" process can be divided into two stages: forward transmission and backward transmission.

[0109] Furthermore, in a preferred embodiment of a method for adaptively adjusting the brightness of building lighting based on target perception according to the present invention, the controlling the lamp to emit corresponding light brightness according to a preset value includes adjusting the lighting brightness:

[0110] The driving unit generates a pulse modulation signal to drive the lighting unit to light up;

[0111] Increase or decrease the duty cycle of the pulse modulation signal to adjust the brightness of the lighting unit;

[0112] When the duty cycle of the pulse modulation signal increases but does not reach 100%, continue to increase the duty cycle of the pulse modulation signal, then the lighting time of the lighting unit continues to increase and the brightness continues to increase;

[0113] When the duty cycle of the pulse modulation signal increases to 100%, continue to increase the duty cycle of the pulse modulation signal, then the lighting time of the lighting unit does not increase and the brightness does not increase;

[0114] When the duty cycle of the pulse modulation signal is lower than the set lower limit value, the lighting unit starts to alternate between bright and dark and flickers;

[0115] When the duty cycle of the pulse modulation signal is reduced to 0, the lighting time of the lighting unit is 0 and the lighting unit goes out.

[0116] When the duty ratio of the generated pulse modulation signal is 100%, the lighting time reaches the longest, the brightness increases to the maximum, and each time it is adjusted, the duty ratio of the generated pulse modulation signal increases / decreases by 30%. When the increase / decrease of the duty ratio of the pulse modulation signal is greater than 30%, it will cause the brightness adjustment to be unable to achieve precise adjustment, and flickering is very likely to occur. Such a setting can ensure that each adjustment can reach the optimal change value of the lighting time, making the brightness adjustment reach the most significant change.

[0117] In summary, the building lighting brightness adaptive adjustment system and method based on target perception of the present invention can independently capture face images, can turn on different lighting environments for the user's face, intelligently "recognize people" to control the brightness of lamps at different positions in the room, can automatically adjust the filtering and gain amplification circuits of the signal acquisition circuit according to the physiological characteristics and physiological signal characteristics of the collected object, and achieve accurate acquisition of physiological signals. By using a neural network based on deep learning to recognize the face state, and comparing the collected information to obtain the state of the face target person, the lighting module is mobilized to control the on / off state of the lighting equipment. The present invention realizes the control of the brightness of the lighting of the corresponding lighting module by recognizing the face state, thereby regulating the lighting light according to the state of the target person to soothe the psychology, achieving the purpose of improving the user experience and comfort. Thus, the lighting light interacts with the target, providing more possibilities for creating the spatial atmosphere of smart buildings, making the smart building lighting have interactive and immersive interactive experiences, and being more energy-saving and environmentally friendly, realizing the adaptive response in lighting switching and brightness adjustment.

[0118] The above are only the preferred embodiments of the present invention, and do not limit the implementation manners and protection scope of the present invention. For those skilled in the art, it should be realized that all equivalent replacements and obvious changes made by using the description and illustrations of the present invention should be included in the protection scope of the present invention.

[0119] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "upper", "lower", "front", "rear", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation to the present invention.

[0120] The above are only the preferred embodiments of the present invention, and do not limit the implementation manners and protection scope of the present invention. For those skilled in the art, it should be realized that all equivalent replacements and obvious changes made by using the description and illustrations of the present invention should be included in the protection scope of the present invention.

[0121] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "upper", "lower", "front", "rear", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention.

[0122] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

[0123] In addition, it should be understood that although this specification is described in terms of embodiments, not every embodiment only contains an independent technical solution. This narrative way of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. The building lighting brightness adaptive adjustment system based on target perception is characterized by: It includes an information collection module, an analysis and evaluation module, a connection module, a processing module and a lighting unit; The information collection module is used to collect information of users in the environment in real time, pre-process the collected information, and send the pre-processed information to the analysis and evaluation module; The analysis and evaluation module is used to receive the pre-processed user information, use the directional gradient histogram feature input convolutional neural network to parse and identify the user information, extract the user's facial information, and determine the user's state information in various situations, wherein the state information is the user's physiological state and / or indicates that the user is in an awake state or a sleeping state; The connection module is used to send the status information determined by the analysis and evaluation module to the processing module; The processing module is used to receive the state information sent by the analysis and evaluation module, and generate light adjustment output information according to the current physiological state of the user; The lighting unit is used to receive the output information of the processing module and control the lamp to emit corresponding light brightness and color tone according to preset values.

2. The building lighting brightness adaptive adjustment system based on target perception as claimed in claim 1, characterized in that: The analysis and evaluation module is arranged at a local end that realizes a local area network connection with the information acquisition module; or the analysis and evaluation module is arranged at a service end that realizes a remote connection with the information acquisition module.

3. The building lighting brightness adaptive adjustment system based on target perception as claimed in claim 1, characterized in that: The information acquisition module includes a camera unit, and the camera unit is used to acquire an image signal of the user's face.

4. The building lighting brightness adaptive adjustment system based on target perception as claimed in claim 1, characterized in that: The analysis and evaluation module includes an image processing unit, which is used to parse the image signal using a physiological prediction neural network model to obtain the user's current state information and output it in the state information.

5. The building lighting brightness adaptive adjustment system based on target perception as claimed in claim 1, characterized in that: The device comprises a driving unit, wherein the driving unit is connected to the lighting unit by signal, and the driving unit comprises: A waveform generation module, used for generating a pulse modulation signal; A waveform adjustment module, signal-connected to the waveform generation module, is used to adjust the duty cycle of the pulse modulation signal.

6. A method for adaptively adjusting building lighting brightness based on target perception, comprising a system for adaptively adjusting building lighting brightness based on target perception as described in any one of claims 1 to 5 above, characterized in that: The following steps are involved: Collect the user's status information in real time, pre-process the collected status information, and send the pre-processed status information to the analysis and evaluation module; The analysis and evaluation module receives the pre-processed state information of the user, uses the directional gradient histogram feature input convolutional neural network to parse and identify the user's information, extracts the user's facial information, determines the state information of the user in various situations, and sends the determined state information to the monitoring feedback module; receiving the state information, and generating light adjustment output information according to determining the current physiological state of the user; The output information of the processing module is received, and the lamp is controlled to emit corresponding light brightness and hue according to preset values.

7. The method for adaptively adjusting building lighting brightness based on target perception according to claim 6, characterized in that: Using the directional gradient histogram feature input convolutional neural network includes using a physiological prediction neural network model to parse the image signal to obtain the user's current state information and output it in the state information.

8. The method for adaptively adjusting building lighting brightness based on target perception according to claim 6, characterized in that: The physiological prediction neural network models used include: Collect and obtain original modeling data, select the detected indicators of facial features, facial movement features, and head movement features as input values ​​in the model training stage, and select the expression value corresponding to the input value as the expected output value in the model training stage; According to the selected input and expected output, a BP neural network model is constructed, wherein the BP neural network model includes a three-layer feedforward neural network structure, namely an input layer, a hidden layer and an output layer, wherein the input index of the input layer is the selected input, and the output index of the output layer is the expected output; according to the actual prediction accuracy requirement, an expected error E is set; Training the BP neural network model with current training data; According to the currently measured data, the model is applied, and the state information is confirmed using the BP neural network model; The input layer, hidden layer and output layer all include nodes corresponding to the types of expressions. When there are M types of expressions, the input layer has M+5 nodes, the output layer has M nodes, and the hidden layer has M+7 nodes. The activation function of the hidden layer adopts the Relu function, and the activation function of the output layer adopts the linear function.

9. The method for adaptively adjusting building lighting brightness based on target perception according to claim 6, characterized in that: Training the BP neural network model includes: Take a sample P from the index i , Q j , P i Enter the network; Calculate the error measure E i and the actual output O i ; Repeat the weight adjustment until ∑E i <ε; Calculate the actual output O p With the ideal output Q i difference; Adjusting the output layer weight matrix according to the error of the output layer; The error of the leading layer of the output layer is estimated by the error of the output layer, thereby obtaining error estimates of other layers; Modification of the weight matrix is ​​achieved through error estimation; Among them, the error calculation formula is:

10. The method for adaptively adjusting building lighting brightness based on target perception according to claim 6, characterized in that: The controlling of the lamp to emit corresponding light brightness according to the preset value includes adjusting the lighting brightness: The driving unit generates a pulse modulation signal to drive the lighting unit to light up; Increasing or decreasing the duty cycle of the pulse modulation signal to adjust the brightness of the lighting unit; When the duty cycle of the pulse modulation signal does not increase to 100%, the duty cycle of the pulse modulation signal continues to increase, so that the lighting time of the lighting unit continues to increase and the brightness continues to increase; When the duty cycle of the pulse modulation signal increases to 100%, if the duty cycle of the pulse modulation signal continues to increase, the lighting time of the lighting unit does not increase, and the brightness does not increase; When the duty cycle of the pulse modulation signal is lower than the set lower limit, the lighting unit starts to alternate between bright and dark and flickers; When the duty cycle of the pulse modulation signal is reduced to 0, the lighting time of the lighting unit is 0, and the lighting unit is turned off.

Images