CN115866852B

CN115866852B - Lighting lamp light adjusting method, device, equipment and storage medium

Info

Publication number: CN115866852B
Application number: CN202310146123.5A
Authority: CN
Inventors: 周煊; 余亚利; 单晓明; 杨碧婉; 卢铬坤; 杜伟濠; 谭茵
Original assignee: Earda Technologies Co ltd
Current assignee: Earda Technologies Co ltd
Priority date: 2023-02-22
Filing date: 2023-02-22
Publication date: 2023-05-09
Anticipated expiration: 2043-02-22
Also published as: CN115866852A

Abstract

The invention discloses a light adjusting method, a device, equipment and a storage medium of a lighting lamp, wherein the method comprises the following steps: driving a microwave radar to emit a plurality of frames of original electromagnetic wave signals to a bedroom, and receiving a plurality of frames of target electromagnetic wave signals reflected by the bedroom to the plurality of frames of original electromagnetic wave signals; for each frame of target electromagnetic wave signal, detecting the gesture presented by the user when the user moves in the bedroom according to the target electromagnetic wave signal; for each frame of target electromagnetic wave signal, detecting the distance between a user and the lighting lamp according to the target electromagnetic wave signal; correcting the distance and the gesture mutually; identifying a scene of the user activity in the bedroom according to the corrected gesture; and adjusting the light emitted by the lighting lamp according to the corrected distance and the scene. According to the distance and scene self-adaptive adjustment of the light emitted by the lighting lamp, the light emitted by the lighting lamp can meet the requirements of users, the convenience in controlling the lighting lamp is improved, and the time delay in controlling the lighting lamp is reduced.

Description

Lighting lamp light adjusting method, device, equipment and storage medium

Technical Field

The present invention relates to the technical field of lamps, and in particular, to a method, an apparatus, a device, and a storage medium for adjusting light of a lighting lamp.

Background

The lighting lamp is one of household appliances commonly used by users, a plurality of lighting lamps can provide various lighting modes, such as a strong white lamp, a weak white lamp, a yellow lamp and the like, and the users can manually control the lighting lamp to switch different lighting modes according to own requirements through control modes such as a switch, a remote controller, a sound control and the like, and the control modes are complex in operation, so that the control delay is high.

Disclosure of Invention

The invention provides a light adjusting method, device and equipment of a lighting lamp and a storage medium, which aim to solve the problem of reducing the delay of controlling the lighting lamp.

According to an aspect of the present invention, there is provided a light adjusting method of a lighting fixture installed in a bedroom and configured with a microwave radar, the method comprising:

driving the microwave radar to emit a plurality of frames of original electromagnetic wave signals to the bedroom, and receiving a plurality of frames of target electromagnetic wave signals reflected by the bedroom to the plurality of frames of original electromagnetic wave signals;

detecting the gesture presented by a user when the user moves in the bedroom according to the target electromagnetic wave signal for each frame of the target electromagnetic wave signal;

Detecting a distance between the user and the lighting fixture according to the target electromagnetic wave signal for each frame of the target electromagnetic wave signal;

correcting the distance and the gesture mutually;

identifying a scene of the user's activity in the bedroom according to the corrected gesture;

and adjusting the light emitted by the lighting lamp according to the corrected distance and the scene.

Optionally, the detecting, for each frame of the target electromagnetic wave signal, a gesture that a user takes when the user is active in the bedroom according to the target electromagnetic wave signal includes:

loading a preset gesture recognition network, wherein the gesture recognition network is provided with a depth separable convolution layer, a two-way long-short-term memory network and a plurality of multi-layer perceptrons;

inputting the target electromagnetic wave signal into the depth separable convolution layer for each frame of the target electromagnetic wave signal to extract a first electromagnetic wave feature in space;

inputting the first electromagnetic wave characteristics into the two-way long-short-term memory network to extract second electromagnetic wave characteristics on time sequence;

sequentially executing normalization operation and activation operation on the first electromagnetic wave characteristics to obtain third electromagnetic wave characteristics;

Fusing the second electromagnetic wave feature and the third electromagnetic wave feature into a fourth electromagnetic wave feature;

respectively inputting the fourth electromagnetic wave characteristics into each multi-layer perceptron to map to the probability of a certain gesture;

and determining the gesture corresponding to the probability with the maximum value as the gesture presented by the user when the user is active in the bedroom.

Optionally, the multi-layer perceptron comprises a first perceptron, a second perceptron and a third perceptron;

the mapping the fourth electromagnetic wave characteristic into the probability of a certain original gesture in each multi-layer perceptron respectively comprises the following steps:

inputting the fourth electromagnetic wave characteristics into the first perceptron to map to the probability of a station;

inputting the fourth electromagnetic wave characteristics into the second sensing machine and mapping the fourth electromagnetic wave characteristics into sitting probabilities;

and inputting the fourth electromagnetic wave characteristic into the third perceptron to map to the probability of lying.

Optionally, the correcting the distance and the gesture includes:

the gestures are respectively arranged into a first sequence and the distances are arranged into a second sequence according to time sequence;

adding a first window in the first sequence, and sliding the first window;

Adding a second window in the second sequence, and sliding the second window, wherein the length of the first window is the same as the length of the second window;

screening abnormal gestures in the first window according to the change trend of the gestures, and taking the abnormal gestures as first abnormal points;

screening the abnormal distance from the second window according to the change trend of the distance to be used as a second abnormal point;

if the position of the first abnormal point in the first window is the same as the position of the second abnormal point in the second window, performing interpolation processing on the first abnormal point according to the change trend of the gesture in the first window so as to correct the first abnormal point, and performing interpolation processing on the second abnormal point according to the change trend of the distance in the second window so as to correct the second abnormal point.

Optionally, the screening the abnormal gesture in the first window according to the trend of the gesture, as a first abnormal point, includes:

setting the gesture at a midpoint of the first window to a target state;

counting a first reference state for the gesture positioned at the left side of the target state in the first window and counting a second reference state for the gesture positioned at the right side of the target state in the first window respectively so as to represent the change trend of the gesture, wherein the first reference state is the gesture with the duty ratio exceeding a preset first threshold value, and the second reference state is the gesture with the duty ratio exceeding a preset second threshold value;

If the first reference state and the second reference state are not empty and the target state is different from any one of the first reference state and the second reference state, determining that the target state is abnormal as a first abnormal point;

if the first reference state is empty, the second reference state is not empty, and the target state is different from the gesture positioned on the left side of the target state in the first window, determining that the target state is abnormal, and taking the abnormal target state as a first abnormal point;

and if the first reference state is not empty, the second reference state is empty, and the target state is different from the gesture positioned on the right side of the target state in the first window, determining that the target state is abnormal, and taking the abnormal target state as a first abnormal point.

Optionally, the method comprises:

filtering a plurality of distances with the largest value and a plurality of distances with the smallest value in the second window;

if filtering is finished, calculating an average value of the distances remaining in the second window;

calculating a first difference between the distance and the average value for each distance in the second window, and comparing the first difference with a preset error range;

If the first difference value is in the error range, the change trend of the distance mark is 0;

if the first difference value is smaller than the lower limit value of the error range or larger than the upper limit value of the error range, mapping the difference value into a change trend of the distance, wherein the sign of the change trend is the same as that of the first difference value, and the numerical value of the change trend is positively correlated with the numerical value of the first difference value;

respectively calculating a second difference value between the current change trend of the distance and the adjacent change trends of the two distances according to the current distance;

and if the two second difference values are larger than 1, determining that the current distance is abnormal, and taking the current distance as a second abnormal point.

Optionally, the identifying a scene of the user activity in the bedroom according to the corrected gesture includes:

loading a preset decision tree;

arranging the corrected gestures into a third sequence according to a time sequence;

adding a third window in the third sequence, and sliding the third window;

and the gesture corrected in the third window is used as the attribute of the user, and is sequentially input into the decision tree to decide that the scene of the user moving in the bedroom is reading, moving or resting.

Optionally, the adjusting the light emitted by the lighting lamp according to the corrected distance and the scene includes:

loading a mapping table matched with the scene, wherein the mapping table records the relation of mapping distance to brightness and/or color temperature;

inquiring brightness and/or color temperature of the distance map after correction in the mapping table;

and adjusting the lighting lamp to enable the lighting lamp to emit light according to the brightness and/or the color temperature.

According to another aspect of the present invention, there is provided a light adjusting device of a lighting fixture installed in a bedroom and configured with a microwave radar, the device comprising:

the microwave detection module is used for driving the microwave radar to emit a plurality of frames of original electromagnetic wave signals to the bedroom and receiving a plurality of frames of target electromagnetic wave signals reflected by the bedroom to the plurality of frames of original electromagnetic wave signals;

the gesture recognition module is used for detecting the gesture presented by the user when the user moves in the bedroom according to the target electromagnetic wave signal for each frame of the target electromagnetic wave signal;

the distance detection module is used for detecting the distance between the user and the lighting lamp according to the target electromagnetic wave signal for each frame of the target electromagnetic wave signal;

The correction module is used for correcting the distance and the gesture mutually;

the scene recognition module is used for recognizing the scene of the user activity in the bedroom according to the corrected gesture;

and the light adjusting module is used for adjusting the light emitted by the lighting lamp according to the corrected distance and the scene.

Optionally, the gesture recognition module is further configured to:

Optionally, the multi-layer perceptron comprises a first perceptron, a second perceptron and a third perceptron; the gesture recognition module is further configured to:

Optionally, the correction module is further configured to:

adding a first window in the first sequence, and sliding the first window;

Optionally, the correction module is further configured to:

setting the gesture at a midpoint of the first window to a target state;

Optionally, the correction module is further configured to:

Optionally, the scene recognition module is further configured to:

loading a preset decision tree;

adding a third window in the third sequence, and sliding the third window;

Optionally, the light adjusting module is further configured to:

According to another aspect of the present invention, there is provided an electronic apparatus including:

At least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the light adjustment method of the lighting fixture according to any one of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer readable storage medium storing a computer program for causing a processor to execute the light adjustment method of the lighting fixture according to any embodiment of the present invention.

In the embodiment, the microwave radar is driven to emit a plurality of frames of original electromagnetic wave signals to the bedroom, and receives a plurality of frames of target electromagnetic wave signals reflected by the bedroom on the plurality of frames of original electromagnetic wave signals; for each frame of target electromagnetic wave signal, detecting the gesture presented by the user when the user moves in the bedroom according to the target electromagnetic wave signal; for each frame of target electromagnetic wave signal, detecting the distance between a user and the lighting lamp according to the target electromagnetic wave signal; correcting the distance and the gesture mutually; identifying a scene of the user activity in the bedroom according to the corrected gesture; and adjusting the light emitted by the lighting lamp according to the corrected distance and the scene. The light emitted by the lighting lamp is adaptively adjusted according to the distance and the scene, so that the light emitted by the lighting lamp can meet the requirements of users, the frequency of manually controlling the lighting lamp by the users is reduced, the convenience of controlling the lighting lamp is improved, and the time delay of controlling the lighting lamp is reduced.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a light adjusting method of a lighting fixture according to a first embodiment of the present invention;

fig. 2 is a schematic structural diagram of a light adjusting device of a lighting fixture according to a second embodiment of the present invention;

fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

Fig. 1 is a flowchart of a light adjusting method of a lighting fixture according to a first embodiment of the present invention, where the method may be performed by a light adjusting device of the lighting fixture according to a situation that a microwave radar detects a user's activity in a bedroom to correspondingly adjust the lighting fixture, where the light adjusting device of the lighting fixture may be implemented in hardware and/or software, and where the light adjusting device of the lighting fixture may be configured in an electronic device, and where the electronic device may be inherited in a switch of the lighting fixture or may be inherited in the lighting fixture. As shown in fig. 1, the method includes:

Step 101, driving a microwave radar to transmit a plurality of frames of original electromagnetic wave signals to a bedroom, and receiving a plurality of frames of target electromagnetic wave signals reflected by the bedroom to the plurality of frames of original electromagnetic wave signals.

In this embodiment, the lighting fixture may be in the form of a ceiling lamp, a wall lamp, or the like, and may be installed in a bedroom, and the lighting fixture is configured with a microwave radar for non-contact detection, tracking, and positioning of one or more objects by electromagnetic waves, where the operating frequency of the microwave radar is between 3MHz and 300GHz, and the wavelength is between 100m and 1 mm.

The antenna of the microwave radar emits an electromagnetic wave signal in the form of microwaves, which moves at the speed of light, and when the electromagnetic wave signal hits an object, the electromagnetic wave signal changes and is reflected back to the microwave radar. The electromagnetic wave signal arriving at the antenna of the microwave radar contains information about the detected object.

In the running process of the lighting lamp, the microwave radar can be continuously controlled to emit multi-frame electromagnetic wave signals to the bedroom, the electromagnetic wave signals emitted by the microwave radar are marked as original electromagnetic wave signals for convenience in distinguishing, and the microwave radar can continuously receive multi-frame electromagnetic wave signals reflected by the bedroom on the multi-frame original electromagnetic wave signals, and the electromagnetic wave signals received by the microwave radar are marked as target electromagnetic wave signals for convenience in distinguishing.

Step 102, detecting the gesture presented by the user when the user is active in the bedroom according to the target electromagnetic wave signal for each frame of the target electromagnetic wave signal.

In general, a user starts a lighting lamp in a bedroom, and reads (can be the reading behavior of a paper file or the reading behavior of electronic data such as a television, a movie, and the like), moves (such as yoga), rests and other activities by means of light emitted by the lighting lamp, so that the user is in the bedroom with high probability, targets are detected for each frame of target electromagnetic wave signals by taking the user as targets, the user is tracked, and the user in the bedroom can be detected, and at the moment, the gesture of the user when moving in the bedroom is detected for each frame of target electromagnetic wave signals.

In one embodiment of the present invention, step 102 may include the steps of:

step 1021, loading a preset gesture recognition network.

In this embodiment, the gesture recognition network may be constructed in advance based on deep learning, and the manually labeled sample (i.e., the electromagnetic wave signal and the gesture of the user labeled on the electromagnetic wave signal) is used to train the gesture recognition network, so that the gesture recognition network may be used to recognize the gesture of the user on the electromagnetic wave signal.

Structurally, the gesture recognition network has a depth separable convolutional layer (Depthwise Separable Convolution Layer), a Bi-directional long-short term memory network (Bi-directional Long Short Term Memory, bi-LSMT), a plurality of multi-layer perceptrons (Multilayer Perceptron, MLP).

The conventional convolution operation is to apply 32 convolution kernels of 3×3×16 to the input of 16 channels, and then obtain the required parameters of 32×3×16+1=4640 according to the calculation formula of the parameter amount of the convolution layer.

If 16 convolution kernels (3×3×1) with a size of 3×3 are applied to the inputs of 16 channels, 16 feature maps are obtained, and then the above obtained 16 feature maps are traversed by 32 convolution kernels (1×1×16) with a size of 1×1 before performing the fusion operation, and according to the calculation formula of the convolution layer parameters, the required parameters are (3×3×1×16+16) + (1×1×16×32+32) =706.

The above-mentioned process is that the feature extraction and feature combination of the common convolution layer are completed and output once, and the depth separable convolution firstly uses a convolution kernel (layered convolution depthwise) of 3*3 with thickness of 1, then uses a convolution kernel (point convolution pointwise) of 1*1 to adjust the channel number, and the feature extraction and feature combination are performed separately.

Bidirectional long and short time memory combines information of input sequences in both forward and backward directions on the basis of a long and short time memory network (directional Long Short Term Memory, LSMT). For the output of time t, the forward LSTM layer has information of time t and previous times in the input sequence, and the backward LSTM layer has information of time t and subsequent times in the input sequence. The output of the forward LSTM layer t moment is denoted as the output of the backward LSTM layer t moment, and the vectors output by the two LSTM layers may be processed by adding, averaging, or concatenating.

The multi-layer perceptron is divided into at least three layers. The first layer is an input layer, the last layer is an output layer, the middle is a hidden layer, multiple layers can be built according to the requirement, each layer can be provided with multiple nodes, and all nodes of adjacent layers are mutually connected. All nodes have the functions of inputting, outputting and storing data, and the hidden layer and the output layer have the functions of calculating weighted sums and activating function processing.

Each connecting line between adjacent layers contains different weights, represents the importance degree of the corresponding node of the previous layer, is generally stored in a matrix form, and is also biased between the adjacent two layers like a single-layer perceptron, and is generally stored in a vector form.

Step 1022, inputting the target electromagnetic wave signal into the depth separable convolution layer to extract the first electromagnetic wave feature in space for each frame of the target electromagnetic wave signal.

And sequentially inputting each frame of target electromagnetic wave signal into the depth separable convolution layer, and extracting the features of the depth separable convolution layer, namely the first electromagnetic wave features, of the target electromagnetic wave signal in a shallow layer in space.

Step 1023, inputting the first electromagnetic wave characteristic into the two-way long-short term memory network to extract the second electromagnetic wave characteristic on the time sequence.

For the first electromagnetic wave characteristics of each frame, two paths of processing can be divided, wherein one path of processing is performed, the first electromagnetic wave characteristics of each frame are input into a two-way long-short-period memory network, and the two-way long-period memory network extracts the characteristics on the time sequence and marks the characteristics as second electromagnetic wave characteristics.

Step 1024, sequentially performing normalization operation and activation operation on the first electromagnetic wave feature to obtain a third electromagnetic wave feature.

And the other path of processing, namely performing normalization operation on the first electromagnetic wave characteristics of each frame by using an operator such as BN (batch normalization), and performing activation operation on the first electromagnetic wave characteristics of each frame by using an operator such as RelU (Rectified Linear Unit, modified linear unit) if normalization operation is completed, so as to obtain third electromagnetic wave characteristics.

Step 1025, merging the second electromagnetic wave feature and the third electromagnetic wave feature into a fourth electromagnetic wave feature.

The second electromagnetic wave characteristic and the third electromagnetic wave characteristic are fused into the fourth electromagnetic wave characteristic by using Concat (increased channel number) algorithm and the like, the spatial characteristic jumps the connection of some neurons, the interlayer is connected with the characteristic on time sequence, the strong connection between the weakening layers can be increased, the information quantity of the fourth electromagnetic wave characteristic can be increased, and the accuracy of the subsequent recognition gesture is improved.

And 1026, respectively inputting the fourth electromagnetic wave characteristics into each multi-layer perceptron to map to the probability of a certain gesture.

Step 1027, determining the gesture corresponding to the probability with the largest numerical value as the gesture presented by the user when the user is active in the bedroom.

Each multi-layer perceptron is responsible for recognizing a specific gesture, so that the type of gesture recognizable by the gesture recognition network is consistent with the number of the multi-layer perceptrons, the fourth electromagnetic wave features are respectively input into each multi-layer perceptrons, and the multi-layer perceptrons perform multi-layer mapping on the fourth electromagnetic wave features, so that the probability of the gesture responsible for the occurrence of the current frame target electromagnetic wave signal is output.

And comparing the probabilities of the various gestures, and selecting the gesture corresponding to the probability with the largest numerical value as the gesture presented by the user when the user moves in the bedroom.

The user can perform activities in the bedroom in a limited manner, such as reading, movement, rest and other activities, and the activities are concentrated in gestures, such as reading, sitting, standing and lying in the postures of movement, and sitting and lying in the postures of rest, so that three multi-layer perceptrons can be configured in the gesture recognition network, including a first perceptron, a second perceptron and a third perceptron, wherein the first perceptron is responsible for recognizing the sitting, the second perceptron is responsible for recognizing the sitting, and the third perceptron is responsible for recognizing the lying.

In this example, the fourth electromagnetic wave feature is input into the first perceptron to map to a station probability, the fourth electromagnetic wave feature is input into the second perceptron to map to a sitting probability, and the fourth electromagnetic wave feature is input into the third perceptron to map to a lying probability.

Step 103, detecting the distance between the user and the lighting lamp according to the target electromagnetic wave signal for each frame of the target electromagnetic wave signal.

In this embodiment, according to different types of microwave radars, such as CW (single frequency microwave continuous wave) radar, IR-UWB (ultra wideband) radar, FMCW (linear frequency modulated continuous wave) radar, and the like, for each frame of target electromagnetic wave signal, the distance between the user and the microwave radar may be measured according to the characteristic amounts of the phase difference, time difference, difference value, and the like of the target electromagnetic wave signal and the original electromagnetic wave signal, and may be assigned as the distance between the user and the illumination lamp.

Step 104, the distance and the gesture are mutually corrected.

When the distance between the user and the lighting lamp and the gesture of the user are detected by using the target electromagnetic wave signals, errors such as accuracy of an algorithm and the like can occur, and target electromagnetic wave signal anomalies (such as microwave radar anomalies, microwave radar blocked by flies and other obstacles) can also occur, the distance between the user and the lighting lamp and the gesture of the user are detected according to the same sequence of target electromagnetic wave signals, and certain correlation exists between the distance between the user and the lighting lamp and between the gesture of the user and the target electromagnetic wave signal of the same frame, so that the distance between the user and the lighting lamp and the gesture of the user can be compared, the distance between the user and the lighting lamp and the gesture of the user are corrected mutually, and the situation of the target electromagnetic wave signal anomalies is eliminated.

In one embodiment of the present invention, step 104 may include the steps of:

in step 1041, the gestures are arranged into a first sequence and the pair distances are arranged into a second sequence according to the time sequence.

For the gestures of the user, the gestures may be arranged in a time sequence (e.g., from small to large, i.e., from far to near) to obtain a first sequence.

For the distance between the user and the microwave radar, the distances may be arranged in time order (e.g. from small to long to short), resulting in a second sequence.

Since the target electromagnetic wave signal has the detection time, when the distance between the user and the lighting fixture and the gesture of the user are detected by using the target electromagnetic wave signal, the distance between the user and the lighting fixture and the gesture of the user all carry the time stamp of the target electromagnetic wave signal, and therefore, the distance and the gesture which are positioned at the same position on the first sequence and the second sequence are detected by the target electromagnetic wave signal of the same frame.

Step 1042, adding a first window in the first sequence and sliding the first window.

Adding a preset first window from a starting point in the first sequence, and sliding the first window according to a preset step length at each moment, wherein the step length is generally smaller than the length of the first window.

Step 1043, adding a second window in the second sequence, and sliding the second window.

Adding a preset second window from the starting point in the second sequence, and sliding the second window according to a preset step length at each moment, wherein the step length is generally smaller than the length of the second window.

The length of the first window is the same as that of the second window, and the sliding step length is the same, so that the position of the first window in the first sequence is the same as that of the second window in the first sequence at each moment, that is, the distance between the gesture in the first window and the distance between the gesture in the second sequence at each moment are detected by the same frame of target electromagnetic wave signal.

Step 1044, screening out abnormal gestures in the first window according to the gesture change trend, and using the abnormal gestures as the first abnormal points.

In a shorter time, the gesture of the user is basically in a continuously changing state and no abrupt change exists, so that the abnormal gesture can be screened out according to the change trend of the gesture in the first window and is marked as a first abnormal point.

In a specific implementation, the gesture at the midpoint of the first window is set to a target state.

And respectively counting a first reference state for the gestures positioned on the left side of the target state in the first window and counting a second reference state for the gestures positioned on the right side of the target state in the first window so as to represent the change trend of the gestures, wherein the first reference state is a gesture with the ratio exceeding a preset first threshold value in all the gestures positioned on the left side of the target state, and the second reference state is a gesture with the ratio exceeding a preset second threshold value in all the gestures positioned on the right side of the target state.

If the first reference state and the second reference state are not empty (i.e. all the postures on the left side of the target state and all the postures on the right side of the target state are in a stable state), and the target state is not the same as any one of the first reference state and the second reference state, determining that the target state is abnormal as a first abnormal point.

If the first reference state is empty, the second reference state is not empty (i.e. all the gestures on the left side of the target state are in the transformed critical state, the gesture recognition network cannot clearly distinguish the gestures of the user, all the gestures on the right side of the target state are in a stable state), and the gestures on the left side of the target state in the first window are different, the target state is determined to be abnormal and used as the first abnormal point.

If the first reference state is not empty, the second reference state is empty (i.e. all the gestures on the left side of the target state are in a stable state, all the gestures on the right side of the target state are in a transformed critical state, the gesture recognition network cannot clearly distinguish the gestures of the user), and the gestures on the right side of the target state in the first window are different, the target state is determined to be abnormal and used as a first abnormal point.

Step 1045, screening the abnormal distance from the second window according to the change trend of the distance, and using the abnormal distance as the second abnormal point.

In a shorter time, the position of the user is basically in a continuously changing state, so that the distance between the user and the lighting lamp is free from abrupt change, and therefore, the abnormal distance can be screened out according to the change trend of the distance in the second window and is recorded as a second abnormal point.

In a specific implementation, a plurality of distances with the largest value and a plurality of distances with the smallest value are filtered out in the second window, so that the influence of the accuracy of the distance measuring algorithm is reduced.

If filtering is completed, calculating an average value of the remaining distances in the second window.

For each distance in the second window, a first difference between the distance and the average value is calculated, and the first difference is compared with a preset error range.

If the first difference value is in the error range, the change trend of the distance mark is 0, which indicates that the change trend is stable.

If the first difference is smaller than the lower limit value of the error range or larger than the upper limit value of the error range, the difference is mapped into a change trend of the distance, and the descending amplitude or the ascending amplitude of the change trend is indicated.

The sign of the variation trend is the same as the sign of the first difference, that is, the sign of the first difference is negative, the sign of the variation trend is negative, the sign of the first difference is positive, and the sign of the variation trend is positive.

And, the value of the variation trend is positively correlated with the value of the first difference, i.e., the larger the value of the first difference, the larger the value of the variation trend, the smaller the value of the first difference, and the smaller the value of the variation trend.

For example, a trend of-1 indicates a 1-step decrease in distance, a trend of-2 indicates a 2-step decrease in distance, a trend of 1 indicates a 1-step increase in distance, and a trend of 2 indicates a 2-step increase in distance.

And respectively calculating a second difference value between the change trend of the current distance and the change trend of two adjacent distances according to the current distance.

If the two second difference values are larger than 1, the change is larger, and the current distance is determined to be abnormal and used as a second abnormal point.

Step 1046, if the position of the first abnormal point in the first window is the same as the position of the second abnormal point in the second window, performing interpolation processing on the first abnormal point according to the variation trend of the gesture in the first window to correct the first abnormal point, and performing interpolation processing on the second abnormal point according to the variation trend of the distance in the second window to correct the second abnormal point.

If the position of the first abnormal point in the first window is the same as the position of the second abnormal point in the second window, the probability of representing the abnormality of the target electromagnetic wave signal is higher, at this time, for the first abnormal point, interpolation processing can be performed on the first abnormal point according to the change trend of the gesture in the first window, thereby correcting the first abnormal point, and for the second abnormal point, interpolation processing can be performed on the second abnormal point according to the change trend of the distance in the second window, thereby correcting the second abnormal point.

Step 105, recognizing the scene of the user activity in the bedroom according to the corrected gesture.

If the distance between the user and the lighting fixture and the gesture of the user are corrected mutually, the scene of the user activity in the bedroom can be identified by using the corrected gesture based on deep learning, mechanical learning, rules and the like.

In one embodiment of the invention, decision trees may be constructed and trained beforehand based on machine learning using manually annotated samples (i.e., corrected poses and scenes annotated to the poses) so that the decision trees may be used to identify scenes of user activity from the user's poses.

In this embodiment, a preset decision tree may be loaded, the corrected poses (i.e. sitting, standing, lying) are arranged in a time sequence into a third sequence, a third window is added in the third sequence, and the third window is slid according to a preset step size, which is generally smaller than the length of the third window.

The corrected gestures in the third window are used as attributes of the user, the attributes are sequentially input into a decision tree, the scene of the user moving in the bedroom is decided to be reading, moving or resting, and as the gestures of the user are not clearly distinguished, certain errors exist when the gesture recognition network recognizes the gestures, the decision tree makes a decision on a series of gestures, the influence caused by the sporadic nature of the gestures can be reduced, and the accuracy of recognizing the scene is improved.

And 106, adjusting the light emitted by the lighting lamp according to the corrected distance and the scene.

In the scene of different activities, the light that the user needs can exist certain difference to the light that the illumination lamps and lanterns sent can decay along with the increase of the distance between user and the illumination lamps and lanterns, consequently, in this embodiment, can adjust the light that the illumination lamps and lanterns sent under the constraint of the distance after the correction, make the light that the illumination lamps and lanterns sent and scene adaptation.

In a specific implementation, a mapping table matched with a scene can be loaded, the mapping table records the relation between the distance mapping and the brightness and/or the color temperature, the mapping table can be generated by simulating various active scenes in an experimental environment by technicians, the mapping table is preset in the lighting lamp before the lighting lamp leaves the factory, and the mapping table can be updated and maintained by a cloud after the lighting lamp leaves the factory.

The corrected distance is used as a key word of an index, brightness and/or color temperature of the corrected distance map is queried in a mapping table, the distance is generally recorded in a range form in the mapping table, the corrected distance is compared with each range in the mapping table, and if the corrected distance is within a certain range, the brightness and/or color temperature of the range map can be extracted.

The brightness and/or color temperature is issued to the driving circuit of the lighting fixture, whereby the brightness and/or color temperature of the lighting fixture is adjusted such that the lighting fixture emits light according to the brightness and/or color temperature, adapting the scene of the activity performed by the user at the distance (after correction).

Example two

Fig. 2 is a schematic structural diagram of a light adjusting device of a lighting lamp according to a second embodiment of the present invention. The lighting fixture is installed in a bedroom and is provided with a microwave radar, as shown in fig. 2, the device comprises:

the microwave detection module 201 is configured to drive the microwave radar to transmit a plurality of frames of original electromagnetic wave signals to the bedroom, and receive a plurality of frames of target electromagnetic wave signals reflected by the bedroom to a plurality of frames of original electromagnetic wave signals;

a gesture recognition module 202, configured to detect, for each frame of the target electromagnetic wave signal, a gesture that is presented when a user is active in the bedroom according to the target electromagnetic wave signal;

a distance detection module 203, configured to detect, for each frame of the target electromagnetic wave signal, a distance between the user and the lighting fixture according to the target electromagnetic wave signal;

a correction module 204, configured to correct the distance and the gesture;

a scene recognition module 205, configured to recognize a scene of the user's activity in the bedroom according to the corrected gesture;

and the light adjusting module 206 is used for adjusting the light emitted by the lighting lamp according to the corrected distance and the scene.

In one embodiment of the present invention, the gesture recognition module 202 is further configured to:

In one embodiment of the present invention, the multi-layer perceptron includes a first perceptron, a second perceptron, a third perceptron; the gesture recognition module 202 is further configured to:

In one embodiment of the present invention, the correction module 204 is further configured to:

adding a first window in the first sequence, and sliding the first window;

setting the gesture at a midpoint of the first window to a target state;

In one embodiment of the present invention, the scene recognition module 205 is further configured to:

loading a preset decision tree;

adding a third window in the third sequence, and sliding the third window;

In one embodiment of the present invention, the light adjustment module 206 is further configured to:

The light adjusting device of the lighting lamp provided by the embodiment of the invention can execute the light adjusting method of the lighting lamp provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the light adjusting method of the lighting lamp.

Example III

Fig. 3 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 3, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the light adjustment method of the lighting fixture.

In some embodiments, the light adjustment method of the lighting fixture may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the light adjustment method of the lighting fixture described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the light adjustment method of the lighting fixture by any other suitable means (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

Example IV

Embodiments of the present invention also provide a computer program product comprising a computer program which, when executed by a processor, implements a light adjustment method of a lighting fixture as provided by any of the embodiments of the present invention.

Computer program product in the implementation, the computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method of adjusting the light of a lighting fixture, the lighting fixture being installed in a bedroom and configured with a microwave radar, the method comprising:

correcting the distance and the gesture mutually;

adjusting the light emitted by the lighting lamp according to the corrected distance and the scene;

wherein the detecting, for each frame of the target electromagnetic wave signal, a gesture that a user exhibits when the user is active in the bedroom according to the target electromagnetic wave signal includes:

2. The method of claim 1, wherein the multi-layer perceptron comprises a first perceptron, a second perceptron, a third perceptron;

3. The method of any of claims 1-2, wherein said mutually modifying said distance and said pose comprises:

Adding a first window in the first sequence, and sliding the first window;

4. A method according to claim 3, wherein said screening out the abnormal gesture in the first window according to the trend of the gesture comprises:

If the gesture is located at the midpoint of the first window, setting the gesture as a target state;

counting a first reference state for the gesture positioned on the left side of the target state in the first window and counting a second reference state for the gesture positioned on the right side of the target state in the first window respectively so as to represent the change trend of the gesture, wherein the first reference state is the gesture with the duty ratio exceeding a preset first threshold value, and the second reference state is the gesture with the duty ratio exceeding a preset second threshold value;

if the first reference state is not empty, the second reference state is empty, and the target state is different from the gesture positioned on the right side of the target state in the first window, determining that the target state is abnormal, and taking the abnormal target state as a first abnormal point;

The step of screening the abnormal distance in the second window according to the change trend of the distance, as a second abnormal point, includes:

5. The method according to any of claims 1-2, wherein said identifying a scene of the user's activity in the bedroom from the gesture after correction comprises:

loading a preset decision tree;

adding a third window in the third sequence, and sliding the third window;

6. The method according to any one of claims 1-2, wherein said adjusting the light emitted by the lighting fixtures according to the distance and the scene after correction comprises:

7. A light regulating device of a lighting fixture, wherein the lighting fixture is installed in a bedroom and configured with a microwave radar, the device comprising:

the light adjusting module is used for adjusting the light emitted by the lighting lamp according to the corrected distance and the scene;

wherein, the gesture recognition module is further configured to:

8. An electronic device, the electronic device comprising:

at least one processor; and

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the light adjustment method of the lighting fixture of any one of claims 1-6.

9. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program for causing a processor to execute the light adjustment method of the lighting fixture of any one of claims 1-6.