CN116455522A - Method and system for transmitting lamplight interaction control information - Google Patents
Method and system for transmitting lamplight interaction control information Download PDFInfo
- Publication number
- CN116455522A CN116455522A CN202310693910.1A CN202310693910A CN116455522A CN 116455522 A CN116455522 A CN 116455522A CN 202310693910 A CN202310693910 A CN 202310693910A CN 116455522 A CN116455522 A CN 116455522A
- Authority
- CN
- China
- Prior art keywords
- information
- target
- preset
- interaction information
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000005540 biological transmission Effects 0.000 claims abstract description 89
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 57
- 230000007704 transition Effects 0.000 claims abstract description 42
- 238000003909 pattern recognition Methods 0.000 claims description 31
- 230000004927 fusion Effects 0.000 claims description 28
- 230000009471 action Effects 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 21
- 230000002452 interceptive effect Effects 0.000 claims description 20
- 238000005070 sampling Methods 0.000 claims description 19
- 230000002829 reductive effect Effects 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000009467 reduction Effects 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 230000001953 sensory effect Effects 0.000 claims 1
- 230000001133 acceleration Effects 0.000 description 11
- 230000008859 change Effects 0.000 description 9
- 230000000694 effects Effects 0.000 description 9
- 230000011218 segmentation Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 5
- 210000002569 neuron Anatomy 0.000 description 5
- 238000003708 edge detection Methods 0.000 description 4
- 238000011084 recovery Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 230000036961 partial effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000004043 responsiveness Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
- H04L1/0002—Systems modifying transmission characteristics according to link quality, e.g. power backoff by adapting the transmission rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0499—Feedforward networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/04—Protocols for data compression, e.g. ROHC
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/06—Optimizing the usage of the radio link, e.g. header compression, information sizing, discarding information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
- H04W28/18—Negotiating wireless communication parameters
- H04W28/22—Negotiating communication rate
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
- H05B47/105—Controlling the light source in response to determined parameters
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
- H05B47/165—Controlling the light source following a pre-assigned programmed sequence; Logic control [LC]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Abstract
The invention relates to the technical field of control, and particularly provides a method and a system for transmitting lamplight interaction control information, which are used for transmitting lamplight control information, and comprise the steps of acquiring various sensing information of sensors held by a plurality of target objects in a target area, fusing the various sensing information to determine sensing characteristics, and determining interaction information of the plurality of target objects through a pre-constructed mode recognition model based on the sensing characteristics and skeleton information preset by the target objects; according to the network state and bandwidth information of the target area, compressing the interaction information through a self-adaptive transmission algorithm, dynamically adjusting the transmission rate of the compressed interaction information, and transmitting the compressed interaction information to the light controller; and the light controller is combined with the smooth transition control algorithm to control the target lamp to display according to the control mode corresponding to the interaction information.
Description
Technical Field
The disclosure relates to the technical field of control, and in particular relates to a method and a system for transmitting lamplight interaction control information.
Background
In the existing travel scene, the lamplight shows often through the program control display effect that prestores, be difficult to produce the interdynamic with the user, the user often only is ornamental, can't interdynamic to need spectator to wear intelligent wearing equipment, increased spectator's burden, wearing equipment's signal transmission stability also can influence interactive effect simultaneously. In addition, the traffic of people in holiday scenic spots is large, the situation of network congestion is easy to occur, if the interactive control instruction of the user is transmitted to the light controller in a wireless transmission mode, the situation of network congestion and transmission delay can be caused, user experience is reduced, and the light control effect is poor.
Disclosure of Invention
The embodiment of the disclosure provides a method and a system for transmitting lamplight interaction control information, which can at least solve part of problems in the prior art, namely, an audience needs to wear intelligent wearing equipment, the burden of the audience is increased, and meanwhile, the interaction effect can be possibly influenced by the stability of signal transmission of the wearing equipment.
In a first aspect of embodiments of the present disclosure,
the method for transmitting the lamplight interaction control information comprises the following steps:
acquiring various sensing information of sensors held by a plurality of target objects in a target area, fusing the various sensing information to determine sensing characteristics, and determining interaction information of the plurality of target objects through a pre-constructed pattern recognition model based on the sensing characteristics and skeleton information preset by the target objects, wherein the pattern recognition model is constructed based on a neural network and is used for matching a preset pattern for input information;
Compressing the interaction information through a self-adaptive transmission algorithm according to the network state and bandwidth information of the target area, dynamically adjusting the transmission rate of the compressed interaction information, and transmitting the compressed interaction information to a light controller;
and the lamplight controller controls the target lamp to display according to a control mode corresponding to the interaction information by combining a smooth transition control algorithm based on the compressed interaction information, wherein the smooth transition control algorithm is used for generating a smooth numerical sequence to control the target lamp.
In an alternative embodiment of the present invention,
the determining the interaction information of the plurality of target objects through a pre-constructed mode recognition model based on the sensing characteristics and preset skeleton information comprises:
respectively inputting the skeleton feature and the sensing feature into the pattern recognition model, setting a punishment factor and a discarding factor in a hidden layer of the pattern recognition model, fusing the skeleton feature and the sensing feature through a forward propagation algorithm, and determining a fused feature;
and determining similarity scores of the fusion features and the preset pattern templates according to a pattern matching algorithm, wherein the preset pattern template with the highest similarity score is used as interaction information of a plurality of target objects.
In an alternative embodiment of the present invention,
setting a penalty factor and a discard factor in a hidden layer of the pattern recognition model, and fusing the skeleton feature and the sensing feature through a forward propagation algorithm to determine a fusion feature comprises:
setting a jump connection block in a hidden layer of the pattern recognition model, taking the added result of the input and the output of the hidden layer as the input of the next hidden layer, setting a discarding factor in the hidden layer, randomly setting the output value of the hidden layer to be zero, and summarizing all the output values of the hidden layer;
setting a penalty factor in a loss function of the pattern recognition model, and determining fusion characteristics by combining all output values of the hidden layer;
the determining the similarity score of the fusion feature and the preset pattern template according to the pattern matching algorithm comprises the following steps:
the similarity score is determined as shown in the following formula:
；
；
；
wherein sim (x [ i ] y [ j ]) represents a similarity score between the fusion feature x [ i ] and a preset pattern template y [ j ], weight (i, j) represents a weight value obtained by dynamically adjusting an ith element in the fusion feature and a jth element in the preset pattern template, D (x [ i ], y [ j ]) represents a spatial distance between the ith element in the fusion feature and the jth element in the preset pattern template, and min (D [ i-1] [ j ], D [ i ] [ j-1 ]) represents a minimum path value of each element in a two-dimensional matrix corresponding to the fusion feature and the preset pattern template.
In an alternative embodiment of the present invention,
the compressing the interaction information through the adaptive transmission algorithm according to the network state and the bandwidth information of the target area and dynamically adjusting the transmission rate of the compressed interaction information comprises the following steps:
initializing the size of a congestion window, executing a quick retransmission mechanism when retransmission loss occurs, and repeatedly sending the earliest unacknowledged message segment;
when continuous packet loss is detected, a selective retransmission mechanism is executed, and only lost message segments are retransmitted;
the transmission rate is calculated from the congestion window size and the round trip time.
In an alternative embodiment of the present invention,
the method further comprises the steps of:
dividing the compressed interaction information into a plurality of data streams, and carrying out parallel transmission and load balancing through a plurality of preset independent transmission channels;
an independent congestion window adjustment strategy is distributed for each data flow, and the transmission rate is dynamically adjusted according to the congestion condition;
and monitoring the network congestion condition of each transmission channel by using an independent congestion detection mechanism, and adopting a corresponding congestion control strategy according to the congestion condition.
In an alternative embodiment of the present invention,
the light controller controls the target lamp to display according to the control mode corresponding to the interaction information by combining the smooth transition control algorithm based on the compressed interaction information comprises the following steps:
Determining the action speed of the target object based on the interaction information, and determining the transition time by combining the current state and the target state of the target lamp;
and calculating an intermediate transition value according to the current state and the target state through linear interpolation and a buffer function, and mapping the intermediate transition value into a control parameter through a mapping function to control the target lamp.
In an alternative embodiment of the present invention,
the calculating the intermediate transition value by linear interpolation and a buffer function according to the current state and the target state comprises:
；
wherein M is value Represents an intermediate transition value, C value 、T value Representing the current state and the target state respectively, easingFunction (t) the creep function and t the interpolation parameter.
In a second aspect of the embodiments of the present disclosure,
provided is a system for transmitting interactive control information of lamplight, comprising:
the first unit is used for acquiring various sensing information of sensors held by a plurality of target objects in a target area, fusing the various sensing information to determine sensing characteristics, and determining interaction information of the plurality of target objects through a pre-constructed pattern recognition model based on the sensing characteristics and skeleton information preset by the target objects, wherein the pattern recognition model is constructed based on a neural network and is used for matching a preset pattern for input information;
The second unit is used for compressing the interaction information through a self-adaptive transmission algorithm according to the network state and the bandwidth information of the target area, dynamically adjusting the transmission rate of the compressed interaction information and transmitting the compressed interaction information to the light controller;
and the third unit is used for controlling the target lamp to display according to the control mode corresponding to the interaction information by combining a smooth transition control algorithm based on the compressed interaction information, wherein the smooth transition control algorithm is used for generating a smooth numerical sequence to control the target lamp.
In a third aspect of the embodiments of the present disclosure,
provided is a light interaction control information transmission device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the instructions stored in the memory to perform the method described previously.
In a fourth aspect of embodiments of the present disclosure,
there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method as described above.
The beneficial effects of the embodiments of the present disclosure may refer to the corresponding technical parts of the specific embodiments, and are not described herein again.
Drawings
Fig. 1 is a flow chart illustrating a method for transmitting lamplight interaction control information according to an embodiment of the disclosure;
fig. 2 is a schematic structural diagram of a lamplight interaction control information transmission system according to an embodiment of the disclosure.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present disclosure more apparent, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, not all embodiments. Based on the embodiments in this disclosure, all other embodiments that a person of ordinary skill in the art would obtain without making any inventive effort are within the scope of protection of this disclosure.
The technical scheme of the present disclosure is described in detail below with specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
Fig. 1 is a flow chart of a method for transmitting lamplight interaction control information according to an embodiment of the disclosure, as shown in fig. 1, where the method includes:
s101, acquiring various sensing information of sensors held by a plurality of target objects in a target area, fusing the various sensing information to determine sensing characteristics, and determining interaction information of the plurality of target objects through a pre-constructed mode recognition model based on the sensing characteristics and skeleton information preset by the target objects;
For example, the target area in the present application may include an area satisfying image information of a plurality of target objects that the image device acquires standing in the target area, and setting a specific target area is not only beneficial to managing the plurality of target objects, but also to set a light band around the target area, which is adjusted in real time according to a change in the number of target objects, for example, when the number of target objects increases, the brightness, the intensity, or the coverage area of the light band may be increased to create a more spectacular effect, whereas when the number of target objects decreases, the intensity or the range of the light band may be reduced to maintain an appropriate atmosphere.
Optionally, image information of a plurality of target objects in the target area can be acquired through an image device, wherein the image information can comprise a visible light image, the image information comprises a whole body image of the target objects, and the whole body image is used for subsequently extracting skeleton features of the target objects and analyzing actions of the target objects; the sensor held by the target object can comprise sensing equipment with an accelerometer and a gyroscope, and the sensing characteristics are determined by fusing acceleration information and angular velocity information and used for acquiring hand control actions of the target object.
In an alternative embodiment of the present invention,
the extracting skeleton features of the plurality of target objects based on the image information includes:
setting an initialization weight for each pixel in the image information, introducing a learning factor and a time attenuation factor, performing self-adaptive background identification, and dividing the background information and the target information in the image information;
for example, in a travel scene, the illumination environment is often changed severely, and to identify skeleton features of a plurality of target objects from a plurality of scenes of tourists, first, the plurality of target objects need to be determined first, and to determine the plurality of target objects, the plurality of target objects need to be identified from the background information, that is, the target objects need to be segmented from the background information.
In an alternative embodiment of the present invention,
setting an initialization weight for each pixel in the image information, introducing a learning factor and a time attenuation factor, performing self-adaptive background recognition, and dividing the background information from the target information in the image information comprises:
after an initialization weight is set for each pixel in the image information, determining a difference value between each pixel point and a preset background threshold value based on the initialization weight and a pixel value, if the difference value is greater than 0, setting the pixel point as foreground information, and if the difference value is less than 0, setting the pixel point as background information, wherein the foreground information belongs to target information;
And reserving the pixels set as the foreground information, introducing a learning factor and a time attenuation factor to update the weight values of the rest pixels until the segmentation of the foreground information and the background information of all the rest pixels is completed.
For each pixel point, the pixel point can be divided into foreground information and background information, wherein the foreground information is target information, and after the foreground information and the background information are divided, edge information of the target information can be extracted for skeleton extraction; in order to improve the segmentation accuracy of the foreground information and the background information, an initialization weight can be set for each pixel in the image information, wherein the initialization weight can be set randomly, and the value of the initialization weight can be a natural number between 0 and 1; after multiplying the initialization weight and the pixel value, determining the difference value between the initialization weight and a preset background threshold value, if the difference value is larger than 0, determining the pixel point as foreground information, and if the difference value is smaller than 0, determining the pixel point as background information, so as to realize preliminary segmentation. In order to further improve the accuracy of segmentation, the pixels of the foreground information can be reserved, and a learning factor and a time attenuation factor are introduced to update the weight value of the subsequent pixels.
The learning factors can dynamically adjust the change rates of different pixels in the image information according to the reliability and stability of the pixel points; the temporal decay factor may be used to balance the weights of pixels in the foreground and background information, so that the nearest information has higher weight, while the past information has progressively lower weight.
In an alternative embodiment of the present invention,
reserving the pixels set as the foreground information, and introducing the learning factors and the time attenuation factors to update the weight values of the rest pixels comprises the following steps:
the weight value is updated according to the method shown in the following formula:
；
wherein W is i+1 Representing the weight value, W, corresponding to the (i+1) th pixel point i Representing the weight value corresponding to the ith pixel point, I max Representing the number of pixel points, R i Representing learning factors corresponding to the ith pixel point, T i Represents the time attenuation factor corresponding to the i+1th pixel point,W 0 representing the initial weight value, P aver Representing the pixel mean of all pixels.
By updating based on pixel weight, the modeling capability of dynamic textures and moving objects can be improved, the interference to the dynamic textures and the moving objects is reduced, the adaptability to scene changes such as illumination changes and the like is enhanced, the noise and instability of background segmentation are reduced, and the accuracy of foreground detection is improved. The variation of different pixels can be segmented more adaptively, more reliable and stable pixels will have higher weights and thus more contributing to the updating of the background segmentation, and unstable or disturbed pixels will have lower weights and thus reduce their impact on the background segmentation.
Extracting edge information of the segmented target information through an edge detection algorithm, and performing skeleton connection through a skeleton connection algorithm to determine skeleton characteristics of the plurality of target objects;
for example, a target detection algorithm (such as a feature-based detector, a deep-learning target detection model, etc.) may be used to detect the position and bounding box of the target in the image, and then, according to the target detection result, extract the image of the target region from the target information obtained by the background segmentation;
then carrying out graying or binarization processing on the target image so as to facilitate subsequent processing, and extracting edge information in the target image by utilizing an edge detection algorithm; based on the extracted edge information, a skeletonizing algorithm (such as a refining algorithm, a medial axis transformation and the like) is applied to convert the target image into a skeletonized representation; and (3) performing skeleton connection operation according to the skeletonization result, and connecting the broken skeleton line segments to obtain the complete target skeleton characteristics. The edge detection algorithm may include a Canny edge detection algorithm, and the application of the skeletonizing algorithm may include a refinement algorithm, a medial axis transformation algorithm, and the like.
In an alternative embodiment of the present invention,
Fusing the plurality of sensing information to determine a sensing characteristic includes:
illustratively, the sensing information includes acceleration information and angular velocity information, where the sensor held by the target object may include a sensing device with an accelerometer and a gyroscope, where after the data measured by the accelerometer sensor and the gyroscope sensor are converted, the control actions of the target object may be described, but both have the defect that they cannot be ignored separately: the accelerometer has good static performance, but when the sensing equipment is in a motion state, an acceleration is generated in the horizontal direction, and the accelerometer measures the combined acceleration of the component of the gravity acceleration in the horizontal direction and the acceleration in the horizontal direction, so that high-frequency noise interference is generated, and the accuracy of the angle value acquired by the accelerometer is influenced.
The gyroscope has good short-time stability, but static drift can be generated due to the fact that the gyroscope is not perfect in structure and is influenced by factors such as temperature change, magnetic field interference and the like. Although the drift error value is extremely small, the integration operation causes an accumulated error in the angle value, and even an extremely small drift value is accumulated to obtain an extremely large angle error.
From the above analysis, it is clear that, when an accelerometer or a gyro sensor is used alone, the obtained results have large errors, and therefore, it is necessary to fuse the sensing information obtained by the two sensors.
And respectively determining acceleration offset information corresponding to the acceleration information and angular velocity offset information corresponding to the angular velocity information, judging whether the filter gain equation is converged according to the acceleration information, the acceleration offset information, the angular velocity information and the angular velocity offset information and by combining the filter gain equation, and if so, fusing the acceleration information and the angular velocity information in a vector splicing mode.
Illustratively, the filter gain equation of the present application may be represented by the following formula:
；
wherein K (t) and K (t-1) respectively represent the filter gain equations at the time t and the time t-1, and d t Representing the estimated mean square error value at time t,a transpose matrix of the state estimation matrix representing the time t; v (t) represents the measurement noise covariance matrix at time t.
Wherein the convergence criterion is represented by the following formula:
；
wherein P is CON Represents convergence criteria, time loss Representing the time-varying fading factor, con c Represents the convergence adjustment coefficient and,state estimation indicating convergence of t-1 to t-1, K 0 And (t) represents an initial filter gain equation corresponding to the time t.
The measurement noise covariance matrix is used for indicating noise information caused in the actual measurement process of the sensor, errors caused by noise can be comprehensively considered through representation of the covariance matrix, whether a gain equation is converged or not is determined through combination of convergence criteria, and accuracy of finally obtained fusion features is improved.
For example, the pattern recognition model of the embodiment of the present disclosure may be constructed based on a neural network, and is used for matching a preset pattern for input information, where the preset pattern may include a plurality of pre-stored pattern types, for example, a shaking action of a user may trigger a flickering effect of light, a rotation action of the user may control a color change of the light, when a group moves as a whole, the light may change with a speed and a direction of movement, for example, when the group moves in a certain direction, the light may present a flowing effect; when the group stops, the light may stabilize or fade to other effects.
In an alternative embodiment of the present invention,
the determining the fusion characteristic by fusing the skeleton characteristic and the sensing characteristic based on the pre-constructed mode recognition model, and determining the interaction information of the plurality of target objects based on the fusion characteristic and the pre-set mode template comprises the following steps:
Respectively inputting the skeleton feature and the sensing feature into the pattern recognition model, setting a punishment factor and a discarding factor in a hidden layer of the pattern recognition model, fusing the skeleton feature and the sensing feature through a forward propagation algorithm, and determining a fused feature;
and determining similarity scores of the fusion features and the preset pattern templates according to a pattern matching algorithm, wherein the preset pattern template with the highest similarity score is used as interaction information of a plurality of target objects.
Optionally, the pattern recognition model of the present application may be constructed based on an improved multi-layer sensor, where a jump connection block is set between the input and the output of the hidden layer, and the input and the output of the hidden layer are directly added, so that information can be more easily propagated in the network, and the gradient vanishing problem is alleviated, where a specific formula may be: hidden_output=Hidden_input+F (Hidden_input), where F () is a nonlinear transformation function of the Hidden layer, hidden_output represents the Output of the Hidden layer, and Hidden_input represents the Input of the Hidden layer. In addition, the pattern recognition model of the method is provided with a penalty factor in a loss function, is used for controlling the model complexity of the pattern recognition model, and is beneficial to reducing the overfitting. Further, when the pattern recognition model is trained, partial neurons are randomly selected with a certain probability (usually 0.5), and the output values of the partial neurons are set to be zero, so that overfitting dependency among the neurons can be further prevented, and the network is forced to learn multiple independent characteristic representations. During the forward and backward propagation, the discarded neurons do not participate in the computation, but all neurons need to be preserved at the time of prediction to improve the generalization ability and robustness of the model.
In an alternative embodiment of the present invention,
setting a penalty factor and a discard factor in a hidden layer of the pattern recognition model, and fusing the skeleton feature and the sensing feature through a forward propagation algorithm to determine a fusion feature comprises:
setting a jump connection block in a hidden layer of the pattern recognition model, taking the added result of the input and the output of the hidden layer as the input of the next hidden layer, setting a discarding factor in the hidden layer, randomly setting the output value of the hidden layer to be zero, and summarizing all the output values of the hidden layer;
setting a penalty factor in a loss function of the pattern recognition model, and determining fusion characteristics by combining all output values of the hidden layer;
the determining the similarity score of the fusion feature and the preset pattern template according to the pattern matching algorithm comprises the following steps:
the similarity score is determined as shown in the following formula:
；
；
；
wherein sim (x [ i ] y [ j ]) represents a similarity score between the fusion feature x [ i ] and a preset pattern template y [ j ], weight (i, j) represents a weight value obtained by dynamically adjusting an ith element in the fusion feature and a jth element in the preset pattern template, D (x [ i ], y [ j ]) represents a spatial distance between the ith element in the fusion feature and the jth element in the preset pattern template, and min (D [ i-1] [ j ], D [ i ] [ j-1 ]) represents a minimum path value of each element in a two-dimensional matrix corresponding to the fusion feature and the preset pattern template.
According to the method and the device, the weight value is adaptively changed according to the local attribute of the time sequence, so that the accuracy of pattern matching is enhanced, interaction information corresponding to the actual control effect of the target object is obtained, the control accuracy is improved, and the user experience is improved.
Alternatively, a preset pattern template, such as an action sequence or a gesture sequence, may be used to match the fusion feature, a similarity score between the fusion feature and the pattern template may be calculated using a pattern matching algorithm, and interaction information of the target object may be determined based on the similarity score, such as triggering a specific lighting effect, playing music, and the like.
S102, compressing the interaction information through a self-adaptive transmission algorithm according to the network state and bandwidth information of the target area, dynamically adjusting the transmission rate of the compressed interaction information, and transmitting the compressed interaction information to a light controller;
for example, in order to improve the interactive experience of the user, the present application may transmit the interactive information of the user to the light controller in a wireless transmission manner, and in order to avoid the situation that the transmission delay of the interactive information is delayed or even the data is lost due to network congestion in a special holiday such as holiday, the present application embodiment compresses the interactive information through an adaptive transmission algorithm according to the network state and the bandwidth information of the target area, and dynamically adjusts the transmission rate of the compressed interactive information.
In an alternative embodiment of the present invention,
the compressing the interaction information through the adaptive transmission algorithm according to the network state and the bandwidth information of the target area and dynamically adjusting the transmission rate of the compressed interaction information, and transmitting the compressed interaction information to the light controller comprises the following steps:
window sampling is carried out on the interactive information according to a preset sampling window, data sampled by the window are mapped into sampling symbols according to a preset mapping relation, frequency statistics is carried out on the sampling symbols, and symbol frequency of the sampling symbols is determined; according to the sampling symbol and the symbol frequency, the interactive information is encoded into transmission characters;
dividing the transmission character into a plurality of data streams according to the network state and bandwidth information of the target area, and distributing congestion window adjustment strategies corresponding to the independent transmission channels for each data stream through a plurality of preset independent transmission channels;
and dynamically adjusting the transmission rate of the transmission character in the independent transmission channel according to the congestion window adjustment strategy, and transmitting the transmission character to the light controller.
For example, in order to improve the transmission efficiency and avoid the information loss in the information transmission process, the interactive information may be compressed. Optionally, window sampling may be performed on the interactive information according to a preset sampling window, and data sampled by the window may be mapped into sampling symbols according to a preset mapping relationship, where the size of the preset sampling window may be adaptively adjusted according to actually compressed information, which is not limited in this embodiment of the present application, the interactive information in the embodiment of the present application may include sensor fused data and may be mapped into corresponding sampling symbols, where the preset mapping relationship may include that when the interactive information is two-hand swing, the interactive information corresponds to the two-hand image symbol, and the definition of the symbol may consider the characteristics and semantic meaning of the interactive information so as to maintain the understandability and reversibility of the information in the compression process;
The frequency statistics can be carried out on the sampling symbols, the symbol frequency of the sampling symbols is determined, the statistical result can be used as the basis of dictionary construction, and common statistical methods comprise a histogram, frequency counting and the like; constructing a dictionary or a coding table according to the frequency statistics result; the dictionary may be represented using different data structures, such as hash tables, tree structures, etc., and the dictionary construction algorithm of the embodiments of the present application may include huffman tree, lempel-Ziv-Welch algorithm, etc., which are not limited in the embodiments of the present application.
Dividing the transmission character into a plurality of data streams, and distributing congestion window adjustment strategies corresponding to independent transmission channels for each data stream. Therefore, a plurality of independent transmission channels can be fully utilized, the transmission rate of each channel can be dynamically adjusted according to the network state and bandwidth information, and the transmission efficiency and the redundancy fault tolerance are improved.
In an alternative embodiment of the present invention,
the step of dividing the transmission character into a plurality of data streams according to the network state and the bandwidth information of the target area, and distributing congestion window adjustment strategies corresponding to the independent transmission channels to each data stream through a plurality of preset independent transmission channels comprises the following steps:
Determining the comprehensive weight value of the independent transmission channel according to the network state and bandwidth information of the target area and the movable connection number of the plurality of independent transmission channels;
according to the comprehensive weight value, preferentially distributing independent transmission channels with the front comprehensive weight value for the data stream, detecting the congestion value of the independent transmission channels in real time, judging whether packet loss occurs when the congestion value exceeds a preset congestion threshold value,
if packet loss occurs, reducing the half congestion window, and reducing the transmission rate according to a preset speed reduction strategy;
if the packet is not lost, the transmission rate is reduced according to a preset speed reduction strategy.
For example, the network state of the target area can be monitored, including the network congestion degree, the bandwidth utilization rate, the packet loss rate and the like, and available bandwidth information including the bandwidth capacity and the available bandwidth of each independent transmission channel is obtained; dividing characters or data to be transmitted into a plurality of data streams, wherein the division can be performed according to different rules, such as according to time periods, data types, data sizes and the like;
wherein, the comprehensive weight value can be determined according to the network state and the bandwidth information and combining the movable connection number of the transmission channel,
It is assumed that there are multiple physical channels, each with two indicators of latency (latency) and bandwidth (bandwidth). We can calculate the weight value of the channel using the following formula:
weight value = a× (1/delay) +b×bandwidth;
wherein a and B are weight factors for adjusting the relative weights of delay and bandwidth in the weight calculation, the inverse of delay representing the lower the delay the higher the weight, and bandwidth representing the higher the bandwidth the higher the weight.
The values of A and B can be adjusted according to actual conditions by carrying out weighted summation on the delay and the bandwidth so as to balance the influence degree of the delay and the bandwidth on the weight.
The following is an example showing how the weight value of a channel is calculated using a formula:
channel 1: delay = 10ms, bandwidth = 100Mbps
Channel 2: delay = 5ms, bandwidth = 200Mbps
Assuming the setting a=0.6, b=0.4, the following calculations can be used:
weight value channel 1=0.6× (1/10) +0.4×100=0.6+40=40.6;
weight value channel 2=0.6× (1/5) +0.4×200=0.6+80=80.6.
Further, traffic may be allocated according to the number of connections and weights of each server,
assume that three servers are labeled Server1, server2, and Server3, respectively, and their weights are W1, W2, and W3, respectively. Meanwhile, we keep track of the current number of connections for each server, C1, C2 and C3, respectively.
The algorithm comprises the following steps:
initializing the connection number: c1 =0, c2=0, c3=0. When a new request arrives, the number of active connections for each server is calculated, using the following formula:
number of active connections = current number of connections/weight
For Server1: effective connection number 1=c1/W1; for Server2: effective connection number 2=c2/W2; for Server3: effective number of connections 3=c3/W3;
the server with the smallest number of active connections, i.e. the least connected server, is selected. If a plurality of servers have the same minimum effective connection number, further selection can be performed according to the weight; the request is assigned to the selected server and the number of connections to the corresponding server is increased by 1. And returning the distributed server information to the requesting client. Update server connection number: and updating the connection number of each server according to the actual situation.
The following is an example:
server1: weight w1=3, current connection number c1=5;
server2: weight w2=2, current connection number c2=2;
server3: weight w3=1, current connection number c3=3;
calculating the number of effective connections:
effective connection number 1=c1/w1=5/3≡1.67;
effective connection number 2=c2/w2=2/2=1;
Effective connection number 3=c3/w3=3/1=3;
since the effective connection number 2 is the smallest, the Server2 is selected as the target Server for load balancing, and the connection number C2 is increased by 1.
The comprehensive weight value can splice the network state and the bandwidth information and the number of the movable connections.
According to the comprehensive weight value, preferentially distributing independent transmission channels with the front comprehensive weight value for the data stream, detecting the congestion value of the independent transmission channels in real time, judging whether packet loss occurs when the congestion value exceeds a preset congestion threshold value,
if packet loss occurs, reducing the half congestion window, and reducing the transmission rate according to a preset speed reduction strategy;
if the packet is not lost, the transmission rate is reduced according to a preset speed reduction strategy.
Illustratively, the congestion window size (cwnd) may be initialized to a small value, such as 1 MSS (maximum segment length); doubling cwnd whenever an Acknowledgement (ACK) is received; the above steps are continued until cwnd reaches a threshold (ssthresh).
Once cwnd reaches ssthresh, entering a congestion avoidance phase; each time an acknowledgement is received, cwnd is increased by 1/cwnd to linearly increase cwnd; when cwnd reaches a certain threshold, the method can select to perform quick retransmission and quick recovery;
Fast retransmission and fast recovery (Fast Retransmit and Fast Recovery):
if the receiving side continuously receives 3 repeated acknowledgements, the receiving side indicates that one data packet is lost; the sender immediately retransmits the lost data packet and halves cwnd; then, entering a quick recovery stage, setting ssthresh to be half of the current cwnd, and continuing to linearly increase the cwnd; if a timeout occurs, indicating that more severe congestion has occurred in the network, setting ssthresh to half the current cwnd and resetting cwnd to an initial value; entering a slow start phase and restarting the congestion control algorithm.
When packet loss occurs, the half congestion window is reduced, and the transmission rate is reduced according to a preset speed reduction strategy; if the packet is not lost, the transmission rate is reduced according to a preset speed reduction strategy.
The congestion window adjustment strategy corresponding to the independent transmission channel is distributed for each data flow, so that the router and the link in the network can be prevented from being crashed due to overload, and the reliability and the stability of the network are maintained; ensuring that a plurality of transmission sessions (such as TCP connections) share bandwidth on a network fairly, and avoiding that a certain connection occupies excessive network resources, thereby improving the fairness of the network; by dynamically adjusting the sending rate, the congestion control strategy can maximize the throughput of the network, so that the network resources are fully utilized, and the efficiency of data transmission is improved. When the network is congested, the pressure on the network equipment is reduced, and excessive data packets are prevented from waiting in the equipment in a queuing way, so that the load and the power consumption of the equipment are reduced.
S103, the light controller controls the target lamp to display according to a control mode corresponding to the interaction information by combining a smooth transition control algorithm based on the compressed interaction information, wherein the smooth transition control algorithm is used for generating a smooth numerical sequence to control the target lamp.
For example, in order to achieve smooth and natural lighting control effects, the target luminaire may be controlled by a smooth transition control algorithm, where the smooth transition control algorithm is used to generate a smooth sequence of values to control the target luminaire, and interpolation and a slow function may be used to achieve smooth lighting control by calculating appropriate transition parameters.
In an alternative embodiment of the present invention,
the controlling the target lamp to display according to the control mode corresponding to the interaction information based on the interaction information combined with the smooth transition control algorithm comprises the following steps:
determining the action speed of the target object based on the interaction information, and determining the transition time by combining the state of the target lamp;
and calculating an intermediate transition value according to the current state and the target state through linear interpolation and a buffer function, and mapping the intermediate transition value into a control parameter through a mapping function to control the target lamp.
In an alternative embodiment of the present invention,
the calculating the intermediate transition value by linear interpolation and a buffer function according to the current state and the target state comprises:
；/>
wherein M is value Represents an intermediate transition value, C value 、T value Representing the current state and the target state, respectively, easingFunction (t) representing a slow function, and t representing an interpolation parameter.
Illustratively, the intermediate transition values of embodiments of the present application may be represented as a smooth sequence of values. The slow-moving function of embodiments of the present disclosure may be varied according to time or progress such that the transition is slower at the beginning and end, and faster or smoother in the middle. Common slow-moving functions include linear, square, cubic, exponential functions, and the like.
Illustratively, the transitional time length, that is, the time required for transitional from the current state to the target state, is determined according to the current interaction information and the state of the target lamp, and the action speed of the user is calculated according to the recorded action time point. For example, the velocity may be estimated from the time interval between two adjacent actions and the amplitude of the action. The speed may be expressed as a displacement amount per unit time of an action or a frequency of execution of the action. Determining the length of the transition time according to the action speed of the user, if the action speed of the user is high, indicating that the user hopes to obtain instant feedback and rapid light change, the transition time can be shortened so as to keep the real-time performance and the responsiveness of the interaction with the user; conversely, if the user's speed of action is slower, indicating that the user prefers a slow and smooth light change, the transition time may be suitably prolonged.
Assuming that the user makes a series of continuous gesture actions, recording the time point and speed of each action, according to the data, calculating the average action speed of the user, if the average action speed of the user is fast, setting the transition time to be shorter, for example, 0.5 seconds, according to the need so as to keep synchronous with the quick interaction of the user; if the average speed of action of the user is slow, the transition time may be set longer, for example 2 seconds, to ensure a smoother and more comfortable light change. By determining the transition time according to the action speed of the user, the light change can be consistent with the user interaction, and better user experience and interactivity are provided.
In a second aspect of the embodiments of the present disclosure,
fig. 2 is a schematic structural diagram of a lamplight interaction control information transmission system according to an embodiment of the present disclosure, including:
the first unit is used for acquiring various sensing information of sensors held by a plurality of target objects in a target area, fusing the various sensing information to determine sensing characteristics, and determining interaction information of the plurality of target objects through a pre-constructed pattern recognition model based on the sensing characteristics and skeleton information preset by the target objects, wherein the pattern recognition model is constructed based on a neural network and is used for matching a preset pattern for input information;
The second unit is used for compressing the interaction information through a self-adaptive transmission algorithm according to the network state and the bandwidth information of the target area, dynamically adjusting the transmission rate of the compressed interaction information and transmitting the compressed interaction information to the light controller;
and the third unit is used for controlling the target lamp to display according to the control mode corresponding to the interaction information by combining a smooth transition control algorithm based on the compressed interaction information, wherein the smooth transition control algorithm is used for generating a smooth numerical sequence to control the target lamp.
In a third aspect of the embodiments of the present disclosure,
provided is a light interaction control information transmission device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the instructions stored in the memory to perform the method described previously.
In a fourth aspect of embodiments of the present disclosure,
there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method as described above.
The present invention may be a method, apparatus, system, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for performing various aspects of the present invention.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present disclosure, and not for limiting the same; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present disclosure.
Claims (10)
1. The method for transmitting the lamplight interaction control information is characterized by comprising the following steps of:
acquiring various sensing information of sensors held by a plurality of target objects in a target area, fusing the various sensing information to determine sensing characteristics, and determining interaction information of the plurality of target objects through a pre-constructed pattern recognition model based on the sensing characteristics and skeleton information preset by the target objects, wherein the pattern recognition model is constructed based on a neural network and is used for matching a preset pattern for input information;
compressing the interaction information through a self-adaptive transmission algorithm according to the network state and bandwidth information of the target area, dynamically adjusting the transmission rate of the compressed interaction information, and transmitting the compressed interaction information to a light controller;
And the lamplight controller controls the target lamp to display according to a control mode corresponding to the interaction information by combining a smooth transition control algorithm based on the compressed interaction information, wherein the smooth transition control algorithm is used for generating a smooth numerical sequence to control the target lamp.
2. The method according to claim 1, wherein determining the interaction information of the plurality of target objects through a pre-constructed pattern recognition model based on the sensing characteristics and the preset skeleton information comprises:
respectively inputting the skeleton feature and the sensing feature into the pattern recognition model, setting a punishment factor and a discarding factor in a hidden layer of the pattern recognition model, fusing the skeleton feature and the sensing feature through a forward propagation algorithm, and determining a fused feature;
and determining similarity scores of the fusion features and the preset pattern templates according to a pattern matching algorithm, wherein the preset pattern template with the highest similarity score is used as interaction information of a plurality of target objects.
3. The method of claim 2, wherein setting a penalty factor and a discard factor in a hidden layer of the pattern recognition model, fusing the skeletal features and the sensory features by a forward propagation algorithm to determine fused features comprises:
Setting a jump connection block in a hidden layer of the pattern recognition model, taking the added result of the input and the output of the hidden layer as the input of the next hidden layer, setting a discarding factor in the hidden layer, randomly setting the output value of the hidden layer to be zero, and summarizing all the output values of the hidden layer;
setting a penalty factor in a loss function of the pattern recognition model, and determining fusion characteristics by combining all output values of the hidden layer;
the determining the similarity score of the fusion feature and the preset pattern template according to the pattern matching algorithm comprises the following steps:
the similarity score is determined as shown in the following formula:
；
；
；
wherein sim (x [ i ] y [ j ]) represents a similarity score between the fusion feature x [ i ] and a preset pattern template y [ j ], weight (i, j) represents a weight value obtained by dynamically adjusting an ith element in the fusion feature and a jth element in the preset pattern template, D (x [ i ], y [ j ]) represents a spatial distance between the ith element in the fusion feature and the jth element in the preset pattern template, and min (D [ i-1] [ j ], D [ i ] [ j-1 ]) represents a minimum path value of each element in a two-dimensional matrix corresponding to the fusion feature and the preset pattern template.
4. The method of claim 1, wherein compressing the interaction information by an adaptive transmission algorithm and dynamically adjusting a transmission rate of the compressed interaction information according to the network status and bandwidth information of the target area, and transmitting the compressed interaction information to the light controller comprises:
window sampling is carried out on the interactive information according to a preset sampling window, data sampled by the window are mapped into sampling symbols according to a preset mapping relation, frequency statistics is carried out on the sampling symbols, and symbol frequency of the sampling symbols is determined; according to the sampling symbol and the symbol frequency, the interactive information is encoded into transmission characters;
dividing the transmission character into a plurality of data streams according to the network state and bandwidth information of the target area, and distributing congestion window adjustment strategies corresponding to the independent transmission channels for each data stream through a plurality of preset independent transmission channels;
and dynamically adjusting the transmission rate of the transmission character in the independent transmission channel according to the congestion window adjustment strategy, and transmitting the transmission character to the light controller.
5. The method of claim 4, wherein the dividing the transmission character into a plurality of data streams according to the network status and the bandwidth information of the target area, and allocating a congestion window adjustment policy corresponding to an independent transmission channel to each data stream through a preset plurality of independent transmission channels comprises:
Determining the comprehensive weight value of the independent transmission channel according to the network state and bandwidth information of the target area and the movable connection number of the plurality of independent transmission channels;
according to the comprehensive weight value, preferentially distributing independent transmission channels with the front comprehensive weight value for the data stream, detecting the congestion value of the independent transmission channels in real time, judging whether packet loss occurs when the congestion value exceeds a preset congestion threshold value,
if packet loss occurs, reducing the half congestion window, and reducing the transmission rate according to a preset speed reduction strategy;
if the packet is not lost, the transmission rate is reduced according to a preset speed reduction strategy.
6. The method of claim 1, wherein the controlling, by the light controller, the target light according to the control mode corresponding to the interaction information based on the compressed interaction information in combination with the smooth transition control algorithm comprises:
determining the action speed of the target object based on the interaction information, and determining the transition time by combining the current state and the target state of the target lamp;
and calculating an intermediate transition value according to the current state and the target state through linear interpolation and a buffer function, and mapping the intermediate transition value into a control parameter through a mapping function to control the target lamp.
7. The method of claim 6, wherein said calculating an intermediate transition value from said current state and said target state by linear interpolation and a slow-motion function comprises:
；
wherein M is value Represents an intermediate transition value, C value 、T value Representing the current state and the target state, respectively, easingFunction (t) representing a slow function, and t representing an interpolation parameter.
8. An interactive control information transmission system for lamplight, comprising:
the first unit is used for acquiring various sensing information of sensors held by a plurality of target objects in a target area, fusing the various sensing information to determine sensing characteristics, and determining interaction information of the plurality of target objects through a pre-constructed pattern recognition model based on the sensing characteristics and skeleton information preset by the target objects, wherein the pattern recognition model is constructed based on a neural network and is used for matching a preset pattern for input information;
the second unit is used for compressing the interaction information through a self-adaptive transmission algorithm according to the network state and the bandwidth information of the target area, dynamically adjusting the transmission rate of the compressed interaction information and transmitting the compressed interaction information to the light controller;
And the third unit is used for controlling the target lamp to display according to the control mode corresponding to the interaction information by combining a smooth transition control algorithm based on the compressed interaction information, wherein the smooth transition control algorithm is used for generating a smooth numerical sequence to control the target lamp.
9. An interactive control information transmission device for lamplight, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the instructions stored in the memory to perform the method of any of claims 1 to 7.
10. A computer readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310693910.1A CN116455522B (en) | 2023-06-13 | 2023-06-13 | Method and system for transmitting lamplight interaction control information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310693910.1A CN116455522B (en) | 2023-06-13 | 2023-06-13 | Method and system for transmitting lamplight interaction control information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116455522A true CN116455522A (en) | 2023-07-18 |
| CN116455522B CN116455522B (en) | 2023-08-29 |
Family
ID=87127656
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310693910.1A Active CN116455522B (en) | 2023-06-13 | 2023-06-13 | Method and system for transmitting lamplight interaction control information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116455522B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117395166A (en) * | 2023-12-11 | 2024-01-12 | 四海良田(天津)智能科技有限公司 | Intelligent agricultural management platform based on Internet of things |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202306130U (en) * | 2011-09-28 | 2012-07-04 | 深圳市数虎图像科技有限公司 | Inductive and interactive holographic imaging system |
| JP3186532U (en) * | 2013-07-31 | 2013-10-10 | 錦標 陳 | Interactive lighting interactive control device |
| CN103369795A (en) * | 2013-07-22 | 2013-10-23 | 中国地质大学（武汉） | Interactive lamplight intelligent control system |
| CN204316779U (en) * | 2014-09-23 | 2015-05-06 | 江苏天楹之光光电科技有限公司 | A kind of multimedia shadow interaction systems |
| CN108541116A (en) * | 2018-03-27 | 2018-09-14 | 努比亚技术有限公司 | Lamp light control method, terminal and computer readable storage medium |
| CN210225853U (en) * | 2019-07-30 | 2020-03-31 | 利亚德(成都)文旅科技有限公司 | Light show interactive control system |
| CN110996430A (en) * | 2019-12-20 | 2020-04-10 | 贵州元音在线电子技术有限公司 | Light control method, light control equipment and music room |
| CN111194122A (en) * | 2018-11-13 | 2020-05-22 | 杭州勇电照明有限公司 | Somatosensory interactive light control system |
| CN111442227A (en) * | 2020-03-19 | 2020-07-24 | 深圳市汉丰光电有限公司 | Interactive light ball system |
| CN111586927A (en) * | 2020-05-27 | 2020-08-25 | 大峡谷照明系统（苏州）股份有限公司 | Light control system and method |
| CN212163795U (en) * | 2020-06-11 | 2020-12-15 | 广东彩立方科技有限公司 | Light interaction system |
| CN212515761U (en) * | 2020-08-10 | 2021-02-09 | 天强诺信(北京)展览展示有限责任公司 | Interactive water flow wall |
| CN113055662A (en) * | 2021-03-06 | 2021-06-29 | 深圳市达特文化科技股份有限公司 | Interactive light art device of AI |
| WO2021184456A1 (en) * | 2020-03-17 | 2021-09-23 | 江苏天楹之光光电科技有限公司 | Led landscape lamp which interacts with clothes color |
| CN113741847A (en) * | 2021-09-09 | 2021-12-03 | 杭州勇电照明有限公司 | Light control method, system and storage medium |
| CN114554660A (en) * | 2022-01-13 | 2022-05-27 | 广东睿住智能科技有限公司 | Light control method and device, electronic equipment and storage medium |
| CN115334730A (en) * | 2022-09-07 | 2022-11-11 | 深圳市齐创绿色科技有限公司 | Intelligent lamp effect control method, device and system and readable storage medium |
| CN115869612A (en) * | 2021-09-30 | 2023-03-31 | 耀灵人工智能(浙江)有限公司 | Offline acousto-optic effect display method |
| CN116149465A (en) * | 2022-11-22 | 2023-05-23 | 上汽大众汽车有限公司 | System and method for carrying out multi-person bare-hand interaction in virtual reality |
| CN116204229A (en) * | 2021-12-01 | 2023-06-02 | 成都拟合未来科技有限公司 | Light control method, device, computer readable storage and terminal |
-
2023
- 2023-06-13 CN CN202310693910.1A patent/CN116455522B/en active Active
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202306130U (en) * | 2011-09-28 | 2012-07-04 | 深圳市数虎图像科技有限公司 | Inductive and interactive holographic imaging system |
| CN103369795A (en) * | 2013-07-22 | 2013-10-23 | 中国地质大学（武汉） | Interactive lamplight intelligent control system |
| JP3186532U (en) * | 2013-07-31 | 2013-10-10 | 錦標 陳 | Interactive lighting interactive control device |
| CN204316779U (en) * | 2014-09-23 | 2015-05-06 | 江苏天楹之光光电科技有限公司 | A kind of multimedia shadow interaction systems |
| CN108541116A (en) * | 2018-03-27 | 2018-09-14 | 努比亚技术有限公司 | Lamp light control method, terminal and computer readable storage medium |
| CN111194122A (en) * | 2018-11-13 | 2020-05-22 | 杭州勇电照明有限公司 | Somatosensory interactive light control system |
| CN210225853U (en) * | 2019-07-30 | 2020-03-31 | 利亚德(成都)文旅科技有限公司 | Light show interactive control system |
| CN110996430A (en) * | 2019-12-20 | 2020-04-10 | 贵州元音在线电子技术有限公司 | Light control method, light control equipment and music room |
| WO2021184456A1 (en) * | 2020-03-17 | 2021-09-23 | 江苏天楹之光光电科技有限公司 | Led landscape lamp which interacts with clothes color |
| CN111442227A (en) * | 2020-03-19 | 2020-07-24 | 深圳市汉丰光电有限公司 | Interactive light ball system |
| CN111586927A (en) * | 2020-05-27 | 2020-08-25 | 大峡谷照明系统（苏州）股份有限公司 | Light control system and method |
| CN212163795U (en) * | 2020-06-11 | 2020-12-15 | 广东彩立方科技有限公司 | Light interaction system |
| CN212515761U (en) * | 2020-08-10 | 2021-02-09 | 天强诺信(北京)展览展示有限责任公司 | Interactive water flow wall |
| CN113055662A (en) * | 2021-03-06 | 2021-06-29 | 深圳市达特文化科技股份有限公司 | Interactive light art device of AI |
| CN113741847A (en) * | 2021-09-09 | 2021-12-03 | 杭州勇电照明有限公司 | Light control method, system and storage medium |
| CN115869612A (en) * | 2021-09-30 | 2023-03-31 | 耀灵人工智能(浙江)有限公司 | Offline acousto-optic effect display method |
| CN116204229A (en) * | 2021-12-01 | 2023-06-02 | 成都拟合未来科技有限公司 | Light control method, device, computer readable storage and terminal |
| CN114554660A (en) * | 2022-01-13 | 2022-05-27 | 广东睿住智能科技有限公司 | Light control method and device, electronic equipment and storage medium |
| CN115334730A (en) * | 2022-09-07 | 2022-11-11 | 深圳市齐创绿色科技有限公司 | Intelligent lamp effect control method, device and system and readable storage medium |
| CN116149465A (en) * | 2022-11-22 | 2023-05-23 | 上汽大众汽车有限公司 | System and method for carrying out multi-person bare-hand interaction in virtual reality |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117395166A (en) * | 2023-12-11 | 2024-01-12 | 四海良田(天津)智能科技有限公司 | Intelligent agricultural management platform based on Internet of things |
| CN117395166B (en) * | 2023-12-11 | 2024-02-13 | 四海良田(天津)智能科技有限公司 | Intelligent agricultural management platform based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116455522B (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107171842B (en) | Multipath transmission protocol congestion control method based on reinforcement learning | |
| CN116455522B (en) | Method and system for transmitting lamplight interaction control information | |
| US20200162535A1 (en) | Methods and Apparatus for Learning Based Adaptive Real-time Streaming | |
| CN111010582B (en) | Cloud desktop image processing method, device and equipment and readable storage medium | |
| US20090022055A1 (en) | Systems and methods for improving tcp-friendliness of delay-based congestion control | |
| CN105704055B (en) | It is a kind of based on the network congestion prevention method inspired naturally | |
| Su et al. | QRED: A Q-learning-based active queue management scheme | |
| CN111314022A (en) | Screen updating transmission method based on reinforcement learning and fountain codes | |
| CN111182220A (en) | Image processing apparatus, remote device, and communication system | |
| CN115989530A (en) | Generating and processing video data | |
| Feng et al. | Vabis: Video adaptation bitrate system for time-critical live streaming | |
| CN112866746A (en) | Multi-path streaming cloud game control method, device, equipment and storage medium | |
| CN114389959B (en) | Network congestion control method, device, electronic equipment and storage medium | |
| US20200322663A1 (en) | Controlled Uplink Adaptive Streaming based on Server Performance Measurement Data | |
| Motoo et al. | Client-side network delay compensation for online shooting games | |
| CN113595684A (en) | MPTCP dynamic coding scheduling method and system based on deep reinforcement learning | |
| CN113518246B (en) | Data transmission method, data transmission device, computer equipment, storage medium and program product | |
| CN113301398B (en) | Information processing method and system, server device and client device | |
| CN113996056A (en) | Data sending and receiving method of cloud game and related equipment | |
| CN114747225B (en) | Method, system and medium for selecting a format of a streaming media content item | |
| Lee et al. | REINDEAR: REINforcement learning agent for Dynamic system control in Edge-Assisted Augmented Reality service | |
| KR101932130B1 (en) | Apparatus and method for improving quality of experience of remote display | |
| CN114785757B (en) | Multipath transmission control method for real-time conversation service | |
| CN116915706B (en) | Data center network congestion control method, device, equipment and storage medium | |
| Tamizhselvi et al. | Delay-aware bandwidth estimation and intelligent video transcoder in mobile cloud |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |