CN116800382B - Index modulation method and device based on visual sensor - Google Patents
Index modulation method and device based on visual sensor Download PDFInfo
- Publication number
- CN116800382B CN116800382B CN202311034545.XA CN202311034545A CN116800382B CN 116800382 B CN116800382 B CN 116800382B CN 202311034545 A CN202311034545 A CN 202311034545A CN 116800382 B CN116800382 B CN 116800382B
- Authority
- CN
- China
- Prior art keywords
- mcs
- direct path
- signal
- signal receiver
- obstacle
- 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.)
- Active
Links
- 230000000007 visual effect Effects 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000013145 classification model Methods 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims description 35
- 230000006854 communication Effects 0.000 claims description 24
- 238000004891 communication Methods 0.000 claims description 23
- 230000008054 signal transmission Effects 0.000 claims description 11
- 230000003068 static effect Effects 0.000 claims description 10
- 230000004888 barrier function Effects 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 abstract description 16
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000001276 controlling effect Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Abstract
The application discloses an index modulation method and device based on a visual sensor, comprising the steps of obtaining direct path information between a signal sender and a signal receiver through a preset visual sensor; extracting obstacle information based on the direct path information if the direct path information indicates that a new obstacle exists; determining an MCS value matched with the obstacle information based on the obstacle information and a pre-trained multi-classification model; transmitting a target symbol in a WiFi radio frame to the signal receiver by the signal sender by using the MCS value; wherein one of the MCS values corresponds to at least one of the target symbols. The application can improve the MCS adjusting efficiency and the wireless transmission efficiency.
Description
Technical Field
The application relates to the technical field of communication, in particular to an index modulation method and device based on a visual sensor.
Background
At present, wi-Fi communication includes a standard frequency band communication mode and a millimeter wave frequency band communication mode, wherein the standard frequency band communication mode is for example 2.4GHz and 5GHz frequency band communication, and the millimeter wave frequency band communication mode is for example 45GHz and 60GHz frequency band communication.
In practice, it is found that, for the communication mode in the millimeter wave band, the conventional MCS (Modulation and Coding Scheme, modulation and coding strategy) adjustment mode of Wi-Fi performs MCS adjustment according to the result of acknowledgement of the previous frame ACK (Acknowledge character, acknowledgement character). However, if there is an obstacle in the direct path of the millimeter wave scenario, such as a crowd moving in the direct paths of the sender and receiver, this may result in a lag in MCS adjustment. As can be seen, in the case where an obstacle exists in the direct path, the existing MCS adjustment method has a problem of low adjustment efficiency, thereby resulting in low wireless transmission efficiency.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The embodiment of the application provides an index modulation method and device based on a visual sensor, which are used for at least improving MCS (modulation scheme) regulation efficiency and wireless transmission efficiency.
According to an aspect of an embodiment of the present application, there is provided an index modulation method based on a vision sensor, the method including: acquiring direct path information between a signal sender and a signal receiver through a preset visual sensor; extracting obstacle information based on the direct path information if the direct path information indicates that a new obstacle exists; determining an MCS value matched with the obstacle information based on the obstacle information and a pre-trained multi-classification model; transmitting a target symbol in a WiFi radio frame to the signal receiver by the signal sender by using the MCS value; wherein one of the MCS values corresponds to at least one of the target symbols.
As an optional implementation manner, the visual sensor is preset on the WiFi router corresponding to the signal sender, and the visual sensor faces the signal receiver.
As an alternative embodiment, the method further comprises: determining the environment category of the signal sender and the signal receiver; if the environment category is a dynamic environment, setting a frame structure of the WiFi radio frame as a first frame structure for each WiFi radio frame; if the environment category is a static environment, setting a frame structure of the WiFi radio frame as a second frame structure for each WiFi radio frame; the first frame structure corresponds to one MCS with one symbol, and the second frame structure corresponds to one WiFi wireless frame with one MCS.
As an optional implementation manner, the obtaining, by a preset vision sensor, direct path information between a signal sender and a signal receiver includes: before network communication is carried out between the signal sender and the signal receiver, acquiring an obstacle-free image of a direct path between the signal sender and the signal receiver through the preset visual sensor; after network communication is carried out between the signal sender and the signal receiver, acquiring a real-time image of a direct path between the signal sender and the signal receiver through the preset visual sensor; and comparing the real-time image with the barrier-free image to obtain a comparison result, and taking the comparison result as the direct path information.
As an alternative embodiment, extracting obstacle information based on the direct path information includes: and carrying out background cancellation on the real-time image and the barrier-free image based on the direct path information to obtain the barrier information.
As an alternative embodiment, the method further comprises: and if the direct path information indicates that no new obstacle exists, transmitting the target symbol in the WiFi wireless frame to the signal receiver by the signal sender according to the current MCS value.
As an alternative embodiment, the method further comprises: acquiring a training scene set and MCS annotation values matched with each training scene in the training scene set; and training the multi-classification neural network based on each training scene and each MCS labeling value to obtain the pre-trained multi-classification model.
According to another aspect of the embodiment of the present application, there is also provided an index modulation device based on a vision sensor, the device including: a path acquisition unit for acquiring direct path information between a signal sender and a signal receiver through a preset vision sensor; an obstacle determination unit configured to extract obstacle information based on the direct path information if the direct path information indicates that a new obstacle exists; an MCS value determining unit for determining an MCS value matched with the obstacle information based on the obstacle information and a multi-classification model trained in advance; the signal transmission unit is used for transmitting the target symbol in the WiFi wireless frame to the signal receiver by the signal sender by utilizing the MCS value; wherein one of the MCS values corresponds to at least one of the target symbols.
As an optional implementation manner, the visual sensor is preset on the WiFi router corresponding to the signal sender, and the visual sensor faces the signal receiver.
As an alternative embodiment, the apparatus further comprises: a frame structure setting unit, configured to determine an environment category in which the signal sender and the signal receiver are located; if the environment category is a dynamic environment, setting a frame structure of the WiFi radio frame as a first frame structure for each WiFi radio frame; if the environment category is a static environment, setting a frame structure of the WiFi radio frame as a second frame structure for each WiFi radio frame; the first frame structure corresponds to one MCS with one symbol, and the second frame structure corresponds to one WiFi wireless frame with one MCS.
As an alternative embodiment, the path acquisition unit is specifically configured to: before network communication is carried out between the signal sender and the signal receiver, acquiring an obstacle-free image of a direct path between the signal sender and the signal receiver through the preset visual sensor; after network communication is carried out between the signal sender and the signal receiver, acquiring a real-time image of a direct path between the signal sender and the signal receiver through the preset visual sensor; and comparing the real-time image with the barrier-free image to obtain a comparison result, and taking the comparison result as the direct path information.
As an alternative embodiment, the obstacle determining unit is specifically configured to: and carrying out background cancellation on the real-time image and the barrier-free image based on the direct path information to obtain the barrier information.
As an alternative embodiment, the signal transmission unit is further configured to: and if the direct path information indicates that no new obstacle exists, transmitting the target symbol in the WiFi wireless frame to the signal receiver by the signal sender according to the current MCS value.
As an alternative embodiment, the apparatus further comprises: the model training unit is used for acquiring a training scene set and MCS annotation values matched with each training scene in the training scene set; and training the multi-classification neural network based on each training scene and each MCS labeling value to obtain the pre-trained multi-classification model.
In the embodiment of the application, the channel condition on the direct path can be directly acquired through the visual sensor, whether the channel has obstacle interference or not is judged, and when the obstacle interference is judged, through a multi-classification model which is trained in advance, the MCS value which needs to be regulated is determined, and the MCS value is used for controlling the transmission of at least one target symbol in the WiFi radio frame. On the one hand, the process combines the vision sensor to judge the obstacle situation more accurately, and on the other hand, the MCS value is intelligently generated according to the obstacle situation, so that the MCS adjusting efficiency and the wireless transmission efficiency can be improved under the condition that the obstacle exists in the direct path. And, adopt a MCS numerical control WiFi radio frame at least one goal symbol transmission. Compared with signal transmission with whole frame granularity, the signal transmission with symbol granularity has more accurate MCS adjustment.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 is a flow chart of an alternative vision sensor-based index modulation method in accordance with an embodiment of the present application;
fig. 2 is a schematic diagram illustrating the arrangement of a frame structure of an alternative WiFi radio frame according to an embodiment of the application;
fig. 3 is a schematic diagram illustrating the arrangement of a frame structure of an alternative WiFi radio frame according to an embodiment of the application;
FIG. 4 is a schematic illustration of an alternative visual sensor arrangement according to an embodiment of the present application;
FIG. 5 is a schematic diagram of the structure of an alternative multi-classification model according to an embodiment of the application;
fig. 6 is a schematic structural view of an alternative vision sensor-based index modulation device according to an embodiment of the present application.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application 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 application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application 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 application 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.
The embodiment of the application provides an optional index modulation method based on a visual sensor, as shown in fig. 1, which comprises the following steps:
s101, acquiring direct path information from a signal sender to a signal receiver through a preset visual sensor.
In this embodiment, the execution body may be a signal sender or a signal receiver. The signal sender or the signal receiver may be electronic devices such as various terminal devices and servers for Wi-Fi communication, which is not limited in this embodiment.
The preset visual sensor may be a preset sensor for acquiring visual information of a direct path between the signal sender and the signal receiver, for example, the visual sensor may be a camera. The visual sensor may be provided to the signal transmitter, the signal receiver, or independent of the signal transmitter and the signal receiver, which is not limited in this embodiment.
Wi-Fi (namely IEEE 802.11 protocol) communication mode of millimeter wave frequency band is adopted between the signal sender and the signal receiver. The distance between the signal sender and the signal receiver is smaller, a visual image of a direct path between the signal sender and the signal receiver can be acquired through a preset visual sensor, and then the visual image is analyzed and processed, so that direct path information can be obtained.
The direct path information may be an image or video of a direct path between the signal sender and the signal receiver, or may be a direct path image after the background cancellation process.
S102, if the direct path information indicates that a new obstacle exists, extracting obstacle information based on the direct path information.
In the present embodiment, if the direct path information indicates that a new obstacle exists in the direct path between the current signal sender to the signal receiver, the obstacle information matching the new obstacle may be determined based on the direct path information.
In the process of communication between the signal sender and the signal receiver, direct path information is continuously acquired, and if the initial direct path information indicates that an obstacle exists, the direct path information is considered to indicate that a new obstacle exists, and the obstacle information is extracted. For non-initial direct path information, if an obstacle is indicated to exist in the direct path and the obstacle is different from the obstacle in the direct path information acquired last time, the direct path information is considered to indicate the existence of a new obstacle, and the obstacle information is extracted.
The obstacle information is information corresponding to a new obstacle, such as an image corresponding to the new obstacle. If the direct path information is an image or video of a direct path between the signal sender and the signal receiver at the current moment, the image or video can be analyzed to obtain an image or video corresponding to a new obstacle in the image or video, and the image or video corresponding to the new obstacle is determined to be the obstacle information. If the direct path information is the direct path image after the background cancellation processing, the direct path image after the background cancellation processing can be directly determined as the obstacle information.
S103, determining the MCS value matched with the obstacle information based on the obstacle information and a pre-trained multi-classification model.
In this embodiment, the pre-trained multi-classification model may employ conventional classifier models, such as logistics and SVM models, by which the impact of obstacles in the field of view is divided into multiple types, each type mapping an MCS. Alternatively, the pre-trained multi-classification model may also employ a neural network model to implement the classifier.
Wherein, by taking the obstacle information as the input data of the pre-trained multi-classification model, the MCS value output by the pre-trained multi-classification model can be obtained.
Wherein, the execution subject can compare the shooting signal (signal without obstacle) of the default direct path with the signal with obstacle, if the obstacle is found, the target signal extracted by subtracting the two signals is input into the model for recognition. At this time, the target signal extracted by subtracting the two is the obstacle information.
And S104, transmitting the target symbol in the WiFi wireless frame to the signal receiver by the signal sender by using the MCS value.
Wherein one of the MCS values corresponds to at least one of the target symbols.
In the communication process between the signal sender and the signal receiver, multiple frames of WiFi radio frames need to be sent, and one frame of WiFi radio frame may include multiple symbols (symbols). In addition, in the embodiment of the application, for each symbol in the WiFi radio frame, the MCS value may be set according to the symbol granularity. One MCS value corresponds to at least one symbol. For example, one MCS value may correspond to one symbol, and one MCS value may also correspond to two symbols.
In this embodiment, after obtaining the MCS value matched with the current obstacle information, at least one target symbol corresponding to the MCS value may be transmitted using the MCS value.
As an optional implementation manner, the visual sensor is preset on the WiFi router corresponding to the signal sender, and the visual sensor faces the signal receiver.
In this embodiment, the vision sensor (such as a camera) may be used as an independent device on the wireless transmitting end (corresponding to the WiFi router of the signal transmitting party), and is always in an operating state. In general, since millimeter wave transmission is a direct path, the scene of the millimeter wave transmission is usually a close-range fixed scene, and in the case of fixed positions of a sender and a receiver, the camera can be set by a method of manual setting (i.e. the camera is rotated to a specified direction and position), so that a visual sensor faces a signal receiver, and image information on the direct path is acquired.
As an alternative embodiment, the method further comprises: determining the environment category of the signal sender and the signal receiver; if the environment category is a dynamic environment, setting a frame structure of the WiFi radio frame as a first frame structure for each WiFi radio frame; if the environment category is a static environment, setting a frame structure of the WiFi radio frame as a second frame structure for each WiFi radio frame; the first frame structure corresponds to one MCS with one symbol, and the second frame structure corresponds to one WiFi wireless frame with one MCS.
In this embodiment, since there is no channel change at all times during actual operation, the MCS does not need to be adjusted so frequently. If the current environment is a dynamic environment, i.e. more barriers, an area with one MCS attached to each Symbol can be set, so that the MCS adjustment of Symbol level is realized, and the flexibility is improved. If the current environment is relatively static, then one MCS modulation scheme may be fixed at this time and this MCS may be used in the transmission of the entire frame. Essentially, in this case, the network is a transport mode that reverts to traditional Wi-Fi.
The environment conditions respectively matched with the dynamic environment and the static environment can be preset, such as setting a threshold value of the number of barriers, a threshold value of the size of the barriers and the like, so as to assist in judging the environment types of the signal sender and the signal receiver. For dynamic environments, the frame structure is set to one MCS for one symbol. For static environments, the frame structure is set to one MCS for one WiFi radio frame.
Alternatively, the environment category may be divided into several levels, and different levels correspond to different mapping relations between MCS and symbols, not limited to dynamic environment and static environment. The mapping relation here may include not only one MCS corresponding to one symbol, one MCS corresponding to one WiFi radio frame, but also two MCS corresponding to two symbols, three MCS corresponding to one symbol, and the like, which is not limited in this embodiment.
As an optional implementation manner, the obtaining, by a preset vision sensor, direct path information between a signal sender and a signal receiver includes: before network communication is carried out between the signal sender and the signal receiver, acquiring an obstacle-free image of a direct path between the signal sender and the signal receiver through the preset visual sensor; after network communication is carried out between the signal sender and the signal receiver, acquiring a real-time image of a direct path between the signal sender and the signal receiver through the preset visual sensor; and comparing the real-time image with the barrier-free image to obtain a comparison result, and taking the comparison result as the direct path information.
In this embodiment, a plurality of pictures without any obstacle on the direct path may be captured by a visual sensor (such as a camera) as the cleanest path image, that is, the above-mentioned obstacle-free image. After the network operation starts, the camera works in real time, and at the moment, the camera can capture pictures on the direct path in real time, namely the real-time images. And comparing the real-time image with a background pattern without an obstacle (an obstacle-free image) to obtain a comparison result, and taking the comparison result as direct path information. The direct path information here may be information obtained by performing background cancellation on a real-time image and an obstacle-free image.
As an alternative embodiment, extracting obstacle information based on the direct path information includes: and carrying out background cancellation on the real-time image and the barrier-free image based on the direct path information to obtain the barrier information.
In this embodiment, if a new obstacle is found to exist in the direct view, the information after the background cancellation is extracted and transferred to the classifier model.
As an alternative embodiment, the method further comprises: and if the direct path information indicates that no new obstacle exists, transmitting the target symbol in the WiFi wireless frame to the signal receiver by the signal sender according to the current MCS value.
In this embodiment, if no object is moving in the direct view, it is determined that no new obstacle is indicated, the current MCS is kept unchanged, and the operation is continued.
As an alternative embodiment, the method further comprises: acquiring a training scene set and MCS annotation values matched with each training scene in the training scene set; and training the multi-classification neural network based on each training scene and each MCS labeling value to obtain the pre-trained multi-classification model.
In this embodiment, if the multi-classification model that is trained in advance is a neural network model, some training scenarios may be artificially constructed, for example, a person stays on the direct path for a long time, a numerical value of MCS setting at that time is set, a small obstacle stays on the direct path, MCS setting at that time, and the like, and obstacles under different conditions are constructed and corresponding MCS numerical values are set. And training the multi-classification neural network by taking the values as training data (each training scene and each MCS labeling value) to obtain a multi-classification model.
Referring to fig. 2 and 3 together, fig. 2 is a schematic diagram illustrating a frame structure of an alternative WiFi radio frame according to an embodiment of the application, and fig. 3 is a schematic diagram illustrating a frame structure of another alternative WiFi radio frame according to an embodiment of the application. As shown in fig. 2 and 3, for WiFi radio frames, an MCS may be introduced into each symbol, which may employ a different MCS (fig. 2). Alternatively, for a WiFi radio frame, one MCS may be assigned 2 symbols (fig. 3). In fig. 3, the MCS is also placed in one symbol, but the MCS is indicated to be included in the symbol corresponding to the current symbol. It can be appreciated that the present application can make the MCS correspond to any number of symbols, and the longest case corresponds to a standard Wi-Fi frame, that is, a case where one frame has only one MCS.
Referring to fig. 4 together, fig. 4 is a schematic diagram illustrating an alternative arrangement of a vision sensor according to an embodiment of the present application, as shown in fig. 4, where the camera is the vision sensor. The Wi-Fi router includes a router host, a router antenna, and fig. 4 is a case of only two antennas, it can be understood that in actual situations, a plurality of antennas may be included, which is not limited in this embodiment. The router also comprises a camera module, namely the camera is used as a visual sensor to acquire the transmission condition under the direct path in real time, and the coverage area of the camera needs to be aligned with the direct path of the antenna, so that the best detection effect can be obtained.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an alternative multi-classification model according to an embodiment of the present application, as shown in fig. 5, after training is completed, camera monitoring information with background interference removed is input into a network, so as to obtain a corresponding MCS result. Finally, the MCS is applied to the symbol and sent out. The multi-classification model shown in fig. 5 may include an input layer, a hidden layer, and an output layer. The content of the input layer is real-time monitoring information (after background cancellation) acquired by the camera, the hidden layer is a parameter acquired through training, and the output layer directly corresponds to the parameter of the MCS. The model is a training model with a teacher, and the specific training process is described above and will not be repeated here.
In the embodiment of the application, the channel condition on the direct path can be directly acquired through the visual sensor, whether the channel has obstacle interference or not is judged, and when the obstacle interference is judged, through a multi-classification model which is trained in advance, the MCS value which needs to be regulated is determined, and the MCS value is used for controlling the transmission of at least one target symbol in the WiFi radio frame. On the one hand, the process combines the vision sensor to judge the obstacle situation more accurately, and on the other hand, the MCS value is intelligently generated according to the obstacle situation, so that the MCS adjusting efficiency and the wireless transmission efficiency can be improved under the condition that the obstacle exists in the direct path. And, adopt a MCS numerical control WiFi radio frame at least one goal symbol transmission. Compared with signal transmission with whole frame granularity, the signal transmission with symbol granularity has more accurate MCS adjustment.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.
Further, an embodiment of the present application provides an optional index modulation device based on a visual sensor, as shown in fig. 6, where the index modulation device based on a visual sensor includes:
a path acquisition unit 601, configured to acquire direct path information between a signal sender and a signal receiver through a preset vision sensor;
an obstacle determination unit 602 configured to extract obstacle information based on the direct path information if the direct path information indicates that a new obstacle exists;
an MCS value determining unit 603 for determining an MCS value matching the obstacle information based on the obstacle information and a multi-classification model trained in advance;
a signal transmission unit 604, configured to transmit, by using the MCS value, a target symbol in a WiFi radio frame to the signal receiver by the signal sender; wherein one of the MCS values corresponds to at least one of the target symbols.
As an optional implementation manner, the visual sensor is preset on the WiFi router corresponding to the signal sender, and the visual sensor faces the signal receiver.
As an alternative embodiment, the apparatus further comprises: a frame structure setting unit, configured to determine an environment category in which the signal sender and the signal receiver are located; if the environment category is a dynamic environment, setting a frame structure of the WiFi radio frame as a first frame structure for each WiFi radio frame; if the environment category is a static environment, setting a frame structure of the WiFi radio frame as a second frame structure for each WiFi radio frame; the first frame structure corresponds to one MCS with one symbol, and the second frame structure corresponds to one WiFi wireless frame with one MCS.
As an alternative embodiment, the path acquisition unit 601 is specifically configured to: before network communication is carried out between the signal sender and the signal receiver, acquiring an obstacle-free image of a direct path between the signal sender and the signal receiver through the preset visual sensor; after network communication is carried out between the signal sender and the signal receiver, acquiring a real-time image of a direct path between the signal sender and the signal receiver through the preset visual sensor; and comparing the real-time image with the barrier-free image to obtain a comparison result, and taking the comparison result as the direct path information.
As an alternative embodiment, the obstacle determining unit 602 is specifically configured to: and carrying out background cancellation on the real-time image and the barrier-free image based on the direct path information to obtain the barrier information.
As an alternative embodiment, the signal transmission unit 604 is further configured to: and if the direct path information indicates that no new obstacle exists, transmitting the target symbol in the WiFi wireless frame to the signal receiver by the signal sender according to the current MCS value.
As an alternative embodiment, the apparatus further comprises: the model training unit is used for acquiring a training scene set and MCS annotation values matched with each training scene in the training scene set; and training the multi-classification neural network based on each training scene and each MCS labeling value to obtain the pre-trained multi-classification model.
In the embodiment of the application, the channel condition on the direct path can be directly acquired through the visual sensor, whether the channel has obstacle interference or not is judged, and when the obstacle interference is judged, through a multi-classification model which is trained in advance, the MCS value which needs to be regulated is determined, and the MCS value is used for controlling the transmission of at least one target symbol in the WiFi radio frame. On the one hand, the process combines the vision sensor to judge the obstacle situation more accurately, and on the other hand, the MCS value is intelligently generated according to the obstacle situation, so that the MCS adjusting efficiency and the wireless transmission efficiency can be improved under the condition that the obstacle exists in the direct path. And, adopt a MCS numerical control WiFi radio frame at least one goal symbol transmission. Compared with signal transmission with whole frame granularity, the signal transmission with symbol granularity has more accurate MCS adjustment.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
The integrated units in the above embodiments may be stored in the above-described computer-readable storage medium if implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing one or more computer devices (which may be personal computers, servers or network devices, etc.) to perform all or part of the steps of the method of the various embodiments of the present application.
In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In several embodiments provided by the present application, it should be understood that the disclosed client may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and are merely a logical functional division, and there may be other manners of dividing the apparatus in actual implementation, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application, which are intended to be comprehended within the scope of the present application.
Claims (10)
1. An index modulation method based on a visual sensor, the method comprising:
acquiring direct path information between a signal sender and a signal receiver through a preset visual sensor;
extracting obstacle information based on the direct path information if the direct path information indicates that a new obstacle exists;
determining an MCS value matched with the obstacle information based on the obstacle information and a pre-trained multi-classification model;
transmitting a target symbol in a WiFi radio frame to the signal receiver by the signal sender by using the MCS value; wherein one of the MCS values corresponds to at least one of the target symbols.
2. The method of claim 1, wherein the visual sensor is pre-disposed on a WiFi router corresponding to the signal sender, and the visual sensor faces the signal receiver.
3. The method according to claim 1, wherein the method further comprises:
determining the environment category of the signal sender and the signal receiver;
if the environment category is a dynamic environment, setting a frame structure of the WiFi radio frame as a first frame structure for each WiFi radio frame;
if the environment category is a static environment, setting a frame structure of the WiFi radio frame as a second frame structure for each WiFi radio frame;
the first frame structure corresponds to one MCS with one symbol, and the second frame structure corresponds to one WiFi wireless frame with one MCS.
4. The method according to claim 1, wherein the obtaining, by a preset vision sensor, direct path information between a signal sender and a signal receiver includes:
before network communication is carried out between the signal sender and the signal receiver, acquiring an obstacle-free image of a direct path between the signal sender and the signal receiver through the preset visual sensor;
after network communication is carried out between the signal sender and the signal receiver, acquiring a real-time image of a direct path between the signal sender and the signal receiver through the preset visual sensor;
and comparing the real-time image with the barrier-free image to obtain a comparison result, and taking the comparison result as the direct path information.
5. The method of claim 4, wherein extracting obstacle information based on the direct path information comprises:
and carrying out background cancellation on the real-time image and the barrier-free image based on the direct path information to obtain the barrier information.
6. The method according to claim 1, wherein the method further comprises:
and if the direct path information indicates that no new obstacle exists, transmitting the target symbol in the WiFi wireless frame to the signal receiver by the signal sender according to the current MCS value.
7. The method according to claim 1, wherein the method further comprises:
acquiring a training scene set and MCS annotation values matched with each training scene in the training scene set;
and training the multi-classification neural network based on each training scene and each MCS labeling value to obtain the pre-trained multi-classification model.
8. An index modulation device based on a vision sensor, said device comprising:
a path acquisition unit for acquiring direct path information between a signal sender and a signal receiver through a preset vision sensor;
an obstacle determination unit configured to extract obstacle information based on the direct path information if the direct path information indicates that a new obstacle exists;
an MCS value determining unit for determining an MCS value matched with the obstacle information based on the obstacle information and a multi-classification model trained in advance;
the signal transmission unit is used for transmitting the target symbol in the WiFi wireless frame to the signal receiver by the signal sender by utilizing the MCS value; wherein one of the MCS values corresponds to at least one of the target symbols.
9. The apparatus of claim 8, wherein the visual sensor is pre-disposed on a WiFi router corresponding to the signal sender, and the visual sensor faces the signal receiver.
10. The apparatus of claim 8, wherein the apparatus further comprises:
a frame structure setting unit, configured to determine an environment category in which the signal sender and the signal receiver are located; if the environment category is a dynamic environment, setting a frame structure of the WiFi radio frame as a first frame structure for each WiFi radio frame; if the environment category is a static environment, setting a frame structure of the WiFi radio frame as a second frame structure for each WiFi radio frame; the first frame structure corresponds to one MCS with one symbol, and the second frame structure corresponds to one WiFi wireless frame with one MCS.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311034545.XA CN116800382B (en) | 2023-08-17 | 2023-08-17 | Index modulation method and device based on visual sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311034545.XA CN116800382B (en) | 2023-08-17 | 2023-08-17 | Index modulation method and device based on visual sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116800382A CN116800382A (en) | 2023-09-22 |
| CN116800382B true CN116800382B (en) | 2023-11-03 |
Family
ID=88046151
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311034545.XA Active CN116800382B (en) | 2023-08-17 | 2023-08-17 | Index modulation method and device based on visual sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116800382B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112640343A (en) * | 2020-04-27 | 2021-04-09 | 深圳市大疆创新科技有限公司 | MCS (modulation and coding scheme) adjusting method and device for sending end, unmanned aerial vehicle and storage medium |
| CN113905446A (en) * | 2020-06-22 | 2022-01-07 | 中国移动通信有限公司研究院 | Method, device and network equipment for estimating downlink modulation coding mode |
| CN114747257A (en) * | 2019-11-26 | 2022-07-12 | 华为技术有限公司 | System and method for estimating the position of signal-obscuring obstacles and signal reflectors in a wireless communication network |
| CN115396977A (en) * | 2022-08-12 | 2022-11-25 | 中国联合网络通信集团有限公司 | Method, device and equipment for determining signal transmission path and storage medium |
| WO2023029751A1 (en) * | 2021-08-31 | 2023-03-09 | 中兴通讯股份有限公司 | Adaptive coding and modulation method and apparatus, electronic device and storage medium |
| WO2023077298A1 (en) * | 2021-11-03 | 2023-05-11 | Huawei Technologies Co., Ltd. | Devices and methods for punctured transmission in a wireless network |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114071681A (en) * | 2020-08-05 | 2022-02-18 | 艾锐势企业有限责任公司 | Method, electronic device, medium, and apparatus for setting transmission power of wireless signal |
| US20230099883A1 (en) * | 2021-09-24 | 2023-03-30 | Qualcomm Incorporated | Phase tracking reference signal pilot allocation sizes |
-
2023
- 2023-08-17 CN CN202311034545.XA patent/CN116800382B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114747257A (en) * | 2019-11-26 | 2022-07-12 | 华为技术有限公司 | System and method for estimating the position of signal-obscuring obstacles and signal reflectors in a wireless communication network |
| CN112640343A (en) * | 2020-04-27 | 2021-04-09 | 深圳市大疆创新科技有限公司 | MCS (modulation and coding scheme) adjusting method and device for sending end, unmanned aerial vehicle and storage medium |
| CN113905446A (en) * | 2020-06-22 | 2022-01-07 | 中国移动通信有限公司研究院 | Method, device and network equipment for estimating downlink modulation coding mode |
| WO2023029751A1 (en) * | 2021-08-31 | 2023-03-09 | 中兴通讯股份有限公司 | Adaptive coding and modulation method and apparatus, electronic device and storage medium |
| WO2023077298A1 (en) * | 2021-11-03 | 2023-05-11 | Huawei Technologies Co., Ltd. | Devices and methods for punctured transmission in a wireless network |
| CN115396977A (en) * | 2022-08-12 | 2022-11-25 | 中国联合网络通信集团有限公司 | Method, device and equipment for determining signal transmission path and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| "5GAA_S-200230_TR 103 439 stable draft v003_5GAA edit".3GPP inbox\lss_from_external_bodies.2020,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116800382A (en) | 2023-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107968689B (en) | Perception identification method and device based on wireless communication signals | |
| US11212650B2 (en) | Device-free localization methods within smart indoor environments | |
| CN108156519B (en) | Image classification method, television device and computer-readable storage medium | |
| US10671058B2 (en) | Monitoring server, distributed-processing determination method, and non-transitory computer-readable medium storing program | |
| US20210219384A1 (en) | Procedure for optimization of self-organizing network | |
| Arshad et al. | Leveraging transfer learning in multiple human activity recognition using WiFi signal | |
| CN112001274B (en) | Crowd density determining method, device, storage medium and processor | |
| US20240073797A1 (en) | Systems and methods for time domain channel representation information for wi-fi sensing | |
| CN111466130A (en) | Performing analysis and management of a mobile communication network based on performance information, configuration information and environment information | |
| US20240031774A1 (en) | Device-free localization methods within smart indoor environments | |
| WO2021183993A1 (en) | Vision-aided wireless communication systems | |
| CN116095778A (en) | WIFI network switching method based on indoor azimuth depth perception | |
| CN116800382B (en) | Index modulation method and device based on visual sensor | |
| Tong et al. | A fine-grained channel state information-based deep learning system for dynamic gesture recognition | |
| US11469797B2 (en) | Rank indicator (RI) and channel quality indicator (CQI) estimation using a multi-layer perceptron (MLP) | |
| JP2019208188A (en) | Communication system, traffic control device, and traffic control method | |
| US20230291517A1 (en) | Communication method, communications apparatus, and communications device | |
| EP4236428A1 (en) | Communication data processing method and apparatus, and communication device | |
| Mukhtar | Machine learning enabled-localization in 5g and lte using image classification and deep learning | |
| Liu et al. | Deep learning based encryption policy intrusion detection using commodity WiFi | |
| CN109558839A (en) | Adaptive face identification method and the equipment and system for realizing this method | |
| US20230299841A1 (en) | Dynamic Channel Selection For Unmanned Aerial Vehicles | |
| EP3783925B1 (en) | Determination of indoor/outdoor in mobile networks using deep learning | |
| US20230292282A1 (en) | Wireless lan signal based motion detection method and device | |
| CN116318297A (en) | Wireless gesture sensing solution method and device |
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 |