CN118200492B - Wi-Fi-based video transmission method and device, automatic aircraft and storage medium - Google Patents
Wi-Fi-based video transmission method and device, automatic aircraft and storage medium Download PDFInfo
- Publication number
- CN118200492B CN118200492B CN202410612697.1A CN202410612697A CN118200492B CN 118200492 B CN118200492 B CN 118200492B CN 202410612697 A CN202410612697 A CN 202410612697A CN 118200492 B CN118200492 B CN 118200492B
- Authority
- CN
- China
- Prior art keywords
- target
- value
- code rate
- module
- gray scale
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000007689 inspection Methods 0.000 claims abstract description 102
- 238000001514 detection method Methods 0.000 claims description 50
- 238000004590 computer program Methods 0.000 claims description 21
- 238000013507 mapping Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 7
- 230000003213 activating effect Effects 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 230000008859 change Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000003828 downregulation Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 230000000875 corresponding effect Effects 0.000 description 2
- 230000002222 downregulating effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000013526 transfer learning Methods 0.000 description 2
- 230000003827 upregulation Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
- H04N7/185—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source from a mobile camera, e.g. for remote control
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/146—Data rate or code amount at the encoder output
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a Wi-Fi-based video transmission method, a Wi-Fi-based video transmission device, an automatic aircraft and a storage medium, wherein the Wi-Fi-based video transmission method comprises the following steps: when the industrial equipment flies above and performs equipment inspection tasks, acquiring original video data of the industrial equipment; inquiring a code rate set for equipment inspection tasks; encoding the original video data into target video data according to the code rate; invoking a Wi-Fi module to transmit target video data to a machine nest distributed around the industrial equipment so as to detect the target probability of the safety event of the industrial equipment according to the target video data; determining a gray scale interval according to the code rate; calculating uncertainty of equipment inspection tasks according to the original video data and flight parameters of the automatic aircraft; the signal parameters of the Wi-Fi module are linearly fused into the Wi-Fi module to calculate a transmission quality value; and adjusting the code rate according to the uncertainty and the transmission quality value on the relation between the target probability and the gray scale interval. Dynamic change of code rate is realized, and efficiency of detecting safety events is improved.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a Wi-Fi-based video transmission method and device, an automatic aircraft and a storage medium.
Background
In the scenes of power systems, industrial parks, rail transit and the like, an automatic aircraft (Unmanned AERIAL VEHICLE, UAV) is used for inspecting industrial equipment (such as a power transmission line, a transformer, a warehouse, a rail and the like), video data are collected for the industrial equipment, the video data are transmitted to a cloud in real time or in a delayed manner, and whether safety events such as fire disasters, artificial damages and the like occur in the industrial equipment are analyzed.
At present, an automatic aircraft encodes video data with a code rate set by an offline experiment, and the environment of the automatic aircraft changes faster, and the flexibility of a fixed code rate is lower, so that the efficiency of detecting a security event is lower.
Disclosure of Invention
The invention provides a Wi-Fi-based video transmission method and device, an automatic aircraft and a storage medium, so as to improve the flexibility of the code rate of video data transmitted by the automatic aircraft.
According to an aspect of the present invention, there is provided a Wi-Fi-based video transmission method applied to an automatic aircraft, in which a Wi-Fi module is provided, the method including:
when an industrial device flies above and executes a device inspection task, acquiring original video data of the industrial device;
Inquiring a code rate set for the equipment inspection task;
Encoding the original video data into target video data according to the code rate;
invoking the Wi-Fi module to transmit the target video data to a machine nest distributed around the industrial equipment so as to detect the target probability of the safety event of the industrial equipment according to the target video data;
Determining a gray scale interval according to the code rate; the upper limit value of the gray scale interval is a critical point of the industrial equipment for generating a safety event, and the lower limit value of the gray scale interval is a critical point of the industrial equipment for not generating the safety event;
calculating uncertainty of the equipment inspection task according to the original video data and the flight parameters of the automatic aircraft;
linearly fusing signal parameters of the Wi-Fi module into the Wi-Fi module to calculate a transmission quality value;
And adjusting the code rate according to the uncertainty and the transmission quality value on the relation between the target probability and the gray scale interval.
According to another aspect of the present invention, there is provided a Wi-Fi based video transmission apparatus for use in an automatic aircraft in which a Wi-Fi module is provided, the apparatus comprising:
the video acquisition module is used for acquiring original video data of the industrial equipment when the industrial equipment flies above and executes equipment inspection tasks;
the code rate inquiry module is used for inquiring the code rate set for the equipment inspection task;
the video coding module is used for coding the original video data into target video data according to the code rate;
The target detection module is used for calling the Wi-Fi module to transmit the target video data to a machine nest distributed around the industrial equipment so as to detect the target probability of the safety event of the industrial equipment according to the target video data;
the gray scale interval determining module is used for determining a gray scale interval according to the code rate; the upper limit value of the gray scale interval is a critical point of the industrial equipment for generating a safety event, and the lower limit value of the gray scale interval is a critical point of the industrial equipment for not generating the safety event;
the uncertainty calculation module is used for calculating uncertainty of the equipment inspection task according to the original video data and the flight parameters of the automatic aircraft;
the transmission quality value calculation module is used for linearly fusing the signal parameters of the Wi-Fi module into the Wi-Fi module to calculate a transmission quality value;
And the code rate adjusting module is used for adjusting the code rate according to the uncertainty and the transmission quality value on the relation between the target probability and the gray scale interval.
According to another aspect of the present invention, there is provided an automatic aircraft comprising:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the Wi-Fi based video transmission method of any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing a computer program for causing a processor to implement the Wi-Fi based video transmission method according to any one of the embodiments of the present invention when executed.
In the embodiment, the dynamic change of the code rate according to the uncertainty of the equipment inspection task and the performance of Wi-Fi is realized, the flexibility of the code rate of the video data transmitted by the automatic aircraft is improved, and the adaptation degree of the equipment inspection task and the actual detection condition is improved, so that the efficiency of detecting the security event is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a video transmission method based on Wi-Fi according to a first embodiment of the present invention;
Fig. 2 is a schematic structural diagram of a video transmission device based on Wi-Fi according to a second embodiment of the present invention;
Fig. 3 is a schematic structural view of an automatic aircraft according to a third embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein are capable of being practiced otherwise than as specifically illustrated and described. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a Wi-Fi based video transmission method according to an embodiment of the present invention, where the method may be performed by a Wi-Fi based video transmission device, and the Wi-Fi based video transmission device may be implemented in hardware and/or software, and the Wi-Fi based video transmission device may be configured in an automatic aircraft. As shown in fig. 1, the method includes:
And 101, acquiring original video data of the industrial equipment when the industrial equipment flies above and performs equipment inspection tasks.
In this embodiment, the present invention is applicable to an automatic vehicle, particularly a commercial automatic vehicle such as a four-axis automatic vehicle, a six-axis automatic vehicle, or the like, which may be powered by a battery or may be powered by fuel, but the present invention is not limited thereto.
A plurality of machine nests are arranged on the periphery of industrial equipment, are remote take-off and landing platforms of the automatic aircraft, can resist severe weather such as strong wind and heavy rain, are interconnected and communicated with the cloud, and realize the functions of storage, charging, state monitoring, data transmission and the like of the automatic aircraft.
The device comprises a plurality of machine nests, wherein Wi-Fi (WIRELESS FIDELITY ) modules are arranged in each machine nest, wi-Fi modules, cameras, gyroscopes, height sensors, speed sensors and other components are arranged in the automatic aircraft, and the Wi-Fi modules in the automatic aircraft can be in wireless connection with the Wi-Fi modules in any machine nest.
In practical application, equipment inspection tasks can be generated for industrial equipment periodically or irregularly (such as faults and the like), namely whether safety events occur in the industrial equipment or not is inspected, a flight route is planned for the industrial equipment, the flight route is written into the equipment inspection tasks, the equipment inspection tasks are sent to an automatic aircraft, the automatic aircraft executes the equipment inspection tasks and flies above the industrial equipment according to the flight route, and in the flying process, a camera is called to acquire video data for the industrial equipment and record the video data as original video data.
And 102, inquiring the code rate set for the equipment inspection task.
In this embodiment, it may be detected that an automatic aircraft performs a device inspection task in an experimental environment, and scene information about when an industrial device flies, such as signal quality of a Wi-Fi module, confidence level of detecting that an industrial device has a security event, and the like, and an appropriate code rate is selected according to the scene information, and the code rate is written into a configuration file of the automatic aircraft for performing the device inspection task.
When the automatic aircraft executes a new equipment inspection task, the code rate set for the equipment inspection task is read from the configuration file and used as an initial code rate.
Step 103, the original video data is encoded into target video data according to the code rate.
In this embodiment, the automatic aircraft starts the encoder, and the encoder encodes (including software encoding and/or hardware encoding) the original video data according to the currently set code rate, so as to obtain the target video data.
The control mode of the code rate is variable code rate control (Variable Bitrate, VBR), namely, the encoder can dynamically adjust the bit rate according to the signal parameters of the Wi-Fi module, the uncertainty of the equipment inspection task and other factors, and the dynamic change of the code rate is realized.
Then, the currently set code rate may be the initial code rate, or the code rate that is adjusted according to the signal parameter of the Wi-Fi module, the uncertainty of the equipment inspection task, and the like.
Step 104, invoking the Wi-Fi module to transmit the target video data to a machine nest distributed around the industrial equipment so as to detect the target probability of the safety event of the industrial equipment according to the target video data.
In practical application, each machine nest uses Wi-Fi module to set up an Access Point (AP), and the Wi-Fi module is automatically flown and called to detect the RSSI (RECEIVED SIGNAL STRENGTH Indication) of each AP, and establishes wireless connection with the AP with the highest RSSI, and the target video data is transmitted to the machine nest distributed around the industrial equipment through the wireless connection.
In one case, the machine nest serves as an edge computing node, a first detection model can be deployed in the machine nest, and each frame of target image data in the target video data is input into the first detection model to detect the target probability of the occurrence of a security event of the industrial equipment.
In another case, a first detection model is deployed in the cloud, the machine nest transmits target video data to the cloud, and the cloud inputs each frame of target image data in the target video data into the first detection model to detect target probability of occurrence of a safety event of industrial equipment.
Further, the first detection model is a network based on training of deep learning whether a safety event occurs for the industrial equipment, the structure of the first detection model is not limited to a neural network designed manually, may be a target detection network, may be a classification network of two or more classifications, for example AlexNet, VGGNet, resNet, YOLO, R-CNN, etc., may be a neural network optimized by a model quantization method, a neural network searched for characteristics of the industrial equipment by a NAS (Neural Architecture Search, neural network structure search) method, etc., which is not limited in this embodiment.
And 105, determining a gray scale interval according to the code rate.
In practical application, the code rate of the target video data is positively correlated with the definition of the target image data in the target video data, and the definition of the target image data is positively correlated with the confidence that the first detection model detects the safety event of the industrial equipment, so that the code rate of the target video data affects the confidence that the first detection model detects the safety event of the industrial equipment to a certain extent.
In this embodiment, the gray scale interval may be selected according to the adaptive code rate, where the upper limit value of the gray scale interval is a critical point where the industrial device generates a security event, and the lower limit value of the gray scale interval is a critical point where the industrial device does not generate a security event, and the target probability of the industrial device generating a security event is compared with the gray scale interval, so as to determine whether the industrial device generates a security event.
Specifically, if the target probability of the occurrence of the security event by the industrial device is greater than or equal to the upper limit value of the gray scale interval, which indicates that the confidence of the occurrence of the security event by the industrial device is high, the occurrence of the security event by the industrial device may be determined.
If the target probability of the safety event of the industrial equipment is smaller than the lower limit value of the gray scale interval, the confidence of the safety event of the industrial equipment is higher, and it can be determined that the safety event of the industrial equipment does not occur.
If the target probability of the safety event of the industrial equipment is smaller than the upper limit value of the gray level interval and larger than or equal to the lower limit value of the gray level interval, the confidence of the safety event of the industrial equipment is lower, the possibility of false detection exists, whether the safety event of the industrial equipment occurs cannot be directly distinguished, and the safety event of the industrial equipment is obtained by correcting the safety event according to the history and/or future detection results (namely whether the safety event of the industrial equipment occurs).
For example, the interval mapping table may be constructed experimentally in advance, and written into a configuration file of the automatic aircraft for performing the equipment inspection task.
The interval mapping table records mapping relations between a plurality of coding ranges and gray intervals; the larger the coding range (expressed as a midpoint), the larger the upper limit value of the gray scale interval (expressed as a midpoint), the smaller the lower limit value of the gray scale interval (expressed as a midpoint), so that the larger the length of the gray scale interval, whereas the smaller the coding range (expressed as a midpoint), the smaller the upper limit value of the gray scale interval (expressed as a midpoint), the larger the lower limit value of the gray scale interval (expressed as a midpoint), and the larger the lower limit value of the gray scale interval (expressed as a midpoint), so that the smaller the length of the gray scale interval.
When the automatic aircraft executes a new equipment inspection task, an interval mapping table set for the equipment inspection task is queried from a configuration file, and the current code rate is compared with each coding range, so that a gray scale interval mapped by the coding range where the current code rate is located is extracted.
And 106, calculating uncertainty of the equipment inspection task according to the original video data and the flight parameters of the automatic aircraft.
In practical application, certain information is lost in the process of encoding the original video data into the target video data, and in the process of acquiring the original video data by the automatic aircraft, the picture quality of the original video data is influenced by the state of the automatic aircraft and the surrounding environment, and the influences are superposed on the target video data, so that the uncertainty of equipment inspection tasks is increased.
Where uncertainty refers to the relative entropy in probability of detecting whether a security event has occurred in an industrial device, the uncertainty may be represented differently for data of different state quantities, e.g., a single variance number for a one-dimensional state quantity, a covariance for a two-dimensional state quantity, etc.
Therefore, the original video data and the target video data can be compared, the loss degree of information is measured, the flight parameters of the automatic aircraft are collected, the influence of the self state and the surrounding environment is reflected, and the uncertainty of the equipment inspection task is comprehensively measured.
For the detection of a single factor, the fluctuation of uncertainty is large, and the detection of a plurality of factors is integrated, so that the fluctuation of uncertainty can be reduced, and the accuracy of measuring the uncertainty is improved.
In one embodiment of the present invention, step 106 may include the steps of:
Step 1061, loading a second detection model trained by the first detection model as a teacher network and used as a student network.
And when offline, the teacher network and the student network in the transfer learning (TRANFERS LEARNING) can compress the first detection model, and at the moment, the first detection model is set as the teacher network, and the second detection model serving as the student network is compressed.
In general, a teacher network is often a more complex model with higher performance and generalization capability, and is used as a soft target to guide another simpler student network to learn, so that a simpler student network with less parameter calculation can also have performance similar to the teacher network.
In the transfer learning, the first detection model is used for detecting the target probability of the safety event of the industrial equipment according to the target image data in the target video data, and correspondingly, the second detection model is used for detecting the original probability of the safety event of the industrial equipment according to the original image data in the original video data.
The second detection model used as the student network belongs to a lightweight network, can be used as an end-side network to be carried on an automatic aircraft, and can be loaded to a memory for operation when the automatic aircraft executes a new equipment inspection task.
Besides, the second detection model can also detect the original probability of the safety event of the industrial equipment in real time according to the original image data in the original video data in the equipment inspection task with higher real-time performance besides the uncertainty of the equipment inspection task, judge whether the safety event of the industrial equipment occurs according to the original probability by using a threshold method and other methods, trigger safety measures such as alarm and the like when judging that the safety event of the industrial equipment occurs, and realize real-time monitoring of the safety state of the industrial equipment.
Step 1062, inputting the original image data in the original video data into the second detection model to detect an original probability of the industrial equipment generating a security event.
In this embodiment, the nest may send the target probability and the frame identifier (such as the frame number and the frame ID) of the target image data thereof to the automatic aircraft by using the Wi-Fi module, and the automatic aircraft may select the original image data of the same frame as the target image data from the cached original video data according to the frame identifier, that is, the original image data is encoded to be the target image data, so that the original image data and the target image data have the same content, and the uncertainty is convenient to calculate.
The frame of raw image data is preprocessed (e.g., rotated, cropped, compressed, brightness adjusted, etc.), and after the preprocessing is completed, the frame of raw image data is input into a second detection model for processing, and the second detection model outputs the raw probability of the safety event of the industrial equipment.
Step 1063, comparing the original probability with the target probability to generate a first fluctuation value for the equipment inspection task.
Under the conditions that the content is the same and the performances of the first detection model and the second detection model are close, the original probability and the target probability are compared, the uncertainty caused by coding can be measured to a certain extent, and a first fluctuation value for measuring the uncertainty is generated for the equipment inspection task according to the comparison result.
Illustratively, taking a series of original probabilities and a corresponding series of target probabilities as discrete random variables, the original probabilities and the target probabilities may be substituted into the following formula to generate a first fluctuation value for the equipment inspection task, thereby measuring the distribution difference of the two discrete random variables:
；
Wherein F 1 is a first fluctuation value, P 1i is an original probability of the i-th frame original image data, P 2i is a target probability of the i-th frame target image data, i e n, n is a number of original image data and a number of target image data, μ 1 is an average value of the original probabilities of the n-frame original image data, μ 2 is an average value of the target probabilities of the n-frame target image data, σ 1 is a standard deviation of the original probabilities of the n-frame original image data, and σ 2 is a standard deviation of the target probabilities of the n-frame target image data.
Step 1064, inquiring the flying height, flying speed and flying amplitude of the automatic aircraft as flying parameters.
In one aspect, a height sensor may be activated, and the altitude of flight at which the raw video data was acquired is read from the height sensor as one of the flight parameters.
In another aspect, a speed sensor may be activated, from which the speed of flight at the time of acquisition of the raw video data is read as one of the flight parameters.
In yet another aspect, a gyroscope may be activated, angular velocities in each direction may be read from the gyroscope, integrated over a dimension of time to obtain magnitudes in each direction, and euclidean distances calculated for the magnitudes in each direction to obtain a flight rotor as one of the flight parameters. The flight rotor then represents the magnitude of the automatic vehicle rotation.
Step 1065, generating a second fluctuation value for the equipment inspection task according to the flight altitude.
Aiming at the same industrial equipment, the scales of video data collected by the automatic aircraft at different flying heights are different, and the first detection model and the second detection model have different performances on the image data at different scales, so that the flying height can measure the uncertainty of the self state to the equipment inspection task to a certain extent, and therefore, a second fluctuation value for measuring the uncertainty can be generated for the equipment inspection task independently according to the flying height.
For example, an average value may be calculated for a flight height of a segment when the original video data is collected, to obtain an average height, and a second fluctuation value may be calculated for the equipment inspection task with a natural number as a base and a ratio between the average height and a preset standard height as an index.
The standard height is an ideal flying height measured on the automatic aircraft in the aspects of obstacle avoidance, scale and the like according to an experimental mode.
Then, the second fluctuation value may be expressed as:
F2=exp(H/High)
wherein F 2 is a second fluctuation value, exp () is an exponential function based on a natural number, H is an average height, and High is a standard height.
Step 1066, generating a third fluctuation value for the equipment inspection task according to the flying speed and the flying amplitude.
In practical application, the automatic aircraft can encounter natural wind with unequal intensity and unequal direction during flight, and the natural wind can cause shaking problem for the automatic aircraft, so that the decision flying speed of the automatic aircraft is influenced, and the picture quality of video data is also influenced.
For an automatic aircraft for industrial inspection, no professional wind speed sensor is carried, and parameters such as the intensity and the direction of natural wind cannot be directly measured, but the flying speed and the flying amplitude can reflect the decision of the automatic aircraft against the natural wind to a certain extent, so that the uncertainty of the self state and the surrounding environment complex to the equipment inspection task can be measured to a certain extent, and a third fluctuation value for measuring the uncertainty can be generated for the equipment inspection task according to the flying speed and the flying amplitude.
Illustratively, an average value is calculated for a segment of the flight speed when the original video data is acquired to obtain an average speed, and an average value is calculated for a segment of the flight width when the original video data is acquired to obtain an average width.
In one aspect, the average speed and the average amplitude are linearly fused to a real-time jitter value.
On the other hand, a correlation coefficient between the flying speed and the flying amplitude is calculated, such as a Pearson correlation coefficient, a Spearman correlation coefficient, a Kendall correlation coefficient, and a product between a preset standard jitter value and the correlation coefficient is calculated to obtain a target jitter value.
The standard jitter value is an ideal jitter value measured by the automatic aircraft in the aspects of obstacle avoidance, scale and the like in an experimental mode, and a value obtained by mapping the ideal jitter value in a linear or nonlinear mode is used.
And calculating a third fluctuation value for the equipment inspection task by taking the natural number as a base and the ratio between the real-time jitter value and the target jitter value as an index.
Then, the third fluctuation value may be expressed as:
F3=exp((αV+βA)/ShakeC)
Wherein F 3 is a third fluctuation value, exp () is an exponential function based on a natural number, V is an average speed, a is an average rotation amplitude, C is a correlation coefficient, shake is a standard jitter value, α is a weight configured for the average speed in linear fusion, and β is a weight configured for the average rotation amplitude in linear fusion.
Step 1067, linearly fusing the first fluctuation value, the second fluctuation value and the third fluctuation value into uncertainty of the equipment inspection task.
In this embodiment, the first fluctuation value, the second fluctuation value and the third fluctuation value may be linearly fused to obtain uncertainty of the equipment inspection task.
Then, the uncertainty of the device inspection task is expressed as:
Uncertainty=w1F1+w2F2+w3F3
wherein, uncertinty is the Uncertainty of the equipment inspection task, F 1 is the first fluctuation value, F 2 is the second fluctuation value, F 3 is the third fluctuation value, w 1 is the weight configured for the first fluctuation value in linear fusion, w 2 is the weight configured for the second fluctuation value in linear fusion, and w 3 is the weight configured for the third fluctuation value in linear fusion.
And 107, linearly fusing the signal parameters of the Wi-Fi module into the Wi-Fi module to calculate a transmission quality value.
In practical application, the signal quality of the Wi-Fi module on the automatic aircraft has a certain influence on the transmission quality (such as time delay, packet loss rate and the like) of the original video data.
In this embodiment, signal parameters, such as transmit power, antenna gain, etc., when the original video data is collected may be detected, and because of the fluctuation of these signal parameters, these signal parameters may be characterized by statistical data such as average value, maximum value, minimum value, etc., and these signal parameters are combined into Wi-Fi module to calculate a transmission quality value, i.e. the transmission quality value is a performance parameter reflecting the Wi-Fi module as a whole.
And step 108, adjusting the code rate according to the uncertainty and the transmission quality value on the relation between the target probability and the gray scale interval.
In practical application, comparing the target probability with the gray scale interval to obtain the relation between the target probability and the gray scale interval, on the basis, adjusting the code rate by combining the uncertainty of the equipment inspection task and the transmission quality value of the Wi-Fi module, returning to execute step 103, and continuously encoding the original video data into the target video data according to the new code rate until the automatic aircraft completes the equipment inspection task and drops into a certain aircraft nest.
In one embodiment of the present invention, step 108 may include the steps of:
Step 1081, mapping the uncertainty and the transmission quality value to an amplitude for adjusting the code rate.
In this embodiment, the uncertainty of the equipment inspection task and the transmission quality value of the Wi-Fi module may be mapped together in a linear or nonlinear manner to an amplitude for adjusting the code rate.
The amplitude of the adjustment code rate is inversely related to the uncertainty of the equipment inspection task, and the amplitude of the adjustment code rate is positively related to the transmission quality of the Wi-Fi module.
And if the uncertainty of the equipment inspection task is larger, the amplitude of the adjustment code rate is smaller, otherwise, the uncertainty of the equipment inspection task is smaller, and the amplitude of the adjustment code rate is larger, so that the stability of the equipment inspection task is maintained.
The higher the transmission quality of the Wi-Fi module is, the larger the amplitude of the adjustment code rate is, and the lower the transmission quality of the Wi-Fi module is, the smaller the amplitude of the adjustment code rate is, so that the balance between the performance of the Wi-Fi module and the performance of the equipment inspection task is achieved, when the performance of the Wi-Fi module is higher, the performance of the Wi-Fi module is fully utilized, the high-quality target video data is transmitted, the accuracy of the equipment inspection task is improved, and when the performance of the Wi-Fi module is lower, the high-quality target video data is transmitted within the allowable range of the performance of the Wi-Fi module, and the executability and the instantaneity of the equipment inspection task are improved under the condition that the equipment inspection task has a certain accuracy are ensured.
Illustratively, the product between the transmission quality value of the Wi-Fi module and the preset first weight is subtracted by the product between the uncertainty of the equipment inspection task and the preset second weight to obtain an adjustment base, the adjustment base is activated by using an activation function such as Sigmoid to obtain an adjustment coefficient, and the product between the adjustment coefficient and the preset step length is calculated to obtain the amplitude of the adjustment code rate.
Then the magnitude of the adjustment code rate can be expressed as:
Volume=StepActive(γSignal-δUncertainty)
wherein Volume is the amplitude of the adjustment code rate, signal is the transmission quality value of Wi-Fi module, uncertainty is the Uncertainty of the equipment inspection task, step is the Step size, gamma is the first weight, delta is the second weight, and Active () is the activation function.
Step 1082, if the target probability is greater than or equal to the upper limit value of the gray scale interval and the difference between the target probability and the upper limit value of the gray scale interval is greater than or equal to the preset safety threshold value, calculating the difference between the current target probability and the last target probability to obtain the probability deviation.
If the target probability is greater than or equal to the upper limit value of the gray scale interval and the difference between the target probability and the upper limit value of the gray scale interval is greater than or equal to a preset safety threshold value, the code rate has a space for down adjustment under the condition that the accuracy of the equipment inspection task is ensured, and at the moment, the difference between the target probability at the current moment and the target probability at the last moment can be calculated and used as probability deviation.
Step 1083, if the probability deviation is greater than or equal to the preset deviation threshold, maintaining the code rate unchanged.
If the probability deviation is larger than or equal to a preset deviation threshold, the probability deviation indicates that the fluctuation of the equipment inspection task is larger, so that the code rate can be maintained unchanged, and the stability of the equipment inspection task is maintained.
Step 1084, if the probability deviation is smaller than the preset deviation threshold, the code rate is adjusted down according to the amplitude.
If the probability deviation is smaller than a preset deviation threshold, the probability deviation indicates that the fluctuation of the equipment inspection task is smaller, and the current code rate can be adjusted down according to the amplitude.
When the current code rate is adjusted downwards, the amplitude is subtracted on the basis of the current code rate, and a new code rate is obtained.
And if the automatic aircraft supports the new code rate, confirming the new code rate as the code rate after the down-regulation.
If the automatic vehicle does not support the new code rate, other code rates that are smaller than the current code rate and that are closest to the new code rate may be set as the code rate after the downregulation.
Step 1085, if the target probability is greater than or equal to the upper limit value of the gray scale interval and the difference between the target probability and the upper limit value of the gray scale interval is less than the preset safety threshold value, maintaining the code rate unchanged.
If the target probability is greater than or equal to the upper limit value of the gray scale interval and the difference value between the target probability and the upper limit value of the gray scale interval is smaller than the preset safety threshold value, the code rate is maintained unchanged without a down-regulating space under the condition that the accuracy of the equipment inspection task is ensured.
Step 1086, if the target probability is smaller than the upper limit value of the gray scale interval and greater than or equal to the lower limit value of the gray scale interval, adjusting the code rate according to the amplitude.
If the target probability is smaller than the upper limit value of the gray interval and larger than or equal to the lower limit value of the gray interval, that is, the target probability is located in the gray interval, the code rate can be adjusted up according to the amplitude, and the confidence of the target probability can be improved.
When the current code rate is adjusted upwards, the amplitude is added on the basis of the current code rate, and a new code rate is obtained.
And if the automatic aircraft supports the new code rate, confirming the new code rate as the code rate after the up-regulation.
If the automatic vehicle does not support the new code rate, other code rates that are greater than the current code rate and that are closest to the new code rate may be set as the up-regulated code rate.
Step 1087, if the target probability is smaller than the lower limit value of the gray scale interval, maintaining the code rate unchanged.
If the target probability is smaller than the lower limit value of the gray scale interval, the code rate can be maintained unchanged.
In the embodiment, when the industrial equipment flies above and performs equipment inspection tasks, original video data are collected for the industrial equipment; inquiring a code rate set for equipment inspection tasks; encoding the original video data into target video data according to the code rate; invoking a Wi-Fi module to transmit target video data to a machine nest distributed around the industrial equipment so as to detect the target probability of the safety event of the industrial equipment according to the target video data; determining a gray scale interval according to the code rate; the upper limit value of the gray scale interval is the critical point of the industrial equipment for generating the safety event, and the lower limit value of the gray scale interval is the critical point of the industrial equipment for not generating the safety event; calculating uncertainty of equipment inspection tasks according to the original video data and flight parameters of the automatic aircraft; the signal parameters of the Wi-Fi module are linearly fused into the Wi-Fi module to calculate a transmission quality value; and adjusting the code rate according to the uncertainty and the transmission quality value on the relation between the target probability and the gray scale interval. The method and the device realize dynamic change of the code rate according to the uncertainty of the equipment inspection task and the performance of Wi-Fi, improve the flexibility of the code rate of video data transmitted by an automatic aircraft, and improve the adaptation degree of the equipment inspection task and the actual detection condition, thereby improving the efficiency of detecting the security event.
Example two
Fig. 2 is a schematic structural diagram of a video transmission device based on Wi-Fi according to a second embodiment of the present invention. As shown in fig. 2, the device is applied to an automatic aircraft, and a Wi-Fi module is arranged in the automatic aircraft, and the device comprises:
the video acquisition module 201 is used for acquiring original video data of industrial equipment when the industrial equipment flies above and performs equipment inspection tasks;
the code rate inquiry module 202 is configured to inquire a code rate set for the equipment inspection task;
A video encoding module 203, configured to encode the original video data into target video data according to the code rate;
The target detection module 204 is configured to invoke the Wi-Fi module to transmit the target video data to a nest distributed around the industrial device, so as to detect a target probability of a security event occurring in the industrial device according to the target video data;
A gray scale interval determining module 205, configured to determine a gray scale interval according to the code rate; the upper limit value of the gray scale interval is a critical point of the industrial equipment for generating a safety event, and the lower limit value of the gray scale interval is a critical point of the industrial equipment for not generating the safety event;
An uncertainty calculation module 206, configured to calculate uncertainty for the equipment inspection task according to the original video data and the flight parameters of the automatic aircraft;
a transmission quality value calculation module 207, configured to linearly fuse signal parameters of the Wi-Fi module into the Wi-Fi module to calculate a transmission quality value;
And the code rate adjusting module 208 is configured to adjust the code rate according to the uncertainty and the transmission quality value in a relation between the target probability and the gray scale interval.
In one embodiment of the present invention, the gray scale interval determining module 205 includes:
the mapping table inquiry module is used for inquiring the interval mapping table; the interval mapping table is recorded with mapping relations between a plurality of coding ranges and gray intervals; the upper limit value of the gray scale interval is inversely related to the coding range, and the lower limit value of the gray scale interval is positively related to the coding range;
and the gray scale interval extraction module is used for extracting the gray scale interval mapped by the coding range where the code rate is located.
In one embodiment of the present invention, the uncertainty calculation module 206 includes:
the detection model loading module is used for loading a second detection model which is trained by the first detection model as a teacher network and is used as a student network; the first detection model is used for detecting target probability of the industrial equipment for generating a security event according to target image data in the target video data;
The original detection module is used for inputting original image data in the original video data into the second detection model to detect the original probability of the industrial equipment for generating a safety event; the original image data is encoded to be the target image data;
the first fluctuation value generation module is used for comparing the original probability with the target probability to generate a first fluctuation value for the equipment inspection task;
the flight parameter query module is used for querying the flight height, the flight speed and the flight amplitude of the automatic aircraft to serve as flight parameters;
the second fluctuation value generation module is used for generating a second fluctuation value for the equipment inspection task according to the flying height;
The third fluctuation value generation module is used for generating a third fluctuation value for the equipment inspection task according to the flying speed and the flying amplitude;
And the uncertainty fusion module is used for linearly fusing the first fluctuation value, the second fluctuation value and the third fluctuation value into uncertainty of the equipment inspection task.
In one embodiment of the present invention, the first fluctuation value generation module is further configured to:
Substituting the original probability and the target probability into the following formula to generate a first fluctuation value for the equipment inspection task:
；
Wherein F 1 is a first fluctuation value, P 1i is the original probability of the original image data of the i-th frame, P 2i is the target probability of the target image data of the i-th frame, i e n, n is the average value of the original probabilities of the original image data of the n-th frame, μ 1 is the average value of the target probabilities of the target image data of the n-th frame, σ 1 is the standard deviation of the original probabilities of the original image data of the n-th frame, and σ 2 is the standard deviation of the target probabilities of the target image data of the n-th frame.
In one embodiment of the present invention, the second fluctuation value generation module is further configured to:
calculating an average value of the flying heights to obtain an average height;
calculating a second fluctuation value for the equipment inspection task by taking a natural number as a bottom and the ratio between the average height and a preset standard height as an index;
The third fluctuation value generation module is further configured to:
calculating an average value of the flying speeds to obtain an average speed;
calculating an average value of the flying frames to obtain an average frame;
linearly fusing the average speed and the average amplitude to form a real-time jitter value;
calculating a correlation coefficient between the flying speed and the flying rotor;
Calculating the product between a preset standard jitter value and the correlation coefficient to obtain a target jitter value;
And calculating a third fluctuation value for the equipment inspection task by taking a natural number as a bottom and the ratio between the real-time jitter value and the target jitter value as an index.
In one embodiment of the present invention, the code rate adjustment module 208 includes:
An amplitude mapping module, configured to map the uncertainty and the transmission quality value to an amplitude for adjusting the code rate; said amplitude being inversely related to said uncertainty and positively related to said transmission quality;
The probability deviation calculation module is used for calculating the difference between the current target probability and the previous target probability to obtain probability deviation if the target probability is larger than or equal to the upper limit value of the gray scale interval and the difference between the target probability and the upper limit value of the gray scale interval is larger than or equal to a preset safety threshold value;
The first maintenance module is used for maintaining the code rate unchanged if the probability deviation is greater than or equal to a preset deviation threshold value;
the down-regulation module is used for down-regulating the code rate according to the amplitude if the probability deviation is smaller than a preset deviation threshold value;
the second maintenance module is used for maintaining the code rate unchanged if the target probability is greater than or equal to the upper limit value of the gray scale interval and the difference value between the target probability and the upper limit value of the gray scale interval is smaller than a preset safety threshold value;
The up-regulation module is used for up-regulating the code rate according to the amplitude if the target probability is smaller than the upper limit value of the gray scale interval and larger than or equal to the lower limit value of the gray scale interval;
And the third maintenance module is used for maintaining the code rate unchanged if the target probability is smaller than the lower limit value of the gray scale interval.
In one embodiment of the invention, the amplitude mapping module is further configured to:
Subtracting the product between the uncertainty and a preset second weight from the product between the transmission quality value and a preset first weight to obtain an adjustment base;
activating the adjustment base to obtain an adjustment coefficient;
And calculating the product between the adjustment coefficient and a preset step length to obtain the amplitude for adjusting the code rate.
The Wi-Fi-based video transmission device provided by the embodiment of the invention can execute the Wi-Fi-based video transmission method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the Wi-Fi-based video transmission method.
Example III
Fig. 3 shows a schematic structural view of an automatic aircraft 10 that may be used to implement an embodiment of the present invention. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 3, the automatic vehicle 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In RAM 13, various programs and data required for the operation of the automatic aircraft 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the automatic aircraft 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the automatic aircraft 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as Wi-Fi based video transmission methods.
In some embodiments, the Wi-Fi based video transmission method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the automatic aircraft 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the Wi-Fi based video transmission method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the Wi-Fi based video transmission method in any other suitable way (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Example IV
The embodiments of the present invention also provide a computer program product comprising a computer program which, when executed by a processor, implements a Wi-Fi based video transmission method as provided by any of the embodiments of the present invention.
Computer program product in the implementation, the computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (8)
1. The Wi-Fi-based video transmission method is characterized by being applied to an automatic aircraft, wherein a Wi-Fi module is arranged in the automatic aircraft, and the method comprises the following steps:
when an industrial device flies above and executes a device inspection task, acquiring original video data of the industrial device;
Inquiring a code rate set for the equipment inspection task;
Encoding the original video data into target video data according to the code rate;
invoking the Wi-Fi module to transmit the target video data to a machine nest distributed around the industrial equipment so as to detect the target probability of the safety event of the industrial equipment according to the target video data;
Determining a gray scale interval according to the code rate; the upper limit value of the gray scale interval is a critical point of the industrial equipment for generating a safety event, and the lower limit value of the gray scale interval is a critical point of the industrial equipment for not generating the safety event;
calculating uncertainty of the equipment inspection task according to the original video data and the flight parameters of the automatic aircraft;
linearly fusing signal parameters of the Wi-Fi module into the Wi-Fi module to calculate a transmission quality value;
adjusting the code rate according to the uncertainty and the transmission quality value in the relation between the target probability and the gray scale interval;
Wherein, the determining the gray scale interval according to the code rate includes:
Querying an interval mapping table; the interval mapping table is recorded with mapping relations between a plurality of coding ranges and gray intervals; the upper limit value of the gray scale interval is inversely related to the coding range, and the lower limit value of the gray scale interval is positively related to the coding range;
Extracting a gray scale interval mapped by the coding range where the code rate is located;
the calculating uncertainty of the equipment inspection task according to the original video data and the flight parameters of the automatic aircraft comprises the following steps:
Loading a second detection model which is trained by taking the first detection model as a teacher network and is taken as a student network; the first detection model is used for detecting target probability of the industrial equipment for generating a security event according to target image data in the target video data;
inputting original image data in the original video data into the second detection model to detect the original probability of the industrial equipment for generating a security event; the original image data is encoded to be the target image data;
Comparing the original probability with the target probability to generate a first fluctuation value for the equipment inspection task;
inquiring the flying height, the flying speed and the flying amplitude of the automatic aircraft as flying parameters;
generating a second fluctuation value for the equipment inspection task according to the flying height;
Generating a third fluctuation value for the equipment inspection task according to the flying speed and the flying amplitude;
And linearly fusing the first fluctuation value, the second fluctuation value and the third fluctuation value into uncertainty of the equipment inspection task.
2. The method of claim 1, wherein the comparing the raw probability with the target probability to generate a first fluctuation value for the equipment inspection task comprises:
Substituting the original probability and the target probability into the following formula to generate a first fluctuation value for the equipment inspection task:
；
Wherein F 1 is a first fluctuation value, P 1i is the original probability of the original image data of the i-th frame, P 2i is the target probability of the target image data of the i-th frame, i e n, n is the average value of the original probabilities of the original image data of the n-th frame, μ 1 is the average value of the target probabilities of the target image data of the n-th frame, σ 1 is the standard deviation of the original probabilities of the original image data of the n-th frame, and σ 2 is the standard deviation of the target probabilities of the target image data of the n-th frame.
3. The method of claim 1, wherein generating a second fluctuation value for the equipment inspection mission as a function of the altitude of flight comprises:
calculating an average value of the flying heights to obtain an average height;
calculating a second fluctuation value for the equipment inspection task by taking a natural number as a bottom and the ratio between the average height and a preset standard height as an index;
The generating a third fluctuation value for the equipment inspection task according to the flying speed and the flying amplitude comprises the following steps:
calculating an average value of the flying speeds to obtain an average speed;
calculating an average value of the flying frames to obtain an average frame;
linearly fusing the average speed and the average amplitude to form a real-time jitter value;
calculating a correlation coefficient between the flying speed and the flying rotor;
Calculating the product between a preset standard jitter value and the correlation coefficient to obtain a target jitter value;
And calculating a third fluctuation value for the equipment inspection task by taking a natural number as a bottom and the ratio between the real-time jitter value and the target jitter value as an index.
4. A method according to any of claims 1-3, wherein said adjusting said code rate in dependence on said uncertainty and said transmission quality value in relation to said target probability and said gray scale interval comprises:
Mapping the uncertainty and the transmission quality value to an amplitude that adjusts the code rate; said amplitude being inversely related to said uncertainty and positively related to said transmission quality;
if the target probability is greater than or equal to the upper limit value of the gray scale interval and the difference value between the target probability and the upper limit value of the gray scale interval is greater than or equal to a preset safety threshold value, calculating the difference value between the current target probability and the last target probability to obtain probability deviation;
if the probability deviation is greater than or equal to a preset deviation threshold, maintaining the code rate unchanged;
If the probability deviation is smaller than a preset deviation threshold, the code rate is adjusted downwards according to the amplitude;
If the target probability is greater than or equal to the upper limit value of the gray scale interval and the difference between the target probability and the upper limit value of the gray scale interval is smaller than a preset safety threshold value, the code rate is maintained unchanged;
If the target probability is smaller than the upper limit value of the gray scale interval and larger than or equal to the lower limit value of the gray scale interval, the code rate is adjusted upwards according to the amplitude;
And if the target probability is smaller than the lower limit value of the gray scale interval, maintaining the code rate unchanged.
5. The method of claim 4, wherein said mapping the uncertainty with the transmission quality value to adjust the magnitude of the code rate comprises:
Subtracting the product between the uncertainty and a preset second weight from the product between the transmission quality value and a preset first weight to obtain an adjustment base;
activating the adjustment base to obtain an adjustment coefficient;
And calculating the product between the adjustment coefficient and a preset step length to obtain the amplitude for adjusting the code rate.
6. A Wi-Fi based video transmission device, characterized in that it is applied to an automatic aircraft, in which a Wi-Fi module is arranged, said device comprising:
the video acquisition module is used for acquiring original video data of the industrial equipment when the industrial equipment flies above and executes equipment inspection tasks;
the code rate inquiry module is used for inquiring the code rate set for the equipment inspection task;
the video coding module is used for coding the original video data into target video data according to the code rate;
The target detection module is used for calling the Wi-Fi module to transmit the target video data to a machine nest distributed around the industrial equipment so as to detect the target probability of the safety event of the industrial equipment according to the target video data;
the gray scale interval determining module is used for determining a gray scale interval according to the code rate; the upper limit value of the gray scale interval is a critical point of the industrial equipment for generating a safety event, and the lower limit value of the gray scale interval is a critical point of the industrial equipment for not generating the safety event;
the uncertainty calculation module is used for calculating uncertainty of the equipment inspection task according to the original video data and the flight parameters of the automatic aircraft;
the transmission quality value calculation module is used for linearly fusing the signal parameters of the Wi-Fi module into the Wi-Fi module to calculate a transmission quality value;
the code rate adjusting module is used for adjusting the code rate according to the uncertainty and the transmission quality value on the relation between the target probability and the gray scale interval;
wherein, the gray scale interval determining module comprises:
the mapping table inquiry module is used for inquiring the interval mapping table; the interval mapping table is recorded with mapping relations between a plurality of coding ranges and gray intervals; the upper limit value of the gray scale interval is inversely related to the coding range, and the lower limit value of the gray scale interval is positively related to the coding range;
The gray scale interval extraction module is used for extracting a gray scale interval mapped by the coding range where the code rate is located;
The uncertainty calculation module includes:
the detection model loading module is used for loading a second detection model which is trained by the first detection model as a teacher network and is used as a student network; the first detection model is used for detecting target probability of the industrial equipment for generating a security event according to target image data in the target video data;
The original detection module is used for inputting original image data in the original video data into the second detection model to detect the original probability of the industrial equipment for generating a safety event; the original image data is encoded to be the target image data;
the first fluctuation value generation module is used for comparing the original probability with the target probability to generate a first fluctuation value for the equipment inspection task;
the flight parameter query module is used for querying the flight height, the flight speed and the flight amplitude of the automatic aircraft to serve as flight parameters;
the second fluctuation value generation module is used for generating a second fluctuation value for the equipment inspection task according to the flying height;
The third fluctuation value generation module is used for generating a third fluctuation value for the equipment inspection task according to the flying speed and the flying amplitude;
And the uncertainty fusion module is used for linearly fusing the first fluctuation value, the second fluctuation value and the third fluctuation value into uncertainty of the equipment inspection task.
7. An automatic aircraft, the automatic aircraft comprising:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the Wi-Fi based video transmission method of any of claims 1-5.
8. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program for causing a processor to implement the Wi-Fi based video transmission method of any one of claims 1-5 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410612697.1A CN118200492B (en) | 2024-05-17 | 2024-05-17 | Wi-Fi-based video transmission method and device, automatic aircraft and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410612697.1A CN118200492B (en) | 2024-05-17 | 2024-05-17 | Wi-Fi-based video transmission method and device, automatic aircraft and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118200492A CN118200492A (en) | 2024-06-14 |
| CN118200492B true CN118200492B (en) | 2024-07-30 |
Family
ID=91401021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410612697.1A Active CN118200492B (en) | 2024-05-17 | 2024-05-17 | Wi-Fi-based video transmission method and device, automatic aircraft and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118200492B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106657882A (en) * | 2016-10-18 | 2017-05-10 | 国网湖北省电力公司检修公司 | Real-time monitoring method for power transmission and transformation system based on unmanned aerial vehicle |
| CN112953922A (en) * | 2021-02-03 | 2021-06-11 | 西安电子科技大学 | Self-adaptive streaming media control method, system, computer equipment and application |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107465947A (en) * | 2017-08-21 | 2017-12-12 | 广州多益网络股份有限公司 | A kind of adjusting method, device and the Transmission system of the dynamic code rate of streaming media |
| CN111279691B (en) * | 2019-01-31 | 2021-12-07 | 深圳市大疆创新科技有限公司 | Multi-load multipath graph transmission method, control system, terminal, unmanned aerial vehicle and server |
| CN110139113B (en) * | 2019-04-30 | 2021-05-14 | 腾讯科技（深圳）有限公司 | Transmission parameter distribution method and device for video resources |
| US11538347B2 (en) * | 2020-06-12 | 2022-12-27 | Workhorse Group Inc. | UAV delivery control system for UAV delivery of packages |
| CN114006816B (en) * | 2021-11-09 | 2022-11-22 | 湖南大学 | Mobile cloud computing task unloading and resource allocation method and system under uncertain condition |
| CN114253300B (en) * | 2021-12-03 | 2023-04-07 | 国网智能科技股份有限公司 | Unmanned aerial vehicle inspection system and method for gridding machine nest |
| CN114444854A (en) * | 2021-12-20 | 2022-05-06 | 江西怡杉环保股份有限公司 | Lake remote control method and system |
| CN114359758B (en) * | 2022-03-18 | 2022-06-14 | 广东电网有限责任公司东莞供电局 | Power transmission line detection method and device, computer equipment and storage medium |
| CN114913619A (en) * | 2022-04-08 | 2022-08-16 | 华能苏州热电有限责任公司 | Intelligent mobile inspection method and system |
| CN115348417A (en) * | 2022-07-07 | 2022-11-15 | 国电南瑞科技股份有限公司 | Method for realizing code rate self-adaptive control in power video monitoring system |
| CN115759353A (en) * | 2022-10-26 | 2023-03-07 | 国网天津市电力公司 | Digital power flow reliable control method of high-information uncertainty electric power system |
| CN117611950A (en) * | 2023-12-07 | 2024-02-27 | 日立楼宇技术（广州）有限公司 | Sample collection method, system, equipment and storage medium |
-
2024
- 2024-05-17 CN CN202410612697.1A patent/CN118200492B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106657882A (en) * | 2016-10-18 | 2017-05-10 | 国网湖北省电力公司检修公司 | Real-time monitoring method for power transmission and transformation system based on unmanned aerial vehicle |
| CN112953922A (en) * | 2021-02-03 | 2021-06-11 | 西安电子科技大学 | Self-adaptive streaming media control method, system, computer equipment and application |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118200492A (en) | 2024-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113705478B (en) | Mangrove single wood target detection method based on improved YOLOv5 | |
| CN110321853A (en) | Distribution cable external force damage prevention system based on video intelligent detection | |
| CN114333424B (en) | Bridge prevents ship and hits monitoring early warning system | |
| CN110929646A (en) | Power distribution tower reverse-off information rapid identification method based on unmanned aerial vehicle aerial image | |
| CN110516529A (en) | It is a kind of that detection method and system are fed based on deep learning image procossing | |
| CN113076899B (en) | High-voltage transmission line foreign matter detection method based on target tracking algorithm | |
| CN115761537A (en) | Power transmission line foreign matter intrusion identification method oriented to dynamic characteristic supplement mechanism | |
| US10611495B2 (en) | Sea state estimation | |
| CN116664359A (en) | Intelligent fire early warning decision system and method based on multi-sensor fusion | |
| KR102341471B1 (en) | Method and aooaratus for object regobnition using thermal imaging sensor and imaging sensor | |
| CN110262529B (en) | Unmanned aerial vehicle monitoring method and system based on convolutional neural network | |
| CN115082813A (en) | Detection method, unmanned aerial vehicle, detection system and medium | |
| CN118200492B (en) | Wi-Fi-based video transmission method and device, automatic aircraft and storage medium | |
| CN113971775A (en) | Optimized yolov4 algorithm-based violation behavior identification method and system | |
| CN113606099A (en) | Method and system for monitoring icing of blades of wind turbine generator | |
| KR102457470B1 (en) | Apparatus and Method for Artificial Intelligence Based Precipitation Determination Using Image Analysis | |
| CN117177096A (en) | High-voltage transmission line monitoring method and system based on narrow-band satellite network | |
| CN116822716A (en) | Typhoon prediction method, system, equipment and medium based on space-time attention | |
| CN115080629B (en) | Meteorological element forecasting system and method based on remote sensing technology | |
| CN116503798A (en) | Telegraph pole tower inclination monitoring method based on rotation target detection | |
| US11875560B2 (en) | Unmanned aerial vehicle and image recognition method thereof | |
| CN117452958A (en) | Unmanned aerial vehicle inspection scheme making method and system based on artificial intelligence | |
| CN111291597B (en) | Crowd situation analysis method, device, equipment and system based on image | |
| CN114545098B (en) | Thunderstorm forecasting method and lightning positioning method | |
| CN118334543B (en) | Unmanned aerial vehicle-based well lid identification method and device, computer equipment and medium |
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 |