CN116363751A - Climbing action recognition method, device and equipment for electric power tower climbing operation and storage medium - Google Patents
Climbing action recognition method, device and equipment for electric power tower climbing operation and storage medium Download PDFInfo
- Publication number
- CN116363751A CN116363751A CN202310253608.4A CN202310253608A CN116363751A CN 116363751 A CN116363751 A CN 116363751A CN 202310253608 A CN202310253608 A CN 202310253608A CN 116363751 A CN116363751 A CN 116363751A
- Authority
- CN
- China
- Prior art keywords
- climbing
- action
- operator
- data
- motion
- 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.)
- Pending
Links
- 230000009194 climbing Effects 0.000 title claims abstract description 61
- 230000002493 climbing effect Effects 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012706 support-vector machine Methods 0.000 claims abstract description 37
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 230000009471 action Effects 0.000 claims description 66
- 230000006870 function Effects 0.000 claims description 37
- 230000001133 acceleration Effects 0.000 claims description 20
- 230000008859 change Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 11
- 230000000875 corresponding effect Effects 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 10
- 230000003238 somatosensory effect Effects 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 9
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000009434 installation Methods 0.000 abstract description 3
- 238000004590 computer program Methods 0.000 description 19
- 238000004891 communication Methods 0.000 description 8
- 230000006399 behavior Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000002159 abnormal 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
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a device, equipment and a storage medium for identifying climbing actions of electric power tower climbing operation. The method comprises the following steps: the motion data acquired by the motion sensor is acquired, the motion sensor is arranged on a safety belt of an operator, the motion data of the operator are acquired, the motion data are subjected to feature extraction, the motion features of the operator are obtained, the motion features are input into a support vector machine trained in advance to be processed, the recognition result of whether the operator has climbing motion is obtained, the influence on climbing detection caused by camera installation problems, pixel problems and the like in the conventional image recognition technology in the prior art is avoided, the climbing behavior recognition accuracy is improved, and the operation safety is improved.
Description
Technical Field
The present invention relates to computer-aided operation technologies, and in particular, to a method, an apparatus, a device, and a storage medium for identifying climbing actions in power tower climbing operations.
Background
The power engineering is often required to carry out power rush-repair, and when the power is rush-repaired, the power facilities are positioned at high positions, so that the power facilities need to be stepped on the tower for rush-repair by a rush-repair person. Because the scene environment of the aerial work is complex and changeable, a plurality of unknown potential risks exist, such as the aerial work personnel is easy to fall or get electric shock in the climbing process, and the main measures for avoiding the casualties of the aerial work are wearing safety protection measures and strictly implementing the standard operation of each step of aerial work. Whether to operate and wear the safety protection tool is mainly based on subjective consciousness and operation of operators at present or by taking care of the conditions of the operation site by on-site supervisory personnel at any time, problems are found and pointed out. For management of operators and operation sites, great manpower and material resources are required, and as supervision efficiency of various factors cannot be guaranteed, complex factors such as weather, illumination and the like of the high-altitude operation sites are changeable, visual sense fatigue of the site supervision personnel is easily caused, and the guardian and the operator are added with the height difference, so that the guardian is difficult to observe the behaviors of the high-altitude operation personnel.
In the prior art, whether an operator is in a climbing condition is detected by using an image recognition technology, or climbing is identified by using a key point identification method, a key point detection model is obtained by marking common points of skeleton movement when a human body is in climbing, and then whether a monitor is in a climbing state is judged by information such as distance, position, angle and the like among the key points.
By using the image recognition technology, although a detection mode of climbing motion can be provided, by shooting an operator, the climbing motion of the operator is analyzed and processed, and further the abnormal tower climbing operation behavior of the operator is recognized, but there are cases of false detection or missing detection caused by deformation of a target, sudden movement, background clutter, shielding, video frame loss and the like. The identification method based on key point detection can define climbing actions of high-altitude operators in detail, but is also limited by the defects of cameras, is only suitable for deployment of cameras at left and right angles of vertical towers, has a narrow effective monitoring range, is not suitable for deployment in a large range, can intelligently shoot the side of the operators when the operators are far away from the cameras, has lower accuracy of human key point detection, and has almost no effect when more than one operator appears on a working site and the bodies of the two operators are shielded.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for identifying climbing actions of electric power tower climbing operation, which are used for improving the accuracy of climbing action identification and improving the operation safety.
In a first aspect, the invention provides a method for identifying climbing actions of electric power tower climbing operation, comprising the following steps:
acquiring action data acquired by a body sensor, wherein the body sensor is arranged on a safety belt of an operator and is used for acquiring the action data of the operator;
extracting the characteristics of the action data to obtain the action characteristics of the operator;
and inputting the action characteristics into a pre-trained support vector machine for processing to obtain a recognition result of whether the operator has climbing actions.
Optionally, the body sensor includes an acceleration sensor and a gyroscope, the motion data includes acceleration data collected by the acceleration sensor and gesture data collected by the gyroscope, and the motion data is extracted to obtain motion features of the operator, including:
the acceleration data and the gesture data are aligned in time, so that action data are obtained;
selecting action data of a plurality of acquisition points which are continuous in time as a target frame, and recording sequence numbers of the target frame;
performing Fourier transformation on the motion data of the target frame, and extracting frequency domain features and time domain statistical features of the motion data of the target frame;
and taking the sequence number of the target frame, the frequency domain feature and the time domain statistical feature as action features of the operator in the target frame.
Optionally, inputting the motion feature into a pre-trained support vector machine for processing, to obtain a recognition result of whether the operator has climbing motion, including:
mapping the action features from low dimension to high dimension by using a kernel function to obtain high dimension features;
and inputting the high-dimensional features into a pre-trained discriminant function for calculation to obtain a recognition result of whether the operator has climbing actions.
Optionally, the kernel function is a radial basis kernel function, and the radial basis kernel function is:
wherein K (x ', x) is a high-dimensional feature, x is an action feature, x' is the center of the radial basis function, and σ is the radial basis function width parameter.
Optionally, the discriminant function is:
wherein, (x) i ,y i ) To support vector alpha i And b is a parameter of the support vector machine obtained through training.
Optionally, the method further comprises:
acquiring air pressure data acquired by an air pressure sensor, wherein the air pressure sensor is arranged on a safety belt of an operator;
determining a change value of the air pressure of the current sampling point relative to the air pressure of the previous sampling point based on the air pressure data;
and judging whether the worker has climbing action or not based on the change value of the air pressure and the identification result obtained by the support vector machine.
Optionally, before acquiring the motion data acquired by the somatosensory sensor, the method further comprises:
acquiring a plurality of groups of motion data samples acquired by a motion sensor and motion labels corresponding to the motion data samples;
and training a support vector machine by adopting a plurality of groups of action data samples and corresponding action labels, and determining parameters of the support vector machine.
In a second aspect, the present invention further provides a climbing action recognition device for electric power tower climbing operation, including:
the data acquisition module is used for acquiring action data acquired by a body sensing sensor, wherein the body sensing sensor is arranged on a safety belt of an operator and used for acquiring the action data of the operator;
the feature extraction module is used for extracting the features of the action data to obtain the action features of the operators;
and the judging module is used for inputting the action characteristics into a pre-trained support vector machine for processing to obtain the identification result of whether the climbing action exists for the operator.
In a third aspect, the present invention also provides an electronic device, including:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the power tower climbing operation climbing action identification method as provided in the first aspect of the present invention.
In a fourth aspect, the present invention also provides a computer readable storage medium, where computer executable instructions are stored, where the computer executable instructions are used to implement the method for identifying climbing actions of electric power tower climbing operations according to the first aspect of the present invention when executed by a processor.
The invention provides a climbing action recognition method for electric power tower climbing operation, which comprises the following steps: the motion data acquired by the motion sensor is acquired, the motion sensor is arranged on a safety belt of an operator, the motion data of the operator are acquired, the motion data are subjected to feature extraction, the motion features of the operator are obtained, the motion features are input into a support vector machine trained in advance to be processed, the recognition result of whether the operator has climbing motion is obtained, the influence on climbing detection caused by camera installation problems, pixel problems and the like in the conventional image recognition technology in the prior art is avoided, the climbing behavior recognition accuracy is improved, and the operation safety 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 flow chart of a climbing action recognition method for electric power tower climbing operation provided by an embodiment of the invention;
fig. 2 is a schematic structural diagram of a climbing action recognition device for electric power tower climbing operation according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Specific embodiments thereof have been shown by way of example in the drawings and will herein be described in more detail. These drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Fig. 1 is a flowchart of a method for identifying climbing actions of electric power tower climbing operation provided in an embodiment of the present invention, where the method may be applied to determining a situation of climbing actions of electric power operators based on action data collected by a motion sensor, and the method may be performed by an apparatus for identifying climbing actions of electric power tower climbing operation provided in an embodiment of the present invention, where the apparatus may be implemented by software and/or hardware, and is typically configured in a computer device, as shown in fig. 1, where the method for identifying climbing actions of electric power tower climbing operation includes:
s101, acquiring action data acquired by a somatosensory sensor.
In the embodiment of the invention, the body sensor is arranged on a safety belt of an operator and used for collecting action data of the operator. The motion data may include acceleration, gesture, etc., which are not limited herein.
S102, extracting characteristics of the action data to obtain action characteristics of the operator.
In some embodiments of the present invention, a motion sensor includes an acceleration sensor and a gyroscope, motion data includes acceleration data collected by the acceleration sensor and gesture data collected by the gyroscope, and feature extraction is performed on the motion data to obtain motion features of an operator, including the following sub-steps:
1. and aligning the acceleration data and the gesture data in time to obtain action data.
It is known that each sensor has its own clock source with a clock drift that is different for each source, so that even if the individual sensor time stamps are aligned at the initial time, after a certain period of operation, the results of the previous alignment still deviate. Therefore, it is necessary to time align the acceleration data acquired by the acceleration sensor and the attitude data acquired by the gyroscope to obtain the motion data. Illustratively, in some embodiments of the invention, the same reference time is provided to each sensor by a unified clock source, and each sensor calibrates its own clock time according to the provided reference time, thereby achieving time synchronization from hardware.
2. And selecting action data of a plurality of acquisition points which are continuous in time as a target frame, and recording the sequence numbers of the target frames.
The motion data is usually discrete data acquired by a sensor for a plurality of times, and after the aligned motion data is obtained, motion data of a plurality of acquisition points which are continuous in time are selected as target frames, and sequence numbers of the target frames are recorded. Illustratively, in one embodiment of the present invention, motion data for 500 acquisition points that are temporally consecutive is selected as the target frame.
3. And carrying out Fourier transformation on the motion data of the target frame, and extracting the frequency domain characteristics and the time domain statistical characteristics of the motion data of the target frame.
In the embodiment of the invention, discrete Fourier transform is performed on the motion data of the target frame, and the frequency domain characteristics and the time domain statistical characteristics of the motion data of the target frame are extracted. Illustratively, in some embodiments of the invention, the frequency domain features and the time domain statistical features include: total energy, root mean square, skewness, kurtosis, zero crossing rate, spectral entropy, slope sign change number, mean, standard deviation, quartile range, real and imaginary part values of complex numbers at each frequency point of 0-20Hz after Fourier transform, and three inter-axis cross-correlation coefficients of the acceleration sensor and the gyroscope respectively.
4. And taking the sequence number, the frequency domain characteristic and the time domain statistical characteristic of the target frame as action characteristics of operators in the target frame.
After the frequency domain features and the time domain statistical features are obtained, the sequence number of the target frame, the frequency domain features and the time domain statistical features are combined, and the action features of operators in the target frame are obtained.
S103, inputting the action characteristics into a pre-trained support vector machine for processing, and obtaining the recognition result of whether the climbing action exists for the operator.
In the embodiment of the invention, the extracted action features are input into a pre-trained support vector machine for processing, so as to obtain the recognition result of whether the operator has climbing actions. The support vector machine (Support Vector Machine, SVM) is a generalized linear classifier for binary classification of data according to a supervised learning mode, and the decision boundary is the maximum margin hyperplane for solving a learning sample, so that the problem can be converted into a problem for solving convex quadratic programming.
In the embodiment of the invention, the kernel function is adopted to map the action feature from low dimension to high dimension to obtain high dimension feature, and the high dimension feature is input into a pre-trained discriminant function to calculate, so as to obtain the recognition result of whether the operator has climbing action.
Illustratively, in some embodiments of the invention, the kernel function is a radial basis function, which is:
where K (x ', x) is a high-dimensional feature, x is an action feature, x' is the center of the radial basis function, and σ is the radial basis function width parameter.
Illustratively, in some embodiments of the invention, the discriminant function is:
wherein, (x) i ,y i ) To support vector alpha i And b is a parameter of the support vector machine obtained through training. The sgn () function is a sign of the extracted function result, and corresponds to a determination result, for example, the determination function is positive, indicating that the operator has climbing behavior, and when the determination function is negative, indicating that the operator has no climbing behavior.
In some embodiments of the present invention, in order to improve the accuracy of determining the climbing motion, the climbing motion may be determined by combining air pressure data collected by an air pressure sensor. Exemplary, specific steps are as follows:
1. and acquiring air pressure data acquired by an air pressure sensor.
The air pressure sensor is arranged on a safety belt of an operator and used for collecting air pressure data.
2. A change value of the air pressure of the current sampling point relative to the air pressure of the previous sampling point is determined based on the air pressure data.
Comparing the air pressure acquired at the current moment with the air pressure acquired at the previous moment, and calculating the change value of the air pressure of the current sampling point relative to the air pressure of the previous sampling point.
3. And judging whether the worker has climbing action or not based on the change value of the air pressure and the identification result obtained by the support vector machine.
The positive and negative of the air pressure change value reflects the height change of the operator, and when the air pressure change value is positive, the height of the operator is reduced, and when the air pressure change value is negative, the height of the operator is increased. For example, in the embodiment of the invention, when the air pressure change value is negative and the identification result obtained by the support vector machine is that the climbing action exists, whether the operator has the climbing action is judged.
The method for identifying the climbing actions of the electric power tower climbing operation provided by the embodiment of the invention comprises the following steps: the motion data acquired by the motion sensor is acquired, the motion sensor is arranged on a safety belt of an operator, the motion data of the operator are acquired, the motion data are subjected to feature extraction, the motion features of the operator are obtained, the motion features are input into a support vector machine trained in advance to be processed, the recognition result of whether the operator has climbing motion is obtained, the influence on climbing detection caused by camera installation problems, pixel problems and the like in the conventional image recognition technology in the prior art is avoided, the climbing behavior recognition accuracy is improved, and the operation safety is improved.
In the embodiment of the invention, before the support vector machine is applied, the support vector machine is trained, and the specific training process is as follows:
1. and acquiring a plurality of groups of motion data samples acquired by the motion sensor and motion labels corresponding to the motion data samples.
Illustratively, in the embodiment of the present invention, a plurality of groups of motion data samples collected by a somatosensory sensor and motion labels corresponding to the motion data samples are obtained from a history database. The action tag is used to indicate whether or not the set of action data samples has a climbing action.
2. And training a support vector machine by adopting a plurality of groups of action data samples and corresponding action labels, and determining parameters of the support vector machine.
Illustratively, in an embodiment of the present invention, for each set of data samples, the acceleration data and the attitude data are aligned in time, resulting in motion data samples. And selecting action data of a plurality of acquisition points which are continuous in time from each group of action data samples as target frame samples, and recording sequence numbers of the target frame samples. And carrying out Fourier transformation on the motion data of the target frame sample, and extracting the frequency domain characteristics and the time domain statistical characteristics of the motion data of the target frame sample. And taking the sequence number, the frequency domain characteristic and the time domain statistical characteristic of the target frame sample as action characteristics of operators in the target frame. And inputting the action characteristics of the target frame sample into a support vector machine to be trained for processing, and obtaining a prediction result of whether the operator has climbing action. Repeating the above process to obtain the prediction result of each group of action data samples. And calculating a loss value of the prediction result of the support vector machine based on the prediction results of the plurality of groups of motion data samples and the motion labels, re-acquiring the motion data samples when the loss value is higher than a preset value, adjusting parameters of the support vector machine, re-training, and determining that the support vector machine is trained when the loss value is lower than the preset value.
The embodiment of the invention also provides a device for identifying the climbing action of the electric power tower climbing operation, and fig. 2 is a schematic structural diagram of the device for identifying the climbing action of the electric power tower climbing operation, as shown in fig. 2, the device for identifying the climbing action of the electric power tower climbing operation comprises:
the data acquisition module 201 is configured to acquire motion data acquired by a motion sensor, where the motion sensor is disposed on a safety belt of an operator, and is configured to acquire the motion data of the operator;
a feature extraction module 202, configured to perform feature extraction on the motion data to obtain motion features of the operator;
and the judging module 203 is configured to input the motion feature into a pre-trained support vector machine for processing, so as to obtain a recognition result of whether the operator has climbing motion.
In some embodiments of the present invention, the motion data includes acceleration data collected by the acceleration sensor and gesture data collected by the gyroscope, and the feature extraction module 202 includes:
the time alignment sub-module is used for aligning the acceleration data and the gesture data in time to obtain action data;
the target frame determining submodule is used for selecting action data of a plurality of acquisition points which are continuous in time as a target frame and recording the sequence numbers of the target frame;
the feature extraction sub-module is used for carrying out Fourier transformation on the motion data of the target frame and extracting frequency domain features and time domain statistical features of the motion data of the target frame;
and the action characteristic determining submodule is used for taking the sequence number of the target frame, the frequency domain characteristic and the time domain statistical characteristic as action characteristics of the operator in the target frame.
In some embodiments of the present invention, the determining module 203 includes:
the feature mapping submodule is used for mapping the action features from low dimension to high dimension by adopting a kernel function to obtain high-dimension features;
and the identification result determination submodule is used for inputting the high-dimensional characteristics into a pre-trained discriminant function for calculation to obtain an identification result of whether the operator has climbing actions.
In some embodiments of the invention, the kernel function is a radial basis function, the radial basis function being:
wherein K (x ', x) is a high-dimensional feature, x is an action feature, x' is the center of the radial basis function, and σ is the radial basis function width parameter.
In some embodiments of the invention, the discriminant function is:
wherein, (x) i ,y i ) To support vector alpha i And b is a parameter of the support vector machine obtained through training.
In some embodiments of the invention, the power tower climbing operation climbing action recognition device further comprises:
the air pressure data acquisition module is used for acquiring air pressure data acquired by an air pressure sensor, and the air pressure sensor is arranged on a safety belt of the operator;
the air pressure change value determining module is used for determining the change value of the air pressure of the current sampling point relative to the air pressure of the previous sampling point based on the air pressure data;
and the climbing action determining module is used for determining whether the worker has climbing action or not based on the change value of the air pressure and the identification result obtained by the support vector machine.
In some embodiments of the present invention, before acquiring the motion data collected by the motion sensor, the power tower climbing operation climbing motion recognition device further includes:
the sample data acquisition module is used for acquiring a plurality of groups of action data samples acquired by the somatosensory sensor and action labels corresponding to the action data samples;
and the training module is used for training the support vector machine by adopting a plurality of groups of action data samples and corresponding action labels and determining parameters of the support vector machine.
The electric power tower climbing operation climbing action recognition device can execute the electric power tower climbing operation climbing action recognition method provided by any embodiment of the application, and has the corresponding functional modules and beneficial effects of executing the electric power tower climbing operation climbing action recognition method.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 3, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the power tower climbing job climbing action recognition method.
In some embodiments, the power tower climbing job climbing action identification method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the power up-tower job climbing action recognition method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the power tower job climbing action identification method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
The embodiment of the invention also provides a computer program product, which comprises a computer program, wherein the computer program realizes the method for identifying the climbing actions of the power tower climbing operation according to any embodiment of the application when being executed by a processor.
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 (10)
1. The electric power tower climbing operation climbing action recognition method is characterized by comprising the following steps of:
acquiring action data acquired by a body sensor, wherein the body sensor is arranged on a safety belt of an operator and is used for acquiring the action data of the operator;
extracting the characteristics of the action data to obtain the action characteristics of the operator;
and inputting the action characteristics into a pre-trained support vector machine for processing to obtain a recognition result of whether the operator has climbing actions.
2. The method for identifying climbing actions in electric power tower climbing operation according to claim 1, wherein the motion sensor comprises an acceleration sensor and a gyroscope, the motion data comprises acceleration data collected by the acceleration sensor and gesture data collected by the gyroscope, the motion data is subjected to feature extraction, and the motion features of the operator are obtained, and the method comprises the following steps:
the acceleration data and the gesture data are aligned in time, so that action data are obtained;
selecting action data of a plurality of acquisition points which are continuous in time as a target frame, and recording sequence numbers of the target frame;
performing Fourier transformation on the motion data of the target frame, and extracting frequency domain features and time domain statistical features of the motion data of the target frame;
and taking the sequence number of the target frame, the frequency domain feature and the time domain statistical feature as action features of the operator in the target frame.
3. The method for identifying climbing actions of electric power tower climbing operation according to claim 1 or 2, wherein the step of inputting the action features into a support vector machine trained in advance for processing to obtain an identification result of whether the climbing action exists for the operator comprises the steps of:
mapping the action features from low dimension to high dimension by using a kernel function to obtain high dimension features;
and inputting the high-dimensional features into a pre-trained discriminant function for calculation to obtain a recognition result of whether the operator has climbing actions.
4. The method for identifying climbing actions for electric power tower climbing operations according to claim 3, wherein the kernel function is a radial basis kernel function, and the radial basis kernel function is:
wherein K (x ', x) is a high-dimensional feature, x is an action feature, x' is the center of the radial basis function, and σ is the radial basis function width parameter.
5. The method for identifying climbing actions in electric power tower climbing operation according to claim 4, wherein the discriminant function is:
wherein, (x) i ,y i ) To support vector alpha i And b is a parameter of the support vector machine obtained through training.
6. The power tower climbing operation climbing action identification method according to claim 1, further comprising:
acquiring air pressure data acquired by an air pressure sensor, wherein the air pressure sensor is arranged on a safety belt of an operator;
determining a change value of the air pressure of the current sampling point relative to the air pressure of the previous sampling point based on the air pressure data;
and judging whether the worker has climbing action or not based on the change value of the air pressure and the identification result obtained by the support vector machine.
7. The electric power tower climbing operation climbing action recognition method according to claim 1, further comprising, before acquiring the action data acquired by the somatosensory sensor:
acquiring a plurality of groups of motion data samples acquired by a motion sensor and motion labels corresponding to the motion data samples;
and training a support vector machine by adopting a plurality of groups of action data samples and corresponding action labels, and determining parameters of the support vector machine.
8. An electric power climbing operation climbing action recognition device, characterized by comprising:
the data acquisition module is used for acquiring action data acquired by a body sensing sensor, wherein the body sensing sensor is arranged on a safety belt of an operator and used for acquiring the action data of the operator;
the feature extraction module is used for extracting the features of the action data to obtain the action features of the operators;
and the judging module is used for inputting the action characteristics into a pre-trained support vector machine for processing to obtain the identification result of whether the climbing action exists for the operator.
9. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the power tower climbing operation climbing action identification method according to any one of claims 1-7.
10. A computer readable storage medium, wherein computer executable instructions are stored in the computer readable storage medium, which when executed by a processor is configured to implement the method for identifying climbing actions of an electric power tower climbing operation according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310253608.4A CN116363751A (en) | 2023-03-15 | 2023-03-15 | Climbing action recognition method, device and equipment for electric power tower climbing operation and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310253608.4A CN116363751A (en) | 2023-03-15 | 2023-03-15 | Climbing action recognition method, device and equipment for electric power tower climbing operation and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116363751A true CN116363751A (en) | 2023-06-30 |
Family
ID=86940991
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310253608.4A Pending CN116363751A (en) | 2023-03-15 | 2023-03-15 | Climbing action recognition method, device and equipment for electric power tower climbing operation and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116363751A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117523667A (en) * | 2023-11-15 | 2024-02-06 | 岳阳长炼机电工程技术有限公司 | Identification method for up-down straight ladder of handhold object |
-
2023
- 2023-03-15 CN CN202310253608.4A patent/CN116363751A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117523667A (en) * | 2023-11-15 | 2024-02-06 | 岳阳长炼机电工程技术有限公司 | Identification method for up-down straight ladder of handhold object |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107808139B (en) | Real-time monitoring threat analysis method and system based on deep learning | |
| CN112784778A (en) | Method, apparatus, device and medium for generating model and identifying age and gender | |
| US20230186634A1 (en) | Vision-based monitoring of site safety compliance based on worker re-identification and personal protective equipment classification | |
| CN113947188A (en) | Training method of target detection network and vehicle detection method | |
| CN112989995A (en) | Text detection method and device and electronic equipment | |
| CN115565101A (en) | Production safety abnormity identification method and device, electronic equipment and storage medium | |
| CN107918688B (en) | Scene model dynamic estimation method, data analysis method and device and electronic equipment | |
| CN112800975A (en) | Behavior identification method in security check channel based on image processing | |
| CN112989987A (en) | Method, apparatus, device and storage medium for identifying crowd behavior | |
| CN113627361B (en) | Training method and device for face recognition model and computer program product | |
| CN111783613B (en) | Anomaly detection method, model training method, device, equipment and storage medium | |
| CN111563541B (en) | Training method and device of image detection model | |
| CN115641607A (en) | Method, device, equipment and storage medium for detecting wearing behavior of power construction site operator | |
| CN116363751A (en) | Climbing action recognition method, device and equipment for electric power tower climbing operation and storage medium | |
| CN115641360A (en) | Battery detection method and device based on artificial intelligence and electronic equipment | |
| CN113989568A (en) | Target detection method, training method, device, electronic device and storage medium | |
| CN114663972A (en) | Target marking method and device based on motion difference | |
| CN113989720A (en) | Target detection method, training method, device, electronic equipment and storage medium | |
| CN113935482A (en) | Training method and device for pedestrian re-recognition network | |
| CN117333929B (en) | Method and system for identifying abnormal personnel under road construction based on deep learning | |
| CN116189028B (en) | Image recognition method, device, electronic equipment and storage medium | |
| CN112990045A (en) | Method and apparatus for generating image change detection model and image change detection | |
| CN114155589B (en) | Image processing method, device, equipment and storage medium | |
| CN116935127A (en) | Transformer temperature anomaly identification method and device, electronic equipment and medium | |
| CN118052755A (en) | High-altitude parabolic simulation test method and device, electronic equipment and storage 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 |