WO2023020084A1 - 海上无人机巡检飞行路径生成方法、装置及无人机 - Google Patents
海上无人机巡检飞行路径生成方法、装置及无人机 Download PDFInfo
- Publication number
- WO2023020084A1 WO2023020084A1 PCT/CN2022/098344 CN2022098344W WO2023020084A1 WO 2023020084 A1 WO2023020084 A1 WO 2023020084A1 CN 2022098344 W CN2022098344 W CN 2022098344W WO 2023020084 A1 WO2023020084 A1 WO 2023020084A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- uav
- flight path
- inspection
- model
- offshore wind
- Prior art date
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000012937 correction Methods 0.000 claims abstract description 25
- 230000015654 memory Effects 0.000 claims description 22
- 238000004422 calculation algorithm Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000007613 environmental effect Effects 0.000 claims description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 11
- 238000009877 rendering Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 229910000831 Steel Inorganic materials 0.000 claims description 3
- 239000010959 steel Substances 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- 238000005457 optimization Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 239000002245 particle Substances 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241001515997 Eristalis tenax Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000037396 body weight Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
Definitions
- the disclosure belongs to the field of automatic detection, and relates to a method and device for generating a flight path for inspection of a marine unmanned aerial vehicle, and the unmanned aerial vehicle.
- the purpose of the present disclosure is to overcome the above-mentioned shortcomings of the prior art, and provide a method and device for generating a flight path of a marine UAV inspection flight path, and a UAV, so as to realize the self-adaptive inspection of the UAV and improve the efficiency of the UAV inspection.
- Efficiency reducing the inspection risk, which can effectively improve the detection efficiency of fan blades.
- a method for generating a flight path for inspection of a marine unmanned aerial vehicle comprising:
- the initial flight path is corrected to generate the final inspection flight path of the UAV.
- constructing a three-dimensional model of an offshore wind farm includes:
- the three-dimensional model of the offshore wind farm is generated based on the three-dimensional model of the environment, the three-dimensional model of the wind turbine, the location information of the offshore wind farm, the depth information of the water area, and the physical parameters of the wind turbine.
- building a 3D model of a wind turbine includes:
- the point cloud data is rough-lined and feature points extracted to generate the initial 3D model of each fan;
- the photographic digital orthophotograph without quality problems is used as the 3D model of the wind turbine.
- calling the 3D model of the offshore wind farm to generate the initial flight path of the UAV includes:
- x+ ⁇ (cos ⁇ ,sin ⁇ ) T belongs to the obstacle range
- d is the distance
- ⁇ is the distance coefficient.
- P is divided into multiple continuous intervals by obstacles in the sensor field of view.
- TangentBUG algorithm uses The endpoints of these intervals avoid obstacles in the workspace.
- generating the final inspection flight path of the drone includes:
- the final inspection flight path is generated with the optimal path as the goal.
- correcting the track points in the initial flight path includes:
- the flight speed calculation relation is:
- c 1 , m 1 , n 1 are the influence factors of the field environment on the work of the UAV, c 1 is the wind force at sea, m 1 is the wave height, and n 1 is the influence of the fan blades factor, P best is the optimal position under the influence of the field environment, is the position of the UAV in the k-1th iteration, r 1 , s 1 is the influence weight of the UAV itself, r 1 is the remaining task amount, s 1 is the battery life time, G best is the influence weight of the UAV itself The optimal position under the factor;
- the position update relation is:
- the flight speed and position information of the track points in the initial flight path are corrected according to the current flight speed and the current position.
- a maritime unmanned aerial vehicle inspection flight path generating device comprising:
- the model construction module is used to construct a three-dimensional model of the offshore wind farm based on the information of the offshore wind farm and the wind turbine in advance;
- the path generation module is used to call the 3D model of the offshore wind farm to generate the initial flight path of the UAV based on the total amount of current inspection tasks;
- the path correction module is used to correct the initial flight path according to the current environmental parameters and the UAV's own parameters, so as to generate the final inspection flight path of the UAV.
- a computer device including a memory, a processor, and a computer program stored in the memory and operable on the processor.
- the processor executes the computer program, it realizes the above-mentioned maritime wireless The steps of the method for generating the human-machine inspection flight path.
- a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for generating the flight path of the maritime drone inspection described in any one of the above are realized.
- An unmanned aerial vehicle including an unmanned aerial vehicle body, an image acquisition device and a processor;
- the image acquisition device and processor are mounted on the body of the drone; the image acquisition device is connected to the processor;
- the image acquisition device collects the image data of the current environment after receiving the image acquisition instruction
- the processor When the processor is used to execute the computer program stored in the memory, it realizes the steps of the method for generating the flight path of the marine UAV inspection as described in any one of the above.
- This disclosure generates an initial path image based on a three-dimensional model of an offshore wind farm, and optimizes the flight route in real time according to the actual on-site environment, such as environmental factors such as strong winds, waves, and fan blade rotation, as well as its own factors such as the battery power of the drone itself.
- the actual on-site environment such as environmental factors such as strong winds, waves, and fan blade rotation, as well as its own factors such as the battery power of the drone itself.
- FIG. 1 is a schematic flow diagram of a method for generating a flight path of an unmanned aerial vehicle according to an embodiment of the present disclosure
- FIG. 2 is a block diagram of a UAV flight path generating device according to an embodiment of the present disclosure
- FIG. 3 is a block diagram of an electronic device according to an embodiment of the disclosure.
- Fig. 4 is a schematic structural diagram of an unmanned aerial vehicle according to an embodiment of the present disclosure.
- FIG. 1 is a schematic flow diagram of a method for generating a flight path of a drone provided by an embodiment of the present disclosure.
- Embodiments of the present disclosure may include the following:
- S101 Constructing a three-dimensional model of the offshore wind farm in advance based on the information of the offshore wind farm and the information of the wind turbines.
- the offshore wind farm information includes but is not limited to the environmental information of the offshore wind farm, location parameter information, water area information and image data of the offshore wind farm collected by drones
- the wind turbine information includes but is not limited to the physical parameters of the wind turbine , working parameters, location information, and image data of wind turbines collected by drones.
- the location, height, blade length parameters, images and other data of offshore wind farm fans can be obtained first; then based on the offshore wind farm fan parameters, images and other data, a 3D model of an offshore wind farm in a typical scenario can be constructed.
- the longest east-west direction of the offshore wind farm is about 6.6km
- the widest north-south direction is about 3.5km. 70-150m.
- S102 Based on the total amount of current inspection tasks, call the 3D model of the offshore wind farm to generate the initial flight path of the UAV.
- an initial path image can be generated based on the total amount of the current inspection task by using an algorithm such as TangentBUG.
- the TangentBUG algorithm can be used to avoid obstacles through the GIS (Geographic Information System, geographic information system) platform, and the initial flight path can be generated with the goal of satisfying the preset path parameter conditions.
- the preset path parameter condition may be the shortest path.
- those skilled in the art can determine the preset path parameter condition according to actual needs, and this application does not make any limitation thereto.
- S103 Perform line correction on the initial flight path according to the current environmental parameters and the UAV's own parameters, so as to generate a final inspection flight path of the UAV.
- the initial path image can be optimized in real time based on factors such as the actual on-site environment and the UAV itself, so as to realize the obstacle avoidance of the UAV in the complex environment of the sea and the operation of the fan blades.
- the actual on-site environment such as strong winds, waves, fan blade rotation and other environmental factors, and the drone's own parameters such as battery power, body weight and other factors.
- Any path optimization algorithm such as particle swarm optimization algorithm can be used for line correction.
- the initial path image is generated based on the 3D model of the offshore wind farm, and according to the actual site environment, such as environmental factors such as strong winds, waves, and fan blade rotation, as well as the battery power of the drone itself, etc. Its own factors optimize the flight route in real time, realize the obstacle avoidance of the UAV in the complex environment at sea and the operation of the fan blades, realize the self-adaptive inspection of the UAV, improve the efficiency of the UAV inspection, and reduce the inspection time. check risk.
- step S101 there is no limitation on how to execute step S101.
- An optional implementation manner is given in this embodiment, which may include the following steps:
- the three-dimensional model of the offshore wind farm is generated based on the three-dimensional model of the environment, the three-dimensional model of the wind turbine, the location information of the offshore wind farm, the depth information of the water area, and the physical parameters of the wind turbine.
- image recognition technology and automatic feature extraction technology can be used to generate 3D model files, and then a 3D model of the environment including real scenes can be produced based on the image data and wind farm data acquired by drone inspections.
- image recognition technology the three-dimensional information of ground objects can be extracted by methods such as contour extraction and patch fitting, and at the same time, the multi-view images can be imaged by image segmentation, edge extraction, texture clustering and other methods to obtain all-round texture information of ground objects.
- image segmentation, edge extraction, texture clustering and other methods to obtain all-round texture information of ground objects.
- the corresponding relationship between geometric information and texture information of ground objects is established, and at the same time, the overall light and color uniformity is combed to realize the orthographic processing of multi-view images.
- the construction process of the 3D model of the wind turbine may include: external operation scanning of different types of wind turbines on the sea surface, including the foundation, tower body, wind turbine, blade, etc., to generate point cloud data; through internal operation processing, rough model drawing of the point cloud data and feature point extraction to generate a rough 3D model of each fan as the initial 3D model; based on the initial 3D model, by drawing the steel structure and rendering the model, a refined 3D model of each type of fan is generated; through regional color correction, using Perform digital differential correction on refined 3D models to generate photographic digital orthophotographs; conduct quality inspection on photographic digital orthophotographs, and process quality issues such as image blur, dislocation, distortion, deformation, loopholes and other phenomena The problem is dealt with accordingly, and finally the photo digital orthophoto map without quality problems is used as the three-dimensional model of the wind turbine.
- the database is used to save information such as the type, location, size, and serial number of the fan, as well as the type, length, and brand of the key components of the fan.
- the database file supports both PC (Person Computer, personal computer) terminal and mobile terminal display and information update.
- step S103 there is no limitation on how to execute step S103.
- an optional optimization method of the inspection path is given, which may include the following steps:
- Pre-set the current environmental parameters and the weight factor of the drone's own parameters obtain the offshore wind value, wave height value, fan blade rotation information in normal working state, drone task load, and battery life; according to the offshore wind value, The weight factors of wave height value, fan blade rotation information, task load and battery life time are used to correct the track points in the initial flight path; based on the corrected track points, the final inspection flight is generated with the optimal path as the goal path.
- the camera sensor of the drone can be used to scan the scene in front of the drone.
- the internal processor of the UAV can use the TangentBUG algorithm to make advance avoidance actions on obstacles to obtain a shorter and smoother UAV flight path.
- x is the position of the UAV and ⁇ is the scanning angle of the sensor, satisfying the formula:
- x+ ⁇ (cos ⁇ ,sin ⁇ ) T belongs to the obstacle range
- d is the distance
- ⁇ is the distance coefficient.
- P is divided into multiple continuous intervals by obstacles within the sensor's field of view.
- the TangentBUG algorithm uses the endpoints of these intervals to avoid obstacles in the workspace.
- the particle swarm algorithm can be used for path optimization.
- the weight of the influence of the actual flight environment on the UAV is introduced, including: the size of the wind at sea, the height of the waves, and the rotation of the normal working fan blades.
- the flight speed calculation relational expression of the UAV can be preset, and then the flight speed calculation relational expression is called to calculate the current flight speed of the UAV.
- the flight speed calculation relational expression can be expressed as:
- i is the i-th speed correction
- w is the inertia weight
- c 1 , m 1 , n 1 are the factors affecting the work of the UAV on site environment
- c 1 is the wind force at sea
- m 1 is the wave height
- n 1 is the influence factor of the wind turbine blade.
- P best is the optimal position under the influence of the site environment, is the position of the UAV in the k-1th iteration (that is, the position of the UAV at the last moment).
- r 1 , s 1 is the influence weight of the drone itself
- r 1 is the remaining task amount
- s 1 is the battery life time
- G best is the optimal position under the influence factors of the drone itself.
- the current position of the UAV is calculated by using the pre-set position update relation of the UAV, and the position update formula of the UAV can be expressed as:
- This embodiment can use the TangentBUG algorithm and the particle swarm algorithm to quickly generate the initial inspection path of the UAV through the GIS platform, and correct the flight path in real time, and input the corrected track points into the three-dimensional model of the offshore wind farm; Offshore wind farm parameters, images and other data construct the track points in the 3D model of offshore wind farms in typical scenarios, and use the optimal path as the goal to generate the UAV path for offshore wind power inspections to ensure that UAVs can operate stably and smoothly. Execute the inspection task.
- the embodiment of the present disclosure also provides a corresponding device for the UAV flight path generation method, which further makes the method more practical.
- the device can be described separately from the perspective of functional modules and hardware.
- the following is an introduction to the UAV flight path generation device provided by the embodiments of the present disclosure.
- the UAV flight path generation device described below and the UAV flight path generation method described above can be referred to in correspondence.
- Fig. 2 is a structural diagram of a UAV flight path generation device provided by an embodiment of the present disclosure in a specific implementation manner, the device may include:
- the model construction module 201 is used to construct a three-dimensional model of the offshore wind farm based on the information of the offshore wind farm and the wind turbine in advance;
- the path generation module 202 is used to call the 3D model of the offshore wind farm to generate the initial flight path of the UAV based on the total amount of current inspection tasks;
- the path correction module 203 is configured to correct the initial flight path according to the current environment parameters and the UAV's own parameters, so as to generate the final inspection flight path of the UAV.
- the above-mentioned model building module 201 can be used to: obtain the location information of the offshore wind farm, the depth information of the water area, the physical parameters of the wind turbine, the image data of the offshore wind farm, and the image data of the wind turbine; Construct a 3D model of the environment from image data of the wind farm; construct a 3D model of the wind turbine based on the image data of the wind turbine; generate a 3D model of the offshore wind farm based on the 3D environment model, the 3D model of the wind turbine, the location information of the offshore wind farm, the depth information of the water area, and the physical parameters of the wind turbine.
- the above-mentioned model building module 201 can also be further used to: perform external operation scanning on different types of wind turbines on the sea surface to generate point cloud data; through internal operation processing, point cloud data Perform rough model drawing and feature point extraction to generate the initial 3D model of each fan; based on the initial 3D model, by drawing the steel structure and rendering the model, generate a refined 3D model of each type of fan; through regional color correction, use Refining the three-dimensional model for digital differential correction to generate a digital orthophoto image; checking the quality of the digital orthophoto image and dealing with the corresponding quality problems; digital orthophoto images that do not have quality problems As a 3D model of a wind turbine.
- the above-mentioned path correction module 203 can be further used to: preset the current environmental parameters and the weight factors of the drone's own parameters; The rotation information of fan blades in normal working state, the task load of UAV, and the battery life time; according to the weight factors of offshore wind value, wave height value, fan blade rotation information, task load and battery life time, the initial flight path The track points are corrected; based on the corrected track points, the final inspection flight path is generated with the optimal path as the goal.
- the above-mentioned path correction module 203 can also be further used to: call the flight speed calculation relational expression to calculate the current flight speed of the drone, and the flight speed calculation relational expression is:
- the position update relational expression is:
- n 1 is the influence factor of the field environment on the UAV work
- c 1 is the wind force at sea
- m 1 is the wave height
- n 1 is the wind blade influence factor.
- P best is the optimal position under the influence of the site environment, is the position of the drone at the last moment.
- r 1 , s 1 is the influence weight of the drone itself, r 1 is the remaining task amount, s 1 is the battery life time, and G best is the optimal position under the influence factors of the drone itself.
- the above-mentioned path generation module 202 can be further used to: use the TangentBUG algorithm to avoid obstacles through the GIS platform, and generate the initial flight path with the goal of satisfying the preset path parameter conditions ;
- P is divided into multiple continuous intervals by obstacles in the sensor field of view, and the endpoints of these intervals are used to avoid obstacles in the workspace through the TangentBUG algorithm.
- each functional module of the UAV flight path generation device in the embodiment of the present disclosure can be implemented according to the method in the above method embodiment, and the specific implementation process can refer to the relevant description of the above method embodiment, and will not be repeated here.
- FIG. 3 is a schematic structural diagram of an electronic device provided in an embodiment of the present application in an implementation manner.
- the electronic device includes a memory 30 for storing a computer program; a processor 31 for implementing the steps of the method for generating a flight path of a drone as mentioned in any of the above-mentioned embodiments when executing the computer program.
- the processor 31 may include one or more processing cores, such as a 4-core processor or an 8-core processor, and the processor 31 may also be a controller, a microcontroller, a microprocessor, or other data processing chips.
- Processor 31 can adopt at least one hardware form in DSP (Digital Signal Processing, digital signal processing), FPGA (Field-Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array, programmable logic array) accomplish.
- Processor 31 may also include a main processor and a coprocessor, the main processor is a processor for processing data in a wake-up state, also called CPU (Central Processing Unit, central processing unit); the coprocessor is Low-power processor for processing data in standby state.
- the processor 31 may be integrated with a GPU (Graphics Processing Unit, image processor), and the GPU is used for rendering and drawing the content that needs to be displayed on the display screen.
- the processor 31 may also include an AI (Artificial Intelligence, artificial intelligence) processor, where the AI processor is used to process computing operations related to machine learning.
- AI Artificial Intelligence, artificial intelligence
- Memory 30 may include one or more computer-readable storage media, which may be non-transitory.
- the memory 30 may also include high-speed random access memory and non-volatile memory, such as one or more magnetic disk storage devices and flash memory storage devices.
- the memory 30 may be an internal storage unit of an electronic device, such as a hard disk of a server.
- the memory 30 can also be an external storage device of the electronic device, such as a plug-in hard disk equipped on a server, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash memory Card (Flash Card), etc.
- the memory 30 may also include both an internal storage unit of the electronic device and an external storage device.
- the memory 30 can not only be used to store application software and various data installed in the electronic device, such as: program codes for executing the vulnerability handling method, etc., but also can be used to temporarily store data that has been output or will be output.
- the memory 30 is at least used to store the following computer program 301, wherein, after the computer program is loaded and executed by the processor 31, it can realize the relevant steps of the UAV flight path generation method disclosed in any of the foregoing embodiments.
- the resources stored in the memory 30 may also include an operating system 302 and data 303, etc., and the storage method may be temporary storage or permanent storage.
- the operating system 302 may include Windows, Unix, Linux and so on.
- the data 303 may include, but not limited to, data corresponding to the result of generating the flight path of the drone, and the like.
- the above-mentioned electronic device may further include a display screen 32 , an input/output interface 33 , a communication interface 34 or network interface, a power supply 35 and a communication bus 36 .
- the display screen 32 and the input/output interface 33 such as a keyboard are user interfaces, and optional user interfaces may also include standard wired interfaces, wireless interfaces, and the like.
- the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, and the like.
- a display may also be properly called a display screen or a display unit, and is used for displaying information processed in an electronic device and for displaying a visualized user interface.
- the communication interface 34 may optionally include a wired interface and/or a wireless interface, such as a WI-FI interface, a Bluetooth interface, etc., which are generally used to establish a communication connection between an electronic device and other electronic devices.
- the communication bus 36 may be a peripheral component interconnect standard (PCI for short) bus or an extended industry standard architecture (EISA for short) bus or the like.
- PCI peripheral component interconnect standard
- EISA extended industry standard architecture
- FIG. 3 does not constitute a limitation to the electronic device, and may include more or less components than shown in the figure, for example, may also include a sensor 37 for implementing various functions.
- the UAV flight path generation method in the above embodiments is implemented in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.
- the technical solution of the present application is essentially or part of the contribution to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , executing all or part of the steps of the methods in the various embodiments of the present application.
- the aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), electrically erasable programmable ROM, registers, hard disk, multimedia Various media that can store program codes, such as cards, card-type memories (such as SD or DX memories), magnetic memories, removable disks, CD-ROMs, magnetic disks, or optical disks.
- program codes such as cards, card-type memories (such as SD or DX memories), magnetic memories, removable disks, CD-ROMs, magnetic disks, or optical disks.
- an embodiment of the present disclosure also provides a readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the method for generating a flight path of a drone described in any one of the above embodiments are described.
- each functional module of the readable storage medium in the embodiments of the present disclosure can be specifically implemented according to the methods in the above method embodiments, and the specific implementation process can refer to the relevant descriptions of the above method embodiments, which will not be repeated here.
- An embodiment of the present disclosure also provides a drone, please refer to FIG. 4 , which may include a drone body 41 , a processor 42 and an image acquisition device 43 . Both the image acquisition device 43 and the processor 42 are mounted on the drone body, and the image acquisition device 43 is connected to the processor 42 .
- the image acquisition device 43 acquires the image data of the current environment after receiving the image acquisition instruction.
- the image collection device 43 can directly store the collected image data locally, or in the cloud, or directly send it to the processor 42, which does not affect the implementation of this application.
- the processor 42 can be used to implement the steps of the method for generating the flight path of the drone as described in any one of the above embodiments when executing the computer program stored in the memory.
- each embodiment in this specification is described in a progressive manner, each embodiment focuses on the difference from other embodiments, and the same or similar parts of each embodiment can be referred to each other.
- the hardware including devices and electronic equipment disclosed in the embodiments since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and for related details, please refer to the description of the methods.
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
本公开公开了一种海上无人机巡检飞行路径生成方法、装置及无人机,预先基于海上风电场信息和风机信息构建海上风电场三维模型;基于当前巡检任务总量,调用海上风电场三维模型生成无人机的初始飞行路径;根据当前环境参数和无人机自身参数,对初始飞行路径进行线路修正,以生成所述无人机的最终巡检飞行路径。实现无人机自适应巡检,提高了无人机巡检的效率,降低了巡检风险,从而可有效提高风机叶片的检测效率。
Description
相关申请的交叉引用
本公开基于申请号为202110963456.8、申请日为2021年8月20日的中国专利申请提出,并要求该中国专利申请的优先权,该中国专利申请的全部内容在此引入本申请作为参考。
本公开属于自动化检测领域,涉及一种海上无人机巡检飞行路径生成方法、装置及无人机。
近年来,海上风电的发展尤为显著,海上风电机组进一步向大型化趋势发展,风机高度超过100m,叶片长度达到90m。
海上风电机组在运行过程中,叶片整体裸露在外,不可避免地会经常受到盐腐蚀、台风等恶劣环境的影响,导致设备叶片损伤。传统技术通常采用人工巡检方式对风机叶片进行检测,例如可包括望远镜、高空吊篮等方式。为了解决传统人工巡检方式的弊端,相关技术在无人机上搭建图像采集设备,通过人工控制无人机在其飞行过程中采集风机叶片图像来实现对风机叶片的检测。
但是,由于无人机载荷与续航里程的限制条件,以及海面上大风与海浪的影响,这种人工操作控制无人机的飞行方式会导致无人机飞行效率低下,风机叶片的检测效率也会相对的降低,无法满足风机叶片的高检测率的现实需求。
发明内容
本公开的目的在于克服上述现有技术的缺点,提供一种海上无人机巡检飞行路径生成方法、装置及无人机,实现无人机自适应巡检,提高了无人机巡检的效率,降低了巡检风险,从而可有效提高风机叶片的检测效率。
为达到上述目的,本公开采用以下技术方案予以实现:
一种海上无人机巡检飞行路径生成方法,包括:
预先基于海上风电场信息和风机信息构建海上风电场三维模型;
基于当前巡检任务总量,调用海上风电场三维模型生成无人机的初始飞行路径;
根据当前环境参数和无人机自身参数,对初始飞行路径进行线路修正,以生成无人机的最终巡检飞行路径。
在本公开的实施例中,构建海上风电场三维模型包括:
获取海上风电场的位置信息、水域深度信息、风机物理参数、海上风电场图像数据和风机图像数据;
根据海上风电场图像数据构建环境三维模型;
根据风机图像数据构建风机三维模型;
基于环境三维模型、风机三维模型、海上风电场的位置信息、水域深度信息和风机物理参数生成海上风电场三维模型。
进一步,构建风机三维模型包括:
对海面上不同类型的风机进行外作业扫描,生成点云数据;
通过内作业处理,对点云数据进行粗模勾线和特征点提取,生成各风机的初始三维模型;
基于初始三维模型,通过绘制钢化结构与进行模型渲染,生成各类型风机的精细化三维模型;
通过区域色彩校正,利用精细化三维模型进行数字微分纠正,生成像片数字正射影像图;
对像片数字正射影像图进行质量检查,并处理相应的质量问题;
将不存在质量问题的像片数字正射影像图作为风机三维模型。
在本公开的实施例中,基于当前巡检任务总量,调用海上风电场三维模型生成无人机的初始飞行路径包括:
通过GIS平台利用TangentBUG算法对障碍物进行规避,以满足预设路径参数条件为目标,生成初始飞行路径,
其中在无人机传感器的感测区域P(x,θ)中,x是无人机位置和θ是传感器扫描角度,满足公式
其中x+λ(cosθ,sinθ)
T属于障碍物范围,d为距离,λ为距离系数,对于某一个固定的位置x,P被传感器视野内的障碍物分割成多个连续区间,TangentBUG算法利用这些区间的端点避开工作空间中的障碍物。
在本公开的实施例中,生成无人机的最终巡检飞行路径包括:
预先设置当前环境参数和无人机自身参数的权重因子;
获取海上风力值、海浪高度值、处于正常工作状态的风机叶片旋转信息、无人机的任务 量和电池续航时间;
根据海上风力值、海浪高度值、风机叶片旋转信息、任务量和电池续航时间的权重因子,对初始飞行路径中的航迹点进行修正;
基于修正后的航迹点,以最优路径为目标生成最终巡检飞行路径。
进一步,对初始飞行路径中的航迹点进行修正包括:
调用飞行速度计算关系式计算无人机的当前飞行速度,飞行速度计算关系式为:
其中
为第k次迭代的飞行速度,i为第i次速度修正,w为惯性权重,
为第k-1次迭代的飞行速度,c
1,m
1,n
1为现场环境对无人机工作的影响因子,c
1为海上风力大小,m
1为海浪高度,n
1为风机叶片影响因子,P
best在现场环境影响下最优位置,
为第k-1次迭代的无人机位置,r
1,s
1为无人机自身的影响权重,r
1为剩余任务量,s
1为电池续航时间,G
best为在无人机自身影响因素下的最优位置;
调用位置更新关系式计算无人机的当前位置,位置更新关系式为:
根据当前飞行速度和当前位置对初始飞行路径中的航迹点的飞行速度和位置信息进行修正。
一种海上无人机巡检飞行路径生成装置,包括:
模型构建模块,用于预先基于海上风电场信息和风机信息构建海上风电场三维模型;
路径生成模块,用于基于当前巡检任务总量,调用海上风电场三维模型生成无人机的初始飞行路径;
路径修正模块,用于根据当前环境参数和无人机自身参数,对初始飞行路径进行线路修正,以生成无人机的最终巡检飞行路径。
一种计算机设备,包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序,所述处理器执行所述计算机程序时实现如上述任意一项所述海上无人机巡检飞行路径生成方法的步骤。
一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行时实现如上述任意一项所述海上无人机巡检飞行路径生成方法的步骤。
一种无人机,包括无人机机身、图像采集设备和处理器;
图像采集设备和处理器搭载在无人机机身;图像采集设备与处理器相连;
图像采集设备在接收到图像采集指令后,采集当前环境的图像数据;
处理器用于执行存储器中存储的计算机程序时实现如上述任意一项所述海上无人机巡检飞行路径生成方法的步骤。
与现有技术相比,本公开具有以下有益效果:
本公开基于海上风电场的三维模型生成初始的路径图像,并根据实际现场环境,如大风、海浪、风机叶片旋转等环境因素,以及无人机本身电池电量等自身因素,对飞行线路进行实时优化,实现了无人机在海上复杂环境以及风机叶片运转下的避障,实现无人机自适应巡检,提高了无人机巡检的效率,降低了巡检风险。
图1为根据本公开实施例的无人机飞行路径生成方法的流程示意图;
图2为根据本公开实施例的无人机飞行路径生成装置的框图;
图3为根据本公开实施例的电子设备的框图;
图4为根据本公开实施例的无人机的结构示意图。
下面结合附图对本公开做进一步详细描述:
为了使本技术领域的人员更好地理解本公开方案,下面结合附图和具体实施方式对本公开作进一步的详细说明。显然,所描述的实施例仅仅是本公开一部分实施例,而不是全部的实施例。基于本公开中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本公开保护的范围。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”“第四”等是用于区别不同的对象,而不是用于描述特定的顺序。此外术语“包括”和“具有”以及他们任何变形,意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元,而是可包括没有列出的步骤或单元。
在介绍了本公开实施例的技术方案后,下面详细的说明本申请的各种非限制性实施方式。
首先参见图1,图1为本公开实施例提供的一种无人机飞行路径生成方法的流程示意图,本公开实施例可包括以下内容:
S101:预先基于海上风电场信息和风机信息构建海上风电场三维模型。
其中,海上风电场信息包括但并不限制于海上风电场的环境信息、位置参数信息、水域 信息及无人机采集的海上风电场的图像数据,风机信息包括但并不限制于风机的物理参数、工作参数、位置信息及无人机采集的风机的图像数据。可先获取海上风电场风机的位置、高度、叶片长度工参、影像等数据;然后基于海上风电场风机工参、影像等数据构建典型场景下的海上风电场三维模型。举例来说,海上风电场东西向最长约6.6km,南北向最宽约3.5km,涉海面积12.7km
2,水深范围16m~18m,风机分布其中,风机70台,风机模型高度值范围为70-150m。
S102:基于当前巡检任务总量,调用海上风电场三维模型生成无人机的初始飞行路径。
在本实施例中,可基于海上风电场三维模型,利用诸如TangentBUG算法在实现当前巡检任务总量的基础上生成初始的路径图像。进一步来说,可通过GIS(Geographic Information System,地理信息系统)平台利用TangentBUG算法对障碍物进行规避,在满足预设路径参数条件为目标,生成初始飞行路径。预设路径参数条件如可为最短路径,当然,所属领域技术人员可根据实际需求确定预设路径参数条件,本申请对此不作任何限定。
S103:根据当前环境参数和无人机自身参数,对初始飞行路径进行线路修正,以生成无人机的最终巡检飞行路径。
在上个步骤生成初始飞行路径之后,可对初始路径图像进行实际现场环境情况、无人机本身情况等因素进行实时优化,实现了无人机在海上复杂环境以及风机叶片运转下的避障,生成海上风电场无人机巡检的自适应飞行线路。实际现场环境如大风、海浪、风机叶片旋转等环境因素,无人机本身参数如电池电量、机身重量等自身因素。在线路修正时,可利用任何一种路径寻优算法如粒子群算法。
在本公开实施例提供的技术方案中,基于海上风电场的三维模型生成初始的路径图像,并根据实际现场环境,如大风、海浪、风机叶片旋转等环境因素,以及无人机本身电池电量等自身因素,对飞行线路进行实时优化,实现了无人机在海上复杂环境以及风机叶片运转下的避障,实现无人机自适应巡检,提高了无人机巡检的效率,降低了巡检风险。
需要说明的是,本申请中各步骤之间没有严格的先后执行顺序,只要符合逻辑上的顺序,则这些步骤可以同时执行,也可按照某种预设顺序执行。图1只是一种示意方式,并不代表只能是这样的执行顺序。
在上述实施例中,对于如何执行步骤S101并不做限定,本实施例中给出一种可选的实施方式,可包括如下步骤:
获取海上风电场的位置信息、水域深度信息、风机物理参数、海上风电场图像数据、风机图像数据;
根据海上风电场图像数据构建环境三维模型;
根据风机图像数据构建风机三维模型;
基于环境三维模型、风机三维模型、海上风电场的位置信息、水域深度信息和风机物理参数生成海上风电场三维模型。
其中,可采用影像识别技术、特征物自动提取技术生成三维模型文件,然后根据无人机巡检所获取的影像数据和风电场数据制作包含实景的环境三维模型。可通过影像识别的技术,采用轮廓提取、面片拟合等方法提取地物三维信息,同时对多视角影像进行影像分割、边缘提取、纹理聚类等方法获取地物全方位纹理信息。最后建立地物几何信息与纹理信息的对应关系,同时进行整体匀光匀色梳理,实现多视影像的正射处理。风机三维模型的构建过程可包括:对海面上不同类型的风机包括基础、塔身、风机、叶片等进行外作业扫描,生成点云数据;通过内作业处理,对点云数据进行粗模勾线和特征点提取,生成每个风机的粗略三维模型作为初始三维模型;基于所述初始三维模型,通过绘制钢化结构与进行模型渲染,生成各类型风机的精细化三维模型;通过区域色彩校正,利用精细化三维模型进行数字微分纠正,生成像片数字正射影像图;对像片数字正射影像图进行质量检查,并诸如对影像模糊、错位、扭曲、变形、漏洞问题及现象进行处理等质量问题进行相应的处理,最后将不存在质量问题的像片数字正射影像图作为风机三维模型。采用数据库保存风机的类型、位置、大小、编号等信息,保存风机关键部件的类型、长度、品牌等信息,数据库文件同时支持PC(Person Computer,个人计算机)端和移动端的展示和信息更新。
在上述实施例中,对于如何执行步骤S103并不做限定,本实施例中给出巡检路径的一种可选的优化方式,可包括如下步骤:
预先设置当前环境参数和无人机自身参数的权重因子;获取海上风力值、海浪高度值、处于正常工作状态的风机叶片旋转信息、无人机的任务量、电池续航时间;根据海上风力值、海浪高度值、风机叶片旋转信息、任务量和电池续航时间的权重因子,对初始飞行路径中的航迹点进行修正;基于修正后的航迹点,以最优路径为目标生成最终巡检飞行路径。
在本实施例中,可使用无人机自带的摄像头传感器扫描无人机前方场景。无人机内部处理器可使用TangentBUG算法对障碍物做出提前规避动作,获得更短更平滑的无人机飞行路径。在无人机传感器的感测区域P(x,θ)中,x是无人机位置和θ是传感器扫描角度,满足公式:
其中x+λ(cosθ,sinθ)
T属于障碍物范围,d为距离,λ为距离系数。对于某一个固定的位 置x,P被传感器视野内的障碍物分割成多个连续区间。TangentBUG算法利用者些区间的端点避开工作空间中的障碍物。
在无人机使用TangentBUG算法避障的同时,可使用粒子群算法进行路径优化。在其中引入实际飞行环境对无人机的影响权重,包括:海上风力大小、海浪高度、正常工作的风机叶片旋转等。在粒子群算法中,可预先设置无人机的飞行速度计算关系式,然后调用飞行速度计算关系式计算无人机的当前飞行速度,飞行速度计算关系式可表示为:
式中
为第k次迭代的飞行速度(可作为当前时刻飞行速度),i为第i次速度修正,w为惯性权重,c
1,m
1,n
1为现场环境对无人机工作的影响因子,c
1为海上风力大小,m
1为海浪高度,n
1为风机叶片影响因子。P
best在现场环境影响下最优位置,
为第k-1次迭代的无人机位置(即上一时刻无人机位置)。r
1,s
1为无人机自身的影响权重,r
1为剩余任务量,s
1为电池续航时间,G
best为在无人机自身影响因素下的最优位置。
根据当前飞行速度对初始飞行路径中的航迹点的飞行速度进行修正。
利用预先设置的无人机的位置更新关系式计算无人机的当前位置,无人机的位置更新公式可表示为:
根据无人机的当前位置对初始飞行路径中的航迹点的位置信息进行修正,确保无人机的剩余电量可使无人机飞回充电处,最后将修正后的航迹点输入到海上风电场三维模型中,从而得到最终的无人机巡检路径。
本实施例可通过GIS平台利用TangentBUG算法和粒子群算法快速生成无人机的初始巡检路径,并对飞行路径进行实时修正,将修正后的航迹点输入到海上风电场三维模型中;基于海上风电场风机工参、影像等数据构建典型场景下的海上风电场三维模型中航迹点,以最优路径为目标生成海上风电巡检的无人机路径,保证无人机可稳定、顺利地执行完巡检任务。
本公开实施例还针对无人机飞行路径生成方法提供了相应的装置,进一步使得方法更具有实用性。其中,装置可从功能模块的角度和硬件的角度分别说明。下面对本公开实施例提供的无人机飞行路径生成装置进行介绍,下文描述的无人机飞行路径生成装置与上文描述的无人机飞行路径生成方法可相互对应参照。
基于功能模块的角度,参见图2,图2为本公开实施例提供的无人机飞行路径生成装置在一种具体实施方式下的结构图,该装置可包括:
模型构建模块201,用于预先基于海上风电场信息和风机信息构建海上风电场三维模型;
路径生成模块202,用于基于当前巡检任务总量,调用海上风电场三维模型生成无人机的初始飞行路径;
路径修正模块203,用于根据当前环境参数和无人机自身参数,对初始飞行路径进行线路修正,以生成无人机的最终巡检飞行路径。
可选的,在本实施例的一些实施方式中,上述模型构建模块201可用于:获取海上风电场的位置信息、水域深度信息、风机物理参数、海上风电场图像数据、风机图像数据;根据海上风电场图像数据构建环境三维模型;根据风机图像数据构建风机三维模型;基于环境三维模型、风机三维模型、海上风电场的位置信息、水域深度信息和风机物理参数生成海上风电场三维模型。
作为本实施例的一种可选的实施方式,上述模型构建模块201还可进一步用于:对海面上不同类型的风机进行外作业扫描,生成点云数据;通过内作业处理,对点云数据进行粗模勾线和特征点提取,生成各风机的初始三维模型;基于所述初始三维模型,通过绘制钢化结构与进行模型渲染,生成各类型风机的精细化三维模型;通过区域色彩校正,利用精细化三维模型进行数字微分纠正,生成像片数字正射影像图;对像片数字正射影像图进行质量检查,并处理相应的质量问题;将不存在质量问题的像片数字正射影像图作为风机三维模型。
可选的,在本实施例的另一些实施方式中,上述路径修正模块203可进一步用于:预先设置当前环境参数和无人机自身参数的权重因子;获取海上风力值、海浪高度值、处于正常工作状态的风机叶片旋转信息、无人机的任务量、电池续航时间;根据海上风力值、海浪高度值、风机叶片旋转信息、任务量和电池续航时间的权重因子,对初始飞行路径中的航迹点进行修正;基于修正后的航迹点,以最优路径为目标生成最终巡检飞行路径。
作为本实施例的一种可选的实施方式,上述路径修正模块203还可进一步用于:调用飞行速度计算关系式计算无人机的当前飞行速度,飞行速度计算关系式为:
调用位置更新关系式计算所述无人机的当前位置,所述位置更新关系式为:
根据所述当前飞行速度和当前位置对所述初始飞行路径中的航迹点的飞行速度和位置信息进行修正。
在飞行速度公式中:
为第k次迭代的飞行速度,i为第i次速度修正,w为惯性权重,c
1,m
1,n
1为现场环境对无人机工作的影响因子,c
1为海上风力大小,m
1为海浪高度,n
1为风机叶片影响因子。P
best在现场环境影响下最优位置,
为上一时刻无人机位置。r
1,s
1为无人机自身的影响权重,r
1为剩余任务量,s
1为电池续航时间,G
best为在无人机自身影响因素下的最优位置。
作为本实施例的另外一种可选的实施方式,上述路径生成模块202可进一步用于:通过GIS平台利用TangentBUG算法对障碍物进行规避,以满足预设路径参数条件为目标,生成初始飞行路径;
其中在无人机传感器的感测区域P(x,θ)中,x是无人机位置和θ是传感器扫描角度,满足公式
其中x+λ(cosθ,sinθ)
T属于障碍物范围,d为距离,λ为距离系数,
对于某一个固定的位置x,P被传感器视野内的障碍物分割成多个连续区间,通过TangentBUG算法利用这些区间的端点避开工作空间中的障碍物。
本公开实施例无人机飞行路径生成装置的各功能模块的功能可根据上述方法实施例中的方法具体实现,其具体实现过程可以参照上述方法实施例的相关描述,此处不再赘述。
由上可知,本公开实施例可有效提高风机叶片的检测效率。
上文中提到的无人机飞行路径生成装置是从功能模块的角度描述,进一步的,本申请还提供一种电子设备,是从硬件角度描述。图3为本申请实施例提供的电子设备在一种实施方式下的结构示意图。如图3所示,该电子设备包括存储器30,用于存储计算机程序;处理器31,用于执行计算机程序时实现如上述任一实施例提到的无人机飞行路径生成方法的步骤。
其中,处理器31可以包括一个或多个处理核心,比如4核心处理器、8核心处理器,处理器31还可为控制器、微控制器、微处理器或其他数据处理芯片等。处理器31可以采用DSP(Digital Signal Processing,数字信号处理)、FPGA(Field-Programmable Gate Array,现场可编程门阵列)、PLA(Programmable Logic Array,可编程逻辑阵列)中的至少一种硬件形式来实现。处理器31也可以包括主处理器和协处理器,主处理器是用于对在唤醒状态下的数据进行处理的处理器,也称CPU(Central Processing Unit,中央处理器);协处理器是用于对在待机状态下的数据进行处理的低功耗处理器。在一些实施例中,处理器31可以集成有GPU(Graphics Processing Unit,图像处理器),GPU用于负责显示屏所需要显示的内容的渲染和绘制。一些实施例中,处理器31还可以包括AI(Artificial Intelligence,人工智能)处理器, 该AI处理器用于处理有关机器学习的计算操作。
存储器30可以包括一个或多个计算机可读存储介质,该计算机可读存储介质可以是非暂态的。存储器30还可包括高速随机存取存储器以及非易失性存储器,比如一个或多个磁盘存储设备、闪存存储设备。存储器30在一些实施例中可以是电子设备的内部存储单元,例如服务器的硬盘。存储器30在另一些实施例中也可以是电子设备的外部存储设备,例如服务器上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。进一步地,存储器30还可以既包括电子设备的内部存储单元也包括外部存储设备。存储器30不仅可以用于存储安装于电子设备的应用软件及各类数据,例如:执行漏洞处理方法的程序的代码等,还可以用于暂时地存储已经输出或者将要输出的数据。本实施例中,存储器30至少用于存储以下计算机程序301,其中,该计算机程序被处理器31加载并执行之后,能够实现前述任一实施例公开的无人机飞行路径生成方法的相关步骤。另外,存储器30所存储的资源还可以包括操作系统302和数据303等,存储方式可以是短暂存储或者永久存储。其中,操作系统302可以包括Windows、Unix、Linux等。数据303可以包括但不限于无人机飞行路径生成结果对应的数据等。
在一些实施例中,上述电子设备还可包括有显示屏32、输入输出接口33、通信接口34或者称为网络接口、电源35以及通信总线36。其中,显示屏32、输入输出接口33比如键盘(Keyboard)属于用户接口,可选的用户接口还可以包括标准的有线接口、无线接口等。可选地,在一些实施例中,显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(Organic Light-Emitting Diode,有机发光二极管)触摸器等。显示器也可以适当的称为显示屏或显示单元,用于显示在电子设备中处理的信息以及用于显示可视化的用户界面。通信接口34可选的可以包括有线接口和/或无线接口,如WI-FI接口、蓝牙接口等,通常用于在电子设备与其他电子设备之间建立通信连接。通信总线36可以是外设部件互连标准(peripheral component interconnect,简称PCI)总线或扩展工业标准结构(extended industry standard architecture,简称EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。为便于表示,图3中仅用一条粗线表示,但并不表示仅有一根总线或一种类型的总线。
本领域技术人员可以理解,图3中示出的结构并不构成对该电子设备的限定,可以包括比图示更多或更少的组件,例如还可包括实现各类功能的传感器37。
本公开实施例所述电子设备的各功能模块的功能可根据上述方法实施例中的方法具体实现,其具体实现过程可以参照上述方法实施例的相关描述,此处不再赘述。
可以理解的是,如果上述实施例中的无人机飞行路径生成方法以软件功能单元的形式实 现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,执行本申请各个实施例方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、电可擦除可编程ROM、寄存器、硬盘、多媒体卡、卡型存储器(例如SD或DX存储器等)、磁性存储器、可移动磁盘、CD-ROM、磁碟或者光盘等各种可以存储程序代码的介质。
基于此,本公开实施例还提供了一种可读存储介质,存储有计算机程序,所述计算机程序被处理器执行时如上任意一实施例所述无人机飞行路径生成方法的步骤。
本公开实施例所述可读存储介质的各功能模块的功能可根据上述方法实施例中的方法具体实现,其具体实现过程可以参照上述方法实施例的相关描述,此处不再赘述。
本公开实施例还提供了一种无人机,请参见图4,可包括无人机机身41、处理器42和图像采集设备43。图像采集设备43和处理器42均搭载在无人机机身上,图像采集设备43与处理器42相连。
其中,图像采集设备43在接收到图像采集指令后,采集当前环境的图像数据。图像采集设备43可将采集的图像数据直接存储在本地,也可存储在云端,还可直接发送给处理器42,这均不影响本申请的实现。处理器42可用于执行存储器中存储的计算机程序时实现如上任意一个实施例中所记载的无人机飞行路径生成方法的步骤。
本公开实施例所述无人机的各功能模块的功能可根据上述方法实施例中的方法具体实现,其具体实现过程可以参照上述方法实施例的相关描述,此处不再赘述。
由上可知,本公开实施例可有效提高风机叶片的检测效率。
本说明书中各个实施例采用递进的方式描述,每个实施例重点说明的都是与其它实施例的不同之处,各个实施例之间相同或相似部分互相参见即可。对于实施例公开的硬件包括装置及电子设备而言,由于其与实施例公开的方法相对应,所以描述的比较简单,相关之处参见方法部分说明即可。
专业人员还可以进一步意识到,结合本文中所公开的实施例描述的各示例的单元及算法步骤,能够以电子硬件、计算机软件或者二者的结合来实现,为了清楚地说明硬件和软件的可互换性,在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本公 开的范围。
以上对本申请所提供的一种无人机飞行路径生成方法、装置、无人机、电子设备及可读存储介质进行了详细介绍。本文中应用了具体个例对本公开的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本公开的方法及其核心思想。应当指出,对于本技术领域的普通技术人员来说,在不脱离本公开原理的前提下,还可以对本申请进行若干改进和修饰,这些改进和修饰也落入本申请权利要求的保护范围内。以上内容仅为说明本公开的技术思想,不能以此限定本公开的保护范围,凡是按照本公开提出的技术思想,在技术方案基础上所做的任何改动,均落入本公开权利要求书的保护范围之内。
Claims (15)
- 一种海上无人机巡检飞行路径生成方法,包括:预先基于海上风电场信息和风机信息构建海上风电场三维模型;基于当前巡检任务总量,调用海上风电场三维模型生成无人机的初始飞行路径;根据当前环境参数和无人机自身参数,对初始飞行路径进行线路修正,以生成无人机的最终巡检飞行路径。
- 根据权利要求1所述的海上无人机巡检飞行路径生成方法,其中构建海上风电场三维模型包括:获取海上风电场的位置信息、水域深度信息、风机物理参数、海上风电场图像数据和风机图像数据;根据海上风电场图像数据构建环境三维模型;根据风机图像数据构建风机三维模型;基于环境三维模型、风机三维模型、海上风电场的位置信息、水域深度信息和风机物理参数生成海上风电场三维模型。
- 根据权利要求2所述的海上无人机巡检飞行路径生成方法,其中构建风机三维模型包括:对海面上不同类型的风机进行外作业扫描,生成点云数据;通过内作业处理,对点云数据进行粗模勾线和特征点提取,生成各风机的初始三维模型;基于初始三维模型,通过绘制钢化结构与进行模型渲染,生成各类型风机的精细化三维模型;通过区域色彩校正,利用精细化三维模型进行数字微分纠正,生成像片数字正射影像图;对像片数字正射影像图进行质量检查,并处理相应的质量问题;将不存在质量问题的像片数字正射影像图作为风机三维模型。
- 根据权利要求1至4中任一项所述的海上无人机巡检飞行路径生成方法,其中生成无人机的最终巡检飞行路径包括:预先设置当前环境参数和无人机自身参数的权重因子;获取海上风力值、海浪高度值、处于正常工作状态的风机叶片旋转信息、无人机的任务量和电池续航时间;根据海上风力值、海浪高度值、风机叶片旋转信息、任务量和电池续航时间的权重因子,对初始飞行路径中的航迹点进行修正;基于修正后的航迹点,以最优路径为目标生成最终巡检飞行路径。
- 根据权利要求5所述的海上无人机巡检飞行路径生成方法,其中对初始飞行路径中的航迹点进行修正包括:调用飞行速度计算关系式计算无人机的当前飞行速度,飞行速度计算关系式为:其中 为第k次迭代的飞行速度,i为第i次速度修正,w为惯性权重, 为第k-1次迭代的飞行速度,c 1,m 1,n 1为现场环境对无人机工作的影响因子,c 1为海上风力大小,m 1为海浪高度,n 1为风机叶片影响因子,P best在现场环境影响下最优位置, 为第k-1次迭代的无人机位置,r 1,s 1为无人机自身的影响权重,r 1为剩余任务量,s 1为电池续航时间,G best为在无人机自身影响因素下的最优位置;调用位置更新关系式计算无人机的当前位置,位置更新关系式为:根据当前飞行速度和当前位置对初始飞行路径中的航迹点的飞行速度和位置信息进行修正。
- 一种海上无人机巡检飞行路径生成装置,包括:模型构建模块,用于预先基于海上风电场信息和风机信息构建海上风电场三维模型;路径生成模块,用于基于当前巡检任务总量,调用海上风电场三维模型生成无人机的初始飞行路径;路径修正模块,用于根据当前环境参数和无人机自身参数,对初始飞行路径进行线路修 正,以生成无人机的最终巡检飞行路径。
- 根据权利要求7所述的海上无人机巡检飞行路径生成装置,其中模型构建模块进一步用于:获取海上风电场的位置信息、水域深度信息、风机物理参数、海上风电场图像数据、风机图像数据;根据海上风电场图像数据构建环境三维模型;根据风机图像数据构建风机三维模型;基于环境三维模型、风机三维模型、海上风电场的位置信息、水域深度信息和风机物理参数生成海上风电场三维模型。
- 根据权利要求8所述的海上无人机巡检飞行路径生成装置,其中模型构建模块进一步用于:对海面上不同类型的风机进行外作业扫描,生成点云数据;通过内作业处理,对点云数据进行粗模勾线和特征点提取,生成各风机的初始三维模型;基于所述初始三维模型,通过绘制钢化结构与进行模型渲染,生成各类型风机的精细化三维模型;通过区域色彩校正,利用精细化三维模型进行数字微分纠正,生成像片数字正射影像图;对像片数字正射影像图进行质量检查,并处理相应的质量问题;将不存在质量问题的像片数字正射影像图作为风机三维模型。
- 根据权利要求7至10中任一项所述的海上无人机巡检飞行路径生成装置,其中路径修正模块进一步用于:预先设置当前环境参数和无人机自身参数的权重因子;获取海上风力值、海浪高度值、处于正常工作状态的风机叶片旋转信息、无人机的任务量、电池续航时间;根据海上风力值、海浪高度值、风机叶片旋转信息、任务量和电池续航时间的权重因子,对初始飞行路径中的航迹点进行修正;基于修正后的航迹点,以最优路径为目标生成最终巡检飞行路径。
- 根据权利要求11所述的海上无人机巡检飞行路径生成装置,其中路径修正模块进一步用于:调用飞行速度计算关系式计算无人机的当前飞行速度,飞行速度计算关系式为:其中 为第k次迭代的飞行速度,i为第i次速度修正,w为惯性权重,c 1,m 1,n 1为现场环境对无人机工作的影响因子,c 1为海上风力大小,m 1为海浪高度,n 1为风机叶片影响因子,P best在现场环境影响下最优位置, 为第k-1次迭代的无人机位置,r 1,s 1为无人机自身的影响权重,r 1为剩余任务量,s 1为电池续航时间,G best为在无人机自身影响因素下的最优位置;调用位置更新关系式计算无人机的当前位置,位置更新关系式为:根据当前飞行速度和当前位置对初始飞行路径中的航迹点的飞行速度和位置信息进行修正。
- 一种计算机设备,包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序,其中所述处理器执行所述计算机程序时实现如权利要求1至6任意一项所述海上无人机巡检飞行路径生成方法的步骤。
- 一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,其中所述计算机程序被处理器执行时实现如权利要求1至6任意一项所述海上无人机巡检飞行路径生成方法的步骤。
- 一种无人机,包括无人机机身、图像采集设备和处理器;图像采集设备和处理器搭载在无人机机身;图像采集设备与处理器相连;图像采集设备在接收到图像采集指令后,采集当前环境的图像数据;处理器用于执行存储器中存储的计算机程序时实现如权利要求1至6任意一项所述海上无人机巡检飞行路径生成方法的步骤。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110963456.8A CN113485453B (zh) | 2021-08-20 | 2021-08-20 | 一种海上无人机巡检飞行路径生成方法、装置及无人机 |
CN202110963456.8 | 2021-08-20 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023020084A1 true WO2023020084A1 (zh) | 2023-02-23 |
Family
ID=77947013
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2022/098344 WO2023020084A1 (zh) | 2021-08-20 | 2022-06-13 | 海上无人机巡检飞行路径生成方法、装置及无人机 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN113485453B (zh) |
WO (1) | WO2023020084A1 (zh) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116087235A (zh) * | 2023-04-07 | 2023-05-09 | 四川川交路桥有限责任公司 | 一种多源耦合的桥梁损伤探测方法及系统 |
CN116501091A (zh) * | 2023-06-27 | 2023-07-28 | 珠海优特电力科技股份有限公司 | 基于无人机自动调整航线的风机巡检控制方法和装置 |
CN116798030A (zh) * | 2023-08-28 | 2023-09-22 | 中国建筑第六工程局有限公司 | 曲面观光雷达高塔验收方法、系统、装置及存储介质 |
CN116823872A (zh) * | 2023-08-25 | 2023-09-29 | 尚特杰电力科技有限公司 | 基于目标追踪和图像分割的风机巡检方法及系统 |
CN116952222A (zh) * | 2023-09-18 | 2023-10-27 | 中安锐达(北京)电子科技有限公司 | 一种低慢小目标探测系统多源数据融合方法 |
CN117146832A (zh) * | 2023-10-31 | 2023-12-01 | 北京佳格天地科技有限公司 | 融合无线通信和人工智能的农机自动驾驶控制方法及系统 |
CN117170408A (zh) * | 2023-10-11 | 2023-12-05 | 中电投新疆能源化工集团吐鲁番有限公司 | 基于无人机的光伏板场地巡检路径智能规划系统及方法 |
CN117268402A (zh) * | 2023-11-17 | 2023-12-22 | 黑龙江哲讯信息技术有限公司 | 一种基于5g通信技术的无人机勘察路径规划方法 |
CN117294820A (zh) * | 2023-11-24 | 2023-12-26 | 国网电力空间技术有限公司 | 一种风力发电场无人机巡检系统 |
CN117499439A (zh) * | 2023-11-14 | 2024-02-02 | 北京理工大学前沿技术研究院 | 一种基于工业物联网的巡检数据处理系统及其处理方法 |
CN117536797A (zh) * | 2023-10-24 | 2024-02-09 | 华能安徽怀宁风力发电有限责任公司 | 一种基于无人机的风机叶片巡检系统及方法 |
CN117631692A (zh) * | 2024-01-26 | 2024-03-01 | 国网江西省电力有限公司电力科学研究院 | 一种无人机红外自主巡检航线智能推荐方法 |
CN117788737A (zh) * | 2023-12-27 | 2024-03-29 | 中水珠江规划勘测设计有限公司 | 一种基于无人机高光谱遥感的测绘方法 |
CN118210328A (zh) * | 2024-05-21 | 2024-06-18 | 中科方寸知微(南京)科技有限公司 | 基于模型轻量化技术的无人机自主导航系统 |
CN118587621A (zh) * | 2024-08-02 | 2024-09-03 | 浙江臻越建设有限公司 | 一种基于无人机遥感的建筑测绘方法及系统 |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113485453B (zh) * | 2021-08-20 | 2024-05-10 | 中国华能集团清洁能源技术研究院有限公司 | 一种海上无人机巡检飞行路径生成方法、装置及无人机 |
CN114153224B (zh) * | 2021-10-15 | 2024-07-23 | 广西电网有限责任公司电力科学研究院 | 基于微气象的无人机飞行路径智能规划控制系统及方法 |
CN114020002B (zh) * | 2021-12-20 | 2024-05-03 | 复亚智能科技(太仓)有限公司 | 无人机巡检风机叶片的方法、装置、设备、无人机及介质 |
CN114610070B (zh) * | 2022-03-21 | 2024-06-21 | 大连理工大学 | 一种无人机协同的风电场智能巡检方法 |
CN114967726A (zh) * | 2022-07-18 | 2022-08-30 | 中国华能集团清洁能源技术研究院有限公司 | 风机巡检无人机飞行参数的自适应调整方法、装置及设备 |
CN115480589B (zh) * | 2022-09-06 | 2023-07-25 | 中科云尚(南京)智能技术有限公司 | 基于无人机的风机巡检航线生成方法及系统 |
CN116011695B (zh) * | 2023-03-27 | 2023-06-30 | 湖南胜云光电科技有限公司 | 一种获取无人机目标路径的数据处理系统 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200103924A1 (en) * | 2018-10-01 | 2020-04-02 | Rockwell Collins, Inc. | Systems and methods for optimized cruise vertical path |
CN111552306A (zh) * | 2020-04-10 | 2020-08-18 | 安徽继远软件有限公司 | 支持杆塔关键部件巡检的无人机路径生成方法和装置 |
CN112327920A (zh) * | 2020-11-16 | 2021-02-05 | 国网新疆电力有限公司检修公司 | 一种无人机自主避障巡检路径规划方法及装置 |
CN112379679A (zh) * | 2021-01-15 | 2021-02-19 | 北京理工大学 | 一种无人车辆局部路径规划方法 |
CN112783196A (zh) * | 2020-12-17 | 2021-05-11 | 国网山西省电力公司运城供电公司 | 配网线路无人机自主飞行路径规划方法及系统 |
CN113204247A (zh) * | 2021-04-16 | 2021-08-03 | 深圳市艾赛克科技有限公司 | 一种无人机巡检系统 |
CN113485453A (zh) * | 2021-08-20 | 2021-10-08 | 中国华能集团清洁能源技术研究院有限公司 | 一种海上无人机巡检飞行路径生成方法、装置及无人机 |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106202744B (zh) * | 2016-07-12 | 2019-09-13 | 中国能源建设集团广东省电力设计研究院有限公司 | 海上风电场集电系统避障路径优化方法和系统 |
CN108733079B (zh) * | 2018-06-19 | 2021-08-10 | 上海扩博智能技术有限公司 | 通过无人机对风机进行自动巡检飞行路径确定方法及系统 |
CN110282143B (zh) * | 2019-06-14 | 2022-09-27 | 中国能源建设集团广东省电力设计研究院有限公司 | 一种海上风电场无人机巡检方法 |
CN110879607A (zh) * | 2019-09-27 | 2020-03-13 | 哈尔滨理工大学 | 一种基于多无人机编队协同探测的海上风电叶片检测方法 |
CN111640220A (zh) * | 2020-06-29 | 2020-09-08 | 盛东如东海上风力发电有限责任公司 | 一种用于海上风电场的无人船巡检系统及其工作方法 |
CN112904877A (zh) * | 2021-01-14 | 2021-06-04 | 星闪世图(台州)科技有限公司 | 一种基于无人机的风机叶片自动巡检系统及方法 |
-
2021
- 2021-08-20 CN CN202110963456.8A patent/CN113485453B/zh active Active
-
2022
- 2022-06-13 WO PCT/CN2022/098344 patent/WO2023020084A1/zh unknown
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200103924A1 (en) * | 2018-10-01 | 2020-04-02 | Rockwell Collins, Inc. | Systems and methods for optimized cruise vertical path |
CN111552306A (zh) * | 2020-04-10 | 2020-08-18 | 安徽继远软件有限公司 | 支持杆塔关键部件巡检的无人机路径生成方法和装置 |
CN112327920A (zh) * | 2020-11-16 | 2021-02-05 | 国网新疆电力有限公司检修公司 | 一种无人机自主避障巡检路径规划方法及装置 |
CN112783196A (zh) * | 2020-12-17 | 2021-05-11 | 国网山西省电力公司运城供电公司 | 配网线路无人机自主飞行路径规划方法及系统 |
CN112379679A (zh) * | 2021-01-15 | 2021-02-19 | 北京理工大学 | 一种无人车辆局部路径规划方法 |
CN113204247A (zh) * | 2021-04-16 | 2021-08-03 | 深圳市艾赛克科技有限公司 | 一种无人机巡检系统 |
CN113485453A (zh) * | 2021-08-20 | 2021-10-08 | 中国华能集团清洁能源技术研究院有限公司 | 一种海上无人机巡检飞行路径生成方法、装置及无人机 |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116087235A (zh) * | 2023-04-07 | 2023-05-09 | 四川川交路桥有限责任公司 | 一种多源耦合的桥梁损伤探测方法及系统 |
CN116501091A (zh) * | 2023-06-27 | 2023-07-28 | 珠海优特电力科技股份有限公司 | 基于无人机自动调整航线的风机巡检控制方法和装置 |
CN116501091B (zh) * | 2023-06-27 | 2023-11-07 | 珠海优特电力科技股份有限公司 | 基于无人机自动调整航线的风机巡检控制方法和装置 |
CN116823872A (zh) * | 2023-08-25 | 2023-09-29 | 尚特杰电力科技有限公司 | 基于目标追踪和图像分割的风机巡检方法及系统 |
CN116823872B (zh) * | 2023-08-25 | 2024-01-26 | 尚特杰电力科技有限公司 | 基于目标追踪和图像分割的风机巡检方法及系统 |
CN116798030A (zh) * | 2023-08-28 | 2023-09-22 | 中国建筑第六工程局有限公司 | 曲面观光雷达高塔验收方法、系统、装置及存储介质 |
CN116798030B (zh) * | 2023-08-28 | 2023-11-14 | 中国建筑第六工程局有限公司 | 曲面观光雷达高塔验收方法、系统、装置及存储介质 |
CN116952222A (zh) * | 2023-09-18 | 2023-10-27 | 中安锐达(北京)电子科技有限公司 | 一种低慢小目标探测系统多源数据融合方法 |
CN116952222B (zh) * | 2023-09-18 | 2023-12-08 | 中安锐达(北京)电子科技有限公司 | 一种低慢小目标探测系统多源数据融合方法 |
CN117170408A (zh) * | 2023-10-11 | 2023-12-05 | 中电投新疆能源化工集团吐鲁番有限公司 | 基于无人机的光伏板场地巡检路径智能规划系统及方法 |
CN117536797B (zh) * | 2023-10-24 | 2024-05-31 | 华能安徽怀宁风力发电有限责任公司 | 一种基于无人机的风机叶片巡检系统及方法 |
CN117536797A (zh) * | 2023-10-24 | 2024-02-09 | 华能安徽怀宁风力发电有限责任公司 | 一种基于无人机的风机叶片巡检系统及方法 |
CN117146832B (zh) * | 2023-10-31 | 2024-01-02 | 北京佳格天地科技有限公司 | 融合无线通信和人工智能的农机自动驾驶控制方法及系统 |
CN117146832A (zh) * | 2023-10-31 | 2023-12-01 | 北京佳格天地科技有限公司 | 融合无线通信和人工智能的农机自动驾驶控制方法及系统 |
CN117499439A (zh) * | 2023-11-14 | 2024-02-02 | 北京理工大学前沿技术研究院 | 一种基于工业物联网的巡检数据处理系统及其处理方法 |
CN117268402B (zh) * | 2023-11-17 | 2024-01-30 | 黑龙江哲讯信息技术有限公司 | 一种基于5g通信技术的无人机勘察路径规划方法 |
CN117268402A (zh) * | 2023-11-17 | 2023-12-22 | 黑龙江哲讯信息技术有限公司 | 一种基于5g通信技术的无人机勘察路径规划方法 |
CN117294820A (zh) * | 2023-11-24 | 2023-12-26 | 国网电力空间技术有限公司 | 一种风力发电场无人机巡检系统 |
CN117294820B (zh) * | 2023-11-24 | 2024-03-15 | 国网电力空间技术有限公司 | 一种风力发电场无人机巡检系统 |
CN117788737A (zh) * | 2023-12-27 | 2024-03-29 | 中水珠江规划勘测设计有限公司 | 一种基于无人机高光谱遥感的测绘方法 |
CN117788737B (zh) * | 2023-12-27 | 2024-05-28 | 中水珠江规划勘测设计有限公司 | 一种基于无人机高光谱遥感的测绘方法 |
CN117631692A (zh) * | 2024-01-26 | 2024-03-01 | 国网江西省电力有限公司电力科学研究院 | 一种无人机红外自主巡检航线智能推荐方法 |
CN117631692B (zh) * | 2024-01-26 | 2024-05-14 | 国网江西省电力有限公司电力科学研究院 | 一种无人机红外自主巡检航线智能推荐方法 |
CN118210328A (zh) * | 2024-05-21 | 2024-06-18 | 中科方寸知微(南京)科技有限公司 | 基于模型轻量化技术的无人机自主导航系统 |
CN118587621A (zh) * | 2024-08-02 | 2024-09-03 | 浙江臻越建设有限公司 | 一种基于无人机遥感的建筑测绘方法及系统 |
Also Published As
Publication number | Publication date |
---|---|
CN113485453B (zh) | 2024-05-10 |
CN113485453A (zh) | 2021-10-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2023020084A1 (zh) | 海上无人机巡检飞行路径生成方法、装置及无人机 | |
CN110163087B (zh) | 一种人脸姿态识别方法及系统 | |
CN112633277A (zh) | 基于深度学习的航道船牌检测、定位及识别方法 | |
CN110597937B (zh) | 一种无人智能巡检的方法、装置、设备及存储介质 | |
CN112344869B (zh) | 基于侧面拟合的铁塔变形监测方法及系统 | |
CN109657403A (zh) | 一种基于无人机倾斜摄影的三维实景桥梁建模优化方法 | |
CN112700498A (zh) | 一种基于深度学习的风力发电机叶尖定位方法及系统 | |
CN109583367A (zh) | 图像文本行检测方法及装置、存储介质和电子设备 | |
CN116091709B (zh) | 建筑物的三维重建方法、装置、电子设备和存储介质 | |
WO2024037562A1 (zh) | 三维重建方法、装置及计算机可读存储介质 | |
CN116486290B (zh) | 一种无人机监测追踪方法、装置、电子设备及存储介质 | |
CN115311418B (zh) | 一种多细节层次树木模型单体化重建方法及装置 | |
CN116934300A (zh) | 一种输电线路巡检的路径规划方法、装置及介质 | |
US20230036294A1 (en) | Method for processing image, electronic device and storage medium | |
CN107918935A (zh) | 嵌入式系统的图像匹配切割装置及切割方法 | |
CN115830438A (zh) | 基于深度学习的复杂场景下违章建筑物体检测方法及装置 | |
CN112949641A (zh) | 图像分割方法及电子设备、计算机可读存储介质 | |
CN110610492A (zh) | 在役风机全尺寸叶片外部损伤识别方法、系统、存储介质和终端 | |
CN105182739B (zh) | 一种船舶航行增阻等级的评估方法 | |
CN116229209B (zh) | 目标模型的训练方法、目标检测方法及装置 | |
CN113327285B (zh) | 一种图片拍摄方位的识别方法、装置及其电子设备 | |
CN118279949A (zh) | 一种三维数字人的表情驱动方法及电子设备 | |
Kong | Deep learning-based building envelope information extraction for BIPV application | |
CN115830484A (zh) | 一种风力发电机组塔架净空获取方法及装置 | |
CN115311402A (zh) | 贴图uv信息的处理方法及装置、存储介质和电子设备 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22857397 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |