CN219978855U - Power monitoring system for satellite electric propeller - Google Patents
Power monitoring system for satellite electric propeller Download PDFInfo
- Publication number
- CN219978855U CN219978855U CN202321211717.1U CN202321211717U CN219978855U CN 219978855 U CN219978855 U CN 219978855U CN 202321211717 U CN202321211717 U CN 202321211717U CN 219978855 U CN219978855 U CN 219978855U
- Authority
- CN
- China
- Prior art keywords
- processor module
- monitoring system
- camera
- graphics processor
- interface
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000005259 measurement Methods 0.000 claims description 12
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000013473 artificial intelligence Methods 0.000 description 9
- 238000012549 training Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 238000000034 method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000003213 activating effect Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004660 morphological change Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The utility model provides a power monitoring system for a satellite electric propulsion, comprising: camera, embedded system, graphics processor module; the camera is used for shooting an operation state image of the electric propeller and transmitting the operation state image to the embedded system; the embedded system is used for receiving the image data transmitted by the camera and transmitting the image data to the graphic processor module; the graphics processor module is used for performing image processing and recognition on the received image data to recognize the state of the electric propeller. The monitoring system can realize the judgment of power monitoring of the satellite electric propeller through a target monitoring technology, provides an intelligent solution for real-time monitoring of the satellite on-orbit power running state, and does not need to pay attention to the satellite power condition manually in real time.
Description
Technical Field
The utility model relates to the field of satellites, in particular to a power monitoring system for a satellite electric propeller.
Background
Patent number CN103917451B entitled a method for adjusting the attitude of a satellite and an attitude-controlled satellite, discloses a method for attitude control of a satellite by activating an electric thruster. However, there is currently a lack of an efficient, intelligent, intuitive method to monitor the propulsion state of an electric propulsion.
In order to realize intelligent identification of the running state of the satellite electric propeller, it is important to design a power monitoring system for the satellite electric propeller.
Disclosure of Invention
The utility model aims to overcome the defects of the prior art and provides a power monitoring system for a satellite electric propeller.
The utility model provides a power monitoring system for a satellite electric propulsion, comprising: camera, embedded system, graphics processor module; the camera is used for shooting an operation state image of the electric propeller and transmitting the operation state image to the embedded system; the embedded system is used for receiving the image data transmitted by the camera and transmitting the image data to the graphic processor module; the graphics processor module is used for performing image processing and recognition on the received image data to recognize the state of the electric propeller.
According to one embodiment of the utility model, the embedded system comprises an FPGA chip electrically connected to the camera and the graphics processor module, respectively, for receiving and transmitting image data of the camera to the graphics processor module.
According to one embodiment of the utility model, the FPGA chip adopts an XC7K325T chip.
According to one embodiment of the utility model, the FPGA chip is connected with the camera through a CameraLink input interface.
According to one embodiment of the utility model, the system further comprises a measurement and control system; the FPGA chip is also used for receiving the identification result of the graphic processor module; the FPGA chip is connected with the measurement and control system through a CameraLink output interface so as to transmit the identification result of the graphic processor module to the ground through the measurement and control system.
According to one embodiment of the utility model, the graphics processor module employs a Jetson AGX Xavier industrial module.
According to one embodiment of the utility model, the graphics processor module is connected to the FPGA chip through an MIPI interface to receive image data transmitted by the FPGA chip.
According to one embodiment of the utility model, the MIPI interface employs a TC358746AXBG interface.
According to one embodiment of the present utility model, the FPGA further includes a first SPI interface and a first GPIO interface, and the graphics processor module further includes a second SPI interface and a second GPIO interface as reserved interfaces for the FPGA and the graphics processor module to be electrically connected to each other.
According to one embodiment of the utility model, a plurality of said cameras are included.
According to the power monitoring system for the satellite electric propulsion, the judgment of power monitoring of the satellite electric propulsion can be realized through a target monitoring technology, an intelligent solution is provided for monitoring the in-orbit power running state of the satellite in real time, and the satellite power condition does not need to be manually focused in real time.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the scope of the utility model, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the utility model and, together with the description, serve to explain the principles of the utility model.
FIG. 1 is a schematic diagram of a power monitoring system for a satellite electric propulsion machine according to one embodiment of the utility model;
FIG. 2 is a flow chart of power monitoring for satellite electric propulsion based on artificial intelligence in accordance with one embodiment of the utility model;
FIG. 3 is artificial intelligence training model training data for one embodiment of the utility model;
FIG. 4 is a schematic diagram of monitoring and identifying the power running state of the satellite electric propeller based on artificial intelligence according to one embodiment of the utility model.
Detailed Description
Features and exemplary embodiments of various aspects of the present utility model will be described in detail below, and in order to make the objects, technical solutions and advantages of the present utility model more apparent, the present utility model will be described in further detail below with reference to the accompanying drawings and the detailed embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the principles of the present utility model and not in limitation thereof. In addition, the mechanical components in the drawings are not necessarily to scale. For example, the dimensions of some of the structures or regions in the figures may be exaggerated relative to other structures or regions to help facilitate an understanding of embodiments of the present utility model.
The directional terms appearing in the following description are all directions shown in the drawings and do not limit the specific structure of the embodiment of the present utility model. In the description of the present utility model, it should be noted that, unless otherwise indicated, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be directly connected or indirectly connected through an intermediate medium. The specific meaning of the above terms in the present utility model can be understood as appropriate by those of ordinary skill in the art.
Furthermore, the terms "comprises," "comprising," "includes," "including," "having," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a structure or assembly that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such structure, assembly. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in an article or apparatus that comprises the element.
Spatially relative terms such as "under", "below", "under …", "low", "above", "over …", "high", and the like, are used for convenience of description to explain the positioning of one element relative to a second element and to represent different orientations of the device in addition to those shown in the figures. In addition, for example, "one element above/below another element" may mean that two elements are in direct contact, or that other elements are present between the two elements. Furthermore, terms such as "first," "second," and the like, are also used to describe various elements, regions, sections, etc., and do not specifically address the order or sequence and should not be taken as limiting. Like terms refer to like elements throughout the description.
It will be apparent to one skilled in the art that the present utility model may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the utility model by showing examples of the utility model.
FIG. 1 is a schematic diagram of a power monitoring system for a satellite electric propulsion machine according to one embodiment of the utility model; FIG. 2 is a flow chart of power monitoring for satellite electric propulsion based on artificial intelligence in accordance with one embodiment of the utility model; FIG. 3 is artificial intelligence training model training data for one embodiment of the utility model; FIG. 4 is a schematic diagram of monitoring and identifying the power running state of the satellite electric propeller based on artificial intelligence according to one embodiment of the utility model.
As shown in fig. 1, the present utility model provides a power monitoring system for a satellite electric propulsion, comprising: camera, embedded system, graphics processor module. The camera is used for shooting an operation state image of the electric propeller and transmitting the operation state image to the embedded system. The embedded system is used for receiving the image data transmitted by the camera and transmitting the image data to the graphic processor module. The graphics processor module is used for performing image processing and identification on the received image data to identify the state of the electric propeller.
Specifically, the embedded system comprises a board card module. Because of its powerful real-time computing power and reliability, DSPs are widely used in the aerospace field, and the board card architecture of conventional spaceborne computers typically employs Digital Signal Processors (DSPs). However, because the DSP has the disadvantages of weaker image processing capability and fewer interface resources, the board architecture design of the on-board computer is evolving toward diversification. With the development of new technology, graphics Processing Units (GPUs) have become a good choice for current board card designs as a main control chip because of their advantages of floating point computing capability, strong parallel computing capability, and rich memory interface resources. Furthermore, in practice, satellite cameras are a key load that can scan and take pictures of specific targets, resulting in high-pixel photographs.
In this embodiment, the camera may be a satellite camera. The satellite camera is able to scan and take pictures of specific objects (electric propellers) and produce higher quality photographs. The Graphic Processing Unit (GPU) chip has the advantages of excellent data and image processing capability, strong parallel computing capability, rich memory interface resources and the like, and can be used for image processing and recognition, so that the high-performance requirement of satellite computing tasks can be met, and the positioning and recognition of an electric propeller target are realized. Therefore, the graphics processor is used as a core computing power, and the embedded system is combined with the graphics processor to form an on-board computer carrier, so that stronger image processing capability is provided. In addition, the monitoring system provided by the embodiment supports the application of the artificial intelligent image recognition technology to the monitoring of the satellite electric propeller, and can be realized by a high-power computer carried on a satellite. By building an artificial intelligent network learning model on a high-power computer, the power monitoring of the satellite electric propeller can be judged through a target monitoring technology, an intelligent solution is provided for monitoring the satellite in-orbit power running state in real time, the satellite power condition does not need to be manually focused in real time, and more references are provided for a satellite attitude and orbit control technology. The monitoring system provided by the embodiment can also select high-quality pictures and feed back the pictures to the ground, so that the propulsion state of the electric propeller can be monitored more effectively, intelligently and intuitively, and the capability of processing satellite camera pictures is further improved.
According to one embodiment of the utility model, the embedded system comprises an FPGA chip electrically connected to the camera and the graphics processor module, respectively, for receiving image data of the camera and transmitting it to the graphics processor module.
The monitoring system provided by the embodiment adopts a framework of combining a Graphic Processor (GPU) and an FPGA, builds an artificial intelligent model, applies a computer vision and deep learning algorithm to a satellite-borne computer carrier plate, provides an intelligent solution for satellite electric propeller power monitoring, and improves the efficient processing and computing capacity of electric propeller photos. As shown in fig. 2, 3 and 4, taking a single camera of a camera as an example, an artificial intelligent model is built, and the process of detecting and identifying the power running state of the satellite electric propeller is as follows:
s01: and acquiring power running state data of the electric propeller by a camera, and marking the data by labelImg according to different colors and shooting angles.
S02: and constructing an artificial intelligent model, and selecting a one-stage target detection model Retinonet as a basic model.
S03: according to the training set: verification set: test set = 7:2:1 ratio divides the data and trains the model.
S04: and packaging the artificial intelligent model and the deployment environment by using a docker.
S05: and detecting and identifying the power running state of the satellite electric propeller.
The method can be used for shooting the running and non-running conditions of the electric propeller at multiple angles by using an industrial camera, performing preliminary identification classification on the running state of the electric propeller by using labelImg, then dividing the identified content into Annotations, imageSets, JPEGImages folders by using a VOC2007 format for storage respectively, dividing the data into 7:2:1 according to a data set, and training a power running state monitoring model of the satellite electric propeller. According to the requirements on the accuracy and response speed of identification and judgment, a one-stage target detection model Retinonet can be selected as a basic model, and a network comprising a resnet and a network of fpn is included. The electric propeller target is positioned by layer-by-layer feature extraction and retention amplification by using python to program based on pytorch, and model training is achieved to a good degree by adjusting each super parameter. Experiments prove that after 30 rounds of iteration, the model can obtain good effect, and the ap score reaches more than 0.9 from 0.1. The Retinonet is selected as a basic network, has excellent suitability, the iteration times are about one tenth of those of yolo, the accuracy is far higher than that of yolo, and the satellite electric propeller power monitoring and identifying task can be completed, so that space self-learning and self-updating become possible.
In step S03, a plurality of cameras can be linked, an artificial intelligent monitoring model with multidimensional linkage is built, and the problems that a single camera is easy to lose a target, inaccurate in judgment and the like can be solved. The step can also comprise the steps of constructing a scoring and sorting module, sorting every 100 pictures according to the AP score from large to small by comparing the AP score of each picture in the test set, selecting two highest-score pictures in each hundred, and transmitting original pictures (without data marking) of the two highest-score pictures to the ground for real-time observation and use. Because of the limitation of satellite communication data transmission rate, the grading and sorting module is built and preferentially transmitted to the ground, so that the pressure of transmission overload is reduced, and the discrimination result and quality are improved.
In step S04, the artificial intelligent model and the deployment environment are packaged and packaged by using a dock container technology, so that the artificial intelligent model can be rapidly deployed on a plurality of satellites, and the deployment convenience and batch capacity of the artificial intelligent model are greatly improved. The deployment environment can well run on a satellite-mounted system and run independently of other system environments without being interfered and affected by the other system environments.
The artificial intelligent model applied to the monitoring of the power running state of the satellite electric propeller is deployed on the satellite, can provide referent monitoring and feedback for the satellite state, and provides further support and development for the attitude and orbit control technology based on electric propulsion.
According to one embodiment of the utility model, the FPGA chip employs an XC7K325T chip.
In the embodiment, the embedded system adopts a high-reliability military-grade FPGA chip XC7K325T (purchased through commercial paths) of Xilinx company, so that a satellite-borne computer carrier of a satellite has high stability and reliability and can adapt to a severe aerospace environment.
According to one embodiment of the utility model, the FPGA chip is connected with the camera through a CameraLink input interface.
In this embodiment, the FPGA chip may be an XC7K325T chip from Xilinx, which has 3 paths of CameraLink input interfaces, each of which can be used to receive photo data of a camera.
According to one embodiment of the utility model, the detection system includes a measurement and control system in addition to the camera, the embedded system, and the graphics processor module. The FPGA chip is also used for receiving the identification result of the graphic processor module. The FPGA chip is connected with the measurement and control system through the CameraLink output interface so as to transmit the identification result of the graphic processor module to the ground through the measurement and control system.
In this embodiment, the FPGA chip XC7K325T of Xilinx corporation further has a 1-way CameraLink output interface for connection with a measurement and control system. The XC7K325T chip transmits the received photo data of the industrial camera to the GPU module (namely the graphic processor module) for processing, then the processing result is sent to the measurement and control system, and the measurement and control system transmits the processing result to the ground.
According to one embodiment of the utility model, the graphics processor module employs a JetsonaGX Xavier industrial module.
In this embodiment, the core power Graphics Processor (GPU) module adopts JetsonAGX Xavier industrial module (commercially available) from NVIDIA corporation, so that the satellite-borne computer carrier of the satellite has high stability and reliability, and can adapt to a severe aerospace environment.
According to one embodiment of the utility model, the graphics processor module is connected to the FPGA chip through the MIPI interface to receive image data transmitted by the FPGA chip.
In this embodiment, the JetsonAGX Xavier industrial module of NVIDIA company has 4 paths of MIPI interfaces, which can all receive data transmitted by the FPGA chip, so as to implement image transmission between the FPGA and the Graphics Processor (GPU).
According to one embodiment of the utility model, the MIPI interface employs the TC358746AXBG interface.
In this embodiment, the MIPI of the graphics processor module employs TC358746AXBG of TOSHIBA to enable conversion of CSI-2TX/RX parallel data to MIPI data.
According to one embodiment of the utility model, the FPGA comprises a first SPI interface and a first GPIO interface in addition to the CameraLink input interface and the CameraLink output interface. In addition to the MIPI interface, the graphics processor module also includes a second SPI interface and a second GPIO interface as reserved interfaces for the FPGA and graphics processor module to be electrically connected to each other.
In this embodiment, the graphics processor module may be a Jetson AGX Xavier industrial module from NVIDIA, which has 3 second SPI interfaces and 5 first GPIO interfaces, which are all available for electrical connection with the FPGA.
According to one embodiment of the utility model, besides the CameraLink input interface and the CameraLink output interface, the FPGA further comprises a first CAN_FD interface and a first Ethernet interface which are reserved as communication interfaces of the FPGA. The FPGA of the monitoring system uses a CameraLink, a first CAN_FD and a plurality of communication interfaces of a first Ethernet, realizes data transmission and communication between the FPGA and an external system, and leaves a reserved interface for subsequent function expansion.
In this embodiment, the FPGA chip may be an XC7K325T chip from Xilinx corporation, which has a 2-way first CAN FD interface and a 2-way first ethernet interface.
According to one embodiment of the utility model, the Graphics Processor (GPU) module includes a second CAN FD interface and a second ethernet interface in addition to the MIPI interface as a reserved interface for the Graphics Processor (GPU) to communicate with the outside. The FPGA of the monitoring system uses MIPI, a second CAN_FD and a second Ethernet multiple communication interfaces, realizes data transmission and communication between a Graphic Processor (GPU) and an external system, and leaves a reserved interface for subsequent function expansion.
In this embodiment, the graphics processor module may employ a Jetson AGX Xavier industry module from NVIDIA, which has a 2-way second CAN FD interface and a 2-way second ethernet interface.
According to one embodiment of the utility model, a plurality of cameras are included.
In this embodiment, the plurality of cameras may employ industrial cameras. The plurality of industrial cameras can collect propeller data at the same time from different angles and transmit the propeller data to the embedded system through the CameraLink interface. The image data acquired needs to be marked separately due to morphological changes of the image data caused by different shooting angles. According to the difference of color and shooting angle, the image data can be marked by labelImg, and the training set can be used for: verification set: test set = 7:2: 1.
In the utility model, the model Retinonet is a result obtained by optimizing a plurality of artificial intelligence basic model frames, and the super parameter setting is optimized, and the model Retinonet is only used for explaining that the power monitoring system for the satellite electric propeller provided by the utility model can support the application of the artificial intelligence model and is not used for limiting the protection scope of the utility model. Those skilled in the art will appreciate that the monitoring system may be used to perform monitoring tasks, and that other basic models may be employed, including but not limited to the basic artificial intelligence framework of Yolo, RCNN, SDD, etc.
The above-described embodiments of the present utility model can be combined with each other with corresponding technical effects.
The foregoing description of the preferred embodiments of the utility model is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the utility model.
Claims (10)
1. A power monitoring system for a satellite electric propulsion machine, comprising: camera, embedded system, graphics processor module; the camera is used for shooting an operation state image of the electric propeller and transmitting the operation state image to the embedded system; the embedded system is used for receiving the image data transmitted by the camera and transmitting the image data to the graphic processor module; the graphics processor module is used for performing image processing and recognition on the received image data to recognize the state of the electric propeller.
2. The monitoring system of claim 1, wherein the embedded system comprises an FPGA chip electrically connected to the camera and the graphics processor module, respectively, for receiving and transmitting image data of the camera to the graphics processor module.
3. The monitoring system of claim 2, wherein the FPGA chip employs an XC7K325T chip.
4. The monitoring system of claim 3, wherein the FPGA chip is connected to the camera through a CameraLink input interface.
5. The monitoring system of claim 4, further comprising a measurement and control system; the FPGA chip is also used for receiving the identification result of the graphic processor module; the FPGA chip is connected with the measurement and control system through a CameraLink output interface so as to transmit the identification result of the graphic processor module to the ground through the measurement and control system.
6. The monitoring system of claim 5, wherein the graphics processor module employs a JetsonAGXXavier industrial module.
7. The monitoring system of claim 6, wherein the graphics processor module is coupled to the FPGA chip via a MIPI interface to receive image data transmitted by the FPGA chip.
8. The monitoring system of claim 7, wherein the MIPI interface employs a TC358746AXBG interface.
9. The monitoring system of claim 7, wherein the FPGA further comprises a first SPI interface and a first GPIO interface, and the graphics processor module further comprises a second SPI interface and a second GPIO interface as reserved interfaces for the FPGA and the graphics processor module to be electrically connected to each other.
10. The monitoring system of claim 1, comprising a plurality of said cameras.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202321211717.1U CN219978855U (en) | 2023-05-19 | 2023-05-19 | Power monitoring system for satellite electric propeller |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202321211717.1U CN219978855U (en) | 2023-05-19 | 2023-05-19 | Power monitoring system for satellite electric propeller |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN219978855U true CN219978855U (en) | 2023-11-07 |
Family
ID=88584360
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202321211717.1U Active CN219978855U (en) | 2023-05-19 | 2023-05-19 | Power monitoring system for satellite electric propeller |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN219978855U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118067399A (en) * | 2024-04-19 | 2024-05-24 | 哈尔滨工业大学 | Near-field plume imaging monitoring method for on-orbit state of plasma thruster |
-
2023
- 2023-05-19 CN CN202321211717.1U patent/CN219978855U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118067399A (en) * | 2024-04-19 | 2024-05-24 | 哈尔滨工业大学 | Near-field plume imaging monitoring method for on-orbit state of plasma thruster |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN219978855U (en) | Power monitoring system for satellite electric propeller | |
| CN104967783B (en) | Towards the micro- image capturing system of multichannel of micro-nano star | |
| US11748949B2 (en) | Object scanning using planar segmentation | |
| CN109191415A (en) | Image interfusion method, device and electronic equipment | |
| CN108764051A (en) | Image processing method, device and mobile terminal | |
| CN115294476A (en) | Edge calculation intelligent detection method and device for unmanned aerial vehicle power inspection | |
| CN114035606A (en) | Pole tower inspection system, pole tower inspection method, control device and storage medium | |
| CN109194284A (en) | Photovoltaic plant cruising inspection system, ground based terminal and equipment of taking photo by plane | |
| CN103345765A (en) | Detecting device and detecting method for moving objects under mobile platform based on DSP+FPGA | |
| Liang et al. | Design and development of ground control system for tethered uav | |
| WO2021149485A1 (en) | Display control device, display control method, and program | |
| CN203397395U (en) | Moving object detection device in platform based on DSP + FPGA | |
| CN117332370A (en) | Underwater target acousto-optic panorama cooperative identification device and identification method | |
| CN116662593A (en) | FPGA-based full-pipeline medical hyperspectral image neural network classification method | |
| CN113496138A (en) | Dense point cloud data generation method and device, computer equipment and storage medium | |
| CN110906922A (en) | Unmanned aerial vehicle pose information determining method and device, storage medium and terminal | |
| CN116805397A (en) | System and method for detecting and identifying small objects in images using machine learning algorithms | |
| CN115267762A (en) | Low-altitude slow-speed small target tracking method integrating millimeter wave radar and visual sensor | |
| CN216900172U (en) | Sample positioning navigation device suitable for scanning electron microscope and optical camera are used jointly | |
| CN213186308U (en) | Panoramic image splicing system for airborne camera array of unmanned aerial vehicle | |
| CN114280649A (en) | Comprehensive geographic information data processing system | |
| CN110175418B (en) | Satellite earth observation task planning method for simulation | |
| CN114298268A (en) | Training method of image acquisition model, image detection method, device and equipment | |
| CN207541503U (en) | A kind of unmanned plane wireless communication system based on dynamic routing technology | |
| CN212850798U (en) | Scene recognition system based on unmanned aerial vehicle cruise video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |