Satellite-borne intelligent image data processing platform based on spacecraft operating system

Abstract

The invention provides a spaceborne intelligent image data processing platform based on a spacecraft operating system. The spaceborne intelligent image data processing platform comprises a spaceborne high-performance CPU processor, a high-performance DSP processor, an FPGA processor, a high-density integrated solid-state memory and a spaceborne operating system. And the high-performance DSP processor, the FPGA processor and the high-density integrated solid-state memory are all connected with the satellite-borne high-performance CPU. The satellite-borne operating system is used for uniformly managing data of the intelligent data processing platform, and multiple APP programs run in the environment of the satellite-borne operating system. According to the invention, the on-satellite data processing capability, especially the image processing capability, of the satellite is remarkably improved, the satellite optical remote sensing data processing performed on the satellite in a preposed manner is enabled to have higher flexibility by configuring the intelligent image data processing APP, and only the processed effective information is downloaded through the satellite-ground data transmission channel, so that the data processing efficiency is improved. Therefore, the processing and application efficiency of the satellite data is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of satellite platform technology, and in particular to a satellite-borne intelligent image data processing platform and method based on a spacecraft operating system. Background Art

[0002] Remote sensing satellites have the characteristics of wide detection range and high detection efficiency, and play an important role in land and ocean observation. Optical remote sensing satellites are satellites with onboard visible light imaging cameras, hyperspectral imaging cameras and other remote sensing instruments as payloads. The ground can obtain a large number of land and sea observation photos, observation spectra and other data through optical remote sensing satellites. The observation data has the characteristics of high resolution and small distortion, and can be widely used in scientific research and industrial and agricultural production, contributing important image data to disaster prevention and mitigation, land surveys, map surveying and mapping and other fields.

[0003] However, the amount of optical remote sensing data generated by traditional optical remote sensing satellites is huge, up to 100 gigabytes. In order to reduce the transmission pressure of the back-end data transmission channel, the original observation data needs to be compressed and then transmitted. However, with the improvement of the resolution of optical remote sensing instruments, the compressed optical remote sensing data still puts a lot of pressure on the satellite-to-ground data transmission link, and has high requirements for ground receiving equipment. Therefore, based on image compression, more complex image processing of image data according to the actual needs of ground users and improving the message entropy value of the transmitted data have become a hot topic in aerospace technology research in recent years. Traditional on-board image processing often uses a separate on-board terminal to achieve this function, and the entire satellite has no information system, which is extremely limited in terms of function expansion. However, for microsatellites, due to the strict restrictions on power consumption and weight of the entire satellite, the satellite hardware functions are required to be highly integrated, light weight, and highly flexible. Therefore, the use of satellite operating systems and on-board APPs can efficiently solve the strict weight requirements and diverse functional requirements faced in the development of the current microsatellite field.

[0004] The patent document with publication number CN114513244A discloses a spacecraft integrated intelligent information system, which can realize the spacecraft integrated intelligent information system. The system consists of a service center, a mission center and a data center, and the service center, the mission center and the data center constitute an integrated intelligent information system. It is characterized by sharing a hardware resource platform and building a platform using existing standardized and universal hardware modules, including channel processing modules, storage modules, channel modules, communication modules, measurement modules, drive modules, switching modules, and power modules, thereby integrating important navigation, measurement and control, and integrated electronics of traditional satellite platforms. Compared with the present invention, the present invention adds an operating system as a software environment for data processing, which is better in software scalability than the present invention.

[0005] The patent document with publication number CN114036103A discloses a satellite-borne AI integrated electronic system architecture based on Huawei Ascend AI processor. The architecture is based on Huawei Ascend processing chip, including AI computing power module, FPGA module and satellite-borne data processing module. Its characteristics are that it adopts on-board hardware processing architecture, improves satellite computing power and intelligence, and effectively reduces satellite construction costs. Compared with the present invention, the present invention adopts hardware processing with CPU+DSP processor cluster as the core. Different from the single Ascend processor processing architecture, the architecture adopted by the present invention has better scalability.

[0006] The patent document with publication number CN114138497A discloses a satellite-borne intelligent data processing device based on a GPU core processing module, a power module, a command bus module, a data bus module, a command output module, and an MCU management module. The invention is mainly aimed at processing on-orbit payload data of micro-satellites. Compared with the present invention, the present invention adds a processing method based on a DSP processor.

[0007] The patent document with publication number CN111891398A discloses a flexible and universal intelligent satellite hardware architecture, which mainly sorts out the satellite on-orbit hardware architecture and provides a universal architecture. Compared with the present invention, the present invention adopts the CPU+DSP+FPGA mode, runs the adapted AI processing algorithm in the on-board operating system, and uses the advanced AI algorithm to process the effective data on the satellite. Summary of the invention

[0008] In view of the defects in the prior art, the object of the present invention is to provide a space-borne intelligent image data processing platform and method based on a spacecraft operating system.

[0009] According to the present invention, a satellite-borne intelligent image data processing platform based on a spacecraft operating system includes: a satellite-borne high-performance CPU processor, a high-performance DSP processor, an FPGA processor, a high-density integrated solid-state memory and a satellite-borne operating system;

[0010] The high-performance DSP processor, FPGA processor, and high-density integrated solid-state memory are all connected to the onboard high-performance CPU. The onboard operating system is used to uniformly manage the data of the intelligent data processing platform, and multiple APP programs run in the onboard operating system environment.

[0011] Preferably, the high-speed data between the high-performance CPU processor and the high-performance DSP processor, FPGA processor, and high-density integrated solid-state memory is connected via a high-speed Serdes interface, and the low-speed data is connected via an RS422 interface and a CAN bus interface;

[0012] The multiple APP programs include intelligent image processing APP, satellite service function APP, attitude and orbit control APP, and integrated space-ground network routing APP.

[0013] Preferably, the high-performance CPU processor, high-performance DSP processor, FPGA processor, and high-density integrated solid-state memory are integrated in the same device and are all connected according to the GT I / O interface, RS422 interface, and CAN bus interface of the modular integrated PCB board.

[0014] Preferably, the CPU processor has multi-threaded parallel logic program processing capabilities, and a highly stable operating system can be extended to run on the high-performance CPU processor.

[0015] Preferably, the high-performance DSP processor is a multi-core processor with fixed-point and floating-point computing capabilities. It interacts with the intelligent image processing APP running on the CPU processor, processes the image data according to the output parameters of the APP, and feeds back the processing results to the intelligent image processing APP.

[0016] Preferably, the FPGA processor is used for data interaction and data processing of the interface, and the operating system and various APP software running on the CPU processor access various interfaces through the FPGA processor.

[0017] Preferably, the high-density integrated solid-state memory is mainly used to store original image data and processed data, and at the same time stores valid data required to be stored by each APP according to the scheduling of the onboard operating system;

[0018] The effective data includes remote control and telemetry data and attitude and orbit control raw data.

[0019] Preferably, the onboard operating system provides data interfaces for various hardware accesses for the running APP program;

[0020] The intelligent image processing APP, satellite service function APP, attitude and orbit control APP, and integrated space-ground network routing APP are all carried on the onboard operating system in the form of executable programs or plug-ins. The onboard operating system chooses to execute one or more APP programs according to the needs of ground users.

[0021] Preferably, the satellite-borne operating system, intelligent image processing APP, satellite service function APP, attitude and orbit control APP, and integrated space-ground network routing APP all have the ability to be updated in orbit. The ground can change the APP program according to the latest needs and update the on-board APP in accordance with the agreed form.

[0022] According to a satellite-borne intelligent image data processing method adopted by the present invention, the satellite-borne intelligent image data processing platform based on the spacecraft operating system is adopted, and the data processing method includes:

[0023] Step S1: After the satellite is separated from the rocket, the CPU processor automatically starts up and the onboard operating system software is loaded by the boot program;

[0024] Step S2: After the onboard operating system software is started normally, the satellite service function APP, attitude and orbit control APP, and intelligent image processing APP are started in sequence according to the set software startup sequence;

[0025] Step S3: The satellite service function APP receives ground instructions, controls the optical remote sensing observation equipment to perform remote sensing observation of the ground, obtains image files and stores the image data in a high-density integrated solid-state memory;

[0026] Step S4: The satellite service function APP loads the preset image recognition processing algorithm into the DSP processor according to the set timing;

[0027] Step S5: After the image data is stored in the solid-state memory, the hardware interface access component of the operating system is called to read the image data from the solid-state memory in a certain format and sequence, and send it to the DSP processor for recognition processing;

[0028] Step S6: The DSP processor identifies the target in the image according to the parameter settings of the intelligent image processing APP, and outputs the image slice containing the target.

[0029] Step S7: The intelligent image processing APP stores the processed slices in a solid-state memory.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] 1. The present invention significantly improves the on-board data processing capability of the satellite, especially the image processing capability. By configuring an intelligent image data processing APP, the satellite optical remote sensing data processing performed on-board the satellite has higher flexibility.

[0032] 2. The present invention only transmits processed valid information through the satellite-to-ground data transmission channel, thereby effectively improving the processing and application efficiency of satellite data. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0034] Figure 1The schematic diagram of the structure of the onboard intelligent image data processing platform based on the spacecraft operating system of the present invention is shown in FIG. DETAILED DESCRIPTION

[0035] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0036] The hardware supporting system of the present invention specifically includes a satellite-borne high-performance CPU processor, a high-performance DSP processor, an FPGA processor, and a high-density integrated solid-state memory, and the software supporting system includes a satellite-borne scalable high-stability operating system, an intelligent image processing APP, a satellite service function APP, an attitude and orbit control APP, and a space-ground integrated network routing APP. Each of the APP software is carried by the operating system and communicates or accesses the hardware through a software interface.

[0037] According to the present invention, a spaceborne intelligent image data processing platform based on a spacecraft operating system is provided. Figure 1 As shown, it includes: a satellite-borne high-performance CPU processor, a high-performance DSP processor, an FPGA processor, a high-density integrated solid-state memory and a satellite-borne operating system. The high-performance DSP processor, the FPGA processor, and the high-density integrated solid-state memory are all connected to the satellite-borne high-performance CPU. The satellite-borne operating system is used to uniformly manage the data of the intelligent data processing platform, and the intelligent image data processing APP runs in the satellite-borne operating system environment.

[0038] The high-speed data between the high-performance CPU processor and the high-performance DSP processor, FPGA processor, and high-density integrated solid-state memory is connected through a high-speed Serdes interface, and the low-speed data such as remote control and telemetry is connected through an RS422 interface and a CAN bus interface. The high-performance CPU processor, high-performance DSP processor, FPGA processor, and high-density integrated solid-state memory are integrated in the same device and are connected according to the GT I / O interface, RS422 interface, and CAN bus interface of the modular integrated PCB board.

[0039] The CPU processor has multi-threaded parallel logic program processing capabilities, and the scalable high-stability operating system runs on a high-performance CPU processor.

[0040] The high-performance DSP processor is a multi-core processor with fixed-point and floating-point computing capabilities. It interacts with the intelligent image processing APP running on the CPU processor, efficiently processes the image data according to the output parameters of the APP, and feeds back the processing results to the intelligent image processing APP.

[0041] The FPGA processor is used for data interaction and data processing of the interface, and the operating system and various APP software running on the CPU processor access various interfaces through the FPGA processor.

[0042] The high-density integrated solid-state memory is mainly used to store original image data and processed data. At the same time, according to the scheduling of the onboard operating system, it stores the valid data required by each APP, including remote control and telemetry data, attitude and orbit control original data, etc.

[0043] The satellite-borne operating system is a platform operating system environment capable of carrying and executing multiple APP programs simultaneously. The operating system provides data interfaces for various types of hardware access for the running APP programs. The intelligent image processing APP, satellite service function APP, attitude and orbit control APP, and integrated space-ground network routing APP are all carried on the satellite-borne operating system in the form of executable programs or plug-ins. The operating system selects to execute one or more APP programs according to the needs of ground users. The satellite-borne operating system, intelligent image processing APP, satellite service function APP, attitude and orbit control APP, and integrated space-ground network routing APP all have the ability to update on-orbit. The ground can change the APP program according to the latest needs and update the on-board APP in the agreed form. The intelligent image processing APP is a cluster of satellite-borne APPs based on intelligent image processing algorithms. The satellite-borne operating system can load and run one or more different types of intelligent image processing APPs according to actual processing needs, thereby realizing multi-dimensional processing of optical remote sensing images.

[0044] According to a satellite-borne intelligent image data processing method provided by the present invention, the satellite-borne intelligent image data processing platform based on the spacecraft operating system is adopted, and the data processing method comprises:

[0045] Step S1: After the satellite is separated from the rocket, the CPU processor automatically starts up and the onboard operating system software is loaded by the boot program;

[0046] Step S2: After the operating system software is started normally, the satellite service function APP, attitude and orbit control APP, and intelligent image processing APP will be started in sequence according to the set software startup sequence.

[0047] Step S3: The satellite service function APP receives ground instructions, controls the optical remote sensing observation equipment to perform remote sensing observation of the ground, obtains image files, and stores the image data in a high-density integrated solid-state memory.

[0048] Step S4: The satellite service function APP loads the preset image recognition processing algorithm into the DSP according to the set timing.

[0049] Step S5: After the image data is stored in the solid-state memory, the hardware interface access component of the operating system is called to read the image data from the solid-state memory in a certain format and sequence, and send it to the DSP software for recognition processing.

[0050] Step S6: The DSP identifies the target in the image according to the parameter settings of the intelligent image processing APP, and outputs the image slices containing the target.

[0051] Step S7: The intelligent image processing APP stores the processed slices in a solid-state memory.

[0052] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, it is entirely possible to realize the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0053] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A spaceborne intelligent image data processing platform based on a spacecraft operating system, characterized in that: include: Onboard high-performance CPU processor, high-performance DSP processor, FPGA processor, high-density integrated solid-state memory and onboard operating system; The high-performance DSP processor, FPGA processor, and high-density integrated solid-state memory are all connected to the onboard high-performance CPU; the onboard operating system is used to uniformly manage the data of the intelligent data processing platform, and multiple APP programs run in the onboard operating system environment.

2. The onboard intelligent image data processing platform based on a spacecraft operating system according to claim 1, characterized in that: The high-speed data between the high-performance CPU processor and the high-performance DSP processor, FPGA processor, and high-density integrated solid-state memory is connected via a high-speed Serdes interface, and the low-speed data is connected via an RS422 interface and a CAN bus interface; The multiple APP programs include intelligent image processing APP, satellite service function APP, attitude and orbit control APP, and integrated space-ground network routing APP.

3. The onboard intelligent image data processing platform based on a spacecraft operating system according to claim 1, characterized in that: The high-performance CPU processor, high-performance DSP processor, FPGA processor, and high-density integrated solid-state memory are integrated in the same device and are all connected according to the GTI / O interface, RS422 interface, and CAN bus interface of the modular integrated PCB board.

4. The onboard intelligent image data processing platform based on a spacecraft operating system according to claim 1, characterized in that: The CPU processor has multi-threaded parallel logic program processing capabilities and can expand a high-stability operating system to run on the high-performance CPU processor.

5. The onboard intelligent image data processing platform based on a spacecraft operating system according to claim 1, characterized in that: The high-performance DSP processor is a multi-core processor with fixed-point and floating-point computing capabilities. It interacts with the intelligent image processing APP running on the CPU processor, processes the image data according to the output parameters of the APP, and feeds back the processing results to the intelligent image processing APP.

6. The onboard intelligent image data processing platform based on a spacecraft operating system according to claim 1, characterized in that: The FPGA processor is used for data interaction and data processing of the interface, and the operating system and various APP software running on the CPU processor access various interfaces through the FPGA processor.

7. The onboard intelligent image data processing platform based on a spacecraft operating system according to claim 1, characterized in that: The high-density integrated solid-state memory is mainly used to store original image data and processed data, and at the same time stores valid data required by each APP according to the scheduling of the onboard operating system; The effective data includes remote control and telemetry data and attitude and orbit control raw data.

8. The onboard intelligent image data processing platform based on a spacecraft operating system according to claim 1, characterized in that: The onboard operating system provides data interfaces for various hardware accesses for running APP programs; The intelligent image processing APP, satellite service function APP, attitude and orbit control APP, and integrated space-ground network routing APP are all carried on the onboard operating system in the form of executable programs or plug-ins. The onboard operating system chooses to execute one or more APP programs according to the needs of ground users.

9. The onboard intelligent image data processing platform based on a spacecraft operating system according to claim 2, characterized in that: The satellite-borne operating system, intelligent image processing APP, satellite service function APP, attitude and orbit control APP, and integrated space-ground network routing APP all have the ability to be updated in orbit. The ground can change the APP program according to the latest needs and update the on-board APP in accordance with the agreed form.

10. A method for processing satellite-borne intelligent image data, characterized in that: Using the onboard intelligent image data processing platform based on a spacecraft operating system as described in any one of claims 1 to 9, the data processing method comprises: Step S1: After the satellite is separated from the rocket, the CPU processor automatically starts up and the onboard operating system software is loaded by the boot program; Step S2: After the onboard operating system software is started normally, the satellite service function APP, attitude and orbit control APP, and intelligent image processing APP are started in sequence according to the set software startup sequence; Step S3: The satellite service function APP receives ground instructions, controls the optical remote sensing observation equipment to perform remote sensing observation of the ground, obtains image files and stores the image data in a high-density integrated solid-state memory; Step S4: The satellite service function APP loads the preset image recognition processing algorithm into the DSP processor according to the set timing; Step S5: After the image data is stored in the solid-state memory, the hardware interface access component of the operating system is called to read the image data from the solid-state memory in a certain format and sequence, and send it to the DSP processor for recognition processing; Step S6: The DSP processor identifies the target in the image according to the parameter setting of the intelligent image processing APP, and outputs the image slice containing the target; Step S7: The intelligent image processing APP stores the processed slices in a solid-state memory.

Images