Relay tracking application method and system for large and medium-sized ships in open sea

Abstract

The invention discloses a relay tracking application method and system for large and medium-sized ships in open seas, and the method comprises the following steps: S1, obtaining the current position information of a target ship, and delimiting a circular region of interest based on the current position information; s2, performing overhead satellite calculation within half an hour based on the region of interest; the current position of the target ship is determined for uploading tasks to satellites passing through the top attention area in a short time; after receiving the AIS signal of the target ship, the micro-nano satellite transmits the AIS signal to the ground; and S3, selecting to enter a regular imaging tracking mode under the condition of stable AIS signal receiving or a search imaging tracking mode under the condition of short-time AIS signal loss according to the AIS signal receiving condition, and carrying out relay tracking on the target ship. The method has the advantages that the remote sensing image data transmission quantity for carrying out the tasks and the time consumed for completing the tasks can be greatly compressed, and the requirements of high-timeliness tasks such as high-sea far-field ship escorting and marine ship searching and rescuing are met.

Description

Technical Field

[0001] The present invention relates to the field of remote sensing image intelligent interpretation and application technology, and in particular to a method and system for relay tracking application of large and medium-sized ships in the open sea. Background Art

[0002] Carrying out escort support for distant sea and distant areas ships, emergency search and rescue of ships at sea in a wide area, etc. based on remote sensing is of great significance to safeguarding maritime rights and interests, and ensuring national and people's livelihood security. At present, low-orbit satellite constellations are developing rapidly, and many low-orbit satellite constellation missions have been proposed and launched into orbit; with the support of on-board intelligent processing and inter-satellite communication technology, through multi-satellite coordination, low-orbit micro-nano satellite constellations support various space-based accompanying support missions in orbit, such as relay tracking of distant sea ships. Space-based relay tracking of distant sea ships refers to the use of multiple earth observation satellites passing overhead near the position of large and medium-sized ships far away from land and in the open sea, and the acquisition of AIS signals or remote sensing imaging of ships multiple times and continuously at short time intervals. By processing the acquired information, the ship's geographic location, identity and other information can be continuously mastered.

[0003] In recent years, the rise of artificial intelligence has led to rapid development and technological innovation in fields such as computer vision and natural language processing. In the field of remote sensing, many intelligent interpretation methods based on deep learning have been proposed, and breakthroughs and applications have been made in the fields of remote sensing target detection, target fine identification, and target segmentation. Using lightweight intelligent interpretation algorithms deployed on remote sensing satellites to detect and finely identify ships at sea is a key means to achieve relay tracking of ships. This can greatly reduce the amount of satellite-to-ground data transmission, greatly reduce the workload of personnel, and meet the needs of fast processing and high-efficiency application tasks. At the same time, it is also the only way to develop intelligent satellite systems that are independent of ground stations and have autonomous intelligent processing capabilities on orbit.

[0004] However, searching, detecting and identifying ships on a wide sea surface remote sensing image by using the traditional sliding window to traverse remote sensing images is undoubtedly like looking for a needle in a haystack; this method will consume a large amount of computing and storage resources of the satellite platform, and the timeliness of information acquisition is poor, which seriously restricts the benefits of satellite applications. The Automatic Identification System (AIS) is a marine radio communication system that can automatically broadcast ship dynamic information (position, speed, heading, etc.) and static information (ship name, nationality, call sign, draft, etc.). Due to the mandatory installation and self-reporting characteristics of AIS, AIS has been gradually promoted and applied to various aspects such as sea area perception and sea surface monitoring, and its marine application value has become increasingly prominent. The satellite-borne ship identification subsystem (satellite-borne AIS system) equipped on the remote sensing satellite can receive, process and extract the AIS information transmitted by the ship AIS equipment in real time on the satellite, and realize the recognition of ship target attributes and location acquisition. The current coverage range of satellite-borne AIS receivers is about 2000km (500km orbit altitude) and the positioning accuracy is better than 20 meters (GPS positioning accuracy). Therefore, combining AIS signal acquisition and on-orbit remote sensing imaging, using the ship positioning information provided by AIS as a guide, designing the search direction and area range in a targeted manner, and performing on-orbit intelligent interpretation of the remote sensing images of the area, is a better way to conduct wide-area maritime ship target search, detection, and identification.

[0005] With the continuous development of satellite mass production capacity and inter-satellite communication network technology, the earth observation satellite system is gradually evolving towards large-scale, flexible and sustainable development. Building real-time remote sensing satellite constellations based on star clusters and inter-satellite high-speed communications has become the current mainstream. By giving full play to the advantages of star cluster collaboration and combining on-orbit intelligent processing to reduce time delays in each link, improve the timeliness and accuracy of data processing, and realize fully automated and intelligent near-real-time star cluster intelligent services, it can lay the foundation for realizing all-day, all-weather, fast and efficient intelligent services for earth observation.

[0006] Therefore, the present invention proposes a method and system for relay tracking of large and medium-sized ships in the open sea based on multi-source information support, high and low orbit multi-satellite collaboration, and space-ground human-machine collaboration. Low-orbit micro-nano remote sensing satellites are equipped with onboard AIS receiving payloads. In addition to remote sensing imaging capabilities, satellites also have the ability to receive, analyze and compare AIS signals. By using onboard AIS receivers and optical remote sensing imaging payloads, the relay tracking of large and medium-sized ships in the open sea is achieved through the fusion and complementarity of ship AIS information and optical remote sensing imaging information. Summary of the invention

[0007] The object of the present invention is to provide a method and system for relay tracking applications of large and medium-sized ships in the open sea, so as to solve the above-mentioned problems existing in the prior art.

[0008] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0009] A method for relay tracking application of large and medium-sized ships in the open sea, comprising the following steps:

[0010] S1. Draw a focus area based on the current position information of the target ship, and calculate the satellites that will pass through the focus area within half an hour based on the focus area; assign tasks to satellites that will pass through the focus area in the short term to determine the current position of the target ship; after receiving the AIS signal of the target ship, the micro-nano satellite transmits it to the ground;

[0011] S2. When the AIS signal reception is stable, enter the periodic imaging tracking mode under the condition of stable AIS signal reception, and relay track the target ship. If the AIS signal is lost during operation, switch to the search imaging tracking mode under the condition of short-term loss of AIS signal; When the AIS signal reception is short-term loss, enter the search imaging tracking mode under the condition of short-term loss of AIS signal, and relay track the target ship. If the AIS signal is restored during operation, switch to the periodic imaging tracking mode under the condition of stable AIS signal reception;

[0012] In both modes, if the planned preset running time is exceeded, the process returns to step S1, and the task planning for the next preset running time is performed with reference to the updated ship position, otherwise, the current mode is maintained and continued to run.

[0013] Preferably, step S1 specifically includes the following contents:

[0014] S11. If the time since the last satellite pass is more than half an hour, a focus area is delineated with the current navigation position of the target ship as the center, and the focus area is used as a reference. Based on the coverage of the satellite-borne AIS receiver and the satellite orbit parameters, the low-orbit remote sensing satellite that will pass over the focus area in the next half an hour and have an observation side swing angle of less than 45° is calculated.

[0015] S12, assigning a task to the satellites that will be over the area of ​​interest in the short term, i.e., receiving and analyzing the AIS signals of ships, obtaining the identities of the ships in the AIS information by comparison, and determining the current position of the target ship;

[0016] S13. After the micro-nano satellite stably and continuously receives and identifies the AIS signal of the target ship, it will transmit the information to the ground through the inter-satellite topology communication link or the geostationary orbit communication satellite at a regular interval.

[0017] Preferably, the periodic imaging tracking mode under the condition of stable AIS signal reception specifically includes the following contents: A1, turning on the satellite AIS receiver passing over the circular area of ​​interest;

[0018] A2: The satellite that recognizes the AIS signal of the target ship will transmit the latest navigation information of the ship to the ground every minute;

[0019] A3, check whether it is the scheduled imaging time, if not, return to A1 to execute; if it is the scheduled imaging time, start the imaging tracking process;

[0020] A4. Predict the future position of the target ship based on the most recently acquired state of the target ship, and plan and upload the imaging mission to the overhead satellite;

[0021] A5, the overhead satellite receives the AIS signal of the target ship and images the target ship's location area;

[0022] A6. Overhead satellites use the position of the target ship at the time of imaging as the center and perform intelligent detection and identification of the target ship in different areas from the inside to the outside;

[0023] A7. If the target ship is not identified, return to A3 for execution; if the target ship is identified, transmit the target ship slice image and the target ship AIS information data acquired at the imaging time to the ground, and update the navigation status of the target ship;

[0024] A8. If the target ship tracking mission is not completed, return to A1 for execution; otherwise, end.

[0025] Preferably, step A6 is specifically as follows: taking the real-time position of the target ship AIS broadcast at the imaging moment as the center, 1024*1024 pixels as an intelligent detection and identification unit range, forming multiple candidate detection and identification units, and adjacent candidate detection and identification units overlap by 25% area; starting from the center, detection and identification are performed layer by layer and unit by unit from the inside to the outside; the candidate detection and identification unit that is more consistent with the heading direction of the target ship and the closer the distance is, the higher the detection and identification priority is, and therefore the detection and identification is performed first.

[0026] Preferably, the detection and recognition is implemented based on a deep learning network, and the deep learning network is an improved YOLO_v10 network; wherein,

[0027] The scale of the network input image is 1024×1024×3, and the scale of the prediction output layer is 128×128, 64×64, and 32×32;

[0028] The network uses the Circular Smooth Label algorithm to modify the target detection into the rotation box detection; the network output part uses the non-maximum suppression algorithm for rotating target applications;

[0029] After the HEAD module at the top layer of the network and before the prediction layer, a plug-and-play lightweight convolutional block attention module is added, which combines the channel attention mechanism and the spatial attention mechanism.

[0030] Preferably, the search imaging tracking mode in the case of a short-term loss of the AIS signal specifically includes the following contents:

[0031] B1. Based on the recent navigation status of the target ship, predict the possible route of the target ship in the next 15 minutes;

[0032] B2. Using the predicted target ship route as a reference, calculate the satellites that will pass over the target ship within 15 minutes; select three satellites with an interval of nearly 5 minutes, and plan and assign imaging tasks to the selected imaging satellites;

[0033] B3. The three satellites image the predicted position in turn, and use the predicted position of the target ship at the time of imaging as the center to perform intelligent detection and identification of the target ship in different areas from the inside to the outside;

[0034] B4. If one of the three satellites detects and identifies the target ship, the target ship slice image and imaging time information data will be transmitted to the ground, and the navigation status of the target ship will be updated;

[0035] B5. If the three satellites fail to search and identify the target ship, the mission is terminated, otherwise it returns to B3 for execution; B6. If the target ship tracking mission is not completed, it returns to B1 for execution, otherwise it ends the mission.

[0036] Preferably, step B3 specifically comprises:

[0037] When each satellite performs intelligent detection and identification of target ships in remote sensing images, it takes the predicted position of the target ship at the current moment of imaging as the center, and searches from the inside to the outside layer by layer and unit by unit. The unit with the more consistent heading direction and the closer distance to the target ship has a higher detection and identification priority, and is detected and identified first.

[0038] Assume S n-5 To S n-1 Sn is the actual position of the target ship when it was searched and identified most recently, Sn-1 is the actual position of the target ship when it was searched and identified most recently; S n-1 S' is the track line of uniform straight-line navigation, starting from the actual position of the target ship when it was last searched and identified, with its heading as the navigation direction and the average speed as the navigation speed; S n-1 The three positions PA, PB, and PC on S' are the predicted positions of the target ship corresponding to the imaging moments of the three satellites selected with an interval of nearly 5 minutes. If the satellite imaging at the PA position fails to search and identify the target ship, and the satellite imaging at the PB position searches and identifies the target ship, the actual position of the target ship is S n Then the actual position S of the target ship when it was last searched and identified will be used as the nAs the starting point, with its current heading as the navigation direction and the average speed as the navigation speed, it sails in a straight line at a uniform speed to obtain the new track line S n S; thus repeating the above process to achieve target ship search imaging and tracking when the AIS signal is lost for a short time.

[0039] Preferably, in step S2, when the periodic imaging tracking mode is in operation under the condition of stable AIS signal reception, if the ground gives an end-task instruction, the current task is stopped, otherwise, the current mode is maintained and continued to operate;

[0040] When the AIS signal is lost for a short time and the search imaging mode is in operation, if the ground gives an instruction to end the mission, the current mission will be stopped. Otherwise, the ship target search imaging tracking situation will be judged first. If the target ship is lost, the current mission will be stopped. If the target ship can be tracked by predicting the position combined with the imaging search, the current mode will be maintained.

[0041] The present invention also aims to provide a system for relay tracking of large and medium-sized ships in the open sea, which can implement the above-mentioned method. The system includes a remote sensing image access unit, a satellite-borne AIS receiver, a remote sensing image intelligent processing unit and an integrated interface baseboard.

[0042] The remote sensing image access unit is composed of a field programmable gate array, a random access memory and a solid state drive. On the one hand, it provides a high-speed data transmission channel for reading the original remote sensing image from the optical remote sensing imaging payload, and also provides a high-speed data transmission channel for the flow of the original remote sensing image between the remote sensing image intelligent processing unit and the satellite platform. On the other hand, it is used to store the original remote sensing image, the remote sensing image slices after intelligent processing, and the operating system, software and models required for intelligent processing.

[0043] The satellite-borne AIS receiver receives the ship's AIS signal and completes data analysis;

[0044] The remote sensing image intelligent processing unit is composed of a central processing unit and a graphics processing unit, and mainly provides an algorithm operation platform for remote sensing image preprocessing and intelligent detection and identification of ships in remote sensing images. It runs the Linux kernel operating system and is equipped with image preprocessing algorithms and deep learning algorithms related to intelligent detection and identification of large and medium-sized ship targets, providing powerful program control management, data flow processing, and parallel computing functions for image intelligent processing.

[0045] The integrated interface baseboard consists of a power control unit and multiple types of interface channels. On the one hand, it provides power control for the above-mentioned components in the system and provides interface management with the satellite platform. On the other hand, it provides mechanical installation support for the above-mentioned components, supports modular and stacked design, and is easy to realize personalized functional combination design.

[0046] Preferably, the files stored in the solid-state hard disk include the operating system, software programs and dependent libraries required for the application program to run in the remote sensing image intelligent processing unit; relevant parameter files for preprocessing newly acquired remote sensing images; remote sensing images after preprocessing; deep learning network structures, model parameter files and configuration files for ship target detection and recognition;

[0047] The random access memory is used to provide a high-speed cache for the reading and writing operations of the original remote sensing image data, the pre-processed remote sensing image and the result data after intelligent processing.

[0048] The beneficial effects of the present invention are as follows: (1) Compared with the traditional wide-area ship search and identification, the present invention integrates the ship AIS signal data and satellite remote sensing image data, and uses the AIS positioning data to guide the imaging satellite to complete the ship target search and identification faster and autonomously and intelligently on orbit; compared with the cumbersome data processing and application processes such as the traditional remote sensing data downlink, ground processing, and uplink control, the present invention can greatly reduce the amount of remote sensing image data transmission and the time required to complete the task, and support the high-timeliness task requirements such as the escort of ships in the distant seas and the search and rescue of ships at sea. (2) The present invention proposes a ship tracking process based on AIS information-guided remote sensing imaging, and designs the tracking process according to the AIS signal status, divided into two situations of "stable reception of AIS signal" and "short-term loss of AIS signal" and their state conversion. The regular imaging tracking process under the condition of stable AIS reception can achieve the ship target tracking capability all day, all weather, and globally; the search imaging tracking process under the condition of short-term loss of AIS signal can achieve the ship target tracking capability under good weather conditions (no clouds or thin clouds) and daytime conditions and globally. The tracking modes in the two situations can achieve good conversion, and the ship target tracking task can be smoothly executed. (3) The system proposed by the present invention has a simple composition and low cost, and can provide a modular and intelligent solution for micro-satellites to realize relay tracking of large and medium-sized ships at sea. The system has good portability, compatibility and scalability. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a flow chart of a method for relay tracking application in an embodiment of the present invention;

[0050] Figure 2 is a flow chart of a periodic imaging tracking mode under the condition of stable reception of AIS signals in an embodiment of the present invention;

[0051] Figure 3 Schematic diagram of a method for searching and identifying ship targets in remote sensing images guided by position information in an embodiment of the present invention;

[0052] Figure 4is a flow chart of the search imaging tracking mode in the case of a short-term loss of the AIS signal in an embodiment of the present invention;

[0053] Figure 5 Schematic diagram of a ship target search and identification method guided by ship track prediction in an embodiment of the present invention;

[0054] Figure 6 is a structural diagram of a deep learning network in an embodiment of the present invention;

[0055] Figure 7 It is a structural diagram of a system for relay tracking application in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation methods described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] At present, satellite platforms and payload technologies, communication technologies, etc. related to low-orbit micro-nano remote sensing satellites are developing rapidly. Low-orbit micro-nano remote sensing satellites have technical capabilities such as high-resolution imaging, wide-bandwidth imaging, high-speed intersatellite communication, and multi-payload compatibility; combined with the empowerment of on-orbit intelligent processing technology, large-scale remote sensing satellite constellations can achieve global high revisit frequency, on-orbit autonomous intelligent processing, multi-source information fusion applications, and near-real-time data downlink. The above-mentioned capability advantages of large-scale remote sensing satellite constellations can provide solutions for tasks with high timeliness requirements, such as carrying out escort support for distant sea and remote areas of ships based on space-based information, and emergency search and rescue of ships at sea in a wide area. Therefore, the present invention proposes a method and system for relay tracking applications of large and medium-sized ships in the distant sea based on multi-source information support, high and low orbit multi-satellite collaboration, and space-ground human-machine collaboration. Low-orbit micro-nano remote sensing satellites are equipped with onboard AIS receiving payloads. In addition to remote sensing imaging capabilities, satellites also have the ability to receive, analyze and compare AIS signals. By using satellite-borne AIS receivers and optical remote sensing imaging payloads, the relay tracking of large and medium-sized ships in the open sea can be achieved through the fusion and complementation of ship AIS information and optical remote sensing imaging information. Figure 1 As shown, in this embodiment, the method of the present invention includes the following four parts:

[0058] 1. Obtaining the target ship’s location information

[0059] Get the current position (latitude and longitude) information of the target ship.

[0060] II. Calculation of over-the-top satellites based on the area of ​​interest and AIS signal reception and verification tasks

[0061] According to the current position information of the target ship, a focus area is drawn, and satellites passing overhead within half an hour are calculated based on the focus area; satellites passing overhead in the focus area are registered in the short term to determine the current position of the target ship; after the micro-nano satellite receives the AIS signal of the target ship, it is transmitted to the ground. Specifically, it includes the following contents:

[0062] 2.1. If the time since the last satellite overpass is more than half an hour, a focus area (e.g., a circular area with a diameter of 20 km) is delineated with the current navigation position of the ship target as the center. Based on this area and the coverage range of the satellite-borne AIS receiver, satellite orbit parameters and other prior information, the low-orbit remote sensing satellite that will continue to overpass the focus area in the next half an hour (the AIS signal reception range covers the focus area) and the observation side swing angle is less than 45° is calculated.

[0063] 2.2. The above-mentioned satellites that will be passing over the area of ​​concern in the short term are assigned a task, namely, to receive and analyze the AIS signals of ships, obtain the identity of the ship in the AIS information by comparison, and determine the current position of the target ship; the signal reception coverage of the satellite-borne AIS receiver is wide (the satellite-borne AIS signal reception range at an orbital altitude of 500km can reach more than 2000km). Under the background of the star cluster, multiple satellites can achieve multiple coverage of the area of ​​concern centered on the ship, and can achieve continuous grasp of the ship's AIS signals.

[0064] 2.3. After the micro-nano satellite stably and continuously receives and identifies the AIS signal of the target ship, it will transmit the information to the ground at a regular interval (e.g., once per minute) through the inter-satellite topology communication link or the geostationary orbit communication satellite.

[0065] 3. Select the corresponding mode to relay track the target ship according to the AIS signal reception situation

[0066] When the AIS signal is stably received, the system enters the periodic imaging tracking mode under the condition of stable AIS signal reception, and relays the target ship. If the AIS signal is lost during operation, the system switches to the search imaging tracking mode under the condition of short-term loss of the AIS signal. When the AIS signal is lost for a short time, the system enters the search imaging tracking mode under the condition of short-term loss of the AIS signal, and relays the target ship. If the AIS signal is restored during operation, the system switches to the periodic imaging tracking mode under the condition of stable AIS signal reception. In these two modes, if the preset running time is exceeded, the system returns to step S2, and uses the updated ship position as a reference to perform the task planning for the next preset running time. Otherwise, the system maintains the current mode and continues to run.

[0067] When operating in the periodic imaging tracking mode with stable AIS signal reception, if the ground gives an end-mission command, the current mission will be stopped, otherwise, the current mode will be maintained; when operating in the search imaging mode with short-term AIS signal loss, if the ground gives an end-mission command, the current mission will be stopped, otherwise, the ship target search imaging tracking situation will be judged first. If the target ship is lost, the current mission will be stopped. If the target ship can be tracked by predicting the position combined with imaging search, the current mode will be maintained.

[0068] In this embodiment, Figure 2 As shown in the figure, the periodic imaging tracking mode under the condition of stable AIS signal reception specifically includes the following contents:

[0069] (1) The satellite AIS receivers passing over the circular area of ​​interest are turned on; under the conditions of the micro-nano constellation, coupled with the wide coverage of the satellite-borne AIS signal reception, multiple satellites can continuously acquire, analyze and identify the AIS signals of the target ship.

[0070] (2) Satellites that recognize the target ship's AIS signal will transmit the latest acquired ship navigation information, such as the ship's position, heading, speed, etc., to the ground every minute through inter-satellite high-speed communication or geostationary orbit communication satellites.

[0071] (3) Check whether it is time for scheduled imaging (once every 10 minutes). If it is not time for scheduled imaging, return to A1 for execution; if it is time for scheduled imaging, start the imaging tracking process.

[0072] (4) Based on the most recently acquired ship status, assuming that the ship is sailing in a straight line at a uniform speed approximately in accordance with the most recently acquired heading and speed, the position of the ship at a certain moment in the future is predicted. This moment is the moment when the satellite that will pass over this position is closest to the predicted position of the target ship. In this way, the satellite most suitable for remote sensing imaging tasks can be selected; the remote sensing imaging task is assigned to the satellite that undertakes the imaging tracking task. The imaging payload startup time can be selected from the calculated time. The imaging side swing angle is determined according to the real-time position of the target ship obtained by the satellite at that moment. The satellite can perform a rough posture maneuver in advance according to the real-time position of the target ship to ensure that the target ship is located near the center of the remote sensing image.

[0073] (5) The satellite that has received the imaging mission instruction adjusts the satellite attitude according to the AIS information of the target ship that is continuously received. The goal is to make the target ship within the vicinity of the remote sensing image center. Before the imaging start time, the satellite attitude will be stabilized in advance to ensure the imaging quality. At the planned imaging time, the satellite remote sensing payload will start imaging and record the AIS information of the target ship obtained at the imaging time.

[0074] (6) The acquired remote sensing images are pre-processed on the imaging satellite. Based on the AIS information of the target ship acquired at the time of imaging, the position, heading, speed and other information of the target ship can be obtained. With the position of the target ship at the time of imaging as the center, the target ship is intelligently detected and identified in different areas from the inside to the outside.

[0075] The intelligent detection and recognition in this process adopts the ship target search and recognition method in the remote sensing image guided by the position information. The specific method is as follows: Figure 3 As shown in the figure, point D is the real-time position of the target ship broadcast by the AIS at the moment of imaging, and the error between this position and the actual position is better than 20 meters. With position D as the center, 1024*1024 pixels are an intelligent detection and identification unit range, forming 9 candidate detection and identification units, and adjacent monitoring and identification units overlap by 25% area. The numbers 1-6 in the box in the figure show the priority order of detection and identification, and the smaller the number, the higher the priority. The unit at position D has the highest priority and is detected and identified first. As can be seen from the figure, the unit with a more consistent heading direction and a closer distance to the target ship has a higher detection and identification priority, so it is detected and identified first.

[0076] The above detection and recognition process relies on the deep learning network, which is improved based on the YOLO_v10 network. Compared with the YOLO_v10 network, the deep learning network for the detection and recognition of large and medium-sized ships at sea has the following improvements:

[0077] (1) The scale of the network input image is 1024×1024×3, and the scale of the prediction output layer is 128×128, 64×64, and 32×32.

[0078] (2) Using the Circular Smooth Label (CSL) algorithm, the target detection is modified to rotated box detection to achieve a better envelope of the rotating target. At the same time, the non-maximum suppression algorithm (NMS) of the network output part is modified accordingly to the non-maximum suppression algorithm NMS_obb algorithm for rotating target applications.

[0079] (3) A plug-and-play lightweight Convolutional Block Attention Module (CBAM) is added after the top-level HEAD module and before the prediction layer. This attention module combines the channel attention mechanism and the spatial attention mechanism, which can promote the representation ability of the convolutional neural network in the feature extraction process, making the model pay more attention to the significant features that play a greater role in supporting the detection and identification of target ships, thereby improving the detection and identification performance.

[0080] (7) If the target ship is not identified, the process returns to step (3) for execution; if the target ship is identified, the target ship slice image and the target ship AIS information data acquired at the time of imaging are transmitted to the ground via an intersatellite communication link or a geostationary orbit communication satellite; the navigation status of the target ship is updated, including the slice image, position, heading, speed, etc.

[0081] (8) If the target ship tracking mission has not been completed, return to (1) to execute, otherwise end.

[0082] In this embodiment, in the periodic imaging tracking mode under the condition of stable reception of AIS signals, under the guidance of obtaining the real-time position of the ship by using the AIS signal, the imaging satellite can be scheduled in near real time to image the area where the ship is located regularly (such as every 10 minutes), and the ship target detection, identification and comparison confirmation can be achieved through on-board intelligent processing. If the weather conditions are good (such as cloudless and thin cloud conditions, daytime), after accurately identifying and confirming the ship, the target ship slice image can be transmitted to the ground through the inter-satellite topological communication link or the geostationary orbit communication satellite; if the target ship cannot be detected and identified due to poor weather (such as thick and dense cloud conditions, night), but since the satellite can stably receive the target ship AIS signal at this time, it is considered that the target ship is in normal condition, and imaging can be performed without other supplementary means.

[0083] In this embodiment, Figure 4 As shown in the figure, the search imaging tracking mode in case of short-term loss of AIS signal specifically includes the following contents:

[0084] (1) Based on the target ship's most recent navigation status, predict the target ship's possible route within the next 15 minutes; the predicted route is approximately a uniform straight-line navigation with the most recently acquired ship's heading and speed as the initial state.

[0085] (2) Using the predicted target ship route as a reference, calculate the number of satellites that will pass over the target ship within 15 minutes. That is, calculate the time, predicted ship position, and satellite position corresponding to the time when the passing satellite is closest to the predicted position of the target ship. Select three satellites with an interval of nearly 5 minutes as satellites for the imaging search and tracking mission.

[0086] The satellite responsible for search, imaging and tracking tasks is assigned a remote sensing imaging task. The imaging payload startup time can be selected from the time calculated above, and the imaging side swing angle is determined according to the predicted position of the target ship. The satellite can perform pre-position maneuvers based on the predicted position of the target ship to ensure that the target ship is near the center of the remote sensing image.

[0087] (3) The three satellites responsible for search, imaging and tracking tasks complete the pre-processing of the acquired remote sensing satellite images on board; with the predicted position of the target ship at the time of imaging as the center, the target ship is intelligently detected and identified in different areas from the inside to the outside.

[0088] The intelligent detection and recognition in this process adopts the ship target search and recognition method guided by ship trajectory prediction. The specific method is as follows: Figure 5 As shown, S n-5 To S n-1 Sn is the actual position of the target ship when it was searched and identified most recently, Sn-1 is the actual position of the target ship when it was searched and identified most recently; S n-1 S' is the track line of uniform straight-line navigation, starting from the actual position of the target ship when it was last searched and identified, with its heading as the navigation direction and the average speed as the navigation speed; S n-1 The three positions PA, PB, and PC on S' are the predicted positions of the target ship corresponding to the imaging time of the three satellites selected with an interval of nearly 5 minutes. When the satellite performs intelligent detection and identification of the target ship in the remote sensing image, it takes the predicted position of the target ship at the current imaging moment as the center and searches from the inside to the outside layer by layer and unit by unit (similar to Figure 3 As shown in the figure, the unit with the more consistent heading direction and closer distance to the target ship has a higher detection and identification priority, and is detected and identified first. Figure 5 A typical possible result is given in Figure 1, that is, the satellite imaging the PA position fails to search and identify the target ship, the satellite imaging the PB position searches and identifies the target ship, and the actual position of the target ship is S n Therefore, the next step is to use the actual position S of the target ship when it was last searched and identified. n As the starting point, with its current heading as the navigation direction and the average speed as the navigation speed, it sails in a straight line at a uniform speed to obtain the new track line S n S; thus repeating the above process to achieve target ship search imaging and tracking when the AIS signal is lost for a short time.

[0089] (4) If one of the three satellites detects and identifies the target ship, the target ship slice image and imaging time information data are transmitted to the ground through the inter-satellite communication link or the geostationary orbit communication satellite; the navigation status of the target ship is updated, including the slice image and position. The target heading information can also be obtained based on the slice image. By comparing the position and time of the target ship identified in the last search, the average speed and other information of the target ship can be roughly obtained.

[0090] (5) If none of the three satellites can find the target ship, the mission ends; otherwise, the process returns to step (3);

[0091] (6) If the target ship tracking mission has not been completed, return to (1) to execute, otherwise the mission is terminated.

[0092] In this embodiment, in the search imaging tracking mode under the condition of short-term loss of AIS signal, when more than 3 overhead satellites cannot receive the AIS signal of the target ship, the imaging means is activated to search for the target ship to achieve tracking and accompanying. Under the background of the star cluster, the ship's running direction and position are predicted based on the recently received information such as the ship's target position and heading, and the fastest overhead micro-nano satellite is determined based on this information. After the micro-nano satellite is imaged, the target ship will be searched, identified and confirmed in the remote sensing image in a layered manner from the inside to the outside with the predicted position of the target ship as the center; the current speed and heading of the target ship are updated and calculated based on the target's current position and the last moment's position information, the target detection orientation and other information. After confirming the identity of the target ship, the slice image and navigation status information (speed, heading, etc.) of the target ship are transmitted to the ground in a timely manner through the intersatellite topology communication link or the geostationary orbit communication satellite. If the weather conditions are good (such as cloudless and thin cloud conditions, daytime), the target ship relay tracking is achieved through the above-mentioned "position prediction" and "search and identification" process methods. If the weather conditions are poor (such as thick clouds or at night), consider dispatching radar imaging satellites to conduct imaging searches (because the present invention focuses on using AIS signals as the main method and optical remote sensing imaging as the auxiliary method to solve the tracking and accompanying tasks of target ships under good weather conditions, the relay tracking of target ships based on radar imaging under poor weather conditions is not described in detail in the present invention).

[0093] In this embodiment, Figure 7 As shown, a system for relay tracking applications of large and medium-sized ships in the open sea is also provided. The system consists of four parts: a remote sensing image storage and access unit, a satellite-borne AIS receiver, a remote sensing image intelligent processing unit and an integrated interface baseboard.

[0094] (1) The remote sensing image access unit is composed of a field programmable gate array (FPGA), a random access memory (RAM), and a solid-state drive (SSD). On the one hand, it provides a high-speed data transmission channel for reading the original remote sensing images from the optical remote sensing imaging payload, and also provides a high-speed data transmission channel for the flow of original remote sensing images between the remote sensing image intelligent processing unit and the satellite platform. On the other hand, it is used to store the original remote sensing images (read from the remote sensing imaging payload), remote sensing image slices after intelligent processing (output from the remote sensing image intelligent processing unit), and the operating system, software, and models required for intelligent processing.

[0095] The remote sensing image access unit is connected to the remote sensing image intelligent processing unit and the integrated interface baseboard through a high-speed LVDS communication interface, which supports the remote sensing image intelligent processing unit to read remote sensing image data from the solid-state drive for pre-processing and intelligent detection and recognition applications, supports the processed data to be written and stored into the solid-state drive, and supports the satellite platform to read relevant data from the optical remote sensing imaging payload or solid-state drive.

[0096] The solid-state drive (SSD) is used to store the following files: ① Basic files such as the operating system, software programs, and dependent libraries required for the operation of applications in the remote sensing image intelligent processing unit; ② Parameter files related to the preprocessing (radiation correction and geometric correction) of newly acquired remote sensing images; ③ Remote sensing images after preprocessing; ④ Deep learning network structures, model parameter files, and configuration parameter files used for ship target detection and recognition; ⑤ After intelligent processing, cropped ship target slice images, detection and recognition result files, and other achievement data.

[0097] Random access memory (RAM) is used to provide high-speed cache for reading and writing operations of original remote sensing image data, pre-processed remote sensing images, and intelligently processed result data.

[0098] (2) Satellite-borne AIS receiver is a receiving device for receiving ship AIS signals. Its receiving antenna is installed on the outer layer of the satellite structure and is connected to the satellite-borne AIS receiver via a radio frequency cable. The device uses commercial off-the-shelf (COTS) products and performs management control and data exchange through the CAN interface.

[0099] (3) Remote sensing image intelligent processing unit, which consists of a central processing unit (CPU) and a graphics processing unit (GPU), mainly provides an algorithm operation platform for remote sensing image preprocessing, intelligent detection and identification of ships in remote sensing images, etc. This unit runs the Linux kernel operating system and is equipped with image preprocessing (radiation correction, geometric correction, etc.) algorithms and deep learning algorithms related to intelligent detection and identification of large and medium-sized ship targets. It provides powerful program control management, data flow processing, and parallel computing functions for image intelligent processing.

[0100] (4) The integrated interface baseboard consists of a power control unit (PCU) and multiple types of interface channels. On the one hand, it provides power control for the above-mentioned components in the system and provides interface management between them and the satellite platform. On the other hand, it provides mechanical installation support for the above-mentioned components, supports modular and stacked design, and is easy to realize personalized functional combination design. The power control of the power control unit is managed by the satellite platform through the CAN1 interface. By adjusting the external power provided by the satellite platform, it can provide the required power supply voltage and current for each unit in the system, and provide power control management functions according to the CAN communication instructions of the satellite platform. The integrated interface baseboard also provides multiple and multiple types of data interaction interfaces such as CAN and LVDS to support the expansion of system payloads or units; the remote sensing image access unit, the satellite-borne AIS receiver, and the remote sensing image intelligent processing unit are interconnected through CAN2 to support the state information data interaction between each payload or unit, and the CAN communication network is connected to the satellite platform through the communication interface provided by the integrated interface baseboard, supporting the satellite platform to manage the payload and unit and support data interaction with the satellite platform. The system can be used as a subsystem of the satellite and is compatible with various remote sensing satellite platforms. It has good portability and compatibility, strong expansion capabilities, supports the integration of multiple payloads and processing units, and is adaptable to multi-scenario applications.

[0101] By adopting the above technical solution disclosed in the present invention, the following beneficial effects are obtained:

[0102] The present invention provides a method and system for relay tracking of large and medium-sized ships in the open sea. Compared with the traditional wide-area ship search and identification, the present invention integrates the ship AIS signal data and satellite remote sensing image data, and uses AIS positioning data to guide the imaging satellite to complete the ship target search and identification faster and autonomously and intelligently on orbit; compared with the cumbersome data processing and application processes such as traditional remote sensing data downlink, ground processing, and uplink control, the present invention can greatly reduce the amount of remote sensing image data transmission and the time required to complete the task, and support high-timeliness tasks such as escort of distant sea ships and search and rescue of ships at sea. The present invention proposes a ship tracking process based on AIS information-guided remote sensing imaging, and designs the tracking process according to the AIS signal status, divided into two situations of "stable reception of AIS signal" and "short-term loss of AIS signal" and their state conversion. The regular imaging tracking process under the condition of stable AIS reception can achieve the ship target tracking capability all day, all weather and globally; the search imaging tracking process under the condition of short-term loss of AIS signal can achieve the ship target tracking capability under good weather conditions (no cloud or light cloud) and daytime conditions and globally. The tracking modes in the two situations can achieve good conversion and realize the smooth execution of ship target tracking tasks. The system proposed by the present invention has a simple composition and low cost, and can provide a modular and intelligent solution for micro-satellites to realize relay tracking of large and medium-sized ships at sea, and the system has good portability, compatibility and scalability.

[0103] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be considered as the scope of protection of the present invention.

Claims

1. A method for relay tracking application of large and medium-sized ships in the open sea, characterized by: The following steps are included: S1. Delineate a focus area based on the current position information of the target ship, and calculate the satellites that will pass overhead within half an hour based on the focus area; assign tasks to satellites that will pass overhead in the focus area in the short term to determine the current position of the target ship; After receiving the AIS signal from the target ship, the micro-nano satellite transmits it to the ground; S2. When the AIS signal reception is stable, enter the periodic imaging tracking mode under the condition of stable AIS signal reception, and relay track the target ship. If the AIS signal is lost during operation, switch to the search imaging tracking mode under the condition of short-term loss of AIS signal; When the AIS signal reception is short-term loss, enter the search imaging tracking mode under the condition of short-term loss of AIS signal, and relay track the target ship. If the AIS signal is restored during operation, switch to the periodic imaging tracking mode under the condition of stable AIS signal reception; In both modes, if the planned preset running time is exceeded, the process returns to step S1, and the task planning for the next preset running time is performed with reference to the updated ship position, otherwise, the current mode is maintained and continued to run.

2. The method for relay tracking of large and medium-sized ships at sea according to claim 1 is characterized in that: Step S1 specifically includes the following contents: S11. If the time since the last satellite pass is more than half an hour, a focus area is delineated with the current navigation position of the target ship as the center, and the focus area is used as a reference. Based on the coverage of the satellite-borne AIS receiver and the satellite orbit parameters, the low-orbit remote sensing satellite that will pass over the focus area in the next half an hour and have an observation side swing angle of less than 45° is calculated. S12, assigning a task to the satellites that will be over the area of ​​interest in the short term, i.e., receiving and analyzing the AIS signals of ships, obtaining the identities of the ships in the AIS information by comparison, and determining the current position of the target ship; S13. After the micro-nano satellite stably and continuously receives and identifies the AIS signal of the target ship, it will transmit the information to the ground through the inter-satellite topology communication link or the geostationary orbit communication satellite at a regular interval.

3. The method for relay tracking of large and medium-sized ships at sea according to claim 1 is characterized in that: The periodic imaging tracking mode under the condition of stable AIS signal reception specifically includes the following contents: A1. Turn on the satellite AIS receiver over the circular area of ​​interest; A2: The satellite that recognizes the AIS signal of the target ship will transmit the latest navigation information of the ship to the ground every minute; A3, check whether it is the scheduled imaging time, if not, return to A1 to execute; if it is the scheduled imaging time, start the imaging tracking process; A4. Predict the future position of the target ship based on the most recently acquired state of the target ship, and plan and upload the imaging mission to the overhead satellite; A5, the overhead satellite receives the AIS signal of the target ship and images the target ship's location area; A6. Overhead satellites use the position of the target ship at the time of imaging as the center and perform intelligent detection and identification of the target ship in different areas from the inside to the outside; A7. If the target ship is not identified, return to A3 for execution; if the target ship is identified, transmit the target ship slice image and the target ship AIS information data acquired at the imaging time to the ground, and update the navigation status of the target ship; A8. If the target ship tracking mission is not completed, return to A1 for execution; otherwise, end.

4. The method for relay tracking of large and medium-sized ships at sea according to claim 3 is characterized in that: Step A6 is specifically as follows: taking the real-time position of the target ship AIS broadcast at the imaging moment as the center, 1024*1024 pixels as an intelligent detection and identification unit range, forming multiple candidate detection and identification units, and adjacent candidate detection and identification units overlap by 25% area; starting from the center, detection and identification are performed layer by layer and unit by unit from the inside to the outside; the candidate detection and identification unit that is more consistent with the heading direction of the target ship and the closer the distance is, the higher the detection and identification priority is, and therefore the detection and identification is performed first.

5. The method for relay tracking application of large and medium-sized ships at sea according to claim 4 is characterized in that: Detection and recognition are based on a deep learning network, which is an improved YOLO_v10 network. The scale of the network input image is 1024×1024×3, and the scale of the prediction output layer is 128×128, 64×64, and 32×32; The network uses the Circular Smooth Label algorithm to modify the target detection into the rotation box detection; the network output part uses the non-maximum suppression algorithm for rotating target applications; After the HEAD module at the top layer of the network and before the prediction layer, a plug-and-play lightweight convolutional block attention module is added, which combines the channel attention mechanism and the spatial attention mechanism.

6. The method for relay tracking of large and medium-sized ships at sea according to claim 4 is characterized in that: The search imaging tracking mode in the case of short-term loss of AIS signal includes the following: B1. Based on the recent navigation status of the target ship, predict the possible route of the target ship in the next 15 minutes; B2. Using the predicted target ship route as a reference, calculate the satellites that will pass over the target ship within 15 minutes; select three satellites with an interval of nearly 5 minutes, and plan and assign imaging tasks to the selected imaging satellites; B3. The three satellites image the predicted position in turn, and use the predicted position of the target ship at the time of imaging as the center to perform intelligent detection and identification of the target ship in different areas from the inside to the outside; B4. If one of the three satellites detects and identifies the target ship, the target ship slice image and imaging time information data will be transmitted to the ground, and the navigation status of the target ship will be updated; B5. If none of the three satellites can find the target ship, the mission ends. Otherwise, the mission returns to B3. B6. If the target ship tracking mission is not completed, return to B1 for execution; otherwise, the mission is terminated.

7. The method for relay tracking of large and medium-sized ships at sea according to claim 6 is characterized in that: Step B3 specifically comprises: When each satellite performs intelligent detection and identification of target ships in remote sensing images, it takes the predicted position of the target ship at the current moment of imaging as the center, and searches from the inside to the outside layer by layer and unit by unit. The unit with the more consistent heading direction and the closer distance to the target ship has a higher detection and identification priority, and is detected and identified first. Assume S n-5 To S n-1 Sn is the actual position of the target ship when it was searched and identified most recently, Sn-1 is the actual position of the target ship when it was searched and identified most recently; S n-1 S' is the track line of uniform straight-line navigation, starting from the actual position of the target ship when it was last searched and identified, with its heading as the navigation direction and the average speed as the navigation speed; S n- The three positions PA, PB, and PC on 1S' are the predicted positions of the target ship corresponding to the imaging moments of the three satellites selected with an interval of nearly 5 minutes; if the satellite imaging at the PA position fails to search and identify the target ship, and the satellite imaging at the PB position searches and identifies the target ship, the actual position of the target ship is S n Then the actual position S of the target ship when it was last searched and identified will be used as the n As the starting point, with its current heading as the navigation direction and the average speed as the navigation speed, it sails in a straight line at a uniform speed to obtain the new track line S n S; thus repeating the above process to achieve target ship search imaging and tracking when the AIS signal is lost for a short time.

8. The method for relay tracking application of large and medium-sized ships at sea according to claim 1 is characterized in that: In step S2, when the AIS signal is stably received in the periodic imaging tracking mode, if the ground gives an end-task instruction, the current task is stopped, otherwise, the current mode is maintained and continued to operate; When the AIS signal is lost for a short time and the search imaging mode is in operation, if the ground gives an instruction to end the mission, the current mission will be stopped. Otherwise, the ship target search imaging tracking situation will be judged first. If the target ship is lost, the current mission will be stopped. If the target ship can be tracked by predicting the position combined with the imaging search, the current mode will be maintained.

9. A system for relay tracking of large and medium-sized ships at sea, characterized by: The system can implement the method described in any one of claims 1 to 8 above, and the system includes a remote sensing image access unit, a satellite-borne AIS receiver, a remote sensing image intelligent processing unit and an integrated interface baseboard. The remote sensing image access unit is composed of a field programmable gate array, a random access memory and a solid state drive. On the one hand, it provides a high-speed data transmission channel for reading the original remote sensing image from the optical remote sensing imaging payload, and also provides a high-speed data transmission channel for the flow of the original remote sensing image between the remote sensing image intelligent processing unit and the satellite platform. On the other hand, it is used to store the original remote sensing image, the remote sensing image slices after intelligent processing, and the operating system, software and models required for intelligent processing. The satellite-borne AIS receiver receives the ship's AIS signal and completes data analysis; The remote sensing image intelligent processing unit is composed of a central processing unit and a graphics processing unit, and mainly provides an algorithm operation platform for remote sensing image preprocessing and intelligent detection and identification of ships in remote sensing images. It runs the Linux kernel operating system and is equipped with image preprocessing algorithms and deep learning algorithms related to intelligent detection and identification of large and medium-sized ship targets, providing powerful program control management, data flow processing, and parallel computing functions for image intelligent processing. The integrated interface baseboard consists of a power control unit and multiple types of interface channels. On the one hand, it provides power control for the above-mentioned components in the system and provides interface management with the satellite platform. On the other hand, it provides mechanical installation support for the above-mentioned components, supports modular and stacked design, and is easy to realize personalized functional combination design.

10. The system for relay tracking of large and medium-sized ships at sea according to claim 9 is characterized in that: The files stored in the solid-state hard disk include the operating system, software programs and dependent libraries required for the application program to run in the remote sensing image intelligent processing unit; and relevant parameter files for preprocessing newly acquired remote sensing images; Preprocessed remote sensing images; deep learning network structure, model parameter files and configuration files for ship target detection and recognition; The random access memory is used to provide a high-speed cache for the reading and writing operations of the original remote sensing image data, the pre-processed remote sensing image and the result data after intelligent processing.

Images