51 results about "Marine radar" patented technology

The invention provides a marine radar oil film extraction method and system based on an improved South goose algorithm, and relates to the technical field of image processing. According to the technical key points, the method comprises the following steps: firstly, preprocessing an obtained radar oil film image; then, feature extraction is carried out on the preprocessed image, an oil film region of interest is generated, interference of high-brightness clutters is effectively removed in combination with an SIFT feature filtering algorithm based on an intensity threshold value, and the oil film region of interest better fitting the actual shape of an oil film is generated through region expansion and boundary smoothing processing; then, an improved South goose algorithm is utilized to carry out segmentation extraction on the preprocessed image, the improved South goose algorithm effectively avoids a local optimum problem, a higher convergence speed is realized, and a more stable segmentation effect is further realized based on an optimal threshold obtained by solving; and finally, performing fusion processing on the oil film region of interest and the segmented and extracted image to obtain an oil film image. The precision of oil film extraction is improved.

The invention discloses a marine radar multi-target tracking method and system. The method comprises the following steps: constructing an RSDT small target detection algorithm and training to obtain a marine radar image ship identification model; identifying the ship position of the current frame of the marine radar video stream through a marine radar image ship identification model to obtain a ship detection frame; constructing a ship trajectory prediction model, and predicting the ship position of the current frame according to the ship position of the previous frame of the marine radar video stream to obtain a ship prediction frame; matching the ship detection frame and the ship prediction frame of the same frame to obtain a matching result; if the matching is successful, inputting the ship detection frame and the ship prediction frame into the ship trajectory prediction model and updating the ship detection frame and the ship prediction frame, and outputting a new ship motion trajectory; and if the matching fails, creating a high-confidence detection frame in the ship detection frame as a new ship motion track, thereby realizing accurate identification of the ship target and stable tracking of the ship track in the marine radar scene.

The invention belongs to the technical field of target detection, and particularly relates to a marine radar target detection method, system and equipment based on space-frequency feature fusion, and the method comprises the steps: constructing a marine target detection model based on space-frequency feature fusion, and extracting the multi-scale spatial domain features of an input image through a spatial domain feature sensing module in the model; frequency domain feature extraction and enhancement are carried out on the spatial domain features through a frequency domain feature sensing module to obtain frequency domain enhanced features, and the spatial domain features and the frequency domain enhanced features are fused through a space-frequency feature fusion module to obtain multi-scale enhanced feature representation; and performing layer-by-layer feature fusion on the multi-scale enhanced feature representation through a feature fusion network to obtain a final feature map, performing target detection on the final feature map through a detection head, and realizing radar target detection by using a trained marine target detection model. According to the method, a space-frequency double-domain fusion framework is constructed, and the method has high accuracy for radar image crowded scenes, multi-scale scenes and small target detection tasks.

The invention discloses a marine radar target detection algorithm and system based on a space-time joint filtering technology, and belongs to the technical field of marine remote sensing. In order to solve the problem of low target detection probability under strong sea clutter interference, three-stage processing is adopted: firstly, same-frequency interference suppression is performed on an original radar image sequence, polar coordinate echo data is converted to a frequency wavenumber domain through three-dimensional Fourier transform, and sea clutter energy in a frequency band [kx, ky] is filtered by using a dispersion relation filter; secondly, intercepting a central region of a specific wave number spectrum, extracting target energy meeting a linear equation by adopting a Hough straight line detection filter, and reconstructing a target enhanced image through three-dimensional inverse Fourier transform; and finally, performing target point fine detection on the processing sequence. According to the method, the strong sea clutter signal can be effectively suppressed and the target signal can be extracted only by using the echo amplitude information of the radar, so that the signal-to-noise ratio of the image is enhanced, the target detection probability under the strong sea clutter condition is further improved, and the method is suitable for all marine radars.

The invention relates to an ocean radar navigation method based on an AIS (Automatic Identification System) signal, which belongs to the technical field of ocean navigation and radio orientation and comprises the following steps: acquiring a navigation section and a navigation time sequence in navigation task data; determining navigation key points and effective navigation windows thereof; optimizing and solving a radar navigation strategy by taking a radar scanning distance interval and a scanning frequency interval corresponding to the monitoring type information and the risk level as constraints; a ship control instruction is generated based on the strategy, and radar / AIS signals are synchronously collected to execute navigation risk judgment; and dynamically updating the task data and the navigation strategy according to the navigation execution state. Real-time cooperative verification and active collision avoidance navigation of ship identity-position-environment under complex sea conditions are realized; the technical problem of collision avoidance delay caused by large radar and AIS target matching error and fixed scanning parameters in the prior art is solved.

The present invention discloses a method for rapid detection of marine radar targets. Radar echo data samples on a single scan line are selected from offline radar data, including radar echo samples containing targets and pure sea clutter radar echo samples without targets; characteristic parameters are selected, and the echo eigenvalue of the samples is input into an RBF neural network for training to obtain a trained RBF neural network classifier model; the echo data to be measured on a single scan line in the radar image is obtained, and the echo eigenvalue of the echo data to be measured is calculated according to the characteristic parameters to obtain an input feature matrix; the input feature matrix is input into the trained RBF neural network classifier model to obtain a decision function value y; y is compared with the classifier threshold to determine whether there is a target on the scan line: if y is greater than the threshold, there is a target; if y is less than the threshold, there is no target. The present invention can reduce the detection time and improve the target detection efficiency and target detection accuracy.

The application provides an ice area navigation dynamic sea ice risk early warning method and system, the method first acquires the navigation information of a target ship, the first navigation radar image information of a first time point and the second navigation radar image information of a second time point, and calculates the time interval of the two time points, then respectively extracts the interested region of the sea ice echo through a mask matrix, fills the pixels of the interested region of the sea ice echo and the pixels of other regions except the interested region of the sea ice echo with different colors to obtain the binary image of the sea ice echo of the two time points, then calculates the distance, azimuth angle of each piece of sea ice and the target ship, and the latitude and longitude coordinates of the sea ice centroid of the two time points by using a specific calculation method, calculates the sea ice collision probability and the sea ice collision consequence, further calculates the sea ice collision risk index, and performs corresponding different level sea ice risk early warning on the sea ice according to the comparison result of the sea ice collision risk index and the preset risk threshold of different levels.

The present invention discloses a method, device, storage medium and radar for estimating the operating range of a marine radar. The method includes: when the theoretical operating range of the radar is greater than the critical range, determining a correction coefficient according to the theoretical operating range of the radar, the critical range, the equivalent earth curvature radius and the target equivalent height; correcting the theoretical operating range of the radar according to the correction coefficient to obtain the corrected operating range of the radar; and making the evaluated detection operating range closer to the actual level of the radar. The method for estimating the operating range of the marine radar proposed by the present invention is simple and easy to understand. Through multiple batches of navigation radar sailing tests, it is verified that its estimation result is closer to the actual operating range of the radar, more accurate, and is beneficial to become an important reference for estimating the operating range of the marine radar.

This application provides a sea clutter suppression method based on complex numbers and adaptive dynamic weighting, relating to the field of marine radar signal processing technology. The method includes performing a short-time Fourier transform on the raw radar echo data to generate a spectrum; standardizing preprocessing to obtain preprocessed in-phase and quadrature component signals; performing frequency domain pre-separation to obtain low-frequency sea clutter component signals; performing phase compensation and outputting the IMF corresponding to the low-frequency sea clutter components through improved complex EMD decomposition; performing multi-criteria adaptive selection to obtain the filtered IMF; calculating the high-frequency residual of the original signal; and performing dynamic weighted reconstruction and energy calibration based on the high-frequency residual and the filtered IMF to output the target signal after clutter suppression. This application improves the method's ability to capture signal phase information and suppresses mode aliasing by extending the time-domain EMD to the complex domain; and introduces an adaptive dynamic weighting mechanism to adjust the weight allocation in real time during the decomposition process, thereby improving sea clutter suppression performance.

The utility model discloses a lifting device of a marine radar mast, which is characterized in that the lifting device is arranged in an inner column body and an outer column body, the lifting device is preferably a hydraulic cylinder, the lifting device can stretch out and draw back to drive the inner column body to lift up and down along the outer column body, and a limiting fixing device is arranged on the inner column body; the limiting and fixing device limits and fixes the inner column body, the outer column body and the inner column body form an integrated supporting structure under the action of the limiting and fixing device to support the radar mast, the situation that the lifting device, namely the hydraulic cylinder, is in a pressurized state all the time is avoided, and the lifting safety and stability of the radar mast are improved; the supporting end is arranged at the lower end of the inner column body, when the radar mast descends to the corresponding position, the supporting end makes contact with the ship body for supporting, when the radar mast descends to the corresponding position, the inner column body supports the radar mast, the pressure of the lifting device, namely the hydraulic cylinder is reduced, and the lifting safety and stability of the radar mast are improved.

The invention aims to provide a target detection method and system for suppressing marine radar image sequence clutters based on time-space domain Hough transform, and the method comprises the steps: firstly removing sea clutter spectrum energy through employing a frequency domain and wave number domain combined filter based on a dispersion relation, and then intercepting a spectrum center region; the method comprises the following steps: firstly, performing clutter suppression on an image sequence, acquiring target frequency spectrum parameters by using Hough detection to establish a clutter frequency spectrum filter so as to realize further clutter filtering, finally performing generalized extreme value distribution modeling on the image sequence subjected to clutter suppression to obtain mu, sigma and xi values conforming to data background clutters, and performing target point detection by using a rejection inclusion detector. The algorithm is verified by using the real data of the X-band marine radar, and the method can effectively suppress the strong clutter signal, thereby enhancing the signal-to-noise ratio of the image, and further improving the target detection probability under the strong sea clutter condition.

The invention provides a multi-modal fusion-driven ship navigation target detection method and device, and the method comprises the steps: extracting the feature vectors of ship vision, marine radar, AIS and ship navigation data, taking the vector of the marine radar as a dominant vector, taking the other feature vectors as supplementary fusion, and achieving the modal complementation. And mapping the fusion feature vector to a bird's-eye view semantic space to obtain bird's-eye view features, decoding the bird's-eye view features, and inputting the decoded bird's-eye view features into a detection head for target detection to obtain a target detection result. In this way, through multi-modal fusion complementation and semantic space mapping, the problem that existing multi-modal data fusion only stays at a data layer for direct splicing or shallow feature level fusion can be avoided, and the space-time isomerism and semantic difference between multi-modal data are overcome. The consistency and robustness of target detection in the ship navigation process are improved under the complex sea condition, and the reliability and accuracy of the detection result are ensured.

This invention provides a method for identifying and suppressing false echoes from marine radar under calm sea conditions. The specific process is as follows: For a single-frame radar image, extended target information is obtained. The recorded extended target information is converted into point coordinate information, i.e., the wave crest position of the echo is retained, and the azimuth and range information of the wave crest position are extracted. Simultaneously, the echo intensity information of the target is added and stored as an initial target information matrix. Azimuth feature information is judged, and target information that conforms to the azimuth feature of the false echo is saved. Range feature information is judged, and target information that conforms to the range feature of the false echo is saved. The false echo occurrence scenario is judged to determine whether the conditions for false echo occurrence are met. Echo intensity feature information is judged, and target information that does not conform to the echo intensity feature of the false echo is deleted. Simultaneously, the initial target information matrix is ​​updated to a false echo target information matrix. Based on the information in the false echo target information matrix, a suppression threshold for the digital domain of the radar echo data is set to suppress false echoes in the single-frame target information.

The invention aims to provide a marine radar image target detection method and system based on airspace sea clutter suppression, and the method comprises the steps: firstly obtaining sea clutter frequency spectrum information in a three-dimensional frequency wave number domain in a three-dimensional space-time joint domain processing channel, and the sea clutter frequency spectrum information comprises a wave number, an angular frequency and a wave direction corresponding to each frequency spectrum point; the method comprises the following steps: firstly, acquiring information of a sea clutter spectrum, then converting the information into a two-dimensional spatial domain as priori knowledge to establish a filter model, filtering an image spectrum after two-dimensional Fourier transform to realize rapid suppression of sea clutter spectrum energy, and finally, carrying out Burr distribution modeling on an image sequence after clutter suppression to obtain c, k and alpha values conforming to data background clutters. And target point detection is carried out by using a WHOS detector. The algorithm is verified by using the real data of the X-band marine radar, and the method can effectively model a background clutter distribution model under the background of sea clutter suppression, thereby improving the target detection probability of the image after the sea clutter suppression of the marine radar.

The invention relates to a beacon light anti-collision warning device and a control method thereof.The device comprises a beacon light structure arranged on the sea surface, the beacon light structure comprises a beacon light body, a beacon light and a beacon light platform, a circular ring support is arranged on the outer side of the beacon light platform, a ranging radar is arranged on the circular ring support, the circular ring support is connected with the beacon light body, and the beacon light body is connected with the ranging radar; a buzzer, an AIS module and a solar power supply module are arranged in the beacon light body. Compared with the prior art, the method has the advantages of preventing seawater from influencing the work of the marine radar sensor and the like.

The present invention relates to an ocean radar navigation method based on AIS signals, belonging to the field of ocean navigation and radio direction finding technology. The method comprises: obtaining navigation sections and navigation timings from navigation mission data; determining navigation key points and their effective navigation windows; optimizing and solving radar navigation strategies based on radar scanning distance intervals and scanning frequency intervals corresponding to monitoring type information and risk levels; generating ship control instructions based on the strategy and synchronously collecting radar / AIS signals to perform navigation risk assessment; and dynamically updating mission data and navigation strategies based on the navigation execution status. This method achieves real-time collaborative verification of a ship's identity, position, and environment, as well as active collision avoidance navigation, in complex sea conditions. The present application addresses the technical issues in the prior art caused by large matching errors between radar and AIS targets and fixed scanning parameters leading to collision avoidance delays.

The invention relates to the technical field of marine environment monitoring, and discloses a marine radar oil spill detection method and system based on a neural network and GMM clustering, and the method comprises the steps: obtaining a marine radar image, and dividing the marine radar image into a plurality of image blocks; extracting an eight-dimensional feature vector from each image block and performing dimension reduction processing to obtain a four-dimensional feature vector; clustering the four-dimensional feature vectors to generate a region of interest; performing feature extraction and anomaly detection on non-background pixels in the region of interest based on a neural network, and marking abnormal points; after abnormal points are removed, clustering is carried out on residual non-background pixels based on a Gaussian mixture model, and an oil film segmentation result is obtained; and fusing an oil film segmentation result with the preprocessed image, converting a fusion result from a Cartesian coordinate system into a polar coordinate system, and outputting a final detection result. According to the scheme, the detection precision and robustness can be remarkably improved, stable and reliable oil spill identification is realized under complex sea conditions, and support is provided for marine environment monitoring.

The invention provides a marine radar performance monitor system based on frequency sweep, which comprises a radar antenna, a magnetron pulse transmitting module, an echo receiving module, a display module, a PM antenna, a receiving and detecting module and a regular image transmitting module, and is characterized in that the output end of the magnetron pulse transmitting module is connected with the input end of the radar antenna; the output end of the radar antenna is connected with the input end of the echo receiving module, the output end of the echo receiving module is connected with the input end of the displayer, the output end of the PM antenna is connected with the output end of the receiving and detecting module, and the output end of the receiving and detecting module is connected with the input end of the regular image transmitting module. The output end of the regular image transmitting module is connected with the input end of the PM antenna, the regular calibration pulse width can be broadened and can be stably kept within the response range of the echo receiving module, and the problem that the transmitting width of a pulse radar of a traditional marine radar performance monitor system is narrow is solved.

1. The name of the design product: solid-state marine radar (X-band). 2. The use of the design product: the appearance of X-band solid-state marine radar. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view.

The invention provides a marine radar oil spill detection method and system based on BiLSTM and SOM, and relates to the technical field of target detection. The method comprises the following steps: preprocessing original radar image data; extracting multi-modal texture features of the preprocessed image, and generating a pseudo tag of the image by using a K-means clustering algorithm; using a BiLSTM algorithm to extract time sequence features of the preprocessed image; inputting the time sequence features into a trained self-organizing mapping network, and finding out a winning neuron for each feature vector; allocating a pseudo label of a pixel corresponding to each feature vector to a corresponding winning neuron so as to obtain a classification result of each pixel in the preprocessed image; and on the basis of the categories of other pixels in the neighborhood window of each pixel in the classification result, carrying out iterative updating on the category of each pixel to determine a final classification result of each pixel, and then carrying out morphological processing to obtain an oil spill image. According to the invention, a new solution is provided for accurate detection of radar oil spill in a complex scene.

The invention belongs to the technical field of ship and ocean engineering, and discloses a multi-feature ocean environment perception method and system based on a cross-scale attention mechanism, and the method comprises the steps: carrying out the multi-working-condition effective region selection of X-waveband coherent marine radar time calendar data, carrying out the data segmentation, and dividing the data into a training set and a test set; training set data are input into a constructed multi-feature marine environment perception model based on a cross-scale attention mechanism, the model gradually reduces the resolution of a feature map and increases the number of channels through four stages, and hierarchical feature representation from local details to global context is generated. And an activation value cooling layer is adopted to improve the gradient explosion problem in the model performance, and finally a pre-trained optimal multi-feature marine environment perception model is used to establish a mapping relation between radar amplitude and phase information and wind and wave marine environment parameters, so that high-precision real-time perception of the marine storm environment is realized. The method provides basic technical means support for marine economic development and safety guarantee in China, and has important engineering significance.

This invention belongs to the field of intelligent collision avoidance and early warning technology for ships, specifically relating to a method and system for collision avoidance and early warning in open sea areas. The method includes the following steps in sequence: multi-source navigation data acquisition and analysis, intelligent filtering of open water conditions, real-time calculation of collision risk parameters, collision risk early warning triggering, automatic recording of close-range navigation events, and ship-shore synchronization of early warning and recorded information. The main hardware used in the system includes an AIS signal controller, marine ARPA radar, GPS equipment, gyrocompass, serial port server, switch, collision avoidance tablet computer, captain's cabin computer, ship-side communication host, and shore-side platform. This invention aims to solve the problems of "alarm fatigue" and safety risks caused by numerous invalid alarms and poor scene adaptability in traditional collision avoidance early warning systems during navigation in open sea areas by integrating intelligent scene filtering, accurate risk calculation, and ship-shore collaborative management into a system and method, thereby achieving efficient and reliable automatic collision early warning.

The invention belongs to the technical field of radar systems, and discloses a dual-system all-solid-state marine radar. The system comprises an antenna pedestal rotary table, a low-profile waveguide slot antenna, a servo unit, a power supply unit, a radio frequency switching unit, a pulse transceiving unit, a continuous wave transceiving unit, a main control unit and a display control terminal. According to the invention, the design of an all-solid-state and all-coherent dual-system radar system is utilized, the inherent technical defects of a traditional magnetron monopulse system and a single solid-state system marine radar are made up, the technical advantages of a pulse compression system and a linear frequency modulation continuous wave system are integrated, the radar performance is improved, and more abundant functions are integrated at the same time; and the use requirements of modern ships in application scenes such as open sea navigation, narrow water channel passing, port entering and leaving, search and rescue, collision early warning, panoramic blind compensation and the like can be met.

This invention discloses a virtual simulation method and system for marine radar, comprising the following steps: constructing a virtual test environment consistent with the real marine environment, including an unmanned vessel, marine radar, and maritime targets; using a quaternion calculation method to transform measurements in the local coordinate system of the virtual radar to the world coordinate system; determining the radar field of view through horizontal and vertical scanning coverage; realizing simulated ray tracing and collision detection of the marine radar beam; calculating echo distance and angle, calculating echo intensity, and generating standardized radar echo data records; dynamically adjusting the echo intensity through adjustable gain control and range compensation mechanisms, and mapping the echo data to a color space; persistently storing and time-attenuating the echo data to simulate radar afterglow effects; and drawing range rings, azimuth markers, and dynamic scan lines on the radar display interface to construct a complete radar visualization system.

The invention aims to provide a radar image sea clutter suppression method and system based on a spatial domain filtering technology, and the method comprises the steps: firstly obtaining sea clutter frequency spectrum information in a three-dimensional frequency wave number domain in a three-dimensional space-time joint domain processing channel, and the sea clutter frequency spectrum information comprises a wave number, an angular frequency and a wave direction corresponding to each frequency spectrum point; then the information is converted into a two-dimensional spatial domain to serve as priori knowledge to establish a filter model, filtering is carried out on an image spectrum after two-dimensional Fourier transform, sea clutter spectrum energy is rapidly suppressed, and finally target point detection is carried out on the image after sea clutter suppression. The algorithm is verified by using the real data of the X-band marine radar, and the method can effectively suppress the strong sea clutter signal, thereby enhancing the signal-to-noise ratio of the image, and further improving the target detection probability under the strong sea clutter condition.

The ship path planning method based on the improved CSAC-APF algorithm disclosed in the present invention combines the CSAC algorithm with a potential energy-based reward mechanism, and proposes a CSAC-APF algorithm. It uses sensors (marine radar equipment) to collect ship and environmental information, and uses the state information of the ship, target point and obstacles as the input data of the algorithm. Through model training and learning, the cumulative reward benefits in the learning process are maximized, and the optimal action strategy is finally determined. When the model training is completed, the ship can avoid obstacles to reach the destination and plan a safe and economical path. The present invention can achieve better global path planning in a static environment, and can perform collision avoidance actions according to the International Regulations for Preventing Collisions at Sea in dynamic encounter scenarios to reduce the risk of collision.

This embodiment discloses an AIS-assisted method for identifying sidelobe echoes in marine radar. It utilizes AIS data to establish a pre-selected area, removes the main lobe, determines the sidelobe, and then selectively zeros and restores the main lobe to achieve accurate identification and effective suppression of sidelobe echoes. This method effectively identifies and eliminates interfering sidelobe echoes, ensuring that the true echo (main lobe) of the target ship is not mistakenly detected, thus preserving the core information of radar detection. After suppressing the sidelobes, the radar range-azimuth image becomes clearer, reducing interference from false targets. This helps the navigator more accurately assess the surrounding navigation situation, reducing the risk of navigational decision errors and improving the readability and safety of radar images. Furthermore, the introduction of AIS reported target data as a high-precision reference makes the locking of the main lobe echo more stable, avoiding potential biases that might arise from relying solely on the radar image's own features for clustering, thus providing technical support for suppressing or eliminating sidelobe echoes.

This invention relates to a method for inverting marine radar echoes based on satellite data, belonging to the field of meteorological data processing technology. The invention acquires and processes multi-channel satellite observation data and combined radar reflectivity observation data within the same spatiotemporal range of a target area; then, it constructs a deep convolutional neural network model based on the U-Net architecture and trains the model using the preprocessed data; finally, it inputs multi-channel satellite observation data of the area to be inverted into the trained model, outputting the combined radar reflectivity inversion data for that area. This invention fills the gap in marine radar observation through artificial intelligence technology, achieving high inversion accuracy, strong model generalization ability, and significant operational application value.

The invention relates to a vessel collision monitoring system that automatically and continuously compares radar and AIS observations over time. The movement of all (or many) vessels (12, 14) in the area (5) around an offshore installation (1) can be monitored and this data can be recorded and used to produce trends and reports indicating where there is a discrepancy between AIS “targets” and radar observations. In this way, potential blind spots (10) in the radar system can be identified and appropriate action taken, e.g. maintenance of the radar system (2) or moving or adding radar transmitters or receivers to remove a blind spot.

The invention discloses a superpixel-based marine radar target rapid detection algorithm and system under a sea clutter dynamic distribution background, and belongs to the technical field of ship target detection under a marine environment condition. The method comprises the following steps of: 1, acquiring radar signal data, performing super-pixel segmentation on an obtained radar image, and performing rapid target detection by adopting a k-means clustering algorithm through super-pixel weighted information entropy features to obtain a candidate target super-pixel set and a pure sea clutter super-pixel set so as to realize rough positioning of a target; and 2, selecting a certain number of pure sea clutter superpixels by taking the candidate target superpixel as a center, carrying out data fitting to obtain sea clutter dynamic distribution, and carrying out CFAR point-by-point target fine detection on the candidate target superpixel by using the sea clutter dynamic distribution to obtain a target detection result of the whole radar image. The accuracy of the sea clutter distribution model is improved, and the detection efficiency is improved.