Vision-aided display method and system based on matching of expected motion position

Abstract

This invention provides a visually assisted display method and system based on expected motion position matching, relating to the field of aircraft control technology. The method includes: acquiring a historical trajectory dataset of successful docking of a flight platform, and real-time data of the current flight platform; performing baseline trajectory modeling processing based on the historical trajectory dataset to obtain a baseline spatial trajectory function; parameterizing nodes based on the baseline spatial trajectory function to obtain a standardized node sequence; performing visual mapping based on the standardized node sequence to generate a set of annular geometric parameters; matching the real-time data stream with the annular geometric parameter set to output an index identifier for the next target node; and guiding state transition based on the index identifier to output the final docking correction parameter vector. This invention also utilizes a dual-mode visual guidance mechanism to achieve a continuous transition from annular matching to beam alignment, significantly improving the dynamic docking accuracy and operational reliability of the flight platform under complex disturbance environments.

Description

Technical Field

[0001] This invention relates to the field of aircraft control technology, and more specifically, to a visual aid display method and system based on expected motion position matching. Background Technology

[0002] In the field of dynamic docking technology for unstable aircraft platforms, high-precision vision guidance systems are the core guarantee for safe and reliable docking in complex environments. With the improvement of the autonomous operation capabilities of flight platforms, the problem of end-point trajectory instability of docking terminals (such as cones and capture rings) under airflow disturbances and mechanical vibrations is becoming increasingly prominent, especially in the final hundred meters of approach, where the target exhibits nonlinear drift characteristics. Existing technologies mainly employ two types of solutions: one is a static guidance system based on fixed geometric lines, using preset light beams to assist spatial positioning; the other is dynamic tracking technology relying on real-time image processing, utilizing edge features for servo control. However, static systems struggle to adapt to centimeter-level random shifts in the target caused by environmental disturbances, leading to frequent spatial perception deviations for operators in turbulent environments; while pure vision solutions face the risk of feature loss in scenarios with sudden changes in lighting or occlusion, and are more prone to computational delays and tracking interruptions during high-speed movement. More importantly, existing methods lack the ability to physically model the motion patterns of the target, failing to convert historically successful docking trajectory data into reusable guidance knowledge. This necessitates readjusting to the dynamic environment for each operation, significantly increasing operational workload and collision risk under low visibility conditions. These technological bottlenecks severely restrict the all-weather operational capabilities of flight platforms in missions such as resupply and rescue.

[0003] Based on the shortcomings of the existing technology, there is an urgent need for a visual aid display method and system based on expected motion position matching. Summary of the Invention

[0004] The purpose of this invention is to provide a visual aid display method and system based on expected motion position matching, so as to improve the above-mentioned problems. To achieve the above objective, the technical solution adopted by this invention is as follows:

[0005] In a first aspect, this application provides a visual aid display method based on expected motion position matching, including:

[0006] Acquire historical trajectory datasets of successful docking of the flight platform, as well as real-time data of the current flight platform. The real-time data includes the coordinates of the cone center point, equivalent radius, relative speed, and real-time images.

[0007] Based on the historical trajectory dataset, a baseline trajectory modeling process is performed to obtain a baseline spatial trajectory function;

[0008] Node parameterization is performed based on the reference spatial trajectory function to obtain a standardized node sequence containing at least two target cone sleeve positions and corresponding dimensions;

[0009] Visual mapping is performed based on the standardized node sequence. Static light column line parameters are obtained by projection transformation with a fixed oil gun installation angle. The expected field coordinates and scaling factor of the cone sleeve at each node are calculated based on the perspective projection model to generate a set of circular geometric parameters.

[0010] The real-time data stream is matched with the set of geometric parameters of the annulus. The pixel deviation between the real-time image and the annulus template is calculated, and the index identifier of the next target node is output.

[0011] The guided state transition is performed based on the index identifier. The alignment deviation vector of the light column is calculated by detecting the field coordinates of the target node against the over-boundary state of the display boundary, and the final docking correction parameter vector is output.

[0012] Secondly, this application also provides a visual aid display device based on expected motion position matching, including:

[0013] The acquisition module is used to acquire historical trajectory datasets of successful docking of the flight platform, as well as real-time data of the current flight platform. The real-time data includes the coordinates of the cone center point, the equivalent radius, the relative speed, and real-time images.

[0014] The modeling module is used to perform baseline trajectory modeling processing based on the historical trajectory dataset to obtain a baseline spatial trajectory function;

[0015] The extraction module is used to parameterize nodes according to the reference spatial trajectory function to obtain a standardized node sequence containing at least two target cone positions and their corresponding dimensions;

[0016] The conversion module is used to perform visual mapping based on the standardized node sequence, obtain the static light column line parameters through projection transformation of the fixed oil gun installation angle, and calculate the expected field coordinates and scaling factor of the cone sleeve at each node based on the perspective projection model to generate a set of circular geometric parameters.

[0017] The matching module is used to match the real-time data stream with the set of geometric parameters of the annulus, and output the index identifier of the next target node by calculating the pixel deviation between the real-time image and the annulus template.

[0018] The output module is used to guide the state transition according to the index identifier, calculate the beam alignment deviation vector by detecting the target node's field of view coordinates against the display boundary's out-of-bounds state, and output the final docking correction parameter vector.

[0019] The beneficial effects of this invention are as follows:

[0020] This invention integrates historical trajectory data modeling with real-time image feature matching to construct a standard position point sequence based on physical laws, and utilizes a dual-mode visual guidance mechanism to achieve a continuous transition from ring matching to beam alignment, significantly improving the dynamic docking accuracy and operational reliability of the flight platform in complex disturbance environments.

[0021] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of the visual aid display method based on expected motion position matching as described in an embodiment of the present invention;

[0024] Figure 2 This is a schematic diagram of the visual aid display system structure based on expected motion position matching as described in an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of the visual aid display device based on expected motion position matching as described in an embodiment of the present invention.

[0026] The diagram is labeled as follows: 800, Visual aid display device based on expected motion position matching; 801, Processor; 802, Memory; 803, Multimedia component; 804, I / O interface; 805, Communication component; 901, Acquisition module; 902, Modeling module; 903, Extraction module; 904, Conversion module; 905, Matching module; 906, Output module. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0028] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0029] Example 1:

[0030] This embodiment provides a visual aid display method based on expected motion position matching.

[0031] See Figure 1 The figure shows that the method includes steps S100, S200, S300, S400, S500 and S600.

[0032] Step S100: Obtain the historical trajectory dataset of successful docking of the flight platform, as well as the real-time data of the current flight platform. The real-time data includes the coordinates of the cone center point, the equivalent radius, the relative speed, and the real-time image.

[0033] Understandably, the initial data acquisition phase integrates both historical experience and real-time perception. The historical trajectory dataset contains the spatial motion patterns of multiple successful docking processes, while the real-time data stream synchronously collects the instantaneous spatial pose (center coordinates, equivalent radius), relative motion state (velocity vector), and visual morphology (real-time image) of the cone sleeve through sensors, providing a dynamic input basis for subsequent processing to cope with airflow disturbances and mechanical vibrations.

[0034] Step S200: Perform baseline trajectory modeling processing based on the historical trajectory dataset to obtain the baseline spatial trajectory function;

[0035] Benchmark modeling based on historical trajectories is essentially a mathematical abstraction of physical laws. This step analyzes the spatiotemporal distribution characteristics of a large number of successful docking trajectories, extracts the dynamic characteristics of the conical sleeve motion under the influence of turbulence, and constructs a continuous spatial trajectory function. This function not only represents the motion path of the conical sleeve under ideal conditions, but also implicitly includes statistical compensation for uncertainties such as wake disturbances, forming a spatial expression of reproducible successful experiences.

[0036] Step S300: Parameterize the nodes according to the reference space trajectory function to obtain a standardized node sequence containing at least two target cone positions and corresponding dimensions;

[0037] This step addresses the non-uniform motion characteristics exhibited by the cone sleeve during approach (such as large swings at the near end and smooth movement at the far end). It dynamically divides the trajectory into segments based on the rate of change of trajectory curvature and acceleration extreme points, and enhances visual guidance density in high-dynamic regions. The resulting node sequence essentially discretizes continuous motion into guiding keyframes with clear physical meaning.

[0038] Step S400: Perform visual mapping based on the standardized node sequence, obtain the static light column line parameters through projection transformation of the fixed oil gun installation angle, and calculate the expected field coordinates and scaling factor of the cone sleeve at each node based on the perspective projection model to generate a set of circular geometric parameters.

[0039] It should be noted that the visual mapping stage establishes the geometric relationship between the physical space and the display space. The generation of static light column parameters depends on the rigid body transformation relationship of the oil gun installation angle, forming a stable guiding reference that is not affected by the platform posture. The circular parameters, on the other hand, transform the expected spatial position and size attenuation characteristics of the cone sleeve into display coordinates and scaling factors through the perspective projection model, realizing the dynamic adaptation of visual elements as distance changes.

[0040] Step S500: Match the real-time data stream with the set of geometric parameters of the ring, and output the index identifier of the next target node by calculating the pixel deviation between the real-time image and the ring template.

[0041] Understandably, this step calculates the positional deviation after deformation compensation in pixel space by fusing the cone-shaped contour features in real-time images with the geometric parameters of a preset circular template. Combined with the dynamic adjustment of the convergence threshold based on relative velocity, this enables a quantitative assessment of the degree of agreement between the actual motion state of the cone and the expected trajectory, thereby triggering the intelligent advancement of the guiding node.

[0042] Step S600: Guide state transition according to index identifier, calculate the beam alignment deviation vector by detecting the target node field coordinates and the over-boundary state of the display boundary, and output the final docking correction parameter vector.

[0043] It should be noted that when the target node approaches the display boundary, the two-dimensional screen coordinate deviation is mapped into a three-dimensional spatial correction vector based on the geometric spatial relationship between the centerline of the light column and the position of the cone sleeve. This process achieves a seamless transition from visual guidance of the ring to geometric guidance of the light column, ensuring that the spatial alignment accuracy at the final docking stage is not constrained by the reduction in the display field of view.

[0044] Further, step S200 includes steps S210 to S230.

[0045] Step S210: Perform time synchronization processing based on the historical trajectory dataset. By aligning multiple sets of historical trajectory data to a unified time reference, a synchronized spatiotemporal coordinate sequence is obtained.

[0046] Step S220: Perform dynamic constraint compression processing based on the synchronized spatiotemporal coordinate sequence, and filter trajectory points that conform to the laws of physical motion based on the preset acceleration threshold to obtain an optimized trajectory point set;

[0047] Step S230: Construct a continuous trajectory function based on the optimized trajectory point set, and fit the spatial path through a B-spline basis function that preserves multi-order continuity to obtain the reference spatial trajectory function.

[0048] Specifically, in the core processing of baseline trajectory modeling, the time difference in the acquisition of multi-source historical trajectory data is first eliminated through time synchronization processing, and the scattered timestamps are mapped onto a unified time reference axis to solve the trajectory jitter problem caused by asynchronous recording. Then, based on dynamic constraint compression processing, effective trajectory points that conform to the laws of Newtonian mechanics are selected using a preset acceleration threshold, and abnormal data points caused by sudden changes in airflow or operational jitter are eliminated, while retaining key positional information that characterizes the true motion trend of the conical sleeve. Finally, a multi-order continuous B-spline basis function is used to fit the spatial path of the optimized trajectory point set. By forcing the continuity of the second derivative, the generated trajectory function is ensured to remain smooth in terms of the rate of curvature change, forming a baseline spatial trajectory function that can reflect historical successful experience and adapt to the laws of physical motion.

[0049] Further, step S300 includes steps S310 to S330.

[0050] Step S310: Extract the oscillation features of the conical sleeve motion based on the reference space trajectory function. By separating the extreme points of the normal acceleration of the trajectory function from the swing phase reversal points, the key feature point set of the conical sleeve swing is obtained.

[0051] Step S320: Divide the turbulence-affected zone according to the key feature point set. Based on the historical distribution data of the wake disturbance of the flight platform, divide the trajectory into a stable approach segment and an oscillation correction segment to obtain the aerodynamic characteristic graded trajectory segment.

[0052] Step S330: Perform visual adaptive sampling processing on the graded trajectory segments according to aerodynamic characteristics, and perform super-density sampling on the oscillation correction segment through the principle of near-end perspective distortion enhancement to generate a standardized node sequence for size deformation compensation.

[0053] Specifically, the process first extracts and processes the higher-order dynamic characteristics of the analytical trajectory function by analyzing the oscillation features of the conical sleeve: For the inherent periodic oscillation behavior of the conical sleeve under airflow disturbance, a vector analysis method is used to calculate the normal acceleration field along the trajectory curve, with its local maxima corresponding to the peak position of the oscillation amplitude; simultaneously, the phase reversal point of the oscillation is detected by the change in the sign of the dot product of the velocity vector, accurately capturing the critical moment when the conical sleeve undergoes a sudden change in motion direction due to the impact of the wingtip vortex. The key feature point set extracted in this way physically characterizes the key turning pose of the conical sleeve from forced oscillation to self-stabilization. Subsequently, based on the historical distribution data of the wake disturbance of the flight platform, the turbulence-affected sections are divided: a three-dimensional wake probability envelope model pre-constructed through wind tunnel tests or CFD simulations is loaded, and the trajectory function is substituted into the envelope space for integration. When a local trajectory segment crosses the wake core area, it is marked as an oscillation correction segment; the rest are marked as stable approach segments. This process is essentially a statistical learning and spatial mapping of historical turbulence disturbance patterns. Finally, visual adaptive sampling processing is performed: a super-density sampling mechanism is introduced in the oscillation correction segment, and size deformation compensation parameters are injected into each node, so that the generated standardized node sequence can adapt to the nonlinear deformation law of the cone sleeve caused by hydrodynamics and the visual perspective distortion characteristics related to the viewing angle in terms of spatial distribution and size representation.

[0054] Further, step S320 includes steps S321 to S323.

[0055] Step S321: Reconstruct the wake probability field based on the key feature point set. Fit the historical distribution data of the flight platform's wake disturbance using a Gaussian mixture model to obtain the three-dimensional wake probability density field. The formula for calculating the three-dimensional wake probability density field is:

[0056]

[0057] in, Representing a three-dimensional spatial vector The wake probability density field; Indicates the number of wake vortex cores; Represents the vortex core Weighting coefficients; Indicates the serial number of the vortex core; Represents a three-dimensional spatial position vector; Indicates the location of the vortex core center; Indicates the radius of the disturbance effect.

[0058] Step S322: Quantize the trajectory disturbance intensity based on the three-dimensional wake probability density field, and obtain the trajectory disturbance intensity spectrum through curvature-weighted path integral calculation. The formula for calculating the trajectory disturbance intensity is:

[0059]

[0060] in, This indicates the intensity of the combined impact of wake turbulence disturbance on the cone sleeve; Indicates the trajectory arc length parameter; This indicates the length of the integration window (0.5m). Function representing trajectory position; Represents the wake probability density function; Represents the trajectory curvature factor; The integral variable representing the arc length of the trajectory.

[0061] Step S323: Perform adaptive threshold segmentation based on the trajectory disturbance intensity spectrum, and mark it using a dynamically enhanced decision function to obtain aerodynamic characteristic graded trajectory segments.

[0062]

[0063] in, This represents the adaptive decision threshold function; Indicates the global maximum disturbance intensity; , , These are the weighting coefficients; Indicates the distance attenuation coefficient; This indicates the magnitude of the acceleration component of the cone sleeve's trajectory in the normal direction; Represents the natural base.

[0064] The segmentation rule is reflected in: when The time marker indicates an oscillation correction segment; otherwise, it indicates a stable approach segment.

[0065] Further, step S400 includes steps S410 to S430.

[0066] Step S410: Perform coordinate system alignment processing based on the cone sleeve position coordinates in the standardized node sequence. By transforming the world coordinate system to a local coordinate system with the oil gun base point as the origin, the oil gun relative spatial coordinate set is obtained.

[0067] Step S420: Perform static light column generation processing based on the relative spatial coordinate set of the oil gun, solve the light column direction vector through the fixed projection relationship of the oil gun installation angle, and output the static light column line parameters;

[0068] Step S430: Perform perspective geometry calculation based on the cone sleeve size parameters and the relative spatial coordinate set of the oil gun in the standardized node sequence. Calculate the ring display size using the pinhole camera model and viewing distance scaling ratio to generate a ring geometry parameter set.

[0069] It should be noted that, as Figure 3 As shown, the process first transforms the position coordinates of the cone sleeve in the world coordinate system to a local coordinate system with the oil gun mounting base point as the origin through coordinate system alignment, eliminating the spatial offset caused by changes in the flight platform's attitude and obtaining the relative spatial coordinate set of the oil gun. Then, based on the fixed geometric relationship of the oil gun mounting angle, the mapping relationship of the light column direction vector on the display plane is solved through orthogonal projection transformation, generating static light column line parameters that are not affected by platform motion. Finally, perspective geometry is calculated by combining the pinhole camera model and the physical law of line of sight. The visual scaling ratio is calculated using the cone sleeve size parameters and relative distance, and the perspective projection error is corrected through the radial distortion compensation function, generating a set of annular geometric parameters containing the expected field of view coordinates and the adaptive display size, realizing a stable mapping from three-dimensional physical space to two-dimensional display space.

[0070] Further, step S500 includes steps S510 to S530.

[0071] Step S510: Perform multimodal feature fusion processing on the real-time image in the real-time data stream, enhance the positioning accuracy through the edge extraction algorithm constrained by the center coordinate, and obtain spatiotemporally synchronized cone sleeve contour data;

[0072] Step S520: Based on the conical sleeve contour data, the coordinates of the conical sleeve center point in the real-time data stream, the equivalent radius, and the set of geometric parameters of the annulus, perform dynamic template reconstruction processing, adjust the target annulus size through the radius scaling compensation mechanism, and perform projection space registration to obtain a matching deviation field with confidence weights.

[0073] Step S530: Perform sequence advancement decision processing based on the matching deviation field and the relative velocity in the real-time data stream. Calculate the dynamic decision threshold using a velocity adaptive convergence algorithm. When the overall deviation value is lower than the dynamic threshold, output the index identifier of the next target node.

[0074] In real-time matching, firstly, the visual features of the cone-shaped sleeve in the real-time image are spatially aligned with the sensor center coordinates through multimodal feature fusion processing. A sub-pixel edge extraction algorithm constrained by the center coordinates is used to enhance the contour localization accuracy of the image segmentation mask within the spatial reference framework provided by the sensor, effectively suppressing image blurring and edge jitter caused by airflow disturbances, and generating high-confidence cone-shaped sleeve contour data that is spatiotemporally synchronized. Then, based on a dynamic template reconstruction mechanism, the cone-shaped sleeve contour data, real-time equivalent radius, and preset annular geometric parameters are fused. The display size of the target annular template is dynamically adjusted using a radius scaling compensation function to adapt to the real-time deformation characteristics of the cone-shaped sleeve under hydrodynamic forces. Next, a projection spatial registration algorithm is used to calculate the pixel-level deviation field between the real-time contour and the dynamic template, and each deviation vector is assigned a confidence weight based on contour integrity. Finally, a sequence advancement decision is made by combining relative velocity parameters: a velocity-adaptive dynamic convergence threshold function is designed. When the weighted average deviation value is lower than the threshold boundary that increases with velocity, the current node is considered to have completed matching and the index identifier is updated, achieving robust advancement of the docking process in turbulent environments.

[0075] Further, step S600 includes steps S610 to S630.

[0076] Step S610: Perform target node tracking processing based on the index identifier, obtain the field coordinates and size parameters of the current target cone sleeve by querying the standard node sequence, and obtain the over-boundary detection input data;

[0077] Step S620: Perform display domain boundary determination processing based on the out-of-bounds detection input data. By solving the shortest Euclidean distance between the target node's field of view coordinates and the effective display range of the HUD, an out-of-bounds status flag is output when the distance is less than or equal to the dynamic boundary threshold.

[0078] Step S630: Calculate the deviation vector based on the over-boundary state flag, establish a mapping function based on the spatial geometric relationship between the center line of the light column and the target node position, and calculate and output the final docking correction parameter vector.

[0079] In the guided state transition process, the index identifier is first mapped to the standard node sequence through target node tracking, and the field coordinates and size parameters of the current target cone are extracted to construct a boundary detection input dataset containing spatial position and visual size. Then, the shortest Euclidean distance between the target node's field coordinates and the effective display boundary (left / right / upper / lower boundary) of the HUD is calculated based on the display domain boundary determination algorithm. A dynamic boundary threshold model is introduced. When the detection distance is less than or equal to the threshold, it is determined that the cone is about to move out of the visible area, triggering the boundary state flag. Finally, the deviation vector calculation is initiated based on the boundary state flag. The direction vector of the light column centerline is coupled with the spatial coordinates of the target node through the spatial geometric mapping function: a local coordinate system with the light column projection reference point as the origin is constructed, and the screen coordinate deviation is converted into the pitch correction angle and azimuth correction angle of the oil gun in the relative space, generating a three-dimensional correction parameter vector to realize closed-loop control from display plane anomaly to physical space calibration.

[0080] Further, step S630 includes steps S631 to S633.

[0081] Step S631: Based on the over-boundary state flag, construct the light column reference. Solve the projection reference point of the light column centerline in the field of view coordinate system by analyzing the linear parametric equation of the light column and the display unit space matrix to obtain the light column reference coordinate system.

[0082] Step S632: Perform offset decomposition processing based on the optical column reference coordinate system. Separate the position deviation into radial offset and azimuth deflection angle through polar coordinate system transformation to obtain the geometric deviation vector.

[0083] Step S633: Perform flight dynamic compensation processing based on the geometric deviation vector, and generate the final docking correction parameter vector based on the preset distance attenuation function and attitude coupling correction function.

[0084] Specifically, firstly, the linear parametric equations of the light pillar are analyzed by constructing a reference system. Then, the reference projection point of the light pillar centerline on the field of view plane is solved using the spatial projection matrix of the display unit, establishing an orthogonal reference coordinate system. Next, based on this coordinate system, the two-dimensional deviation between the target node's field of view coordinates and the reference point is converted into polar coordinates. The radial offset, representing the degree of positional deviation, and the azimuth deflection angle, indicating the direction of deviation, are separated, forming a geometric deviation vector with physical meaning. Finally, real-time environmental parameters are fused through flight dynamic compensation processing. A distance attenuation function is applied to weight the radial offset by distance, and an attitude coupling correction matrix is ​​introduced to compensate for the roll angle rotation transformation of the azimuth angle, generating the final docking correction parameter vector for the spatial control quantity mapping. The distance attenuation function is:

[0085]

[0086] in, Indicates the distance attenuation coefficient; Indicates the reference distance; Indicates the reference distance; Indicates the attenuation characteristic length; Represents the natural base.

[0087] The attitude coupling correction function is:

[0088]

[0089] in, This represents the final docking correction parameter vector; Represents the original deviation vector; This indicates the roll angle of the flight platform.

[0090] Example 2:

[0091] like Figure 2 As shown, this embodiment provides a visual aid display device based on expected motion position matching. The device includes:

[0092] The acquisition module 901 is used to acquire the historical trajectory dataset of the successful docking of the flight platform, as well as the real-time data of the current flight platform. The real-time data includes the coordinates of the center point of the cone, the equivalent radius, the relative speed, and the real-time image.

[0093] Modeling module 902 is used to perform baseline trajectory modeling processing based on historical trajectory datasets to obtain baseline spatial trajectory functions;

[0094] The extraction module 903 is used to parameterize nodes according to the reference space trajectory function to obtain a standardized node sequence containing at least two target cone positions and corresponding dimensions;

[0095] The conversion module 904 is used to perform visual mapping based on the standardized node sequence, obtain the static light column line parameters through projection transformation of the fixed oil gun installation angle, and calculate the expected field coordinates and scaling factor of the cone sleeve at each node based on the perspective projection model to generate a set of circular geometric parameters.

[0096] The matching module 905 is used to match the real-time data stream with the set of geometric parameters of the annulus. By calculating the pixel deviation between the real-time image and the annulus template, it outputs the index identifier of the next target node.

[0097] The output module 906 is used to guide the state transition based on the index identifier, calculate the beam alignment deviation vector by detecting the target node's field of view coordinates against the over-boundary state of the display boundary, and output the final docking correction parameter vector.

[0098] In one specific embodiment of this application, the modeling module 902 includes:

[0099] The first modeling unit is used to perform time synchronization processing based on the historical trajectory dataset. By aligning multiple sets of historical trajectory data to a unified time reference, a synchronized spatiotemporal coordinate sequence is obtained.

[0100] The second modeling unit is used to perform dynamic constraint compression processing based on the synchronized spatiotemporal coordinate sequence, and to filter trajectory points that conform to the laws of physical motion based on a preset acceleration threshold to obtain an optimized trajectory point set.

[0101] The third modeling unit is used to construct a continuous trajectory function based on the optimized trajectory point set. It fits the spatial path through a B-spline basis function that preserves multi-order continuity to obtain the reference spatial trajectory function.

[0102] In one specific embodiment of this application, the extraction module 903 includes:

[0103] The first extraction unit is used to extract the oscillation features of the conical sleeve motion based on the reference spatial trajectory function. By separating the extreme points of the normal acceleration of the trajectory function from the swing phase reversal points, the key feature point set of the conical sleeve swing is obtained.

[0104] The second extraction unit is used to divide the turbulence-affected zone according to the key feature point set. Based on the historical distribution data of the wake disturbance of the flight platform, the trajectory is divided into a stable approach segment and an oscillation correction segment to obtain the aerodynamic characteristic graded trajectory segment.

[0105] The third extraction unit is used to perform visual adaptive sampling processing on the graded trajectory segments according to aerodynamic characteristics. It performs super-density sampling on the oscillation correction segment through the principle of near-end perspective distortion enhancement to generate a standardized node sequence for size deformation compensation.

[0106] Example 3:

[0107] Corresponding to the above method embodiments, this embodiment also provides a visual aid display device based on expected motion position matching. The visual aid display device based on expected motion position matching described below and the visual aid display method based on expected motion position matching described above can be referred to in correspondence with each other.

[0108] Figure 3 This is a block diagram illustrating a visual aid display device 800 based on expected motion position matching according to an exemplary embodiment. Figure 3 As shown, the visual aid display device 800 based on expected motion position matching may include: a processor 801 and a memory 802. The visual aid display device 800 based on expected motion position matching may also include one or more of the following: a multimedia component 803, an I / O interface 804, and a communication component 805.

[0109] The processor 801 controls the overall operation of the visual aid display device 800 based on expected motion position matching to complete all or part of the steps in the aforementioned visual aid display method based on expected motion position matching. The memory 802 stores various types of data to support the operation of the visual aid display device 800 based on expected motion position matching. This data may include, for example, instructions for any application or method operating on the visual aid display device 800 based on expected motion position matching, as well as application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 802 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 805 is used for wired or wireless communication between the vision-assisted display device 800, which is based on expected motion position matching, and other devices. Wireless communication includes, for example, Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or one or more combinations thereof. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0110] In an exemplary embodiment, the visual aid display device 800 based on expected motion position matching may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the aforementioned visual aid display method based on expected motion position matching.

[0111] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the visual aid display method based on expected motion position matching described above. For example, the computer-readable storage medium may be the memory 802 including the program instructions described above, which may be executed by the processor 801 of the visual aid display device 800 based on expected motion position matching to complete the visual aid display method based on expected motion position matching described above.

[0112] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0113] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A visual aid display method based on expected motion position matching, characterized in that, include: Acquire historical trajectory datasets of successful docking of the flight platform, as well as real-time data of the current flight platform. The real-time data includes the coordinates of the cone center point, equivalent radius, relative speed, and real-time images. Based on the historical trajectory dataset, a baseline trajectory modeling process is performed to obtain a baseline spatial trajectory function; Node parameterization is performed based on the reference spatial trajectory function to obtain a standardized node sequence containing at least two target cone sleeve positions and corresponding dimensions; Visual mapping is performed based on the standardized node sequence. Static light column line parameters are obtained by projection transformation with a fixed oil gun installation angle. The expected field coordinates and scaling factor of the cone sleeve at each node are calculated based on the perspective projection model to generate a set of circular geometric parameters. The real-time data stream is matched with the set of geometric parameters of the annulus. The pixel deviation between the real-time image and the annulus template is calculated, and the index identifier of the next target node is output. The guided state transition is performed based on the index identifier. The alignment deviation vector of the light column is calculated by detecting the field coordinates of the target node against the out-of-bounds state of the display boundary, and the final docking correction parameter vector is output.

2. The visual aid display method based on expected motion position matching according to claim 1, characterized in that, Based on the historical trajectory dataset, a baseline trajectory modeling process is performed to obtain a baseline spatial trajectory function, including: Based on the historical trajectory dataset, time synchronization processing is performed. By aligning multiple sets of historical trajectory data to a unified time reference, a synchronized spatiotemporal coordinate sequence is obtained. Based on the synchronized spatiotemporal coordinate sequence, dynamic constraint compression processing is performed, and trajectory points that conform to the laws of physical motion are selected based on a preset acceleration threshold to obtain an optimized trajectory point set; The optimized trajectory point set is used to construct a continuous trajectory function. The spatial path is then fitted using a B-spline basis function that preserves multi-order continuity to obtain the baseline spatial trajectory function.

3. The visual aid display method based on expected motion position matching according to claim 1, characterized in that, Based on the reference spatial trajectory function, node parameterization is performed to obtain a standardized node sequence containing at least two target cone sleeve positions and corresponding dimensions, including: Based on the reference spatial trajectory function, the cone sleeve motion oscillation feature extraction process is performed. By separating the extreme points of the normal acceleration of the trajectory function and the swing phase reversal points, the key feature point set of the cone sleeve swing is obtained. Based on the set of key feature points, the turbulence-affected sections are divided. Based on the historical distribution data of the wake disturbance of the flight platform, the trajectory is divided into a stable approach section and an oscillation correction section to obtain aerodynamic characteristic graded trajectory segments. Based on the aerodynamic characteristics graded trajectory segments, visual adaptive sampling processing is performed. The oscillation correction segment is subjected to super-density sampling through the near-end perspective distortion enhancement principle to generate a standardized node sequence for size deformation compensation.

4. The visual aid display method based on expected motion position matching according to claim 1, characterized in that, Visual mapping is performed based on the standardized node sequence. Static light column line parameters are obtained through projection transformation with a fixed oil gun installation angle. The expected field-of-view coordinates and scaling factors of the cone sleeve at each node are calculated based on the perspective projection model, generating a set of annular geometric parameters, including: Based on the cone sleeve position coordinates in the standardized node sequence, coordinate system alignment is performed. By transforming the world coordinate system to a local coordinate system with the oil gun base point as the origin, the oil gun relative spatial coordinate set is obtained. Static light column generation is performed based on the relative spatial coordinate set of the oil gun. The direction vector of the light column is solved by the fixed projection relationship of the oil gun installation angle, and the straight line parameters of the static light column are output. Based on the conical sleeve size parameters in the standardized node sequence and the relative spatial coordinate set of the oil gun, perspective geometry calculation is performed. The ring display size is calculated using the pinhole camera model and the viewing distance scaling ratio, and a set of ring geometric parameters is generated.

5. The visual aid display method based on expected motion position matching according to claim 1, characterized in that, Matching the real-time data stream with the set of annular geometric parameters, and calculating the pixel deviation between the real-time image and the annular template, the index identifier of the next target node is output, including: Multimodal feature fusion processing is performed on the real-time images in the real-time data stream, and the positioning accuracy is enhanced by the edge extraction algorithm constrained by the center coordinates to obtain spatiotemporally synchronized cone sleeve contour data; Dynamic template reconstruction is performed based on the conical sleeve contour data, the coordinates of the conical sleeve center point in the real-time data stream, the equivalent radius, and the set of geometric parameters of the annulus. The size of the target annulus is adjusted through a radius scaling compensation mechanism and projection space registration is performed to obtain a matching deviation field with confidence weights. Sequence advancement decision processing is performed based on the matching deviation field and the relative velocity in the real-time data stream. A dynamic decision threshold is calculated using a velocity adaptive convergence algorithm. When the overall deviation value is lower than the dynamic threshold, the index identifier of the next target node is output.

6. The visual aid display method based on expected motion position matching according to claim 1, characterized in that, Guided state transition is performed based on the index identifier. The alignment deviation vector of the optical column is calculated by detecting the target node's field-of-view coordinates against the out-of-bounds state of the display boundary, and the final docking correction parameter vector is output, including: The target node is tracked according to the index identifier. The field coordinates and size parameters of the current target cone are obtained by querying the standard node sequence, and the over-boundary detection input data is obtained. Based on the out-of-bounds detection input data, the display domain boundary determination process is performed. By solving the shortest Euclidean distance between the target node's field of view coordinates and the effective display range of the HUD, an out-of-bounds status flag is output when the distance is less than or equal to the dynamic boundary threshold. The deviation vector is calculated based on the super-boundary state flag. A mapping function is established based on the spatial geometric relationship between the center line of the light column and the target node position. The final docking correction parameter vector is calculated and output.

7. The visual aid display method based on expected motion position matching according to claim 6, characterized in that, Based on the aforementioned over-boundary state flag, a deviation vector is calculated. A mapping function is established based on the spatial geometric relationship between the beam centerline and the target node position. The final docking correction parameter vector is calculated and output, including: The light column reference is constructed based on the aforementioned over-boundary state flag. The projection reference point of the light column centerline in the field of view coordinate system is obtained by analyzing the linear parametric equation of the light column and the spatial matrix of the display unit. Based on the optical column reference coordinate system, offset decomposition processing is performed, and the position deviation is separated into radial offset and azimuth deflection angle through polar coordinate system transformation to obtain the geometric deviation vector. Flight dynamic compensation is performed based on the geometric deviation vector, and the final docking correction parameter vector is generated based on the preset distance attenuation function and attitude coupling correction function.

8. A visual aid display system based on expected motion position matching, characterized in that, include: The acquisition module is used to acquire historical trajectory datasets of successful docking of the flight platform, as well as real-time data of the current flight platform. The real-time data includes the coordinates of the cone center point, the equivalent radius, the relative speed, and real-time images. The modeling module is used to perform baseline trajectory modeling processing based on the historical trajectory dataset to obtain a baseline spatial trajectory function; The extraction module is used to parameterize nodes according to the reference spatial trajectory function to obtain a standardized node sequence containing at least two target cone positions and their corresponding dimensions; The conversion module is used to perform visual mapping based on the standardized node sequence, obtain the static light column line parameters through projection transformation of the fixed oil gun installation angle, and calculate the expected field coordinates and scaling factor of the cone sleeve at each node based on the perspective projection model to generate a set of circular geometric parameters. The matching module is used to match the real-time data stream with the set of geometric parameters of the annulus, and output the index identifier of the next target node by calculating the pixel deviation between the real-time image and the annulus template. The output module is used to guide the state transition according to the index identifier, calculate the beam alignment deviation vector by detecting the target node's field of view coordinates against the display boundary's out-of-bounds state, and output the final docking correction parameter vector.

9. The visual aid display system based on expected motion position matching according to claim 8, characterized in that, The modeling module includes: The first modeling unit is used to perform time synchronization processing based on the historical trajectory dataset, and obtain a synchronized spatiotemporal coordinate sequence by aligning multiple sets of historical trajectory data to a unified time reference. The second modeling unit is used to perform dynamic constraint compression processing based on the synchronized spatiotemporal coordinate sequence, and to filter trajectory points that conform to the laws of physical motion based on a preset acceleration threshold to obtain an optimized trajectory point set. The third modeling unit is used to construct a continuous trajectory function based on the optimized trajectory point set, and to obtain the reference spatial trajectory function by fitting the spatial path through a B-spline basis function that preserves multi-order continuity.

10. The visual aid display system based on expected motion position matching according to claim 8, characterized in that, The extraction module includes: The first extraction unit is used to extract the oscillation features of the conical sleeve motion based on the reference spatial trajectory function. By separating the extreme points of the normal acceleration of the trajectory function from the swing phase reversal points, the key feature point set of the conical sleeve swing is obtained. The second extraction unit is used to divide the turbulence-affected zone according to the set of key feature points. Based on the historical distribution data of the wake disturbance of the flight platform, the trajectory is divided into a stable approach segment and an oscillation correction segment to obtain the aerodynamic characteristic graded trajectory segment. The third extraction unit is used to perform visual adaptive sampling processing on the graded trajectory segments according to the aerodynamic characteristics, and to perform super-density sampling on the oscillation correction segment through the near-end perspective distortion enhancement principle to generate a standardized node sequence for size deformation compensation.

Images