733 results about "Global coordinate system" patented technology

The invention belongs to the technical field of tunnel inspection and auxiliary rescue, and particularly discloses an unmanned aerial vehicle multi-source fusion inspection and auxiliary rescue method based on an urban tunnel, multiple sensors are integrated on an unmanned aerial vehicle platform, and multi-source data are processed through a dynamic weighting factor graph optimization method based on a sliding window. By introducing a Mahalanobis distance consistency test mechanism, dynamically evaluating the consistency between sensor observation data and IMU prediction data, screening out data with high credibility, and endowing each factor with different optimization weights, the better the quality of the sensor observation data is, the higher the factor weight is, so that the robustness of final target estimation is improved, and the target estimation accuracy is improved. And then uniformly converting sensor data at each moment into a global coordinate system by using an SLAM framework, gradually constructing a three-dimensional map of the tunnel, and finally realizing high-precision real-time positioning of the unmanned aerial vehicle and construction of the three-dimensional map of the tunnel for subsequent inspection and auxiliary rescue tasks.

The invention relates to a common-field-of-view-free camera external parameter calibration method and system based on a laser tracker. The method comprises the following steps: firstly, setting a laser tracker and defining a global coordinate system based on calibration of external parameters of a common-field-of-view-free camera of the laser tracker; for each single camera, if no common view exists between the single camera and the tracker, the tracker is transferred to the position with the common view, a temporary calibration plate is arranged, and the pose relation between the temporary calibration plate and the global coordinate system is calculated; when a public view exists, a calibration plate with a target seat is arranged in the public view, a laser tracker is used for measuring coordinates of a target ball, a camera is used for measuring coordinates of a conversion ball, a target ball coordinate system and a conversion ball coordinate system are respectively established and unified, and therefore the pose relation between the camera and the calibration plate and the pose relation between the calibration plate and the global coordinate system are calculated; and finally, obtaining external parameters of the common-field-of-view-free camera by combining all pose relationships. Compared with the prior art, the method has the advantages that the external parameters of the camera can be accurately and efficiently acquired when the camera system without the public view field is processed, the anti-interference capability is strong, the efficiency is high and the like.

The invention provides a property system virtual-real mapping inspection method, device and equipment based on digital twinning and a medium, and belongs to the technical field of property inspection. Real-time mapping of an equipment entity and a virtual model is achieved through layered design of a physical layer, a data layer, a twinning layer and an application layer; collecting static / dynamic data and reducing noise, and establishing a global coordinate system; constructing a 1: 1 parameterized model and binding equipment attributes; the state analysis model is used for evaluating the equipment health degree, and virtual-real identification and work order visualization are triggered when abnormity occurs; the inspection path is dynamically optimized, and the processing efficiency is improved in combination with AR assistance and dual-stage verification; and finally, updating the model weight and adjusting the inspection strategy through data-driven acceptance feedback. Real-time synchronization and intelligent decision making of the equipment state are realized, the inspection efficiency is improved, the fault omission ratio is reduced, the resource allocation is optimized, and the operation and maintenance transparency and reliability are enhanced.

The invention discloses an anti-collision monitoring system based on a depth estimation and instance segmentation fused three-dimensional model, particularly relates to the field of intelligent driving security and protection, is used for solving the problem of target recognition and anti-collision in an environment, realizes efficient feature extraction of global semantics and local textures through a multi-branch network structure, and ensures the accuracy and comprehensiveness of target segmentation. In combination with a cross-frame identity association and conflict detection mechanism, the consistency of target identities is effectively maintained, and the mismatching problem caused by shielding or similar appearances is reduced; multi-scale space-time shielding mode analysis and boundary motion consistency verification are adopted, a fusion algorithm is utilized to comprehensively evaluate shielding complexity and segmentation robustness, a high-risk shielding area is identified, secondary difference correction is executed, and space positioning information of a target is remarkably optimized; and finally, integrating the optimized segmentation and depth data into a global coordinate system, constructing a high-precision and coherent three-dimensional semantic scene, and providing stable and high-quality input data for collision detection and trajectory prediction.

The invention relates to the technical field of optical detection and calibration, in particular to an optical detection and calibration method based on a laser cross calibration method, which comprises the following steps of: 1, suppressing dynamic ambient light and adjusting laser parameters; step 2, extracting anti-distortion feature points; 3, multi-view error collaborative optimization: inputting the corrected coordinates output in the step 2 and mechanical motion parameters of a rotating shaft encoder into a splicing optimization model, constructing a coordinate transformation matrix with curvature constraint, and obtaining a three-dimensional calibration point cloud under a global coordinate system through iterative optimization; and 4, dynamic closed-loop compensation: dynamically correcting the laser power compensation coefficient in the step 1 and the distortion correction parameter in the step 2. Through close cooperation of multiple steps, high-precision, stable and self-adaptive laser calibration is realized, and reliable optical detection and calibration results can be provided in various environments and working conditions.

The invention relates to the technical field of image compensation, in particular to a reflection compensation method based on image processing, and provides the following scheme: acquiring an environment panoramic image by using a panoramic camera to establish a scene global coordinate system, and acquiring a multi-view original image in combination with a camera array arranged in the circumferential direction of an object; determining a rotation symmetry axis according to the multi-view contour features, reconstructing a three-dimensional geometric body, and calculating normal distribution and curvature change; generating a prediction image based on diffuse reflection and specular reflection hypothesis in the surface expansion domain through virtual visual angle disturbance, identifying a reflection region according to color and gradient consistency, and generating a reflection mask; and performing texture reconstruction on the reflective area by using geometric registration and multi-view compensation, and finally performing splicing and fusion to obtain a non-reflective high-fidelity panoramic image. The method does not need to change the field illumination condition, and can achieve the precise recognition and compensation of the complex curved surface reflection in the cultural relic in-situ collection environment.

The invention relates to a road section risk early warning method based on thunder-vision fusion perception, and the method comprises the following steps: S1, obtaining the high-precision space-time position information of a vehicle in a tunnel through the multi-source information fusion of a millimeter-wave radar and machine vision; s2, mapping the vehicle position under the global coordinate system to a coordinate system expanded along a road center line, and representing the vehicle position as a longitudinal projection position and a transverse offset along the road direction; s3, under the coordinate system, taking anti-collision time as a core index, combining lane judgment and relative speed, constructing a dynamic longitudinal risk grading model, and performing linkage triggering with a warning system; s4, constructing a regional risk integral model; and S5, speed limiting information is issued to all driving-in vehicles in real time through the variable speed limiting screen, and the rear-end collision risk is actively prevented and controlled. According to the method, the sudden risk response time can be shortened, the speed limit control response precision can be improved, the rear-end collision rate of the diversion and convergence areas can be reduced, false alarm interference can be reduced, and the tunnel driving safety and the information guiding efficiency can be improved.

The invention relates to the technical field of computer vision and artificial intelligence, and discloses a computer vision-based hundred-million-pixel panoramic situation awareness method and system, and the method comprises the steps: synchronously collecting original local field-of-view images through multiple cameras; independently executing target detection and semantic segmentation in an original image domain; constructing local-to-global coordinate mapping based on the calibration parameters; projecting the target features to a global coordinate system and detecting a cross-view-field target; extracting multi-view-field texture, edge and color features, and performing weighted fusion according to a visible area; according to the method, through identification preposition and semantic level feature fusion, geometric splicing distortion is avoided, the cross-boundary identification precision is improved, the calculation load is reduced, target continuous tracking and situation real-time output in a high-density scene are realized, and the method has high engineering suitability and industrial popularization value.

The invention discloses an interferometer error calibration method and device and a computer readable storage medium, and belongs to the technical field of measurement equipment.The method comprises the steps that measurement data collected when an interferometer moves on the x / y axis of a motion table is obtained, and x / y axis compensation amount is generated through calculation processing; meanwhile, a coordinate system transformation matrix is established and optimized by using data of a marking plate arranged on a motion table, and x-axis and y-axis non-orthogonal parameters are obtained. And then the compensation amount and the non-orthogonal parameters are input into a preset kinematic model, and the accurate position of the motion platform under the global coordinate system is calculated in real time. And when a preset updating condition is met, dynamically updating the error compensation value of the interferometer through the deviation between the actual position detected by the visual system and the calculated position. Reflector surface type error compensation and non-orthogonal parameter correction are fused, and high-precision error compensation calibration of the interferometer is achieved.

The invention discloses a dynamic unmanned aerial vehicle cluster electromagnetic characteristic modeling method and system based on a digital array radar, and the method specifically comprises the steps: setting radar system parameters, building a time-varying motion model of an unmanned aerial vehicle cluster, and obtaining the formation pose distribution of the unmanned aerial vehicle cluster under a global coordinate system; component decomposition is carried out on an unmanned aerial vehicle CAD model, shielding analysis is carried out under the radar sight line constraint condition, time-varying scattering center parameter extraction is carried out according to the dynamic electromagnetic effect between targets, scattering center space distribution of an unmanned aerial vehicle cluster is updated in a time sequence recursion mode, and construction of a time-varying scattering center model is completed; a radar system signal model is constructed according to digital array radar DAR parameters, multi-dimensional dynamic feature extraction and parameter mapping are carried out, digital array radar multichannel signal modulation and unmanned aerial vehicle cluster target radar echo construction are completed, and radar scattering electromagnetic characteristic modeling of a dynamic unmanned aerial vehicle cluster is realized. According to the method, the model description accuracy is improved, and the calculation process is more efficient.

The invention discloses a high-precision point cloud map construction method based on pose map optimization, and the method comprises the steps: preliminarily detecting the observation reliability of each frame of GNSS, and screening credible data; a priori factor is constructed for initial position GNSS signal quality, and map coordinate anchoring is completed; estimating a relative pose between adjacent frames, and constructing an inter-frame constraint edge; scanning context global descriptors are introduced to realize efficient screening and accurate matching of loopback candidate frames; further evaluating the quality of the GNSS by using a loopback detection result and the pose of the laser odometer, setting a GNSS factor weight, and constructing a GNSS factor edge; constructing a complete pose graph model, performing overall optimization on all pose nodes by using a nonlinear optimization method, and correcting accumulative errors; and converting the laser point cloud into a global coordinate system, and splicing to generate a global consistent high-precision point cloud map. According to the invention, the global positioning capability of the high-quality GNSS data and the local geometric precision of the laser point cloud can be effectively fused, and the high-precision point cloud map can be continuously and stably constructed.

The invention provides a method for automatically calibrating collected data of high-precision measurement and control deformation monitoring equipment, and belongs to the technical field of wind tunnel inner profile measurement. Multi-equipment clock synchronization is realized by establishing a unified time reference system, and measurement data of different frequencies are processed by adopting a CPU-GPU heterogeneous parallel processing architecture, so that the measurement accuracy is improved. The method comprises the following steps: performing three-level alignment on time, space and precision dimensions by using a multi-level clustering algorithm, eliminating clock differences among equipment by using a clock drift correction equation set, establishing a space coordinate system conversion matrix to unify a global coordinate system, and performing adaptive data fusion according to a precision weight by using a Kalman filtering fusion algorithm. And a data quality evaluation system is established to ensure the accuracy of a calibration result, a high-precision calibration data set is finally output, and the technical problem that the measurement precision is reduced due to space-time inconsistency of heterogeneous data of multiple devices is solved.

The invention discloses an underground environment laser radar and millimeter wave radar cooperative SLAM method, and relates to unmanned driving positioning. The method comprises the following steps: collecting point cloud data of an underground environment by using a laser radar, and carrying out filtering processing; collecting target data by using a millimeter wave radar and carrying out filtering processing; curvature-based feature extraction is carried out on the preprocessed point cloud data to obtain a point cloud feature set, spatial correlation is carried out on a target point set with a speed label and the point cloud feature set, point cloud features corresponding to a dynamic target are identified and eliminated according to the speed label, and a static environment feature set is obtained; inter-frame matching and pose estimation are carried out based on the static environment feature set, a static target in a target point set with a speed label is used as an additional constraint, and an optimized pose sequence is obtained through a graph optimization method; and projecting the static environment feature set to a global coordinate system according to the optimized pose sequence, and constructing a static environment map. According to the invention, the interference of the dynamic target on the SLAM is avoided.

The invention relates to the technical field of intelligent welding, in particular to a distributed reinforcement learning control method and system for multi-robot cooperative welding, each welding robot collects vision measurement information under a global coordinate system by using a local vision sensor, and forms self observation information in combination with robot state information obtained by a self-sensor; the information is input into respective Actor-Critic networks, an Actor-Critic algorithm is executed, control actions are generated, welding operation is achieved, visual measurement information between the robots is shared through a 5G communication network, cooperation efficiency is enhanced, the Actor-Critic networks are trained with a cross entropy loss function as a target and with a two-norm of an action value as a constraint condition, and the robot vision measurement information is obtained. The target network adopts a soft update algorithm, the parameter update efficiency is improved, the central control bottleneck is eliminated by the distributed reinforcement learning architecture, and the robustness and reliability of the system are enhanced.

The invention relates to a BEV space drivable area boundary automatic marking method based on a point cloud, and the method comprises the steps: obtaining a continuous frame point cloud data stream and corresponding positioning data, and separating ground and non-ground point clouds through a pavement segmentation algorithm; and distinguishing initial dynamic and static point clouds, and eliminating static point cloud noise. And projecting the ground point cloud to a global coordinate system, and combining multiple frames to generate a dense global ground point cloud. Dividing point clouds into voxel grids according to an XY plane, extracting static obstacle point clouds and updating ground point clouds; and projecting the static obstacle point cloud to a global coordinate system to generate a dense static point cloud. Misclassified ground points in the initial dynamic point clouds are removed to obtain dynamic obstacle point clouds, and the dynamic obstacle point clouds and the static point clouds are combined into comprehensive obstacle point clouds. And on the basis of the updated ground point cloud and the comprehensive obstacle point cloud, generating a drivable area boundary in the BEV view through a ray scanning algorithm, and outputting the drivable area boundary to a user interaction interface, so that high-precision automatic marking is realized, obstacles in any form are covered, and the manual marking cost is reduced.

The invention provides a multi-dimensional map generation method and device based on multi-sensor tight coupling SLAM. The method comprises the following steps: acquiring image data, point cloud data and inertial data acquired by using a predetermined sensor combination; state propagation is carried out based on the inertial data, and positioning output under a global coordinate system and an estimation result used for point cloud position correction are obtained; generating a three-dimensional map and a semantic map; geometric elements are extracted based on the three-dimensional map, and a geometric annotation map is formed by global coordinates according to the geometric elements; projecting the spatial information to a plane, and superposing ground color textures from the image data to generate a two-dimensional texture grid map; and associating the positioning output, the three-dimensional map, the semantic map, the geometric annotation map and the two-dimensional texture grid map, and providing an association result for a positioning and path planning module of the mobile equipment to call. The multi-dimensional map can be synchronously output through one-time mapping, the coordinates of the four layers are uniformly updated in real time, and the manual labeling cost is remarkably reduced.

The invention relates to a tunnel three-dimensional holographic splicing method and device for panoramic array camera networking, and the method comprises the steps: enabling a reference transmission camera array and a three-dimensional laser scanner on an inspection vehicle to move to different inspection positions along with the inspection vehicle for adjustment, achieving the transmission of peripheral control information at two ends of a tunnel into a measurement region, and constructing a dynamic control field; the limitation on measurement conditions is reduced; high-precision positioning and attitude determination are carried out based on fixed connection constraints of a look-around camera array and a three-dimensional laser scanner and a constructed dynamic control field, so that a measurement platform is unified to a global coordinate system, and the inherent defect of large accumulative error of a traditional three-dimensional modeling method is effectively avoided; and then the high-resolution look-around image is mapped to the three-dimensional point cloud data under the global coordinate system, so that high-resolution and high-precision three-dimensional holographic splicing of the tunnel ring surface under the global coordinate system is realized, global and local high-resolution and high-precision are achieved, and the acquisition precision of the tunnel three-dimensional hologram is greatly improved.

The invention provides a high-dynamic deformation measurement system and method based on laser section contour differential scanning. The measurement system is composed of a section contour measurement unit, a calibration unit, an error compensation unit and a data processing unit, wherein the section contour measurement unit comprises a multi-sight-line structured light sensor module, a speed sensing module and a distance measurement module; the calibration unit comprises a synchronous control module, an adjustment module and a common tooth-shaped calibration target; the error compensation unit comprises a vibration detection module, a posture detection module and a temperature detection module; the data processing unit is a device with programming and computing functions. The measuring method comprises the following steps: (1) calibrating a laser plane and an image plane; (2) unifying a global coordinate system; (3) obtaining point cloud data; (4) error compensation; (5) constructing a deformation time-history model; and (6) carrying out maximum deformation global optimization. According to the measurement system and method, accurate expression and maximum value global optimization of a pavement micro-deformation three-dimensional space under the load effect can be realized.

The invention belongs to the technical field of measurement and positioning, and particularly relates to an aircraft manufacturing measurement and positioning method, which deeply combines an interference networking measurement method and a space coordinate measurement method of a laser tracker, adopts interference networking to construct a global coordinate system # imgabs0 # by reference control TB points in a small amount of open space, and performs re-system by reference control TB points in an effective distance measurement range. According to the method, an expanded reference ERS point is expanded, a local expanded reference system # imgabs1 # is established to measure and position a local measurement object, the sequence and boundary of global measurement and local measurement in the measurement process according to size chain superposition are defined, and the method has high measurement precision.

The invention provides a small target detection method and device based on a high-resolution fusion feature map. The method comprises the following steps: dividing an image to be detected into a plurality of overlapped sub-regions and recording position information of the overlapped sub-regions; performing feature extraction and multi-scale fusion on each sub-region to generate a high-resolution fusion feature map; generating geometric parameters and initial confidence of candidate frames based on each spatial position on the image, and performing preliminary screening to obtain a candidate frame set of the sub-regions; mapping candidate frames in all the candidate frame sets to a global coordinate system according to the position information, and combining repeated candidate frames pointing to the same small target to form a global candidate frame set; for each candidate frame in the global candidate frame set, cutting a local image area in the to-be-detected image to carry out fine judgment to obtain a fine trimming confidence coefficient; and fusing the initial confidence coefficient and the refined confidence coefficient to obtain a comprehensive confidence coefficient, and outputting a final small target detection result according to a comparison result of the comprehensive confidence coefficient and an adaptive threshold value. According to the invention, the tiny target in the image can be accurately captured.

The invention discloses a free curve feature design optimization method, which comprises the following steps of: constructing a free curve feature region containing a central bus, and setting the direction and the position of the central bus to obtain a free curve feature region; a two-dimensional coordinate transformation formula is adopted to transform the free curve characteristic area from a global coordinate system to a local coordinate system with a central bus as an X axis, and bending control of the structure in any direction is achieved; a height function is utilized to describe changes of a longitudinal boundary, an implicit modeling mode is adopted to construct a region boundary with a longitudinal coordinate smaller than a height function value, and adjustability of the longitudinal form of a feature region is achieved by controlling parameters of the height function. The method has the advantages that through free curve feature modeling, flexible expression of a complex structure form and precise boundary control are achieved; meanwhile, by taking control parameters as design variables and combining an iterative optimization algorithm, the structural layout is optimized, the performance is improved, the boundary is ensured to be clear, and dual optimization of the structural performance and the design freedom degree is achieved.

The invention discloses a method for optimizing micro-crack segmentation based on deep learning and super-resolution reconstruction, and the method comprises the steps: cutting an image in real time, obtaining an image block which takes a component as a target main body, and synchronously recording a homography matrix for geometric mapping; selecting an amplification strategy to improve the resolution, and recording a scale mapping relation; inputting the enhanced image block into a double-flow network; adaptive fusion and reconstruction are carried out on the two branch features, and a high-resolution texture image is output; generating a geometrically corrected ortho-image, fusing the geometrically corrected ortho-image with original illumination information, and outputting a corrected image with a known pixel size; identifying cracks, spalling and honeycomb diseases in parallel; generating a unified defect confidence map; calculating real geometric parameters of the BIM in a BIM global coordinate system through coordinate back projection; and generating quantitative defect reports and maintenance suggestions. The method has the advantage that seamless connection between the detection result and the BIM global coordinates is realized.

The invention discloses a real scenic spot cloud data and BIM point cloud data fusion method and device, and belongs to the technical field of point cloud registration, and the method comprises the steps: obtaining real scenic spot cloud data of a railway scene; building a building information model BIM of the railway scene; based on the BIM of the railway scene, acquiring BIM point cloud data of the railway scene; performing multiple registration on the BIM point cloud data and the real spot cloud data; converting the registered BIM point cloud data and the real scene point cloud data into a global coordinate system to obtain global point cloud data; and correcting the global point cloud data by taking the geometric consistency function and the global consistency function as constraints to obtain a fusion result of the real scenic spot cloud data and the BIM point cloud data. According to the method, high-precision fusion of the real spot cloud and the BIM point cloud can be realized.

The invention provides a complex heterogeneous molded surface three-dimensional vision measurement method and system, and the method comprises the following steps: (1), extracting part design model features through a semantic segmentation and intelligent recognition method, and building a to-be-measured feature set; (2) a three-dimensional measurement viewpoint planning method based on reinforcement learning is adopted to obtain a viewpoint sequence and a motion path; (3) when the local measurement system reaches a preset viewpoint, a self-adaptive single-pixel imaging feature matching method is adopted for mutual reflection and semitransparent molded surfaces; for other molded surfaces, a parameter adaptive fringe projection three-dimensional measurement method is adopted to obtain a single-viewpoint three-dimensional point cloud; (4) converting the single-viewpoint three-dimensional point cloud into a global coordinate system to realize three-dimensional point cloud splicing; (5) traversing each viewpoint of the viewpoint sequence, and executing the steps (3) and (4) to obtain a multi-viewpoint spliced three-dimensional point cloud; and (6) based on the point cloud error estimation, fusing the multi-view three-dimensional point cloud. The problem of accurate acquisition of the three-dimensional point cloud of the complex heterogeneous molded surface is solved.

The invention discloses a multi-sensor fusion-based obstacle detection and recognition method for a wharf unmanned vehicle, and relates to the technical field of intelligent driving, and the method comprises the steps: setting a maximum threshold value and a minimum threshold value, comparing a sensor coverage rate with the maximum threshold value and the minimum threshold value, executing a sensor increase and decrease strategy, and carrying out the time synchronization of sensor data; obtaining an internal parameter matrix, a distortion coefficient and an external parameter matrix, projecting three-dimensional point coordinates of the point cloud data into two-dimensional coordinates of an image plane, and converting the two-dimensional coordinates in the image data into three-dimensional coordinates in a global coordinate system; labeling the sensor data to obtain a two-dimensional bounding box and a three-dimensional bounding box, and obtaining the category and pose label of an obstacle; building a multi-modal fusion perception model, and training the multi-modal fusion perception model by taking the sensor data and the categories and pose labels of the obstacles as training data; and deploying the optimized multi-modal fusion perception model, and outputting the category and pose information of the obstacle, so that the method is suitable for a complex driving environment.

The invention provides a hydraulic mechanical arm structure control method and system based on data fusion, and the method comprises the steps: firstly initializing a mechanical arm structure and unifying a global coordinate system, then collecting multi-source heterogeneous sensor data in real time, carrying out the data fusion through an unscented Kalman filtering algorithm, and obtaining the real-time high-dimensional state estimation of the mechanical arm structure. According to construction task requirements and obstacle information and spatial constraint conditions of a construction area, the system uses a path generation algorithm to plan an expected trajectory of an end effector in a world coordinate system. And finally, in combination with real-time high-dimensional state estimation and the expected trajectory, an optimal control instruction for driving the mechanical arm frame and the base is generated by applying a control law based on operation space dynamics, and accurate control is achieved. The operation precision and adaptability of the mechanical arm in a complex environment are effectively improved.

The invention discloses a cylindrical roller trajectory tracking method and device, and the cylindrical roller trajectory tracking method comprises the following steps: obtaining an actual measurement displacement sequence of a key point on the end surface of a roller under a global coordinate system based on a multi-reference matching digital image correlation method; drawing a key point displacement curve about key points and time according to the actually measured displacement sequence; judging the motion state of a roller according to the shape characteristics of the key point displacement curve, dividing a smooth part in the key point displacement curve into a rolling area, and dividing a part with jumping or sharp points into a sliding area; calculating the actual revolution angular velocity and the actual rotation angular velocity of the roller based on the actually measured displacement sequence corresponding to the sliding area; according to the method and the device, the image matching precision can be improved, meanwhile, the rolling and sliding components of the roller are accurately distinguished, the precision of the track of the cylindrical roller is improved, and high-precision and visual experimental data are provided for existing dynamics and tribology models.

The invention provides a new energy construction small target full-link safety management and control method based on cross-view feature collaboration and a dynamic anti-interference closed loop, and relates to the field of new energy construction safety management, and the method comprises the steps: S1, deploying a plurality of heterogeneous sensing devices, and collecting the multi-source data of a small target in a construction region; s2, unifying small target features of different visual angles to a global coordinate system of a construction area through coordinate mapping and feature decomposition fusion according to the multi-source data collected in the step S1, and outputting an aligned small target feature map; and S3, adaptively performing multi-scale feature enhancement and lightweight processing according to the aligned small target feature map output in the step S2 and the scale and texture characteristics of the small target, and outputting an initial recognition result of the small target. Small construction targets such as bolts and buckles can be accurately identified, the cross-view space-time dislocation problem of multi-source equipment is solved, dynamic illumination and equipment vibration interference is inhibited, and full-link management and control from data acquisition, feature enhancement and precision calibration to rectification closed loop is realized.

The invention provides a strong nonlinear simulation method and device suitable for a large floating fan, and the method comprises the steps: dividing a target floating fan into a plurality of body structures according to the model parameters of the target floating fan, so as to construct a multi-body model containing a plurality of degrees of freedom, and building a whole machine load and a motion transmission path; the aerodynamic load input of each body structure is calculated, and the nonlinear dynamic response of the blade is calculated according to the aerodynamic load input of each body structure; according to the coordinate transformation relation, the nonlinear dynamic response of the blade is converted into a whole coordinate system and input into a multi-body dynamic model of the whole machine, generalized active force and generalized inertia force of each body structure in the target floating type draught fan are obtained through calculation, and the motion response of each body structure of the target floating type draught fan is obtained through simultaneous solution. According to the scheme, the motion response of each body structure of the target floating fan can be accurately determined, so that the running state of the floating fan in the deep and far sea complex environment can be accurately evaluated.

The invention discloses a tunnel point cloud high-precision splicing method based on rotation and translation constraint, and belongs to the technical field of engineering measurement and three-dimensional laser scanning. The method comprises the following steps: a data acquisition stage: acquiring absolute coordinates and relative point cloud data of each station through collaborative operation of a total station and a frame station scanner, and completing scanning of a target tunnel section; a point cloud data preliminary transformation stage: performing translation transformation on relative point cloud data of each station by using absolute coordinates of a rack station scanner, and preliminarily transforming the relative point cloud data into a global coordinate system; a two-stage registration stage based on rotation translation constraint: carrying out two-stage registration on the relative point cloud data of the adjacent sites after preliminary transformation; and a global point cloud model generation stage: unifying the relative point cloud data of all sites to a tunnel construction global coordinate system through two-stage registration, and generating a complete tunnel three-dimensional point cloud model. According to the invention, through rotation translation constraint and a two-stage registration strategy, the millimeter-level splicing precision is ensured, and the cost and the operation difficulty are reduced at the same time.