Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

1180 results about "Rectangular coordinates" patented technology

Method for projecting tunnel excavation contour through multi-beam visible laser

The invention belongs to the technical field of tunnel excavation, and particularly relates to a method for projecting a tunnel excavation contour through multi-beam visible laser. Comprises: S1, establishing a tunnel line model; s2, establishing a two-dimensional rectangular coordinate system on the excavation section of the tunnel; s3, arranging more than three target positioning points on the excavation section of the tunnel, and installing reflecting lenses on the target positioning points; s4, converting the space coordinates of the target positioning point obtained in the step S3 under the construction engineering coordinate system into a two-dimensional rectangular coordinate system; s5, converting the two-dimensional rectangular coordinates of each point of the theoretical tunnel contour model into three-dimensional space coordinates; s6, erecting a laser projection device; s7, calculating the horizontal angle and the vertical angle obtained in the step S5 by the laser projection device, and controlling a motor to quickly adjust the angles of the reflecting lenses of the X axis and the Y axis respectively; s8, adjusting the angles of the reflecting lenses of the X axis and the Y axis of the related positioning point; and S9, averaging the mileage of the target positioning point of each total station obtained in the step S4, and taking the averaged mileage as the mileage of the current excavation face to carry out informatization management.
Owner:2ND ENG CO LTD OF CHINA RAILWAY 12TH BUREAU GRP +2

Three-dimensional tomography method and system for gas concentration space distribution detection based on unmanned aerial vehicle

The invention belongs to the technical field of gas concentration detection, and discloses a three-dimensional tomography method and system for gas concentration space distribution detection based on an unmanned aerial vehicle, and the method comprises the steps: 1, building a space rectangular coordinate system, and converting latitude and longitude coordinates into XYZ coordinates; 2, dividing view field grids and grid numbers; 3, calculating the number of intersecting grids of the light beams and the view field and the length of intersecting line segments; 4, calculating a weight coefficient matrix and an integral concentration vector; and 5, reconstructing gas three-dimensional concentration distribution by using an SART algorithm. The system combines the unmanned aerial vehicle and the telemetry technology, realizes gas cloud scanning and three-dimensional gas cloud concentration distribution reconstruction based on the unmanned aerial vehicle, has the characteristics of non-contact measurement, high imaging speed, high precision, autonomous detection, strong environmental adaptability and the like, can monitor and predict the gas diffusion trend in real time, and has a wide application prospect. And a new solution is provided for realizing accurate traceability of methane gas leakage and reconstruction of leakage space distribution in a complex scene.
Owner:HANGZHOU INST FOR ADVANCED STUDY UCAS

Shadowless lamp control system and method based on behavior recognition and prediction

The invention relates to the field of intelligent control, and particularly discloses a shadowless lamp control method based on behavior recognition and prediction, which comprises the following steps: S1, establishing a three-dimensional rectangular coordinate system by taking an initial mounting position of a shadowless lamp as an original point, and determining coordinates as follows by adopting image data acquired by at least two groups of directional image acquisition equipment with different visual angles; s2, capturing the real-time position of the scalpel in real time through an image acquisition device, outputting coordinates, acquiring data of a plurality of continuous durations to form a historical trajectory data set, calling an operation scene template library preset with a plurality of types of typical operation trajectory features by the control terminal for the acquisition times, matching a trajectory feature template corresponding to the current operation type, and outputting the historical trajectory data set; performing feature alignment processing on the data and the input data by a fusion module to obtain adaptive trajectory data; according to the technical scheme, pre-judgment can be carried out in advance, the scene adaptability is high, and sterile fine adjustment is facilitated.
Owner:FOURTH MILITARY MEDICAL UNIVERSITY

Bridge inspection method based on image recognition

The invention discloses a bridge inspection method based on image recognition, and relates to the technical field of bridge inspection, and the method comprises the steps: obtaining the geodetic coordinate data of a target bridge, and obtaining the space rectangular coordinate data of the target bridge through coordinate system conversion; and performing first route planning to obtain a preliminary inspection route, commanding the unmanned aerial vehicle to perform image acquisition on the target bridge according to the preliminary inspection route to obtain a first image set, and classifying the first image set through the first machine learning model to obtain a bridge key part classification result. Performing second route planning and third route planning based on the bridge key part classification result to obtain a formal inspection route; commanding the unmanned aerial vehicle to perform flight inspection according to the formal inspection route, performing real-time adjustment through a safety potential field algorithm to obtain an updated inspection route, and completing inspection shooting to obtain a second image set. And performing defect detection on the second image set through a second machine learning model to obtain a bridge defect identification result, and completing bridge inspection.
Owner:CHINA RAILWAY 23RD CONSTR BUREAU LTD +1

Intelligent avoidance control method for machining of numerical control flanging machine

The invention relates to an intelligent avoiding control method for machining of a numerical control flanging machine. Comprising the following steps that before machining, a correct machining program is compiled on a human-computer interface according to an actual workpiece drawing or a real object forming process; the numerical control system analyzes a machining program to obtain data necessary for a position avoiding algorithm, machining is started, and in a bending forming rectangular coordinate system, pole coordinate values of a current forming shape are automatically calculated in real time; in the continuous machining process, the target positions and the action time sequence of a feeding shaft, a pressing shaft and an edge folding shaft of the edge folding machine in the next step are correctly adjusted, so that a workpiece and an edge folding machine die are prevented from interfering and colliding, and meanwhile set process actions are completed. According to the control method and the numerical control system, the forming shape and related coordinate data of the workpiece can be obtained in real time, the mutual positions of the workpiece, the machine tool moving part and the mold are adjusted in time through the process control instruction, and interference and collision of the workpiece, the machine tool and the mold are correctly avoided.
Owner:JIANGSU YAWEI MACHINE TOOL

Energy distribution management method based on regional resources

The invention discloses an energy distribution management method based on regional resources, and relates to the technical field of distributed energy management, and the method comprises the steps: obtaining a two-dimensional map of a region, building a rectangular plane coordinate system, carrying out the zooming processing of the two-dimensional map, and obtaining a rectangular plane coordinate system; preliminarily dividing the region into a plurality of cells with the same size according to a preset area, calculating the area of the scaled map, and dividing the region into a plurality of macroscopic sub-regions according to a macro standard; dividing each macro sub-region into a plurality of micro-regions according to a micro standard, and setting a unique identification code for marking; setting an initial power supply end according to the macroscopic sub-region and the microscopic region; through macroscopic and microscopic regional division, fine management of regional resources is realized, the reasonability and efficiency of energy distribution are improved, and through accurate regional division and power supply end setting, the effects of accurately matching requirements, improving the overall energy utilization efficiency and reducing energy loss are realized.
Owner:TIANJIN RICHSOFT ELECTRIC POWER INFORMATION TECH +1

Robot energy consumption optimization method based on improved particle swarm optimization

The invention discloses a robot energy consumption optimization method based on an improved particle swarm algorithm, and the method comprises the steps: building a space rectangular coordinate system through a robot base, and carrying out the kinematics and dynamics modeling of the joint parameters of a robot; the pose of the end effector is converted into a joint angle sequence through an inverse solution algorithm, interpolation is conducted on the sequence through a polynomial spline function, and a robot joint movement track is determined; constructing a robot energy consumption optimization model; based on a robot joint motion trail and a robot energy consumption optimization model, the energy consumption of the robot is used as a fitness function of a particle swarm algorithm, and key motion parameters in the motion process of the robot are used as particles of the algorithm in combination with dynamically adjusted inertia weights and learning factors. The energy consumption of the robot in the moving process is reduced by updating the speed and the position of the particles. The energy consumption is reduced to the maximum extent while the task completion quality and the energy consumption calculation accuracy are ensured, and the system efficiency is improved.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Determination method and optimization method for interface deformation degree of gallium oxide crystal grown by edge-defined film-fed growth method

The invention provides an edge-defined film-fed growth gallium oxide crystal interface deformation degree determination method and optimization method.The method comprises the steps that a target crystal interface is determined from a target computational domain, steady-state calculation is conducted on the target computational domain, and a temperature field where the target crystal interface is located is obtained; determining a target function corresponding to the target crystallization interface according to the temperature field; calculating a directional derivative of the target function in the coordinate axis direction of the three-dimensional rectangular coordinate system; determining a temperature change factor of the target grid surface according to the three-dimensional coordinate and the directional derivative of the target grid surface in the three-dimensional rectangular coordinate system; and determining the deformation degree of the target crystal interface according to the temperature change factor of each target grid surface. According to the embodiment of the invention, the deformation degree of the target crystal interface is determined by taking the temperature change factor of each target grid surface as a judgment basis, the subjective judgment of observers is not depended on, and the accuracy and the automation degree of determining the deformation degree of the crystal interface are improved.
Owner:XI AN JIAOTONG UNIV

Point cloud integrity improvement method and system based on Delaunay triangle and minimum curvature

The invention discloses a Delaunay triangle and curvature minimization-based point cloud integrity improvement method and system, and the method comprises the following steps: converting a point cloud under a three-dimensional rectangular coordinate system into a spherical coordinate system, and then projecting the point cloud to a two-dimensional plane coordinate system to form a two-dimensional plane point cloud; carrying out Delaunay triangularization, and then projecting back to a three-dimensional rectangular coordinate system to form a spatial two-dimensional triangular mesh; the side length, the area and the unit normal vector of each triangular mesh are calculated, and abnormal triangular meshes are removed according to the side length; searching boundary points of the point cloud according to the topological relation of the triangular mesh edges; searching the boundary points of the missing part according to the corresponding relation of the boundary points; filling a plurality of points in the missing part based on spherical projection; and calculating the curvature of the filling point, and performing iteration to enable the curvature to be minimum so as to correct the position of the filling point. According to the method, the boundary points of the point cloud can be effectively detected, the filling points are generated, and the missing parts are repaired, so that the integrity and the accuracy of the point cloud are improved.
Owner:SOUTHEAST UNIV +1

Trestle active wave compensation method based on multi-sensor fusion positioning

The invention provides a trestle active wave compensation method based on multi-sensor fusion positioning, and relates to the technical field of wave compensation of maritime work equipment, and the method specifically comprises the following steps: S1, collecting ship data of a laser radar, an inertial sensor I MU and a GPS positioning system, processing the ship data through improved Kalman filtering, and achieving marine precise positioning of a ship; s2, establishing a coordinate system, taking a ship as an initial state when the ship is lapped to a wind power tower at the tail end of a static underwater trestle, and establishing a rectangular coordinate system O by taking the rotation center of the ship as an original point; s3, according to the swaying, surging, yawing, rolling, pitching and heaving information, obtained by an attitude sensor MRU, of the ship at the instantaneous moment, the target position quantity of each joint of the trestle is calculated through motion attitude inverse solution; and S4, each joint is controlled to stably move to a target position, and wave compensation is completed. According to the invention, by designing the Kalman filtering system for multi-sensor fusion positioning, the position of the ship can be positioned more accurately, and the active wave compensation precision of the trestle can be improved.
Owner:NANTONG PENGRUI OFFSHORE TECH CO LTD

Moment compensation-based balanced distribution method for intelligent tunneling oil pressure of shield tunneling machine

Provided in the present invention is a moment compensation-based balanced distribution method for the intelligent tunneling oil pressure of a shield tunneling machine. The method comprises: firstly establishing a space rectangular coordinate system, and determining a first target deviation-correction moment Mx, a second target deviation-correction moment My, and a required target total thrust Ft; then, compensating for the first target deviation-correction moment Mx and the second target deviation-correction moment My and then converting same into corresponding corrected moments; by means of regarding as adjustable the oil pressure of each oil cylinder group which is uniformly distributed on a circumference, and by means of using an obliquely-truncated cylinder mathematical model, performing balanced distribution on the oil pressure of each oil cylinder group under the condition that oil pressure vector endpoints of the oil cylinder groups are coplanar; and then taking as a final partition oil pressure the mean value of the oil pressures which are distributed to all the oil cylinder groups in a partition. Thus, an optimal distribution result can be accurately and efficiently obtained, and a technical foundation is provided for automatic / intelligent control over the attitude of a shield tunneling machine. The distribution result conforms to the balance in a geometric space while meeting distribution targets, thereby facilitating the protection of segment rings during tunneling construction.
Owner:NAT ENG RES CENT OF DREDGING TECH & EQUIP

Position error calibration device and calibration method for an industrial robot

The present invention discloses a position error calibration device and a calibration method for an industrial robot. The position error calibration device in the present invention includes a laser ranging component for measuring the three-dimensional coordinates of the target ball at the end of the robot. The laser ranging component includes a laser interferometer, a beam splitter, a two-dimensional position sensitive detector, and a housing; a two-dimensional moving platform for moving the laser ranging component in the X-axis and Y-axis directions. The two-dimensional moving platform includes a lead screw slider module and a grating scale in the X-axis and Y-axis directions; a supporting device for fixing and supporting the two-dimensional moving platform so that it can work stably in three-dimensional space. Compared with a laser tracker, the present invention does not require transformation between a spherical coordinate system and a rectangular coordinate system, thereby avoiding the amplification effect of the angle error of the inner circle grating in the laser tracker. The present invention can directly measure the three-dimensional coordinate values of the reflecting target ball in the measurement coordinate system, has a good calibration effect, and can meet the calibration requirements of industrial robots.
Owner:CHINA JILIANG UNIV +1

Coded disc surface tiny scratch identification method based on micro texture feature analysis

The invention belongs to the technical field of image processing, and particularly relates to a coded disc surface tiny scratch recognition method based on micro texture feature analysis, which comprises the following steps: acquiring a coded disc grating texture image and converting the coded disc grating texture image into a rectangular coordinate system to obtain an expanded grey-scale map; the optimal main direction of the grating texture is determined through rotation projection analysis; for each pixel point in the grey-scale map, sampling along two sides of the optimal main direction to form a reference sample; calculating a weighted average value of the gray values of the sample points in the reference sample to obtain a trend prediction value, calculating a residual error between the gray values of the pixel points and the trend prediction value, and determining a texture deviation index in combination with the change condition of the gray values of all neighborhood pixel points of the pixel points; and finally, identifying the scratches through threshold segmentation. According to the method, the grating edge interference can be effectively inhibited under the strong periodic texture background, and the tiny scratch features can be accurately extracted.
Owner:AOYINSHEN INTELLIGENT EQUIP (SUZHOU) CO LTD

Ballastless track plane linear reconstruction method and system under large foundation deformation condition

The invention discloses a ballastless track plane linear reconstruction method and system under the condition of large foundation deformation, and the method comprises the steps: judging whether a railway line is staggered on a long straight line or a curve, and determining a linear reconstruction mode; determining the intersection position of the railway line and the fault zone, establishing a rectangular plane coordinate system, and collecting basic data of the line; fitting and reconstructing straight line edges on two sides of the line damage center and a clamping straight line between the two straight line edges, and determining a slope range and a change step length of the clamping straight line; determining an optimization variable, a constraint condition, a target function and a fitness function, and searching an optimal plane line shape reconstruction scheme under each linear slope value by adopting a genetic algorithm and a local search algorithm; and summarizing and comparing the fitness values of the optimal plane line shape reconstruction schemes under each straight line clamping slope value, and selecting the scheme with the maximum fitness value. According to the method, the damage form of the large deformation of the railway foundation to the plane line shape of the ballastless track is analyzed, and reference is provided for post-disaster repair of the ballastless track.
Owner:CHINA STATE RAILWAY GRP CO LTD +4

Nonlinear filtering trajectory drop point prediction method based on Runge-Kutta algorithm

The invention discloses a nonlinear filtering trajectory drop point prediction method based on a Runge-Kutta algorithm, and the method comprises the steps: firstly, preprocessing the trace point information of a shell, and converting a radar array plane rectangular coordinate system into an east-north-sky coordinate system; then, constructing a projectile mass point trajectory model, and if a reliable track exists, carrying out point track association on the preprocessed point track data and the reliable track based on an extended Kalman filtering algorithm; using a logic method track initiation algorithm to associate the trace point data which are not associated with the temporary track which is not prohibited so as to realize track initiation; carrying out track extrapolation on unupdated reliable tracks; performing flight path extinction on the reliable flight path meeting the extinction condition; and finally, resolving a trajectory by utilizing a Runge-Kutta method and combining a trajectory equation set, and further calculating a trajectory drop point. According to the method, target tracking filtering is accurate, trajectory extrapolation errors are reduced, the number of required measurement parameters is small, the calculation speed is high, rapid drop point prediction can be achieved, and the real-time requirement of actual engineering is met.
Owner:NANJING UNIV OF SCI & TECH +1

Surgical robot accurate pose real-time registration method and system based on multi-sensor fusion

The invention belongs to the technical field of medical robots, and discloses a surgical robot accurate pose real-time registration method and system based on multi-sensor fusion, and the system comprises a multi-source sensing collection assembly; a time-space calibration mechanism; fusing a resolving platform and an exception elimination platform; a deformation sensing and dynamic compensation device; and a registration result closed-loop feedback unit. According to the invention, a multi-source sensing acquisition assembly and a synchronous control board are integrated on a hardware level, a nanosecond timestamp is generated by using a high-precision clock driven by an onboard crystal oscillator, and a cross-correlation delay calculation chip is combined to execute a cross-correlation function method delay estimation formula, so that microsecond-level accurate correction of delay amount among sensing sources is realized; the coordinate transformation unit automatically selects a matched calibration matrix according to a correction result, multi-source data such as optical positioning, inertial measurement, a torque sensor, ultrasonic or electromagnetic positioning and the like are unified to a global rectangular coordinate system, and the structure can effectively ensure the consistency of time and space references of data output by different sensors.
Owner:BEIJING ROSSUM ROBOT TECH CO LTD

Multi-unmanned aerial vehicle area coverage path planning method with no-fly zone avoidance

The invention discloses a multi-unmanned aerial vehicle area coverage path planning method with no-fly zone avoidance. The method comprises the following steps: converting an input operation area boundary and longitude and latitude coordinates of a no-fly zone into a UTM plane rectangular coordinate system, carrying out safety buffer area expansion on all no-fly zones, and calculating a difference set between the operation area and the safety buffer areas of all no-fly zones to obtain a final available operation area; segmenting the final available operation region to generate a plurality of sub-regions with balanced areas; for each sub-region, generating a parallel scanning route covering the region; and each sub-region line segment generates a parallel scanning route covering the region according to a preset interval. The method can ensure that the path avoids the no-fly zone, the zone distribution is balanced, and the calculation is efficient.
Owner:XIAMEN YUANTING INFORMATION TECH CO LTD

Object perimeter measurement method and device, computer equipment and storage medium

The invention relates to the technical field of laser radar surveying and mapping, and discloses an object perimeter measurement method and device, computer equipment and a storage medium, and the method comprises the steps: sequentially obtaining timestamps, laser scanning data and radar pose data when all feature points on a to-be-measured object are scanned through a single-line laser radar; according to a timestamp sequence, mapping the laser scanning data of each feature point into a polar coordinate system to obtain first peripheral shape point cloud data; establishing a rectangular coordinate system, and converting the first peripheral shape point cloud data into second peripheral shape point cloud data in the rectangular coordinate system; performing timestamp-by-timestamp data fusion on the radar pose data and the second peripheral shape point cloud data to obtain third peripheral shape point cloud data; generating a curvilinear function according to the third peripheral shape point cloud data; and calculating the length corresponding to the curvilinear function as the object perimeter of the to-be-measured object. The method realizes accurate calculation of the perimeter of the object, and has the advantages of non-contact, high precision, high efficiency and the like.
Owner:SHENZHEN TECH UNIV

Ship electromagnetic environment prediction method and device based on empirical model, equipment and medium

The invention provides a ship electromagnetic environment prediction method and device based on an empirical model, equipment and a medium, and the method comprises the steps: firstly, carrying out the translation of a space field point in a global rectangular coordinate system according to the geometric position of an original point, and constructing a local rectangular coordinate system; then, based on the local rectangular coordinate system, antenna attitude conversion is carried out on the space field points, and array polar coordinates are generated; then, according to the polar coordinates of the array, a discrimination field domain is constructed by discriminating the relative distance between the space field point and the array antenna; and finally, based on the discrimination field domain, performing gain on a preset field point through a three-dimensional gain graph, and performing field intensity calculation on the preset field point to complete prediction of the electromagnetic environment of the preset field point. According to the embodiment of the invention, the prediction of the electromagnetic environment is realized, the calculation efficiency and precision are improved, and the engineering practice requirements are met.
Owner:CHINA SHIP DEV & DESIGN CENT

Gesture cursor mapping method and device, electronic equipment, storage medium and vehicle

The invention relates to a gesture cursor mapping method and device, electronic equipment, a storage medium and a vehicle, and the method comprises the steps: obtaining a space coordinate of each key point in a plurality of key points of a hand in a current frame image in a space rectangular coordinate system, the plurality of key points including a wrist key point and at least two target key points, each target key point is a root key point of a finger except a thumb, and the original point of the space rectangular coordinate system is a wrist key point; based on the space coordinate of each key point, determining a target yaw angle and a target pitch angle of the gesture posture in the current frame image; determining coordinates of a cursor based on the target yaw angle, the target pitch angle, the target plane coordinates and a preset mapping relation; the target plane coordinate is determined according to the plane coordinate of the at least one target key point. The recognition efficiency of determining cursor movement according to the change of the gesture posture can be improved.
Owner:BEIJING CHEHEJIA AUTOMOBILE TECH CO LTD

Steel plate internal damage detection method based on guided waves and PINNs

The invention discloses a steel plate internal damage detection method based on guided waves and PINNs, and the method comprises the following steps: firstly establishing a rectangular plane coordinate system, selecting a guided wave application position and a guided wave receiving point on the surface of a steel plate, applying guided waves to the steel plate, and selecting M time points of free vibration of the steel plate, the method comprises the following steps: carrying out guided wave receiving on a steel plate, calculating out-of-plane displacements of the steel plate at all guided wave receiving points, constructing a PINNs model and a DNN model, training the PINNs model and the DNN model at the same time by using the out-of-plane displacements, coordinates and time of the steel plate at all guided wave receiving points, detecting the steel plate by using the PINNs model and the DNN model, and positioning the damage position of the steel plate. According to the method, the wave equation is approximately solved through the physical information neural network, a complex finite difference method formula is avoided, so that the calculation cost is reduced, compared with a three-dimensional wave equation, the adopted physical equation based on the plate-shell theory is simpler, the calculation cost is reduced, the accuracy of positioning the internal damage of the steel plate is improved, and the accuracy of positioning the internal damage of the steel plate is improved. The internal damage position of the steel plate can be positioned.
Owner:GUANGXI UNIV

Unmanned aerial vehicle-oriented nest site selection method for traffic off-site rapid evidence obtaining

The invention discloses an unmanned aerial vehicle-oriented nest site selection method for traffic off-site rapid evidence obtaining, and belongs to the technical field of unmanned aerial vehicle nest site selection, and the method comprises the steps: firstly searching for an accident high-incidence intersection, obtaining and processing intersection traffic data in a selected region, carrying out the weight distribution of each index in the data through an entropy weight method, and carrying out the calculation of the weight distribution of each index; calculating a comprehensive score of each intersection by using a TOPSIS method, determining a risk threshold value, determining an accident high-incidence intersection as a risk point and allocating a weight, establishing a rectangular plane coordinate system for the accident risk point obtained in the above step, comparing the risk point to the coordinate system, and obtaining a position coordinate of the risk point; and then establishing a traffic accident non-field evidence obtaining unmanned aerial vehicle nest site selection model, and solving the unmanned aerial vehicle nest site selection model based on an NSGA-II algorithm to obtain an optimal nest site selection scheme.
Owner:SHANDONG UNIV OF SCI & TECH

Method for determining shale content of tight sandstone

The invention discloses a method for determining the shale content of tight sandstone, and relates to the technical field of exploration and research of tight rock oil and gas reservoirs. The method comprises the following steps: identifying a rock slice identification photo by using a computer image identification method, obtaining the area percentage of debris particles with the diameter greater than a set threshold value in the slice identification photo, and then calculating the area percentage of argillaceous particles in the slice identification photo; according to the area percentage of the argillaceous particles and the corresponding times of the polarizing microscope, displaying the argillaceous particles in a rectangular coordinate system in a scatter mode; fitting all scatter points by using a nonlinear least square method, and establishing a shale content volume percentage change relation curve under different objective lens multiples of the polarizing microscope; and solving the curvilinear equation, and calculating the shale content of the sample by using the curvilinear equation. According to the method, the error caused by the fact that the shale content is calculated by an eye estimation method singly through a slice identifier is avoided, and the analysis result is more consistent with the real content of the sample, so that the accuracy of the shale content determination by an image method is greatly improved.
Owner:PETROCHINA CO LTD

Gait emotion joint recognition method based on heterogeneous space neural architecture search

The invention provides a gait and emotion joint recognition method based on heterogeneous space neural architecture search. The method comprises the following steps: extracting three-dimensional human body posture joint points in different emotion video data; carrying out space conversion, respectively converting into a rectangular coordinate system and a spherical coordinate system, and carrying out position information space mapping and angle information space mapping on articulation points in different coordinate systems based on a similarity minimization strategy; constructing a neural architecture search space and a joint search strategy under different spaces, respectively searching to obtain an optimal backbone network, and respectively training the optimal backbone network; utilizing the trained optimal backbone network to extract human body time sequence gait emotion features in different spaces, and inputting the human body time sequence gait emotion features into a Softmax classifier to obtain scores of different emotions; and performing joint scoring to complete gait emotion joint recognition based on heterogeneous space neural architecture search.
Owner:THE 28TH RES INST OF CHINA ELECTRONICS TECH GROUP CORP

Voxel-level segmentation method based on three-dimensional medical image

The invention relates to the technical field of medical image segmentation, in particular to a voxel-level segmentation method based on a three-dimensional medical image. The technical problem is that a medical image segmentation method in the prior art uses voxels of a fixed size to perform segmentation, which may cause inaccurate segmentation in a sparse or fuzzy region. According to the technical scheme, the voxel-level segmentation method based on the three-dimensional medical image comprises the steps that voxel coordinates under a three-dimensional rectangular coordinate system are converted into coordinates under a spherical coordinate system, the size and shape of curvature voxels are dynamically defined, a curvature voxel grid of a whole image space is constructed under the spherical coordinate system, and the voxel-level segmentation method based on the three-dimensional medical image is obtained. Calculating curvature similarity between each voxel and a neighborhood voxel of the voxel, and combining the similar voxels into a larger clustering unit according to the curvature similarity; according to the method, voxel coordinates in a three-dimensional rectangular coordinate system are converted into coordinates in a spherical coordinate system, a curvature voxel space is constructed, voxel clustering is carried out based on neighborhood curvature similarity, and therefore accurate segmentation of the medical image is achieved.
Owner:宋莲君

Shafting rotation precision measuring device and method

A shafting rotation precision measuring device and method are suitable for shafting rotation precision measurement of a shaft end assembly, the shafting rotation precision measuring device comprises a lens reflection tool and a rotation precision measuring device from the function aspect, and the readings of a single-shaft photoelectric autocollimator in the horizontal direction and the vertical direction are expanded into Fourier series respectively; first harmonic function calculation is carried out on Fourier series based on a gradienter method, two rectangular coordinates can be obtained, the two components are synthesized, the shaft system rotation precision can be obtained, and the device is simple in structure, convenient to operate and wide in application range. The test verifies and proves that the detection requirement on the rotation precision of the shaft system can be met, and the method has practical engineering significance.
Owner:BEIJING INST OF AEROSPACE CONTROL DEVICES

Air tightness detection device for civil air defense door

The utility model belongs to the field of civil air defense door detection, and discloses an air tightness detection device for a civil air defense door, which comprises a lifting assembly used for descending the civil air defense door into water, and a sealing assembly used for limiting and sealing the lower part of the civil air defense door is arranged on the lifting assembly. And the marking assembly is arranged on the outer side of the sealing assembly and is used for marking gas leakage points after double-shaft sliding position adjustment. According to the air tightness detection device for the civil air defense door, after the position is adjusted through double-shaft sliding, an air leakage point is marked through downward insertion, the marking rod is moved to the position above the air leakage point and is aligned with the air leakage point through downward insertion, and the position of the air leakage point is accurately recorded by adopting a mechanical marking method; through the arrangement of double coordinates, one corner of the civil air defense door is set as an original point, and an air leakage point position is displayed in a rectangular coordinate system mode, so that the air leakage point position is convenient to determine; through the arrangement of the multi-position marks, a plurality of marking rods are arranged, and a plurality of gas leakage point positions are marked at the same time.
Owner:TONGJIAN CONSTR GRP CO LTD

Land gravity far area terrain correction method and system based on digital elevation model

The invention discloses a land gravity far-area terrain correction method and system based on a digital elevation model. The method comprises the following steps of: performing weighted average calculation on a far first region terrain correction value and a far second region generalized terrain correction value of regular distribution measuring points near irregular distribution measuring points by adopting a bilinear interpolation algorithm on the irregular distribution measuring points to obtain a far region terrain correction value; on the basis of a calculation algorithm of a terrain unit gravitational potential vertical partial derivative of a local rectangular coordinate integral kernel of a measuring point under a spherical coordinate system, high-precision calculation and accumulation are carried out on terrain units one by one, the influence of earth surface bending is considered, and a high-precision and high-resolution digital elevation model can be utilized to the greatest extent. A high-precision digital elevation model represented by geographic latitude and longitude is uniformly subdivided for terrain interfaces of a far first area and a far second area, so that digital elevation units with different resolutions are ensured not to be overlapped or have gaps to the greatest extent, and a high-precision and high-resolution digital elevation model is adapted; and subsequent updating and maintenance of the digital elevation model and the remote terrain correction value library are facilitated.
Owner:INST OF GEOPHYSICAL & GEOCHEMICAL EXPLORATION CHINESE ACAD OF GEOLOGICAL SCI

Ship electromagnetic environment prediction method based on deep forest model

The invention discloses a ship electromagnetic environment prediction method based on a deep forest model, and relates to the technical field of electromagnetic compatibility and antennae, and the method comprises the steps: converting the coordinates of each point of given data (simulation data) into a global rectangular coordinate relative to a main ship body, and obtaining an array rectangular coordinate of each point relative to an array plane; converting the array rectangular coordinates of the points relative to the array plane into relative array spherical coordinates of the points when the antenna attitudes are different; the original global rectangular coordinates, the relative array spherical coordinates, the azimuth angle and the pitch angle of each electromagnetic environment simulation point and the logarithmic transformation values of the field intensity values corresponding to the points are constructed into a feature combination of electromagnetic environment prediction; constructing a deep forest model, and training and obtaining optimal hyper-parameters of the model by using electromagnetic environment simulation data; performing coordinate conversion and feature combination on the coordinates of the spatial points to be predicted; obtaining a model prediction value; and obtaining a field intensity value under the original scale. By means of the method, prediction of the electromagnetic environment under a certain simulation working condition can be completed within a very short time.
Owner:CHINA SHIP DEV & DESIGN CENT

Section interpolation method and device for weather radar body scanning data

The invention provides a profile interpolation method and device for weather radar body scanning data, and relates to the technical field of data processing, and the method comprises the steps: obtaining rectangular coordinates of the weather radar body scanning data and all to-be-interpolated vertical profile grid points; performing linear interpolation on the weather radar body scanning data to obtain a first weather radar body scanning data point of a first three-dimensional coordinate and a second weather radar body scanning data point of a second three-dimensional coordinate; converting the rectangular coordinates of the to-be-interpolated vertical section grid points into first to-be-interpolated vertical section grid points of first three-dimensional coordinates and second to-be-interpolated vertical section grid points of second three-dimensional coordinates; based on a trilinear interpolation method, performing interpolation processing on a first weather radar body scanning data point of the first three-dimensional coordinate and a first vertical section grid point to be interpolated of the first three-dimensional coordinate; and performing trilinear interpolation processing on the second weather radar body scanning data point of the second three-dimensional coordinate and the second vertical section grid point to be interpolated of the second three-dimensional coordinate, and determining a final section interpolation calculation result.
Owner:CHINESE FLIGHT TEST ESTAB +1