42 results about "Rigid motion" patented technology

The invention relates to the technical field of face verification, and discloses a face identity verification data processing method based on dynamic feature extraction, which comprises the following steps: acquiring a continuous face video frame sequence and calculating a full-pixel instantaneous velocity vector to generate an original dense optical flow field, selecting rigid region anchor points to calculate a rigid affine transformation matrix and construct a theoretical rigid motion field, performing differential stripping on the theoretical rigid motion field from the original dense optical flow field, and extracting a non-rigid micro-motion residual field; mapping the non-rigid micro-motion residual field to a facial muscle topological grid to generate a time sequence feature tensor, and calculating a geodesic line distance between a covariance matrix of the time sequence feature tensor and a reference dynamic feature in a Riemannian manifold space; when the geodesic distance is smaller than a threshold value, verification is passed, through a rigid-non-rigid orthogonal decomposition mechanism, the special viscoelastic micro-motion and cooperation law of biological soft tissue is captured by utilizing a residual field, and the high-simulation mask is effectively defended.

The invention discloses a miniature bionic robot for in-situ detection of aero-engine blades, and relates to the technical field of aero-engine detection, the miniature bionic robot comprises a rigid movement mechanism, a flexible bending segment, a dual-mode adsorption system and an environment sensing system; the head and the tail of the rigid movement mechanism are connected with the driving foot, the flexible bending section is integrated with the shape memory material and the driving module, and wriggling is achieved through thermal deformation. The dual-mode adsorption system comprises an electrostatic adsorption module, a capillary adsorption module and a self-adaptive supporting structure and is used for stable adsorption; the environment sensing system is provided with an antenna sensor, a micro camera, a photoelectric sensor and a sliding displacement sensor and used for sensing the surrounding environment. According to the robot, disassembly-free in-situ detection of the aero-engine blade is achieved, the detection efficiency and precision are improved, the detection cost is remarkably reduced, the comprehensive performance index is 2-5 times higher than the industrial standard, and the robot has wide application prospects and important engineering value.

The invention provides an interactive multi-model infrared time-sensitive target tracking method fusing image features, aiming at solving the problem that the motion state of a ground target is difficult to determine due to rigid motion generated by an airborne camera influenced by air flow and strong maneuverability of the ground target in infrared target tracking in an air-ground scene. According to the method, under the framework of Kalman filtering, a target detection result is used as a state observer, inter-frame registration is introduced to compensate for errors caused by coordinate system transformation due to shaking of an airborne platform, strong maneuverability of a ground moving target is represented by interactive multiple models, and finally, the moving target is accurately tracked through data association. The tracking method provided by the invention is low in complexity, can well adapt to a complex environment of air-ground imaging, and has important engineering significance, and the tracking precision is not influenced by the precision of a target detection result.

The invention discloses a cross-scale decomposition and control method for an electro-hydraulic servo macro-micro rigid-flexible multi-body system, and belongs to the technical field of intelligent control. The invention aims to research a cross-scale decomposition and control method for an electro-hydraulic servo macro-micro rigid-flexible multi-body system based on a trajectory tracking control law of self-adaptive dynamic programming and a three-parameter four-scale singular perturbation decoupling problem for the electro-hydraulic servo macro-micro rigid-flexible multi-body system with uncertainty and variable load. The dynamics of the electro-hydraulic servo macro-micro rigid-flexible multi-body system mechanical arm is decomposed for three times, and then a slow-varying subsystem rigid motion controller, a secondary slow-varying subsystem flexible vibration controller, a secondary fast-varying subsystem micro mechanical arm controller and a fast-varying subsystem hydraulic controller are designed; and finally, combining all the controllers according to a multi-time scale theory to obtain a combined controller. According to the invention, a complex system can be greatly simplified, and the respective design of the controller is more practical.

The invention provides an anti-saturation fault-tolerant control method and device for a double-flexible-arm space robot, relates to the field of robot control, and solves the multiple challenges that in the prior art, a flexible mechanical arm faces continuous and difficult vibration suppression, an actuator is prone to failure, torque is limited, task time is constrained and the like. The dynamic state of the system is unstable; and the control capability is limited. The method comprises the steps that a hypothesis modal method and a momentum conservation theorem are combined to derive a double-flexible-arm space robot kinetic equation in a Lagrange form; a flexible system singular perturbation technology is utilized to obtain a slow-varying subsystem for representing rigid motion characteristics of a mechanical body and a quick-varying subsystem for representing residual vibration characteristics of a rod piece; for the slow-varying subsystem, designing a fixed-time anti-saturation fault-tolerant controller based on an extreme learning machine and a torque output function; and designing an anti-saturation controller based on state variable negative feedback for the quick change subsystem. The method is used in the robot control process.

An electronic device and method for generation of reflectance maps for relightable 3D models is disclosed. The electronic device acquires multi-view image data that includes a set of images of an object and generates a 3D mesh of the object based on the multi-view image data. The electronic device obtains a set of motion-corrected images based on a minimization of a rigid motion associated with the object between images of the set of images and generates texture maps in a UV space based on the set of motion-corrected images and the 3D mesh. The electronic device obtains specular and diffuse reflectance maps based on a separation of specular and diffuse reflectance components from the texture maps, and obtains a relightable 3D model of the object based on the specular and diffuse reflectance maps.

The invention relates to the technical field of computer vision, and discloses a public resource transaction behavior intelligent supervision and early warning system based on deep learning, which utilizes kinetic energy gating and a speed potential energy field to accurately lock an object keeping rigid motion with a hand, and fundamentally avoids the risk that a static background is misjudged as an operation target; meanwhile, through reverse optical flow reconstruction and gradient direction structured residual verification, a real entity with a three-dimensional volume and a shadow virtual image are accurately distinguished by utilizing a material shielding effect, and interference of dynamic shadow and reflection is thoroughly eliminated; and finally, on the basis of a risk potential field and kinetic energy flux accumulation mechanism, microscopic pixel motion is converted into macroscopic physical action quantity, a substantive transport process along an illegal path is accurately quantified through space-time integration, random jitter and withdrawing actions are effectively filtered, and high-confidence intelligent early warning of high-risk transaction behaviors is realized.

A computing system and method can be used to render 3D shapes from one or more images. Specifically, the present disclosure provides a general pipeline for learning articulated shape reconstruction from images (LASR). The pipeline can reconstruct rigid or non-rigid 3D shapes. Specifically, the pipeline can automatically decompose non-rigidly deformed shapes into rigid motions near a rigid skeleton. The pipeline incorporates synthetic analysis strategies and forward-renders contours, optical flow, and color images, which can be compared with video observations to adjust the internal parameters of the model. By inverting the rendering pipeline and incorporating optical flow, the pipeline can recover the mesh of a 3D model from one or more images input by a user.

The application provides an underactuated bionic dexterous hand, a system and a control method thereof. The underactuated bionic dexterous hand comprises a palm, five fingers, a control plate and a steering engine installed on the back of the palm through a threaded hole. The thumb comprises a joint, a tendon rope for driving the bending of the finger, a metacarpal bone, a proximal phalanx and a distal phalanx connected through a cylindrical pin in sequence. The index finger, the middle finger, the ring finger and the little finger have the same structure and each comprises a joint, a tendon rope for driving the bending of the finger, a distal phalanx, a middle phalanx and a proximal phalanx connected through a cylindrical pin in sequence. A finger root stroke limiter is arranged at the metacarpophalangeal joint of the thumb and the palm, and the metacarpophalangeal joint of the index finger, the middle finger, the ring finger and the little finger and the palm, the middle phalanx and the distal phalanx are each provided with a finger root stroke limiter. The application has high human simulation degree, is light and flexible, and solves the technical problems of the overlarge size, the overly complex structure, the rigid motion and the low human simulation degree of the dexterous hand.

The present disclosure provides a method, apparatus, electronic device, and storage medium for estimating point cloud motion. The method includes: obtaining a point cloud frame to be estimated and a reference point cloud frame; sampling motion center points in the reference point cloud frame to construct a point cloud motion deformation map; determining a first matching relationship between the reference point cloud frame and the point cloud frame to be estimated; constructing a point cloud motion energy equation according to the first matching relationship and the point cloud motion deformation map; solving the point cloud motion energy equation to determine a sparse non-rigid motion field corresponding to the motion center points; performing interpolation on the sparse non-rigid motion field to determine a fine non-rigid motion field; compensating the reference point cloud frame based on the fine non-rigid motion field to obtain a reference motion compensation frame; determining a second matching relationship between the point cloud frame to be estimated and the reference motion compensation frame; constructing an inter-frame rate distortion function between the point cloud frame to be estimated and the reference motion compensation frame based on the second matching relationship; and iteratively estimating the inter-frame rate distortion function to determine the point cloud motion. The estimation accuracy of the point cloud motion can be improved.

The invention relates to the technical field of three-dimensional graphic processing, and discloses a lunar surface / deep space scene target reconstruction and editing method based on 4D Gaussian structuring. The method is particularly suitable for dynamic target modeling and editing in deep space exploration tasks, including detectors, robots and related equipment on the lunar surface, the Mars or other celestial bodies. The method comprises the following steps: synthesizing a plurality of camera visual angles through a diffusion model based on a monocular video of an object, and reconstructing static three-dimensional Gaussian point representation in a standard space; extracting a skeleton structure of the object based on the surface grid, wherein the skeleton structure comprises a skeleton node position and a topological relation; on the basis of the skeleton structure, each Gaussian point is connected with a plurality of skeleton nodes through a linear hybrid skin mechanism, and skeleton-driven rigid deformation is achieved; non-rigid deformation is compensated through feature extraction and a regression network; and in combination with the rigid deformation and the non-rigid deformation, rendering to generate a dynamic Gaussian point model which can change along with time and can be edited. According to the method, motion modeling of an object is explicitly split into rigid motion driven by a framework and non-rigid correction, so that the definition and interpretability of motion representation are greatly improved, and particularly, higher stability and control precision are shown when challenges such as weak texture, violent illumination change and high noise are faced in a deep space environment. According to the method, object behavior modeling in a detection task is more flexible, and the method can be widely applied to scenes such as task planning, target recognition and dynamic editing.

A system for rigid motion correction for magnetic resonance imaging (MRI) of a subject includes an input for receiving motion corrupted k-space data for the subject acquired using an MRI system, a motion parameter estimation module coupled to the input and configured to estimate motion parameters based on the motion corrupted k-space data, a motion correction neural network coupled to the input and the motion parameter estimation module and configured to generate motion corrected k-space data based on the motion corrupted k-space data and the estimated motion parameters, and a reconstruction module coupled to the motion correction neural network and configured to generate a motion corrected image from the motion corrected k-space data.

To provide a horological movement including a device that can simplify the coupling between a rigid element and an elastic element.SOLUTION: A method for coupling a rigid element 10 with a spring 16 includes the steps of: rigidly attaching a first end of the spring 16 to a support; and positioning the support and the rigid element 10 in an initial relative position. The method, in which a coupling member 20 carried by a second end of the spring 16 is located on one side of a stressing ramp 40 which is opposite a specific recess 36 in the rigid element 10 and for which the rigid element 10 and the support can undergo relative movement MR in a first direction D1 from the initial relative position, then includes a coupling step. Here, the relative movement in the first direction is applied between the support and the rigid element 10 so that the coupling member 20 comes to bear against the stressing ramp 40 and then follows the stressing ramp 40, which is configured to move the coupling member 20 towards a rotation axis 22 by stressing the spring 16.SELECTED DRAWING: Figure 3B

The embodiment of the invention provides a modeling and analysis method for suspension four-wheel positioning angle tolerance sensitivity analysis, and the method comprises the steps: obtaining the structural information of a suspension system and the geometric data of system parts, and building a multi-body dynamic model based on the structural information and the geometric data; replacing a rigid kinematic pair in the multi-body dynamic model with a bushing pair, and setting a rigidity parameter of the corresponding bushing pair according to the type of the replaced rigid kinematic pair; collecting process information of system parts, designing a hard point tolerance range based on the process information and an error range of the suspension system, and adjusting a pre-offset value of a bushing pair according to the hard point tolerance range; the rigidity parameters and the pre-offset values of different lining pairs are modified for simulation, simulation results of each time are recorded, and the simulation results are compared to determine the sensitivity influence factors of the four-wheel positioning angle.

The invention relates to a gradient field-based three-dimensional dynamic point cloud denoising method and device. The method comprises the following steps: estimating an initial gradient field for each frame in a dynamic point cloud sequence; based on the estimated initial gradient field, performing time correspondence search on surface blocks of the point cloud through rigid motion to obtain corresponding surface blocks in adjacent frames; constructing a time gradient field by averaging the inverse transform gradient fields of the corresponding surface blocks in the adjacent frames; and based on the constructed time gradient field, denoising the dynamic point cloud through gradient rising. The invention provides a dynamic point cloud denoising normal form based on a gradient field, and denoising is carried out by utilizing a time sequence corresponding relation between adjacent frames and rigid body motion in classical mechanics and by utilizing distribution of noise point clouds; the model provided by the invention is superior to the existing most advanced method under the conditions of synthesizing noise and simulating actual noise.

The invention relates to the technical field of machine vision and image processing, and discloses a non-ferrous metal intelligent impurity removal analysis method based on machine vision, and the method comprises the steps: collecting and correcting the hyperspectral time sequence data of the melt surface; constructing a spectrum prior weighted optical flow energy functional to calculate an accurate motion field capable of retaining a material boundary; combining information of two physical dimensions of spectrum and motion to identify a region of interest which is different from a background melt; extracting multi-dimensional features such as rheology, relative motion and spectral stability representing rigidity, motion independence and material stability of the region for the region; and carrying out collaborative analysis based on the characteristics to judge whether the artifacts are impurities or dynamic fluid artifacts. Through multi-dimensional feature collaborative analysis and physical judgment logic simulation, the problem that targets are difficult to distinguish only by means of single visual features is solved, and the accuracy and reliability of machine vision in intelligent impurity removal analysis application of non-ferrous metals are remarkably improved.

The embodiment of the invention provides a robot non-sensing rigid-flexible coupling track control method and system, and relates to the technical field of robot control technologies. The method comprises the following steps: acquiring actual joint state information and motor input information of the robot; based on the actual joint state information and the motor input information, the real-time interaction force between the robot end effector and the external environment is determined; based on a preset rigid motion track, decomposing the real-time interaction force into an effective interaction force component in the tangential direction of the rigid motion track; determining an expected motion displacement along the rigid motion trajectory based on the effective interaction force component; the expected movement displacement is mapped to the rigid movement track, and the expected three-dimensional space position of an end effector of the robot is determined; and converting the expected three-dimensional space position into an expected joint angle of the robot, and performing driving control on the robot based on the expected joint angle. According to the invention, the problem of poor interaction effect is solved, and the effect of improving the man-machine interaction efficiency and precision is achieved.

A method for combined PET / MR imaging performs a PET / MR scan using a PET / MR scanner. During the scan a frame is reconstructed and co-registered with a reference frame. The reference frame is dynamically updated throughout the PET / MR scan by incorporating most recently co-registered images from previously reconstructed frames.

The invention relates to a control method, device and equipment for reciprocating rescue of an elevating fire truck and a storage medium. The method comprises the following steps: planning a periodic reference trajectory of rigid motion of a boom system according to target point location information of a reciprocating rescue task based on preset motion constraints, and extracting motion state characteristic parameters from the periodic reference trajectory; on the basis of the instantaneous equivalent length of the boom and the instantaneous posture of the boom, obtaining an instantaneous inherent frequency estimated value by inquiring a pre-stored inherent frequency fitting data table; constructing a parameter pair according to the instantaneous motion frequency and the instantaneous inherent frequency estimation value, and generating a stability early warning signal of a corresponding grade according to the position of the parameter pair in a preset parameter unstable area map and the distance between the parameter pair and the unstable area boundary; and selecting a corresponding active control strategy according to the level of the stability early warning signal, and performing control adjustment according to the active control strategy to generate a final control instruction. By adopting the method, the movement speed and the operation efficiency of reciprocating rescue can be improved.

The present invention addresses the problem of difficulty in determining the motion state of ground targets due to the rigid motion of airborne cameras affected by air currents and the strong maneuverability of ground targets in infrared target tracking in air-to-ground scenarios. An interactive multi-model infrared time-sensitive target tracking method that integrates image features is invented. Within the framework of Kalman filtering, the present invention uses target detection results as state observers, introduces inter-frame registration to compensate for errors caused by coordinate system transformation due to the shaking of the airborne platform, uses interactive multi-models to characterize the strong maneuverability of ground moving targets, and finally accurately tracks the moving targets through data association. The tracking method proposed by the present invention has low complexity, can well adapt to the complex environment of air-to-ground imaging, and the tracking accuracy is not affected by the accuracy of the target detection results, which has important engineering significance.

The method of snapshot compressive imaging three-dimensional Gaussian splatting reconstruction belongs to the field of computer vision and computational photography. A reconstruction network based on the hybrid architecture of stochastic gradient Langevin dynamics (SGLD) and explicit three-dimensional Gaussian representation is built. Then, multiple physical perception modules are combined to achieve the deep decoupling and reconstruction of the spatiotemporal information of dynamic scenes. Driven by the embedded decoupling deformation field, the deformation field contains a coarse-grained trajectory prediction branch and a fine-grained integral fitting branch: the coarse-grained branch combines low-frequency time coding with latent embedding features, enabling Gaussian primitives to capture global rigid motion trajectories and serving as a temporal regularizer; the fine-grained branch uses high-frequency time coding to predict non-rigid deformation and physically fits the motion blur stripes generated by temporal integration through anisotropic scale stretching. An adaptive density control strategy compatible with physics is introduced. Using the physical integral imaging simulation module, high-fidelity and multi-view consistent high-speed dynamic three-dimensional scene reconstruction results are obtained.

The utility model discloses a clamping assembly, jacking clamping device and optical module processing equipment, and relates to the technical field of optical module clamping processing, the clamping assembly comprises a rigid motion part and a flexible motion part which are opposite in a first direction, a clamping interval is formed between the rigid motion part and the flexible motion part, the clamping interval is used for placing an optical module, and the flexible motion part is used for clamping the optical module. The rigid moving part and the flexible moving part can be relatively close to each other in the first direction to clamp the optical module, and the rigid moving part has a reference positioning position in the moving stroke of the rigid moving part. According to the technical scheme provided by the utility model, the problem that the housing structure of the optical module is easy to deform due to overpressure in the existing clamping and positioning process is solved.

The invention relates to the technical field of underground structures, in particular to a replaceable node of a bearing-damping decoupling regulation and control mechanism and a working method. The replaceable joint comprises a supporting column, a bearing beam and a decoupling regulation and control component, and the decoupling regulation and control component is located between the supporting column and the bearing beam. The decoupling regulation and control component comprises a connecting beam, energy dissipation pieces and a connecting plate, the energy dissipation pieces are located on the upper side and the lower side of the connecting beam, the outer end of the connecting beam and the outer ends of the energy dissipation pieces are fixedly connected with the supporting column, the inner ends of the energy dissipation pieces are rotationally connected with the outer end of the connecting plate, and a sliding groove is formed in the connecting plate and arranged horizontally. The inner end of the connecting beam is connected with the sliding groove in a sliding mode, and the inner end of the connecting plate is rotationally connected with the bearing beam. According to the invention, bearing-damping decoupling is independently regulated and controlled, and the rigid motion of the support column is utilized to realize relative displacement between the energy consumption piece and the connecting plate to achieve deformation coordination, so that cooperative work is realized.

An electronic device and method for generating a reflectogram for a reilluminable 3D model are disclosed. An electronic device acquires multi-view image data including a set of images of an object, and generates a 3D mesh of the object based on the multi-view image data. The electronic device obtains a set of motion-corrected images based on minimization of rigid motion associated with the object between images of the set of images and generates a texture map in the UV space based on the set of motion-corrected images and the 3D mesh. The electronic device obtains a specular reflection map and a diffuse reflection map based on separating the specular reflection component and the diffuse reflection component from the texture map, and obtains a reilluminable 3D model of the object based on the specular reflection map and the diffuse reflection map.

The application discloses a motion-robust non-contact heart rate detection method, an electronic device and a storage medium. The method comprises the following steps: firstly, extracting a pixel mean time sequence from a selected video face region of interest, including the selection and positioning of the region of interest, tracking the region of interest and extracting the pixel mean time sequence; secondly, removing non-rigid motion or rigid motion, including signal preprocessing, time delay, conversion from a single channel to a multi-channel, extraction of a bottom layer shared source, selection of a motion noise signal and a pulse signal; finally, heart rate estimation, Fourier transform of the pulse signal and corresponding operation to obtain a heart rate value. The application extracts a heart rate related signal from a video image, removes motion noise by using a denoising algorithm, detects the heart rate in a motion state, provides a new direction for non-contact heart rate detection research, and further promotes the application of the non-contact detection technology in a life scene.

The present application relates to the technical field of mechanical arm, and particularly relates to a flexible mechanical arm motion stability adaptive control method and system, the method comprising: decomposing a reference vibration signal composed of vibration data of each target joint of a target mechanical arm obtained in advance at a current time and within a preset time interval before the current time; determining rigidity motion coherence corresponding to each current signal component; reconstructing the reference vibration signal and determining a mutation vibration time corresponding to each target joint; screening out a vibration transmission starting joint; and adaptively controlling a torque at each target joint according to a purified vibration signal and the mutation vibration time corresponding to the vibration transmission starting joint and target joints on both sides of the vibration transmission starting joint. The present application improves the rationality of torque adjustment at the joints of the mechanical arm, thereby improving the motion stability of the mechanical arm.

The invention discloses a CBCT rigid motion artifact correction method and system, and the CBCT rigid motion artifact correction method based on a 3D-2D micro-registration framework outputs a final CT image x and the rigid disturbance quantity of all CT scanning angles through nine steps. According to the method, the estimated reconstructed image is registered to the measurement projection to estimate the rigid disturbance quantity generated in the CBCT scanning process, the rigid disturbance quantity comprises mechanical motion and human body autonomous / non-autonomous motion, the estimated rigid disturbance quantity is used for adjusting imaging geometry so as to reconstruct more accurate images, and the images are also used for achieving more accurate rigid disturbance estimation. The method has the beneficial effects that 1, a rigid motion modeling method is adopted, and a transformation matrix is strictly constrained to meet rigid transformation definition; 2, constructing a gradient-based 3D-2D registration frame, and estimating rigid disturbance by registering a reconstructed image to a measurement projection; and 3, ensuring that the image content is fixed in a specific imaging area by constraining rigid disturbance.

The invention relates to the technical field of mechanical arms, in particular to a flexible mechanical arm motion stability self-adaptive control method and system.The method comprises the steps that reference vibration signals formed by vibration data, obtained in advance, of each target joint point of a target mechanical arm at the current moment and within a preset time interval before the current moment are decomposed; determining rigid motion coherence corresponding to each current signal component; reconstructing the reference vibration signal, and determining a sudden change vibration moment corresponding to each target joint point; a vibration transmission starting joint point is screened out; and according to the purification vibration signals and the abrupt change vibration moments corresponding to the vibration transmission starting joint point and the target joint points on the two sides of the vibration transmission starting joint point, self-adaptive control is conducted on the torque of each target joint point. The rationality of torque adjustment at the joint points of the mechanical arm is improved, and therefore the movement stability of the mechanical arm is improved.

The invention belongs to the technical field of industrial robot precision measurement and kinematics calibration, and particularly relates to a mobile robot base elevation precision calibration method based on a tail end joint. According to the method, a laser tracker and a robot tail end short chain motion strategy are combined, and local high-rigidity motion of a fifth shaft and a sixth shaft of a robot tail end joint is utilized; according to the calibration method, tail end actual measurement pose data under a laser tracker coordinate system and nominal kinematics data under a robot base coordinate system are subjected to alignment resolving through a decentration singular value decomposition algorithm. According to the method, the requirements of efficient data acquisition speed, extremely high parameter identification stability and final positioning precision for base calibration in the field rapid deployment of the mobile robot are met, and the problems in traditional full-axis linkage calibration, especially in the traditional full-axis linkage calibration are solved. The problems of large data dispersion and low precision caused by substantial amplification of basic joint angle measurement error and geometric parameter deviation through a long kinematic chain are solved.

A computing system and method can be used to render a 3D shape from one or more images. In particular, the present disclosure provides a general pipeline for learning articulated shape reconstruction from images (LASR). The pipeline can reconstruct rigid or nonrigid 3D shapes. In particular, the pipeline can automatically decompose non-rigidly deforming shapes into rigid motions near rigid-bones. This pipeline incorporates an analysis-by-synthesis strategy and forward-renders silhouette, optical flow, and color images which can be compared against the video observations to adjust the internal parameters of the model. By inverting a rendering pipeline and incorporating optical flow, the pipeline can recover a mesh of a 3D model from the one or more images input by a user.