632 results about "Human motion" patented technology

The invention discloses a posture feature recognition method based on a video stream, and the method comprises the steps: carrying out the preprocessing of a continuous video stream, obtaining video frame training data, extracting a key frame and an adjacent frame in each frame of image, constructing a feature extraction module for a human body region, and obtaining a global frame, performing local extraction on the human body area by using adjacent frames on the left side and the right side to obtain local frames, and constructing semantic association information for the global frame through time sequence continuity between the local adjacent frames and the current key frame; acquiring enhanced feature representation by adopting a conditional feature aggregation algorithm; obtaining attitude sequence data through the attitude detail features; the method comprises the following steps: establishing three-dimensional coordinates, adaptively extracting posture change data by adopting a human body motion decoupling model, predicting human body posture characteristics through a smooth optimization strategy, and introducing a cross attention mechanism to realize deep fusion of spatio-temporal characteristics, so that the understanding ability of the model to a complex action mode is enhanced; and the attitude expression capability of the model in a sheltered or fuzzy region is obviously improved.

The invention relates to the technical field of computer vision, and discloses a high-speed human motion trail motion mode recognition system. Through multi-modal sensor fusion and an adaptive space-time attention network (ASTAN), the problems that a traditional optical system depends on mark points and IMU accumulative errors exist are effectively solved, and the high-speed movement track reconstruction precision and the environmental adaptability are remarkably improved; self-supervised data enhancement and dynamic model compression technologies are combined, so that the dependence on labeled data is greatly reduced, lightweight edge deployment is realized, and the real-time requirement is met; the system can synchronously output multi-mode feedback instructions, supports multi-scene application such as sports action correction, medical rehabilitation evaluation, security and protection anomaly detection and man-machine interaction control, and solves the core pain points of insufficient precision, real-time performance, robustness and generalization ability in the prior art. And an efficient, reliable and low-cost comprehensive solution is provided for high-speed motion analysis.

The invention discloses a method and a system for generating 3D (three-dimensional) human motion under text driving by utilizing a 2D (two-dimensional) video. The method comprises the following steps of: acquiring the video and preprocessing to obtain a two-dimensional key point sequence and text description; the two-dimensional key point sequence passes through a spatiotemporal feature adapter to obtain a potential spatiotemporal feature sequence, a residual vector quantizer quantizes and outputs a three-dimensional SMP L parameter sequence, and meanwhile, potential spatiotemporal features and a discrete Token sequence are mapped; preprocessing a text to extract a semantic vector, partially covering a Token sequence of a basic quantization layer, reconstructing a prediction sequence through a predictor in combination with the semantic vector, and obtaining a complete sequence through a refiner; constructing a total loss function and a text-to-action loss function to train the module; and inputting the text description and the basic quantization layer Token to a trained module, outputting a three-dimensional SMPL parameter sequence, and rendering to generate a three-dimensional human body grid and animation. According to the method, the end-to-end generation from the text to the three-dimensional SMPL action is realized only by two-dimensional key points and text description.

The invention discloses a human motion posture recognition method and system based on multi-modal data fusion, and relates to the technical field of posture recognition, and the method comprises the steps: firstly, synchronously obtaining a human motion posture video frame and an IMU segment, then carrying out the feature extraction of the two kinds of heterogeneous data in a shunt parallel mode, and carrying out the feature extraction of the two kinds of heterogeneous data; and respectively capturing visual space attitude information and dynamic inertial characteristics of the IMU. Afterwards, specific features of the modals are uniformly expressed through a mixed Token and embedding mechanism, and a space-inertia collaborative attention fusion mechanism is further introduced to realize dynamic association and deep fusion of cross-modal information; and finally, classifying the multi-modal fusion representation vector obtained by fusion so as to realize accurate recognition of the human motion posture. In this way, the defect that traditional fusion is insufficient in capturing subtle action differences can be overcome, and the accuracy and stability of action recognition in a complex scene are improved.

The invention belongs to the technical field of three-dimensional reconstruction, and discloses a three-dimensional digital human generation method and system capable of voice interaction. According to the invention, brand new speaking audios in different languages are automatically generated according to different languages of the input target text and the sampled human voice audios; the sequential stability and detail reduction capability of three-dimensional human motion are guaranteed by using multi-model joint estimation and a sequential loss function, and facial expression details and hand postures in the image can be accurately estimated. After the high-precision three-dimensional human body model is obtained through estimation, human body action and expression generation is carried out based on voice driving, accurate synchronization of actions and expressions generated through voice is achieved, and facial expression movement and body posture movement, namely a whole-body three-dimensional human body model, conforming to brand-new speaking audio are accurately generated; and finally, rendering the whole-body three-dimensional human body model into a real digital human capable of voice interaction by using a three-dimensional neural rendering model. According to the invention, the realization of single person picture input, high-precision three-dimensional digital person generation and voice interaction is facilitated.

The invention discloses a costume design assisting method and system based on artificial intelligence, and belongs to the field of costume intelligent design, and the method comprises the steps: extracting multi-dimensional style feature information from a pre-constructed costume image data set and a fashion trend database through employing a convolutional neural network, and constructing a style vector space model; vector similarity matching is carried out, and a costume design sketch is generated by adopting a graph neural network; based on the design sketch, generating a structured process data packet for proofing; the design sketch and the structural data are input into a three-dimensional human body modeling and simulation module, and wearing effect simulation of virtual clothes is realized based on human body motion capture and physical cloth simulation technologies; and constructing a human-computer interaction interface, and quickly responding to a modification request based on the generative adversarial network model. Structured information such as the garment pattern structure, the sewing sequence, the material specification and the process route is automatically generated through the reinforcement learning algorithm, and the garment proofing efficiency and accuracy are remarkably improved.

In an embodiment, a method for human motion generation with open vocabulary scene-and-text context is provided. The method involves receiving an input that includes a 3D point cloud of a scene containing a goal object with a natural language instruction related to the goal object. A text tokenizer is applied to the text to obtain tokenized text, and a text encoder from a pre-trained vision-language model generates text features. First scene features are generated by applying a pre-trained U-Net scene encoder to the 3D point cloud, which are down sampled to obtain second scene features. A conditional latent is obtained by fusing the second scene features with the text features. A conditional motion generator predicts motion parameters for a parametric human body model over a specific time duration. Finally, 3D human meshes for multiple motion frames are obtained based on the motion parameters and the parametric human body model.

The invention is suitable for the technical field of 3D scanning, and provides a figure model 3D scanning and dynamic attitude capturing method and system, which dynamically triggers 3D scanning by monitoring joint movement intensity in real time, continuously collects continuous movement tracks by using an inertial sensor in a non-scanning period, and reversely deduces space-time parameters of a shielded part through multi-light-source shadow boundary evolution. And constructing a spatio-temporal joint evaluation function to adaptively adjust the scanning frequency and the sampling rate, and finally performing spatio-temporal alignment and confidence weighted fusion on the discrete point cloud, the continuous trajectory and the reverse reckoning data to generate a dynamic biomechanical model. The scheme breaks through the bottleneck of resource waste and blind area shielding of traditional fixed frequency scanning, realizes space-time complementation and precision optimization of motion monitoring, and is suitable for dynamic scenes such as movie and television animation, medical rehabilitation, physical training and the like. According to the system, through multi-modal data fusion and self-adaptive resource scheduling, the data integrity, the real-time performance and the biomechanical analysis capability are remarkably improved, and an efficient solution is provided for human motion digitization.

The invention discloses a millimeter-wave radar sparse point cloud-based human body posture recognition method, which belongs to the technical field of human body posture recognition, and comprises the following steps of: acquiring three-dimensional point cloud data of human body actions through a millimeter-wave radar, and preprocessing the three-dimensional point cloud data; and training a lightweight neural network model by using the preprocessed point cloud data, wherein the model comprises an edge convolution module and a grouping sparse Transform encoder module. The edge convolution module extracts spatial geometric features and detects dynamics, static postures are directly classified, dynamic postures capture a time sequence dependency relationship through a grouping sparse Transform module, attention calculation is only carried out on frames with feature changes exceeding a threshold value, and mean pooling aggregation is carried out on other frames. And finally, classifying the human body postures based on the spatial geometric features and the time sequence dependency relationship to obtain a classification result. The device is simple in structure, accurate in recognition and suitable for efficient deployment of edge equipment.

Provided in the present invention is a reconstruction and driving method based on a multi-view motion video of a clothed human body. The method comprises: using a two-layer three-dimensional Gaussian representation to model a human body and corresponding clothes; defining geometric attributes of three-dimensional Gaussian ellipsoids for any face on coarse three-dimensional meshes of the human body and the clothes; at a reconstruction stage, transforming coarse triangular meshes of the clothes and the body from a canonical space to an observation space, and updating Gaussian geometric attributes; and on the basis of a camera pose and parameters of an input video, rasterizing a three-dimensional Gaussian representation of the observation space to an image space, and rendering a picture on the basis of a Gaussian splatting formula. Self-supervised training can be performed on a model by means of calculating the color difference between a rendered picture and a real picture and using same as an optimization objective; when reconstruction is completed and driving is performed, a geometric result of a current frame is used to calculate the position of the coarse triangular mesh of the clothes in the next frame; and the reconstruction-stage method and related parameters are used to render a driving picture in a new posture.

The invention provides a double-pendulum dynamics guided pedestrian motion track generation type prediction method, and belongs to the technical field of automatic driving scene prediction. Comprising the following steps: establishing a pedestrian motion nonlinear dynamic model based on double-pendulum dynamics, and defining a mapping relation from an attitude space to a double-pendulum state space; establishing a high-degree-of-freedom pedestrian motion nonlinear dynamic state prediction model for predicting the motion state of the pedestrian at the future moment in the double-pendulum state space; establishing a conditional diffusion model for reconstructing the human body posture of the pedestrian at the future moment in the double-pendulum state space; the past state track of the pedestrian, the reconstructed human body posture of the pedestrian at the future moment, the past track of the adjacent pedestrian and semantic map information serve as guiding conditions of a conditional diffusion model, and generation of a future motion track of the pedestrian is guided. The motion state space of the double-pendulum system represents the non-linear dynamic change space of human body motion, and accurate prediction of the pedestrian motion track is realized by utilizing the generation of the conditional diffusion model.

The invention relates to a human body posture estimation key point correction method based on skeleton proportion constraint, and belongs to the technical field of human body posture estimation key point detection. The method comprises the following steps: extracting key points of a human body in a human body motion video, forming a skeleton based on the key points, calculating a skeleton proportion value of each skeleton length and a thoracolumbar spine length in the skeleton, and defining a frame corresponding to the skeleton proportion value not within a preset threshold as an invalid frame; iterating the positions of the key points in the invalid frame until the bone proportion values formed by all key point sequences in the invalid frame are within a preset threshold value or reach a preset maximum number of iterations; and detecting the widths of the four limbs based on the iterated key points, adjusting the positions of the key points to the axis positions corresponding to the width centers of the four limbs to obtain the adjusted key points, and reconstructing a key point sequence to realize key point correction. The objective of the invention is to solve the technical problem of low key point detection accuracy caused by deviation in key point positioning in the prior art.

The invention relates to the technical field of smart home, in particular to a smart home control method and system based on multi-modal fusion and deep learning. The method comprises the steps of triggering a data acquisition instruction, and performing human body data acquisition; acquiring human body data, and generating a global human body motion track sequence according to the preprocessed human body data; predicting a human body track target point and a space region; acquiring a human body track target point and spatial region data, and predicting a target electric appliance and a use probability thereof; the use probability of the target electric appliances is obtained, the target electric appliances are sorted, and electric appliance starting and standby operation is carried out; the system comprises a data acquisition module, a motion trail sequence generation module, a prediction module, a target electric appliance prediction module and an electric appliance operation module. Based on the human body track generated by sensor data, the corresponding electric appliances are pre-started by predicting the room where the user is about to arrive and the electric appliances possibly used by the user, so that multi-scene and multi-space coverage is realized, and a complex indoor environment can be met.

Approaches presented herein provide for the use of reinforcement learning to fine-tune a generative model, such as a motion diffusion model, for a specific objective, such as to generate representations of human motion corresponding to provided text input. A discriminator can be used to guide the training of the generative model. In at least one embodiment, the discriminator can compare the input text and generated motion representation (or embeddings of each) to determine an alignment value or match score, for example, which can then be used to adjust the network parameters or weights of the generative model to improve the alignment between input text and generated motion.

The invention relates to the technical field of pressure monitoring, and discloses a method and system for motion state analysis according to plantar pressure, and the method comprises the steps: receiving multi-modal biomechanical data related to a landing event; extracting a corresponding motion feature vector from the multi-modal biomechanical data; and inputting the motion feature vector into a motion state analysis model for identification to obtain a corresponding damage risk index, and outputting the corresponding damage risk index. By receiving pressure distribution data detected by the plantar pressure sensing array, shear force data detected by the shear force measuring and calculating module and a kinematics data sequence detected by the inertial measurement unit, biomechanical information in the movement process can be comprehensively captured from multiple dimensions; compared with a single data acquisition mode, the fusion of the multi-modal data can reflect the real state of the human body in motion more accurately, and a richer and more accurate data basis is provided for subsequent motion state analysis.

The invention relates to the technical field of posture recognition, in particular to a motion posture recognition method and system based on deep learning, and the method comprises the following steps: based on a human body motion image sequence, analyzing a skeleton center space trajectory, adjusting an acquisition visual angle, recognizing staged skeleton nodes, and generating a node time sequence trigger sequence; and optimizing joint point angle feature grouping and expression to obtain a hierarchical feature expression structure. In the invention, through detection for interference dynamic change characteristics, visual angle adjustment and node staged response in a time sequence are combined, compensation reasoning of a space trajectory is enhanced, and the hierarchical expression capability of motion capture is improved; the input features have the advantages of actively screening background disturbance, dynamically adapting the motion direction, separating action core nodes and perfecting node response association and grouping angle time sequence structures, the integrity and identification degree of action feature structure expression and hierarchical modeling are guaranteed, and higher identification accuracy and complex environment adaptability are brought.

The invention discloses a control method, and the method comprises the steps: collecting the data of a centroid state and an MPC optimal ground acting force in a plurality of motion states of a robot, designing a full-connection residual network, taking the centroid state information as the input, taking the ground acting force as the output, and designing a loss function based on priority. Upper and lower bounds of a friction cone and a sole reaction force are constrained, and the network is trained offline to fit MPC optimization quantity, so that an efficient mode of online reasoning is realized; the joint angle and the angular velocity are fused with the action at the previous moment, the centroid linear velocity and the angular velocity and the foot-ground acting force fitted through a residual network, a bionic reference trajectory is generated through a human motion public data set, different weights are given to a reward function group according to a dominant function value obtained through calculation, and the control performance is improved; symmetrical loss constraint is added to lower limb movement, and the algorithm convergence speed is increased. And finally, training to obtain a whole-body control strategy based on model priori knowledge and a human motion reference trajectory.

A multi-modal human body action generation method based on a large language model comprises the steps that structural features are extracted based on 3D action data, body part-level atomic semantic description is generated in combination with the large language model, and a multi-modal alignment data set containing texts, voices and music is constructed; whole-body actions are decoupled according to parts, an independent vector quantization encoder is adopted to perform residual quantization, and an atomic action token strongly associated with a fine-grained text is generated; splicing the text description and the action token into a mixed action sentence containing a special mark according to a body structure; multi-modal input joint modeling is realized through a large language model, a fine-grained text and an action token sequence are synchronously generated, 3D actions conforming to semantics are output through decoding, and zero sample generation and part-level accurate control are supported. According to the method, the limitation of coarse-grained alignment of a traditional method is broken through, and the semantic consistency, multi-modal adaptability and local controllability of action generation are remarkably improved through fine-grained semantic mapping, decoupling action coding and unified sequence modeling.

The invention belongs to the technical field of sensor measurement and recognition, and particularly relates to a human body motion recognition system based on LSTM (Long Short Term Memory), which comprises a data acquisition module, a data calculation module and a data application module, and utilizes a neural network model and a wearable electronic sensor to detect a human body walking state. A new long short term memory (LSTM) recurrent neural network model, namely an LSTM-STRM model, is established, the model combines multi-task learning, an attention mechanism and spatio-temporal feature fusion to accurately classify the walking state of the human body, and the walking state is compared with the original LSTM model. The result shows that the LSTM-STRM model can be used for classifying the time sequence data collected by the measuring unit, the states of the five targets can be classified with high precision, and the recognition accuracy is higher than that of an original LSTM model. The method improves the recognition precision, is high in adaptability, is suitable for the fields of medical treatment, human-computer interaction, exercise training and the like, and has a wide application prospect.

The invention relates to a tumble risk assessment method and system based on a multi-modal deep learning network, and relates to the technical field of human body posture recognition, and the method comprises the steps: collecting a scene motion image sequence, a plantar pressure feature sequence and personnel basic information; analyzing the scene motion image sequence by using a human body posture estimation network model to determine a human body key feature point sequence; performing feature extraction on the human body key feature point sequence and the scene motion image sequence to generate human body posture sequence features; performing feature extraction fusion on the human body key feature point sequence and the plantar pressure feature sequence to generate human body motion fusion time sequence features; performing feature extraction on the personnel basic information to generate personnel basic information features; and inputting the human body posture sequence features, the human body motion fusion time sequence features and the personnel basic information features into a multi-modal deep learning network for analysis so as to determine a fall risk score. The method and the device have the effect of improving the precision of fall risk assessment.

The invention provides a body function evaluation method and device based on multi-modal sensing fusion. Real-time detection and analysis of human motion and postures are achieved through a multi-modal sensing technology. According to the method, the test process is standardized, operation is automatic, scoring is objective, the accuracy and repeatability of the test are improved, and manual intervention is reduced. Through visualization and voice guidance, action demonstration and prompts are provided on a large screen, it is ensured that a testee completes a test autonomously, and the operation burden of workers is reduced. Meanwhile, the system automatically calculates scores and generates reports according to a standard SPPB scoring rule, provides result interpretation and rehabilitation suggestions, and remarkably improves the evaluation efficiency and practicability. In addition, a personalized video exercise prescription is generated according to the test score, so that the testee can track the training progress conveniently. The closed loop of detection and intervention services is ensured, and the rehabilitation effect is improved.

The embodiment of the invention relates to the technical field of robots, and discloses a control method for improving the humanoid degree of a robot, and the method comprises the steps: obtaining a surface electromyogram signal of a corresponding position through an electromyogram detection assembly disposed at a user, and carrying out the preprocessing of the obtained surface electromyogram signal, so as to obtain an electromyogram activity curve; performing feature extraction on the myoelectricity activity curve to obtain myoelectricity time sequence features, and inputting the myoelectricity time sequence features into an action sequence decoding model for recognition to output action categories and action sequences associated with the action categories; and matching with the to-be-executed machine joint state according to the action category and the action sequence associated with the action category, and if the matching is inconsistent, performing updating operation on the to-be-executed machine joint state according to a matching result. According to the scheme, it is ensured that the motion of the robot is highly consistent with the human motion, and the humanoid degree and motion accuracy of the robot are improved.

The invention relates to the technical field of abnormal behavior recognition, in particular to an abnormal behavior multi-mode recognition method and system for a smart community. Comprising the following steps: multi-modal data acquisition and preprocessing: synchronously acquiring spatio-temporal dynamic data of a target area through a millimeter wave radar, an infrared sensor, a microphone array and a panoramic camera deployed in a community, wherein the spatio-temporal dynamic data comprises a human body motion track, temperature field distribution, environment voiceprint characteristics and a visual image sequence; wherein the millimeter-wave radar adopts a frequency modulation continuous wave system to sample micro-Doppler characteristics of a human body, the infrared sensor realizes temperature field reconstruction through the pyroelectric array, the microphone array collects voiceprint signals through the array structure, and the panoramic camera collects a high-frame-rate image sequence; and environment interference coupling correction: aiming at acoustic reflection characteristics of different materials in the community, and combining an illumination abrupt change rate, an object reflectivity and an air humidity parameter, the method can improve the recognition accuracy and robustness in a complex community environment.

The invention discloses an end joint precision enhancement method and device of an unmarked motion capture system, and relates to the technical field of human motion capture, and the method comprises the steps that a main system collects original motion capture data to obtain a joint initial pose of the whole body of a detected object; an enhancement module is installed at the tail end joint of the measured object, and the enhancement module at least comprises an optical mark point and an inertial sensor; performing spatial position identification on the tail end joint of the detected object to obtain first tail end joint position data, and synchronously acquiring second tail end joint position data of the enhancement module; performing fusion filtering processing on the first tail end joint position data and the second tail end joint position data to obtain high-precision position data of the tail end joint; and the enhanced tail end joint motion data of the enhancement module is collected, and the target tail end joint motion data is output by combining the enhanced tail end joint motion data and the high-precision position data. The method has the effect of improving the accuracy and robustness of the motion capture system.

Systems and methods are disclosed that perform global human and camera motion estimation using a motion diffusion model that is attached to a control branch. For instance, using a controlled motion denoiser that comprises the motion diffusion model and the control branch, global human motions and the corresponding camera motions from “in-the-wild” videos may be estimated. Initially, SLAM may be used to initialize the camera motion and a pose estimation model may be used to estimate the local human motion. Combining the two, embodiments of the present disclosure initialize the global human motion. Then, during optimization and using a COIN system that includes the controlled motion denoiser and / or using a COIN algorithm, embodiments of the present disclosure enforce the global human and camera motion to satisfy a two-dimensional (2D) projection on videos and the motion distribution from the motion diffusion model.

The invention provides an intelligent motion generation method, an intelligent motion generation system, electronic equipment and a computer readable storage medium, in the intelligent motion generation method, motion feature data are mapped and aligned to a virtual human skeleton structure, a preliminary motion sequence is obtained, and in addition, the motion feature data are mapped and aligned to the virtual human skeleton structure; and according to the virtual human skeleton structure and the preliminary action sequence, optimizing the action of the virtual human skeleton structure, and outputting an optimized action sequence, so that after the preliminary action sequence is obtained according to a redirection strategy based on the frame sequence of the video of the human body motion, the motion of the virtual human skeleton structure is optimized. And an optimized action sequence obtained by optimizing the preliminary action sequence can be more matched with the body shape of the virtual human.

The invention discloses a video generation method and system based on a scene adaptive track and mirror moving control, and belongs to the technical field of computer vision. The method comprises the following steps: firstly, aligning a scene point cloud and a parameterized human motion sequence to a unified coordinate system, generating a ground adaptive three-dimensional track according to a two-dimensional track input by a user and scene geometry, and redirecting the motion; projecting the three-dimensional information into a two-dimensional condition graph based on camera parameters; and finally, in a conditional diffusion model generation process, selectively fusing scene geometric condition information after noise addition into the current denoising latent variable by utilizing a visibility mask generated by the depth map, so as to realize view angle self-adaptive mirror operation control. According to the method, the problems of conflict between character motion and scene, inflexible track control and inconsistent background under camera motion are solved, and a controllable video which is physically consistent and visually real can be generated.

The invention discloses a 3D human body action recognition method based on geometry-contour multi-frequency, relates to the technical field of computer vision and behavior recognition, and provides an end-to-end learning framework from point cloud sequence input to action recognition output. The framework innovatively fuses two core processes of geometry-contour space structure modeling and multi-frequency time decomposition modeling: the geometry-contour space structure modeling accurately depicts macroscopic contour postures and microscopic geometry details of a human body to comprehensively capture motion information; the latter decomposes the time attitude sequence into a low-frequency trend flow and a high-frequency detail flow, and digs action mode rules under different frequencies; and through cooperative work of the two, the accuracy of point cloud action recognition and the robustness in a complex scene are remarkably improved.

The invention discloses a reconfigurable exoskeleton power-assisted robot, a control method, equipment and a storage medium. The control method comprises the following steps that human body motion data are collected in real time through a sensor module; calculating an Euler angle by adopting a quaternion fusion algorithm; predicting a target position based on Kalman filtering; compensating a tracking error through a PID controller; switching a working mode according to the motion state; according to the invention, single interaction limitation is broken through, operation convenience and function expandability are both considered, and efficient man-machine cooperation is realized.

The invention discloses a fluid motion control method and system based on an axial flow fan, and the method specifically comprises the steps: carrying out the processing of fluid state data and human motion data through a space-time alignment algorithm, and generating a joint representation model; based on the joint characterization model, constructing a fluid simulation model by adopting an LBM technology, and generating a first fluid motion control parameter through the fluid simulation model and a preset multi-objective optimization function; correcting the first fluid motion control parameter through the PMV-PPD thermal comfort index to form a second fluid motion control parameter; and correcting the first fluid motion control parameter or the second fluid motion control parameter through the user emotional state data to form a third fluid motion control parameter. According to the system, high-precision and intelligent control over fluid motion of the axial flow fan is achieved, the sensing capacity and control precision of the system can be improved, and the collaboration, health guarantee capacity and interactive experience of the system can be enhanced.