277 results about "Object motion" patented technology

The invention discloses a reference video object segmentation method based on semantic consistency and motion perception. The method comprises the following steps: 1, constructing semantic prompt information and video frame information of a reference video object segmentation data set; 2, preprocessing the reference video object segmentation data set; 3, establishing a reference video object segmentation model based on semantic consistency and motion perception: designing a double-branch decoupling strategy for decoupling feature information at semantic and visual levels so as to extract static and motion information of text description and visual features; a hierarchical motion sensing module is designed to capture and align motion information between different frames, and analyze short-term and long-term motion information, so that the model obtains a sensing ability for a long-term motion mode; the semantic consistency module is designed to align semantic description and video features, so that the accuracy of target selection and the integrity of masks are improved, and false detection of negative samples is avoided; a perceptual dynamic fusion mechanism is designed to be used for embedding text information into a visual feature space, so that visual features can obtain text semantic information, and the cross-modal understanding ability of the model is enhanced; 4, constructing a loss function, updating model parameters, setting training parameters, and training to obtain an optimal weight; and 5, detecting the test set image based on the optimal weight to obtain a final segmentation result. According to the method, static and dynamic information is effectively decoupled, the sensing ability to an object motion mode is enhanced, and the segmentation performance is improved.

The invention discloses a robot dynamic grabbing method based on a sliding window self-attention mechanism, and the method comprises the steps: firstly installing a camera, and calculating a transformation matrix between the camera and a mechanical arm coordinate system based on a hand-eye calibration technology; processing the static data set by adopting affine transformation to generate a grabbed dynamic data set with speed information; then, a dynamic grabbing network model based on a sliding window multi-head self-attention mechanism is constructed, and a loss function optimization model considering the object movement speed and the grabbing posture at the same time is designed; and finally, the trained model is deployed in a robot grabbing environment, a visual servo grabbing control scheme based on the position is designed, and follow-up movement and grabbing action of an end effector of a mechanical arm on a to-be-grabbed object are achieved. According to the dynamic grabbing method of the robot, the grabbing posture and the movement speed of the object can be quickly and accurately predicted based on a group of continuous single-channel depth images collected by the camera, and the grabbing problem of a universal object in a complex dynamic environment is solved.

The present invention belongs to the technical field of an object driving device, in particular to an object's motion attitude adjusting device and a puncturing, liquid filling and mixing system. The object's motion attitude adjusting apparatus includes a turntable, a plurality of object's motion attitude adjusting devices provided on the turntable, the object's motion attitude adjusting device including a base and a plurality of object's motion attitude adjusting mechanisms provided on the base, a first driving wheel connected with each of the object's motion attitude adjusting mechanisms in a transmission manner, a first driving component connected with the turntable for driving the turntable, and a second driving component connected with the first driving wheel for driving the first driving wheel.

An approach is provided for computer-vision-based object motion detection. The approach involves receiving a video sequence captured from a perspective of a vehicle / device traveling at street level. The approach also involves processing frames of the videos sequence using computer vision to determine semantic localization feature(s) associated with object(s) detected in the frames. The approach further involves clustering the object(s) into object cluster(s) across the frames based on the semantic localization feature(s). The approach further involves creating an object vector connecting the object(s) in a given cluster of the object cluster(s) across the frames. The approach further involves computing an angle between the object vector and a reference vector associated with a movement of the vehicle / device across the frames. The approach further involves classifying a motion of the object(s) relative to the vehicle / device based on the angle.

A computerized method for vehicle cabin safety includes determining, based on one or more images showing an interior of a vehicle cabin, at least one object in the vehicle cabin. The method includes determining a number of features of the at least one object. The method includes determining a danger level for the at least one object based on the number of features. The method includes, in response to determining that the danger level meets a given criteria, outputting a warning signal.

The invention discloses a video generation method and device, equipment, a medium and a program product, and relates to the field of artificial intelligence. The method comprises the following steps: denoising noise feature representation based on a first text, an object movement track and a camera attitude parameter to obtain video feature representation; and performing video prediction based on the video feature representation to obtain a first video. In addition to the first text, additionally acquiring an object movement track to determine video object movement in the generated first video, namely controlling local movement in the generated first video through the object movement track; in the embodiment of the invention, the camera attitude parameter is additionally acquired to control the camera motion in the determined first video, that is, the global motion in the generated first video is controlled through the camera attitude parameter, so that local motion control and global motion control of the generated first video are realized, and the motion diversity in the first video is improved.

Systems and methods are disclosed for motion forecasting in autonomous vehicles using a machine learning model trained with cycle consistency loss. Some machine learning models are trained to predict future object motion based on past observed motion, using ground truth knowledge of future object motion. In practice, such models are often inaccurate and thus unsuitable for safety-critical operations. Disclosed herein is an improved training mechanism for an object prediction model, which training mechanism utilizes cycle consistency loss. This loss can be calculated using an inverted motion prediction-that is, given observed motion and a predicted future motion, how likely the predicted future motion, if passed through the model as if it were historical data, would result in a prediction of the observed motion. Training based on inverted or backward motion prediction can improve an ability of a machine learning model to accurately predict future motion based on observed motion.

A method includes determining a trajectory of an object based on a mass of the object, and determining a motion of a hand based on the mass of the object and the trajectory of the object. The method can further include generating an animation of the hand interacting with the object based on the trajectory of the object and the motion of the hand.

The invention discloses a robot control method and device, a robot, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence. The robot control method comprises the steps that a first color depth image of a target scene at the current moment and execution action information of a robot are acquired; inputting the first color depth image and the execution action information into a dynamic prediction module of a target world model, and obtaining a prediction scene flow of the target scene at the next moment output by the dynamic prediction module; and inputting the predicted scene flow and the first color depth image into a diffusion module of the target world model to obtain a second color depth image of the target scene at the next moment output by the diffusion module. The method can effectively predict the object motion trail and the environment state change rule, controls the robot according to the prediction result, improves the accuracy and response speed of the robot control strategy, and enhances the reliability of the robot in a complex scene.

The invention provides an object motion trail prediction method and device, and belongs to the technical field of computer vision and image processing, and the method comprises the steps: reconstructing an obtained multi-view time sequence two-dimensional image sequence of a target object, obtaining an original particle point cloud sequence, and generating a sparse key point cloud sequence after sampling; constructing a particle map sequence based on the spatial position of the key point at each moment in the sequence, and performing spatial semantic completion; performing object-level dynamic space-time aggregation on the complemented key point feature sequence to obtain aggregated key point features, inputting the aggregated key point features into a particle diagram converter, and outputting key point updating features after long-range force propagation modeling through the converter; and decoding and predicting key point displacement at a future moment based on the updated feature, and generating a future movement track of the target object according to the key point displacement. Based on the method, the invention further provides a device for predicting the object motion trail. According to the method, the fine appearance and the stable and accurate motion trail of the object can be predicted at the same time.

The invention discloses an object level motion blur three-dimensional scene synthesis method and an object level motion blur three-dimensional scene synthesis device based on three-dimensional Gaussian splash (3D Gaussian splash, 3DGS). According to the method, a multi-view image and corresponding camera parameters are used as input, and three-dimensional Gaussian point scene representation including spatial position, scale, rotation, opacity and appearance characteristics is constructed; generating a binary mask of a moving foreground object and a static background by using an image segmentation model; on the basis, camera exposure time is dispersed into a plurality of time steps, space pose parameters changing along with time are introduced only for three-dimensional Gaussian points corresponding to the foreground object, instantaneous three-dimensional scene representation under each time step is obtained, integration or weighted averaging is carried out on rendering results of the plurality of time steps, and the real-time three-dimensional scene representation of the foreground object is obtained. Generating a motion blur rendering result with real physical significance; meanwhile, a mask-guided foreground-background separation rendering strategy and a partition loss function are adopted, clear rendering supervision is applied to a static background area, fuzzy rendering supervision is applied to a moving foreground area, and joint optimization of three-dimensional Gaussian scene parameters is achieved; in the reasoning stage, the clear background and the fuzzy foreground are fused and output according to the mask, and a three-dimensional scene reconstruction result with the clear background and the reasonable motion fuzzy effect of the foreground is obtained. According to the method, the exposure integral process and the object movement track are explicitly modeled in the three-dimensional geometric space, and object-level controllable fuzzy three-dimensional scene generation is realized.

An object of initial unknown position on a map may be determined by traversing through moving and turning to establish motion trajectory to reduce its spatial uncertainty to a single location that would fit only to a certain map trajectory. An artificial neural network model learns from object motion on different map topologies may establish the object's end-to-end positioning from embedding map topologies and object motion. The proposed method includes learning potential motion patterns from the map and perform trajectory classification in the map's edge-space. Two different trajectory representations, namely angle representation and augmented angle representation (incorporates distance traversed) are considered and both a Graph Neural Network and an RNN are trained from the map for each representation to compare their performances. The results from the actual visual-inertial odometry have shown that the proposed approach is able to learn the map and localize the object based on its motion trajectories.

A method may include using a camera to capture a group of image exposures of an object, where each exposure is illuminated by a respective illumination pulse from a sequence of pulses. The method may further include determining pulse ratios of pairs of the time intervals that exist between the pulses, as well as a distance ratio of two of the distances between two pairs of the exposures. Additionally, the method may include comparing the distance ratio to the pulse ratios to determine a correlation between the illumination pulses and the exposures. The method may also further include using the correlation to determine characteristics of the object's motion, such as the object's velocity, position, speed, trajectory, orientation or spin rates.

To provide a method for generating a dataset of robot motion programs for training a path generation neural network.SOLUTION: A large language model uses a robot task library and an asset geometry database as inputs. The large language model breaks down a task into steps, and then generates code describing a robot and object motion to complete the task. The generated code produces robot motions for the task, and a corresponding robot motion program is created and executed in simulation. The simulated robot motion programs are used to generate collision-free robot paths via RRT and / or optimization, and the collision-free paths are validated for robot reachability and object placement success. The validated motion programs are added to a dataset and used for training a path generation neural network.SELECTED DRAWING: Figure 3

This disclosure relates to a virtual object motion generation method and apparatus, and a computer device. The method includes: parsing the motion description text to obtain respective motion description information of the plurality of semantic levels; separately encoding the motion description information of the plurality of semantic levels to obtain respective motion description representations of the plurality of semantic levels; performing denoising processing at the first semantic level on the sampled noise signal based on a motion description representation of the first semantic level, to obtain a motion eigenvector; performing, at each semantic level after the first semantic level, denoising processing on the sampled noise signal based on a motion eigenvector and respective motion description representations of at least two semantic levels from the first semantic level to the current semantic level, to obtain a motion eigenvector; and decoding the motion eigenvector to obtain the virtual object motion.

The present invention discloses a robot dynamic grasping method based on a sliding window self-attention mechanism. The method first installs a camera and calculates the transformation matrix between the camera and the manipulator coordinate system based on the hand-eye calibration technology; uses affine transformation to process the static data set to generate a grasping dynamic data set with speed information; then constructs a dynamic grasping network model based on the sliding window multi-head self-attention mechanism, and designs a loss function optimization model that simultaneously considers the object's motion speed and grasping posture; finally, deploys the trained model into a robot grasping environment, designs a position-based visual servo grasping control scheme, and realizes the follow-up movement and grasping action of the manipulator end effector to the grasped object. The robot dynamic grasping method of the present invention can quickly and accurately predict the grasping posture and motion speed of an object based on a set of continuous single-channel depth images collected by the camera, solving the grasping problem of general objects in complex dynamic environments.

In-cabin object motion detection is provided. The invention relates to vehicle cabin safety, in particular to detection of objects and their movement in a vehicle cabin. At least one object in the vehicle cabin is determined based on one or more images showing an interior of the vehicle cabin. A number of features of the at least one object is determined and a degree of danger of the at least one object is determined based on the number of features. A warning signal is output in response to determining that the level of hazard meets the given criterion.

The invention provides a progressive motion-power alignment smart operation rapid migration method and system. Relates to the technical field of robot operation control. The method comprises the following steps: extracting hand-object movement and interaction information from an RGB hand-object interaction video; based on kinematics matching, mapping the hand operation track into a primary control signal of the target dexterous hand; performing dynamic optimization on the primary control signal in combination with a multi-level reward mechanism under a reinforcement learning framework, and generating a stable grabbing control strategy; a dexterous wrist control signal is synthesized according to the object target trajectory, and the semantic consistency of operation tasks is kept; and through a multi-dexterous-hand configuration adaptation mechanism, a control signal is migrated to dexterous hands of different configurations. According to the method, the human hand operation track can be automatically converted into control instructions of multiple types of dexterous hands, so that the dexterous hands have the capability of executing complex tasks such as grabbing, moving and operation, the training data acquisition cost of the dexterous hands is reduced, and the cross-equipment operation reusability and generalization capability are improved.

The invention provides a spatial intelligent visual physical process inference method based on an implicit physical large model, and belongs to the field of spatial intelligent and artificial intelligence modeling calculation. The problems of low prediction precision and lack of physical consistency for complex physical scenes in the prior art are solved. The method comprises the following specific steps: acquiring multi-modal data of an environment, and representing the multi-modal data in a unified coordinate system; preprocessing the multi-modal data, designing a geometric coding model, a dynamic prediction model and an energy conservation constraint, introducing a space-time attention mechanism, predicting the motion state of an object according to the multi-modal data, and obtaining prediction data of the motion state of the object; acquiring real observation data of object motion, comparing the difference between the prediction data and the real observation data, and performing correction and weight updating on the prediction data of the model through a self-adaptive residual term; according to the method, visual information and implicit physical law modeling are fused, and the self-supervised physical consistency constraint is utilized, so that automatic learning and prediction of a potential physical process are realized.

The invention belongs to the technical field of synchronous positioning and map creation, and discloses a robot algorithm, a storage medium and equipment for a dynamic shielding scene, and the algorithm comprises the following steps: S1, collecting image information, and carrying out the complete segmentation of a shielded object through an improved segmentation algorithm; s2, analyzing the motion state of the object through an object motion estimation method, and removing the accurately recognized dynamic region; s3, static information in a plurality of adjacent reference frames is utilized to complete restoration of a dynamic region, feature point extraction is performed on a restored data set, and the pose is computed.The method helps a network to deduce information of a shielded part through features in other directions when an object is shielded, and under the condition that boundary semantic information is weak, the network can still be subjected to feature point extraction, and the pose is calculated. The boundary of the object can still be accurately identified, the segmentation accuracy is improved, the key features of the shielded object can be captured, and the segmentation robustness is improved.

Provided are a method and device for driving movement of a target object by a gravitational field generated by a varying electromagnetic field which relate to the technical field of physics. The method includes: generating, by a variable electromagnetic field generator, a time-varying electromagnetic field in space where a target is located; adjusting a frequency, amplitude and phase of the time-varying electromagnetic field so as to generate an effect of a varying magnetic field in the space; and based on the time-varying electromagnetic field, generating an acting force on the target object to drive the target object to move along a predetermined trajectory or direction. The present invention breaks through limitation that the traditional electromagnetic mechanics can only drive metal materials, utilizes the varying characteristics of the electromagnetic field to drive and realize accurate control of movement of all objects comprising a non-magnetic substance and a non-conductive substance.

An object motion pose reproduction method based on a Marker ball comprises the following steps that firstly, size measurement is carried out on a target object, a model file is generated through three-dimensional scanning, and denoising and zooming optimization are carried out; then, a reflective Marker ball is pasted on the surface of an object, and three-dimensional coordinate data of the reflective Marker ball are collected through an optical motion capture system; then, a template group is constructed based on the initial Marker ball position of the object, a target group is constructed in combination with motion capture data, and a rigid body transformation matrix containing a rotation matrix and a displacement vector is solved through least square optimization; and finally, acting the transformation matrix on the model file to reproduce the pose, and reversely optimizing the modeling precision or the Marker point position through error analysis. The object motion pose reproduction method is high in precision, strong in anti-interference capability, simple in algorithm and suitable for the fields of industrial automation, movie and television games and the like.

There is disclosed a computer-implemented method performed in a tracking system for tracking the motion of a body, as a function of time, the method comprising: (a) during a first time period, obtaining first data related to the motion of a body from at least one primary positioning unit, wherein said at least one primary positioning unit is mounted on a first platform carried on the body, or wherein said at least one primary positioning unit is separate to the body, said primary positioning unit being operational during the first time period; (b) during the first time period, obtaining second data from one or more secondary sensors configured to make measurements from which position or movement may be determined, said one or more secondary sensors being mounted on one or more second platforms carried on the body; (c) generating first training data comprising the first data and second data; (d) during a second time period, obtaining third data from the one or more secondary sensors, and; (e) analysing the third data to estimate at least one first metric related to the motion of the body during the second time period using a first algorithm trained using the first training data. A tracking system for tracking the motion of a body, as a function of time, is also disclosed.

There are provided a method and device for controlling motion of a virtual object, which relate to the technical field of motion control. In the method a rotation control vector is generated according to a rotation state of a face of a user in a real three-dimensional space, the rotation state comprising a face rotation angle corresponding to a rotation of the face about at least one rotation axis in the three-dimensional space, and a component of the rotation control vector in at least one dimension being associated with the face rotation angle corresponding to the rotation axis; Motion of the virtual object is controlled through the rotation control vector, the motion comprising rotational motion. The methods and devices of the present disclosure can improve the experience of motion control on the virtual object.

The invention discloses a positioning and mapping method, system and device based on dynamic vision and a medium, and relates to the technical field of simultaneous positioning and mapping, and the method comprises the steps: carrying out the feature point extraction based on the dynamic detection information of a dynamic object, and obtaining a target feature set; compensating the motion track of the dynamic object based on the visual sensor prediction pose, and obtaining the motion state of the object; determining an object detection optimization variable based on the object motion state, the target feature set and the visual sensor motion parameters; performing real-time detection on the dynamic object by fusing the object detection optimization variable, obtaining a real-time detection result of the dynamic object and generating a static map to which the object belongs; according to the method, the motion trail of the dynamic object can be accurately tracked in real time, so that the positioning precision and the real-time performance of the dynamic object are improved, and the dynamic obstacle detection efficiency and the static map construction precision are further improved.

The invention relates to a device for controlling and / or regulating the movement of an object with regard to high dynamics with high accuracy and low energy consumption, said device comprising an electromagnetic actuator (2) which is designed to move the object and which has a stator (3) and a rotor (4), the rotor interacts electromagnetically with the stator (3) to generate movement and is coupled with an object or carries the object; a flexible member (7, 12) for guiding and / or carrying the rotor (4); and at least one sensor (13) for detecting a movement of the rotor (4) and / or of the object, a sensor signal of the at least one sensor (13) generated on the basis of the movement of the rotor (4) and / or of the object being able to be used for controlling and / or adjusting the position of the rotor (4). The invention further relates to a corresponding method.

The invention discloses a convergence judgment method for a round or spherical part layout system, electronic equipment and a storage medium. The method comprises the following steps: dispersing each circle or ball in a container into independent units by adopting a discrete unit method; selecting a model according to the collision deformation degree; the contact force between the circles or the balls is calculated based on the impulse principle; establishing a motion differential equation of a single circle or ball in the vertical direction, and obtaining a second-order transfer function; respectively establishing a time domain model and a complex frequency domain model, and performing simulation verification on convergence under single disturbance and multi-disturbance; by adjusting the disturbance quantity value, the action time and the included angle between the circle center connecting line of the two intersecting circles and the horizontal direction, the steps are repeated to predict convergence under different conditions. According to the method, efficient and accurate convergence judgment can be provided for the field of layout optimization for different types of round (ball) objects, the utilization rate of raw materials is maximized, and waste materials are reduced. And the problem of layout divergence caused by unstable object movement is avoided.

Certain aspects of the present disclosure provide techniques and apparatus for accurately predicting the movement and location of objects in a multidimensional space. An example method generally includes receiving an input defining a location of an object in a three-dimensional space at a first time. The input generally includes a plurality of tokens. Using a transformer neural network, a predicted movement for tokens in the plurality of tokens is generated. Generally, the predicted movement includes a translation and a rotation associated with individual tokens in the plurality of tokens. The predicted movement is translated into an object-wise predicted movement. Based on the object-wise predicted movement and the location of the object in the three-dimensional space, a predicted location of the object at a second time subsequent to the first time is output.