54 results about "Reference space" patented technology

The invention relates to a three-dimensional grid model processing method, computer equipment, a readable storage medium and a program product. The method comprises the steps of performing voxelization on a three-dimensional grid model of a target object to obtain a plurality of voxels corresponding to the target object in a preset reference space; determining the visibility value of the voxel according to the projection information of the voxel under the preset camera visual angle; determining a position relation label of the voxel relative to a reference point according to a communication relation between the voxel and the reference point in a preset reference space; screening out a target voxel from the voxels according to the visibility values and the position relation labels of the voxels; and determining model characterization parameters of the three-dimensional grid model according to the spatial information of the target voxel in the three-dimensional grid model. By adopting the method, the generation precision of the three-dimensional model can be improved.

This invention relates to the field of optical element manufacturing technology, and more particularly to a form and position reference component and a method for manufacturing a multifaceted optical element. The method includes: providing a blank and a form and position reference component; the blank including a connected positioning part and a main body part; determining the target coordinates of the target multifaceted optical element in a reference spatial coordinate system; placing the positioning part in a positioning groove to fix the blank on a base; determining the basic coordinates of the blank in the reference spatial coordinate system; determining the machining allowance based on the difference between the basic coordinates and the target coordinates; machining the blank based on the machining allowance to obtain an initial multifaceted optical element; using a target sphere as a detection reference, sequentially detecting the relative positions and surface shape errors of multiple faces of the initial multifaceted optical element, and iteratively processing until the multifaceted optical element is obtained. This invention at least helps to reduce the manufacturing difficulty of multifaceted optical elements.

The application relates to the technical field of building information model construction, in particular to a parameterized modeling method of a fabricated shear wall BIM structure. The method obtains actual spatial positions, actual stresses, bottom areas, reference spatial positions and reference stresses of the fabricated shear wall; according to the included angle between each fabricated shear wall and its adjacent fabricated shear wall in each construction layer, the difference between the actual stresses and the reference stresses of the adjacent fabricated shear wall, the difference between the actual spatial positions and the reference spatial positions of the adjacent fabricated shear wall and the bottom area of the fabricated shear wall, the layer internal error degree of the construction layer is obtained; according to the layer internal error degree of each construction layer and the difference between the layer internal error degree of the lower construction layer and the layer internal error degree of the lowest construction layer, the comprehensive error degree of the construction layer is obtained to mark the high-risk construction layer. The application accurately marks the high-risk construction layer, realizes accurate identification and visualization of construction errors, and is beneficial to timely management and control of the construction errors.

According to the present invention, a spatial mesh acquired by using a spatial recognition unit of smart glasses to scan a space including a target location in a normal state is pre-registered as a reference spatial mesh. Furthermore, two-dimensional image data of a flat surface in a normal state are pre-registered as reference image data. During abnormality detection, a worker wearing the smart glasses enters a work area and performs a scan to acquire a target spatial mesh. If the target spatial mesh satisfies a detection condition, the target spatial mesh is compared with the reference spatial mesh. Meanwhile, if the target spatial mesh does not satisfy the detection condition, the target spatial mesh is converted into a two-dimensional image to acquire target image data, and the target image data are compared with the reference image data.

Systems and methods for performing document entity extraction are described herein. The method can include receiving an inference document and a target schema. The method can also include generating one or more document inputs from the inference document and one or more schema inputs from the target schema. The method can further include, for each combination of the document input and schema input, obtaining one or more extraction inputs by generating a respective extraction input based on the combination, providing the respective extraction input to the machine-learned model, and receiving a respective output of the machine-learned model based on the respective extraction. The method can also include validating the extracted entity data based on reference spatial locations and inference spatial locations and outputting the validated extracted entity data.

The application is suitable for the field of data processing, and provides a passing path planning method and system, an electronic device and a computer program product, wherein the method comprises: acquiring a space reference space-time network; the space reference space-time network comprises a plurality of space-time edges, each space-time edge connects two waypoints and corresponds to a space-time range between the waypoints; determining at least one target space-time range corresponding to a space emergency event and passing restriction information corresponding to each target space-time range; adjusting a target space-time edge corresponding to the target space-time range in the space reference space-time network based on the target space-time range and the passing restriction information, to obtain a space passable space-time network; and planning a target passing path for each target flight task in the space passable space-time network. The scheme performs fine management on the space, replans the path for the target flight task, and improves the utilization rate of the space resource.

The application discloses a kind of virtual-real superposition precision test method, system and storage medium, it is related to wearable technology field.The method comprises the following steps: controlling the head-mounted display device to be measured to be in different test poses in turn;Get the first image pair obtained by the image of the display picture and the calibration plate of the double-camera acquisition head-mounted display device to be measured in test pose, according to the first space position of the real mark in the virtual-real pair in the first image in the camera coordinate system and the reference virtual-real relative pose corresponding to the virtual-real pair, determine the reference space position of the virtual mark in the virtual-real pair in the camera coordinate system, according to the second space position and reference space position of the virtual mark in the virtual-real pair in the camera coordinate system, determine the virtual-real superposition precision test result corresponding to the camera of the head-mounted display device to be measured in test pose;According to the virtual-real superposition precision test result of the double-camera of the head-mounted display device to be measured in different test poses, determine the virtual-real superposition precision test result of the head-mounted display device to be measured.

The application provides a video blind area compensation transmission method and server based on dynamic field of view fusion, through acquiring multi-source video stream data, integrating all field of view regions under the same timestamp to a unified global reference space to obtain a global field of view splicing layout, constructing a dynamic field of view topology evolution graph containing a blind area hole outline and a pixel mapping transformation relationship between fields of view according to layout changes of continuous timestamps; performing pixel-by-pixel spatial migration on adjacent field of view video frames according to the pixel mapping transformation relationship of the blind area hole periphery to generate a blind area compensation video segment; performing panorama fusion on the compensation segment and the original video segment to obtain a panoramic video stream; analyzing the distribution pattern of the original collection source and the content remapping source in the panoramic video stream to generate a spatial mask, setting a differentiated encoding transmission strategy for different regions and encoding and distributing. The application realizes high-quality compensation of blind area content and regional differentiated efficient transmission of panoramic video streams.

The invention discloses a self-adaptive writing method and system based on support style feature extraction and template generation, and particularly relates to the technical field of self-adaptive writing. According to the method, the writing system has the active recognition and selection capability on the target style in the generation process, style drifting caused by context accumulation in long text and multi-round generation is avoided, meanwhile, a fixed semantic structure and a variable expression mode are combined based on a template constraint model automatically generated in a dominant style interval, and the method is more efficient and efficient. On the premise of ensuring logic integrity and expression normalization, the flexibility and adaptability of the writing process are improved, and a closed-loop self-adaptive regulation and control mechanism is formed by performing literary and physical feature consistency evaluation on the generated text and dynamically adjusting the template slot position weight.

The embodiment of the application provides a kind of spaceborne opportunistic communication window parameter prediction method, electronic equipment, storage medium and program product, related to wireless communication technical field, the method comprises: obtaining the orbital parameter information of multiple available satellites, and the spaceborne metasurface is deployed in available satellite;For each available satellite, according to the orbital parameter information, the orbital state information of available satellite in preset time range is calculated;For each available satellite, determine the available satellite that meets the preset discrimination criterion as candidate satellite by screening, and the preset discrimination criterion is that in preset time range, the subsatellite point position of available satellite is located in mirror surface reflection search area;For each candidate satellite, the reference spatial point corresponding to candidate satellite is used as the pointing target of transmitting station and receiving station, and the beam intersection region of transmitting station and receiving station is calculated;For each candidate satellite, based on the beam intersection region corresponding to candidate satellite, the communication window parameter is predicted, and the precision of passive reflection communication window prediction is improved.

A user equipment (UE) configured for operating in a wireless communication network that supports a plurality of reference signals (RS) such as sounding reference signals, comprises a wireless interface configured for transceiving signals, comprising receiving a configuration signal having a configuration information indicating a reference spatial relation. The UE further comprises a controller for evaluating the configuration information and to determine the reference spatial relation. The UE is configured for using the reference spatial relation as a reference for an uplink RS (UL-RS) in the wireless communication network.

To improve diagnostic accuracy of an elevator.SOLUTION: A diagnostic apparatus creates a reference space for each elevator, compares multidimensional feature quantity data generated from sound-vibration waveform data acquired for the elevator with a reference space prepared for the elevator among reference spaces prepared for respective elevators, and performs diagnosis regarding an abnormality of the elevator on the basis of the result of the comparison.SELECTED DRAWING: Figure 1

The invention is suitable for the field of data processing, and provides a passage path planning method and system, electronic equipment and a computer program product, and the method comprises the steps: obtaining an airspace reference space-time network; the airspace reference space-time network comprises a plurality of space-time edges, and each space-time edge is connected with two waypoints and corresponds to a space-time range between the waypoints; determining at least one target space-time range corresponding to the airspace emergency and traffic restriction information corresponding to each target space-time range; based on the target space-time range and the passing restriction information, adjusting a target space-time edge corresponding to the target space-time range in the airspace reference space-time network to obtain an airspace passable space-time network; and in the airspace passable space-time network, planning a target passage path for each target flight mission. According to the scheme, fine management is carried out on the airspace, the path is re-planned for the target flight task, and the airspace resource utilization rate is improved.

The embodiment of the present application provides an imaging method and system. The imaging method comprises the following steps: using pseudo-thermal light as probe light, and irradiating the probe light to a moving object to form reflected light; receiving the reflected light by using a single-pixel detector, and determining a Doppler frequency shift distribution of the reflected light relative to the probe light by using a frequency analysis system; obtaining a velocity sequence of the moving object based on the Doppler frequency shift distribution of the reflected light relative to the probe light; and constructing a full-view velocity image and a spatial image of the moving object by using a pre-stored reference spatial thermal light field distribution and the velocity sequence based on a correlation imaging algorithm, wherein the spatial image corresponds to a reflectivity distribution of the moving object, the direction of the velocity of the moving object is perpendicular to the plane where the collection surface of the single-pixel detector is located, and the velocity sequence corresponds to the pre-stored reference spatial thermal light field distribution.

To provide a work support method and a work support system that enable a worker to recognize a change in a surrounding situation even in a dark environment.SOLUTION: A space mesh acquired by scanning a space including a target place in a normal state by a space recognition unit of smart glasses is registered in advance as a reference space mesh. The two-dimension image of the flat surface in the normal state is registered in advance as a reference image. When an abnormality is detected, a worker wearing smart glasses enters the work area 101 and acquires a target spatial mesh by scanning. When the target spatial mesh satisfies the detection condition, the target spatial mesh is compared with the reference spatial mesh. On the other hand, when the target spatial mesh does not satisfy the detection condition, the target spatial mesh is converted into a two-dimension image to acquire a target image, and the target image is compared with the reference image.SELECTED DRAWING: Figure 15

The invention relates to the technical field of building information model construction, in particular to a parametric modeling method for a fabricated shear wall BIM structure. The method comprises the steps that the actual space position, the actual stress, the bottom area, the reference space position and the reference stress of the fabricated shear wall are obtained; according to the included angle between each assembly type shear wall and the adjacent assembly type shear wall in each construction layer, the difference between the actual stress and the reference stress of the adjacent assembly type shear wall, the difference between the actual spatial position and the reference spatial position of the adjacent assembly type shear wall and the bottom area of the adjacent assembly type shear wall, the intra-layer error degree of the construction layer is obtained; according to the in-layer error degree of each construction layer, the in-layer error degree difference between the construction layer and the lower construction layer and the in-layer error degree difference between the construction layer and the lowest construction layer, the comprehensive error degree of the construction layers is obtained to mark the high-risk construction layer. By accurately marking the high-risk construction layer, accurate recognition and visualization of the construction error are realized, and timely management and control of the construction error are facilitated.

The invention relates to a hand-object interaction three-dimensional reconstruction method, computer equipment and a program product. Comprising the steps of obtaining a target video sequence and equipment attitude parameters; establishing a mapping relation between the two-dimensional coordinate system and the target three-dimensional coordinate system; mapping a plurality of pixel points included in each of the plurality of video frames to a target three-dimensional coordinate system according to the mapping relationship to obtain a plurality of target three-dimensional sampling points; respectively mapping the plurality of target three-dimensional sampling points into a hand reference space and an object reference space to obtain a plurality of hand target three-dimensional sampling points and a plurality of object target three-dimensional sampling points; performing field attribute fusion rendering processing on the plurality of hand target three-dimensional sampling points and the plurality of object target three-dimensional sampling points to obtain a three-dimensional reconstruction video frame; and arranging the three-dimensional reconstructed video frames to generate a three-dimensional reconstructed video sequence. Therefore, the data of the visible area can be complemented according to the structural adaptation rule of the hand and the object, and the hand and the object can still be accurately restored under the shielding scene.

The invention provides a data processing method and device. The data processing method comprises the following steps: acquiring target direct sound corresponding to a target object and current space attribute information; determining at least one target reference space based on the current space attribute information, and determining a target audio modulation parameter corresponding to each target reference space; based on each target audio modulation parameter, adjusting a target reference reverberation audio corresponding to each target reference space to obtain a target modulation reverberation audio; and generating a target reverberation audio corresponding to the target object based on the target direct sound and the target modulation reverberation audio. According to the invention, the generation efficiency and authenticity of the target reverberation audio are improved.

This invention discloses a robot control method, device, storage medium, and electronic device. The method includes: acquiring a reference pose record of a vision camera on the robot, wherein the reference pose record includes reference coordinate values ​​of the vision camera in a vision calibration board coordinate system and a reference spatial pose of the vision camera in a base coordinate system; acquiring a current pose record of the vision camera, wherein the current pose record includes the current coordinate values ​​of the vision camera in the vision calibration board coordinate system and the current spatial pose of the vision camera in the base coordinate system; if the error between the reference pose record and the current pose record is greater than a first error threshold, controlling the robot to move in the direction of decreasing error until the error is less than or equal to a second error threshold, and resetting the robot's zero position based on the reference spatial pose. This invention solves the technical problems of reduced accuracy and complex recovery processes after robot zero position loss in related technologies.

The invention relates to an arbitrary magnification image super-resolution reconstruction method and device based on double cameras. The method comprises the following steps: acquiring a to-be-processed image and a reference image; determining the scale of the target resolution image based on the target magnification, and generating a target resolution coordinate set corresponding to the scale; and on the basis of the target resolution coordinate set, a preset super-resolution model is utilized to perform query operation and reconstruction operation on the to-be-processed image and the reference image to generate a target resolution image, and the preset super-resolution model comprises a space reference space, a luminosity reference space and a texture reference space. Therefore, the mixed reference space model containing the space reference space, the luminosity reference space and the texture reference space is constructed and utilized to carry out parallel query and reconstruction on the image features in different levels of reference spaces; the problems of poor generalization ability and luminosity distortion or texture blurring of the reconstructed image caused by fixed amplification factor and single alignment space in the prior art are solved.

The application discloses a port safety monitoring edge computing task unloading scheduling method based on deep learning, relates to the technical field of port safety monitoring, and comprises the following steps: performing deep learning inference on a port safety monitoring video to extract abnormal behavior semantic features, quantifying a task processing process to extract task data scale features, and respectively constructing semantic risk potential energy values and load scale potential energy values based on the abnormal behavior semantic features and the task data scale features; constructing a potential energy confrontation domain based on the direction difference of the semantic risk potential energy values and the load scale potential energy values in a unified reference space, and judging whether the abnormal behavior semantic features and the task data scale features conflict according to the potential energy confrontation domain. The application solves the problem that the scheduling emphasis direction cannot be adjusted based on the semantic risk and the task scale conflict intensity, and realizes the effects of high-risk task priority response and dynamic optimization of a scheduling strategy.

The application relates to the technical field of hardware equipment quality tracing, and discloses a hardware full-life-cycle quality tracing method and system based on IoT, which comprises the following steps: acquiring multi-dimensional real-time data flow and arranging the same into a real-time running data set; extracting distribution characteristics based on a historical data archive to obtain a benchmark reference space; projecting the real-time data to calculate a deviation quantitative value, correcting environmental deviation when the deviation quantitative value exceeds a threshold value to obtain a deviation result; extracting degradation characteristics to match historical trajectories to locate a degradation process; performing time sequence analysis to predict residual life to obtain a failure time window; and generating and arranging maintenance intervention instructions into a scheduling instruction set. The method realizes hardware full-life-cycle quality tracing and early abnormality early warning, improves maintenance accuracy, and reduces fault loss.

The invention is suitable for the technical field of intelligent terminals, and provides a pose estimation method and device of a space interaction device, a terminal device and a storage medium, the method comprises the following steps: obtaining a current frame image of the space interaction device collected by a three-dimensional imaging device, the space interaction device being provided with at least two mark points; identifying visible states of all mark points in the current frame image; acquiring inertial measurement data output by an inertial sensor in the space interaction equipment; according to the visible states of all the mark points, the inertial measurement data and reference space coordinates, a pose estimation result of the space interaction equipment is generated, and the reference space coordinates are determined based on historical frame images. According to the method, the robustness of space interaction pose estimation can be improved, and the interaction continuity and precision of space interaction equipment in a complex scene can be guaranteed.

Systems and methods for performing document entity extraction are described herein. The method can include receiving an inference document and a target schema. The method can also include generating one or more document inputs from the inference document and one or more schema inputs from the target schema. The method can further include, for each combination of the document input and schema input, obtaining one or more extraction inputs by generating a respective extraction input based on the combination, providing the respective extraction input to the machine-learned model, and receiving a respective output of the machine-learned model based on the respective extraction. The method can also include validating the extracted entity data based on reference spatial locations and inference spatial locations and outputting the validated extracted entity data.

This application provides a method, device, equipment, and medium for 360° high-precision docking guidance of unmanned vehicles based on surround-view vision. The method includes: acquiring a multi-channel surround-view image sequence and a target docking reference space map; performing distortion correction processing according to the inverse perspective spatial transformation relationship set determined by camera intrinsic and extrinsic parameters, and projecting it into a three-dimensional world coordinate system to generate a panoramic surround-view bird's-eye view feature tensor; performing feature matching processing based on spatial geometric alignment conditions to extract a multi-dimensional spatial offset vector set; and converting the multi-dimensional spatial offset vector set into dynamic docking control commands based on kinematic constraint parameters to control the unmanned vehicle chassis execution unit to perform docking guidance operations. This application, by combining panoramic surround-view feature reconstruction with kinematic constraints, alleviates the defects of local perception blind spots, significantly improving the pose alignment accuracy and control smoothness of unmanned vehicle docking.

The invention discloses a high-steep dangerous rock monitoring method and system based on instability scale calculation, and relates to the technical field of data processing, and the method comprises the steps: obtaining a target rock mass region, obtaining rock surface monitoring nodes and target region fixed nodes, obtaining standard coordinates, and constructing a reference space coordinate sequence and a to-be-processed space coordinate sequence; acquiring an equipment displacement compensation sequence according to the reference space coordinate sequence and the standard coordinates of the target region nodes, and correcting the to-be-processed space coordinate sequence according to the equipment displacement compensation sequence to generate a target space coordinate sequence; acquiring displacement trend parameters of the rock table monitoring nodes according to the target space coordinate sequences of the rock table monitoring nodes, and acquiring typical danger indexes of the target rock mass area according to the displacement trend parameters of the rock table monitoring nodes; and obtaining a monitoring and early warning strategy according to the typical danger index. The method has the advantages of high reliability and accurate regional statistics and monitoring results.

The invention provides a diagnosis device and a diagnosis method of an elevator, and the diagnosis precision of the elevator is improved. A diagnostic device generates a reference space for each elevator. When the elevator is diagnosed, the diagnostic device compares multi-dimensional feature quantity data generated from sound / vibration waveform data acquired for the elevator with a reference space prepared for the elevator among reference spaces prepared for each elevator, and determines whether the elevator is diagnosed on the basis of the result of the comparison. Diagnosis related to abnormality of the elevator is performed.

The invention provides a positioning precision detection system and a positioning precision detection method, which can detect the positioning precision of a surgical robot in real time. The positioning precision detection system (1) comprises an adapter phantom (3), a plurality of detection probes (4), a test tool body (2) and a control device (5), before a simulated operation is carried out, medical three-dimensional image data of the adapter phantom are obtained, an operation plan is made, the adapter phantom is installed on the test tool body and is registered with the medical three-dimensional image data, and the detection probes (4) are used for detecting the positioning precision of the test tool body (2). When the simulation operation is carried out, the adaptive phantom is detached from the testing tool body, the surgical robot carries out the simulation operation in the space through the surgical instrument according to the surgical planning, and the reference spatial position is the spatial position obtained by converting the spatial position, specified in the surgical planning, of the surgical instrument after registration.

The application discloses an abnormality detection method and system based on normal sample reference, relates to the technical field of image processing pattern recognition, and takes a normal state support image as a reference, obtains query features and reference features through a double-branch feature extraction network, obtains reference space mixed features and reference prototype features through reference feature aggregation, realizes semantic information interaction through bidirectional attention feature fusion, and accurately locates a target region.Secondly, secondary feature extraction and fusion are performed on a target image, difference features are constructed by combining target fusion features and reference space mixed features, and an abnormality region is located through an abnormality detector.The application adopts a cascading strategy of positioning first and then detecting, runs through the whole process with normal reference information, effectively suppresses background interference and error accumulation, has the advantages of accurate positioning, strong robustness, adaptation to multiple types of abnormalities and the like, and has high engineering application value.

The application discloses a method for eliminating the clumps on the inner wall of a coal transport vehicle carriage, comprising the following steps: positioning the coal transport vehicle to a preset working position, so that the carriage to be cleaned keeps a standard position; scanning the inner wall of the carriage in the standard position, and obtaining a first space coordinate set of the calibrated actual space position; comparing the first space coordinate set with a pre-stored reference space coordinate set, and identifying a difference coordinate set, wherein the reference space coordinate set calibrates the space position of the inner wall of the carriage in the standard position in a clump-free state, and the difference coordinate set calibrates the actual space position of the clumps; and positioning the clumps on the inner wall of the carriage according to the difference coordinate set. The application can be adapted to railway vehicles and road transport vehicles, and greatly improves the coal transportation efficiency and economy.