15 results about "Global transformation" patented technology

The invention provides a casting deformation compensation method based on point cloud, and belongs to the crossing field of three-dimensional digital detection and precision casting technology, and the method comprises the steps: carrying out the Gaussian filtering and edge point detection of a casting point cloud, sampling an edge point detection result to obtain a source point cloud, registering the source point cloud to a template point cloud coordinate system of a casting through ICP registration, and obtaining a point cloud coordinate system of the casting; obtaining an initial registration point cloud; respectively acquiring a registration feature point set and a template feature point set of the initial registration point cloud and the template point cloud by using SIFT, acquiring a rough matching pair set according to the feature point distance, and performing robust matching on the rough matching pair set to obtain a fine registration point cloud; performing deformation compensation on the fine registration point cloud based on local affine transformation and multi-scale deformation mapping to obtain a final registration point cloud; dividing the final registration point cloud into a rigid layer point cloud and a non-rigid layer point cloud; and transforming the final registration point cloud by using the global transformation matrix to obtain a compensation point cloud. The deformation compensation precision and efficiency of the casting can be effectively improved.

The invention relates to a three-dimensional point cloud registration method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring source point cloud data and target point cloud data; identifying the source point cloud data and the target point cloud data, and determining a target reference point; performing hierarchical clustering on the target reference points to obtain a reference point cluster; determining a global transformation matrix according to the first reference point cluster of the source point cloud data and the second reference point cluster of the target point cloud data; wherein the global transformation matrix represents a pose transformation relationship between the source point cloud data and the target point cloud data; and iterating the source point cloud data and the target point cloud data according to the global transformation matrix in combination with ICP fine registration until point cloud registration is completed. Thus, by extracting the target reference points and performing hierarchical clustering to obtain the reference point clusters, key local units with global structure significance can be extracted from the disordered point cloud, and compared with a traditional point-by-point matching point cloud registration method, redundant calculation and local structure misjudgment can be reduced.

The invention provides an animation production method and device, electronic equipment and a storage medium, and relates to the technical field of computers. The method comprises the steps that a skeleton hierarchy is constructed, the skeleton hierarchy comprises a main skeleton and at least one auxiliary skeleton, the main skeleton is a parent skeleton of the auxiliary skeletons, and global transformation parameters of the auxiliary skeletons in a world coordinate system are obtained; the skeleton can be formed by superposing global transformation parameters of the main skeleton in a world coordinate system and local transformation parameters of the auxiliary skeleton relative to the auxiliary skeleton in the world coordinate system; the preset 2D graphic element is bound to the auxiliary skeleton, and the target animation is generated according to the auxiliary skeleton and the preset basic animation, so that differential motion control based on the hierarchical skeleton is realized, the physical motion law of the real world is simulated, the motion freedom degree of the preset 2D graphic element in the target animation can be improved, and the user experience is improved. Diversity of motion trails is achieved, manufacturing efficiency can be improved, and manufacturing complexity can be reduced.

Some embodiments of a method can include obtaining a point cloud, which can include a first set of information describing geometry of the point cloud and a second set of information describing attributes of the point cloud; performing geometry encoding of the first set of information to generate a geometry bitstream; performing a two-stage attribute compression process to generate an attribute bitstream, wherein a first stage of the two-stage attribute compression process includes performing a block transform on each node of a set of nodes of the point cloud, and wherein a second stage of the two-stage attribute compression process includes performing hierarchical encoding on the set of nodes of the point cloud, and outputting an output bitstream including the geometry bitstream and the attribute bitstream.

The present invention provides modified sophorolipids that can eliminate existing foam and / or prevent the formation of new foam. The modifications including peracetylation and / or global transformation of sophorose hydroxyl groups of sophorolipids to ethers to reduce the HLB value and create biobased defoamers with high biobased carbon content. The present invention also provides compositions comprising modified sophorolipids and methods of using such compositions for inhibiting and / or reducing foam formation.

The invention belongs to the technical field of blade three-dimensional reconstruction, and particularly relates to a coarse-to-fine aero-engine blade three-dimensional reconstruction method based on overlap region guidance, which comprises the following steps: S100, performing coarse registration; the method comprises the following steps: acquiring three groups of point cloud data under different fields of view, performing down-sampling on the point cloud data of multiple fields of view by using Kpconv, extracting geometric features in the fields of view in combination with a geometric self-attention mechanism, capturing geometric consistency features among the fields of view through a cross attention mechanism, predicting the confidence coefficient of an overlapping region, predicting a global transformation vector by using a multi-layer perceptron, and extracting the point cloud data of multiple fields of view by using a multi-layer perceptron. Preliminary alignment of the multi-view cloud is completed; s200, carrying out fine registration; on the basis of a coarse registration result, local features are mined by using an overlapping attention mechanism, weighted fusion is performed on the features in combination with overlapping scores, and transformation vectors are gradually optimized in combination with a weighted loop updating strategy. According to the method, high-precision reconstruction of the three-dimensional morphology of the blade is realized through overlapped region guided feature enhancement and multi-view joint optimization.

The invention provides a cross-coordinate system road network data fusion method based on hierarchical matching and non-rigid registration, belongs to the technical field of road networks, and solves the problems that an existing method is complex in calculation and poor in universality. The method comprises the following steps: acquiring reference and target road network data and preprocessing; estimating a global transformation relation by calibrating feature points, and preliminarily aligning the reference road network to a target coordinate system to obtain an overall area; constructing a fixed image of the target road network and a moving image of the reference road network in the whole area; carrying out non-rigid registration on the fixed image and the moving image by adopting a modeling local nonlinear deformation algorithm such as free deformation of a B spline, and optimizing a cost function to obtain a pixel-level deformation field; and performing geometric correction on the reference road network based on the deformation field, transmitting attribute information of the target road network, and summarizing and outputting a fusion data set. According to the method, through a layering strategy and pixel-level registration, the local matching precision and universality are improved, and the influence of road segment segmentation differences is overcome.

The application discloses a kind of based on global transformation prototype network's small sample relation classification method and device, belong to natural language processing technical field.The method mainly includes: (one) based on pre-training language model and entity mark's relation instance representation extraction mechanism;(two) based on global transformation prototype network of relation instance representation;(three) based on the global prototype representation obtained by the above network, the small sample relation classification method of being carried out.The pre-training language model and entity mark's relation instance representation extraction mechanism of the application can be fully encoded to the entity pair and relevant context included in relation instance;Based on global transformation's prototype network can be fully obtained by support set Global feature of new task, based on this, new relation prototype representation is transformed, so that better domain generalization is carried out.

The present invention provides a method for compensating casting deformation based on a point cloud, which lies at the intersection of three-dimensional digital inspection and precision casting technology. The method comprises performing Gaussian filtering and edge point detection on the casting point cloud, sampling the edge point detection results, obtaining a source point cloud, registering the source point cloud to the casting template point cloud coordinate system using ICP registration, and obtaining an initial registered point cloud. SIFT is used to obtain a set of registration feature points and a set of template feature points for the initial registered point cloud and the template point cloud, respectively. A set of coarse matching pairs is obtained based on feature point distances, and robust matching is performed on the coarse matching pairs to obtain a fine registered point cloud. Deformation compensation is performed on the fine registered point cloud based on local affine transformation and multi-scale deformation mapping to obtain a final registered point cloud. The final registered point cloud is divided into a rigid layer point cloud and a non-rigid layer point cloud. Finally, a global transformation matrix is used to transform the final registered point cloud to obtain a compensated point cloud. The present invention can effectively improve the accuracy and efficiency of deformation compensation for castings.

The application discloses a kind of man-machine cooperation formula multi-dimensional multi-mode industrial robot precision measurement method and device, it is related to precision measurement technical field, comprising: through ant colony-genetic hybrid optimization admittance control algorithm based on six-dimensional force data output target admittance control parameter, initial starting waypoint pose and initial endpoint waypoint pose are determined in combination with dichotomy iterative optimization strategy;Adaptive registration algorithm based on the angle constraint of double straight line is used to correct waypoint pose, and target starting waypoint pose and target endpoint waypoint pose are determined;According to target admittance control parameter, target starting waypoint pose and target endpoint waypoint pose, the measured workpiece is measured, and segmented weighted ICP registration algorithm is used to determine global transformation matrix, when it is judged that waypoint pose needs to be optimized, transformation is not executed waypoint pose to update target starting waypoint pose or / and target endpoint waypoint pose, until the workpiece measurement result is determined.The reliability of industrial robot precision measurement is improved based on the above scheme.

The present invention belongs to the technical field of three-dimensional reconstruction of blades, and particularly relates to a coarse-to-fine three-dimensional reconstruction method of aero-engine blades guided by an overlapping area, including S100: Coarse registration; obtaining three groups of point cloud data under different fields of view, using Kpconv to downsample the point cloud data of multiple fields of view, extracting geometric features within the field of view by combining a geometric self-attention mechanism, capturing geometric consistency features between fields of view through a cross-attention mechanism, predicting the confidence of the overlapping area, and using a multi-layer perceptron to predict the global transformation vector to complete the preliminary alignment of multi-view point clouds; S200: Fine registration; based on the coarse registration result, using an overlapping attention mechanism to mine local features, combining the overlapping score to perform weighted fusion of the features, and gradually optimizing the transformation vector in combination with a weighted cyclic update strategy. The present invention realizes the high-precision reconstruction of the three-dimensional morphology of the blade through feature enhancement guided by the overlapping area and multi-view joint optimization.

The invention discloses a laser cladding repairing method based on point cloud local three-dimensional reconstruction, and belongs to the technical field of laser cladding. A global reference model of the workpiece to be repaired is obtained, and space alignment is completed; collecting local point cloud data of a to-be-restored area, and preprocessing to obtain processed local point cloud; performing hierarchical registration on the processed local point cloud and the global reference model to generate an adaptive registration transformation matrix; establishing a pose map based on the registration transformation matrix, and generating a global transformation chain; according to the global transformation chain, the local point cloud after fusion processing and the global reference model, constructing a global fusion model containing defect features; and performing semantic recognition and boundary segmentation on the global fusion model, and generating a local defect model with a topological relation in combination with deep learning and a region growing algorithm. According to the method, the consistency of local repair and the overall shape of the workpiece is ensured through the global reference model, the problem that traditional local reconstruction only pays attention to the local part and is separated from the global part is solved, and the data processing efficiency and the repair precision are both considered.

The invention provides a three-dimensional model registration method, device and equipment, a medium and a product, and relates to the technical field of three-dimensional model registration. The method comprises the following steps: performing feature extraction on a source three-dimensional model to obtain a plurality of first feature points with spatial invariance and a plurality of second feature points of a target three-dimensional model, determining a plurality of groups of corresponding anchor points between the source three-dimensional model and the target three-dimensional model, and obtaining a plurality of local transformation matrixes; and respectively inputting the plurality of first feature points into a plurality of local transformation matrixes, calculating the overlapping rates of the obtained output points and the corresponding second feature points in the plurality of groups of corresponding anchor points, determining the local transformation matrix with the highest overlapping rate as a global transformation matrix, applying the global transformation matrix to the source three-dimensional model, and obtaining a registration result. The robustness of rotation attacks, translation attacks and scaling attacks is obviously superior through the method of local registration and global registration, detail features are focused, global features are also considered, and the robustness of registration is greatly improved.

The invention relates to a refined face correction method and system based on key point expansion and Delaunay triangulation, and belongs to the technical field of computer vision and image processing. According to the method, a deep learning model is not needed, based on facial features, five basic key points are expanded to a specified number of detailed key points, different generation methods are adopted for eyes, a mouth and a facial contour, the accuracy of key point distribution is ensured, facial feature parameters are automatically calculated according to the five input basic key points, self-adaptive expansion is achieved, and the method is suitable for large-scale popularization and application. Delaunay triangulation is used for dividing a human face into a plurality of small triangular areas, local affine transformation is carried out, and deformation caused by global transformation is avoided.

This invention relates to the field of electronic technology and discloses a method, apparatus, equipment, and medium for deformation inspection of compressed air energy storage chambers. The method includes: acquiring regional point cloud data of multiple key areas in a target chamber and the theoretical positions of monitoring points in each key area, wherein each key area contains multiple monitoring points and the setting method of the monitoring points is different in different key areas; determining the local point cloud data of the corresponding monitoring point in the regional point cloud data with the theoretical position of each monitoring point as the center and the target value as the radius; determining the centroid position based on the local point cloud data of each monitoring point; calculating a global transformation matrix based on the centroid position and theoretical position of each monitoring point; calibrating the local point cloud data of each key area based on the global transformation matrix to obtain the calibrated absolute position of each monitoring point; and determining the deformation inspection result of the corresponding key area based on the absolute positions of multiple monitoring points in each key area and the pre-acquired historical inspection positions.