267 results about "Height map" patented technology

The invention discloses a quadruped robot motion control method based on topographic map reinforcement learning. The quadruped robot motion control method comprises the following steps: S1, building a quadruped robot model; s2, constructing a topographic map confidence estimation model; s3, constructing a state estimation model; s4, constructing an actor network and a commentator network to train the quadruped robot model; and S5, acquiring data of the laser radar and the inertial measurement unit by using a sensor fusion technology, generating a height map around the quadruped robot in real time, and updating environmental terrain information. By introducing the topographic map confidence estimation model and combining topographic map generation and topographic uncertainty estimation, the motion strategy of the quadruped robot in a complex terrain can be adjusted in real time, the adaptability of the robot to irregular terrains, obstacles and topographic changes is remarkably improved, and the reliability of the quadruped robot is improved. And control errors and falling risks caused by topographic changes or sensor noise are reduced.

The invention relates to the technical field of image data processing, in particular to an urban building three-dimensional reconstruction method and device, and the method comprises the steps: obtaining a multi-view satellite orthoimage from the same scene, satellite-borne laser height measurement data of a target region, a digital terrain model and two-dimensional building vector data; performing accurate geometric registration on the multi-view satellite orthoimage, and executing dense matching to generate an initial parallax point cloud; and combining azimuth angle information of the multi-view orthoimage to construct a disparity map with accurate plane positioning. And calculating an elevation value above the earth surface by using satellite-borne laser altimetry data and a digital terrain model. And jointly estimating a parallax elevation proportionality coefficient by using the elevation value and the parallax value so as to convert the parallax map into a height map. And generating three-dimensional building vector data of the target area in combination with the two-dimensional building vector data. Therefore, the problems that cost based on surveying and mapping level remote sensing data is high, data collection is limited, and the requirement for global city three-dimensional reconstruction cannot be met in the prior art are solved.

The invention discloses an ultra-thin glass defect detection system and positioning method based on line scanning and phase deflection, and the system comprises a line scanning camera module, a distortionless phase deflection detection module, a high-magnification microscope module and a central processing unit. The line scanning camera module is used for collecting a 2D grayscale image of the ultrathin glass; the distortionless phase deflection technology detection module is used for collecting a surface height map of the ultra-thin glass; the high-magnification microscope module is used for carrying out depth positioning on the interlayer defect judged by the central processing unit; the central processing unit is used for receiving the 2D gray level image and the surface height map, executing an image registration and defect classification algorithm and sending a depth positioning control instruction to the high-magnification microscope module, a multi-module cooperative work detection system is constructed, the detection efficiency and the detection precision are both considered, and data support is provided for production process improvement.

The invention discloses a machine vision-based enzyme freeze-dried powder quality detection method, and belongs to the technical field of machine vision, and the method specifically comprises the following steps: in a closed optical cavity, synchronously collecting a multispectral polarization sequence of a sample through annular multispectral polarization illumination and microscopic imaging; performing short-time airflow pulse disturbance and continuous imaging on the sample, and constructing a polarization time sequence texture map by means of inter-frame polarization retention difference; according to Stokes parameters, calculating a deskewness graph and a specular reflection component graph, and carrying out joint normalization on the deskewness graph and the specular reflection component graph and the polarization time sequence texture graph to form a multi-channel feature stack; constructing a double-branch encoder, and performing comparative learning on the feature stack to generate an impurity prototype dictionary; using the dictionary to match the feature stack pixel by pixel, and tracking and inhibiting powder agglomeration false detection through a topological constraint connected domain; and recovering a height map by using an oblique incidence fringe phase shift method, performing pixel-level fusion with the candidate image, retaining targets with height abrupt change and consistent polarization characteristics, and outputting an impurity mask.

The invention provides a battery cell appearance detection method and device based on multi-modal image fusion, and the method comprises the steps: obtaining a single-channel gray-scale map and a single-channel height map as input, carrying out the validity verification, generating a target fusion image through multi-modal fusion, and constructing a training set to train a deep learning model, and finally, accurate detection and result output of the appearance defects of the battery cell are realized. According to the invention, through combination of multi-modal image fusion and deep learning, the cell appearance detection precision and efficiency are significantly improved, and efficient and accurate intelligent quality control is realized.

The invention discloses a frequency height map O / X wave trace intelligent extraction method based on a deep neural network, and belongs to the technical field of space environment detection and artificial intelligence. The method comprises the following steps: performing time-frequency feature analysis and data enhancement on an original frequency height map, and constructing a high-quality training set by adopting an expert labeling mode; a double-path attention mechanism network model is innovatively proposed, multi-scale features are captured through a spatial pyramid module, and feature weight distribution is optimized in combination with channel attention; a joint optimization strategy of cross entropy loss and Dice loss is adopted to effectively process the class imbalance problem; and finally, an extraction result is optimized through morphological post-processing. According to the method, the distance deviation at different frequency points is reduced by more than 30% compared with a traditional method, the method has strong anti-noise capability and weak feature capture capability, the ionosphere parameter inversion precision can be improved, and reliable technical support is provided for the fields of space environment monitoring, short-wave communication guarantee and the like.

The invention provides a sweet menu embryo pelleting seed breakage rate detection method based on machine vision, and relates to the technical field of seed detection.The method comprises the steps that firstly, visible light and near-infrared images of seeds under standard illumination and non-standard visible light images under multiple light sources are collected, and reflectivity calibration and polarization difference correction processing are carried out; features such as colors and textures are extracted based on visible light and near-infrared reflectivity images, and multispectral feature vectors are constructed; a surface normal vector is calculated by using a photometric stereoscopic vision technology and combining a plurality of non-standard visible light images, an initial three-dimensional height map is generated through integration, and a plurality of abnormal judgment features are extracted to mark a suspected damaged area. And further calculating an edge sharpness index, removing a mechanical damage area, and determining a final damage area and a three-dimensional contour thereof. And finally, combining the volume loss rate, the projection area ratio and other multi-dimensional features with the multispectral feature vector to construct a damage probability prediction model, thereby realizing accurate and efficient detection of the seed damage rate.

The invention relates to a method for determining a surface map, such as a height map, of a sample surface having a first region and a second region, the first region having a first reflectance and the second region having a second reflectance. The invention also relates to an imaging system for determining a surface map of a sample surface having a first region and a second region, the first region having a first reflectance and the second region having a second reflectance. The invention also relates to a digital data carrier comprising a computer program which, when executed on a processor of an imaging system according to the invention, causes the imaging system to perform a method according to the invention.

The invention discloses a data processing method and device, electronic equipment and a readable storage medium, and the method comprises the steps: generating a target noise map of an initial map through employing a noise map generation function based on a first UV coordinate of the initial map; processing the target noise map by using a first periodic function to obtain first offset information; using the first offset information to disturb the first UV coordinate of the initial map to obtain a second UV coordinate of the initial map; sampling the target noise map based on the second UV coordinate to obtain a first height map; and generating a normal map based on the first height map. A normal map including height information is generated through the method so as to restore the flow effect of the material with the flow characteristic in the real world.

The invention belongs to the technical field of robot autonomous operation and reinforcement learning, and discloses an intelligent active perception and behavior interaction method in an unknown shielding scene. According to the method, a viewpoint planning strategy of an active sensing agent and a pushing strategy of a behavior interaction agent are closely fused, a 2.5 D occupancy height map is combined, and a pushing point screening mechanism of geometric features and task heuristic weights and a dense reward function are fused; the problems of insufficient perception information, low action efficiency and unstable strategy training in an unknown shielding environment are solved. According to the method, the pushing success rate, the environment entropy reduction efficiency and the strategy generalization ability are remarkably superior to those of a traditional method, efficient environment exploration can be achieved only through minimum invasive pushing of the scene, a good foundation is laid for tasks such as downstream grabbing and cleaning, and the method is suitable for robot autonomous operation of disordered shielding scenes such as bookshelves and storage cabinets.

The invention discloses a rotating shaft calibrating and machining method and a machining platform, is applied to the machining platform provided with a 3D camera and a multi-axis movement mechanism, and belongs to the technical field of mechanical machining.The rotating shaft calibrating and machining method comprises the steps that the multi-axis movement mechanism is controlled to drive a calibrating ball to revolve around a rotating shaft, controlling the 3D camera to obtain point cloud data generated by rotation of the calibration ball, and constructing a first transformation matrix from a 3D pixel coordinate system of the 3D camera to a multi-axis space coordinate system of the multi-axis movement mechanism according to the rotation coordinates of the calibration ball driven by the multi-axis movement mechanism and the point cloud data; controlling the 3D camera to obtain a height map scanned by the processing object, extracting a plurality of track feature points according to the height map, and outputting space track data corresponding to the multi-axis space coordinate system according to the track feature points in combination with the first transformation matrix; and the processing platform is controlled to process the processing object according to the space trajectory data, so that the processing precision of the processing object is improved.

The current invention relates to a method for determining a height map of a sample surface of a sample. The invention further relates to a method for determining a height map of a sample surface comprising a pre-scan step and a high-accuracy scan step. The invention further relates to an optical profilometry device configured for determining a height map of the sample surface. The invention further relates to a computer readable data carrier comprising a computer program.

An apparatus may be configured to perform a perception task based on features fused with height information. The apparatus configured may generate 3D sensor features from data from one or more sensors, generate a plurality of height maps from the 3D sensor features at a plurality of times, generate a height gradient map from the plurality of height maps, fuse the 3D sensor features and the height gradient map to generate height informed fused features, and perform the perception task using the height informed fused features.

A wave radar image inversion method based on a convolutional neural network, and the application thereof, which relate to the field of sea condition monitoring. A convolutional neural network autoencoder is used, and a training set generated by means of a simulation tool is input into the convolutional neural network autoencoder for supervised training, wherein an X-band radar image of an inversion region is an input of the training set, and a corresponding sea surface wave height map is an output of the training set, thereby obtaining a mapping relationship model therebetween. The convolutional neural network autoencoder comprises an encoder, fully connected layers and a decoder, wherein the encoder comprises five convolutional layers and five maximum pooling layers, the convolutional layers and the maximum pooling layers being alternately connected, the fully connected layers are two symmetric layers, and the decoder comprises five deconvolutional layers. Using a convolutional neural network deep learning algorithm achieves a better effect in restoring nonlinear components. Using an autoencoder technique can directly restore an X-band radar wave image to a real-time sea surface wave height map with a relatively small error, and can more comprehensively display sea condition information.

The invention discloses a defect concavity and convexity detection algorithm and detection system based on height map and curvature analysis, and the method comprises the following steps: height data collection: obtaining surface height map data by using high-precision three-dimensional measurement equipment, and ensuring that the resolution and precision of the data meet the detection requirements; image preprocessing: denoising, smoothing and normalizing the height map data to improve the data quality; curvature analysis: constructing a local curved surface model based on the processed height map data, and calculating normal curvature and neighborhood curvature features of surface points; defect classification: classifying defects according to curvature characteristics and height distribution information; according to the method, three-dimensional shape data and curvature analysis of the height map can be combined, concave-convex defect detection accurate to the micron level is provided, and tiny surface defects can be recognized.

The invention discloses a building height estimation method and system based on a single satellite image, and belongs to the technical field of remote sensing image processing. The problem that fine-grained spatial information in shallow-layer features and advanced semantic related information in deep-layer features cannot be effectively utilized when an existing neural network is used for predicting the height is solved. Multilayer height features of a single satellite image are extracted by using an encoder, then processing is performed by using a decoder based on an AMHF multi-scale feature fusion module, the AMHF multi-scale feature fusion module integrates a DAFH attention mechanism of a double-branch structure, a branch 1 uses depth separable convolution to extract fine-grained spatial features, a branch 2 uses depth separable convolution to extract fine-grained spatial features, and a branch 3 uses depth separable convolution to extract fine-grained spatial features; and the branch 2 captures global spatial features by using spatial attention and facilitates extraction of macroscopic advanced semantic related information at the same time, a normalized height map is obtained after the two branches are fused, and the normalized height map is multiplied by maxheight to obtain a final prediction height map.

Example methods and systems for inspecting vehicular tires for irregularities. An example method comprises: rotating a tire relative to sensors, obtaining profile data comprising radial and axial spatial locations of a plurality of points on a surface of the tire, obtaining a reference curve representative of at least a portion of the tire surface, processing the set of profile data relative to the reference and identifying irregularities in the surface of the using the processed data. The method may involve identifying tire features and adjusting the profile data based on those features. The method may involve generating height maps to assist with identifying irregularities. The method may involve identifying the tread surface portions of the profile data, matching the tread surfaces to tread pattern template and adjusting the profile data accordingly.

This invention relates to the field of forage seeds, disclosing an efficient and low-loss combined harvesting method and system for forage seeds based on the Internet of Things (IoT). The method includes: sending a detection laser from a combine harvester in the forward direction, and receiving the reflected laser in the combine harvester; constructing a density map and height map of forage plants in the forward direction; adjusting the height of the cutting module to obtain a cutting module with adjusted height; adjusting the perimeter of the conveying module using the height map to obtain a conveying module with adjusted perimeter; adjusting the size of the sieve aperture of the threshing module using the particle diameter to obtain a threshing module with adjusted sieve aperture; adjusting the wind speed of the separation module to obtain a separation module with adjusted wind speed; and completing the combined harvesting of forage seeds using the height-adjusted cutting module, the perimeter-adjusted conveying module, the sieve-aperture-adjusted threshing module, and the wind speed-adjusted separation module. This invention enables efficient and low-loss adjustment of the combine harvester through IoT technology.

The invention discloses a chip packaging method and a related device, and the method comprises the steps: determining an overlapping region, a reference region and a shielding boundary curve according to imaging data, and obtaining interconnection nodes and rigidity constraint data in the overlapping region; acquiring polarization intensity data in the overlapping region, and obtaining a surface slope field through a dual-band intensity ratio and multidirectional fusion conversion; taking the reference area as a Dirichlet boundary condition, taking a normal derivative of the shielding boundary curve as a Noiemann boundary condition, and carrying out Poisson integration on the surface slope field to obtain a relative height map of the upper chip; and solving low-order deformation parameters of the lower-layer chip through elastic constraint energy minimization according to displacement observation and interconnection rigidity constraint of the relative height map at interconnection nodes. According to the scheme, the technical problems that in a traditional method, geometric benchmark missing exists in an overlapping band, and a shielded layer cannot be observed can be solved.

The invention discloses a line laser 3D contourgraph working method integrating various stray light suppression algorithms, and the method comprises the steps: constructing a stray light sensitivity weight map based on a multi-exposure image sequence through the combination of a deep convolutional neural network and a point spread function; guiding Gaussian Laplacian pyramid adaptive filtering by using the weight map, and adjusting the filtering intensity by using a residual stability index to generate a purification intensity image; performing one-dimensional profile analysis based on the purified image and the original height map, calculating a morphological distortion index, extracting an energy concentration ratio through three-level wavelet packet decomposition, and triggering morphological restoration; performing center line extraction and motion blur correlation degree calculation on the repaired image, and performing anisotropic smoothing on the height map when a threshold value is exceeded; and registering the processed multi-frame height map, constructing geometric fidelity as a feedback driving genetic algorithm to optimize an initial parameter, and restarting a whole process until the fidelity meets a precision requirement. According to the invention, the precision of 3D imaging is improved through various stray light suppression algorithms.

A palletizing method includes: detecting, by one or more depth cameras, a stacking pattern on a pallet; generating a height map matrix based on the stacking pattern, wherein a value at each element of a plurality of elements in the height map matrix indicates a height of the stacking pattern at a position on the pallet corresponding to the element; for each box of the one or more boxes: traversing the elements in the height map matrix to obtain a mask matrix generated based on hypothetical situations that a target vertex of the box rests on a position corresponding to each of the elements; determining reward function values corresponding to one or more of elements in the mask matrix with an element value of 1; determining a box number and a box placement posture corresponding to a largest reward function value of the reward function values.

Methods and systems for generating and modifying three-dimensional occlusograms. One method includes calculating a height map and / or a distance field of a tooth of an upper jaw or a lower jaw. An occlusogram for the tooth may be generated based on a space and / or a collision depth between the tooth and a tooth on an opposite jaw. The occlusogram may be displayed over a three-dimensional (3D) model of the tooth. The occlusogram may be dynamically changed in response to a change in one or more input parameters associated with one or more dental treatments on the tooth.

To provide a method for combining height maps and a profilometer for combining height maps.SOLUTION: A method includes: a step 101 of measuring first and second height maps with a sensor of a profilometer; a step 102 of determining a first overlapping area of the first and second height maps; a step 103 of determining first similarity between the first height map and the second height map; a step 104 of determining a second overlapping area of the first height map and the second height map; a step 105 of determining second similarity between the first height map and the second height map; a step 106 of comparing the first and second similarities; a step 107 of combining the first and second height maps; and a step 108 of outputting a composite height map of a sample surface.SELECTED DRAWING: Figure 2

The invention discloses a plate cutting method based on a 3D laser line scanning device, and the method comprises the following steps: arranging the 3D laser line scanning device above a to-be-cut plate, enabling the scanning visual field of the 3D laser line scanning device to cover the to-be-cut plate, and enabling the scanning visual field to cover the thickness of the to-be-cut plate; scanning the point cloud of the to-be-cut plate, then converting the point cloud into a height map, and then converting the height map into a grey-scale map; extracting edges of cut-off parts in the point cloud on the grey-scale map, independently establishing an X array and a Y array for each cut-off part, and storing the X array and the Y array into the arrays according to the edge sequence; the multiple arrays X and Y obtained in the third step are converted into dxf format files, the dxf format files are transmitted to a control system, graphic software is used for opening the dxf format files so that a user can determine an effective area by observing the collected height map, and further cut graphs are determined through the graphic software; and the control system stores the graph as coordinates and imports the coordinates into a cutting device for cutting.

This invention discloses a method for 3D mesh reconstruction of buildings from multispectral LiDAR point clouds, belonging to the field of multispectral LiDAR point cloud processing technology. The method includes: extracting building instances from the input point cloud using a multispectral LiDAR point cloud classification method; extracting geometric features from the height map obtained from the building point cloud, and then extracting spectral features from the spectral map using a spectral adaptive convolution module; inputting the data into a spectral-geometric fusion module to fuse the features of the spectral map and the geometric map to achieve accurate prediction of 2D corner points; projecting the 2D corner points onto the height index of the height map to obtain 3D corner points, and using an attention mechanism jointly guided by multispectral and geometric features to predict the boundary structure of the 3D corner points, generating a wireframe model; finally, achieving seamless and watertight 3D mesh reconstruction of the building under the guidance of the topological relationships contained in the wireframe model. This invention can effectively reduce artifacts and planar misalignment problems during the reconstruction process.

To improve measurement accuracy of a pin even when a tip shape of the pin is different. A setting unit of a setting support device for a measurement device includes a tool for measuring a predetermined measurement object as a measurement item, receives designation of a measurement region, and sets a tool including a measurement region for measuring the measurement object and a filter parameter according to the designation of the measurement region and a size of the target region and / or a representative height in the target region. A symbol corresponding to the target region is displayed on the height image, a measurement object corresponding to the filter parameter in the measurement region is specified on the basis of the setting of the tool, and the measurement of the tool is executed based on the specified measurement value of the measurement object.

The invention provides a three-dimensional online boxing method considering a buffer area based on hierarchical reinforcement learning, and relates to the technical field of intelligent manufacturing, and the method comprises the steps: obtaining a size information list of a plurality of to-be-boxed boxes in the buffer area, and a three-dimensional height map of a current loading state in a container; extracting buffer area state feature vectors, and splicing the state feature vectors to obtain a global state feature vector; inputting the global state feature vector into a high-level strategy network in a trained hierarchical reinforcement learning network, outputting selection probability distribution of each box body in a buffer area, and selecting a target box body to be placed from the buffer area according to the probability distribution; and inputting the size information and the three-dimensional height map of the target box body into the trained low-layer strategy network, outputting probability distribution of each candidate placement position of the bottom surface of the container, generating an effective mask in combination with a preset physical constraint condition, and carrying out masking and renormalization processing on the probability distribution so as to determine a final placement position of the target box body.

The presently disclosed subject matter includes a computer system and a computer-implemented method of generating synthetic examination output images, including synthetic fault images and synthetic fault-free images. The synthetic images comprise artificially generated 3D defects. A machine learning model is trained for transforming examination output images to height maps. The height maps are modified to include certain 3D features, and a second machine learning model is used for transforming the height maps to modified examination output images to exhibit the 3D features.

An imaging system is disclosed herein. The imaging system includes an imaging apparatus and a computing system. The imaging apparatus includes a plurality of light sources positioned at a plurality of positions and a plurality of angles relative to a stage configured to support a specimen. The imaging apparatus is configured to capture a plurality of images of a surface of the specimen. The computing system in communication with the imaging apparatus. The computing system configured to generate a 3D-reconstruction of the surface of the specimen by receiving, from the imaging apparatus, the plurality of images of the surface of the specimen, generating, by the imaging apparatus via a deep learning model, a height map of the surface of the specimen based on the plurality of images, and outputting a 3D-reconstruction of the surface of the specimen based on the height map generated by the deep learning model.

The invention provides a three-dimensional texture automobile interior trim part transfer printing injection molding method and a mold structure, and the method comprises the following steps: step 1, obtaining a target texture image, the image being a two-dimensional texture pattern, the texture pattern being one of wood grains, metal drawn wires or geometric patterns; generating a three-dimensional depth map of the texture pattern by using a deep learning texture reconstruction model; and converting the depth map data into a microstructure code of the shape memory polymer film, wherein the code is a partition expansion height map. 2, inputting the micro-structure coding data into a nano laser etching system, and etching the surface of a thermoplastic polyurethane (TPU) + shape memory polymer (SMP) film layer to form a micro-cavity structure; by means of the programmable thermal response type microstructure film, it is ensured that texture patterns accurately reappear on the surface of the mold; and through efficient combination of a double-phase film structure and an injection molding material, texture delamination and abrasion are prevented.