413 results about "Height map" patented technology

A method for terrain and constraint planning a step plan includes receiving, at data processing hardware of a robot, image data of an environment about the robot from at least one image sensor. The robot includes a body and legs. The method also includes generating, by the data processing hardware, a body-obstacle map, a ground height map, and a step-obstacle map based on the image data and generating, by the data processing hardware, a body path for movement of the body of the robot while maneuvering in the environment based on the body-obstacle map. The method also includes generating, by the data processing hardware, a step path for the legs of the robot while maneuvering in the environment based on the body path, the body-obstacle map, the ground height map, and the step-obstacle map.

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 DnCNN and YOLOv8-based frequency height image denoising and recognition method. The method comprises the steps of inputting an ionized layer detection image into a DnCNN model to obtain a denoised clear image; and inputting the denoised clear image into a YOLOv8 model to obtain a recognition object and outputting ionosphere parameters. Through the precisely adjusted DnCNN model, noise in the ionized layer image is effectively removed, key echo information is reserved, and high-quality input is provided for subsequent image processing; through fine adjustment of the YOLOv8 model, resource consumption is reduced, and the efficiency of model training and the accuracy of object recognition are improved; automation and intellectualization of ionosphere detection image processing are realized, and processing efficiency and practicability are improved. The method is suitable for scientific research and monitoring application requiring high-precision ionosphere image analysis, and has important practical value and scientific significance.

This disclosure relates generally to method and system to track and monitor human using an array of radars. Human tracking is necessarily important in security, especially with the growth of threats and incidents. Conventional systems and method lack in tracking target subject being authenticated to move around the monitoring environment. The present invention provides a method of detect human continually based on radar signals from an array of radars to track the presence of one or more target subjects associated within the monitoring environment. Further, a height surface plot of each target subject present in a radar range is constructed for identification. Then, each target subject present in the radar range of the monitoring environment based on mapping the height surface plot with a predefined height map. The characteristics of each target subject helps in detecting the target subject accurately.

The invention provides a multi-baseline InSAR (Interferometric Synthetic Aperture Radar) elevation fusion method and system for multi-scale geometric analysis, and belongs to the technical field of radar signal processing, and the method comprises the following steps: carrying out non-subsampled shear wave transformation on elevation maps reconstructed by all interferograms to obtain non-subsampled shear wave transformation coefficients of all the elevation maps; the non-subsampled shear wave transformation coefficient is decomposed into a low-frequency coefficient and a plurality of high-frequency coefficients; performing weighted average on the low-frequency coefficients to obtain fused low-frequency coefficients; performing adaptive selection on the high-frequency coefficient to obtain a fused high-frequency coefficient; and performing non-subsampled shear wave inverse transformation on the fused coefficient to obtain a fused elevation map. According to the method, feature extraction of the elevation map is realized, and texture details can be effectively reserved.

System and procedure for the inspection of the surface of a nuclear fuel rod for the automatic detection, localization and characterization of defects, comprising a plurality of point cloud acquisition systems and translation means for the nuclear fuel rod; where the system also comprises processing means capable of transforming the point cloud into a height map, locally thresholding for the segmentation of the height map and obtaining the discontinuities in said map, classifying the discontinuities in different geometric shapes to obtain the area, length, width, position and orientation, projecting the defect on the y-axis to obtain its depth and calculating the equivalent function and its second derivative to obtain the points where the depth of the defect is maximum.

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 provides an airport clearance security situation awareness and management aided decision-making method and system, and the method comprises the steps: collecting distribution detail data, combining the distribution detail data with patrol data to obtain a clearance patrol database, and removing abnormal values according to the integrity, mathematical expectation and standard deviation; judging whether to generate an obstacle block through clustering according to the data distance of any two obstacles, and determining the range of a buffer area by combining the elevation of the obstacle block with the distance between the center of the obstacle block and the airport reference point, the flight navigation precision, the measurement precision and the elevation of the obstacle block; the final obstacle block information is combined with the clearance reference height map, the clearance limit height map and the electromagnetic height map to generate an obstacle distribution map, the final obstacle block limit height is determined, and an obstacle information list is obtained by combining the elevation output risk assessment result and the obstacle crossing height of the obstacle blocks so as to generate a clearance patrol report. And enabling the inspector to recheck and inspect according to the clearance inspection report to make a decision, and adjusting a data acquisition strategy and an analysis model according to the extracted key data.

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 belongs to the field of substation inspection, and discloses an intelligent substation inspection system based on an unmanned aerial vehicle technology and an image analysis technology, which comprises a point cloud processing device, a flight path planning device and an unmanned aerial vehicle, the point cloud processing device is used for processing the point cloud data of the transformer substation to obtain a height image of the transformer substation; the flight path planning device is used for dividing the transformer substation into a plurality of inspection areas based on the height image of the transformer substation and respectively planning a flight path of each inspection area; the unmanned aerial vehicle is used for performing routing inspection on each routing inspection area based on the flight path to obtain a routing inspection image; according to the invention, the unmanned aerial vehicle can inspect each inspection area at a relatively low flight height, so that the hang time of the unmanned aerial vehicle is effectively prolonged, the battery replacement frequency of the unmanned aerial vehicle is reduced, and the inspection efficiency of the transformer substation is effectively improved.

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 present invention discloses an automatic detection method for nanoparticles based on deep learning and AFM images. The method includes: collecting the original AFM images of nanoparticles and processing them to obtain a normalized height map; establishing a deep learning model and training the model; collecting the original AFM detection images of the nanoparticles to be detected and processing them; inputting the detected normalized height map into the trained model, and outputting the regions, aggregation information, and confidence information of the nanoparticles to be displayed in the detected visualization height map; obtaining the pixel-size factor, size information, size distribution information, and aggregation ratio of the nanoparticles according to the detected original images and detected height maps, and finally realizing the automatic detection of nanoparticles. The present invention can automatically segment the nanoparticles in the AFM images and further analyze the nanoparticle information, solving the problems of low accuracy, weak applicability, and semi-automation existing in the current nanoparticle analysis based on traditional machine vision methods.

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 present invention discloses a single-camera multi-projection dual-axis projection structured light three-dimensional reconstruction measurement system, which relates to the technical field of structured light measurement. The method comprises: using a structured light projector to project structured light to a detection object to generate a dual-axis phase-coded fringe image and collect it, reconstructing a height map of the detection object according to the image, eliminating the noise of the occluded area according to the installation position of the structured light projector group and the collected image and obtaining a height map of the unobstructed real height area, fusing the height map of the real height area to obtain a complete and accurate height map, obtaining point cloud data of the detection object according to the height map and performing three-dimensional reconstruction; the present invention can project a 45-degree rotated structured light through a structured light projector and present dual-axis phase-coded fringe on the detection object, eliminate the influence of shadows and high reflections, increase the number of effective point clouds, improve the measurement precision and accuracy of the system, and obtain a complete and accurate measurement result of the detection object.

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.

The invention provides a robot for tidily placing objects in a box body, and the robot comprises a first camera unit which is used for collecting a point cloud picture of the box body and a target object stored in the inner side of the box body in a scene; the processor module is used for acquiring point cloud charts of the box body and target objects stored on the inner side of the box body, generating height charts according to the point cloud charts, clustering and layering the height charts to form a plurality of layer spaces which are sequentially arranged from low to high, constructing a free placement map in each layer space, searching for idle positions in the free placement map located at the bottom layer, and storing the idle positions in the free placement map; when an idle position exists, the target object is placed at the idle position, and when the idle position does not exist, the free placement map located on the upper layer is searched for the idle position until the free placement map located on the topmost layer is full of the target object; and the robot unit comprises an end effector and is used for acquiring the idle position and placing the target object at the idle position. According to the invention, a target object can be placed in the box body in order.

A method for terrain and constraint planning a step plan includes receiving, at data processing hardware of a robot, image data of an environment about the robot from at least one image sensor. The robot includes a body and legs. The method also includes generating, by the data processing hardware, a body-obstacle map, a ground height map, and a step-obstacle map based on the image data and generating, by the data processing hardware, a body path for movement of the body of the robot while maneuvering in the environment based on the body-obstacle map. The method also includes generating, by the data processing hardware, a step path for the legs of the robot while maneuvering in the environment based on the body path, the body-obstacle map, the ground height map, and the step-obstacle 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.