41 results about "Topographical mapping" patented technology

The invention relates to the technical field of intelligent medical treatment, and discloses a cataract surgery navigation control method based on multi-modal fusion, which comprises the following steps: carrying out lightweight preprocessing on an eye fundus image, ultrasonic probe data, a corneal topographic map and intraocular pressure parameters through an edge computing architecture, and constructing an efficient feature extraction network by adopting a knowledge distillation technology; self-adaptive feature fusion is realized based on an uncertainty quantification mechanism, real-time structure recognition is provided by utilizing an augmented reality technology, an intelligent navigation strategy is generated by pre-training a reinforcement learning model, an instrument control system with multilayer safety guarantee is established, and continuous optimization of the system is realized by adopting an online learning mechanism. According to the invention, the precision and safety of the operation are effectively improved, and an effective technical scheme is provided for intelligent navigation control of the cataract operation.

The invention discloses a three-dimensional convolution method for decoding an imaginary language electroencephalogram topographic map. The method solves the problem that for a multi-rhythm electroencephalogram topographic map, an existing convolutional network method is insufficient in modeling capability, so that the decoding precision of the multi-rhythm electroencephalogram topographic map in an imaginary language is remarkably reduced. In the aspect of rectangular BEAM reconstruction, a frequency band specificity self-adaptive variation Kriging interpolation model is built, an optimal variation function is automatically selected according to spatial variation characteristics of electroencephalogram power of each frequency band, a high-resolution BEAM graph sequence under multiple frequency bands and multiple time steps is built, and spatial continuity and CNN structure adaptability are considered. A double-branch three-dimensional convolutional neural network is designed, high-dimensional feature extraction is performed on space-time and space-frequency band tensors, a multi-scale structure and dynamic expression ability of neural activity are mined, discrimination of two feature vector branches is dynamically weighted, and the recognition ability of a classifier to a language imagination electroencephalogram mode is improved.

The invention discloses an orthokeratology parameter optimization method and system, a medium and a product, and relates to the technical field of data processing. By implementing the method, the system is optimized to obtain the corneal topographic maps of the patient before and after the standardized mechanical stress is applied, and point-to-point comparison is carried out, so that the corneal dynamic response deformation map for quantifying actual corneal deformation is obtained. The individualized corneal shaping response coefficient calculated based on the corneal dynamic response deformation map objectively reflects the sensitivity of the cornea of the patient to the mechanical stress. Different from related technologies which only depend on static data and empirical formulas, the method has the advantages that the orthokeratology lens parameter set is subjected to targeted correction through the individualized orthokeratology response coefficient, on one hand, the shaping effect deviation caused by the difference of individual cornea biomechanical characteristics (such as elasticity and viscosity) can be corrected, and on the other hand, the orthokeratology lens parameter set can be corrected; and on the other hand, a finally generated personalized orthokeratology lens parameter set can be more predicated and matched with an actual orthokeratology result.

A roofing tile is described featuring a digitally defined three-dimensional surface profile with controlled minimum and maximum heights and a specified average surface roughness (Ra). The topographical map, generated by computer algorithms—potentially using grey-level speckle maps—enables precise assignment of surface elevations and independent control of roughness parameters. This digital map is material-agnostic and applicable to tiles made from materials such as thermoplastic vulcanizate (TPV), ethylene-propylene-diene terpolymer (EPDM), or polymer-modified asphalt. The surface may include granule-like protrusions or other features, with their size and distribution tailored for functional or aesthetic purposes. The digital topographical map may guide manufacturing equipment to form the surface, and compliance may be verified by three-dimensional profiling. Methods for generating and measuring the surface profile, including pseudo-random algorithms and region-specific roughness, are provided, allowing for customizable, repeatable, and high-performance roofing tile surfaces.

This invention discloses a safety protection system for water conservancy projects based on big data, comprising: a database for centralized information management of digital topographic maps, aerial photographs, and digital topographic model data; an environmental monitoring module for acquiring and locating safety hazard monitoring data, and processing the safety hazard monitoring data into wireless signal data via an information processor for transmission to an environmental data storage module; an environmental data storage module for statistical analysis of safety hazard information; and an environmental judgment module for classifying and classifying safety hazard information based on real-time monitoring data, transmitting information indicating potential dangers to the environmental monitoring module to achieve timely location of safety hazards. This invention can effectively ensure the safety and stability of water conservancy projects.

1. The name of the design product: hand book (R80). 2. The use of the design product: Beidou handheld intelligent terminal, suitable for municipal survey, geographic information, construction lofting, earthwork survey, GNGG control network layout, topographic mapping, etc. 3. The design points of the design product: in shape. 4. The picture or photo that can best show the design points: front view.

The embodiment of the invention discloses a semantic segmentation model training method and a semantic segmentation method, the semantic segmentation model training method can be applied to a digital topographic map, the semantic segmentation model training method comprises the steps that a sample image is acquired, and each sample instance in the sample image has a corresponding category label; inputting the sample image into a preset model, and triggering the preset model to execute the following operations: down-sampling the sample image to obtain at least one first feature; performing up-sampling on the at least one first feature to obtain at least one second feature; performing semantic segmentation on any second feature to obtain a segmentation result; based on any second feature and each category label, determining a corresponding instance feature loss, the instance feature loss indicating a feature loss under a sample instance granularity; determining semantic segmentation loss based on the segmentation result and each category label; and adjusting parameters of a preset model based on the instance feature loss and the semantic segmentation loss to obtain a semantic segmentation model. According to the embodiment of the invention, the semantic segmentation effect is remarkably improved.

A system enables interactive real-time refreshable tactile graphics and braille together enabling blind or visually impaired users to experience and interact with graphics and visual events live and in three dimensions. The tactile graphic display can set each pin in an array of pins to different intermediate heights, enabling users to experience topographical maps and other graphical elements such as shades and color represented as varying heights of pins. The system can simultaneously display high quality of tactile graphics and braille while allowing direct interaction with all digital media-providing real-time refreshable graphics and text in braille. The touch capability of the system enable users to point to any text on the graphic display and have it be instantly rendered in braille on the braille display, thus creating completely new paradigms for reading and creating content. The system further allows continuous monitoring of the touch data in real-time and updating the braille display with any corresponding text.

This invention proposes a multi-layer fusion method and system for pathological images based on self-supervised training and continuous depth field. This method addresses the problems of label dependence and loss of high-frequency biological details caused by neural network spectral bias in existing fluorescence microscopy image fusion. It uses a three-dimensional convolutional neural network to encode spatial and depth joint features of multi-layer image sequences, and decouples the predicted continuous depth field topographic map and foreground confidence mask in parallel. A physically differentiable rendering layer calculates fusion weights based on the continuous depth field to complete weighted fusion, and combines mask soft suppression to output a full depth-of-field image. A self-supervised joint loss function, including high-frequency focusing loss, depth smoothing loss, and mask constraint loss, is constructed based on physical optics priors. The physical correlation between the input sequence and the fused image is used as a supervision signal for closed-loop optimization. High-fidelity fusion can be achieved without manual annotation, effectively preserving the details of minute biological structures.

To provide a boundary line extraction device, a boundary line extraction method, and a program which can extract a boundary line of a geographic feature with higher accuracy.SOLUTION: The boundary line extraction device analyzes a microtopographical representation diagram to extract a boundary line of an area where a prescribed topographic feature appears. The boundary line extraction device comprises: storage means in which a trained model is stored, wherein the trained model is preliminarily trained so as to, in response to input of a microtopographical representation diagram, output a boundary area obtained by extending a line width of a boundary line of an area where a topographical feature appears in the microtopographical representation diagram; acquisition means which inputs a microtopographical representation diagram being an analysis object to the trained model to acquire a boundary area outputted from the trained model; and extraction means which thins the boundary area acquired by the acquisition means and extracts a boundary line of an area where a topographic feature appears in the microtopographical representation diagram being the analysis object.SELECTED DRAWING: Figure 2

The invention belongs to the field of laser processing, and discloses a visual axis center automatic alignment system, device and method. The system comprises an imaging module used for obtaining a corneal topographic map; the adjusting module is used for S1, determining deflection angles of the visual axis around the x axis and the y axis according to the corneal topographic map; generating primary scanning track data according to the corneal topographic map and preset micro-lens parameters; performing three-dimensional rotation transformation on the primary scanning track data; s2, segmenting the three-dimensional point cloud data obtained in the S1 into slice point cloud data of different z-axis planes, performing fitting to obtain each layer of fitting elliptical trajectory, and judging light emitting point information on the fitting elliptical trajectory; and generating a plurality of concentric elliptical trajectories according to each layer of fitting elliptical trajectory and the light emitting point information, and forming a shape envelope of a preset micro lens. According to the system, one-time scanning track data is resampled and fitted, motion compensation of the eyeball off-axis is achieved, and therefore the precision and effect of automatic alignment of the visual axis center are improved.

A system is provided.SOLUTION: A system includes a terminal unit that acquires position information, a terminal unit that captures at least one image data, a server unit that receives the position information and the image data transmitted from the terminal unit and acquires altitude data, a server unit that generates a topographical image from which an artificial object is excluded by using an image generation AI based on the acquired altitude data, and a server unit that transmits the generated topographical image to the terminal unit.SELECTED DRAWING: Figure 1

The application discloses a kind of based on topographic map analysis fetal electrocardiosignal dynamic analysis and fetal state and prediction method, collect clinical pregnant woman abdominal electric signal, obtain fetal electrocardiosignal by pre-processing and signal separation technique, construct signal dynamic analysis benchmark data set.It designs topographic map analysis algorithm suitable for fetal electrocardiosignal, constructs signal state template, generates the time series change graph of fetal electrocardiosignal state, with the state statistical parameter sequence with annotation as the benchmark data set of fetal state prediction;Construct decision tree model, train the training data set of state statistical parameter sequence, obtain trained model;The test set of state statistical parameter sequence is input into decision tree model, and fetal state is predicted.The present application solves the limitation of existing non-invasive fetal electrocardiosignal monitoring in interpretation, visualization and fetal state prediction, significantly optimizes the readability, interpretability and fetal state prediction performance of visualization result.

The application relates to the technical field of topographic mapping, in particular to an interactive DEM smoothing method; the method comprises the following steps: S1, inputting original DEM data; S2, identifying abnormal values in the inputted original DEM data; S3, marking the identified abnormal values in a highlighted form on a two-dimensional terrain view in real time, superimposing an original contour line layer, obtaining a superimposed elevation map, setting a frame selection range, setting a frame selection range for each abnormal value on the superimposed elevation map, correcting the elevation values of each elevation point in the frame selection range, and obtaining corrected DEM data; the application improves the efficiency of DEM abnormal point correction.

This invention discloses a method and system for inverting strong convection along a power transmission line. The method includes: acquiring historical meteorological radar images and DEM data along the power transmission line, and fusing the historical meteorological radar images and DEM data to obtain a topographic image; inputting the topographic image into a convolutional neural network pre-constructed based on topographic weighted features, and generating an initial predicted inversion image corresponding to the topographic image based on the initial network parameters in the convolutional neural network; constructing a target loss function for the convolutional neural network based on the topographic image and the initial predicted inversion image, and training the convolutional neural network based on the target loss function to obtain a strong convection inversion model for the power transmission line; inputting the acquired real-time topographic image into the strong convection inversion model for the power transmission line, and the strong convection inversion model predicts the inversion image in real time. This method can accurately locate the core of strong convection, improve high-resolution edge details, and enhance generalization and robustness in complex scenes.

The invention belongs to the field of biomedical engineering industry, and provides a low-temperature plasma radiofrequency ablation power regulation system based on vocal cord leukoplakia treatment, which comprises the following steps of: firstly, constructing an impedance topographic map of a vocal cord lesion and non-lesion area, planning an ablation route through clustering analysis, monitoring an impedance jump point during an operation, and judging an electrode pollution state; when pollution exists, an impedance jump point-pollutant area coupling model is established, pollution interference is stripped, the real impedance of the tissue is reversely deduced, and then the radiofrequency ablation power is adjusted in real time based on the model; the system realizes dynamic adaptation of power and real impedance of tissue, improves ablation accuracy, reduces normal vocal cord tissue damage, reduces postoperative recurrence rate, and ensures safety and effectiveness of surgery.

A three-dimensional convolution method for imagined language electroencephalography (EEG) topography decoding. It solves the problem of the deficiency of the existing convolutional neural network method in modeling ability for multi-rhythm EEG topography, which leads to a significant decline in decoding accuracy in imagined language. In the aspect of rectangular BEAM reconstruction, a frequency-specific adaptive variogram kriging interpolation model is built, which automatically selects the optimal variogram function according to the spatial variation characteristics of the EEG power of each frequency band, and constructs a high-resolution BEAM map sequence under multi-frequency and multi-time steps, taking into account the spatial continuity and the adaptability of the CNN structure. A double-branch three-dimensional convolutional neural network is designed to extract high-dimensional features from spatial-time and spatial-frequency tensors, respectively, to explore the multi-scale structure and dynamic expression ability of neural activity. The discriminative ability of the two feature vector branches is dynamically weighted to improve the recognition ability of the classifier for the EEG pattern of language imagination.

The present invention pertains to an arrow tracking system that enables a user to locate an arrow after it has been launched. The system includes a nock with an inner housing designed to enclose a GPS module controlled by a micro-controller (MCU). The MCU is activated by a plunger sliding within the nock and also controls a light signaling GPS activation. In certain embodiments, the system comprises a two-unit configuration with a transmitter unit housed within the nock and a receiving unit carried by the user. The transmitter unit includes a nock GPS module, transceiver, and plunger-activated switch. The receiving unit includes a receiving controller coupled to a receiver GPS module and transceiver that calculates distance and directional bearing between units. The receiving unit displays real-time positioning on topographical maps via an integrated screen or mobile device, enabling efficient arrow recovery.

This invention discloses a construction site management system based on a smart supervision APP, including: a region division module, which marks dangerous work points on the topographic information of the acquired construction area topographic map, and sets dangerous work areas and monitoring areas within the construction area according to the topographic information. It relates to the field of construction management technology, and can predict whether there are suspicious personnel intending to enter dangerous work areas based on personnel location and walking dynamics, obtain the work point location of suspicious personnel for subsequent relevant deployment, avoid the problem of unrelated construction personnel accidentally entering dangerous work areas and causing safety accidents, improve the safety control effect, and realize standardized safety management of construction sites.

This invention discloses a non-invasive detection method and device for pediatric dry eye syndrome based on gaze-induced fixation, belonging to the field of ophthalmic medical device technology. The method includes: providing Placido, diffuse white light, and dual-ring infrared illumination modes, and providing visual guidance based on positive and negative stimulus feedback; simultaneously recording ocular surface video; performing image stabilization; capturing spatiotemporal features to obtain non-invasive tear film breakup time and an optimized tear film stability topography map; performing semantic segmentation and feature extraction to obtain a quantitative lipid layer thickness value; and using a preset closure threshold comparator to obtain the proportion of incomplete blinking. This invention can significantly prolong the effective eye-opening and stable gaze time in children, obtain extremely stable micron-level ocular surface video, and integrate three core indicators: NIBUT, LLT, and blink dynamics.

The invention relates to the technical field of acoustic radar detection, in particular to an underground nonmetal pipeline detection method and system based on acoustic radar coupling, and the method comprises the steps: determining a nonmetal pipeline detection area, a system control platform and a detection vehicle, obtaining a detection area map, a detection area satellite map, an existing underground pipeline network map and a detection area topographic map, the method comprises the following steps: dividing a non-metal pipeline detection area to obtain a shortest scanning path, performing mode switching on an antenna array to obtain a low-frequency mode, performing low-frequency radar scanning on the non-metal pipeline detection area to obtain original radar echo data, and performing AI algorithm preliminary identification operation on the original radar echo data to obtain a suspected pipeline area set; and obtaining a region detection report set, and completing underground nonmetal pipeline detection based on acoustic radar coupling based on the region detection report set. According to the invention, the detection precision, efficiency and reliability can be improved.

The invention relates to the technical field of geographic information data processing, and discloses an image-based geographic space vector data quality control method, and the method comprises the steps: obtaining standardized vector topographic map data, and classifying the standardized vector topographic map data into a to-be-checked vegetation surface element data set and a non-vegetation element data set; creating a fixed-resolution graphic buffer area and establishing a coordinate conversion relation; converting the boundary of each element into a pixel coordinate system; a vegetation surface boundary is drawn in the buffer area by adopting a first color, and then a non-vegetation element boundary is drawn by adopting a second color and coverage logic; and traversing the pixels in the buffer area, and identifying the residual first color pixels through color matching so as to determine the sideline missing position. Vector topology verification is converted into pixel color detection, the calculation complexity does not depend on the number of element nodes any more, and the quality inspection efficiency in a massive high-density node scene is remarkably improved.

The invention relates to a method for selecting a motor imagery channel. The method comprises the following steps: collecting an electroencephalogram signal of a user for motor imagery; preprocessing the collected electroencephalogram signals of the motor imagery to obtain clean electroencephalogram signals; a brain topographic map is generated according to the clean electroencephalogram signals, and a proper channel is selected by calculating a bias index; training a decoding model by using the selected channel; performing motor imagery decoding on the electroencephalogram signals of the selected channel by utilizing a trained decoding model, and outputting a motor imagery classification result as a control instruction; the wearable flexible glove robot receives the control instruction and executes the motion training action according to the control instruction. According to the method, electroencephalogram signal denoising and channel selection can be carried out in real time, robustness is achieved, the noise influence is reduced, and the classification precision is improved.

A grid and a vat for a vat assembly of a vertical filter press such as a tower press is disclosed. The grid is provided with a topographical pattern engaging with a corresponding, inverse topographical pattern on the filtrate vat. The topographical patterns guide the filtrate flow towards a filtrate outlet and reduces the formation of vortices and turbulent flow of the filtrate, hence increasing the filtrate flow rate through the vat. Simultaneous, the topographical patterns improve secure attachment of the grid onto the vat, thereby allowing increased travel speed of the filter medium during advancement thereof. As a result, the cycle time of a filtration process may be reduced, and consequently, the overall capacity of the associated filter press is increased. A filtrate vat assembly and a vertical filter are also disclosed.

The invention relates to a pain real-time discrimination and treatment effect evaluation system based on EEG micro-state monitoring. The system comprises a micro-state extraction and analysis module which extracts a GFP peak topographic map from EEG signal data, optimizes the GFP peak topographic map to generate a template map, calculates parameters such as average duration of each micro-state category, and outputs a micro-state feature parameter set; the pain real-time judgment module inputs the micro-state characteristic parameter set into a deep learning model for detection, and a detection result containing a pain level is obtained; the treatment effect evaluation module obtains quantitative treatment effect indexes by obtaining and comparing micro-state characteristic parameter sets before and after treatment, and generates a report containing the indexes, analysis results and a micro-state change trend chart. According to the system, the pain state of a patient is monitored in real time through the EEG micro-state, objective evaluation indexes about the curative effect are provided for clinicians by quantifying the dynamic change of the EEG micro-state of the patient before and after treatment, and the scientificity and accuracy of treatment effect monitoring are improved.

A method to perform automatic corneal topography or tomography difference mapping includes receiving one or more corneal topography or tomography data files and / or a corneal image for an examined patient from a corneal topography or tomography system; receiving personal identification parameters from captured user personal data communicated from the corneal topography or tomography system; and comparing received patient identification parameters to existing patient identification parameters in a database to identify if there are existing topography or tomography data files for a same patient in the database. The method may further include retrieving a prior topography or tomography data file for the patient from the database; and performing difference mapping by comparing the received topography or tomography data files to the prior topography or tomography data file retrieved from the database to generate a topography or tomography difference map.

The application provides a pathological image multi-layer fusion method and system based on self-supervised training and continuous depth field. The method aims to solve the problems of serious label dependence in existing fluorescent microscopic image fusion and high-frequency biological detail loss caused by neural network spectrum deviation. A three-dimensional convolutional neural network is used to perform spatial and depth joint feature coding on a multi-layer image sequence, and a continuous depth field topographic map and a foreground confidence mask are predicted in parallel. A physically differentiable rendering layer calculates a fusion weight based on the continuous depth field, completes weighted fusion, and outputs a panoramic depth image combined with a mask soft suppression. A self-supervised joint loss function is constructed based on physical optics priors, including a high-frequency focusing loss, a depth smoothing loss, and a mask constraint loss. The physical correlation between the input sequence and the fused image is used as a supervision signal for closed-loop optimization, which can achieve high-fidelity fusion without manual annotation and effectively preserve the details of micro biological structures.

The invention discloses a keratoconus element learning diagnosis method under an unbalanced small sample condition. The method comprises two parts of model training and auxiliary reasoning. According to the model training part, firstly, an acquired corneal topographic map is preprocessed and labeled, and then a meta-learning task ensuring complete categories is constructed by adopting a balance task sampler. And a pre-trained Swin Transform is used as a feature extractor to acquire the multi-scale depth features of the image. A plurality of prototypes are generated for early keratoconus categories with high diagnosis difficulty by using K-means clustering, and other categories are uniformly grouped. Classification is completed by calculating the distance between a query sample and a prototype and carrying out probability aggregation, and meta-learning optimization is carried out by adopting a joint loss function combining enhanced focus loss and contrast learning loss. And the auxiliary reasoning part is used for extracting input image features by using the trained model, comparing the input image features with the learned prototype, and outputting a diagnosis category and confidence. According to the method, the auxiliary diagnosis accuracy and generalization ability of the keratoconus are remarkably improved.

The present application relates to a kind of intelligent auxiliary prescription systems of lens eye intraocular lens, comprising: haptics landing line acquisition module, obtain the three-dimensional structure data of anterior chamber and posterior chamber, construct 3D topographic map of ciliary sulcus area by AI three-dimensional image semantics analysis, obtain the best fitting ciliary sulcus line by fitting, with the best fitting ciliary sulcus line as reference, calculate and obtain haptics landing line;Ideal haptics determination module, according to the lateral depth difference between each point on haptics landing line, obtain the ideal haptics position combination sequence of intraocular lens;Crystal matching module, obtain the inventory data of crystal, based on the arch height prediction range and ideal haptics position combination sequence obtained in advance, obtain the best matching intraocular lens and its implant rotation position scheme from the crystal inventory.Compared with prior art, the present application has the advantages of high accuracy of crystal size matching, meeting the stability requirements of crystal implantation, more accurately guiding how to rotate and adjust arch height of crystal and optimizing crystal prescription process.

Generation of treatment recommendations for topographic-based excimer laser surgical procedures is described that includes generating accurate cylinder compensation and spherical compensation values that are adjusted to compensate for unique characteristics of topographic-based excimer laser surgical systems. Generating treatment recommendations generally includes determining a topographic vector, a posterior astigmatism vector and an anterior astigmatism vector, and generating an internal astigmatism vector using the topographic vector, the posterior astigmatism vector, the anterior astigmatism vector, and a manifest astigmatism vector. In embodiments, the cylinder compensation is generated using multiple vectors while subtracting the internal astigmatism vector and the posterior astigmatism vector which remain in the eye after treatment, and the spherical compensation is generated using an initial spherical compensation modified by addback modifiers and a regression analysis nomogram. In procedures where the corneal epithelium is removed, an epithelial refractive vector is determined from an epithelial thickness / topography map and added to the other vectors.