64results about How to "Stable extraction" patented technology

The invention belongs to the technical field of biological medicine and electronic information technology, and discloses an atherosclerosis model based on nano-molecule magnetic resonance imaging and a machine learning algorithm, a nano-targeting probe and application of the atherosclerosis model based on the nano-molecule magnetic resonance imaging and the machine learning algorithm. A high-resolution MRI image capable of specifically displaying foam macrophage distribution in the plaque is obtained; then, image omics features are extracted from the images, a machine learning model which is constructed based on the features and verified by pathological labels is adopted for analysis, and finally an objective and quantitative plaque vulnerability score is output. According to the model disclosed by the invention, an objective and quantitative risk score can be output by fusing nano-targeted molecular imaging and machine learning, and accurate and reliable quantification of plaque vulnerability is realized. According to the invention, through systematic integration of targeted molecular imaging and machine learning, significant technical progress is brought.

The invention relates to a road infrastructure full-automatic inspection method, device and equipment based on an unmanned aerial vehicle group, and a medium thereof. The method aims at the problem that disease characteristics collected by unmanned aerial vehicles in traffic flow and vegetation shielding scenes are broken, and the method comprises the following steps of: decoupling texture and motion characteristics of a dynamic shielding area; feature maps of the effective area and the shielding area are separated; performing cross-frame splicing and continuous repair on the fracture features by using an optical flow constraint generation network, and reconstructing the geometric integrity of a shielded region; infrared data are fused to correct thermal deformation errors, and a high-precision continuous curved surface model is generated; and finally, based on a disease quantitative feature vector matching maintenance strategy, realizing full-process automation from data acquisition to decision output. According to the method, the continuous modeling precision and the maintenance decision reliability of pavement disease detection in the shielded environment are remarkably improved.

The invention discloses a machine tool cutter head fault detection method and device, an electromagnetic type linear displacement sensor is arranged at the corresponding position of a machine tool cutter head, and the method comprises the steps that based on electromagnetic type linear displacement sensing, a displacement signal sequence of the machine tool cutter head is collected in real time; performing adaptive signal decomposition on the displacement signal sequence to obtain at least one first intrinsic mode component and one second intrinsic mode component; calculating a first energy value sequence of the first intrinsic mode component in the continuous time interval, and calculating a second energy value sequence of the second intrinsic mode component; based on the first energy value sequence and the second energy value sequence, the fault type of the machine tool cutter head is judged; the fault types comprise a tool bit deflection fault and a main shaft chip clamping fault. By adopting the electromagnetic linear displacement sensor and combining a self-adaptive signal decomposition technology, the interference of a complex industrial environment on detection is effectively overcome, and accurate distinguishing and reliable detection of a machine tool cutter bit deflection fault and a main shaft chip clamping fault are realized.

The invention provides a large language model text traceability method based on virtual cue word embedding, and belongs to the technical field of artificial intelligence natural language processing and the technical field of digital content security, the method comprises the following steps: (1) constructing a chat input instruction text with a role format; (2) obtaining embedded vector input; (3) obtaining system cue word embedding representation; (4) obtaining a generated text with a user identity information watermark; and (5) recovering user identity information to realize traceability of the generated text. According to the method, on the premise that main body parameters of the large language model are not modified and model text generation quality and response efficiency are not affected, instant embedding of traceable identity information in the large language model generation process is achieved, meanwhile, robustness of embedded watermark information in a text transformation scene is guaranteed, and the method is suitable for large language model generation. Verifiable and reproducible identity identification information can be stably extracted from the generated text, and reliable technical support is provided for source tracing of the generated text.

The application relates to the field of radiation source identification, and specifically provides a high-explainability radiation source identification method and system, a training set radar pulse signal is acquired, a multi-domain joint time-varying fingerprint feature is extracted based on physical layer modeling, the fingerprint feature is input into a time-frequency double-branch feature fusion network to obtain time-frequency fusion features; the time-frequency fusion features are subjected to signal-level physical consistency enhancement and feature-level mixed enhancement; based on the enhanced features, an end-to-end training is conducted on the time-frequency double-branch feature fusion network through a hierarchical contrast learning framework containing intra-class contrast and inter-class prototype contrast, a radiation source identification model is obtained, and the trained radiation source identification model is used to identify the individual class of a radar pulse signal to be identified. Through the introduction of the physical layer explainable time-varying fingerprint feature, the adaptive double enhancement mechanism and the hierarchical contrast learning framework, the application realizes high-credibility, strong-adaptation and stable-identification radiation source individual identification.

The invention relates to the technical field of image recognition, and discloses a wind power fan blade defect recognition method and system based on image recognition, and the method comprises the steps: carrying out the blocking cutting, illumination normalization and image enhancement processing of an original image, constructing a defect-free sample and a defect sample, and dividing the samples into a training set and a test set; the method comprises the following steps: taking a GANopen network as a basic framework, fusing the lightweight design of Mamba-YOLO, constructing a joint loss function by adversarial loss, reconstruction loss and coding loss based on a training set, carrying out unsupervised training, optimizing network parameters until convergence, and obtaining a defect identification model; inputting the preprocessed to-be-detected fan blade image into the trained defect recognition model, performing defect recognition and positioning, and outputting the defect type and position; based on an output result of the defect identification model, dynamically adjusting an early warning level and response measures through a self-adaptive early warning mechanism; according to the invention, the efficiency and accuracy of wind power fan blade defect identification are improved.

This invention relates to the technical field of sorting retired lithium-ion batteries, and provides a sorting method for the cascade utilization of retired lithium-ion batteries, comprising the following steps: safety inspection of the retired batteries to be sorted; electrochemical impedance spectroscopy testing under preset conditions to obtain raw impedance data and construct an initial feature vector; parsing the initial feature vector to convert it into relaxation time distribution data to construct a multimodal feature set containing real data and enhanced data; inputting the multimodal feature set into a Transformer-MLSAE network, performing deep feature distillation and EIS-DRT feature fusion to extract a deep fused feature vector; classifying the batteries into performance level labels according to cascade utilization standards; training a regularized logistic regression classification model based on the deep fused feature vector and performance level labels to obtain a retired battery sorting model; obtaining the deep fused feature vector and inputting it into the trained retired battery sorting model to obtain the predicted performance level of the battery for cascade utilization.

The application discloses a kind of high-altitude operation personnel rule violation identification method based on gesture capture, including the following steps: generating high-altitude operation image frame sequence;Scene reference reconstruction is carried out, and high-altitude operation scene reference data is generated;Personnel region anchoring is generated by carrying out human contour segmentation;Personnel gesture observation sequence is generated;Human posture capture is carried out, and operation personnel gesture joint sequence is generated;Gesture trajectory condenses, and personnel gesture trajectory data is generated;Coupling data of gesture boundary is obtained by gesture-boundary coupling projection;Using improved CleverCatch model, candidate rule violation data is generated;Temporal continuity verification and gesture stability check are carried out, and effective rule violation data is generated, and high-altitude operation personnel rule violation identification result is obtained, improve the accuracy and stability of high-altitude operation personnel rule violation identification, reduce artificial patrol omission and ordinary video identification false alarm.

This application discloses an image processing method, apparatus, device, and storage medium, relating to the field of computer vision technology. The method involves inputting image data into a feature modeling network for feature extraction to obtain a feature map; then, target region detection is performed based on the feature map to determine the target location. The feature modeling network includes a local distortion modeling branch and a global state space modeling branch that receive the same input features. The local distortion modeling branch processes the input features based on convolution and deformable convolution to generate a spatial offset prior field and local enhancement features. The global state space modeling branch processes the input features based on a state space model and introduces a spatial offset prior field to dynamically modulate the global state space modeling process, generating global context features. This application can solve the problem in related technologies where traditional convolutional neural networks based on regular receptive fields struggle to stably extract target features from images with distortion or stretching.

The application discloses an intercalation large-size graphene oxide-based lithium ion separation membrane and a preparation method and application thereof, and belongs to the technical field of membrane filtration and ion separation. The preparation method comprises the following steps: blending an oxidized graphene solution with an intercalation agent, standing to obtain a mixed solution, depositing the mixed solution on a base film, and drying to prepare a salt water lithium extraction membrane. The application also discloses the application of the graphene oxide-based salt water lithium extraction membrane prepared by the preparation method in the extraction of lithium ions from salt water. The interlayer spacing of the graphene oxide membrane can be adjusted by a specific intercalation agent to realize selective filtration of specific ions. With the increase of the size of the graphene oxide, the mechanical properties and film-forming properties of the large-size graphene oxide are improved, the stability of the membrane is improved, the membrane can be kept stable at a relatively thin thickness, and therefore, the lithium ions in salt lakes or brine can be stably extracted with high selectivity and high flux.

The present application relates to the field of laser measurement technology, and more particularly to a kind of steel rail piece geometric dimension intelligent measurement method based on laser scanning.The present application includes the following steps: measurement preparation and system calibration;Laser scanning data acquisition;Point cloud data preprocessing;Geometric dimension intelligent calculation, based on the profile feature extraction of rail head, rail waist and rail bottom of each section profile point cloud after standardization;Measurement result output and storage.The present application constructs global reference axis of steel rail, converts local coordinates of each section to global coordinate system and compensates scanner attitude deviation, establishes continuity constraint of adjacent section profile feature parameters according to steel rail model, obtains optimal profile feature parameters through global optimization, can stably extract profile features of rail head, rail waist and rail bottom under unified reference, reduces the influence of attitude deviation and point cloud noise, and realizes reliable calculation of geometric dimension of steel rail section, full-length straightness and twist degree form error.

The invention discloses a traditional Chinese medicine composition for treating diabetic skin itch and a preparation method thereof, and belongs to the technical field of traditional Chinese medicines. The composition is prepared from angelica sinensis, astragalus membranaceus, radix paeoniae rubra, cortex dictamni, rehmannia, ligusticum wallichii, scalded peach kernels, safflower carthamus, fried tribulus terrestris, divaricate saposhnikovia roots and cicada slough according to a specific weight ratio. On the basis of a classic famous formula of the Chinese angelica potion, the Chinese angelica potion is innovatively prepared aiming at the core pathogenesis of qi deficiency, blood stasis, damp-heat and wind-dryness of diabetic skin itch. The radix paeoniae rubra and the radix paeoniae alba are used for enhancing the effects of cooling blood and dissipating blood stasis; peach kernel and safflower are added to strengthen blood circulation activation and collateral dredging; cortex dictamni is added to enhance dampness eliminating and detoxification; cicada slough and herba schizonepetae are used for enhancing wind dispelling and heat clearing, and the nature is Polygonum multiflorum and liquorice are removed, so that the safety is improved. The whole formula has the effects of tonifying qi, promoting blood circulation, eliminating dampness, detoxifying, dispelling wind and moistening dryness. The invention also provides a preparation method of the composition. The composition can be used for preparing medicines for treating skin diseases such as diabetic skin itch and eczema, and is remarkable in curative effect and high in safety.

This invention discloses a polarity testing method for metering devices suitable for high-noise environments, belonging to the field of metering device testing technology. The method includes: generating a square wave excitation signal with preset parameters based on algorithm control and applying it to the primary side of the metering device; acquiring the secondary side induced response signal, which is then synchronously transmitted after filtering, baseline drift correction, and amplitude scaling preprocessing; integrating the excitation and preprocessed signals, extracting phase difference, delay time, and amplitude characteristic parameters, and sequentially performing polarity, phase sequence, and on / off determination to obtain a preliminary comprehensive result; based on the preliminary result and characteristic parameters, outputting the determination result and confidence level through an improved CNN model, and obtaining the final polarity conclusion through weighted fusion; and visually outputting the final conclusion. This invention, through the collaborative design of precise excitation, anti-interference preprocessing, multi-dimensional preliminary determination, and AI-fused final determination, effectively suppresses noise interference, improves the accuracy and stability of polarity determination, and is suitable for high-noise scenarios such as industrial sites and substations.

This invention provides a method and system for automatically generating parking lot maps based on point cloud and semantic features, belonging to the field of parking lot map construction technology. The method includes: acquiring the original LiDAR point cloud of the parking lot and preprocessing it to obtain a ground point cloud; extracting parking space line point clouds based on the reflection intensity of each point from the obtained ground point cloud; clustering and segmenting the parking space line point clouds to obtain multiple independent parking space line point cloud clusters; performing straight line fitting on each parking space line point cloud cluster to obtain parking space boundary lines and parking space dividing lines; generating parking space boxes based on the intersections of the parking space boundary lines and parking space dividing lines, and outputting the parking lot map. This invention uses a reflection intensity threshold segmentation method to extract parking space line point clouds, overcoming the influence of illumination changes on parking space line extraction; by combining density clustering and a two-step straight line fitting strategy based on geometric constraints, it effectively solves the problems of ineffective differentiation of continuous parking space boundaries and insufficient fitting accuracy of dividing lines.

This invention discloses a signal enhancement method and apparatus for time-slice compressed sensing 3D imaging radar. First, an M×N dimensional random binary matrix is ​​generated as the measurement matrix for compressed sampling. The target area is illuminated using a laser source, and repeated sampling and modulation are performed to obtain a sampling matrix. The j-th column of the sampling matrix is ​​extracted to generate a compressed sampling vector for the corresponding time slice. The covariance between the compressed sampling vector and each column of the measurement matrix is ​​calculated to obtain the compressed sampling covariance vector. The covariance between each column of the measurement matrix and all columns is calculated to obtain the covariance measurement matrix. Based on a compressed sensing 2D reconstruction algorithm, the 2D image of each time slice is reconstructed using the covariance measurement matrix. The reconstructed 2D images of all time slices are stitched together to form a complete 3D image. This method and apparatus can solve the problems of low reconstruction accuracy and poor image quality in existing compressed sensing 3D imaging technologies under noisy environments.

This invention provides a method for tracing the source of large language model text based on virtual prompt word embedding, belonging to the fields of artificial intelligence natural language processing technology and digital content security technology. The method includes: (1) constructing chat input command text with role format; (2) obtaining embedded vector input; (3) obtaining system prompt word embedding representation; (4) obtaining generated text with user identity information watermark; (5) restoring user identity information to achieve source tracing of generated text. This invention achieves real-time embedding of traceable identity information in the large language model generation process without modifying the main parameters of the large language model or affecting the model text generation quality and response efficiency. At the same time, it ensures the robustness of the embedded watermark information in text transformation scenarios, and can stably extract verifiable and reproducible identity information from the generated text, providing reliable technical support for tracing the source of generated text.

The invention discloses an incident angle measurement method and system based on reflection light spot image analysis, and belongs to the technical field of optical measurement. The method comprises the following steps: enabling a laser beam to enter the front surface of a to-be-detected glass window at a preset reference incidence angle; collecting a light spot grayscale image of the reflected light beam, and obtaining an original grayscale image; determining a light spot connected domain according to the corrected image, and intercepting a local processing window by taking the center of the light spot connected domain as the center; obtaining an effective signal image after background removal according to the background estimation area at the periphery of the local processing window; constructing an exclusion mask, and determining an effective pixel set; on the effective pixel set, calculating the center coordinate of the light spot; and according to the displacement component, calculating a deviation value of a reference incident angle by combining geometric parameters of a measurement system, and obtaining an actual incident angle. According to the invention, excessive optical elements are not needed, sub-pixel-level center positioning is realized through cooperation of the image sensor and a high-robustness image processing algorithm, and the method has the advantages of high precision, strong anti-interference capability and simple structure.

This invention relates to the field of elevator technology, and more particularly to an anomaly detection method for elevator polyurethane buffers based on millimeter-wave radar. The method includes: acquiring echo signals within a preset time window after the polyurethane buffer's compression and rebound by millimeter-wave radar; determining the target distance unit and generating a vibration displacement signal in the radar's line-of-sight direction; identifying intervals where the overall vibration envelope shows a decaying trend and extracting the damping response signal; implementing bistable stochastic resonance enhancement and variational mode decomposition to identify the target modal signal; calculating damping characteristic indices using the target envelope amplitude and stiffness characteristic indices using the target phase to construct a health feature vector; and determining whether the obtained health feature vector lies within the constructed health reference space. Using non-contact millimeter-wave radar to acquire echo signals during the polyurethane buffer's rebound process allows for precise capture of phase changes caused by minute movements or vibrations of the target, resulting in high detection efficiency and safety.

This invention discloses a method and system for terrain accessibility assessment of unmanned ground vehicles in unstructured environments, belonging to the field of terrain accessibility analysis technology. The method includes: acquiring image data and LiDAR point cloud data using data acquisition equipment, and extracting features from the image data and LiDAR point cloud data using a pre-trained model to obtain image feature maps and point cloud feature maps; the data acquisition equipment includes a camera and a LiDAR; fusing the image feature maps and point cloud feature maps to obtain multimodal feature maps; spatially transforming the multimodal feature maps to obtain transformed multimodal feature maps; classifying and calculating the transformed multimodal feature maps to obtain an elevation map and a accessibility map, using the accessibility map as the final output of the terrain accessibility assessment. This invention is applicable to unstructured scenarios with complex terrain types and frequent dynamic environmental changes.

The application relates to a tumor intraoperative evaluation method and system based on multi-wavelength photoacoustic mathematical statistics analysis, wherein the method comprises the following steps: irradiating a tumor tissue with a pulsed laser during operation, collecting photoacoustic signals at different wavelengths in time sequence according to a preset wavelength sequence, performing mathematical statistics spectrum analysis after pretreatment to obtain multi-wavelength statistical parameters reflecting the characteristics of the photoacoustic signals; performing parameter mapping on the multi-wavelength statistical parameters to obtain a parameter imaging graph reflecting the scattering characteristics and microstructure differences of the tissue, obtaining a parameter spectrum curve based on the parameter imaging graphs at different wavelengths, and extracting auxiliary features based on the parameter imaging graphs; performing visual analysis based on the parameter imaging graphs and the parameter spectrum curve, spatially positioning a lesion area, selecting a ROI and visually displaying the lesion area; and taking the multi-wavelength statistical parameters and the auxiliary features as inputs of a tumor benignity and malignancy evaluation model to output a tumor classification result. Compared with the prior art, the application has the advantages of being capable of realizing rapid and accurate intraoperative evaluation.

The application provides a multi-energy cooperative heating system, method, equipment and medium, and relates to the technical field of heating. The system comprises: a group of buried tube wells, which are used for transmitting external waste heat into a rock-soil layer to store heat and generate a heat storage rock-soil layer in a non-heating season; a biomass cogeneration unit, which is used for generating power, exhaust steam and flue gas; a ground source heat pump unit, which is used for extracting heat from the heat storage rock-soil layer in a heating season by taking a preset part of the power as a driving source, generating water at a first temperature according to the heat; a flue gas waste heat recovery device, which is used for recovering the flue gas and generating water at a second temperature by taking the flue gas as a driving source; and an absorption heat pump unit, which is used for increasing the temperature of the water at the first temperature and the water at the second temperature, generating water at a third temperature, and outputting the water at the third temperature to a heating pipe network. The application has the technical effect of meeting the long-term needs of a central heating pipe network for heating continuity and hot water quality.

The invention discloses an EGS surrounding rock thermal efficiency estimation method and system based on a dynamic strength criterion, and relates to the technical field of dry hot rock geothermal resource development, and the method comprises the steps: introducing a temperature correction term and a bedding direction coefficient based on a Nova-Zaninetti criterion, and building a dynamic strength equation; establishing a three-dimensional roadway model of the enhanced geothermal system based on excavation; constructing a heat transfer model of the enhanced geothermal system based on the unsteady heat conduction equation; based on the dynamic strength equation, a solid mechanical field model of the enhanced geothermal system is constructed; the heat transfer model and the solid mechanical field model are coupled into the three-dimensional roadway model, and a surrounding rock heat efficiency numerical model of the enhanced geothermal system is constructed; and estimating the thermal efficiency of the enhanced geothermal system based on the surrounding rock thermal efficiency numerical model. According to the invention, the technical problem of large deviation between the thermal efficiency estimation result and the actual thermal efficiency estimation result in the prior art is relieved.

The invention discloses a micro negative pressure separation system for a graphite material super-crushing process, which comprises the following steps: firstly, carrying out ultrasonic pre-dispersion on super-crushed graphite powder under the protection of inert gas, so that agglomerated particles are dissociated to form uniform suspended powder cloud; and then sealed feeding between the normal-pressure area and the negative-pressure grading area is achieved through a spiral airlock mechanism. In a negative pressure environment, powder is sequentially subjected to coarse separation of the speed increasing channel, grading separation of the rotational flow field and dispersion conditioning under the action of the electrostatic field, and a stable gas-solid two-phase system suitable for fine screening is formed. In the fine grading part, a multi-layer ceramic membrane filtering structure is adopted to cut off the particle size of submicron-scale and nano-scale powder, and periodic regeneration of a membrane surface is realized through a pulse back flushing device, so that continuous and stable filtering flux is maintained. The system realizes closed-loop control of atmosphere through negative-pressure air exhaust and oxygen content monitoring, so that the whole process is operated under a low-oxygen condition, and graphite powder with different particle size grades, such as coarse powder, medium powder, fine powder and nano powder, is obtained.

This invention belongs to the technical field of bactericide residue analysis and determination in plant-derived foods, specifically relating to a method for detecting isobutylethoxyquinoline and its metabolites in plant-derived foods. The method includes extraction with acetonitrile under citrate conditions, followed by purification with C18 (25 mg), PAX (25 mg), and XFM64 (nitrogen-doped multi-walled carbon nanotubes, 10 mg) adsorbents. Chromatographic separation is performed using a C18 column with methanol-2 mmol / L ammonium acetate (containing 0.1% formic acid) as the mobile phase, isocratic elution at a flow rate of 0.40 mL / min, electrospray ionization (ESI+), and detection in multiple reaction monitoring (MRM) mode. This invention is simple to operate, has high pretreatment efficiency, and its precision and recovery rate meet the regulatory residue limit monitoring requirements. It is suitable for the simultaneous determination of isobutylethoxyquinoline and its metabolites in plant-derived foods.

This utility model discloses a centrifugal balancing device for blood component preparation, relating to the technical field of centrifugal balancing devices. It includes: a workbench; a balance body disposed at the top of the workbench; two sets of balancing components symmetrically disposed at the top of the balance body; an extraction component disposed at the top of the balancing components; a locking component disposed on the outside of the extraction components for disassembly and maintenance; and a limiting component disposed on the top outside of the extraction components. This utility model, through the coordinated arrangement of the workbench, balance body, balancing components, extraction components, locking components, and limiting components, not only enables centrifugal balancing of blood collection bags but also significantly improves the balancing accuracy of the blood collection bags before centrifugation. Furthermore, disassembly facilitates the recycling and reuse of the balancing solution and the maintenance of the device.

The application discloses a large model-based evaluation method and system for growth stage feeding amount of large yellow croaker, and belongs to the field of aquaculture. The method comprises the following steps: simultaneously collecting underwater images of a fish pond in multiple shooting directions, identifying and segmenting fish body images corresponding to each entity fish in each underwater image; determining the distance between the fish body image corresponding entity fish and the camera collecting the fish body image, and extracting the external features of the fish body image; selecting one fish body image from each shooting direction to form a fish body image associated combination, and screening a second fish body image associated combination from all possible fish body image associated combinations according to the distance and the external features of the fish body image; constructing three-dimensional point cloud data of the entity fish according to the second fish body image associated combination, fitting the three-dimensional body shape parameters of the entity fish through the three-dimensional point cloud data, and determining the final feeding amount of the fish group according to the three-dimensional body shape parameters of each entity fish. The application can solve the problem of low precision of real-time feeding amount of the fish group.

The application provides an extraction method of high-purity type I collagen, and belongs to the technical field of biomedical materials. The application realizes efficient and stable extraction of type I collagen by accurately selecting process conditions, significantly improves the purity and extraction efficiency of the target product, and the obtained collagen has complete three-dimensional structure, extremely low impurity residue and water content, greatly improves the biocompatibility and storage stability of the product, the method is simple in process, easy to control in condition, does not need complex large-scale equipment, is suitable for large-scale production, provides a reliable high-quality raw material source for high-end implant medical devices, and expands the application prospect of collagen in the field of biomedicine.

The invention discloses a pulse wave extraction method and system based on a video space phase. The method comprises the following steps: selecting an optimal sub-region from a target object region as a region of interest according to image quality; performing complex controllable pyramid decomposition on the video sequence of the region of interest; extracting phase information according to a preset target vibration direction, and calculating a phase difference between each frame of each spatial position in the region of interest and the reference frame; combining the phase difference information on the time sequence to form a two-dimensional phase difference matrix; performing band-pass filtering processing on the phase difference matrix, and decomposing the filtered matrix into a low-rank matrix L and a sparse matrix S by using a robust principal component analysis algorithm; phase information is extracted from the low-rank matrix L, pulse wave signals are reconstructed, frequency domain transformation processing is conducted on the reconstructed pulse wave signals, and the pulse waveform and the heart rate of the user are obtained; aiming at poor stability of a non-contact pulse wave extraction method, the non-contact pulse wave extraction method improves the robustness and accuracy of non-contact pulse wave extraction.

The application relates to the technical field of municipal road construction, in particular to a road marking device, which comprises a stirring and advancing assembly, a front cleaning assembly and a spraying assembly. The stirring and advancing assembly comprises two inner-cavity-communicating rollers rotatably arranged at the back of one side of a trailing rocker arm. The axial center lines of the two rollers are on the same straight line, and the two rollers can rotate relative to each other with the axial center line as the axis. The roller is used as a rolling wheel during road advancing, and the inside loaded marking paint is stirred while rolling. The front cleaning assembly comprises a rolling brush obliquely arranged at the front of the other side of the trailing rocker arm, and the rolling brush realizes pre-cleaning of the road to be marked. The existing material bucket and the walking mechanism are integrated, the complexity of the material bucket, the auxiliary function mechanism and the walking mechanism is reduced on the basis of ensuring the working capacity, and the purpose of reducing cost and increasing efficiency is achieved.