1840results about How to "Reduce distractions" patented technology

The invention discloses an electromagnetic transient simulation and mapping method and system oriented to multi-physics field coupling, and belongs to the technical field of substation digital operation and maintenance and electromagnetic simulation. Deploying multiple types of sensors in a transformer substation, preprocessing the acquired multi-physical field data, and fusing with the three-dimensional twinborn model; a coupling algorithm is adopted to carry out multi-physical field coupling analysis, multi-physical quantity display and thermodynamic diagram superposition are realized, and scene evolution change simulation under various typical working conditions is supported; a micro-service architecture is adopted to construct a digital twin system, double closed-loop verification of simulation and actual measurement is performed through actual measurement data and simulation data of a real-model test field, model optimization is completed, and real-time mapping of electromagnetic transient dynamic simulation and a transformer substation physical entity is realized. The method improves the precision of model and entity mapping, meets the requirements of real-time tracking and response of the electromagnetic transient change of the transformer substation, adapts to the digital transformation of different transformer substations, and provides a basis for the operation and maintenance of the transformer substations.

The invention relates to the technical field of deep foundation pit monitoring, and discloses a deep foundation pit micro-deformation InSAR remote sensing method and system and a storage medium. The method comprises the following steps: synchronously acquiring data through a ground radar and an InSAR satellite, and obtaining a point target set and an original scattering characteristic sequence; obtaining a net deformation phase sequence without influence through registration residual correction, phase deduction and weighted fusion processing, and carrying out phase consistency quality control and unwrapping processing to obtain an accumulated deformation quantity sequence; constructing a deformation mechanism correlation characteristic matrix based on correlation analysis of the cumulative deformation quantity sequence and radar reflection intensity amplitude attenuation characteristics; and fusing the deformation mechanism correlation feature matrix and the real-time differential interference image group, extracting deformation rate and phase gradient change, and further generating a deep foundation pit local micro-deformation risk early warning index set. According to the invention, the tiny deformation of the surrounding area of the foundation pit can be effectively detected, potential risks are warned in advance, and the safety and monitoring efficiency in the construction process are improved.

The invention discloses a method for implementing intelligent management and control of a special vehicle operation process based on a virtual space. Only a laser radar and an optical camera which are deployed in a special vehicle operation site and have overlapped detection view fields are used as external sensing equipment to synchronously collect operation environment data; based on the working environment data, constructing a three-dimensional virtual space containing the semantic information of the electrified equipment, and setting a virtual electronic fence to form a security defense area; based on laser radar real-time point cloud data, point cloud clusters of different rigid parts of the special vehicle are identified through segmentation and clustering, and a theoretical three-dimensional contour is generated; extracting a two-dimensional edge of the vehicle part through semantic segmentation based on the optical camera image data, and generating a three-dimensional semantic contour; fusing the theoretical three-dimensional contour with the three-dimensional semantic contour to obtain a high-precision dynamic three-dimensional contour of the moving part of the special vehicle; and calculating the shortest distance between the high-precision dynamic three-dimensional contour and the boundary of the virtual electronic fence, and taking the shortest distance as a reference for executing graded early warning or operating intervention on a special vehicle.

The invention belongs to the technical field of software engineering, particularly relates to an automatic driving system performance enhancement method based on an expert hybrid architecture, and aims to solve the core problems that an end-to-end automatic driving system is confronted with semantic fuzziness to cause unreliable decision, multi-task interference hinders optimization planning, too long reasoning delay increases driving risks and the like. According to the method, an ExpertAD framework is provided, task key features are amplified through a perception adapter (PA), and the relevance of scene context understanding is guaranteed; related driving tasks are dynamically activated through a sparse expert mixture (MoSE), and task interference is minimized; and in combination with a customized training loss function, collaborative optimization of planning effectiveness and reasoning efficiency is realized. Experiments show that compared with an existing method, the method has the advantages that the average collision rate is reduced by 20%, the reasoning delay is reduced by 25%, higher multi-skill planning capacity is achieved in rare scenes (such as accident handling and first-aid vehicle avoiding), and good generalization is achieved for unseen urban environments.

The application provides an atmospheric optical turbulence prediction method and device, the method comprising: obtaining meteorological data at a first time and atmospheric coherence length data within a first time period; inputting the meteorological data into a target model to obtain a preliminary turbulence prediction result; extracting a time feature of the atmospheric coherence length data, and updating the preliminary turbulence prediction result based on the time feature to obtain an updated turbulence prediction result. The method reduces the interference of errors caused by the dynamics and randomness of turbulence on the turbulence prediction result, and improves the accuracy of atmospheric optical turbulence prediction.

The invention provides a clamping device for a thin-wall whole pipe fatigue test and a test method, and belongs to the technical field of clamping devices. The device comprises clamping cushion blocks which are fixedly connected to two ends of a thin-wall whole tube sample main body and are used for transmitting test force; the high polymer material film adhesive tape is wound on a transition area of the clamping cushion block and the thin-wall whole pipe sample main body; the chock plugs are used for being plugged into the two ends of the thin-wall whole-tube sample main body, and packing paper is installed between the chock plugs and the inner wall of the thin-wall whole-tube sample main body and used for supporting the inner wall of the sample and evenly transmitting test force. The clamping cushion blocks are fixedly connected to the two ends of the sample and matched with the high polymer material film adhesive tape to reduce friction, the chock plugs are wound around the packing paper to support the inner wall, a stable clamping structure is formed, and it is ensured that fatigue fracture occurs in the working section. The problems of clamping stress concentration and fracture of a non-working section can be effectively avoided, the accuracy of a fatigue life evaluation result of the whole thin-wall pipe is improved, and the method can be widely applied to high-cycle and low-cycle fatigue performance tests under different conditions.

The invention discloses a vehicle target motion state estimation method based on an unmanned aerial vehicle video, and relates to the technical field of computer vision and intelligent monitoring, and the method comprises the steps: receiving a real-time video stream of an unmanned aerial vehicle, decoding the real-time video stream to obtain an original video frame, carrying out the graying, zooming and normalization preprocessing to obtain a processed image, and synchronously adjusting the size of a vehicle bounding box; vehicle targets are detected, a unique ID is allocated for multi-target tracking, and a motion trail is maintained; determining a background feature region, detecting and tracking feature points to estimate an inter-frame transformation matrix, and performing accumulative transformation to obtain a background overall transformation relation and a historical frame-to-current frame mapping mechanism; calculating a displacement residual error based on the trajectory and the mapping, judging direction consistency, estimating a smooth speed, and updating a motion confidence coefficient to judge a vehicle motion or static state and static duration; outputting the ID, the state, the static duration and the average speed of the vehicle; the method effectively eliminates the motion interference of the unmanned aerial vehicle, improves the estimation precision, is suitable for the traffic monitoring of the unmanned aerial vehicle, and is high in real-time performance and reliability.

The invention discloses an automobile part defect detection method based on multispectrum, and relates to the technical field of spectrum detection. According to the method, an optimal wave band is screened from a data source through spectral response discrimination, and the spectral texture difference between scratches and normal textures is enhanced; normal texture and suspected scratch areas are accurately divided through density clustering, a target area is focused, irrelevant data interference is reduced, and it is ensured that double-feature extraction is higher in pertinence. Further synchronously extracting texture gray level change features and 3D surface height depression features of the suspected area, and capturing dual attributes of two-dimensional texture anomaly and three-dimensional physical form depression of the scratch; and finally, through deviation calculation and relevance verification with a normal region reference feature, the abnormal degree of the double features is quantified, two types of abnormalities are ensured to correspond to the same physical region through spatial relevance, pseudo defects are eliminated, and the problem that scratches are difficult to identify based on texture gray level change and surface height depression in the prior art is solved.

The invention relates to the technical field of natural language processing text classification, in particular to a multi-label text classification method based on semantic representation enhancement and dynamic weighted depolarization contrast learning and application of the multi-label text classification method. Preprocessing data in the training data set to obtain input tensor representation; enhancing text semantic representation by fusing multi-layer hidden semantic representation of a depth model; secondly, an improved label graph convolutional network is constructed, regularization, layer normalization, residual connection and label perception attention pooling are introduced into a graph neural network, fine-grained representation of the relation between labels is achieved, and label-text interaction is enhanced; and finally, introducing depolarization weighted contrast loss to construct dynamic weighted depolarization contrast learning, endowing a negative sample with a higher weight, and reducing false negative sample interference, thereby overcoming label semantic overlapping, and aiming at solving the problem of how to enhance the characterization capability of the model in a multi-label semantic overlapping and label incomplete scene.

This utility model provides an insect branch-fixing survey and rearing observation box, relating to the technical field of insect observation devices, and is designed to solve the problem of easy damage to branches in existing insect survey techniques. The insect branch-fixing survey and rearing observation box includes a first half-box and a second half-box. The first half-box has a first upper half-hole and a first lower half-hole, and the second half-box has a second upper half-hole and a second lower half-hole. The first and second half-boxes are joined to form a receiving cavity. When the first and second half-boxes are joined, the first and second upper half-holes together form a first hole for the branch to pass through, and the first and second lower half-holes together form a second hole for the branch to pass through. The first and second holes are respectively sealed to the branch at different locations. Both the first and second half-boxes are made of transparent material, and at least one of the first and second half-boxes has a ventilation window with a detachable mesh screen. This utility model is less likely to damage branches.

The invention relates to the technical field of coal mining and rock mechanics numerical simulation, and discloses a stress field reconstruction method of a plane strain numerical simulation model for coal mining, and the method comprises the following steps: firstly, obtaining an actually measured vertical stress increment and an actually measured bearing pressure peak value position of a stope face; then, an initial plane strain numerical simulation model is constructed, the space error between the peak position of the simulated bearing pressure and the actual measurement position meets a preset threshold value by adjusting the excavation step pitch, and therefore the numerical simulation calculation state is locked to eliminate space-time dislocation; a simulation strain increment is extracted in a locked state, a theoretical vertical stress difference equation is constructed based on an elastic mechanics plane strain constitutive relation, and a parameter inversion equation set is established in combination with multi-measurement-point data; and solving the corrected elastic modulus and Poisson's ratio by using a least square optimization algorithm. According to the method, through physical state locking and incremental theory inversion, system errors are effectively eliminated, and the reconstruction precision and mechanical preciseness of the mining-induced stress field are improved.

The invention provides a multi-band composite high-integration TR assembly. The multi-band composite high-integration TR assembly comprises a shell, a front multi-layer board, a back multi-layer board, a C / X / Ku band receiving and transmitting circuit, a C / X / Ku band single receiving circuit and a Ka band receiving and transmitting circuit, wherein the front multi-layer board and the back multi-layer board are connected in the shell, the C / X / Ku band receiving and transmitting circuit is connected with the front multi-layer board, and the Ka band receiving and transmitting circuit is connected with the back multi-layer board. The low-cost scheme design of an all-solid-state microwave multilayer board suitable for batch production and testing is adopted, ports and transmission line layout are reasonably designed, multi-band composite mode transmission is achieved in the form of the front face and the back face, a C / X / Ku-band transmitting circuit and an H-polarization receiving circuit are integrated on the front face, and the transmission efficiency is improved. A C / X / Ku frequency band V polarization receiving circuit and a Ka frequency band receiving and transmitting circuit are integrated on the reverse side, different functional circuits are respectively transmitted through a microstrip line and a strip line through an interface circuit structure covering 1-40 GHz and an in-board vertical transition structure, the isolation degree of different circuits is improved, mutual crosstalk between different signals is avoided, and the transmission efficiency is improved. And the functions of high integration, high consistency, ultra wide band, numerical control phase shift, numerical control attenuation and the like of the assembly are realized.

The invention discloses a satellite-ground enhanced signal conversion method and a satellite-ground enhanced signal conversion model based on PPP-RTK, which are used for solving the problems that conventional RTK in a ground-free network area fails, and satellite-based PPP-RTK depends on a special terminal and is slow in convergence. Generating an RTCM-OSR correction number by analyzing the SSR correction number, fusing the orbital clock correction, ionosphere and troposphere correction and performing weighted interpolation; the ambiguity is solved in combination with the observation value of the base station, dual-path verification and weighted fusion are carried out in combination with M-W and LAMBDA algorithms, and the wide lane ambiguity fixing reliability is improved; and when the ground-based signal is interrupted for more than 1 second, inheriting and maintaining Kalman filtering continuity by using the state vector and generating a switching identifier. The model integrates a signal processing module, a correction generation module, an ambiguity verification module and a switching control module, so that a conventional RTK terminal obtains centimeter-level positioning (level 2.3 cm and elevation 4.1 cm) without a public network, the interruption recovery is less than or equal to 1.5 seconds, and the scene upgrading cost of power inspection, power transmission monitoring, wind power plant monitoring and the like is reduced.

The application discloses a kind of based on multi-objective optimization algorithm's advertisement putting real-time effect tracking method, advertisement putting data analysis technical field, including step one: obtaining advertisement putting real-time behavior data;Step two: constructing advertisement putting effect window matrix;Step three: through improved MiniRocket network, execute advertisement effect conduction difference feature extraction and continuous response fragment aggregation processing;Step four: constructing multi-objective tracking objective function set and multi-objective optimization constraint condition;Step five: using improved MOEA / D algorithm, execute state traction decomposition optimization and fragment duration constraint neighborhood replacement processing;Step six: by Canberra distance, execute target deviation analysis processing;Step seven: match target advertisement plan's real-time effect tracking state.The application improves the accuracy of advertisement putting real-time effect tracking by improved MiniRocket network and improved MOEA / D algorithm.

The invention discloses a mode switching control method and related equipment, and the method comprises the steps: obtaining an image of a target region through employing image collection equipment when the image collection equipment is in a night mode that a light supplement lamp is turned on, and taking the image as a detection image; performing block processing on the detection image to obtain a plurality of first image blocks; performing hue detection processing on the plurality of first image blocks in the detection image to obtain hue detection information of the detection image; obtaining the difference between the hue detection information of the detection image and hue reference information, wherein the hue reference information is used for representing the hue characteristics of the image of the target area in the night period; and if the difference reaches a hue evaluation threshold value, switching the image acquisition equipment to a daytime mode in which the light supplement lamp is turned off. According to the technical scheme provided by the embodiment of the invention, the accuracy, reliability and robustness of mode switching of the image acquisition equipment can be improved.

The application discloses a vehicle reverse driving detection method for an expressway, and comprises the following steps: reading single-frame initial data of an expressway video stream, inputting the single-frame initial data into a lane line detection model to obtain lane lines and generate initial lane information; adaptively generating a first region and a second region; merging the two target detection regions, inputting the two target detection regions into a target detection model to obtain vehicle detection results, fusing the vehicle detection results, inputting the fused results into a multi-target tracking algorithm to obtain vehicle trajectory information; judging the driving direction of a lane; and identifying whether reverse driving occurs based on the trajectory information of a current vehicle and the driving direction of the lane where the current vehicle is located. The application can solve the problem of large calculation overhead caused by frame-by-frame analysis of a lane region in a traditional vehicle reverse driving detection method for an expressway by analyzing the relative position relationship between the vehicle motion trajectory and the identified lane in real time.

The application discloses a kind of mixing devices for fermenting feed preparation, belong to fermenting feed mixing field, a kind of mixing devices for fermenting feed preparation, including kettle body, the inside of kettle body is equipped with mixing mechanism, mixing mechanism is also provided with intelligent detection and control module, intelligent detection and control module includes controller, shaft angle detection unit, driving load detection unit and rotational speed detection unit, for this provides a kind of mixing devices for fermenting feed preparation, combine moisture data before and after cleaning, detect stability, different position data difference, shaft angle, driving load and rotational speed change, moisture detection credibility and feed agglomeration state are combined to judge, and according to this implementation liquid supplement adjustment, agglomeration processing and mixed state review.

The application provides a vectorization reverse construction method of an existing building indoor structure scene, and relates to the field of data processing. In the method, laser point cloud data and panoramic image sequences are synchronously acquired, and building structure semantics are extracted by image semantic segmentation. The image semantics are robustly migrated to the point cloud to form structure semantic point clouds. On the basis of eliminating non-building structure elements, a structure point cloud skeleton is constructed, and virtual placeholder point clouds are generated for open structures such as doorways and window openings. Then, continuous structure geometry is recovered by combining voxelization blocking completion and a three-dimensional convolution completion network. Finally, a three-dimensional structure grid model binding structure semantics is generated, and a two-dimensional structure vector drawing meeting engineering drawing rules is obtained by projection vectorization. The technical solution provided by the application facilitates improving the accuracy of the vectorization reverse construction of the existing building indoor structure scene.

The utility model discloses a DSP camera control circuit of golf simulation system detector, 40 feet, 59 feet, 65 feet, 68 feet, 87 feet, 77 feet, 66 feet, 67 feet of blackfin digital signal processor U2 respectively correspond to be connected with resistance R2, resistance R3, resistance R4, resistance R5, resistance R6, resistance R7, resistance R8, resistance R9, 8 feet, 10 feet, 28 feet, 24 feet, 25 feet, 32 feet, 33 feet, 30 feet, 31 feet of CMOS image sensor U4 respectively correspond to be connected with resistance R12, resistance 13, resistance 14, resistance R15, resistance R16, resistance R17, resistance R10, resistance 11, resistance 19, the 23 feet of CMOS image sensor U4 is connected with CMOS logic chip U5, and the 5 feet of CMOS logic chip U5 connects electrolytic capacitor C2 and power supply end CAM3V3, and the resistance R18 is connected between the 1 foot and 3 feet of CMOS logic chip U5, and the 26 feet, 22 feet, 23 feet of CMOS image sensor U4 respectively correspond to be connected with resistance R20, resistance 21, resistance 22, and the resistance of the product plays current -limiting protection and impedance matching, and the protection circuit is prevented from being damaged.

The application provides a quality improvement method and system for hysteroscopic surgery image data, and relates to the technical field of image processing. The method comprises the following steps: acquiring a hysteroscope image of a target patient at a specific time point, and acquiring multi-modal physiological time series data of the target patient before and after the specific time point; performing time series feature fusion analysis on the multi-modal physiological time series data to obtain individual physiological cycle phase information corresponding to the specific time point; inputting the individual physiological cycle phase information into a pre-trained healthy uterine cavity image generation intelligent agent to output a standard healthy uterine cavity reference image corresponding to the specific time point; comparing the hysteroscope image with the standard healthy uterine cavity reference image, generating a pathological residual feature map, and enhancing the display of the pathological residual feature map. The technical problem that abnormal features are not prominent in the existing hysteroscope image is solved.

A storage array, a memory, a reading method thereof, and an electronic device are disclosed. The storage array includes multiple storage cell subarrays, a reference cell column, and a set of reference voltage generation circuits, reference cell switching circuits, and read word line control circuits. The storage cell subarrays and reference cell column in two storage arrays are electrically connected via read bit lines and symmetrically distributed around a read decision unit. The transistors of the reference cells and storage cells are isomorphic and have the same circuit structure. The memory includes at least one pair of open storage arrays, each pair comprising a first storage array, a second storage array, and a set of read decision units. Each storage array is electrically connected to one of the two input terminals of the read decision unit. During reading, the two storage arrays provide a read voltage and a reference voltage, respectively. The two input terminals of the read decision unit have similar RC parameters, and the drift generated by the voltages at the two input terminals is also matched. This application improves storage density and data reading reliability.

The application discloses an information distribution method and system based on a geographic fence and unified credit evaluation, and belongs to the technical field of big data processing. A user publishes business event information in a same account, and independently sets a geographic fence and a receiver credit threshold value; the system determines a second user currently located in the geographic fence and having a credit score not lower than the threshold value, and pushes the information; in response to an acceptance operation of the second user, an interaction relationship between the two parties is established; and in response to a mutual evaluation result after the interaction ends, credit scores of the two parties are dynamically adjusted. Through user-defined distribution conditions, platform implementable auditing and mutual evaluation credit systems, the application breaks the double barriers of traditional socialization and algorithm recommendation, realizes directional, efficient and credible distribution of information, and reduces consumption of network resources and server resources caused by invalid information transmission.

The present application relates to the technical field of heat conduction coating life prediction, and particularly relates to an inorganic high-temperature-resistant heat conduction coating life prediction method and system, which comprises obtaining a heat pipe outlet temperature sequence, a reactor core power sequence, a heat pipe spatial position, a heat pipe adjacency relationship and a cold end boundary category; dividing heat pipe groups according to the heat pipe spatial position and the cold end boundary category; performing power coupling correction on the heat pipe outlet temperature sequence according to the reactor core power sequence to obtain a corrected outlet temperature sequence; obtaining a reference heat pipe group through spatial decoupling screening and consistency screening in a heat pipe group to which a target heat pipe belongs; calculating static difference characteristics and dynamic difference characteristics according to the corrected outlet temperature sequence, and obtaining an interface thermal resistance degradation index through weighted summation; and determining the remaining life according to the change trend of the interface thermal resistance degradation index and life determination conditions. The present application can reduce temperature response deviations caused by power disturbance and spatial coupling, and realize accurate identification and life prediction of heat conduction coating heat conduction capacity degradation.

The utility model discloses a kind of five-way line-in's gigabit network module, it is related to network transmission equipment field, including shell, the left and right sides of the shell are respectively hinged with right shell and left shell, the downside of the right shell and the left shell is fixedly connected with the limit block of symmetrical distribution, the inner wall left side of the left shell is fixedly connected with two symmetrical distribution's connecting plate, the right end of each connecting plate is all penetrated and is provided with clamping groove, the inner wall right side of the right shell is fixedly connected with two symmetrical distribution's buckle, each buckle is all set in the inside of the connecting plate corresponding.The utility model in the multiple limit blocks on right shell and left shell are fixed to cable, and by the different grooves formed between multiple limit blocks, so that cable can take different direction and access inside module, while by limit block, cable inside is fixed, prevent cable from falling off.

This application discloses a wire bridge, an electrical control device, and HVAC equipment. The wire bridge is applied to the electrical control device, which has mating holes. The wire bridge includes a main body and a connecting part. A wire channel is formed within the main body, through which connecting wires are arranged in an orderly manner, making the wiring inside the electrical control box neater and helping to reduce improper contact between connecting wires and components of various circuit modules. The connecting part is connected to the side of the main body opposite to the opening of the wire channel. The connecting part is used to insert into the mating hole to fix the wire bridge inside the electrical control device. This facilitates the installation and replacement of the wire bridge and helps to reduce the size of the wire bridge along the width direction of the wire channel. In the electrical control device of this application, the wire bridge is installed in the electrical control box through the connecting part. The position of the wire bridge is independent of the circuit modules inside the electrical control box. When maintenance or replacement of circuit modules is required, there is no need to disassemble the wire bridge, effectively improving the maintainability and assembly convenience of the electrical control device.

The invention provides a rock mass structural surface strength prediction method driven by a ground vibration load, and relates to the technical field of rock mass mechanics. The method comprises the following steps: acquiring and integrating geometric and mechanical parameters, seismic oscillation parameters and test and numerical simulation data of a structural plane to form a standardized database; cleaning and standardizing database data, constructing a dynamic attenuation factor, and screening and enhancing key features to obtain initial input features; constructing a physical experience reference model and a machine learning predictor, and training a hybrid prediction model by combining prediction results of the physical experience reference model and the machine learning predictor; verifying the model and quantizing the output uncertainty; inputting the basic data calling model to complete calculation and outputting a result. According to the method, the reliability and adaptability of rock mass structural surface strength prediction are improved, and support is provided for seismic design of geotechnical engineering.

The present application belongs to the technical field of concrete preparation detection, and particularly relates to a concrete aggregate water content detection device, which comprises a base and a rack installed above the base. A controller is installed on the side wall of the rack. The device further comprises a through hole opened in the top of the base, a support seat slidably connected inside the through hole, and a weighing mechanism installed inside the through hole for supporting the support seat. A flat hopper is arranged above the base and located on the side of the feed end direction of the support seat. The rack is provided with an adjusting drive mechanism for driving the vertical movement of the flat hopper. A microwave detection unit is arranged on one side of the flat hopper. The present application can perform online detection of the water content of concrete aggregate, improve the detection accuracy by combining weight detection and thickness control, reduce single detection interference error by cross verification of multiple sensing data, and improve data reliability to support subsequent dynamic batching.

This invention belongs to the field of construction equipment technology, specifically a temporary protective device for prefabricated stairs. It includes multiple support frames installed along the stair treads, each connected to a fixing mechanism for securely attaching to the stairs. Support columns are rotatably connected to the support frames via a pivot A, allowing the columns to rotate around the pivot A from a position perpendicular to the stair treads towards the outside of the treads. This invention can adapt to prefabricated stairs with varying degrees of inclination. The clamps, in conjunction with the bottom of the support frames, effectively fix the stairs without drilling, providing effective support for the columns. This reduces interference from the support columns during the handling of large items, lowers the difficulty of moving large items on stairs, effectively reduces damage to the railings from external impacts, forms a secondary buffer, improves the cushioning effect, and extends the lifespan of the equipment.

The application discloses a video instantaneous heart rate detection method based on time-frequency spectrum conversion and an image enhancement network, and comprises the following steps: 1, selecting a face region of interest from a video to obtain a target BVP time sequence; 2, converting the target BVP time sequence into an original time-frequency spectrum through time-frequency spectrum conversion; 3, establishing an image enhancement network to enhance the original time-frequency spectrum and obtain an enhanced time-frequency spectrum; 4, training the image enhancement network; and 5, extracting an instantaneous heart rate value from the enhanced time-frequency spectrum. The application combines time-frequency spectrum conversion and the image enhancement network, extracts a time-frequency spectrum containing instantaneous heart rate information from a face video, can improve the accuracy of instantaneous heart rate detection, and thus provides a new method for non-contact instantaneous heart rate detection based on a video.

This application relates to the field of battery technology, and in particular to a battery pack and power supply device. The battery pack includes a battery module and an infrared temperature sensing component. The infrared temperature sensing component includes a detection bracket and an infrared temperature sensing element. The detection bracket forms a detection chamber that covers one side of the battery module in a first direction, and this side of the detection bracket is in contact with the battery module. The infrared temperature sensing element is disposed within the detection chamber and on the other side of the detection bracket in the first direction, facing the battery module. The battery pack and power supply device provided by this application solve the problem of the limited temperature detection capabilities of traditional temperature sensing elements, making the temperature acquisition results closer to the actual operating state of the battery. Furthermore, it ensures that the infrared signal received by the infrared temperature sensing element mainly comes from the battery module itself, further improving the accuracy of temperature detection.