1629 results about "Thermal emission" patented technology

The invention discloses a visible light and infrared image fusion method based on cross-modal dynamic collaboration. The method comprises the following steps: respectively extracting texture detail features of a visible light image and thermal radiation features of an infrared image through a visible light encoder and an infrared encoder; spatial alignment and channel complementarity optimization of cross-modal features are realized by using a heterogeneous attention collaboration module; and performing layered fusion on deep semantics and shallow detail features through a dynamic gating multi-scale decoder to generate a high-resolution fusion image. According to the method, the problems of feature dislocation, detail loss and unreasonable fusion weight distribution caused by modal difference in the prior art are solved, the detail fidelity, the thermal target saliency and the complex scene adaptability of the fusion image can be remarkably improved, and a high-robustness fusion result is provided for low-illumination environment perception and multi-modal target recognition.

The invention provides an unmanned aerial vehicle identification early warning method and system. The method comprises the following steps: acquiring RGB image data, thermal radiation data and spectral data of an unmanned aerial vehicle no-fly zone through a visible light camera, an infrared thermal imager and a multispectral imager; performing transmission preprocessing on the RGB image data, the thermal radiation data and the spectral data, and adaptively adjusting multi-level fusion of a fusion weight based on real-time environmental parameters to generate target fusion data; based on a deep learning model and a tracking prediction algorithm, performing unmanned aerial vehicle identification early warning on the target fusion data, and generating early warning data; and transmitting the target fusion data and the corresponding abnormal event log to a cloud server, and updating the deep learning model by adopting the target fusion data and the abnormal event log. Through cooperative work of a multi-mode sensor, visible light, infrared, multispectral and other wave bands are covered, all-weather and full-scene unmanned aerial vehicle detection is achieved, the fusion weight is adjusted in real time based on real-time environment parameters, and the accuracy of the recognition result under the complex air situation is ensured.

The invention provides a room obstacle detection optimization method and system based on a cross-modal attention mechanism. Wherein a dynamic compensation coefficient is calculated by acquiring motion track data of the mobile equipment, and a stable visual coordinate system is constructed. Visible light and near-infrared wave band acquisition of the multispectral sensor is synchronously triggered, the visible light captures geometric deformation characteristics of a floor projection surface, and the near-infrared detects a local heat radiation abnormal area. And extracting a thermal feature connected domain conforming to periodic biological motion as a living obstacle, and marking a collision risk boundary of a static obstacle. And based on a living body motion law and a collision boundary deviation trend, synchronously optimizing the dual-band exposure parameters and updating the trajectory prediction model, and forming a closed-loop feedback link of sensing and planning. According to the technical scheme provided by the invention, the living body and the static obstacle are accurately distinguished in a dynamic environment, and the sensor parameters are adaptively adjusted to improve the real-time obstacle avoidance response capability.

The invention relates to the technical field of laser material processing, and discloses a laser annealing temperature control method and device.The method comprises the steps that the specific heat capacity, the heat conductivity coefficient, the heat diffusivity, the heat radiation rate, the heat reflectivity and the heat loss coefficient are obtained, and a material thermal characteristic model is established; performing grid division according to the material thermal characteristic model to obtain a laser energy density parameter; extracting a thermal strain coefficient according to the laser energy density parameter, and establishing a temperature-thermal strain mapping relation prediction model; dynamically adjusting a laser power proportion and a pulse width time sequence according to the temperature-thermal strain mapping relation prediction model to obtain temperature field distribution data; according to the temperature field distribution data, carrying out shortest path analysis to obtain a temperature regulation and control decision; and according to the temperature regulation and control decision, inputting a preset control regulation model, and combining reinforcement learning iteration optimization parameters to obtain a temperature control scheme. According to the method, large-range temperature crossing and fine adjustment in an extremely short time can be realized.

The invention discloses an intelligent forest fire monitoring method and device, electronic equipment and a medium, and the monitoring method employs a multi-mode deep learning model based on a double-attention mechanism to enhance the capturing capability of early flame thermal radiation characteristics and smoke form characteristics, and greatly improves the recognition sensitivity. In combination with triple verification and a confidence coefficient decision-making mechanism, errors caused by environmental interference are effectively avoided, and the recognition reliability is comprehensively improved; meanwhile, based on intelligent gridding three-dimensional monitoring of terrain complexity and vegetation types, the blind area coverage rate is greatly reduced, normalized inspection and post-disaster quick response are performed through the unmanned aerial vehicle platform, the monitoring coverage range is enlarged, and the response efficiency is improved.

The invention relates to the technical field of artificial intelligence welding, and discloses an automatic welding robot based on artificial intelligence and a welding system thereof. The system comprises a welding feature acquisition module, a process parameter generation module, a real-time regulation and control module and a motion planning module. The welding characteristic acquisition module is used for acquiring three-dimensional contour data, material component information and welding seam geometric parameters of a workpiece to be welded, and generating a welding characteristic spectrum through characteristic fusion; a process parameter generation module retrieves a matching template from a welding knowledge base according to the parameters, and outputs a reference welding process parameter combination in combination with an environment temperature and humidity compensation coefficient; the real-time regulation and control module dynamically corrects the reference parameters to generate an optimization instruction according to the molten pool form, thermal radiation distribution and electric arc voiceprint characteristics in the welding process; and the motion planning module calculates a motion track, attitude parameters and a speed curve of the welding execution mechanism according to the optimization instruction to form a robot control instruction set. The system can improve the intelligent level of welding, guarantees stable welding quality, and is suitable for welding scenes of multiple manufacturing industries.

The invention relates to the technical field of target detection and tracking, and discloses a multi-modal real-time target detection and tracking system, which is characterized in that a multi-modal data acquisition module integrates a high-definition camera, a millimeter-wave radar, a laser radar and an infrared sensor and is used for acquiring target information from multiple dimensions such as visual images, distance, speed and angle, three-dimensional point cloud and thermal radiation; and the data preprocessing module is used for carrying out denoising, enhancement, normalization, filtering, coordinate conversion and temperature correction processing on the original data acquired by the multi-modal data acquisition module. Multiple sensors are integrated to collect multi-dimensional data, after preprocessing, efficient fusion is achieved through hierarchical fusion and an attention mechanism, the detection module is combined with an improved algorithm and a dynamic threshold value, the tracking module fuses multiple features and has the online learning ability, and the system control module achieves intelligent management. The system greatly improves the accuracy, the real-time performance and the stability of detection and tracking, has remarkable advantages of an innovative technology, and provides a new scheme for related fields.

The invention relates to the technical field of LED dimming control, in particular to an LED ceiling lamp control system based on dynamic light source adjustment, which comprises a brightness sensing module, a dimming decision module, a light source regulation and control module, an anomaly detection module and a brightness optimization module. According to the invention, the operation load of the lamp is dynamically measured and calculated by combining ambient light and thermal radiation data, the collaborative perception of illumination intensity and thermal energy distribution is realized, the response sensitivity to weak brightness change is improved by comparing the brightness demand with the real-time output deviation and accurately identifying the dimming trigger condition, and the response sensitivity to weak brightness change is improved by comparing the initial brightness with the feedback difference value. The brightness of a plurality of lamps can be adjusted coordinately, the spatial light environment is kept stable and consistent, overload and temperature rise abnormity can be checked and abnormal lamps can be identified by combining current fluctuation and temperature abrupt change analysis, an intervention record and reaction duration comparison mechanism is introduced into a regulation and control instruction, the response efficiency is improved, and the efficiency is improved. And brightness priority adjustment and overall illumination balance control of the key area are realized.

The invention discloses an intelligent AI detection method based on an infrared thermogram and automobile diagnosis, according to the technical scheme, the fireproof safety detection efficiency of an electric automobile is remarkably improved through multi-modal data fusion and intelligent analysis, and a multi-dimensional data basis is constructed through synchronous acquisition of dual-band infrared and vehicle operation parameters; secondly, a dynamic correlation model realizes accurate triggering of abnormal current on heat map enhancement, partition gradient processing is combined with dynamic threshold adjustment to optimize detection sensitivity for thermal characteristics of different parts, three-dimensional thermal field reconstruction breaks through surface detection limitation, internal potential overheat points can be identified, and the detection sensitivity is improved; and finally, closed-loop diagnosis is formed through case library intelligent matching, so that the fault positioning precision reaches a component level, and the whole scheme is coordinated through a multi-level technology, so that the problems of low infrared thermal image contrast and relatively poor detail distinguishing capability due to the fact that electric vehicle fireproof safety detection is carried out only by depending on thermal infrared images in the prior art are solved.

The invention relates to the technical field of intelligent control, and discloses a self-adaptive temperature curve control system for high-temperature alloy vacuum casting, which comprises a sensing module, a control module and a control module, and is characterized in that the sensing module acquires multi-point temperature information and preprocesses the information to obtain temperature distribution in a furnace; the acquisition module obtains vacuum environment parameters. The simulation module establishes a three-dimensional dynamic coupling model based on heat conduction, radiation, convection and phase change heat effect, and obtains a real-time temperature evolution prediction result. The generation module obtains a target temperature curve of the corresponding stage. The prediction control module collects a real-time temperature evolution prediction result and a target temperature curve, deviation calculation and trend analysis are carried out, and a heating power and cooling flow control instruction is generated. And collecting product feedback errors and carrying out self-learning correction on prediction model parameters to obtain an optimized control output result. The control and optimization of the high-temperature alloy vacuum casting temperature field are realized, and the structure uniformity of castings and the quality stability of finished products are improved.

The invention relates to the technical field of environmental pollutant detection, in particular to a straw open-air incineration pollutant emission quantitative method based on multi-source data fusion, which comprises the following steps: based on air pollutant monitoring data, calling a sensor network to obtain PM2.5, CO and NOX concentrations, analyzing fire point heat radiation intensity, collecting meteorological data, and calculating the concentration of PM2.5, CO and NOX; and obtaining a pollution source data set by combining the time sequence change of the fire points and the meteorological parameters. By integrating an environment monitoring sensor, satellite remote sensing and ground meteorological data, the comprehensiveness and accuracy of pollution source monitoring are improved, the combination of fire point intensity and pollutant concentration time sequence data is optimized, the evaluation of fire point and pollution hot spot areas and the comprehensive analysis of wind directions and meteorological conditions are optimized, the accuracy of a pollutant diffusion model is improved, and the pollution source diffusion efficiency is improved. The pollutant release amount is dynamically adjusted, and the diffusion model is corrected by using a geographic information system, so that the scientificity of pollution prediction and emission intensity evaluation is enhanced, and more accurate pollution prevention and control decision support is provided.

The invention provides a non-contact multi-mode thermal imager temperature measurement method, and relates to the technical field of non-contact temperature measurement, and the method comprises the steps: collecting the three-dimensional structure information of a measured object, obtaining infrared thermal radiation data, and collecting meteorological parameters; identifying the material and the surface state of the object, and adjusting an infrared emissivity parameter by using a deep learning model; performing cross-modal feature alignment on the related data; and inputting the meteorological parameters into the environment interference model to correct the infrared signal, determining whether the temperature measurement data is qualified, and if yes, repeating until the temperature measurement of the measured area is completed. According to the invention, by fusing the multi-modal data and utilizing the deep learning model, the space-time attention mechanism, the environment interference model and the like, the dynamic calibration of the infrared emissivity, the feature alignment of the multi-modal data and the effective compensation of the environment interference are realized; the problems of large environmental interference, difficult emissivity calibration, insufficient complex scene adaptability and the like of a traditional method are solved, and the temperature measurement precision and reliability are improved.

The smoke detection method based on multi-sensor fusion analysis provided by the invention comprises the following steps: when a smoke sensor detects that the smoke concentration in a detection range reaches a first threshold value, acquiring a temperature rising speed in the detection range detected by a temperature sensor, acquiring the environmental heat radiation uniformity in the detection range detected by the human body sensor; generating a corresponding correction coefficient to correct the smoke concentration and the first threshold value to obtain a corresponding corrected smoke concentration and a corrected threshold value; if the corrected smoke concentration reaches a corrected threshold value, a comprehensive risk value is calculated based on the corrected smoke concentration and the temperature rising speed; and if the comprehensive risk value reaches a risk threshold, determining that the fire is a real fire. According to the invention, through the fusion processing of the smoke sensor, the temperature sensor and the human body sensor, the defect that fire detection through smoke is easily interfered by the environment and misinformation is generated at present is overcome.

An apparatus may include: (a) a processing chamber including chamber walls and a chamber heater; and (b) a pedestal positioned within the chamber interior and including: (i) a substrate heater having a plurality of light emitting diodes (LEDs), (ii) a window positioned above the substrate heater comprising a material transparent to light from the LEDs, (iii) three or more substrate support pads configured to support a substrate such that the window and the substrate are offset by a nonzero distance; and (iv) a temperature sensor comprising a first detector configured to measure thermal radiation emitted by the substrate, and a second detector configured to measure light transmitted through the substrate.

The invention provides an advertisement pushing method and system based on multi-modal data fusion. The method comprises the following steps: determining a user staying event of each position according to intensity peak value distribution of a user foot heat radiation signal of each position in continuous N time windows; performing frequency domain decomposition on the user foot heat radiation signals at the plurality of positions so as to extract a people flow density component and a staying time length component which are synchronous with a timestamp of a user staying event; calculating a discrete difference degree between the people flow density component and the staying duration component by adopting a variable coefficient method; and according to the discrete difference degree, adjusting a content playing queue of an advertisement screen in the offline commercial place, so that the playing content is matched with the commodity category corresponding to the shelf vertex. According to the technical scheme provided by the invention, the user staying event can be intelligently identified, the content of the advertisement screen is dynamically matched, precise commodity marketing is realized, and a consumption scene is adapted.

The invention discloses a heat effect and stripe noise synchronous progressive correction method based on an RBF curved surface. The method comprises the following steps: acquiring a degraded image; performing gray processing on the degraded image to obtain a gray degraded image; performing guided filtering processing on the gray scale degraded image to obtain a filtered thermal radiation effect estimation image; constructing an RBF kernel matrix according to the thermal radiation effect estimation image and the RBF kernel function, and solving a weight coefficient in combination with a pixel gray vector of the thermal radiation effect estimation image; multiplying the solved weight coefficient by the RBF kernel matrix to generate an RBF thermal radiation effect curved surface; estimating stripe noise through a stripe operator based on the degraded image and the RBF thermal radiation effect curved surface; according to the RBF thermal radiation effect curved surface and the stripe noise, a potential clear image is restored through a synchronous progressive correction optimization algorithm. According to the invention, the thermal radiation effect and possibly accompanied stripe noise of the image can be simply and efficiently removed.

The invention provides an infrared image frequency division enhancement method based on a diffusion model, and the method comprises the steps: firstly carrying out the multi-scale frequency domain decomposition of an infrared image through discrete wavelet transform, and dividing the image into a low-frequency component and a high-frequency component; in the low-frequency component processing process, a diffusion equation is constructed in combination with a thermal radiation physical model, and discretization solution is performed by using a finite difference method. The high-frequency component is converted from a space domain to a frequency domain through Fourier transform, energy distribution of the high-frequency component is analyzed, and a diffusion probability function is adjusted. In the fusion stage, according to the signal-to-noise ratio of the local area of the image, the fusion weight of the low-frequency component and the high-frequency component is dynamically adjusted, the processing results of all the local areas are integrated in a weighted fusion mode, and finally the high-quality enhanced infrared image is generated. The method has excellent performance in improving image contrast, definition and detail performance, is suitable for the fields of security monitoring, military reconnaissance, industrial detection and the like, and can effectively improve monitoring, analysis and detection effects.

The invention discloses an unmanned aerial vehicle target detection method and system based on a visual detection algorithm. The unmanned aerial vehicle target detection method comprises the steps of generating unmanned aerial vehicle cruise route data containing a GPS coordinate sequence through a path planning algorithm; collecting multi-frame street lamp RGB image data through a visible light camera; meanwhile, single-channel infrared thermal radiation image data of the corresponding space-time position are collected through a carried infrared thermal imaging module; establishing a mapping relation between the RGB image data and the infrared thermal radiation image data to form a multi-modal original data set D; preprocessing the multi-modal original data set D to obtain a standardized multi-modal data set; according to the standardized multi-modal data set, constructing an improved UAV-YOLO model for identifying a street lamp heat source; aiming at the problems that a street lamp heat source presents small-size hot spots (10-30 pixels) in an image and is mixed with other heat sources (an automobile, an air conditioner outdoor unit and the like) in an urban environment and the distinguishing accuracy of a traditional algorithm is low under the overlook angle of an unmanned aerial vehicle, the method improves the detection precision.

The invention provides a reinforcing mesh multi-welding-spot quality detection method and system based on infrared thermal imaging. Wherein for each crossed steel bar welding spot, the fusion form of the crossed steel bar welding spot is identified based on the thermal radiation image; based on the fusion forms of all the crossed steel bar welding spots, quality detection results of the multiple welding spots of the steel bar mesh are generated, and the quality detection results comprise geometric judgment results used for representing whether the fusion forms meet preset form requirements or not; and according to the quality detection result, a corresponding early warning mode is adopted for self-adaptive early warning, and welding parameters adopted by the next electric resistance welding process are adjusted according to early warning information. According to the technical scheme provided by the invention, millisecond-level multi-welding-spot synchronous quality detection and process closed-loop optimization are realized, and the production yield and the process adaptability of the large reinforcing mesh are greatly improved.

The invention relates to the technical field of target identification based on multi-modal data fusion, and aims to solve the problems that an existing life detection system is difficult to effectively distinguish spatial distribution of a human body target and a hot pseudo target and cannot realize real-time synchronous analysis of multi-source heterogeneous data, so that the target positioning reliability in an extreme environment is seriously restricted. The invention provides a multi-modal data fusion human body target recognition method based on automatic control, and the method comprises the steps: constructing a feature complementation and interference suppression model based on a deep neural network through fusing the cross-modal data of infrared thermal imaging and visible light imaging, and employing a multi-scale anti-interference network based on wavelet graph convolution and an attention mechanism to recognize a human body target. The environment noise broadband interference is suppressed through the time-frequency localization characteristic, high-robustness recognition of a human body target in severe environments such as dense smoke shielding and thermal radiation interference is achieved, and accurate distinguishing of the human body and a thermal pseudo target in a complex fire scene environment is achieved.

The invention discloses an apple anthracnose leaf blight recognition five-dimensional data fusion method based on a patrol robot, relates to the technical field of anthracnose leaf blight recognition, and solves the problems of limited sensing dimension, large illumination interference and inaccurate spatial positioning in the prior art. Comprising the following steps: S1, acquiring surface curvature characteristics of apple leaves, collecting RGB-D images of the leaves, constructing a three-dimensional topological structure of the leaves, and positioning scab space distribution; s2, acquiring spectral reflection information of apple leaves, quantifying biochemical components of chlorophyll a and carotenoid, and constructing a vegetation index feature set sensitive to diseases; s3, apple tree canopy temperature information is collected, a transpiration anomaly detection model is constructed, and multi-modal fusion of thermal infrared and point cloud data is realized; and S4, integrating spatial distribution, spectral reflection and thermal radiation information, constructing a five-dimensional phenotypic characteristic matrix model, and comprehensively analyzing apple phenotypic characteristics. According to the method, the recognition accuracy under the conditions of blade shielding, uneven illumination, blade posture change and environment interference can be remarkably improved.

The invention relates to the technical field of infrared thermal imaging, and particularly discloses a fire personnel intelligent search and rescue method and device based on infrared thermal imaging, and the method comprises the steps: synchronously collecting fire scene data through an infrared thermal imager and a laser radar, so as to obtain infrared thermal imaging data and fire scene three-dimensional point cloud data; further introducing a data processing technology based on deep learning to carry out feature extraction on the infrared thermal imaging data and the three-dimensional point cloud data of the fire scene so as to capture infrared thermal radiation distribution features and three-dimensional space structure features of the fire scene, and then carrying out fine-grained feature alignment joint perception on the infrared thermal radiation distribution features and the three-dimensional space structure features; therefore, the deep correlation characteristics of the fire scene heat distribution and the three-dimensional space can be captured, and the intelligent detection of the human body target can be realized on the basis. In this way, the problem that heat radiation information and space structure information are separated in a traditional method can be effectively solved, the information utilization rate is increased, and the accuracy and efficiency of human body target recognition are enhanced.

The invention discloses an efficient pulsating heat pipe air pre-heater gas stove, and relates to the technical field of gas stoves. The air pre-heater comprises an air pre-heater body, a pulsating heat pipe and an air supply pipeline, the pulsating heat pipe is embedded in an inner cavity of the air pre-heater body, and the bottom of the air pre-heater body communicates with the top of the air supply pipeline; the air pre-heater body comprises a heat insulation radiation cavity and an air pre-heating cavity. The heat transfer efficiency of the pulsating heat pipe is far higher than that of traditional metal heat conduction, heat of high-temperature flue gas can be rapidly absorbed, waste heat loss is reduced, the heat efficiency is improved, secondary air is heated through the air preheater, the temperature of the secondary air is increased, the combustion temperature is increased, gas combustion is more sufficient, emission of carbon monoxide and nitric oxide is reduced, and the energy-saving and environment-friendly effects are achieved. The pulsating heat pipe has the unique advantages of being small and exquisite in structure, flexible in arrangement and efficient in heat transfer, and the heat efficiency of the gas stove is effectively improved through the L-shaped pulsating heat pipe heat insulation air pre-heater structure.

The invention discloses a parallel U-Net-based dual-domain collaborative infrared and visible light image fusion method. The method comprises the following steps: firstly, extracting initial features of a source image by using dense connection blocks; then, parallel frequency domain branches and spatial domain branches are constructed, the frequency domain branches are combined with discrete wavelet transform and fast Fourier convolution to decompose and enhance multi-scale global frequency domain features, and the spatial domain branches capture long-distance spatial dependence with linear calculation complexity by using a convolutional layer and Mama based on a selective state space model; dynamic interaction and weighted fusion of double-domain information are realized through an adaptive feature fusion module; and finally, generating a fused image through an image reconstruction module. According to the method, the problems of high calculation overhead and video domain information negligence in the prior art are solved, and infrared heat radiation maintenance and visible light texture enhancement are effectively considered.

The invention provides an automatic classification method for multi-modal remote sensing data in a complex scene, belongs to the technical field of electrical digital data processing, and aims to realize matching of multispectral and thermal infrared image resolution through space down-sampling and perform degradation processing on a thermal infrared image to enhance model robustness. The multi-level feature vector construction comprises texture, edge, shape and spectral features, and a rich feature expression set is formed. A sliding window technology is adopted to construct a training data set, and a deep convolutional neural network combining a multi-scale feature extraction module and an attention mechanism is designed. A temperature radiation balance equation is introduced to establish physical correlation between ground object thermal radiation characteristics and spectral reflectivity, and feature weight distribution is optimized. And the fusion classification model training adopts a cross entropy and structural similarity loss function, and a classification result is evaluated through indexes such as overall precision and a Kappa coefficient, so that high-precision classification of the multi-modal remote sensing data in a complex scene is realized.

The invention discloses an infrared and visible light dynamic temperature measurement method based on multispectral fusion. The method specifically comprises the following steps: S1, synchronously acquiring infrared thermal radiation data and visible light image data through a multi-modal data synchronous acquisition module; s2, performing feature matching and region segmentation on the acquired data based on a multispectral data fusion module; s3, environment interference and heat conduction errors are corrected through a dynamic compensation algorithm module; s4, a visual temperature distribution diagram is generated based on the temperature field reconstruction module, and abnormal temperature early warning is triggered, the method is based on a transfer learning method, on the basis of an original task domain model, small sample transfer to a new task domain is achieved, the limitation of sample dependence is relieved, and the universal generalization of the model is improved.

The invention provides a crystal growth device and a crystal growth method, and solves the technical problems of low wafer utilization rate, low crystal growth speed, low efficiency, poor uniformity and the like in the existing chip manufacturing process. According to the invention, a traditional cylindrical ampoule structure is abandoned, and the annular ampoule design is innovatively adopted, so that the crystal grows into an inner hollow cylinder shape which is highly matched with the specification of a target wafer; the heater is arranged on the inner side of the ampoule, a traditional outer side heating mode is replaced, and heat is intensively acted on crystals in cooperation with an adjusting center of a heat preservation material during crystal growth, so that heat loss is reduced; the periphery of the heater is made of heat insulation materials, heat radiation leakage is effectively restrained, meanwhile, the ampoule supporting structure is adjusted, and the whole device is simple, low in cost and light in weight.

The invention relates to the technical field of photoelectric detection and computer vision, and particularly discloses an infrared-based ground-to-air unmanned aerial vehicle detection and tracking method, which comprises the following steps: acquiring an infrared image sequence of a target airspace, dynamically adjusting the integral time and gain parameters of an infrared image by adopting a self-adaptive gain control algorithm based on a scene temperature histogram, and obtaining a target image sequence; generating an infrared image with enhanced thermal radiation characteristics; carrying out multi-level feature fusion detection on the infrared image by adopting a YOLOv5 improved multi-level global feature fusion network, and generating a saliency map containing the thermal features of the unmanned aerial vehicle rotor; according to the invention, by combining the infrared imaging technology, the improved YOLOv5 multi-level global feature fusion network and the improved BotSort algorithm, the detection precision and tracking stability of the low-altitude small unmanned aerial vehicle are effectively improved; the image quality is optimized through a self-adaptive gain control algorithm, the thermal radiation characteristic of the unmanned aerial vehicle is remarkably enhanced, and the failure problem caused by environmental interference in the traditional technology is avoided.

The invention provides an intelligent pod control method and system for an unmanned aerial vehicle. According to the method, multiple frames of thermal radiation images are obtained through an infrared imaging module of an unmanned aerial vehicle pod, a dynamic temperature field atlas is generated through heat source decoupling, and spatial relevance between heat sources is analyzed through an atlas neural network. Damping torque matched with wind disturbance is generated based on the temperature gradient vector, filtering parameters of the magnetofluid holder are optimized, and meanwhile the interference intensity between energy transmission paths is calibrated. A threat propagation path is generated by combining thermal diffusion characteristics, and the pod deflection angle is dynamically adjusted, so that the center of an optical view field is synchronized with the threat centroid, and accurate tracking and anti-interference control are realized. The method is used for intelligent pod control of the unmanned aerial vehicle. Through intelligent heat source analysis and adaptive adjustment, accurate and stable tracking of a threat target by the unmanned aerial vehicle pod is realized.

The invention relates to the related technical field of warm-keeping fabrics, in particular to a hollow warm-keeping yarn fabric which is formed by weaving hollow fibers in a staggered plaid structure, the staggered plaid structure is formed by interweaving warp yarns and weft yarns in a spiral winding mode, and micro air chambers are formed at the interweaving points of the warp yarns and the weft yarns. The hollow fiber comprises a core layer and a sheath layer, the core layer is of a plum blossom petal-shaped multi-cavity structure formed by ultra-high molecular weight polyethylene, cavities are separated through radial connecting bridges, and the sheath layer sequentially comprises a heat conduction enhancing layer, an infrared reflecting layer and a dynamic temperature adjusting layer from inside to outside. Dynamic heat and humidity collaborative management, intelligent temperature response, radiation heat management and structural stability are effectively improved, the heat retention property and moisture permeability of the fabric are improved, self-adaptive adjustment can be achieved according to the body temperature of the human body, the heat radiation transmission efficiency is enhanced, the super-hydrophobic interface modification and covalent bonding technology is adopted, and the thermal radiation performance of the fabric is improved. And the functional layer can still keep high bonding strength after being washed repeatedly.