706 results about "Thermal infrared" patented technology

The invention discloses a multi-modal visual fusion complex scene small target detection tracking method and system, and relates to the technical field of unmanned aerial vehicle target tracking, and the method comprises the steps: employing a visible light camera, an infrared thermal imager and a laser radar sensor which are carried on an unmanned aerial vehicle platform, and synchronously collecting RGB images, thermal infrared images and point cloud data; the consistency of the multi-modal data is ensured through data preprocessing and space-time alignment; constructing a lightweight double-branch network to extract multi-scale features, generating a fusion feature map by adopting adaptive weighted fusion, and generating depth information by utilizing point cloud to assist in scale estimation; a small target detection head is designed based on the fusion feature map, and precise detection is realized in combination with a feature pyramid network, adaptive scale prediction and a context awareness suppression mechanism; furthermore, through multi-mode cooperative tracking, including target association, spatio-temporal context modeling, trajectory prediction and a re-detection mechanism, tracking continuity is ensured.

The invention discloses a multi-source image data fusion-based fine decoration air crack seepage quality problem detection method and device, and solves the technical problem of how to carry out comprehensive, high-precision and intelligent detection on the fine decoration surface air crack seepage quality problem. Comprising the following steps: 1) receiving visible light image data, thermal infrared image data and three-dimensional laser point cloud data of a target refined decoration surface acquired from visible light acquisition equipment, thermal infrared imaging equipment and three-dimensional laser scanning equipment respectively; 2) carrying out feature extraction on the visible light image data, the thermal infrared image data and the three-dimensional laser point cloud data; 3) obtaining point cloud projection coordinates, and then performing association fusion on the first two-dimensional feature and the second two-dimensional feature with corresponding three-dimensional features to generate fusion point cloud data containing multi-source features; and 4) based on the fused point cloud data, carrying out defect classification identification and spatial positioning to obtain a detection result. And comprehensive and high-precision detection of the quality problem of air crack seepage of the finely-decorated surface is realized.

The invention discloses a power distribution equipment on-line monitoring system based on multi-modal data fusion, and relates to the field of power distribution equipment management, and the system comprises a sensing module which is used for collecting an electrical signal, a thermal infrared signal, a mechanical vibration signal and an acoustic signal generated in the operation process of power distribution equipment through a multi-type sensing channel, converting the collected various signals into processable equipment state original data to form an equipment operation state original data set; according to the invention, through accurate acquisition of multi-dimensional signals, combination of space mapping and time delay compensation, data quality is optimized, the reliability of original information is ensured, key features are extracted according to working conditions, subtle state changes are captured by means of temperature field analysis and a variable-resolution spectrum technology, the comprehensiveness, accuracy and response timeliness of equipment operation monitoring are effectively improved, and the real-time performance of equipment operation monitoring is improved. Misjudgment and missed judgment are reduced, and fault risks are avoided in advance.

The invention discloses a soil water and salt dynamic monitoring and quality evaluation method based on multispectral remote sensing, and relates to the field of geological monitoring, and the method comprises the steps: carrying out the scattering deviation correction and roughness correction of an observation spectrum through a satellite remote sensing image, an unmanned aerial vehicle multispectral image, a ground sample and meteorological driving data; the soil intrinsic reflectivity, the vegetation coverage component and the salt crusting component are obtained; a water-salt inversion model is established by combining thermal infrared and red edge wave band information, and multi-temporal soil volumetric moisture content and surface salinity index are inverted; by introducing meteorological conditions and vegetation dynamic characteristics, a water-salt coupling partial differential equation and a graph space-time constraint model are constructed, and continuous space-time distribution of soil water content and salinity is obtained; extracting salinity, moisture, vegetation response and soil health indexes, establishing a soil quality comprehensive evaluation model, and outputting high-risk plaques and a treatment priority sequence. The method realizes dynamic monitoring and quality grading evaluation of soil water and salt, and is suitable for saline-alkali soil treatment and ecological restoration.

The invention relates to the technical field of geological disaster detection, in particular to an unmanned aerial vehicle multi-sensor image fusion slope geological disaster detection system which comprises a data acquisition module, a manifold registration module, a feature fusion module, a weight optimization module, a fusion execution module, a disaster detection module and the like. RGB images, thermal infrared images and laser point cloud data of a slope are collected through an unmanned aerial vehicle, the surface of the slope is modeled as a Riemannian manifold, and high-precision space registration of heterogeneous data is achieved; constructing a feature manifold based on a manifold learning method, and extracting and fusing multi-scale features; evaluating the information amount of different areas by adopting a differential entropy theory, and generating a self-adaptive weight distribution diagram; performing weighted fusion on the registered multi-source data to generate a fused image; geological disaster features such as cracks, abnormal vegetation and water seepage points on the surface of the slope are recognized based on the fused image, and high-precision recognition and early warning of the geological disaster of the slope are achieved.

The invention discloses a wildlife detection method fusing an unmanned aerial vehicle thermal infrared image and a visible light image, and belongs to the field of small target wildlife identification, and the method comprises the following steps: S1, obtaining a preprocessed TIR-RGB image pair set; s2, an FDM-YOLO double-source target detection model improved based on YOLOv81 is constructed, and the improved FDM-YOLO double-source target detection model is trained based on the preprocessed TIR-RGB image pair set obtained in the step S1; and S3, inputting an image acquired in real time into the improved FDM-YOLO double-source target detection model trained in the step S2, and outputting a wild animal detection result. By adopting the wild animal detection method fusing the thermal infrared image and the visible light image of the unmanned aerial vehicle, high-precision, real-time and robust detection of a small target of a wild animal in a complex field environment is realized by improving the FDM-YOLO model.

The invention relates to the technical field of vehicle image recognition, and discloses a multi-modal data enhanced vehicle recognition method and system based on a generative adversarial network, and the method comprises the steps: collecting vehicle multi-modal data (a visible light image, a thermal infrared image and three-dimensional laser point cloud data), and constructing a vehicle multi-modal data set; performing preprocessing and feature alignment on the data set to obtain standardized multi-modal data; constructing a cross-modal generator based on an adaptive attention mechanism, learning inter-modal feature association through a dynamic weight distribution module, and generating vehicle feature fusion data; designing a dual discriminator structure consisting of a perception consistency discriminator and a semantic fidelity discriminator, and optimizing the generator by adopting an alternate adversarial training strategy; generating a supplementary data sample for the complex scene by using the optimized generator, and constructing an enhanced data set; and constructing a multi-mode cooperative vehicle identification model based on the enhanced data set, and realizing high-precision vehicle attribute identification.

The invention relates to the technical field of remote sensing, and discloses a forest land health state analysis method and system based on multi-source remote sensing image analysis. The system comprises a multi-source remote sensing acquisition module, a feature extraction and fusion module, a health assessment module, a traceability analysis module, a strategy matching module, a visual reconstruction module, an early warning decision module and an execution feedback module, and constructs a multi-modal forest land observation data set by fusing multi-source remote sensing data of multispectrum, hyperspectrum, radar and thermal infrared. The comprehensive extraction of multi-dimensional information such as vegetation coverage, canopy biochemical characteristics, under-forest structures and surface thermal environments is realized, the limitation of single data source analysis is overcome, and the comprehensiveness and accuracy of forest land health condition evaluation are improved; through dynamic comparison of multi-stage remote sensing images and health risk level mapping, early identification and early warning of forest growth abnormity, degeneration trend and pest and disease risk are realized.

The invention relates to the technical field of water environment monitoring, and discloses a sewage detection and traceability system based on multi-source data fusion. The system comprises an unmanned aerial vehicle data acquisition module, an edge end preprocessing module, a cloud data fusion and modeling module, a traceability decision module and a closed-loop optimization module, and all the modules work cooperatively to realize sewage detection and traceability full-process automation. Hyperspectral, thermal infrared, LiDAR and meteorological data are collected in an integrated mode through a multi-source sensor, pollution area identification, pollutant concentration quantification, sewage draining exit positioning and pollution diffusion path tracing are accurately completed through edge end preprocessing and cloud deep fusion modeling, a detection strategy is dynamically adjusted through a closed-loop optimization mechanism, and the detection accuracy is improved. And high precision, high efficiency and real-time response of sewage detection under complex terrains are realized.

The invention discloses a house structure safety edge visual monitoring method and device, equipment and a storage medium, and relates to the technical field of building safety monitoring, and the method comprises the steps: collecting multi-modal data which comprises a visible light video stream, a thermal infrared video stream and point cloud data; performing parameter synchronous extraction processing on the multi-modal data to obtain a first displacement sequence, a first inclination angle, a first crack width and a first hollowing mask; packaging the first displacement sequence, the first inclination angle, the first crack width and the first hollowing mask to obtain a first feature data packet; and carrying out structured numerical compression on the first feature data packet to obtain a compression vector, and sending the compression vector to a cloud platform, so that the cloud platform updates the digital twin model in real time according to the first feature data packet and triggers an early warning mechanism to complete safety monitoring of the house structure. High-precision, non-contact and real-time monitoring of multiple parameters such as inclination, settlement, vibration, cracks and hollowing of a building structure is realized.

The invention provides a YOLOv7-based photovoltaic module fault detection method and a YOLOv7-based photovoltaic module fault detection device, and relates to the technical field of target detection. According to the method, a thermal infrared and temperature information fusion module is introduced at the front end of a network, a thermal infrared image and a pixel-level temperature matrix thereof are fused through alignment, coding and attention mechanisms, and the characterization capability of multi-modal features is enhanced. A shallow layer-deep layer information aggregation module is introduced into the neck network, and the context perception and feature discrimination ability of the model to a multi-scale small target is improved. A global context sensing module is introduced in front of a detection head, a directional channel context branch and a query-key value branch of the global context sensing module capture directional global dependence and spatial context relations respectively, and global modulation of features is achieved. According to the method, the detection precision and robustness of various faults such as faults, fragmentation, hot spots and shielding of the photovoltaic module junction box are remarkably improved, the weak and small target positioning capability is optimized, the method is suitable for being deployed on mobile or embedded equipment, and efficient and intelligent inspection of a photovoltaic power station is achieved.

The invention relates to the technical field of image quality optimization, and discloses a hunting camera imaging quality optimization method based on multimode data fusion. The method comprises the following steps: acquiring a visible light image, a thermal infrared image, a laser ranging point cloud and inertial measurement unit data, and carrying out space-time alignment and registration to form synchronous multimode data. A controllable imaging parameter set and scene context description information are separated by performing joint feature extraction on synchronous data. And for each parameter to be optimized, the system retrieves a plurality of candidate strategies from the imaging optimization knowledge base by taking the current value and the scene context as query conditions, selects an optimal strategy through fusion decision calculation, and finally generates and executes a global imaging parameter optimization instruction set to control a camera to complete image capture. According to the method, intelligent optimization of imaging parameters based on depth scene understanding is realized, and the image quality and adaptability of the hunting camera in a complex environment are improved.

The invention provides a multi-platform satellite thermal infrared hyperspectral atmospheric ammonia monitoring method and system, and belongs to the technical field of satellite remote sensing. The method comprises the following steps: collecting thermal infrared hyperspectral data, atmospheric state parameters, earth surface parameters and instrument characteristic parameters of a stationary satellite or a polar orbit satellite; based on a thermal infrared radiation transmission physical mechanism, inputting the preprocessed standardized parameters into a fast radiation transmission forward model to obtain a simulated spectrum consistent with the actually measured data format of a stationary satellite or a polar orbit satellite; constructing a cost function containing observation error constraint and NH3 prior information constraint on the basis of the simulated spectrum and the actually measured spectrum in combination with an optimization estimation theory, solving a minimum value of the cost function by adopting a Levenberg-Marquardt iterative algorithm, and performing inversion to obtain an atmospheric ammonia concentration profile; and performing quality control and column concentration conversion on an inversion result, and verifying the precision by combining multi-source observation data to obtain an atmospheric ammonia concentration data set.

The invention relates to the technical field of production environment monitoring, in particular to a high-temperature and high-brightness production environment monitoring system based on deep learning, which is characterized in that visible light and thermal infrared images in a high-temperature and high-brightness environment are acquired through cooperation of an industrial camera and an infrared camera, space registration and time synchronization are carried out, and accurate alignment of multi-modal data is ensured. Extracting a highlight overflow mask, a dark part texture guide map and color cast estimation, fusing to generate a joint perception feature tensor, inputting the joint perception feature tensor into a model with a cross-modal attention mechanism and time sequence feature modeling, recognizing a potential distortion region in advance, improving the system robustness, outputting an imaging state evaluation result and an imaging parameter reference value, and improving the imaging quality. And furthermore, a camera adjustment parameter is generated through a strategy network, an image acquisition process is dynamically optimized, a prediction control closed loop is constructed, and adaptive maintenance and optimization of image quality in a complex environment are realized.

The invention relates to an unmanned aerial vehicle target tracking method and system based on multi-modal perception and end-to-end, and the method comprises the steps: predicting the future motion track of an unmanned aerial vehicle through the multi-modal fusion of an RGB image, a thermal infrared image and a laser radar point cloud, combining the historical position information of a target, and employing an end-to-end deep learning network. The network structure comprises a trajectory anchor point prediction branch and a target position regression branch, wherein the trajectory anchor point prediction branch outputs a trajectory existence probability, a trajectory offset and a trajectory cost score; and the position regression branch directly predicts the three-dimensional coordinates of the target. And generating the flight path of the unmanned aerial vehicle from the terminal to the terminal. And directly mapping the trajectory points into flight control executable low-level control instructions, including position, speed and attitude instructions, and directly executing the instructions by a flight control system to realize autonomous tracking of the target. The method shows high robustness and accuracy in weak light, shielding and complex environments, and is suitable for various application scenes such as electric power inspection, disaster rescue, security monitoring and automatic driving coordination.

The invention provides a shallow coal seam hidden fire source full-field monitoring and early warning method and system, and belongs to the technical field of coal spontaneous combustion fire monitoring and early warning, and the method comprises the steps: S1, obtaining thermal infrared image and visible light image data; s2, eliminating redundant thermal imaging frames and fuzzy thermal imaging frames; s3, obtaining a preliminary surface temperature field distribution map; s4, an open fire source and a suspicious area are distinguished, and positions are marked; s5, acquiring surface temperature gradient distribution and indication gas concentration data of the suspicious area, and acquiring surface temperature data and underground temperature data of the verification point, indication gas data escaping from the detection hole and radioactive radon content data; s6, establishing identification indexes of the dark fire source; s7, establishing a dark fire source grading risk standard; and S8, outputting an early warning result. According to the method, full-time, full-field and three-dimensional monitoring is realized, the accuracy and the reliability are improved, intelligent graded early warning and decision support are realized, and the environmental adaptability and the automation level are enhanced.

The invention relates to the technical field of building disease detection, in particular to an urban building disease detection method and device, electronic equipment and a storage medium. Multi-modal image data formed by original visible light and thermal infrared image data is obtained, and an original thermal infrared image is subjected to geometric correction; calculating a mapping relation with an original visible light image so as to complete pixel-level registration, obtaining target multi-modal image data, inputting the target multi-modal image data into a hierarchical deep learning recognition model, recognizing building disease information, then performing three-dimensional space mapping, generating a building three-dimensional mesh model containing disease three-dimensional space setting coordinates, and finally performing three-dimensional mesh modeling. And then calculating a relationship between a model surface grid vertex and a disease point cloud density, generating a disease distribution thermodynamic diagram, analyzing disease aggregation characteristics in multiple dimensions according to the thermodynamic diagram, and quantitatively analyzing spatial correlation between the disease and a building construction node in combination with building component information. According to the invention, the urban building disease detection efficiency and precision are improved.

The invention provides a calibration method suitable for a multi-view heterogeneous imaging system, a medium and equipment. The method comprises the following steps: S1, acquiring a multi-modal calibration template image set by each camera of a multi-view heterogeneous imaging system; performing preprocessing by using guide filtering to obtain a filtering result image set of the multi-modal calibration template; s2, carrying out frame mean processing on the filtering result image set of the visible light calibration template; s3, detecting a hot spot extreme value center point of the hot spot of the filtering result image set of the thermal infrared calibration template by using a search maximum value algorithm; s4, determining an accurate center point of the hot spot by using a mean smoothing algorithm; s5, performing grid processing on the hot spot accurate center point set, and reconstructing a thermal infrared checkerboard calibration image set; and S6, calibrating internal and external parameters of each camera of the multi-view heterogeneous imaging system by using a Zhang Zhengyou calibration method. According to the method, calibration of an existing thermal infrared camera and an existing visible camera can be achieved, and then the problem of texture information alignment between heterogeneous images is solved.

The invention discloses an automatic identification method for hot spot defects of a photovoltaic module based on thermal infrared imaging, relates to the technical field of defect identification, and aims to improve the environmental adaptation precision and the multi-frequency thermal wave penetration coverage dimension in the detection process of the hot spot defects of the photovoltaic module, realize efficient and accurate multi-frequency excitation parameter configuration and environmental thermal noise suppression and improve the detection accuracy of the hot spot defects of the photovoltaic module. The defect identification accuracy and the fault diagnosis reliability level in the operation and maintenance process of the photovoltaic module are remarkably improved, the situation that response of fixed excitation parameter setting to actual thermophysical property changes is insufficient is effectively prevented, depth deviation and defect misjudgment caused by experience judgment are avoided, the pertinence and defect identification effect of final heat source distribution field reconstruction are effectively improved, and the method is suitable for large-scale popularization and application. And determining the packaging layer to which the defect influencing the performance of the photovoltaic module belongs, and ensuring that the defect layering identification measure is highly matched with the actual heat source depth distribution risk.

The invention provides a real-time video monitoring intelligent analysis system based on deep learning, and relates to the technical field of computers, and the system comprises a video collection unit which is used for obtaining a real-time monitoring video stream to be analyzed, and extracting a target video frame sequence from the real-time monitoring video stream; the scene analysis unit is used for processing the target video frame sequence by using a pre-trained scene analysis model to obtain a dynamic object mask and a scene semantic graph corresponding to the real-time monitoring video stream; the acquisition unit is used for acquiring thermal infrared characteristics and dynamic environment variable information of a monitoring area corresponding to the real-time monitoring video stream; and the semantic segmentation unit is used for inputting the dynamic object mask, the scene semantic graph, the thermal infrared features and the dynamic environment variable information into a pre-trained semantic segmentation model to obtain a semantic segmentation result output by the semantic segmentation model. By applying the method provided by the invention, the monitoring video can be accurately analyzed.

The invention discloses a pig excretion and diarrhea behavior intelligent identification early warning method and system, and the method comprises the steps: collecting a video stream of pig activities in a pig house through a thermal infrared camera which is installed in a top view manner, and carrying out the Mosaic data enhancement preprocessing of a video image; reasoning the preprocessed video single frame by using a YOLOv10 target detection model, and generating a space attention mask for the excrement area; based on the space attention mask, background noise is suppressed, and spatio-temporal features related to excretion behaviors are enhanced; the enhanced spatial-temporal features are input into an ActionMama network based on a state space model for time sequence action positioning, and an identification result containing urination and defecation behavior types and action starting and ending time is output; and according to the excretion frequency, the single excretion duration and the excretion position space information in the identification result, generating a pig diarrhea behavior early warning signal. According to the embodiment of the invention, the problems of high omission ratio and early warning lag can be effectively solved, and the intelligent level and timeliness of pig health management are improved.

The invention discloses a gas leakage detection method. The method comprises the following steps: S10, carrying out denoising and image enhancement on an acquired visible light image and an acquired thermal infrared image; s20, carrying out image feature point matching; s30, fusing the visible light image and the thermal infrared image after registration; and S40, gas leakage detection based on the improved YOLOv8 framework. According to the invention, thermal imaging, multispectral and visible light imaging multi-source fusion technology is adopted, so that the problems of efficient detection and accurate identification of multiple types of gases in a broadband range are solved.

A strip mine unmanned vehicle advancing obstacle detection method based on thermal infrared and visible light fusion comprises the following steps: firstly, acquiring advancing obstacle image data in two modes in a strip mine area by adopting two visual sensors, namely a thermal infrared camera and a visible light camera; secondly, realizing alignment of the two types of images in space and time by using a method for matching local features between the images based on a deep neural network; and inputting the registered image into a double-branch network to extract features, and based on the obtained multi-scale image features, obtaining position information and a classification result of a detection target by using a positioning classification model. According to the method, feature extraction is carried out on two kinds of modal data through the double-branch network, complementation is realized through cross-modal multi-level feature fusion, feature fusion is realized in the middle stage, the unmanned vehicle can accurately recognize the advancing obstacles on the road in the complex environment of low visibility, low illumination and the like of the strip mine area, and the accuracy of the road obstacle recognition is improved. And the safety and the high efficiency of unmanned mine car operation are greatly improved.

The invention provides an unmanned aerial vehicle biological control method and system based on real-time visual perception and accurate delivery decision. The method comprises the following steps: collecting farmland environment data through multiple sensors, and performing low-illumination enhancement on a visible light image; utilizing an improved target detection network to synchronously identify diseases and insect pests and position a putting point; the two-dimensional image, thermal infrared and three-dimensional point cloud features are fused to realize accurate positioning of the target; a visual language model is introduced for cross-modal reasoning, target disambiguation and priority analysis are completed in combination with a task instruction, and a collision-free delivery sequence is generated; and finally, planning an optimal flight path, and realizing precise drug delivery through trajectory optimization and closed-loop control. The intelligent level and the operation precision of pest control in a complex farmland environment are improved.

The invention discloses an airship type unmanned aerial vehicle inspection system and inspection method, and belongs to the field of inspection unmanned aerial vehicles. The system comprises a laser radar, an image acquisition device, an airship capsule filled with helium, a standby safety airbag, a communication module and a ground control center, in the method, the ground control center sets an inspection path and issues the inspection path, and the unmanned aerial vehicle flies according to a preset path. During fault detection, the high-definition camera collects images to recognize line cracks and broken strands, the thermal infrared imager monitors the joint temperature, the gas sensor detects abnormal gas, and multi-source data fusion assists in defect positioning. The routing inspection takes a starting point-terminal point connecting line of a power transmission line as a reference, identifies main obstacles and surrounding nodes to perform global planning, performs key routing inspection on a risk area in combination with historical data, and initializes and guides a flight direction through a Q value to reduce invalid exploration. The four-rotor unmanned aerial vehicle solves the problems of short flight time and poor stability of a four-rotor unmanned aerial vehicle, improves the inspection stability and cruising ability, and improves the inspection efficiency of a power transmission line and the reliability of a power system.

The invention discloses an intelligent monitoring and evaluation method and system for newly-cultivated land, and relates to the field of intelligent agriculture. The method comprises the steps of planning an unmanned aerial vehicle route and a ground sampling grid based on newly-cultivated land boundaries and topographic data; multispectral and thermal infrared images are obtained through remote sensing of the unmanned aerial vehicle, and spectral data and soil samples are synchronously collected on the ground; performing laboratory analysis on the soil samples to obtain soil physical and chemical indexes, and associating the soil physical and chemical indexes with remote sensing spectral characteristics to construct a training sample set; based on the training sample set, remote sensing features are fused, and a soil physicochemical index spatial distribution diagram is obtained through machine learning model inversion; carrying out quality grade classification and obstacle type diagnosis by combining the soil physical and chemical indexes, the crop growth time sequence and the planting historical information; and based on classification and diagnosis results, combining an agricultural knowledge rule base to form agricultural management suggestions and generate a variable operation prescription map to guide accurate operation. Through air-ground cooperative monitoring and soil quality evaluation, the farmland quality monitoring precision is improved.

The invention discloses a forestry restoration vegetation state identification method and system based on image identification. The method comprises the following steps: obtaining a standard image sequence; segmenting the visible light image through an improved SegFormer network to obtain vegetation areas of different scales, and calculating vegetation canopy temperature distribution characteristics based on the thermal infrared image; extracting vegetation index features based on the multispectral image to obtain multi-scale feature data; according to the multi-scale feature data, utilizing an improved GAT model to process a vegetation spatial relationship graph, learning a spatial dependency relationship between vegetation areas through a multi-head attention mechanism, and generating a vegetation feature vector containing spatial information; and classifying the vegetation states by using an improved multi-scale fusion classifier in combination with the vegetation feature vectors, outputting a vegetation recovery index, and classifying the forestry restoration vegetation states according to the vegetation recovery index. The whole forestry restoration monitoring process is automatic, the monitoring efficiency is improved, and the labor cost is greatly reduced.

The invention discloses a solid waste water content prediction system and method based on an infrared thermal imager. The temperature field of the solid waste on the conveyor belt in the natural convection and forced convection moisture evaporation process is monitored and compared in real time through the thermal infrared imager, and the moisture content of the solid waste can be accurately predicted in combination with data processing, environmental parameter correction and prediction of a regression equation. Compared with a traditional sampling detection method, the method has the advantages of being high in real-time performance, non-contact, simple in equipment, good in economical efficiency and the like, can adapt to a complex industrial field environment, and provides a new technical means for intelligent and refined control over waste incineration. The system is simple in structure, high in reliability, good in detection precision and capable of achieving real-time prediction of the water content of the solid waste entering the furnace.

The invention provides an insulator defect identification method based on cross-modal data fusion. The insulator defect identification method comprises the following steps: acquiring and preprocessing an insulator visible light image, a thermal infrared image and point cloud data which are synchronously acquired; projecting all points in the point cloud to obtain a projection image and a projection mapping matrix; registering the visible light image and the thermal infrared image with the projection image to obtain a corresponding affine transformation matrix, and constructing a shielding matrix for shielding the background according to the projection image; performing feature extraction on the pre-processed visible light image, thermal infrared image and point cloud data to respectively obtain a texture feature map, a temperature feature map and a geometric feature map; fusing the texture feature map, the temperature feature map and the geometric feature map according to the shielding matrix and the affine transformation matrix to obtain cross-modal fusion features; and the cross-modal fusion features are used to discriminate and position insulator defects. According to the method, the problem of leak detection of insulator defects in different scenes by a traditional single-mode method can be solved.

The invention discloses a dam infrared thermal imaging leakage intelligent identification method fused with dynamic frame difference, and the method comprises the steps: building a frame difference graph based on an improved OTSU algorithm through a thermal infrared image sequence, so as to enhance the temperature micro-change perception capability, and achieving the high-precision identification of a leakage abnormal region through combining with a YOLOv8 model; meanwhile, the area of an abnormal region in a frame difference image sequence is extracted, the leakage evolution process is dynamically described, and a quantitative judgment mechanism is constructed in combination with fitting of an area change trend and t test, so that the accuracy and robustness of leakage outlet recognition are improved. Compared with a traditional visible light detection means, the method has earlier response capacity under various complex working conditions, the misjudgment rate and the missed judgment rate in single-frame recognition are remarkably reduced, and powerful technical support and engineering reference are provided for intelligent recognition and safety management of earth and rockfill dam leakage.