348 results about "Model complexity" patented technology

The invention discloses a modulation and signal category identification method based on multi-scale attention and residual error, and relates to the technical field of signal type and modulation mode identification, and the method comprises the steps: obtaining signal data sets under different signal types and modulation modes, and dividing the signal data sets into a training set and a verification set; constructing an end-to-end deep learning model based on an input preprocessing module, a shared convolutional feature extraction module, a multi-task branch module and a joint loss optimization module; the shared convolution feature extraction module comprises a channel expansion convolution layer, a multi-scale attention residual module and a down-sampling module; an end-to-end deep learning model is trained; and inputting the data of the to-be-tested signal into the model to obtain the signal type and the modulation mode of the to-be-tested signal, and through end-to-end deep learning model processing, the problems of model redundancy, computing resource waste, insufficient inter-task information utilization and the like can be solved, and the model complexity and the training overhead are reduced while the identification accuracy is improved.

The invention discloses an industrial product surface defect detection method based on feature coupling, and the method comprises the steps: 1) constructing a four-stage backbone feature extraction network, and integrating a DPSC module to expand a receptive field, thereby achieving the gradual feature learning from local to global; 2) designing a multi-scale feature fusion network, realizing effective fusion of different scale features, and performing deep coupling on high-level semantic information and low-level detail information; 3) constructing a multi-branch detection head to realize full-scale coverage; and 4) performing end-to-end training optimization: calculating a weight importance score by applying an LAMP pruning strategy, deleting redundant parameters, and remarkably reducing the model complexity and the calculation cost while keeping the detection performance. According to the method, through a global-local feature coupling mechanism, the technical problems that in industrial product surface defect detection, the defects are highly similar to the background, and the scale change is large are effectively solved, and high-precision and high-efficiency defect detection is achieved.

The invention discloses an efficient target detection method in a foggy environment, and relates to the technical field of target detection. According to the method, a lightweight foggy day target detection model is established and called DF-DETR, a defogging module of a double-branch structure is designed through an edge enhancement module, and target features of a foggy day image are effectively captured; then, a dual convolution feature extraction module DualConv-Block is designed, so that feature extraction is enhanced, and meanwhile, the complexity and the calculation amount of the model are remarkably reduced; besides, an EAA attention mechanism is combined with an intra-scale feature interaction module to form an AIFI-EAA module, and the AIFI-EAA module is integrated into the hybrid encoder, so that the attention capability of the model on dense targets is improved, and missing detection and false detection are effectively reduced; finally, a dynamic sampling scale attention feature fusion module is designed, alignment of multi-scale features is achieved through dynamic up-sampling, the flexibility and robustness of feature expression are enhanced, and the fusion and expression ability of the multi-scale features is further optimized.

The invention relates to the technical field of cognitive impairment detection, and discloses a cognitive impairment early warning method and device based on an electroencephalogram micro state and an eye movement trajectory, and the method comprises the following steps: S1, data acquisition, S2, electroencephalogram preprocessing, S3, electroencephalogram feature extraction, S4, eye movement feature extraction, S5, feature fusion, and S6, early warning judgment. According to the method, through independent convolution branch of electroencephalogram and eye movement features, a receptive field is expanded by utilizing cavity convolution to capture multi-scale features, and long-distance dependence is modeled by a self-attention layer; after tensor splicing, time sequence information is dynamically fused through a gating cycle unit (GRU), and cross-modal time correlation is captured. The method has the advantages that the multi-modal feature hierarchical extraction and self-adaptive modeling capability is enhanced, the complementarity fusion efficiency is optimized, meanwhile, by means of cavity convolution sparse connection, self-attention parameter sharing and GRU lightweight design, the model complexity and the calculation efficiency are balanced, and efficient feature representation is provided for cognitive impairment early warning.

The invention discloses an SOP defect detection method based on lightweight multi-scale feature fusion, and the method specifically comprises the steps: obtaining an SOP defect image, and marking the defect image; a YOLO-DBS model is provided on the basis of the YOLOv8n; replacing a C2f module in a backbone network with a DCFB module, designing an efficient multi-scale feature fusion pyramid network BiFPN, and adding an SENetV2 module in an input layer of a detection head; training the improved algorithm model by adopting an SOP packaging chip surface defect image training set; and transmitting a defect image test set into the trained model, recording a detection result and evaluating the performance of the model. According to the method, the balance between the precision and the model complexity is realized while the high detection precision is maintained.

The invention discloses a power adaptive digital pre-distortion method, system and device based on sparse GRU and a medium. The method comprises the steps that input and output signals under different powers are collected, a composite feature vector is constructed through amplitude normalization and phase alignment, and a pre-distortion training target is generated in combination with indirect learning; constructing a sparse GRU neural network, introducing L1 regularization constraint, and obtaining a sparse pre-distortion model through joint optimization of mean square error and sparse constraint; partial weight updating is realized based on power grading, and weight fusion output is carried out during power interval switching so as to complete power adaptive optimization; pruning and compressing the sparse GRU model and then deploying the sparse GRU model in a pre-distortion module to compensate the nonlinearity of the power amplifier; according to the method, the model complexity is reduced through rarefaction, the dynamic working condition stability is improved through a power adaptive mechanism, pruning compression adapts to low-power-consumption hardware, high precision, low complexity and adaptive capacity are considered, and the method is suitable for the low-power-consumption and high-performance requirements of a broadband wireless communication system.

The invention relates to the technical field of remote sensing image processing, in particular to a multi-modal target detection method and device based on attention self-modulation fusion, and the method comprises the steps: extracting visible light modal shallow layer features of a visible light modal image, and extracting infrared modal shallow layer features of an infrared modal image; carrying out fusion processing on the visible light modal shallow layer features and the infrared modal shallow layer features to obtain target fusion features, and carrying out feature extraction to obtain deep semantic features; and performing multi-scale feature aggregation on the deep semantic feature, performing feature enhancement on a feature aggregation result based on a preset feature enhancement mechanism to obtain a multi-scale fusion feature, and detecting the multi-scale fusion feature to obtain a detection result. Therefore, the problems of high calculation cost and high model complexity of multi-modal target detection in the background technology are solved, and efficient and lightweight multi-modal target detection is realized.

The invention discloses a water supply system scheduling optimization method and device, electronic equipment and a storage medium, and relates to the field of intelligent scheduling of water supply systems. The method comprises the steps of collecting and preprocessing multi-dimensional data to obtain a data set; the pressure data is analyzed from the space-time dimension, and the unfavorable points and the pressure requirements thereof are accurately identified; the method comprises the following steps: constructing a water volume prediction model by adopting a time sequence model, and constructing a total water head difference prediction model by adopting a Light GBM gradient boosting tree in combination with a MultiOutputRegressor multi-output regression framework; constructing a minimum total water production cost objective function based on a prediction result, and outputting an optimal scheduling scheme by combining water volume and pressure constraint iterative optimization; and establishing a model updating mechanism to ensure dynamic adaptation of the strategy. According to the method, the problems of insufficient pressure guarantee, extensive cost control and weak model practicability and generalization ability are solved, the inherent contradiction that a traditional mechanism model is high in complexity and a pure data driving pressure prediction model is poor in generalization and lacks physical significance is overcome, and safe, stable and efficient intelligent technical support is provided for a water supply system.

The invention is suitable for the technical field of computer vision and deep learning, and provides a multi-scale feature fusion concrete defect detection method based on improved SAM, and the method comprises the steps: obtaining a concrete defect image data set; preprocessing the image data set and dividing the image data set into a training set, a verification set and a test set; the YOLOv9 is trained to automatically detect concrete defects; constructing an improved SAM model, replacing a prompt encoder of the SAM with YOLOv9 and edge detection, and modifying a mask encoder of the SAM; the training effect of the model is evaluated through the four indexes of the accuracy rate, the recall rate, the F1 value and the intersection-to-union ratio, and the improved SAM model is optimized according to the training effect. By improving the structure of the SAM, the detection capability of the model on small defects can be enhanced, and the detection accuracy and efficiency are improved. In addition, according to the method, the complexity of the model can be reduced, and the training efficiency and generalization ability of the model are improved.

The invention discloses a virtual space multi-person interaction synchronous control method oriented to an end-cloud collaborative architecture. The invention relates to a computer graphics and three-dimensional modeling technology, and discloses a cross-format lightweight and geometric consistency maintenance method based on a three-dimensional model. Through format-independent geometric representation and a self-adaptive lightweight strategy, efficient compression and precision maintenance of three-dimensional model cross-format conversion are realized. The method specifically comprises the following steps: performing format analysis and geometric feature extraction on an input model, and establishing a unified internal representation; adaptively selecting a multi-level LOD lightweight strategy based on the complexity of the model; the accuracy of key information is ensured through geometric feature keeping and topology consistency detection; the geometric consistency is dynamically maintained by combining error monitoring and an iterative correction mechanism; and generating a target format lightweight model and carrying out quality verification. According to the method, adaptive precision control, multi-level consistency maintenance and format irrelevant processing are combined, the model size and conversion errors are effectively reduced, and cross-platform compatibility and geometric fidelity are improved. The method can be widely applied to the fields of industrial design, game development, virtual reality and the like.

The invention discloses an apple leaf disease segmentation method based on a lightweight dual-path network, an apple leaf disease segmentation device based on the lightweight dual-path network, an apple leaf disease segmentation device and a computer readable storage medium. The problems that an existing disease segmentation method is high in model complexity and insufficient in multi-scale recognition capability are effectively solved. The lightweight encoder adopts a depth separable convolution and channel recombination technology, so that the parameter quantity and the calculation complexity are greatly reduced while the feature extraction capability is maintained, and the model can be deployed on edge equipment such as an unmanned aerial vehicle and a field robot. The enhanced cavity space pyramid pooling module constructs abundant multi-scale receptive fields through multi-branch parallel cavity convolution with different expansion rates, and can capture feature information of initial tiny disease spots and later fused disease spots at the same time.

The invention discloses a distributed anti-interference fault-tolerant control method and a distributed anti-interference fault-tolerant control system for a multi-six-rotor unmanned aerial vehicle attitude system. The control method comprises the following steps: constructing a multi-six-rotor unmanned aerial vehicle attitude model based on a multi-six-rotor unmanned aerial vehicle attitude system model and interference uncertainty; designing a disturbance observer which is used for estimating the degree of external disturbance and actuator faults; and based on the output of the multi-six-rotor unmanned aerial vehicle attitude model and the degree of external interference and actuator fault, constructing a Lyapunov function by using a backstepping recursion technology, and designing a distributed anti-interference fault-tolerant controller for generating a control output signal to the multi-six-rotor unmanned aerial vehicle attitude model. According to the method, the Lyapunov function is constructed, so that output signals of all followers and leaders are synchronous, and errors are converged. Meanwhile, the general approximation characteristic of the neural network is utilized, the nonlinear term and the unmodeled dynamic are approximated online, and the model complexity is reduced.

The invention relates to an EDSR (Enhanced Depth Super-Resolution) image super-resolution reconstruction method based on particle swarm optimization, and the method comprises the following steps of: (1) carrying out super-resolution reconstruction on an EDSR (Enhanced Depth Super-Resolution) image; the method comprises the following steps: firstly, inputting a low-resolution image data set as a training sample, defining an optimization space containing the number and stage of residual blocks, convolutional layer parameters, an attention module, an up-sampling mode and the like, initializing particle swarm optimization (PSO) parameters, and dynamically constructing a candidate network by particle position coding; a candidate network is dynamically constructed through particle position coding, and a residual block layer, a convolution layer, an attention module and an up-sampling module are sequentially configured. The candidate network is subjected to limited training, and individual and global optimal positions are updated through fitness function evaluation fusing PSNR and model complexity. And finally, a global optimal structure is selected for complete training for low-resolution image reconstruction, the detail reduction capability and the reasoning efficiency are remarkably improved, and a high-quality image is generated.

The invention discloses a multi-target prediction method, system and device for a financial time sequence and a storage medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: firstly obtaining financial time sequence data and auxiliary information, and carrying out the vector conversion and fusion to form a unified input representation; extracting features through a shared encoder, and generating a global feature vector; and inputting the data to a multi-task prediction output head to realize parallel prediction of the prediction tasks. According to the scheme, cross-task feature sharing is realized by using the shared encoder, the modeling collaboration is improved, and resource waste and prediction conflicts are avoided; through data fusion, the depiction capability of complex financial dynamics is enhanced; the generalization and robustness of the model are improved by adopting a lightweight output head, the method is suitable for diversified financial prediction scenes, and the prediction efficiency and accuracy are improved while the model complexity is reduced.

The invention discloses a lightweight identification method for hole diseases in a road, and the method comprises the steps: constructing a road B-Scan radar image data set which accords with a YOLO data set standard, and dividing the data set into a training set, a verification set and a test set; based on an improved YOLO11 target detection network, a training set is used for model training, a backbone network, a neck network and a head network are optimized, and a PConv module, an ADown module and an EMA attention mechanism are introduced to improve the calculation efficiency and precision. According to the method, the recognition accuracy of the road internal cavity disease image is remarkably improved, and meanwhile, the model complexity and the calculation overhead are reduced. The trained target identification model can efficiently process the internal cavity disease image of the to-be-detected road, and an accurate identification result is provided. Experiments show that the processing speed is greatly improved while high detection precision is kept, and an effective solution is provided for intelligent detection of the holes in the road.

The invention discloses a light-weight small target detection method and system for images shot by an unmanned aerial vehicle, and the method specifically comprises the steps: constructing a neural network architecture which comprises a backbone network, a feature aggregation network and a detection head; improvement of light weight and attention enhancement is implemented in the backbone network, and a multi-scale initial feature map is extracted; constructing a feature aggregation network Neck, performing cross-level fusion and refining processing on the multi-scale initial feature map, and outputting a refined feature map; a lightweight target detection head Head is constructed in combination with a large-kernel depth separable convolution module and a special decoupling head structure of a YOLOv11 network, and decoupling prediction is performed on the refined feature map; training is carried out by adopting a mixed loss function based on a normalized Wasserstein distance and modulated IoU, a trained lightweight network is obtained, and detection of a lightweight small target is realized. According to the invention, the complexity of the model is reduced, the detection speed is improved, the high detection precision is maintained, and the method is suitable for real-time detection tasks on an unmanned aerial vehicle resource limited platform.

The invention discloses a multi-view heterogeneous cascade non-stationary time sequence prediction method based on Mama improvement, and belongs to the technical field of time sequence analysis. The prediction method comprises the following steps: collecting and preprocessing time sequence data of a target domain; the time sequence data are stabilized and decomposed; the decomposed seasonal part is embedded from a univariate view angle and a multivariate view angle respectively; an embedding result is correspondingly input into a Mama encoder and a multi-granularity cascade Mama encoder decoder heterogeneous module for feature learning; performing stationarity correction on the features based on an autocorrelation matrix; and predicting the feature representation after stability correction and the decomposed trend part, adding prediction results, and carrying out inverse normalization to obtain a final prediction result. The method provided by the invention solves the technical problem that the trend and periodicity of dynamic evolution in data are difficult to capture when an existing method faces a non-stationary time sequence, and also solves the problems that an existing model is high in complexity and low in prediction accuracy.

The invention provides an inland ship target detection method and system, and relates to the technical field of ship image recognition. The method comprises the following steps: establishing an inland ship target data set; performing data enhancement processing on the inland ship target data set; a BiFPN module is adopted to replace a PANet module in the YOLOv8 model; a SimAm attention module is introduced into the neck network; the detection head is improved by adopting RepConv convolution; the Shape-IoU is introduced to replace the CIoU to serve as a bounding box loss calculation function of the YOLOv8 model; and after the improved YOLOv8 model is obtained, an inland ship target detection model is obtained after inland ship target data set training, and target detection of the to-be-detected image is realized. The method can effectively balance the detection precision and the model complexity under the condition of ensuring the real-time performance, and has obvious advantages in small target detection and complex environments.

The invention discloses an embedded AI intelligent computing power architecture method, and particularly relates to the technical field of artificial intelligence processing architecture. Collecting a resource state parameter set R of the embedded device; obtaining a to-be-executed AI task set T, wherein each task comprises model complexity, real-time requirements, expected response duration and priority; constructing a computing power resource allocation evaluation function F based on R and T, and outputting a task scheduling priority score; allocating tasks to the embedded AI module according to the allocation scheme and executing reasoning; the resource state is dynamically monitored in the task running process, and if it is predicted that resources are about to be overloaded, a scheduling function F is triggered to reconstruct a resource allocation scheme; performing iterative optimization on weight parameters in the function F based on task history feedback; by means of the method and device, optimal adaptation of multi-task concurrent scheduling can be achieved under the condition that resources are limited, the computing power resource utilization rate, the response efficiency and the system stability are improved, and the method and device are suitable for various edge side AI scenes.

The invention belongs to the technical field of uncertainty probability characterization analysis, and discloses a thermoplastic composite material leading edge structure design allowable value probability characterization method and system under a small sample condition, and the method comprises the steps: defining a plurality of candidate probability distribution models; fitting each model based on the original sample data and calculating an AIC value and a BIC value; a dynamic weight factor alpha is calculated according to the sample size n, and then a hybrid information criterion HIC value is calculated; generating a plurality of sample sets through Bootstrap self-service sampling, recalculating the HIC value on each sample set, and counting the selected optimal frequency of each model; and determining an optimal probability distribution model according to the frequency, wherein the optimal probability distribution model is used for representing a design allowable value. According to the method, the dynamic weight factor alpha is introduced, AIC and BIC criteria are effectively unified, optimal balance between prediction precision and model complexity is achieved under the condition of small samples, and engineering practicability and robustness are remarkably improved.

The invention discloses a ship water gauge scale line fitting algorithm, and relates to the technical field of ship water gauge scale calculation, and the method comprises the steps: obtaining a ship water gauge region image through an image collection device to extract a measurement point coordinate, and building a mapping relation between a pixel position and a physical draft; a weighted least square method is adopted to perform nonlinear curve fitting, a weight coefficient is calculated based on a local neighborhood standard deviation, a polynomial order p is dynamically adjusted according to an adjusted decision coefficient, and the decision coefficient is iteratively optimized to improve the balance between amplitude and model complexity. And the system repeatedly corrects model parameters through a dynamic verification mechanism of the residual sum of squares and a preset threshold value, and finally an accurate water gauge scale fitting curve is generated. The method effectively solves the problems that traditional manual observation is prone to environmental interference and large in measurement error, high robustness is kept in a complex water area environment, and reliable data support can be provided for the fields of ship load evaluation, channel safety management and the like.

The invention discloses a safety helmet wearing detection method in a complex environment, and belongs to the technical field of computer vision, and the method comprises the following steps: constructing and dividing a safety helmet image data set according to a proportion; in the backbone network, a C2f-MSEFA module is adopted to replace a C2f module, and a MAConv module is provided; an ASF-FS structure is introduced into the neck network; and an EELD detection head is adopted in the detection head part. Based on the above structure, an MMAE-YOLO model is constructed, iterative training is carried out by setting reasonable network parameters, hyper-parameter configuration is optimized in combination with an experiment result, and finally an optimal network model structure is obtained. And carrying out wearing detection on the to-be-detected safety helmet data set by using the MMAE-YOLO model, and outputting a detection result. Compared with a YOLOv8n model, the MMAE-YOLO algorithm has the advantages that on the premise of ensuring the real-time performance, the detection accuracy of small targets and shielded targets is remarkably improved, the model complexity is effectively reduced, and the MMAE-YOLO algorithm is suitable for efficient and reliable safety monitoring of a construction site.

The invention discloses a multi-variable measurement sensor state lightweight evaluation method based on knowledge distillation, and belongs to the technical field of electric digital data processing and multi-sensor data fusion. The method comprises the following steps: firstly, carrying out time synchronization and physical consistency constraint modeling on original data of multiple sensors, and extracting feature representation; a high-precision teacher model is trained at the cloud end, and the high-dimensional mapping relation of the sensor state is learned; intermediate features, soft output and uncertainty information of a teacher model are extracted to serve as distillation knowledge, lightweight student model training is guided, and effective migration of discrimination knowledge is achieved in combination with soft label constraint, feature alignment and an uncertainty guiding mechanism; and finally, compressing, quantifying and optimizing the student model, and deploying the student model to a vehicle-mounted end to realize real-time evaluation and dynamic updating of the states of multiple sensors. According to the method, the model complexity is greatly reduced while the evaluation precision is ensured through a knowledge distillation framework, and efficient and reliable state perception and fault-tolerant control support is provided for an intelligent driving system.

The invention belongs to the technical field of wind power prediction, and provides a double-layer cascade wind power prediction method and system based on TransformerEncoder, and the method comprises the steps: a fusion variable selection module comprises a Pearson correlation coefficient and an XGBoost regression model; the data processing module preprocesses the input original data to obtain normalized data; a fusion variable selection module screens normalized data, a Pearson correlation coefficient quantifies a linear relation of the normalized data, an XGBoost regression model captures a nonlinear relation, and a correlation feature sequence is obtained through fusion; and the model construction and prediction module processes the related feature sequence, predicts and optimizes a power value, and outputs an optimized power prediction value. According to the method, efficient screening of key variables is realized, change rules of meteorological data, fan speed data and power data are effectively identified, redundant variables are effectively reduced, the complexity of the model is reduced, dynamic characteristics of a wind power system can be better understood and learned, and higher precision and stability are shown in an actual prediction task.

The invention discloses a lightweight cross-domain recommendation method and system based on user alignment Agent driving. The method comprises the following steps: firstly, acquiring historical behavior data of a user in multiple fields, fusing multi-modal contents such as texts and images, generating a fine-grained interest prototype through a cross-domain semantic encoder, and constructing a personalized Agent to simulate the intention of the user; then, in a multi-field collaborative environment, an Agent behavior strategy is optimized by utilizing reinforcement learning and a mixed reward mechanism, general preference and field specific preference are modeled through a hierarchical strategy network, and knowledge fusion is realized through a gating mechanism; and then, in combination with a preference distillation technology, extracting transferable characterization from Agent behaviors, and constructing a lightweight cross-domain knowledge graph. Finally, behavior track compression and cross-domain preference mapping are adopted, and efficient and low-consumption personalized recommendation is achieved. According to the method, the problems of cross-domain data sparsity and model complexity are effectively relieved, recommendation accuracy and system response efficiency are improved, and the method is suitable for real-time recommendation service of multiple scenes.

The invention provides a coal-fired unit digital twin modeling method and device based on a denoising diffusion probability model and a storage medium, and belongs to the field of digital twin modeling. The problems that an existing method is large in modeling difficulty and high in model complexity, and mechanism simplification and data quality dependence cannot be avoided are solved. Comprising the following steps: data preprocessing: selecting equipment parameters highly related to operation of a coal-fired unit as diffusion characteristics, selecting diffusion indexes according to the diffusion characteristics, and carrying out normalization processing on the diffusion characteristics and the diffusion indexes; on the basis of the probability denoising diffusion model, a lightweight MobileNet is adopted to replace a residual block in a UNet network, and a lighter and faster industrial digital twinning denoising diffusion probability model DT-DDPM is obtained; guiding a sampling process by adopting diffusion characteristics; carrying out high-fidelity digital twinborn modeling on the coal-fired unit by adopting an industrial digital twinborn denoising diffusion probability model and historical data of operation of the coal-fired unit; the method is applied to coal-fired unit digital twin modeling.

The invention relates to a multi-modal data fusion 3C assembly process quality accurate prediction method, and belongs to the field of 3C intelligent manufacturing, and the method comprises the steps: carrying out the multi-modal data fusion, and forming a unified feature space containing process parameters and quality characterization; performing multi-dimensional analysis on process quality, performing hierarchical analysis on structured process parameters and unstructured images, and establishing cross-modal feature mapping; predicting the process quality, evaluating the contribution degree of process parameters to the quality by utilizing an integrated learning model based on a fused feature set, screening key parameters to reduce the complexity of the model, dynamically adjusting the prediction model, designing a'sliding window + multi-dimensional index 'monitoring system, and evaluating the model performance and the data distribution drift in real time. Establishing a time-performance-distribution three-dimensional trigger mechanism, and starting an adjustment strategy according to different priorities; a'cleaning-complementation-mechanism-mapping-self-adaption 'closed loop is realized, and the timeliness and accuracy of 3C assembly quality prediction are remarkably improved.

The invention discloses a power equipment defect detection method based on improved YOLOv5s. The invention discloses the power equipment defect detection method based on the improved YOLOv5s, and belongs to the technical field of intelligent detection of power equipment. According to the method, by lightening the network structure and improving the loss function, the model complexity is remarkably reduced, and meanwhile high detection precision is kept. The method specifically comprises the following steps: replacing a traditional convolutional layer in a backbone network and a neck network with a GhostModule layer, and reducing parameter quantity by using low-cost linear transformation; optimizing a feature fusion process by adopting a C3Ghost layer; a detection head loss function is replaced by EIoU, and the positioning precision is improved by separating width and height loss. According to the construction of the data set, unmanned aerial vehicle images, public data and network crawling images are integrated, and the training process is optimized through Mosaic enhancement and self-adaptive anchor frame calculation. The mAP value of the improved model reaches 85.9%, the volume of the model is compressed by 45%, the calculated amount is reduced by 52%, the method is suitable for unmanned aerial vehicle inspection, fixed monitoring and edge equipment deployment, defects such as insulator damage, wire breakage and transformer leakage can be detected in real time, and efficient technical support is provided for safe operation and maintenance of power equipment.

The invention belongs to the technical field of remote sensing image processing, computer vision and deep learning, and particularly relates to a remote sensing image erosion gully semantic segmentation method based on improved OfficientNet-UNet. Comprising the following steps of 1, data preparation and data preprocessing; 2, constructing and enhancing a data set; step 3, model construction and strategy training; and 4, performing contrast experiment and result evaluation. According to the method, detail features of ground features can be more accurately captured, an overfitting phenomenon caused by too high model complexity is reduced, so that the classification precision and boundary recognition accuracy of land coverage data are effectively improved, weights of different types of samples can be automatically adjusted in the training process, and the training efficiency is improved. Particularly, the contribution of background pixels to a loss function is reduced, so that the problem of dominant training of the background pixels is effectively relieved; the method has good expansibility.

The invention discloses a dam multi-point deformation prediction method and system, and relates to the technical field of dam safety monitoring, and the method comprises the steps: constructing a finite element analysis model, calculating a hydraulic component displacement feature set, introducing measuring point space coordinates to construct a dam deformation feature factor set, carrying out the feature screening through employing an improved BorutaShap algorithm, and building a simple and efficient deformation prediction BorutaShap model. And capturing a complex nonlinear relationship contained in a residual error of a model predicted value and a real value by using an iTransform deep learning model, predicting a residual error value, superposing the residual error value with a BorutaShap model predicted value, outputting a final deformation predicted value, and establishing a BorutaShap-iTransform model. According to the dam multi-point deformation prediction method, through feature screening and residual error correction, the model complexity is remarkably reduced, effective information in residual errors is effectively mined, and the dam multi-point deformation prediction precision is greatly improved.