54results about How to "Improve feature extraction efficiency" patented technology

The invention discloses an equipment state sensing system based on peak shifting and danger situation sensing, which relates to the technical field of electric digital data processing and comprises a data acquisition unit, a model training and optimizing unit, a situation sensing unit, a peak shifting regulation and control unit and a system interface and user interaction unit. According to the method, the device state data feature similarity is dynamically calculated by using the Gaussian kernel function, the similarity matrix is adjusted in combination with the gradient update item, dynamic weighting is performed in feature extraction, and redundant features are reduced by adopting the adaptive discarding probability, so that the feature extraction efficiency of the model in a high-dimensional feature space is improved; the problem that the dimension reduction effect is affected by too many redundant features of the equipment state data is solved. Equipment state features are extracted layer by layer through a deep forest algorithm of a multi-layer random forest structure, a decision tree is optimized in combination with a dynamic adjustment weight mechanism and a reinforcement learning strategy, and the classification capability of the model for equipment state changes and abnormal states is enhanced.

The invention relates to a marine ranch power supply system line fault diagnosis method based on MS-2DResNet and ICBAM, and belongs to the field of power supply system line fault diagnosis. The fault diagnosis method is mainly divided into two stages, namely, multi-scale feature extraction and attention mechanism feature fusion. Firstly, a preprocessed fault data sample is converted into two-dimensional data to be input into a fault diagnosis model; in the first stage, local and global feature extraction is performed on the converted fault data by using multi-scale convolution, so that the robustness of the model for fault data features of different sizes and scales is improved. And then, entering an attention feature fusion stage, and carrying out weighted fusion on stacked data from different scale channels by utilizing the improved CBAM, so that the model pays more attention to useful fault features and neglects useless features, and further, the fault diagnosis accuracy of the model is improved. The method has the characteristics of high diagnosis accuracy and good anti-noise performance.

The invention discloses an unmanned aerial vehicle target detection method based on feature fusion and detection head collaborative optimization, and the method comprises the steps: obtaining a multi-scale feature map through employing a backbone network formed by stacking a convolution module CBS and a residual module C2f, sequentially transmitting the feature maps of various scales to a multi-level feature fusion module (ML-FFM), carrying out the feature fusion from a deep layer to a shallow layer, and carrying out the detection of a target target. Semantic information of shallow layer features is enhanced; inputting the fused feature map into a refined feature enhancement module (RFEM), eliminating position conflicts and redundant information based on a space-time attention mechanism, and optimizing details and positioning capability of deep features; and the enhanced feature map is sent to a prediction head based on Transform for detection, and target classification and positioning of the aerial image of the unmanned aerial vehicle are completed. According to the method, the problems that the unmanned aerial vehicle aerial image is large in scale change, and small targets are high in proportion and dense in distribution are solved, so that the precision of target detection in the unmanned aerial vehicle aerial image is improved. The modules proposed in the method can significantly reduce the calculation amount, and are suitable for the real-time detection scene of the unmanned aerial vehicle.

The invention provides a circuit breaker mechanical fault voiceprint feature extraction method, which belongs to the technical field of circuit breaker mechanical fault voiceprint, and comprises the following steps: collecting sound signals of a circuit breaker in normal operation and various mechanical fault states; performing filtering and noise reduction on the collected sound signal to obtain a preprocessed sound signal, and extracting an abnormal waveform segment set; processing the preprocessed sound signal by using a CUDA parallel processing stream of the GPU, and processing an abnormal waveform segment set by using an input stream of the CPU; performing time-frequency domain feature extraction on the preprocessed sound signal to obtain a first feature matrix; clustering the first feature matrix to obtain a plurality of clustering centers as typical sound features, and constructing a second feature matrix; extracting features of the abnormal waveform segment set to obtain a third feature matrix, and performing feature fusion and dimension reduction on the third feature matrix and the second feature matrix; and finally, a mechanical fault voiceprint feature matrix is obtained. The technical problem that a traditional serial processing mode is low in efficiency is solved.

The invention discloses a grinding workpiece edge shape detection method and system based on machine learning, and the method comprises the steps: obtaining an original image of a grinding workpiece, and carrying out the preliminary image preprocessing; denoising the image and enhancing edge information by combining image filtering and mathematical morphology image processing; based on a second-order differential operator, edge detection is carried out in combination with the morphological gradient, and a workpiece edge contour is obtained; performing feature extraction on the image by using a convolutional neural network, automatically learning workpiece edge features, and constructing and training an edge detection model; acquiring a workpiece image in real time, inputting the workpiece image into the edge detection model for detection, and dynamically correcting the model; and S6, outputting a final edge detection result. According to the invention, by combining image preprocessing, composite image filtering, second-order differential operator and morphological gradient edge detection and feature extraction and model construction of the convolutional neural network, high-precision and robust detection of the edge of the grinding workpiece is realized.

The invention discloses a COD (Chemical Oxygen Demand) prediction method based on a two-channel convolution time sequence mechanism, which comprises the following steps of: acquiring COD original data for preprocessing to obtain COD input characteristics; constructing a prediction model, and importing data into a dual-channel convolution module; importing the first double-channel convolution output feature vector and the second double-channel convolution output feature vector into a double attention memory network to obtain a time sequence dependence feature; the time sequence dependence characteristics are imported into an output module, and predicted COD output is obtained; training the model, and in the training process, optimizing hyper-parameters of the model based on an improved pelican algorithm; and importing real-time COD original data into the trained model, and obtaining real-time COD output. According to the method, a high-efficiency effluent COD content prediction model of the sewage treatment plant is constructed by creatively fusing the two-channel convolution and the double-attention memory network.

The invention belongs to the technical field of image analysis, and particularly relates to a mulberry growth period identification method and system based on image analysis, and the method comprises the steps: obtaining image data of each growth period of a mulberry, preprocessing the image data, and inputting the preprocessed image data into a feature extraction module; performing feature extraction on the image data in each growth period, and establishing a feature comparison table of the images in each growth period of the mulberry trees; mulberry image data of each mulberry planting area to be identified is collected in real time, and after preprocessing, the mulberry image data is input into the feature extraction module for real-time image feature extraction; inputting the real-time image features into a feature comparison module, calling a mulberry growth period image feature comparison table, and matching the real-time image features with the mulberry growth period image feature comparison table; obtaining the mulberry growth period of each mulberry planting area to be identified according to the matching result of the real-time image feature and the mulberry growth period image feature comparison table; a preset mulberry growth period management measure table is called, management measures of the mulberries in the mulberry planting areas are obtained, mulberry planting management is facilitated, and the economic benefits of mulberry planting are improved.

The invention relates to the technical field of image processing, in particular to a lightweight remote sensing scene classification method based on a neural network, and the method comprises the steps: firstly obtaining a remote sensing image data set, and preprocessing the remote sensing image data set to obtain a training set and a test set; then, a teacher model including ConvNext and a student model remote sensing scene classification network of a ShuffleNetv2 network embedded with a mixed attention structure are constructed; inputting the training set into a teacher model and a student model at the same time to train the remote sensing scene classification network to obtain a remote sensing scene classification model; and finally, inputting the test set into the remote sensing scene classification model for classification prediction, and comparing an obtained prediction label with a real label of the test set to complete the test of the remote sensing scene classification model. According to the invention, the feature extraction capability is improved by using a mixed attention structure; and a knowledge distillation method is used to transmit dark knowledge of the teacher model to the student model, so that the precision of the neural network is improved.

The invention relates to the technical field of audio decoding, and discloses an audio decoding performance optimization method and device for a multimode SoC main control chip, and the method comprises the steps: carrying out the framing processing of input audio data through a DSP processing unit, and extracting audio feature data; performing period detection and multi-frame smoothing processing on the audio characteristic data to obtain an audio period characteristic vector; performing principal component transformation and feature dimension reduction based on the audio period feature vector to obtain decoding prediction data, and inputting the decoding prediction data into a task division model to perform decoding processing sequence analysis to obtain decoding task data; carrying out hidden Markov modeling on the decoding task data, and calculating to obtain decoding optimization data; and mapping the decoding optimization data to a hardware acceleration unit of the multi-mode SoC main control chip, and executing parallel decoding operation to obtain target decoding data. According to the invention, adaptive optimization of the decoding process is realized, and the decoding strategy can be flexibly adjusted according to different audio data characteristics and processing requirements.

The invention provides a small-scale target detection method and device for power line inspection, a medium and a terminal. The method comprises the steps of obtaining a power transmission line data set and performing small-scale target labeling; the reference Faster-RCNN algorithm model is improved, and an improved Faster-RCNN algorithm model is obtained; and training and evaluating the improved Faster-RCNN algorithm model by using the marked data set, so as to perform small-scale target detection on the power transmission line image of the inspection area acquired in real time by using the unmanned aerial vehicle end. The improved Faster-RCNN algorithm model adopts an AdvResNet network combined with a feature pyramid structure to improve the feature extraction efficiency, a guide feature refining module improves the detection capability of a small-scale target, and an ROI alignment network improves the positioning precision of a bounding box, so that the reliability and safety of power transmission line inspection are improved.

The invention discloses an ultrasonic endoscope intelligent training system, and relates to ultrasonic endoscope training data processing, and the technical scheme is characterized in that a data collection module is used for collecting an action image set of a student and organ feedback data and body operation data of an experimental subject in the training process; the data processing module is used for preprocessing the collected action image set to obtain a high-quality image set, and performing feature processing on organ feedback data and body operation data of the experimental subject to obtain a feature data set; the scheme generation module is used for inputting the high-quality image set and the feature data set after data fusion into the trained GoogLeNet network learning model to obtain a training scheme of the trainee; all the modules are connected in a wired and / or wireless mode, all the modules are connected in a wired and / or wireless mode, and personalized scheme generation of ultrasonic endoscope intelligent training is achieved.

The invention discloses a flaw detection method and device based on FabricMosaic and an improved fine-grained feature extraction network, relates to the technical field of cloth flaw detection, and solves the problems that in the prior art, a flaw target is incomplete and small target flaws are prone to missing detection due to the fact that a fixed cutting mode is adopted. A dynamic FabricMosaic data enhancement strategy based on target foreground and cloth texture background features is adopted to carry out sample expansion, images in a training set serve as input of a YOLOv5s network model, feature extraction is carried out through a feature fine-grained enhancement extraction module based on a divergent path to obtain a global fine-grained feature map, the YOLOv5s network model is trained, and a target foreground and cloth texture background feature is obtained. The final YOLOv5s network model is used for cloth flaw detection, a dynamic FabricMosaic data enhancement strategy is used for sample expansion, the integrity of a flaw target can still be effectively reserved in the sample integration process, and the risk of missing detection during small target flaw detection is reduced.

The invention discloses an intelligent monitoring and regulation system for a connector, and relates to the field of monitoring data processing, and the key points of the technical scheme are that a data acquisition module acquires comprehensive working data and environmental data of the connector; the data optimization module is used for preprocessing the comprehensive working data, and the preprocessing modes comprise data synchronous calibration, weighting processing on repeated current values or voltage values existing at a single time point, and interpolation method filling on data missing at the single time point; obtaining adjustment data; the feature analysis module is used for performing singular spectrum analysis SSA on the adjustment and calibration data to obtain feature data; and the prediction regulation and control module inputs the feature data into a pre-trained neural network model, a regulation and control decision of the connector is obtained through prediction, all the modules are connected in a wired and / or wireless mode, and intelligent monitoring and regulation and control of the connector are achieved.

The invention relates to the technical field of road traffic marking detection, and provides a road traffic marking detection method based on efficient visual transformation. According to the method, road traffic marking data sets are combined, screened, expanded and labeled; constructing a road traffic marking detection model composed of a feature extraction network, a multi-scale feature map enhancement network and a detection head; inputting into a feature extraction network for feature extraction; inputting into a multi-scale feature map enhancement network for feature fusion; and inputting into a detection head for detection and classification to obtain a final detection result. According to the scheme of the invention, the feature extraction network utilizes an efficient attention mechanism to improve the global context information capture capability and improve the complex road traffic marking detection precision; the multi-scale feature map enhancement network adopts a bottom-up path structure to enhance the capturing capability of small target features, and the recognition precision and robustness under a complex background are improved.

The invention discloses an aircraft assembly point cloud registration method and device based on LiDAR scanning data, and belongs to the field of three-dimensional point cloud processing. The method comprises the following steps: acquiring a source point cloud and a target point cloud of an airplane model; performing feature extraction and downsampling on the source point cloud and the target point cloud to obtain downsampling points, and jointly constructing a local patch by each super point and nearby K sampling points; calculating a prediction rigid body transformation matrix of the source point cloud and the target point cloud; calculating density consistency loss, attitude consistency loss, geometric consistency loss and point matching loss of the global prediction rigid body transformation matrix and the real rigid body transformation matrix, and comprehensive loss of the global prediction rigid body transformation matrix and the real rigid body transformation matrix, and optimizing the global prediction rigid body transformation matrix for point cloud registration by taking the minimum comprehensive loss as a target to obtain a target rigid body transformation matrix; and registering the source point cloud and the target point cloud according to the target rigid body transformation matrix. And high-efficiency and high-precision aircraft point cloud registration is realized.

The invention provides a stacking model-based obesity genetic risk model construction method, electronic equipment and a storage medium, the method comprises the following steps: obtaining a data set, the data set comprising genetic feature data, and the genetic feature data comprising single nucleotide polymorphism; screening the single nucleotide polymorphisms by using a random forest to obtain a first genetic feature set related to obesity genetic risks; screening the single nucleotide polymorphism by using a distributed gradient enhanced library model to obtain a second genetic feature set related to the obesity genetic risk; obtaining a significant genetic feature set according to the first genetic feature set and the second genetic feature set; constructing an obesity genetic risk model; according to the method, the model evaluation result of the obesity genetic risk model is obtained, the parameters of the obesity genetic risk model are optimized according to the model evaluation result, stacking training is carried out by integrating multiple basic learners and combining meta-classifier logistic regression, the advantages of different algorithms are effectively fused, and the method is suitable for large-scale popularization and application. And the accuracy and the stability of obesity genetic risk prediction are improved.

The invention discloses a bridge apparent slender disease identification method based on a parallel convolution adaptive segmentation model, and the method comprises the steps: a constructed bridge apparent slender disease detection model comprises a feature extraction network with a built-in parallel feature extraction module DCM, adaptive spatial feature fusion models ASFF, RPN, RoI Align and a network head architecture; dCM is a parallel module which is embedded in each stage of a feature extraction network and fuses standard convolution and dynamic snakelike convolution, each stage is interspersed in a parallel mode, each stage dynamically adjusts a convolution kernel through iteration offset by using the dynamic snakelike convolution, the morphological features of the bridge apparent slender disease are further sensed, and the morphological features of the bridge apparent slender disease are extracted. Carrying out global information constraint on the other branch by utilizing standard convolution; and the ASFF performs layer-by-layer superposition fusion on the high-semantic feature map of the last convolution stage and other feature maps except the first convolution stage, and realizes feature adaptive fusion through learnable parameters. According to the invention, automatic and refined detection of bridge appearance slender diseases can be realized.

The invention relates to an insulator material defect detection method, system, device, medium and program, and the method comprises the steps: carrying out the denoising filtering and image standardization operation of an insulator image obtained in advance, and obtaining a standard insulator image; performing multi-channel convolution and residual connection on the standard insulator image to obtain an insulator image feature set; performing global attention coding on the insulator image feature set to obtain an attention image feature set; extracting global channel image features from the insulator image feature set, and performing channel fusion and spatial fusion on the global channel image features to obtain perception image features; and performing layer-by-layer feature decoding on the attention image feature set by using the perception image features to obtain a defect detection result, thereby improving the insulator defect detection efficiency.

The invention relates to the field of situation awareness, in particular to an intention recognition method and device based on target track classification. The method mainly comprises the steps that a feature vector set related to intention is acquired through track information, a global feature extraction network is built based on an inception network, and global features in the feature vector set are acquired through the global feature extraction network; constructing a local feature extraction network based on a BiGRU-Attention network, and extracting time sequence features in the sample set by using the local feature extraction network; according to the method, target tracks are classified by using global features and time sequence features, a cross entropy loss function is optimized by using local loss, the weight of a minority class is adjusted, and a result of intention recognition is output by using softmax. According to the method, the intention recognition hierarchy can be improved through multi-layer feature extraction, the feature extraction efficiency is improved, and the problem that the classification precision is not high is solved.

The present invention discloses a method for fine-grained biological image classification based on a Transformer model. Aiming at the need for fine-grained biological classification, the method of the present invention establishes a classification model including a feature extraction module, a feature selection module and a prediction module; the feature extraction module is implemented based on a Transformer network, and outputs image features represented by feature blocks patches; the feature selection module performs nonlinear mapping on the patches, and then generates weights through a softmax function to select a certain number of patches as new image features, and the prediction module predicts fine-grained biological classification according to the image features. During training, the cosine distance between sample features is calculated as the distance loss, and then the classification model parameters are optimized in combination with the classification loss. The method of the present invention is applicable to different Transformer-based backbone networks, and achieves fine-grained biological image classification with high classification accuracy.

The invention discloses a gas boiler operation state determination method, system and device, a medium and a product, and relates to the technical field of gas boiler state monitoring, the method comprises the following steps: carrying out word segmentation processing on a historical inspection report text set to obtain candidate new words; performing feature extraction on the candidate new words by using a TF-IDF weighting method to obtain a plurality of risk feature words; calculating a correlation coefficient between every two risk feature words, and combining the risk feature words of which the correlation coefficients exceed a first preset threshold value to obtain a risk expression statement; determining a first-level evaluation index, and determining a second-level evaluation index according to each risk expression statement; based on the first-level evaluation indexes, the second-level evaluation indexes and preset expert weights, determining the weight of each first-level evaluation index and the weight of each second-level evaluation index by adopting a group analytic hierarchy process; and determining the operation state of the gas boiler based on the weight of each primary evaluation index and the weight of each secondary evaluation index. According to the method, the operation state determination efficiency of the gas-fired boiler is improved.

The invention relates to the technical field of intelligent driving, in particular to an efficient real-time vehicle intelligent detection and recognition method and system based on YOLO-BOS, and the method comprises the steps: training a YOLO-BOS model through a vehicle sample image, and obtaining a vehicle detection and recognition model; the YOLO-BOS model comprises an input end used for preprocessing an input image, a backbone network used for carrying out feature extraction on the preprocessed image, a head network used for fusing the extracted image features, and a prediction output end used for carrying out classification prediction on the fused and output image features. The backbone network uses double-layer routing in a BRSA attention mechanism to adjust each spatial position weight in the image to screen and strengthen key features, and the head network uses full-dimensional dynamic convolution to expand a model receptive field and a perception range to capture related features in feature fusion; and extracting the category and bounding box information of the target vehicle in the to-be-detected image by using the vehicle detection and identification model. The method can adapt to complex and changeable conditions of road targets, and improves the vehicle detection and recognition precision.

The invention discloses a landscape painting authenticity identification method based on multi-scale feature fusion. The method comprises the steps of establishing a landscape painting authenticity data set, preprocessing the data set, constructing a landscape painting authenticity identification network, training the landscape painting authenticity identification network and testing the landscape painting authenticity identification network. According to the landscape painting authenticity identification network, a residual block serves as a basic network model structure and is improved to extract image features, the technical problem of feature extraction of different dimensions of landscape painting images is solved, and the feature extraction efficiency of the landscape painting images is improved; an attention mechanism module is introduced, so that the technical problem of insufficient attention of a feature map is solved, and the extraction and identification precision of the network on image features is improved; the feature fusion module solves the technical problem of comprehensively considering the multi-dimensional features of the landscape painting, and improves the efficiency of true and false identification of the landscape painting. The method has the advantages of diversified feature information, high true and false identification efficiency, high identification speed and the like, and can be used for true and false identification of landscape paintings.

The invention discloses a fish image recognition method and system based on deep learning, and the method designs a Bilatal-Net underwater image enhancement model which comprises a mixed domain self-attention-based contrast enhancement module, a bilateral feature fusion module and a multi-dimensional loss function module. A contrast enhancement module based on mixed domain self-attention is introduced, a bilateral feature fusion module is designed for detail blurring of an underwater image to enhance detail features of the image, and a multi-dimensional loss function is designed for color deviation of the underwater image. Aiming at the characteristics of large inter-class difference and small intra-class difference of fish images, a FishResNet18 fish recognition model of an attention residual module based on a channel domain and a spatial domain is proposed, extraction of important features in the fish images is stimulated from two aspects of the channel and the spatial domain, the learning effect is improved, meanwhile, the degradation phenomenon of CNN is reduced, and the recognition efficiency is improved. And the recognition efficiency of the fish image is improved from local to global.

The invention discloses a model processing method, a picture processing method and related equipment for pictures, and the method comprises the steps: obtaining an object region picture of a target training picture in a training data set, and enabling the object region picture to be determined according to a part of image regions in the target training picture; inputting the object region picture into a to-be-trained feature extraction model to obtain an object feature vector of the object region picture; the object feature vector is input into n image processors GPUs, a loss function value is obtained based on the object feature vector and a sub-linear matrix configured in each GPU, the sub-linear matrix configured in each GPU is determined after a linear matrix of a linear layer in a to-be-trained feature extraction model is divided, and n is a positive integer; and training a to-be-trained feature extraction model according to the loss function value to obtain a feature extraction model which is used for extracting object features corresponding to the to-be-processed picture. In this way, the image processing efficiency can be improved.

The invention provides a quantum computing auxiliary analysis and marketing prediction method for private domain traffic pool data, which comprises the following steps of: acquiring and processing user behavior data, coding the user behavior data into a quantum state by using a quantum algorithm, extracting user behavior characteristics by using a quantum support vector machine (QSVM), and analyzing a periodic mode through quantum Fourier transform, so as to realize the quantum computing auxiliary analysis and marketing prediction of the private domain traffic pool data. According to the method, a marketing prediction model is constructed based on a quantum algorithm, model parameters are optimized by using a quantum annealing technology, the prediction accuracy is improved, and the method further comprises the step of carrying out classical verification and optimization on a quantum calculation result so as to realize personalized marketing. According to the invention, efficient analysis and precise marketing prediction of the private domain traffic pool are realized, and the pertinence and effectiveness of enterprise marketing strategies are improved.

The present application belongs to the field of image processing technology, and discloses a multimodal image fusion model and construction method of an asymmetric U-Net structure, in which a first coding unit uses visible light feature information gradually extracted by each first coding block to inject into a compression and excitation module to form an attention map of visible light information, which is multiplied with the infrared light feature information extracted by the corresponding second coding block and then assists the next second coding block to extract infrared light feature information, so as to speed up the feature extraction efficiency of the infrared light coding branch for the infrared image, so that the corresponding second coding block can extract more infrared light feature information, and finally fuse the feature images extracted by multiple first coding blocks and multiple second coding blocks, which can reduce the loss of shallow information of the fusion result or the bias towards a single mode, and obtain a fused image with good quality.

The application provides a facial expression recognition method based on a double attention mechanism, named Adaptive Spatio-Excitation Transformer (ASET). This method introduces Adaptive Squeeze-and-Excitation (ASE) attention mechanism and spatial attention mechanism, and combines with Transformer network, which significantly improves the accuracy and efficiency of facial expression recognition. The core of the application is to recalibrate the channels of feature maps through ASE mechanism, and focus on the key areas of the face through spatial attention mechanism, so as to more efficiently extract expression features. In addition, the application also introduces visualization technology to highlight the key areas in the face image, helping to understand the decision-making process of the model. Experimental results show that the application has achieved excellent performance on multiple standard datasets such as FER2013, CK+ and JAFFE, and has significantly improved performance compared with existing technology. The application can be widely used in human-computer interaction, sentiment analysis and other fields, providing an efficient and accurate solution for facial expression recognition.

This invention provides an automatic SAR target detection method and apparatus based on adaptive feature focusing, belonging to the field of SAR image detection. The method includes: constructing a lightweight EOD-Net; after the backbone network extracts multi-scale features, the latent target perception branch PTBranch outputs a mask to coarsely locate the target region; and using a no-overlap feature map cropping NOFC to iteratively remove overlapping blocks, retaining only non-overlapping target feature blocks for the detection head to regress. During the training phase, a Gaussian-binary hybrid mask supervises PTBranch, and the focus loss and DICE loss are jointly optimized. This invention outperforms comparable methods such as YOLOv11 and Faster RCNN, achieving high-precision and efficient SAR image detection.

The invention discloses a voxel-oriented end-to-end 3D target detection method. The voxel-oriented end-to-end 3D target detection method comprises the following steps of A1, point cloud data input and data enhancement; a2, backbone network feature extraction: after the point cloud data is voxelized, the point cloud data is processed by two IDW-MSA modules, and rich feature information is extracted; and A3, detecting and classifying. According to the method, the IDW module is introduced, the large kernel convolution is used, the receptive field of the model is greatly increased, the MSA module is introduced, the attention mechanism is perceived by using neurons, additional parameters do not need to be added, the calculation efficiency is remarkably improved, and meanwhile high detection precision is kept; compared with the prior art, the method provided by the invention has the advantages that the target detection accuracy and speed under a complex background are remarkably improved.