5032 results about "Backbone network" patented technology

The invention relates to the technical field of industrial automatic quality inspection, and provides a PCBA surface defect detection method and system based on deep learning and a medium, and the method is used for carrying out defect detection on a preset PCBA board. Comprising the following steps: acquiring a surface image of a PCBA board according to a preset multi-angle light source and a high-resolution camera, and performing adaptive illumination compensation and noise removal processing on the surface image to generate a standardized image; performing multi-scale segmentation on the standardized image to obtain image blocks including local details and a global structure; constructing a double-branch deep learning model, wherein the double-branch deep learning model comprises a backbone network, a multi-scale feature fusion module and a defect detection branch; inputting the image blocks into a double-branch deep learning model, and outputting a thermodynamic diagram and probability distribution by the double-branch deep learning model; performing binarization processing on the thermodynamic diagram by using a dynamic threshold segmentation algorithm to generate a defect mask; and outputting a defect detection result of the PCBA board according to the defect mask and the probability distribution, and completing the defect detection of the PCBA board.

The invention discloses an unmanned aerial vehicle image small target detection method based on dynamic filtering and an adaptive sparse Transform. According to the method, an end-to-end target detection framework is adopted, a dynamic filtering module is introduced into a backbone network, global feature interaction is achieved through data-dependent frequency domain operation, and linear calculation complexity is maintained. For feature interaction in a scale, an adaptive sparse Transform module is introduced to enhance the capability of focusing key information on high semantic hierarchy features of a model, and noise interference and feature redundancy are effectively suppressed at the same time. Through the combination of dynamic filtering and adaptive sparse Transform, the model can extract image foreground information more effectively on the premise of not significantly increasing the calculation burden, and the problem that a traditional target detection model is susceptible to complex background interference is significantly relieved.

The invention relates to an unmanned aerial vehicle aerial image small target detection method and a computer readable storage medium. The method comprises the steps of obtaining unmanned aerial vehicle aerial image data, and dividing the data into a training set and a verification set after processing; yOLOv8n is used as a basic model, traditional convolution structures of a shallow layer and a middle layer are replaced by full-dimensional dynamic convolution in a backbone network of the YOLOv8n model, an enhanced space attention mechanism based on routing is introduced into the backbone network of the YOLOv8n model, and an original SPPF structure of the backbone network is replaced by a multi-scale context modulation module. Performing collaborative design of a multi-scale structure and a detection head in a neck network and a head network of the YOLOv8n model to obtain an improved YOLOv8n model; training and verifying the improved YOLOv8n model by using the training set and the verification set to obtain a trained unmanned aerial vehicle aerial image small target detection model; and inputting a to-be-detected unmanned aerial vehicle aerial image into the trained unmanned aerial vehicle aerial image small target detection model to obtain a detection result. According to the invention, the small target detection precision and speed are improved.

The invention discloses a two-way visual saliency detection method and device combining difference guidance and texture enhancement, and the method comprises the following steps: 1, obtaining an image to be subjected to saliency detection, and carrying out the marking and preprocessing of a data set; 2, constructing a visual saliency detection model which comprises a dual-path encoder (a saliency detection path and an image reconstruction path), an adaptive interaction network, a decoder network and an output network; a significance detection path in the dual-path encoder network uses a pre-trained ConvNeXt encoder, and an image reconstruction path uses VQ-VAE as a backbone network; the adaptive interactive network comprises a multi-scale convolution module and a gating fusion module; the decoder network comprises a mutual conversion attention module and a double-gating fusion module; the output network comprises a multi-level feature fusion module; 3, training the saliency detection model to obtain a trained saliency detection model; and 4, carrying out saliency detection on the image data by adopting the trained saliency detection model.

The invention discloses an unmanned aerial vehicle aerial image target detection method based on PSO-DETR, and belongs to the technical field of unmanned aerial vehicle aerial image target detection. Firstly, a parallel patch perception attention feature extraction module is constructed, and an efficient multi-branch backbone network C3KCSPnet is designed by fusing a CSPDarknet53 structure; according to the network, gradient flow is improved through deep optimization, and the capturing capacity of high-level semantic information is enhanced. And secondly, an enhanced channel offset hybrid operator is provided, the dependency relationship between channels is enhanced through a channel shuffling mechanism, and cross-channel interaction of local space information is realized in combination with channel offset operation, so that the feature recovery quality and fusion efficiency in an up-sampling stage are improved, and the problem of missed detection of a shielded target is further relieved. And finally, a re-parameterization hierarchical aggregation network is designed, effective integration of shallow details and deep semantics is realized through an efficient hierarchical fusion mechanism on the premise of ensuring controllable calculation complexity, and the detection performance of the small target is further enhanced.

The road crack detection method based on the improved RT-DETR comprises the following steps: shooting a road at a preset flight height by using an unmanned aerial vehicle to obtain an original road image containing a crack; a pre-trained crack detection model is utilized to carry out crack detection based on an original road image to obtain crack parameters, and the crack detection model is obtained through improvement and training based on an RT-DETR (Real-Time Detecting Transformer) model; the method for improving the RT-DETR model to obtain the crack detection model comprises the following steps: replacing a basic residual block at the tail end of a ResNet18 backbone network in the RT-DETR model with a dynamic snakelike convolution residual block (DSCRBlock); a cross-scale feature fusion module (CCFM) in a hybrid encoder in an RT-DETR model is replaced by a bidirectional diffusion focusing pyramid network (BDFPN), and the bidirectional diffusion focusing pyramid network comprises a primary focusing sub-network and a secondary focusing sub-network. The method can efficiently and accurately identify the road crack, can be applied to the unmanned aerial vehicle, and is easier to implement.

The invention provides a signal optimization transmission system and method based on HPLC and HRF dual-mode communication, a signal acquisition and processing module of the signal optimization transmission system based on HPLC and HRF dual-mode communication is used for acquiring signals of two communication modes of HPLC and HRF in real time, preprocessing the signals and extracting key signal parameters; the dual-mode switching module is used for dynamically switching an HPLC mode and an HRF mode based on channel quality; the access module is used for constructing a longitudinal backbone network and a transverse Mesh network, forming a hybrid topology, optimizing a routing path and coordinating resource allocation and conflict avoidance of HPLC and HRF; the intelligent decision module is used for predicting future interference intensity according to the historical interference data and adjusting channel parameters; the central coordinator module is used for network initialization and resource allocation; according to the system and the method, the HPLC mode and the HRF mode are automatically switched according to the channel quality, the longitudinal HPLC backbone network is combined with the transverse HRF Mesh network to form a four-dimensional communication network, and the robustness in a complex scene is remarkably improved.

The invention belongs to the technical field of computer vision and artificial intelligence, belongs to the cross technical field of target detection, deep learning and image processing, and particularly relates to a YOLOv8 algorithm improvement method based on an unmanned aerial vehicle aerial image small target detection model, which comprises the following steps of: introducing a user-defined feature enhancement module into a YOLOv8 backbone network, a neck part and a detection head part; the self-defined feature enhancement module comprises a context guide self-adaptive fusion module introduced into a backbone network so as to replace part of traditional convolution operation; a space edge sensing feature up-sampling module and a space sensing enhanced convolution module are adopted in the neck fusion network; a fine-grained dynamic pruning detection head is introduced into a detection head detection network. According to the method, the performance of the model in a small target detection scene is effectively enhanced, and the accuracy, robustness and real-time response capability of a detection system are remarkably improved.

The present invention relates to a solar azimuth estimation method and system based on multi-channel feature enhancement and region-aware attention, belonging to the technical field of intelligent navigation for low-altitude economy unmanned systems. Aiming at the problem of decreased accuracy in solar azimuth estimation based on polarization images under complex cloud cover conditions, the present invention proposes a deep learning framework integrating multi-channel features and direction-aware attention. First, based on polarization light field information acquired by a division-of-focal-plane polarization camera, a three-channel composite input feature composed of a polarization intensity map, an adaptive threshold gradient map, and high-frequency residual edge information is constructed. Second, a ResNet backbone network embedded with a squeeze-and-excitation mechanism is adopted, and a direction-aware polarization attention module is introduced to achieve adaptive fusion of multi-scale features through luminance guidance, deep feature enhancement, and a gradient edge branch.

The invention discloses a remote sensing image cultivated land segmentation method and system fusing context and boundary perception, and belongs to the technical field of remote sensing image processing and agricultural information. Constructing a cultivated land segmentation initial model composed of a backbone network, a feature enhancement module, a multi-scale feature fusion de-wharf module and a mask prediction module; training set data are input into the initial model, a composite loss function value is calculated, back propagation is executed, and a cultivated land segmentation model with boundary sensing ability is obtained through multi-round iterative optimization; and inputting the remote sensing image into the trained cultivated land segmentation model, and outputting a binary segmentation image representing the cultivated land position. Visual state space modeling and large receptive field convolution are combined, deep and shallow layer information is fused through feature injection, boundary perception supervision and composite loss are introduced, cultivated land boundary discrimination is improved, remote sensing image cultivated land high-precision extraction is achieved, and the method is suitable for agricultural interpretation and monitoring.

The invention relates to a large-scale road network traffic control method based on a deep reinforcement learning large model, and belongs to the technical field of intelligent traffic control. The method comprises the following steps: sensing real-time multi-modal road network information including urban road intersections, highway entrance ramps and emergency lanes, and generating a space-time fusion representation vector representing a current traffic network state by fusing a space diagram construction method and a time sequence embedding method; the space-time fusion representation vector and historical state memory are spliced to serve as input, a backbone network of a pre-training large language model is used for state feature distillation so as to enhance state representation, and a traffic control decision is output through a strategy network with a layered action space; through cross-modal knowledge migration and a progressive course learning strategy, a training process of a deep reinforcement learning algorithm is guided and optimized so as to improve model training efficiency and generalization ability. According to the method, the generalization performance and the accuracy of the control strategy are improved while the real-time response speed is ensured.

The present disclosure discloses a small target detection method based on improved YOLOv8, including: inputting a small target image to be detected into a pre-trained small target detection model based on the improved YOLOv8 for identification to obtain a detection result, where a method for training a small target detection model based on the improved YOLOv8 includes: acquiring a small target image data set and dividing the small target image data set into a training set and a validation set; replacing a backbone network of YOLOv8 with a backbone network ATDeNet and constructing the small target detection model based on the improved YOLOv8; and training the constructed small target detection model by using the training set and the validation set to obtain a trained small target detection model based on the improved YOLOv8. The accuracy and efficiency of small target detection can be significantly improved.

The invention discloses a degraded image defect detection method and system cooperating with text prompt and visual restoration. The method comprises the following steps: generating a degraded image through a high-order degraded model; extracting semantic clues related to the detection target from the degraded image, and encoding the semantic clues into text feature vectors; inputting the degraded image into an anti-degraded backbone network of an integrated low-rank adaptive module, and outputting a robust visual feature map; inputting the text feature vector and the robust visual feature map into an encoder, and outputting an enhanced visual feature of a fusion text prompt; a collaborative learning strategy guided by visual restoration is introduced, the enhanced visual features prompted by the fusion text are restored and enhanced, the feature quality is improved, and meanwhile query distribution under the noise condition is improved; and the enhanced visual features prompted by the fusion text are input to a decoder after being processed by a collaborative learning strategy guided by visual restoration, and the position and category information of the defect is output. According to the method, the degraded image can be directly optimized, and the degraded information is effectively extracted and utilized.

The invention discloses an electric power scene defect small target detection method based on Gaussian mask supervision and cross-layer attention guidance, and the method comprises the steps: inputting an electric power scene image into a detection model, extracting an initial feature map through a backbone network, carrying out the multi-stage feature extraction of the initial feature map according to a convolution path, and carrying out the multi-stage feature extraction of the initial feature map; processing the multi-stage features based on a path aggregation network, and outputting a plurality of fusion feature maps with different feature levels from shallow to deep; and based on cross-scale window attention, guiding a shallow fusion feature map to carry out semantic information modeling by using a deep fusion feature map with high semantics in every two adjacent fusion feature maps, and after a plurality of output feature maps are obtained, respectively processing and outputting prediction results by using a multi-branch detection head. According to the method, shallow feature activation prediction and cross-scale window attention guidance are fused, and the detection robustness and positioning precision of a tiny fault target in an unmanned aerial vehicle inspection image can be effectively improved.

The invention discloses a lightweight multi-modal content recognition system based on a double-track migration framework, and relates to the technical field of content recognition, and the system comprises a data collection module which is used for synchronously collecting multi-source content of a text and an image and carrying out standardization processing and tensor construction to form a fusion tensor X; and the model construction module is used for inputting the fusion tensor into a dual-track migration structure constructed based on a Transform backbone network, and the dual-track migration structure realizes task semantic alignment and structure migration under parameter freezing through Prompt Learning embedding and Adapter-Tuning insertion, and outputs an intermediate representation of modal alignment. According to the method, the training and deployment cost of multi-modal content recognition is remarkably reduced, the semantic expression ability in the modal is enhanced, the cross-modal alignment precision and fusion depth are effectively improved, and the perception and recognition ability of the model to the complex semantic relationship is enhanced.

The invention provides a defect identification method and device for substation equipment and electronic equipment, and relates to the field of image identification. According to the method, an infrared image, an electric field leakage map and a visible light image are obtained through a multi-channel imaging system deployed in a substation site, and a multi-channel image tensor is generated and input into a multi-channel recognition model to extract fusion features. And fusing the features, inputting the fused features into a YOLOv8 backbone network, constructing a joint attention domain in combination with an equipment prior structure, generating a high-confidence candidate box, and performing non-maximum suppression to obtain a detection result. And constructing an inter-frame residual tensor for a detection result to perform time sequence modeling, thereby improving the detection effect. And for equipment with complex shielding, complementing a structure contour through an edge prediction path, and finally outputting target boundary and defect positioning information. By implementing the technical scheme provided by the invention, defect identification of the substation equipment is facilitated.

The invention relates to a ship detection method for a complex synthetic aperture radar (SAR) scene, and belongs to the technical field of remote sensing image target detection.The method comprises the steps that an obtained high-resolution synthetic aperture radar image is input into a DPM-YOLO ship detection network, a ship target detection effect picture is output, the DPM-YOLO ship detection network is improved based on a YOLOv11 network, and the ship target detection effect picture is obtained; a DPSConv module is introduced into a backbone network to capture multi-scale context information by using a receptive field while keeping fine feature details, and a PromptFusionMod module is introduced into a neck network to perform multi-modal feature fusion through four processing stages of space compression and prompt fusion, an efficient attention mechanism, a lightweight multi-layer perceptron and output fine processing. And the original detection head is replaced by the MscaleASFHead detection head. Compared with the prior art, the method has the advantages that fine-grained feature extraction, cross-scale semantic alignment and lightweight deployment can be considered, and ship detection precision and robustness in a complex sea condition scene are improved.

The invention discloses a mobile terminal streetscape image real-time segmentation method based on a lightweight neural network, and relates to the technical field of image segmentation. The method comprises the following steps: firstly, carrying out 320 * 320 adjustment, Z-score standardization, adaptive histogram equalization and 3 * 3 Gaussian filtering preprocessing on an input streetscape image; then, an improved MobileNetV3 backbone network is used, and a five-scale feature map is output in combination with DropBlock regularization through eight feature extraction stages including depth separable convolution and an SE attention module; multi-scale features are fused through a U-shaped structure, and a fusion feature map is generated through up-sampling, element-by-element addition of dimension reduction low-layer features and an attention gating module; and during reasoning, outputting a segmentation mask by using a convolutional layer, Softmax and a conditional random field, and finally performing knowledge distillation, weight pruning, 8-bit quantization and TensorRT optimization. According to the invention, high-precision real-time street view segmentation is realized, the robustness is high, and the method is suitable for different devices and scenes.

The invention discloses a small target detection and state perception method based on multi-scale feature fusion, and belongs to the field of computer vision and deep learning. Multi-scale semantic features are extracted through a backbone network; two uplink fusion paths and two cascaded downlink enhancement paths are constructed, and multi-scale feature fusion is performed, so that the perception capability of targets with different sizes is enhanced, and the accuracy and robustness of detection are improved; and meanwhile, a regional state sensing mechanism is constructed based on a detection result, continuous monitoring and intelligent analysis of target space distribution, behavior trend and dynamic change are realized, and the adaptability and response speed of the system in a complex environment are improved. The method gives consideration to the detection precision and the calculation efficiency, and is suitable for real-time application scenes with limited resources.

The invention discloses a light-weight instrument small target detection model and method for a complex industrial scene, belongs to the crossing field of deep learning and edge calculation, and aims to solve the problem that an existing method cannot meet the real-time detection requirements of edge equipment such as an inspection robot in the aspects of precision, efficiency and small target detection capability. The model comprises a lightweight backbone network used for extracting multi-scale features from an input image; the cross-scale feature fusion network is used for bidirectionally fusing the multi-scale features, retaining shallow space details and deep semantic information and outputting fused features; the deformable large-kernel target sensing module is deployed at a specified position of the cross-scale feature fusion network so as to better capture feature information related to a target area and improve the feature expression capability of a small target; and the multi-task decoupling prediction network performs classification, positioning regression and confidence prediction on the input image in parallel, and a positioning regression branch adopts an EIOU loss function of decoupling width and height optimization.

The invention relates to the technical field of deep learning, in particular to a stress distribution monitoring and crack risk prediction method for a silicon carbide part, which realizes comprehensive sensing of the stress state of the silicon carbide part, accurate positioning of a risk area and advanced early warning of a crack fault. The method comprises the following steps: synchronously acquiring multi-modal data through multiple types of sensors, and realizing cross-modal time sequence synchronization through feature alignment; designing a crack risk multi-branch feature extraction module, and respectively extracting general depth features and risk features oriented to thermal stress mismatch, microcrack evolution and structural instability through a shared backbone network and a special branch network; constructing a stress nephogram generation and risk area positioning module based on a graph neural network, and realizing visual reasoning and risk area marking from discrete features to full-field stress distribution; and designing a crack risk comprehensive prediction module based on multi-dimensional risk feature fusion, fusing an instantaneous state and an evolution trend, outputting a multi-risk confidence vector and triggering graded early warning.

The invention discloses a power transmission line foreign matter detection method and system based on multi-modal image fusion, and relates to the technical field of intelligent operation and maintenance and state monitoring of a power system, a lightweight Ev-Mama architecture is introduced into a backbone network part of YOLOv13, the model keeps relatively low calculation complexity, and meanwhile, the power transmission line foreign matter detection efficiency is improved. And the modeling capability of the method on the long-range dependency relationship and the global semantic information is obviously enhanced. Besides, by using the CDIDF module, the EVCS module and the MHSAA module, on the basis of increasing a small amount of calculation, the scale sensing ability, the space structure modeling ability and the context understanding ability of the model are effectively improved, and the performance bottleneck of a traditional YOLO series network in the aspects of processing small targets, shielding targets and cross-scale information fusion is effectively relieved.

The invention discloses a complex scene traffic sign detection method and system based on dynamic frequency band focusing and double-domain attention screening. The method comprises the following steps: carrying out data preprocessing and data enhancement on a collected road traffic sign image; a CADPCM module and a CHAttention cross coordination attention mechanism are used to construct a CACHNet backbone network; designing a DWMSN neck network, and establishing a dynamic fusion mechanism of multi-scale features; a CACHNet and a DWMSN neck network are used to construct a CDWN model, and a traffic sign enhancement data set is used to train the CDWN model to determine the optimal model weight thereof. Compared with the prior art, the method has the advantages that the average detection precision is improved by 3.3% while the light weight of the model is maintained by constructing a three-level framework of the feature extraction unit, the attention feature expression enhancement and the dynamic feature fusion, the complex scenes such as illumination variation and shielding can be effectively dealt with, and the method is suitable for popularization and application. And high-precision traffic sign detection support is provided for a vehicle-mounted intelligent auxiliary driving system.

The invention provides an end-to-end tiny target detection method, and aims to solve the problems of missing detection and false detection of tiny targets caused by interference of sparse features, halo, noise and the like. According to the method, a TINYDETR model is constructed, and the TINYDETR model is composed of an HGNetv2 backbone network, an LGFSI module, an SO-CSFF module and a decoder with an auxiliary prediction head. Wherein the LGFSI module realizes global-local information interaction through joint modeling of a frequency domain and a spatial domain, and background interference is effectively suppressed; the SO-CSFF module enhances the fusion of shallow details and deep semantics through a bidirectional feature flow mechanism, and enhances the feature expression of a tiny target. After the model is trained and optimized, high-precision detection of a tiny target can be realized.

The invention discloses an intelligent road disease detection method and equipment based on dynamic multi-scale convolution. The method comprises the following steps: performing target category labeling on a training sample set to form a corresponding relationship between sample data and labels; establishing a detection framework including a backbone network, a neck network and a detection network, the backbone network extracting features through convolution layer and cross-stage local layer stacking, introducing spatial pyramid pooling to enhance multi-scale expression, and enhancing fine-grained disease area attention by enhancing spatial attention; the neck network is integrated with dynamic multi-scale convolution and is matched with an upper sampling layer and a cross-stage local layer to fuse high and low layer features; the detection network is provided with a plurality of parallel detection heads, and disease detection is carried out corresponding to different scale feature maps. According to the method, rapid detection and accurate positioning of disease targets of various sizes can be realized, and the detection capability of sparse and small-scale disease targets is remarkably improved through collaborative optimization of a dynamic multi-scale convolution kernel and an enhanced space attention mechanism.

The invention discloses a high-precision image detection method for a micro-drill blade surface based on deep learning, and the method comprises the following steps: S1, collecting a visible light image and a structured light image of the micro-drill blade surface, and completing the image preprocessing; s2, performing spatial alignment on the image, executing cross-modal fusion, and generating a feature fusion tensor; s3, inputting the feature fusion tensor into a multi-scale residual backbone network, and extracting a hierarchical semantic feature set; s4, inputting the semantic feature set into three task branches of defect detection, region segmentation and type classification, and outputting a corresponding prediction result; s5, calculating a multi-task loss function, dynamically adjusting task branch weights, and optimizing a feature sharing structure; and S6, generating a detection report according to a prediction result, and outputting defect coordinates, a boundary contour, a type label and a confidence value. According to the method, multi-modal fusion, high-precision identification and structured output of the micro-drill blade surface are realized, and the accuracy, efficiency and automation level of defect detection are remarkably improved.

The invention discloses a pavement throwing detection method and device based on deep learning, electronic equipment and a program product. The method is realized through a trained detection model, the model adopts an LMSADet detection head, a multi-scale feature extraction and space attention mechanism is introduced into a task branch, and multi-scale modeling is decoupled from a backbone network and a neck network and integrated to the detection head so as to fit a detection task to directly optimize local details and scale differences of a throwing target. In order to suppress background interference and improve the recognition effect of fuzzy boundaries, the neck network is added into an MSHA module so as to efficiently capture the semantic relation between the thrown object and the background and enhance the regional understanding ability. A C3ESP module is introduced into the backbone network, deep features are extracted through stacking depth separable convolution, and information loss is avoided in combination with residual optimization fusion; meanwhile, a PEMA attention mechanism is introduced, the importance of different receptive field features is dynamically adjusted, the model focuses on key features, data information is captured more comprehensively, and therefore the detection performance is remarkably improved.

The invention provides an SDN (Software Defined Network) inter-domain traffic engineering method based on reinforcement learning, which comprises the following steps of: deploying a data traffic demand monitoring platform and a control system, and constructing a global network topological graph; calculating a short link identifier for the link in the network and distributing the short link identifier to each network device; flow judgment is carried out, upward notification is carried out according to requirements, and pre-operation of intelligent routing is cooperatively completed; deploying a reinforcement learning model in the total intelligent body, outputting an optimal cross-domain path strategy to the cooperative controller, disassembling the optimal cross-domain path strategy into flow table rules which can be executed by each domain, and issuing the flow table rules to local controllers of related domains; and each local controller pushes the flow table configuration to the domain switching equipment to complete the forwarding decision of the flow. According to the method, a complete closed-loop process of flow measurement, intelligent decision making, cross-domain control and path issuing is realized, feasible reference is provided for actual deployment of an intelligent network, and the method has good engineering popularization value and is suitable for intelligent scheduling scenes such as an operator backbone network, an industrial internet and metro edge cloud.

The invention discloses a small sample target detection method based on target feature enhancement and semantic fusion perception, and relates to a computer vision technology. A data set is divided into a query set and a support set, after features are extracted through a backbone network, background noise in the support features is inhibited through a dynamic hypergraph construction module, and high-order semantic association of a target area is enhanced; fusing the category name text semantics and the image specific prototype by using a semantic fusion perception module to generate a high-discrimination category prototype; modeling semantic distribution by means of a variational auto-encoder, and extracting variational features; and fusing the region-of-interest features and the variation features through a channel attention mechanism to realize classification and regression. According to the method, the prototype characterization capability is effectively improved, and experiments show that the method remarkably improves the detection precision and is suitable for labeling sample scarce scenes. More accurate small sample target detection is realized by enhancing the feature expression of the support feature map and the semantic meaning of the category prototype, and higher robustness and recognition performance are shown in a complex scene.

The invention discloses a Busbar welding seam segmentation method and system based on improved YOLOv11, and the method comprises the steps: constructing a Busbar welding seam segmentation model which takes a YOLOv11 model as a reference network, and comprises a backbone network, a neck network, a head network and mask branches; an LSKA module is embedded after each down-sampling stage of the backbone network of the YOLOv11 model; a CIoU loss function in the training process of the YOLOv11 model is replaced by a Focaler-IoU loss function; the LSKA module is used for enhancing the feature sensing ability of the model to a welding seam global structure and a pole small target by linear calculation complexity through a decomposable large kernel convolution structure; and collecting an image of a Busbar welding area, inputting the image into the trained Busbar welding seam segmentation model, and outputting binary masks of the welding seam and the pole. According to the method and the system, feature attention to the welding seam and the pole column area is enhanced, feature extraction of the welding seam area is enhanced, it is ensured that the mask boundary is clear, and wrong segmentation is reduced.