31522 results about "Targeted detection" patented technology

A method for detecting an infrared ship target based on an improved YOLOv7 is provided, including the following steps: obtaining an infrared maritime ship data set; reforming a YOLOv7 network structure based on an MobileNetv3 network and a bidirectional weighted feature pyramid network, and obtaining an infrared ship target detection model by introducing an attention mechanism and an optimized loss function; training and verifying the infrared ship target detection model based on the infrared maritime ship data set to obtain the infrared ship target detection model trained; and detecting a maritime ship based on the infrared ship target detection model trained.

A 3D target detection method based on multimodal fusion and a depth attention mechanism includes the following steps: obtaining and preprocessing original point cloud data and original image data; inputting the preprocessed point cloud data and image data into a 3D target detection network based on multimodal fusion and the depth attention mechanism, where the 3D target detection network based on multimodal fusion and the depth attention mechanism includes a generation phase for 3D bounding box proposals and a refinement phase for 3D bounding boxes, and the network outputs parameters and classification confidence of a target bounding box; training the 3D target detection network based on multimodal fusion and the depth attention mechanism; and processing the collected lidar point cloud data and image data by using the trained detection network, and outputting 3D target information, to realize 3D target detection.

The present invention discloses an edge-guided RGBD underwater salient object detection method with multi-attention, which includes the steps of: S1 performing channel-dimension preprocessing on RGB image and depth map and serially connecting them to obtain an RMD image; S2 inputting the RMD image into a trained salient object detection model including an encoder structure and a decoder structure; and S3 obtaining salient images and edge images output from the salient object detection model as object detection results, in which the encoder generates feature maps with reduced resolution layer by layer using the RMD image based on a residual neural network, and the decoder structure includes an edge detection branch used to fuse the feature maps layer by layer, and a saliency detection branch used to fuse the feature maps and edge feature maps layer by layer. The present invention preprocesses the input image with underwater imaging features, and uses an edge prediction image to guide multi-layer salient object detection, thereby enhancing edge details of the salient image.

The invention provides a robot alarm processing method and system based on a target detection algorithm and a cloud platform, and relates to the technical field of robot alarm processing, and the method comprises the steps: carrying out the detection of an abnormal target based on a convolutional neural network target detection model of the cloud platform in combination with a residual structure, a channel attention mechanism and an improved anchor-frame-free target detection algorithm, performing feature fusion through a feature fusion network guided by depth information to obtain accurate three-dimensional representation data, constructing a dynamic anomaly association graph by using an improved time sequence graph neural network, and generating a multi-level decision sequence in combination with an improved hierarchical reinforcement learning algorithm, and finally, collaborative task planning is carried out through a task decomposition network to obtain a task allocation scheme, and the robot carries out exception handling according to the optimal motion track, obstacle avoidance track data, real-time pose data, key operation sequence data and contact force feedback data.

The invention relates to the technical field of computers, provides an automatic test script dynamic generation method and system based on multi-modal AI recognition, and is used for remarkably improving the coverage dimension and execution robustness of test cases while reducing the manual maintenance cost. The method comprises the following steps: acquiring target test interface data, extracting dynamic interaction characteristics in the test interface data, calling a trained target detection network to carry out element positioning processing on the test interface data, generating an interface element coordinate set, and generating a target test interface based on the interface element coordinate set. Calling a character recognition network to carry out multi-modal feature analysis on the interface element distribution information, and generating a feature fusion result containing character semantic features and icon classification features; the feature fusion result is input into a script generation model for dynamic path planning processing, automatic test script elements are output, and the automatic test script elements comprise logic control instructions generated based on the element operation sequence and coordinate self-correction parameters.

The invention provides a road traffic anomaly detection method and related equipment based on holographic perception, and the method comprises the steps: carrying out the time-space registration and preprocessing of video streams, point clouds, vehicle motion states, traffic parameters and environment data collected by multi-source sensor equipment of a target road network, and obtaining a multi-source data stream; performing feature acquisition and fusion processing through a preset target detection model and a feature extraction network to obtain target feature data and scene semantic information; establishing a space-time diagram data structure according to the target feature data and the scene semantic information, and performing target trajectory analysis through a space-time attention mechanism; and carrying out association analysis processing in combination with the analysis result and the environment data to obtain target behavior characteristics and interaction relation data, and realizing road traffic anomaly detection through the target behavior characteristics and the interaction relation data. Through multi-source data fusion and a deep learning model, the accuracy of environment perception is improved, and multi-dimensional information in a complex road network is captured for road traffic anomaly detection.

The present disclosure relates to the technical field of target detection, and particularly relates to a model deployment method, an end-side device and a storage medium, which are used for solving the problem in the related art of the accuracy of a deployed model being low. The method comprises: performing target detection on a video frame image input into a first model, and acquiring a first target detection result and a first confidence; if the first confidence is greater than or equal to a first confidence threshold value, recording the video frame image and the first target detection result as samples in a training set; if the first confidence is less than the first confidence threshold value, performing target detection on the video frame image on the basis of a second model, and recording the video frame image and an acquired second target detection result as samples in the training set; and training the first model on the basis of the training set, and replacing the current first model with a trained first model for subsequent target detection. In this way, the accuracy and model generalization capability of a first model are improved.

A target detection method, system and device based on cross-modal fusion and an attention guiding mechanism and a medium, the target detection method comprises the following steps: obtaining a visible light-infrared image pairing data set, and carrying out data processing and division on the visible light-infrared image pairing data set to obtain a training set, a verification set and a test set; constructing a multi-modal target detection network; setting network training parameters; training and optimizing the multi-modal target detection network by using the training set, outputting a training weight file after the training is finished, verifying the trained weight file by using the verification set, and selecting the weight file with the highest precision as an optimal weight file; loading the test set and the optimal weight file into a multi-modal target detection network, and performing target detection on the test set to obtain a target detection result; the system, the device and the medium are used for bearing and implementing the method. The method has lower false detection and false detection conditions, and improves the robustness and accuracy of target detection.

The invention discloses a rolled metal surface defect automatic labeling method based on a multi-task self-adaptive model, which comprises the following steps: S1, collecting a rolled metal surface image, preprocessing and enhancing the rolled metal surface image, performing data labeling, and constructing a rolled metal surface defect data set; s2, constructing a multi-task adaptive model, and training the multi-task adaptive model by using the data set to obtain an automatic defect labeling model; and S3, inputting a to-be-labeled metal surface image into the defect automatic labeling model, and outputting a surface defect labeling result by executing the target detection task. According to the method, a multi-task learning framework is combined, joint training of target detection and instance segmentation tasks of metal surface defects in the rolling technology is achieved, the target detection task is focused in the reasoning stage, the labeling efficiency is improved, the labor cost is remarkably reduced, and the labeling efficiency is improved. The method can be widely applied to industrial defect detection and data automatic labeling scenes of rolling process metal, and is suitable for defect image automatic labeling tasks in a complex industrial environment.

The invention discloses a manipulator grabbing method based on deep learning target detection and image segmentation, and relates to the technical field of artificial intelligence and robotics.The manipulator grabbing method comprises the following steps that a scene image to be processed is collected, the image quality is improved through the multi-light-source fusion image enhancement technology, and recognition errors caused by uneven illumination are reduced; and inputting the enhanced image to a pre-trained deep learning model, executing a target detection task, and outputting an initial bounding box and a category label of the target object. According to the method, through multi-light-source image enhancement and high-precision image segmentation, the accuracy of target recognition and contour extraction is remarkably improved, and the capture failure rate caused by image misjudgment is reduced. And meanwhile, geometric consistency verification and a multi-factor grabbing scoring mechanism are introduced, dynamic screening and collision pre-detection are conducted on the paths, the grabbing stability and safety of the mechanical arm in the complex environment are effectively guaranteed, and the intelligence and robustness of the whole system are remarkably improved.

The invention relates to the technical field of construction progress monitoring, and discloses a construction progress monitoring method and system based on big data. The method comprises the following steps: forming a space-time alignment data set through multi-source data acquisition, filtering and quality evaluation; performing feature extraction and registration to generate a digital model; target detection classification is performed to form a completion state table; progress evaluation is achieved through component-task mapping; trend analysis and risk identification are performed to generate a prediction result; decision reference is provided for personalized information screening and augmented reality display. Through multi-source data acquisition, fusion and intelligent analysis, accurate perception, objective evaluation, scientific prediction and visual presentation of the actual state of the construction site are realized, so that a comprehensive, accurate and prospective construction progress monitoring method is provided, the construction period delay risk is effectively reduced, and the construction management efficiency is improved.

The invention relates to the technical field of marine monitoring, in particular to a marine target visual servo tracking method, which comprises the steps of multi-modal sensor fusion, a self-adaptive visual tracking algorithm, a servo control and visual collaboration mechanism and a shielding processing and target re-identification strategy. The problem that tracking is unstable under the conditions of illumination change, ship body shaking, target shielding and the like in a traditional method is solved. The IMU, the GNSS and the visual data are fused through extended Kalman filtering, ship body shaking is compensated, and the target state estimation precision is improved; the improved D-Fi ne target detection model is combined with an online feature updating mechanism to dynamically adapt to the appearance change of the target; the prediction and correction control strategy and the double-closed-loop PI D controller cooperate to adjust the camera holder, and the tracking delay is reduced; the multi-clue shielding detection and space-time joint feature matching technology ensures accurate re-identification of the target after shielding is removed. The real-time performance and robustness of the tracking system on an embedded platform are improved, and an efficient and stable target tracking solution is provided.

The invention relates to a remote sensing target detection method and device and a medium, and the method comprises the steps: inputting a feature map to a backbone network for feature extraction, inputting an extracted feature tensor into a multi-branch expansion convolution structure, and extracting multi-scale features through convolution kernels with different expansion rates. Then, multi-scale features are fused through a space and channel double-path attention mechanism, and enhanced features are generated; and the enhanced features are further input into a cascade pooling module to generate multi-level reconstruction features, and weight coefficients are calculated through a gating fusion network to carry out weighted fusion, so that multi-scale fusion features are obtained. Next, these features are input into an asymmetric decomposition convolutional layer for downsampling, and dynamic channel attention calibration is performed to generate channel enhanced features. And finally, inputting the feature map processed by the backbone network and the neck network into a detection head network, and outputting a target bounding box and category prediction. According to the method, high-precision detection of multi-scale rotating targets and high-density small targets is realized in a complex remote sensing scene.

The invention relates to a multisource pavement disease identification method based on a language and an image large model, and the method comprises the following steps: collecting related standards of road pavement disease detection, building a knowledge corpus, and reading a road disease image through a large language model LLM; when it is determined by the LLM that the crack crosses the whole image, cutting is carried out in the direction perpendicular to the crack by passing through the center point of the image, and the image is cut into two images; afterwards, all images and corresponding text prompts are input, target detection is carried out on pavement diseases by using a visual language large model VLM, and a prediction box is output; and performing fine adjustment on the SAM by using the image marked with the disease mask to obtain the RoadSAM adapted to the road disease segmentation task. According to the method, a large language model, a visual language large model and a segmentation large model are combined, corresponding fine adjustment is carried out on the segmentation large model SAM, dependence on a large amount of annotation data is reduced, and meanwhile unified segmentation of multi-source and multi-mode pavement disease images is achieved.

The invention relates to the technical field of image target detection, and discloses a complex scene small target detection system and method based on mask attention and context feature optimization, and the system comprises a backbone network integrating a mask attention mechanism, a backbone network in which an original image is input into the integrated mask attention mechanism, and a background network in which the original image is input into the integrated mask attention mechanism. Redundant background information is filtered through a mask mechanism, and a multi-scale feature map is output; the context-aware enhanced feature refining encoder is used for carrying out multi-branch processing on the multi-scale feature map, and finally weighted fusion is carried out to generate a multi-scale fusion feature sequence; and the deformable Transform decoder inputs the multi-scale fusion feature sequence, processes the multi-scale fusion feature sequence through a cross attention and self-attention module, constructs a target query, and generates a detection result containing bounding box coordinates, category labels and confidence scores. According to the method, the performance of small target detection is improved by introducing efficient feature extraction, a fusion mechanism and a sampling and attention strategy.

The invention provides an engine internal damage identification method and system based on target detection, and the method comprises the steps: obtaining the distribution of thermal stress and mechanical stress under different working conditions through finite element analysis for typical working conditions of high temperature, high pressure and heat engine coupling load according to the structural characteristics and fault modes of an engine cylinder; processing an ultrasonic guided wave signal through a synthetic aperture focusing algorithm, reconstructing a three-dimensional shape of a crack by combining a three-dimensional geometric model of the cylinder body and guided wave propagation characteristics, and determining a crack propagation rate so as to analyze crack propagation of the cylinder body; the residual service life of the cylinder body under the given working condition is predicted according to the crack size, the crack growth rate and the high-risk working condition parameters in combination with the material mechanical property parameters of the fracture toughness; and according to the crack instability critical length, the cylinder body crack propagation analysis result and the high-risk working condition judgment result, the engine operation working condition is optimized, the occurrence frequency of the high-risk working condition is reduced, the service life of the cylinder body is prolonged, and the crack detection and recognition precision is improved.

The invention relates to the technical field of radar induction, and discloses a danger alarm method, device and equipment based on radar induction and a storage medium, and the method comprises the steps: carrying out the preprocessing of three-dimensional point cloud data collected by a laser radar and original image data collected by a security camera, and obtaining target point cloud data and target image data; constructing a target Voronoi diagram of the monitoring area; performing feature extraction and feature fusion to obtain a fused feature vector; inputting the fusion feature vector into a deep learning model for target detection and classification to obtain an initial detection result of each potential dangerous target; carrying out danger level evaluation to obtain the danger level and confidence of each potential danger target; according to the method, the monitoring parameters of the laser radar and the security and protection camera are optimized, the cooperation monitoring parameter combination of the equipment is output, the monitoring parameters of the laser radar and the security and protection camera are optimized in real time, cooperation monitoring of the equipment is achieved, and the overall monitoring efficiency of the system is improved.

The invention discloses a PPY-YOLO-based steel surface defect detection method and a PPY-YOLO-based steel surface defect detection system. The PPY-YOLO-based steel surface defect detection method comprises the following steps: step 1, preprocessing a steel surface defect image; 2, a neck structure Faster-Neck, a deep learning module C3K2Faster and a spatial pyramid pooling module SPPFSim are introduced into the YOLOv11 network, and a PPY-YOLO target detection model is obtained; step 3, training a PPY-YOLO target detection model; and 4, acquiring a steel image, and inputting the steel image into the trained PPY-YOLO target detection model to obtain the category and positioning information of the steel surface defects. A new model is constructed, the backbone network and the neck network are improved, the backbone network is formed by connecting the input end of the C2PSA module with the output end of the SPPFSim module, and an up-sampling group and a down-sampling group are added to the neck network, so that the model has a relatively good detection effect.

The invention discloses an unmanned aerial vehicle aerial small target detection method based on improved YOLOv8, and relates to the field of target detection, and the method comprises the steps: obtaining an unmanned aerial vehicle aerial image data set, and carrying out the preprocessing of the obtained data set; constructing an unmanned aerial vehicle aerial photography small target detection model based on improved YOLOv8, wherein the improved method comprises the steps of designing an SR-Conv module to replace a standard convolution module of an original backbone network, adding a small target detection layer, introducing a BiFPN to improve a neck network, and introducing a normalized weighted distance (NWD) loss function to optimize an original loss function; training the improved YOLOv8 unmanned aerial vehicle aerial photography small target detection model by using the training set; inputting a to-be-detected image into the trained target detection model to obtain a target detection result; the system, the equipment and the medium are used for implementing the method. The method can better aim at the unmanned aerial vehicle aerial photography small target detection task, improves the unmanned aerial vehicle aerial photography small target detection precision, and has wide applicability.

The invention relates to the technical field of target detection, in particular to a robot three-dimensional environment sensing method and device based on deep visual learning, and the method comprises the steps: collecting visual data based on a sensing system carried by a robot, carrying out the synchronous processing, extracting the spatial structure characteristics of a synchronous visual data stream and a preliminary semantic segmentation map, and carrying out the recognition of a target image; combining the spatial structure features with the preliminary semantic segmentation map to generate a geometric semantic feature map; extracting and optimizing local, regional and global features of the geometric semantic feature map, and performing three-dimensional modeling processing according to a multi-scale feature tensor to generate a three-dimensional geometric model; and carrying out fusion optimization on the structure information of the three-dimensional geometric model and the geometric semantic feature map, and carrying out verification processing based on a verification framework to obtain three-dimensional environment perception data. Through deep visual learning and visual data fusion, the defects of insufficient accuracy and limited deep semantic understanding ability in complex three-dimensional environment perception in the prior art are solved.

The invention provides a multi-target tracking detection method and system based on cascade matching and trajectory confirmation, and relates to the technical field of digital video monitoring and tracking, and the method comprises the steps: obtaining a personnel construction video, and decomposing a video frame into a plurality of images; identifying a target in the current frame of image based on an improved YOLOv5 network, obtaining a target detection frame, and obtaining a prediction trajectory frame of the current frame through a Kalman filtering algorithm based on the trajectory frame of the previous frame; performing multi-target tracking on the target detection frame and the prediction trajectory frame of the current frame by using a DeepSort algorithm, respectively obtaining motion features and appearance features of the target detection frame and the prediction trajectory frame, performing cascade matching on the motion features and the appearance features of the target detection frame and the prediction trajectory frame by using a Hungary algorithm, and performing matching optimization by using an IOU matching algorithm; and carrying out fusion updating on the successfully matched target detection frame and prediction trajectory frame by using a Kalman filtering algorithm, and replacing the original prediction trajectory frame to obtain a tracking result.

The present invention relates to the technical field of intelligent remote-sensing-image interpretation, and specifically provides a texture-aware and boundary-aware target detection method and system for a weak and small target in a remote sensing image. The method comprises: inputting a remote sensing image into a feature extraction network to extract a basic feature, and then extracting a texture-aware feature; inputting the remote sensing image into a boundary map extraction module to extract a binary boundary map, and then extracting a boundary-aware feature; fusing the boundary-aware feature with the basic feature by means of a boundary-guided feature module, so as to obtain a boundary-guided feature; and decoupling the texture-aware feature and the boundary-guided feature and outputting same, inputting the texture-aware feature and the boundary-guided feature into a task-decoupling RCNN for double-branch decoupling prediction, so as to obtain a classification and positioning result, and completing texture-aware and boundary-aware target detection. By means of the method and system in the present invention, information that is hard for remote-sensing weak and small targets to show can be mined, thereby further improving the expression of the weak and small targets, and thus improving the detection performance regarding the weak and small targets.

The invention relates to the technical field of target detection and tracking, in particular to a highway abnormal event detection and tracking method under the view angle of an unmanned aerial vehicle, which comprises the following steps: establishing an aerial photography historical data set of the view angle of the unmanned aerial vehicle; constructing a target detection model and a target tracking model, and training the target detection model and the target tracking model based on the historical data set; acquiring a real-time aerial image of a highway, inputting the real-time aerial image into the trained target detection model, and acquiring position information and environment information of a target vehicle; inputting the detected target vehicle information into the trained target tracking model, and obtaining the motion track information of the target vehicle; according to the position information, the environment information and the movement track information of the target vehicle, analyzing and judging whether the target vehicle has an abnormal event or not; and outputting a detection result of the abnormal event. The technical scheme of the invention can effectively capture the dynamic state of the vehicle and provide effective support for timely discovery and processing of abnormal events, thereby improving the safety and efficiency of road operation.

The invention discloses an unmanned aerial vehicle small target aerial photography detection method and system based on RT-DETR, a medium and equipment, and belongs to the technical field of unmanned aerial vehicle visual detection, aerial photography images are collected based on an unmanned aerial vehicle, the images are input into a trained target detection model, and target position and category information is obtained. The method comprises the following steps: firstly, extracting low-layer features of an image, and simultaneously capturing information of a channel dimension and a space dimension based on an efficient multi-scale attention mechanism; and outputting features through the convolution residual block. Key features are processed based on a single-scale feature interaction module; for the coded feature map, fusing information of a shallow layer and information of a deep layer step by step in an up-sampling and transverse connection mode; in a down-sampling stage, context semantic information of a target is reserved, and global and local information interaction is enhanced. According to the method, the accuracy and robustness of small target detection are remarkably improved, and the practicability and deployment value in actual application scenes such as unmanned aerial vehicle aerial photography and remote sensing monitoring are expanded.

The invention discloses an underwater small target detection method based on YOLOv8 improvement, and aims to solve the problem of small target detection caused by illumination variation, background complexity and target scale difference in an underwater environment. According to the method, optimization is carried out based on a YOLOv8 architecture, firstly, a star convolution StarsBlock in a StarNet backbone network is combined with a C2F module of the YOLOv8, an improved C2FStarsBlock module is obtained, and the diversity and robustness of feature extraction are remarkably improved. Secondly, a CARAFEEnhanced module is adopted to replace up-sampling operation of a YOLOv8 neck, and dynamic convolution, grouping convolution and a nonlinear feature enhancement strategy are introduced, so that the calculation efficiency and adaptability of the model are optimized; and finally, integrating a gradient-guided multi-scale convolution attention mechanism GMSAA, introducing the gradient-guided attention mechanism in a back propagation stage, accurately focusing on a target area, and reducing background interference. The method effectively improves the detection precision of the underwater small target, and is especially suitable for efficient automatic detection of small underwater targets such as marine organisms.

The invention provides an unsupervised video monitoring anomaly detection method and system based on semantic modeling, and belongs to the technical field of computer vision, artificial intelligence and video monitoring. Comprising the following steps: carrying out key frame identification on a monitoring video by adopting an image-text joint embedding model, and carrying out target cross-frame tracking based on a depth target detection algorithm to extract behavior semantic information so as to construct a semantic behavior map; sending the key frame sequence of the graph structure information into a frame prediction model, and predicting a next frame image or a target state; and carrying out abnormal scoring on the obtained prediction result, and carrying out threshold judgment by outputting a comprehensive abnormal score value so as to determine whether the current frame is an abnormal event or not. According to the method, the intelligent level and the overall efficiency of video anomaly detection can be effectively improved on the premise of ensuring the real-time performance and the stability, and support is provided for video monitoring anomaly detection in actual scenes such as smart cities, rail transit, industrial parks and commercial security.

The invention relates to the technical field of computer vision and multi-modal learning, in particular to a weak supervision target detection method guided by cross-modal pseudo labels. According to the method, a labeled source domain data set is constructed to train an image classification teacher model, and a teacher-student network structure is constructed; clustering the regional features of the target domain image, allocating pseudo tags to each cluster by optimizing the allocation cost between the source domain category and the target domain cluster, and constructing a pseudo tag pool; and training a student model on the pseudo label pool for region feature detection of the target domain image. According to the method, a cross-modal attention mechanism is introduced, so that more accurate semantic alignment between a source category label and a target domain feature is realized; the stability of label distribution is improved by a structure keeping regular term; the generalization ability of the model is further enhanced by multiple rounds of pseudo-label confidence learning. The method can be widely applied to tasks such as target detection, cross-domain transfer learning and open world recognition, and efficient and accurate weak supervision target detection is realized.

The invention provides an image acquisition card multi-mode identification method and system based on intelligent security and protection. The method comprises the following steps: acquiring a multi-mode original data stream according to a global clock signal of an image acquisition card; performing space-time calibration on the multi-modal original data stream to generate a synchronous multi-modal data queue; extracting a multi-modal feature tensor of the synchronous multi-modal data queue through data preprocessing; performing hierarchical attention fusion on the multi-modal feature tensor to generate a fusion feature matrix; performing channel pruning on the fusion feature matrix through a lightweight convolutional neural network, and constructing a target detection model; and determining a detection result corresponding to the multi-modal original data stream according to the target detection model. Through the synergistic effect of a global clock signal and a dynamic space-time calibration algorithm, a time synchronization and space alignment compensation mechanism is constructed in a multi-modal data stream, and the problem of multi-modal information complementary advantage attenuation caused by space-time mismatch is effectively solved.

The invention discloses a ship target detection method, device and equipment and a storage medium, relates to the technical field of image recognition, and discloses a ship target detection method comprising the following steps: obtaining a preset ship image data set; training a preset target detection model based on the preset ship image data set to obtain a ship target detection model, the preset target detection model comprising a feature extraction network, a feature fusion network and a multi-scale detection head which are connected in sequence, the feature extraction network is a lightweight convolutional neural network improved based on an attention mechanism; and obtaining a to-be-detected image, and performing ship target detection on the to-be-detected image through the ship target detection model to obtain a ship target detection result. According to the scheme, the ship target detection model has high real-time performance and accuracy when processing large-scale image data, and the detection precision of ship targets of different scales is improved.

The invention relates to a PCB defect detection method and system based on a YOLOv8 network, and belongs to the technical field of target detection. Collecting and preprocessing a PCB sample image data set for training a PCB defect detection model; inputting a to-be-detected image into the trained defect detection model to obtain a detection result; the to-be-detected image is generated by collecting and processing image data of the to-be-detected PCB; wherein the defect detection model comprises a trunk network, a neck network and a head network, and the trunk network extracts features through a mobile reverse bottleneck convolution module and a C2f module to generate an intermediate feature map; and the neck network performs splicing fusion on the middle feature map to generate a spliced feature map, the head network performs re-weighting on the spliced feature map through a convolution kernel attention fusion module to generate a third feature map, and then the detection module outputs a detection result. The method not only improves the precision of the defect detection model in detecting the features of the tiny target, but also improves the detection speed and generalization ability, and reduces the calculation cost and complexity at the same time.