15 results about "Region proposal" patented technology

The application discloses a kind of dual paradigm combined remote sensing image end-to-end fine-grained target detection method, it is related to computer vision and pattern recognition technical field, including: extracting multi-scale feature map by feature extraction network;Based on sparse directional proposal network, using one-to-one sparse matching strategy, generate no duplicate sparse directional region proposal and its corresponding proposal feature and coarse-grained target confidence;Based on query perception refinement head, using one-to-many dense matching strategy, obtain fine-grained classification probability and refined bounding box;In the training stage, introduce double auxiliary supervision head to provide additional dense supervision signal;In inference stage, adopt two-stage consensus scoring mechanism, finally obtain fine-grained target detection result.The method realizes the end-to-end remote sensing image fine-grained target detection without NMS dependence, through the cooperation of sparse and dense dual paradigm, effectively improves the positioning accuracy and fine-grained classification performance.

This invention discloses a controlled knowledge transfer-based generalized small-sample target detection method and system for marine remote sensing. The method includes the following steps: extracting multi-scale features from remote sensing images to generate multi-scale feature representations; generating candidate region features from the multi-scale feature representations via a region proposal network; inputting the candidate region features into a parameter-independent base class feature extraction branch and a new class feature extraction branch to generate base class features and new class features, respectively; performing a two-level fusion process on the base class features and new class features to generate fused features; applying dual constraints to the fused features using knowledge distillation loss and mutual information regularization loss, whereby the knowledge distillation loss constrains the consistency between the fused features and the base class features, and the mutual information regularization loss reduces the redundant correlation between the new class features and the base features; and inputting the fused features into a classification branch and a regression branch to obtain the detection results.

The present application relates to the technical field of detection data processing, and particularly relates to a textile fiber component analysis system and method based on machine learning; the direction gradient attention module provided in the embodiment has strong direction bias in feature representation before generating a candidate region proposal, which makes the region proposal network more easily locate the geometric center of the fiber according to the extension direction of the fiber, so as to generate a more compact and accurate candidate box, and lay a foundation for subsequent disentanglement of the adhered fiber. By focusing attention on several main directions related to the fiber, the direction gradient attention module naturally suppresses the edge response from random direction background noise, purifies the features, and improves the robustness of the model.

The application discloses a kind of feature fusion-based remote sensing image small target detection method and system, and the specific steps of the method are as follows: the remote sensing image to be detected is input into the network architecture mainly constituted by convolutional neural network and feature fusion network;Image will enter convolutional neural network and region proposal network after entering network architecture, region proposal network will cooperate with convolutional neural network to carry out pooling operation on image region of interest, while the deep feature of image region of interest is output to feature fusion network, image will obtain image region of interest after entering region proposal network, and the manual feature of image region of interest is output to feature fusion network by calculation;Deep feature and manual feature enter feature fusion network, and feature fusion network includes two feature conversion modules and a feature embedding module.

This invention discloses a method and system for stacked forging instance segmentation based on an improved Mask R-CNN. The method includes: inputting the image of the stacked forging to be detected into a trained DSFE-Mask network; first, inputting the forging image into an MResNet feature extraction network to generate multi-level feature maps; inputting the multi-level feature maps into an AFPN feature progressive fusion network to output multi-scale feature maps; inputting the multi-scale feature maps into a Region Proposal Network (RPN) to obtain candidate regions; mapping the candidate regions onto the feature maps of corresponding scales through a Region of Interest (RoI) Align layer; generating a high-precision instance segmentation mask on one hand, and outputting target category information and corresponding detection boxes on the other hand; and outputting the instance segmentation result of the stacked forging. This invention significantly improves segmentation accuracy and robustness, and experimental verification on an industrial stacked forging dataset shows a significant improvement in mAP.

The application discloses a feature enhancement fine-tuning method for cross-domain few-shot object detection, relates to the technical field of model fine-tuning, and solves the problem that it is difficult to extract robust features which can effectively focus on target regions and have strong semantic discrimination ability from limited samples in a cross-domain few-shot scene; the application comprises the following steps: obtaining enhanced instance features by enhancing instance features obtained from a support set through an instance feature enhancement module; for a query set image, generating region proposals, visual features and RoI features by applying a pre-trained detector, a region proposal network and an RoI alignment module, obtaining enhanced RoI features by reconstructing the RoI features through an RoI feature enhancement module; taking the region proposals, the visual features and the enhanced instance features as inputs, executing a positioning task and generating a positioning loss by a detection head; executing a classification task based on the enhanced instance features and the enhanced RoI features by a classification head, and generating a classification loss; and the application performs data enhancement at the feature level, thereby relieving the distribution sparsity problem under few-shot.

The present application relates to the technical field of image processing, in particular to a machine vision classification method for defect detection of an inductor automatic production line, comprising: acquiring an original gray image and a surface depth distribution map of an inductor to be tested on the automatic production line by using an image acquisition device; then extracting global histogram statistical features and local texture features of the gray image in parallel through a convolutional neural network, and performing normalization processing on the depth distribution map to obtain a depth topographic feature vector; then introducing a self-attention weighting module, taking the local texture features as a query vector, and generating a comprehensive feature map by fusing the depth topography and global statistical features; then inputting the map into a region proposal network, and screening out an inductor main body region of interest and a suspected defect region in combination with a preset aspect ratio anchor point; finally extracting semantic features by using a classification recognizer, and analyzing the spatial distribution of landmark points in combination with a polarity discrimination model to determine an inductor defect class label and a polarity direction angle.

The application provides a small sample fabric defect detection method based on category centroid calibration and dynamic discrimination constraint, acquires a fabric defect image dataset, and divides the dataset according to categories of a small sample target detection task; a small sample fabric defect detection network model is constructed; the fabric defect detection network model comprises a backbone network, a region proposal network and a detection head which are connected in sequence; a centroid feature calibration module CFCM is introduced between the backbone network and the region proposal network, and is used for processing input features based on a category centroid feature calibration method to guide different defect features to align to a stable global semantic centroid; a dynamic discrimination constraint module DDCM is introduced in a classification branch of the detection head, and is used for actively widening a discrimination boundary according to a semantic similarity relationship between a fabric image sample and a category prototype. The application can effectively maintain the stability of model detection and improve discrimination precision.

This invention relates to the field of power technology and provides a multi-target detection method for transmission lines based on a scene knowledge integration network. The method includes: acquiring an image of the hardware to be detected; extracting original scene features and region proposal features from the image using a Faster-R-CNN network; inputting the region proposal features into a pre-trained multi-layer convolutional network to obtain hardware structure information; processing the hardware structure information through a scene semantic feature pool to obtain enhanced features; fusing the enhanced features with the original scene features to obtain fused features; and detecting the hardware in the image based on the fused features. This invention can improve the detection accuracy of occluded hardware and small target hardware.

This invention relates to the fields of artificial intelligence and computer vision, specifically a multimodal learning method combining context optimization and ROI attention collaboration. The method includes: acquiring input image data and a target category text set; performing region proposal to generate candidate bounding boxes and ROI mask matrices; inputting the image into a frozen visual encoder and injecting ROI masks into the attention layer for spatial truncation, outputting clean visual features; constructing a continuous learnable context prefix matrix and concatenating it with category word vectors, then inputting it into a frozen text encoder to output text features; performing region-of-interest pooling on the clean visual features, combining them with text features to generate a predicted probability distribution, and obtaining the soft label distribution in the zero-sample state; calculating the KL divergence between the two and updating only the context prefix matrix to achieve multimodal alignment optimization. This invention solves the problem that traditional global image-text matching cannot support region-level tasks.

This invention discloses a method, apparatus, device, and medium for training an object detection model and for object detection, relating to the field of computer vision technology. The method includes: fusing a reliable image and an ambiguous image to obtain a fused image; the reliable image is an image that does not contain ambiguous object regions, and the ambiguous image is an image that contains at least one ambiguous object region; inputting the fused image into a region proposal network to obtain candidate regions in the fused image; correcting the labels of ambiguous object regions in the ambiguous image based on the candidate regions in the fused image; and training a model to be trained based on the corrected labels to obtain an object detection model. The technical solution of this invention can solve the problem of difficult manual labeling of ambiguous targets, reduce the interference of noisy targets on the model, and improve the stability of model training.

This invention relates to the fields of computer vision and information retrieval, and discloses a method, system, medium, and device for image-text retrieval of pedestrian clothing attributes based on a multimodal large model. The method includes: inputting an original pedestrian image into a region proposal network for body part perception to obtain detection boxes for each body part; inputting the segmented body part regions into a CLIP visual encoder to extract visual embedding vectors, and inputting a natural language query into a CLIP text encoder to generate text embedding vectors; constructing a preliminary adjacency matrix using the visual embedding vectors as nodes in a graph and inputting it into a graph convolutional network; processing the visual embedding vectors of the graph nodes and forming an overall clothing attribute representation through global information fusion; taking the visual embedding vector corresponding to the original image as the output of the graph convolutional network; calculating cosine similarity using the obtained text embedding vectors and visual embedding vectors; obtaining the cosine similarity of all images, and taking the top k images as the text retrieval query results.

This invention proposes a remote sensing image instance segmentation method based on multi-scale feature fusion and multi-resolution sampling mask generation, comprising: Step 1, acquiring a remote sensing image instance segmentation dataset; Step 2, constructing an improved Mask R-CNN network model, obtaining initial multi-scale feature maps using a backbone network (swin transformer) and a feature pyramid (FPN), and fusing them using a two-dimensional weighting module to obtain a fused multi-scale feature map. The fused feature map is then processed by a Region Proposal Network (RPN) to obtain the coarse location of each instance. The RoIAlign algorithm at multiple resolutions is used to extract feature maps of interest at the target locations in both the initial and fused feature maps. The fused feature maps of interest are used for classification and bounding box detection. Cross-attention is calculated between the feature maps of interest before and after fusion to predict the segmentation result; Step 3, training the instance segmentation model constructed in Step 2 using the remote sensing dataset; Step 4, using the trained model to detect remote sensing images.

The application provides a smart meter visual fault detection method and system based on multi-task routing and memory retrieval, which comprises: after normalizing and preprocessing a smart meter image, the image is input into a two-stage backbone network to extract features. In the base class training stage, the feature map generates a to-be-detected region feature through a region proposal network, and the region feature is sent into a multi-task dynamic routing module to adaptively decouple regression and classification task features; the classification features are input into a visual prototype memory regularization module to construct a memory bank, and the two types of features are jointly input into a task head to output a prediction and calculate a loss. In the new class fine-tuning stage, the task features are extracted through the multi-task dynamic routing; the classification features pass through a visual prototype semantic refinement module to calculate an attention weight, and weighted classification features are obtained, which are input into the task head together with the regression features to output a prediction, calculate a loss, and iteratively optimize the model. Finally, the to-be-detected meter image is input into the trained model to realize fault category detection.

The application provides a small sample fabric defect detection method based on feature uncertainty coding and feature storage S1: a data set is acquired, the data set is preprocessed, and the preprocessed data set is divided into a base class training set, a new class training set, a verification set and a test set; a small sample target detection network model is constructed; the small sample target detection network model comprises a feature extraction network, a region proposal network, an ROI head network and a detection head connected in sequence; the feature extraction network comprises a backbone network and a feature enhancement module in sequence; a feature uncertainty coding module is constructed in the region proposal network; a feature storage module is constructed in the ROI head network; a trained detection model is used to detect a test set image, and target positioning and classification results are obtained. The application realizes high-precision and high-robustness detection of fabric defects in a small sample scene by stabilizing the feature distribution of a new class.