13results about How to "Improve segmentation performance" patented technology

The invention provides a point cloud semantic segmentation method for improving a RandLA-Net network. The method comprises the following steps: step 1, carrying out data preprocessing grid downsampling; step 2, calculating a point cloud normal vector by a local curved surface fitting method; thirdly, local multi-dimensional feature fusion is carried out, and local geometric information is captured; fourthly, important features are automatically learned and aggregated through a self-attention module and attention pooling; 5, cascading an up-sampling result with the intermediate feature of the coding layer through jump connection; and 6, predicting the semantic tag by using a full connection layer. According to the invention, high-precision and high-efficiency automatic point cloud semantic segmentation in a large-scale outdoor scene is realized.

The invention discloses an MRI (Magnetic Resonance Imaging) brain tumor segmentation method based on a multi-scale attention mechanism and a secondary segmentation strategy, and belongs to the field of semantic segmentation. The method comprises the following steps: firstly, acquiring MRI brain tumor data and preprocessing the MRI brain tumor data; secondly, designing a 3D U-Net model, and combining a multi-scale attention mechanism and depth separable convolution to extract features; then, secondary segmentation guided by a cascade strategy is introduced; and finally, predicting by using the optimal model, storing and verifying a result, and calculating and comparing evaluation indexes. A depth separable convolution module is used for replacing a traditional convolution module, so that the parameter and calculation cost is reduced, and the segmentation precision is kept. In addition, a multi-scale attention fusion module is introduced to the first two layers of the encoder, the ability of capturing shallow information is enhanced, and important features are further extracted. A cascade attention mechanism is introduced into a decoder, and the segmentation capability of a small target area is improved. And training is carried out through a BraTS2020 data set, and the result shows that the optimized network significantly improves the MRI brain tumor segmentation accuracy.

The invention relates to the field of computer vision, and discloses a few-sample semantic segmentation method based on image-text fusion, comprising the following steps: S1, collecting and preprocessing data sets, grouping the data sets according to categories, each group comprising a plurality of support images and query images; s2, extracting multi-scale image features by using a pre-trained deep neural network; s3, extracting text features prompted by a preset text by using a text encoder; s4, fusing the extracted text features with the image features; s5, mining the correlation between the support image features and the query image features by using an attention mechanism; and S6, performing up-sampling on the fused image features, and decoding to generate a segmentation prediction result. According to the method, semantic information is supplemented through image-text fusion and text prompt, and the accuracy and performance of few-sample semantic segmentation are remarkably improved.

The invention provides a melanoma segmentation method fusing a convolutional neural network and Transform. The method comprises the following specific steps: step 1, obtaining a melanoma training set; 2, expanding the data volume of the training set by adopting a data enhancement technology, and further enhancing the general applicability or generalization ability of the constructed model; and step 3, by innovatively introducing an SViT-C encoder, the excellent local feature extraction capability of a convolutional neural network (CNN), the excellent global dependence modeling advantage of Transform and the spatial pyramid pooling characteristic of PSP-Net are fused. The encoder ingeniously utilizes local features to guide global features, so that higher-level semantic association is accurately captured; 4, implementing a model training process to optimize and determine a training weight; and 5, implementing detailed performance evaluation and robustness test on the independent test set.

The invention relates to the field of computer vision, and discloses a few-sample semantic segmentation method based on prototype perception, comprising the following steps: S1, collecting and preprocessing a data set comprising a training set and a test set; s2, dividing all the images in the data set into four fols which are equal in size and are not intersected according to categories; s3, extracting features of the support image and the query image by using a pre-trained deep neural network; s4, based on the support image features and the query image features, performing cyclic consistency screening to obtain a credible query feature set; s5, iteratively optimizing a foreground prototype and a background prototype by using the credible query feature set, and performing feature matching based on the optimized prototypes; and S6, inputting a test image, performing semantic segmentation through the optimized model, and calculating a segmentation result. According to the method, through high-confidence feature matching, cyclic consistency screening and cascade prediction optimization, the accuracy and robustness of few-sample semantic segmentation are remarkably improved.

The invention relates to a TransUNet liver parenchyma image segmentation method based on an attention mechanism, and the method comprises the steps: introducing AxialAttention and a residual connection mode in TransUNet, solving a problem of information loss in skip connection through the method, better capturing a long-range dependence relation between positions in a liver parenchyma feature map, and improving the segmentation accuracy of the liver parenchyma image. The accuracy and expression ability of the liver parenchyma segmentation model are improved.

The invention belongs to the technical field of medical image processing, and provides a left atrium and left atrium scar automatic segmentation method based on a cardiac medical image to solve the technical problem that the left atrium and left atrium scar segmentation precision is not very high in the prior art, and the method comprises the following steps: S1, carrying out the preprocessing of training data and test data, obtaining processed training data and test data; s2, training is carried out on a Boundy Loss Constrained Mutil-Attention U-Net model by using the processed training data, and five trained segmentation models are obtained; and S3, segmenting the processed test data by using the segmentation model to obtain five segmentation results, and taking an average value of the segmentation results as a final segmentation result. According to the method, the problem of class imbalance between the left atrium and the scar can be relieved, and the segmentation capability of the baseline model is remarkably improved.

The invention discloses an intelligent forest stand parameter extraction system based on laser radar point cloud data, which belongs to the technical field of laser radar point cloud data processing and forest resource investigation and comprises a multi-scale point cloud preprocessing module, a semantic guidance depth segmentation module, an intelligent parameter calculation module and a self-adaptive quality optimization module. High-precision and high-reliability intelligent extraction of forest stand parameters is realized through deep learning semantic segmentation of a Transform architecture, parameter calculation of confidence coefficient weighting, uncertainty quantification of Monte Carlo sampling and adaptive quality optimization of closed-loop feedback, a deep coupling relationship is formed among modules, the segmentation confidence coefficient directly affects the parameter weight, and the reliability of the forest stand parameters is improved. The uncertainty index triggers closed-loop adjustment, the adjustment parameter is fed back to the front module, a closed-loop optimization path of preprocessing, segmentation, parameter calculation, quality evaluation, adaptive adjustment and reprocessing is formed, and the precision and robustness of forest stand parameter extraction under a complex forest stand structure are remarkably improved.

This invention discloses a one-step generative segmentation method, system, and medium for 3D medical images based on the average flow model, belonging to the field of medical image processing technology. The invention acquires the 3D medical image to be segmented and anatomical condition information, samples Gaussian noise as an initial latent variable, and inputs it into a MeanFlow network after temporal embedding. Anatomical conditions are input into a VeloMod module to generate scale and offset tensors, and the MeanFlow network features are modulated pixel-by-pixel. The average velocity field is calculated using the average flow identity, and target distribution features are generated through one-step mapping. A 3D segmentation mask aligned with the original image space is output by a 3D decoder. This invention achieves single-step function evaluation and inference, significantly improving segmentation speed and anatomical fidelity. It possesses advantages such as small-sample generalization, multimodal robustness, missing modality compatibility, and strong interpretability, meeting the needs of real-time clinical navigation, intraoperative planning, and high-throughput screening. It has significant application value in the field of intelligent 3D medical image segmentation.

The invention relates to the field of computer vision and camouflage target segmentation, in particular to a camouflage target segmentation method of a reversible expansion network based on SAM guidance, which comprises the following steps of: firstly, constructing a foreground space priori graph, a background space priori graph and a high-quality SAM pseudo mask by utilizing a segmentation cutting model SAM; the prior redundancy is eliminated through low-dimensional orthogonal subspace projection, and the separability of the foreground and the background is enhanced; pixel-level and gradient-level feature fitting items and SAM subspace priori constraint items are fused to construct an overall objective function, the objective function is expanded into a multi-stage alternating iteration process of a foreground optimization submodule SFOS and a background optimization submodule SBOS, and a foreground feature map and a background feature map are refined step by step; and finally, generating a camouflage target segmentation mask according to the iteratively optimized foreground feature map. Through large model prior guidance, two-stage feature modeling and multi-stage expansion optimization, the integrity and accuracy of camouflage target segmentation are significantly improved.

The application discloses a SAM2 small sample segmentation method based on semantic-visual double memory fusion, constructs semantic query memory, visual query memory and query related support visual memory, fuses the semantic query memory and the visual query memory through a memory refinement module guided by the query related support visual memory, and combines SAM2 dense matching and decoding module end-to-end training. The method solves the single memory and foreground-background confusion problems of the existing method, enhances target semantic consistency and fine-grained modeling capability, significantly improves segmentation precision and generalization capability in a complex scene, and is suitable for medical image analysis, automatic driving and the like.

The application discloses a retinal cross-modal segmentation method and device based on domain-invariant contrast learning, relates to the technical field of medical image segmentation, and comprises the following steps: acquiring a retinal image; establishing a retinal cross-modal segmentation model; inputting the retinal image into the retinal cross-modal segmentation model to obtain a segmentation result of the retinal image, wherein the retinal cross-modal segmentation model is based on a U-net model as a basic framework, is trained by using image data of different modes, and is obtained through domain-invariant contrast learning and uncertainty perception self-integrated teacher framework. The application can effectively adapt to new modes and realize accurate image segmentation under limited labeled data.

The invention discloses an ultrasonic image defect segmentation method based on a memory bank-patch denoising diffusion probability model, and belongs to the field of ultrasonic nondestructive testing. The method is an ultrasonic image unsupervised automatic segmentation method which is based on a memory bank and does not need labels, a defect-free image is adopted to train an unsupervised anomaly detection model, and the trained model is used to carry out automatic defect segmentation on a defect-containing image. According to the method, the anomaly detection capability is improved through the memory bank module, automatic segmentation of ultrasonic image defects can be realized on the premise that data does not need to be labeled, and excellent segmentation performance is obtained. According to the method, the dependence on a large amount of manual annotation data can be effectively relieved, and a more accurate solution is provided for automatic segmentation of ultrasonic image defects.