12results about How to "Improve segmentation quality" patented technology

The invention provides a large-scale forest individual tree instance segmentation method and device based on laser radar point clouds, and the method comprises the steps: carrying out the voxelization processing of a forest point cloud to be subjected to individual tree instance segmentation, and obtaining a plurality of target voxels; obtaining voxel features, offsets and semantic tags of the target voxels according to a pre-trained sparse convolutional neural network backbone model; constructing an offset space according to the offset; determining a rough instance mask corresponding to each individual tree instance in the forest point cloud to be subjected to individual tree instance segmentation according to each target voxel and a predetermined average voxel number corresponding to individual tree instances of different tree species; determining coordinates and features of initial query vectors corresponding to the individual tree instances according to the rough instance masks; determining super-points, super-point features and super-point space coordinates corresponding to the forest point cloud to be subjected to individual tree instance segmentation; and based on a pre-trained model, the super-point features, the super-point space coordinates and the initial query vectors, obtaining a segmentation result, and realizing high-quality segmentation.

The invention relates to the field of network live broadcast, and discloses a live broadcast stream image segmentation method and device, equipment and a medium, and the method comprises the steps: sequentially calling image frames from an image sequence of a live broadcast stream as current image frames; a depth estimation segmentation model is called, a segmented figure mask corresponding to the figure image is determined based on the current image frame, and the depth estimation segmentation model is supervised and trained by using scene depth information; performing inter-frame smoothing processing on the segmented figure mask of the current image frame by using the practical figure mask iteration of the historical image frame to obtain a practical figure mask of the current image frame; and determining a figure image in the current image frame according to the practical figure mask of the current image frame. By fusing the depth information and the inter-frame smoothing technology, real-time, accurate and stable live broadcast stream image segmentation is realized, the live broadcast watching experience is improved, and the industry technology progress is promoted.

A small sample semantic segmentation method based on query autocorrelation enhancement belongs to the technical field of image segmentation, aims to solve the problems in the prior art, and comprises the following steps: step 1, constructing a network model: sharing a backbone network of weight; generating a prototype; the Transform decoder is used for inputting a support prototype and a query feature; the prior enhancement module is used for obtaining prior mask information with high guidance by utilizing interaction between high-level features; the feature enrichment module enriches query features from different scales by using a support prototype and a prior mask; filtering out a predicted mask from the query feature with an output of the decoder; 2, a data set is prepared, wherein the data set is preprocessed according to a small sample segmentation task; 3, training a network model: inputting the data set prepared in the step 2 into the network model constructed in the step 1 for training; 4, selecting a minimum loss function and an optimal evaluation index; and 5, finely adjusting and storing the model.

The application discloses a kind of semantic boundary guided robot operation scene point cloud segmentation methods. Firstly, the three-dimensional point cloud of robot operation scene is obtained;Then, the semantic boundary point in the scene three-dimensional point cloud is predicted using point cloud learning network;The scene three-dimensional point cloud is input into point cloud Transformer model for feature extraction, and the semantic boundary point is used as the extended key point of self-attention mechanism in Transformer model, wherein for the point feature of each boundary region, a contrast learning loss function is added to reduce the semantic ambiguity of boundary point feature;Finally, based on the point feature of each point, the semantic class of each point is predicted to obtain the point cloud semantic segmentation result. The application enhances the learned point feature by introducing semantic boundary information in the point cloud feature extraction process, and improves the misclassification problem caused by boundary ambiguous features, effectively improves the point cloud segmentation quality of robot operation scene, and has good engineering practical value.

This invention relates to a method, apparatus, and medium for rapid sorting of poultry meat percentage based on X-ray imaging. The method includes: Step S1: acquiring X-ray images of the poultry to be tested; Step S2: identifying the sternal region and skin boundary based on the X-ray image; Step S3: drawing a normal at the sternal apex, obtaining the intersection of the normal at the sternal apex and the skin boundary as the first surface point, and obtaining the initial bone-skin distance based on the distance from the sternal apex to the first surface point; Step S4: obtaining the angle between the X-ray machine's visual axis direction and the normal direction of the first surface point as the consistency difference angle, obtaining the sternal integrity ratio and sternal principal axis attitude angle based on the sternal region, and correcting the initial bone-skin distance based on the consistency difference angle, sternal integrity ratio, and sternal principal axis attitude angle to obtain the corrected bone-skin distance; Step S5: obtaining the meat percentage grading result based on the corrected bone-skin distance. Compared with the prior art, this invention can achieve poultry meat percentage sorting based on X-ray imaging.

The invention discloses a method for detecting sperm morphological anomaly through an improved Pasteur staining method, and relates to the technical field of morphological analysis, and the method comprises the following steps: carrying out staining treatment on a sperm smear by using the improved Pasteur staining method to obtain a training data set and a test data set; based on a U-Net network, designing a convolutional neural network VCA-Net applied to sperm morphological anomaly detection; based on the training data set and the test data set, performing model training and testing on the designed convolutional neural network VCA-Net to obtain a final convolutional neural network VCA-Net; and evaluating the final convolutional neural network VCA-Net by using the evaluation index to complete the anomaly detection of the sperm morphology by the improved Pasteur staining method. The problems that in the prior art, SMA automatic detection is difficult to achieve, and manual detection consumes time and labor and is large in workload and high in subjectivity under existing microscopic imaging are solved.

The application relates to a brain tumor image region segmentation method and device, a neural network and electronic equipment, and comprises the following steps: acquiring a brain MRI image, forming a data set, and pre-processing the data set; an improved residual attention block is constructed, and a multilayer perceptron therein is replaced; an improved network model is constructed, the number of the improved residual attention block is adjusted, and a replacement method is replaced by introducing the improved residual attention block; the trained network model is input into a test set for testing, and the network effect is verified; the application has the beneficial effects that the application is based on a convolutional neural network, proposes a brain tumor segmentation method based on an improved residual attention mechanism of UNet, that is, a double-branch model structure, compensates for the problem that UNet cannot utilize global information of an image, and can effectively improve model segmentation quality.

This invention discloses an automatic method and system for extracting landslide areas from remote sensing images based on few-sample enhancement and multimodal fusion. The method includes: acquiring and preprocessing multimodal remote sensing data; constructing a foreground-aware few-sample enhancement module, expanding the training samples through geometric transformation, spectral perturbation, and random cropping enhancement strategies; constructing a dual-branch feature extraction network to extract spectral and topographic features respectively; achieving adaptive fusion of spectral and topographic information through a cross-modal attention fusion unit; training a deep learning model using a composite loss function including cross-entropy loss, Dice loss, and boundary constraint loss; and performing topographic constraint post-processing and morphological optimization on the model output to obtain the automatic extraction result of landslide areas. This invention can achieve high-precision landslide identification under limited sample conditions, effectively reducing the false detection rate and improving the model's generalization ability and adaptability to complex scenes.

A multi-beam point cloud target detection method and device based on attention mechanism and geometric prior is disclosed. Belonging to the fields of underwater computer vision and 3D point cloud processing technology, this method includes a two-stage target detection network based on PointNet++. In the first stage, an elevation attention mechanism is introduced to suppress negative ground samples, significantly reducing excessive computational resource consumption and feature redundancy. In the second stage, a local geometric feature enhancement module is introduced to compensate for the loss of structural information caused by feature aggregation in traditional PointNet++ operators, enhancing the model's ability to characterize subtle geometric features and achieving an effective balance between high-precision target recognition and real-time processing performance.

The utility model discloses a rock core segmenting device which comprises a positioning mechanism and a cutting mechanism, and the positioning mechanism comprises a workbench and two V-shaped supports extending in the same direction; the cutting mechanism comprises a mounting plate, a blade, a rotation driving part and a lifting driving part. The rock core segmenting device provided by the utility model has the beneficial effects that when the rock core segmenting device is used, a cutting position is marked on a rock core to be cut, then the two ends of the rock core are respectively placed in the two V-shaped brackets, the cutting marking position on the rock core is positioned below the blade, and then the mounting plate is driven by the lifting driving piece to move downwards; meanwhile, the blade is driven to rotate by rotating the driving piece, so that the blade moves downwards while rotating, the rock core is cut, the rock core is segmented, and due to the fact that the cutting and segmenting mode is adopted, it can be guaranteed that the cutting face is flat, and the rock core segmenting quality is improved.

The present application relates to the technical field of tobacco processing, in particular to a kind of automatic tobacco stick cutting system and method;Including frame turning machine, intermediate conveying belt machine, slitting machine, loose belt machine and automatic control system;The frame turning machine is set in the front end of system, and can be lifted and turned over after the frame, and then the tobacco stick pile in the frame is transported to the next station;The intermediate conveying belt machine is connected with frame turning machine and slitting machine, and has the functions of buffer and accurate conveying;The slitting machine is provided with a flap mechanism, a second lifting mechanism, a cutter assembly and a knife pressing assembly, which can completely cut the tobacco stick pile after being transported from the intermediate conveying belt machine to the cutter assembly;In the process of controlling the frame turning of the frame turning machine, the tobacco stick pile is compressed by the discharge belt machine, so that the tobacco stick pile of different heights in the frame can be compressed, ensuring the integrity of the stacking form of the tobacco stick pile, and improving the subsequent cutting quality.

This invention discloses a 3D mesh segmentation method based on boundary awareness and contrastive learning, relating to the field of 3D segmentation in computer graphics and 3D vision. The method includes the following steps: data acquisition, labeling the segmented regions of the constructed 3D mesh, assigning a single integer label to each segmented region, labeling each edge of the 3D mesh with a category, forming a dataset from several labeled 3D meshes, and dividing the entire dataset into a training set and a test set; boundary determination and training a deep learning network using a contrastive learning method; model segmentation, obtaining the trained model, inputting other 3D meshes into the model, and finally outputting the mesh segmentation result. This method can improve the quality of mesh boundary segmentation results, making the boundary regions more accurate.