Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

160results about How to "Good segmentation effect" patented technology

Multi-modal semi-supervised medical image segmentation method based on SAM adaptive fine tuning

The invention discloses a multi-modal semi-supervised medical image segmentation method based on SAM adaptive fine tuning, and the method comprises the steps: obtaining an original multi-modal image, adjusting the original multi-modal image to a preset size, and carrying out the image preprocessing, thereby obtaining a multi-modal image pair; simultaneously inputting the multi-modal image pair into a student branch model and a teacher branch model which are completely identical in structure, wherein each of the student branch model and the teacher branch model comprises a fusion module, an SAM encoder and a layered decoder; the multi-modal image pair passes through a fusion module formed by a convolutional network to obtain fusion features, the fusion features are input to the SAM encoder, and output features of different Transform layers are obtained; and inputting the plurality of output features into a hierarchical decoder, performing similarity calculation by the hierarchical decoder according to the plurality of output features to obtain prototype classification, and obtaining a prediction mask through a linear layer. According to the method, the multi-level features can be well utilized to realize fine-grained segmentation, and a good segmentation effect is realized.
Owner:SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI

Multi-modal nuclear medicine image segmentation method and system and storage medium

The invention relates to the field of image segmentation, in particular to a multi-modal nuclear medicine image segmentation method and system and a storage medium. Comprising the steps that image type classification is carried out on multi-modal medical examination images, focus area positioning is carried out, and CT (computed tomography) focus images and PET (positron emission tomography) focus images are obtained respectively; carrying out lesion geometric mutation form prediction on the CT fault lesion image, and carrying out multi-modal image fusion boundary correction on the CT fault lesion image and the PET lesion image to obtain multi-modal lesion image fusion boundary correction data; according to the multi-modal lesion image fusion boundary correction data, performing multi-modal lesion region segmentation combination optimization on the CT image and the PET image to obtain a lesion region segmentation combination optimization strategy; and carrying out image segmentation model construction on the lesion region segmentation combination optimization strategy based on a strategy gradient algorithm to obtain a lesion image segmentation model. According to the method, the image segmentation technology is optimized, so that the image segmentation technology is more perfect.
Owner:SHANGHAI MEIZHONG JIAHE MEDICAL IMAGING DIAGNOSIS CO LTD

Multi-task blood vessel segmentation model construction method based on hybrid encoder

The invention discloses a multi-task blood vessel segmentation model construction method based on a hybrid encoder. The encoder is a Swin Transform path multi-layer encoder based on a Mamform module, and the Mamform multi-layer encoder carries out data processing in combination with a W-MSA and an improved Mamba module; the decoder is a multi-task decoder and consists of three independent decoding paths which are respectively used for blood vessel segmentation, contour edge segmentation and blood vessel connectivity segmentation, and each decoding path adopts Swin Transformblock as a construction block and is used for generating feature mapping with the same size as an input image; an attention mechanism is shared, learned features are shared among decoders, the number of model parameters can be reduced, and overfitting is prevented; in the training process, a total loss function is formed through a loss function of a vascular connectivity decoding path, a self-distillation loss function and the like, the total loss function is calculated, model parameters are updated by using a back propagation algorithm, the segmentation performance of the model is gradually optimized, and after training is completed, the model can carry out precision on a vascular image.
Owner:LIAONING NORMAL UNIVERSITY

Double-encoder semi-supervised heart MRI double-ventricle segmentation method based on improved SAM

The invention belongs to the technical field of medical image processing, and particularly relates to a double-encoder semi-supervised heart MRI double-ventricle segmentation method based on improved SAM. A teacher model and a student model which are used both comprise double encoders, prompt encoders and mask decoders, each double encoder comprises a ViT branch and a CNN-Mama branch which are parallel, parameter fine tuning of the ViT branch is realized through a position adapter and a feature adapter, the CNN-Mama branch mainly comprises a convolution fusion Mama block and a second-order dimension attention block, and the CNN-Mama branch is used for realizing fine tuning of parameters of the CNN-Mama block. The convolution fusion Mama block introduces an enhanced convolution block on the basis of a VSS block, and the second-order dimension attention block uses a covariance matrix to mine second-order statistical information of data; carrying out weighted summation on the output features of the ViT branch and the CNN-Mama branch to obtain the output features of the double encoders; the output features of the double-encoder and the prompt encoder are input into a mask decoder to be decoded, and a segmentation result is obtained; and performing joint training on the teacher model and the student model based on interpolation consistency regularization semi-supervision, and using the trained student model as a segmentation model for double-ventricle segmentation of heart MRI. The segmentation model has strong feature extraction capability, can effectively extract the edge information of the ventricles and the boundary information of the double-ventricle connection region, and improves the segmentation precision.
Owner:HEBEI UNIV OF TECH

Remote sensing image ground object segmentation method based on hierarchical feature extraction and decoding

The invention discloses a remote sensing image ground object segmentation method based on hierarchical feature extraction and decoding, which relates to the technical field of remote sensing image processing, and comprises the following steps: step 1, collecting and preprocessing a remote sensing image, and constructing a training sample set; 2, constructing an image segmentation network, wherein the image segmentation network comprises a hierarchical encoder, a receptive field module unit and a network decoder which are connected in sequence; 3, training and optimizing the image segmentation network by adopting the training sample set to obtain a remote sensing image ground object segmentation model; and 4, collecting a remote sensing image to be segmented, and inputting the remote sensing image to the remote sensing image ground object segmentation model to obtain a ground object segmentation result. According to the method, the advantages of the advanced visual basic model and the U-shaped network architecture are combined, so that rapid and accurate segmentation of the ground target is realized.
Owner:耕宇牧星(北京)空间科技有限公司

Domain adaptation cross-modal medical image segmentation method and device based on boundary comparison, equipment and medium

ActiveCN119295491AEasy to learnFinely tune confidence weightsImage enhancementImage analysisData setSelf training
The invention provides a domain adaptation cross-modal medical image segmentation method and device based on boundary comparison, equipment and a medium, and relates to the technical field of medical image segmentation. The method comprises the following steps: respectively acquiring a source sample and a target domain image from a source domain data set and a target domain data set; the first image segmentation model is used as a teacher model, and weights are distributed for the pseudo labels of the target domain images; a training sample is obtained through bidirectional cross-domain cutmix; performing supervision and self-training by taking a weight learnable first model as a student model; combining supervision loss and comparison loss during training to pull a query sample to a prototype positive sample and push a boundary negative sample as a target optimization parameter, and obtaining a second image segmentation model; and finally, segmenting a second modal medical image by using the model. The method has significant advantages in cross-modal medical image segmentation, and the segmentation performance can be effectively improved.
Owner:CARDIOVASCULAR HOSPITAL AFFILIATED TO XIAMEN UNIV

Method and system for segmenting kidney region in dynamic kidney development image based on mixed attention branches

The invention discloses a method for segmenting a kidney area in a dynamic kidney imaging image based on mixed attention branches, which comprises the following steps: acquiring the dynamic kidney imaging image acquired by a single photon emission computed tomography (SPECT), and preprocessing the dynamic kidney imaging image to obtain a plurality of preprocessed images; and inputting each preprocessed image into a pre-trained kidney dynamic development image segmentation model to obtain a corresponding kidney region. The method can solve the problems that an existing kidney dynamic imaging image segmentation method based on classical UNet and variants thereof enhances feature transfer through jump connection, but the segmentation capability is limited when a kidney dynamic imaging image with rich details is processed; the technical problem that the kidney dynamic imaging image segmentation result is not accurate due to the fact that the model is difficult to accurately capture important features especially in the face of a complex anatomical structure and a low-contrast area is solved, and the technical problem that the existing kidney dynamic imaging image segmentation method based on the Transformer model cannot accurately capture important features when processing large-scale kidney dynamic imaging images is solved. A large number of computing resources are often needed, and the capturing capability of detail features is limited.
Owner:SHANGHAI CHILDRENS HOSPITAL

Underwater in-situ sea cucumber volume measurement method based on binocular vision and electronic equipment

An underwater in-situ sea cucumber volume measurement method based on binocular vision and electronic equipment belong to the field of image processing, are used for solving the problem of keeping in-situ sea cucumber volume measurement, and are technically characterized in that a sea cucumber image is detected in underwater images collected by a binocular camera to obtain a sea cucumber image detection frame; segmenting a sea cucumber image detected in the image according to the sea cucumber image detection frame, and calculating mask information of the sea cucumber on an image plane; mapping the mask information to a global point cloud constructed by binocular information, and obtaining point cloud data of the sea cucumber; performing grid reconstruction on the point cloud data of the sea cucumber to obtain a continuous triangular grid; according to the method, the continuous triangular grids are converted into voxel representation, the number of non-zero elements in the voxel grids and the volume of each element are counted, the volume of the grids is estimated, and the volume of the sea cucumbers is obtained, so that the volume of the in-situ sea cucumbers can be accurately evaluated, and more accurate data support is provided for scientific cultivation of the sea cucumbers.
Owner:DALIAN OCEAN UNIV

Jitter distortion correction image processing system for ophthalmology OCT (Optical Coherence Tomography)

The invention belongs to the technical field of image processing, and particularly relates to a jitter distortion correction image processing system for ophthalmology OCT, which comprises a data acquisition module, an SD-OCT acquisition device is used for acquiring an image of a human eye retina, and different colors are used for marking different layers in the image; the data set division module is used for dividing the collected and annotated images into different subsets, and dividing a test data set and a training data set; the data enhancement module is used for performing data enhancement on the training data set; the task establishment module establishes a training task, a test task and a detection task; the network model is used for executing a training task, a test task and a detection task, and processing an image of the human eye retina needing to be detected by utilizing the trained network model; the problems that in an existing method, a large amount of volume data is needed to serve as reference, consumed time is long, and a diagnosis system is complex are solved, dependence on large-scale reference data is reduced, and the processing efficiency is improved.
Owner:JILIN UNIVERSITY

Improved tissue ultrasound image segmentation lightweight system and method

The invention discloses an improved tissue ultrasonic image segmentation system, and the system comprises an improved image segmentation network model FSwinNet which achieves the efficient segmentation of an image in a resource-constrained environment. The image segmentation network model comprises one or more encoder modules, one or more decoder modules and one or more bottleneck blocks; the Swin Transformer of the encoder module uses an SFFN (Sandwich Forward Neural Network) sand clock feedforward neural network module, and the decoder module uses an MBDW (Multimedia Broadcast Downlink Weight) lightweight operator. The invention further discloses a method for carrying out tissue ultrasound image lightweight segmentation by using the image segmentation system, and the method has a wide application prospect.
Owner:EAST CHINA NORMAL UNIV

Remote sensing image segmentation method based on local consistency and pseudo label filtering

The invention discloses a remote sensing image segmentation method based on local consistency and pseudo label filtering. The method comprises the following steps: acquiring an optical remote sensing data set; constructing a remote sensing image segmentation model, wherein the remote sensing image segmentation model comprises a local consistency loss calculation module and a pseudo label filtering module; and inputting the optical remote sensing data set into the remote sensing image segmentation model to obtain a remote sensing image segmentation result graph. A local consistency loss and pseudo label filtering strategy is provided, local consistency features are effectively learned, pseudo label noise is removed, a good remote sensing image segmentation effect is obtained, more label-free remote sensing images are utilized to improve remote sensing image segmentation precision, remote sensing images acquired by satellites can be segmented, and remote sensing image segmentation efficiency is improved. The problems that in a remote sensing image, objects are dense, the background difference is large, the size change range is large, the color and texture difference is large, local consistency features are difficult to obtain, and a large amount of noise inevitably exists in a pseudo tag are solved.
Owner:XIDIAN UNIV

U-shaped neural network skin lesion segmentation method and equipment

The invention provides a U-shaped neural network skin lesion segmentation method and equipment, and relates to the technical field of image segmentation, and the method comprises the steps: S1, obtaining a skin lesion image set, carrying out the preprocessing and data normalization of the skin lesion image set, and obtaining a training data set; s2, constructing a U-shaped neural network, and training the U-shaped neural network through the training data set to obtain a trained U-shaped neural network; and S3, inputting a to-be-segmented skin lesion image into the trained U-shaped neural network to obtain a segmented skin lesion image. According to the U-shaped neural network, a coding and decoding device is composed of a fusion convolution Mangbar module, rich features can be extracted, a better segmentation effect can be achieved for skin lesions with fuzzy boundaries and low contrast, meanwhile, multi-level and multi-scale information fusion can be achieved by combining a space attention module and a channel attention module, and the method is suitable for being applied to skin lesions. And high-precision skin lesion segmentation is realized.
Owner:CHINA UNIV OF GEOSCIENCES (WUHAN)

Heart AI system based on deep learning

The invention discloses a heart AI system based on deep learning, and relates to the technical field of medical image processing, and the heart AI system comprises a two-dimensional fully-supervised left atrium segmentation algorithm module, a three-dimensional semi-supervised left atrium segmentation algorithm module, and a whole heart segmentation algorithm module. Meanwhile, through combination of Transform and a residual network, semantic information in the image is captured in a larger visual field, so that the segmentation precision of the network is improved; a two-dimensional fully-supervised left atrium segmentation algorithm module based on axial attention is provided from a two-dimensional angle by taking UNet as a basic model, the algorithm module firstly constructs a double-layer residual error convolution module, gradient information is transmitted through a plurality of paths, then a task-driven feature enhancement module is introduced to optimize feature representation, and finally, a task-driven left atrium segmentation algorithm is constructed. A multivariate feature fusion module is designed to integrate features, and finally a feature coupling module is designed, so that the limitation of traditional convolution operation is overcome.
Owner:ZHENJIANG ZHIMING TECH CO LTD

AI identification method and system for millimeter wave image overlapping target, and model training method

The invention discloses an AI identification method and system for a millimeter wave image overlapping target based on a three-branch network, and a model training method, and the method comprises the steps: carrying out the cooperative work of three independent branch networks: an analysis branch network, an aggregation branch network, and a prediction boundary branch network; the problem of security inspection target detection in millimeter wave images with low resolution, mutual interference or mutual overlapping is solved. The analysis branch network stores detail information in the high-resolution feature map; the aggregation branch network realizes feature position offset alignment of high-resolution and low-resolution feature maps through a recursion fusion module; and the prediction boundary branch network extracts high-frequency features, and enhances perception and prediction of the target edge. The multi-branch network structure effectively realizes image segmentation and identification through fusion among branches. While the segmentation performance of the model is improved, the model significantly reduces the calculation complexity, reduces the detection error and missed detection probability in the millimeter wave image, and finally achieves the precise detection of overlapped objects.
Owner:UNIV OF SHANGHAI FOR SCI & TECH

Medical image automatic segmentation method based on dual-aggregation hybrid neural network

The invention discloses a medical image automatic segmentation method based on a dual-aggregation hybrid neural network, and the method comprises the steps: inputting a to-be-segmented medical image into a pre-trained medical image segmentation network, and outputting a medical image segmentation result; according to the medical image segmentation network, a dual-polymerization mixed U-shaped network is adopted, the dual-polymerization mixed U-shaped network comprises two parallel encoders and a single decoder, and the two parallel encoders are a convolutional neural network and a Transformer respectively; local features and global features of the medical image are extracted at the same time through a convolutional neural network and a Transform; performing multi-scale feature fusion on the extracted local features and global features through a collaborative feature aggregation module CFA and a non-collaborative feature aggregation module NCFA; and inputting the features subjected to multi-scale feature fusion into a decoder, and outputting a medical image segmentation result. According to the invention, multi-scale feature fusion can be realized, the segmentation precision of a medical image segmentation result is enhanced, and the performance of a medical image segmentation network is improved.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Hierarchical Transform attention feature fusion-based iPSCs set pluripotency evaluation method

The invention relates to the technical field of iPSCs colony pluripotency evaluation, in particular to an iPSCs colony pluripotency evaluation method based on hierarchical Transform attention feature fusion, and the method comprises the following steps: collecting images in an iPSCs culture process, and establishing a mapping relation between stem cell pluripotency and cell colony morphology; constructing an iPSCs image data set, enabling each pixel in the image to correspond to a pluripotent state category, and marking a pixel level; building an evaluation model based on Transform attention feature fusion, wherein the evaluation model comprises a Gabor edge feature enhancement module, a layered Transform trunk feature extraction module and an attention feature fusion module; the obtained feature layers are fused after being subjected to up-sampling and normalization, and then a prediction image, namely an evaluation result, is obtained after decoding; training the model by using the iPSCs image data set; and carrying out pluripotency evaluation on the image in the iPSCs culture process by using the model obtained by training. According to the method, human factor interference can be prevented, and the precision of iPSCs set pluripotency evaluation is high.
Owner:GUANGDONG UNIV OF TECH

Image segmentation method and system for liquid crystal screen display

The invention relates to the technical field of machine vision, in particular to an image segmentation method and system for liquid crystal screen display. The method comprises the following steps: acquiring basic data of the liquid crystal screen; performing screen response characteristic analysis according to the basic data of the liquid crystal screen to obtain screen response characteristic data; performing multi-scale image acquisition according to the basic data of the liquid crystal screen to generate multi-scale image data; performing characteristic classification on the liquid crystal display according to the screen response characteristic data, and performing edge compensation analysis on the multi-scale image data to obtain edge characteristic compensation data; acquiring real-time data of the touch screen; and performing touch interference identification analysis on the real-time data of the touch screen according to the edge feature compensation data to generate touch interference mask data. By analyzing the screen response characteristics and performing edge compensation analysis, the phenomenon of edge blurring caused by liquid crystal response time limitation is reduced, and the accuracy of edge detection is improved.
Owner:SHENZHEN HUAHEXIN TECH DEV CO LTD

Hip joint X-ray film bone gap automatic segmentation measuring and grading method

The invention provides a hip joint X-ray film bone gap automatic segmentation measurement and grading method, and mainly solves the problems of subjectivity, low efficiency and low accuracy of manual intervention in an existing method. According to the implementation scheme, a data set is divided; respectively constructing a hip joint gap target identification network and a hip joint gap segmentation network; the discrimination performance of the model on the hip joint gap is improved through data enhancement and preprocessing; performing target identification on the hip joint X-ray film based on a convolutional neural network to obtain a to-be-segmented region image, and identifying a patient with a bone gap reaching a fourth-level disease; and segmenting a to-be-segmented region by using the hip joint gap segmentation network, obtaining a gap contour by using an edge extraction method, performing distance measurement, and performing illness state grading on an automatic measurement result. According to the method provided by the invention, a mode which is only limited to skeleton segmentation is broken, the automation degree and accuracy of hip joint gap measurement are improved, and the method can be used for automatic grading of diseases such as coxitis and ankylosing spondylitis.
Owner:FOURTH MILITARY MEDICAL UNIVERSITY

Lightweight 3D heart nuclear magnetic resonance image segmentation algorithm based on three-dimensional sparse MLP and 3D efficient deformable attention

The invention discloses a lightweight 3D heart MRI segmentation algorithm based on 3D efficient partial attention and three-dimensional sparse MLP, and the algorithm obtains an MRI pixel block with a detailed target region feature through a 3D efficient deformable attention module EDA, and fits the edge distribution of a segmented region with lower calculation complexity through reference point translation. Efficient attention calculation ensures feature information extraction and greatly reduces resource consumption; the method comprises the following steps: constructing a cross-shaped receptive field at extremely low cost through information in transverse, longitudinal and depth directions of a three-dimensional sparse MLP module (triSMLP) mixed voxel block, and outputting a fine characteristic spectrum with a global receptive field through three-time superposition; the feature maps output by the EDA and the triSMLP recover down-sampling lost detail features at an encoder through a partial convolution feature fusion decoder. Compared with most of the leading edge 3D segmentation algorithms at present, the method has the advantage that a better segmentation effect is obtained with extremely small computing resources.
Owner:CHONGQING UNIV OF TECH

Electromagnetic pump

The invention discloses an electromagnetic pump which comprises a coil assembly and a holder, the holder is fixed outside the coil assembly and used for conducting magnetism outside the coil assembly, the coil assembly comprises a coil framework on the inner side, and a front magnet yoke ring, a rear magnet yoke ring and an isolating ring are arranged in the coil framework. The isolating ring is located between the front magnet yoke ring and the rear magnet yoke ring, a first winding position, a partition position and a second winding position are longitudinally distributed on the coil framework, a first coil is wound on the first winding position, a second coil is wound on the second winding position, and the partition position corresponds to the position of the isolating ring. According to the electromagnetic pump, no coil is arranged at the partition position, the magnetic line of force at the partition ring is disconnected, the magnetic line of force segmentation effect is better, and meanwhile the coil cost is saved.
Owner:SHENZHEN VEOLO POWER CO LTD

NIR-II video lymphatic vessel segmentation method based on Frangi and multi-frame accumulation

The invention discloses an NIR-II video lymphatic vessel segmentation method based on Frangi and multi-frame accumulation, and belongs to the field of computer vision, and the method comprises the following steps: converting a video into a frame image; preprocessing the frame image by using a contrast limited adaptive histogram equalization algorithm and neighborhood mean filtering; performing top-hat transformation on the preprocessed image to obtain a rough foreground image; taking a mean value of non-zero pixels as a threshold value, and performing adaptive segmentation frame by frame; accumulating the output binary image, and enhancing a tubular structure in the image by using Frangi filtering; and performing certain morphological processing on the image after Frangi filtering to obtain a final lymphatic vessel segmentation result. According to the NIR-II video lymphatic vessel segmentation method based on Frangi and multi-frame accumulation, the detection capability of low-contrast lymphatic vessels with tiny disturbance in the video is improved.
Owner:SHANGHAI INSTITUTE OF TECHNICAL PHYSICS CHINESE ACADEMY OF SCIENCES

Light guide plate defect image data enhancement method and device and medium

The invention relates to a light guide plate defect image data enhancement method and device and a medium, and relates to the technical field of image data enhancement, and the method comprises the steps: obtaining a defect image and a corresponding defect type label, and constructing an original defect image data set; training the defect type prediction initial model through the original defect image data set to obtain a defect type prediction model after preliminary training; generating a potential defect image, and inputting the potential defect image into the preliminarily trained defect type prediction model; comparing the potential defect image with the defect image to obtain the similarity between the potential defect image and the defect image; selecting potential defect images of which the similarity is within a similarity threshold value and corresponding potential defect type labels, and constructing a potential defect image data set; and training the preliminarily trained defect type prediction model through the potential defect image data set to obtain a finally trained defect type prediction model. The light guide plate defect detection method has the effect of improving the light guide plate defect detection accuracy.
Owner:DONGGUAN CITY HYUNDAI SEIKO IND CO LTD

Improved YOLOv8s-based instance segmentation detection method and application

The invention provides an instance segmentation detection method and application based on improved YOLOv8s. The method comprises the following steps: collecting a to-be-segmented data set, preprocessing the to-be-segmented data set, constructing an improved YOLOv8s model, and training the preprocessed data set; the method is applied to target detection of images and / or videos, such as segmentation detection of second-phase particles of nickel-based superalloy. According to the improved model, an SPDConv layer and a small target detection layer are added, and an SIoU loss function is adopted, so that the small target detection performance of the model is greatly improved, and the omission ratio is reduced; second-phase particle dispersion calculation is updated and embedded into the second-phase particle identification process, batch detection is achieved, and indexes such as the average area fraction, the average number, the average size and the dispersion of the second-phase particles can be directly calculated; the model segmentation performance is good, the operation speed is high, the target detection process is opened, and the method can also be applied to other processes, intelligent recognition of macroscopic objects and online recognition and calculation of videos.
Owner:ZHEJIANG UNIV OF TECH

Blood vessel segmentation method based on perceptual tissue rule

The invention discloses a blood vessel segmentation method based on perceptual tissue rules, and belongs to the field of image processing. Comprising the following steps: establishing perceptual organization rules; establishing a neural network based on a perceptual organization rule; establishing a semi-supervised learning method based on a covariant rate; setting a 3D image mode; and defining a loss function and setting an experiment. The method is inspired by a human visual system and comprises two key parts: a neural network based on a perceptual organization rule and a semi-supervised learning method based on a covariant rate. And by calculating perceptual tissue rules such as similarity, proximity and continuity, expression of vascular coherence structure features is enhanced, so that the segmentation effect is improved. The blood vessel segmentation method disclosed by the invention shows excellent diagnostic ability in assisting doctors in clinical diagnosis and treatment, and can be used for quickly analyzing and processing the condition of a patient.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Railway construction protection method and system

The invention discloses a railway construction protection method and system, and the method comprises the steps: firstly, setting hyper-parameters based on a construction operation position; secondly, acquiring video stream data of a construction scene in real time based on an unmanned aerial vehicle; secondly, segmenting a railway in the obtained video stream data by adopting an instance segmentation algorithm, and obtaining pixel point coordinates of an uplink track and pixel point coordinates of a downlink track; then, based on the pixel point coordinates of the uplink track and the pixel point coordinates of the downlink track, a fitting straight line of the uplink track and the downlink track is calculated; then, based on the fitting straight line of the uplink track and the downlink track, an electronic fence is automatically generated; and finally, based on the coordinate position of the constructor and the electronic fence, whether the constructor breaks into the dangerous area is judged. According to the method, the instance segmentation algorithm is adopted to segment the railway, the segmentation effect is good, manual drawing of an electronic fence is not needed, and only the unmanned aerial vehicle needs to be carried to a designated construction site without external cooperation.
Owner:CRSC RESEARCH & DESIGN INSTITUTE GROUP CO LTD

Semantic segmentation model training method, semantic segmentation method and device

The invention relates to the technical field of image processing, in particular to a training method of a semantic segmentation model and a semantic segmentation method and device. Comprising the following steps: acquiring and preprocessing tree-containing images, and constructing an image set; carrying out image segmentation based on a U-Net architecture, wherein the U-Net architecture comprises an encoder, a decoder and a jump connection; based on Dice coefficient loss and weighted cross entropy loss, determining a total loss function to optimize image background and tree category imbalance; the learning rate is adjusted in each training step through an Adam optimizer in combination with gradient first-order moment estimation and gradient second-order moment estimation, and learning rate attenuation adjustment of the Adam optimizer is achieved in combination with cosine annealing scheduling; and training the semantic segmentation model based on the configured Adam optimizer and cosine annealing scheduling until the semantic segmentation model is obtained through convergence. Therefore, based on the obtained semantic segmentation model, subsequent image segmentation processing application in an education robot can be facilitated.
Owner:北京爱宾果科技有限公司

Water area ecological environment pollution monitoring system

The invention relates to the field of image processing, in particular to a water area ecological environment pollution monitoring system which comprises a water area ecological image acquisition module, an edge image acquisition module, an adhesion rate acquisition module, a segmentation module and a water area ecological environment monitoring module. Obtaining the number of edge pixel points under different gradient thresholds according to the gradient amplitudes of all pixel points in the water area ecological image so as to obtain the mutation degree of each gradient threshold, obtaining an optimal edge image according to the mutation degree so as to obtain an aquatic product binary image, obtaining the adhesion rate of each pixel point in a connected domain of the aquatic product binary image, and obtaining the adhesion rate of each pixel point in the connected domain of the aquatic product binary image. And obtaining the size of a structural element of the pixel point according to the adhesion rate, carrying out morphological corrosion on each pixel point in the connected domain to obtain a segmented image, and carrying out water area ecological environment monitoring. The method has a good segmentation effect on the overlapped aquatic products, facilitates dynamic tracking of the aquatic products, and ensures the accuracy of water area ecological environment monitoring.
Owner:SHENZHEN RUICHIAN ELECTRONIC TECHNOLOGY CO LTD

Mask R-CNN-based infrared image segmentation method

The invention provides an infrared image segmentation method based on a Mask R-CNN (Region-Convolutional Neural Network). According to the method, a Mask R-CNN network is used as a basic framework, and an improved attention module is added in the Mask R-CNN network to improve the recognition and segmentation capability of the model on an infrared target. And then a new regression frame loss function and a new mask loss function are designed to replace a loss function of a corresponding part of the original network, the problems that the convergence speed of the original network is too low and foreground and background are unbalanced are solved through an optimization mode without increasing parameters, and the stability of the model in the training process is further improved. In addition, the invention also constructs an infrared image data set containing four types of targets of people, vehicles, bicycles and unmanned aerial vehicles, and divides the infrared image data set into a training set and a test set. The training set is used for training the improved model to obtain optimal parameters; the test set is used for verifying the effect of the improved model and completing the recognition and segmentation of the target in the infrared image. Compared with other infrared image segmentation methods based on deep learning, the infrared image segmentation method based on deep learning has higher segmentation precision and better segmentation effect.
Owner:NANJING UNIV OF SCI & TECH

Novel ceramic tile cutting tool

The invention discloses a novel ceramic tile cutting tool which comprises a base, a guide rail, a supporting plate and a handle and further comprises an adjusting device and a rotating assembly. The adjusting device comprises a gear and a rack area which is matched with the gear and provided with a rack, the rack area is located on the supporting plate and connected with the guide rail, and the gear rotates to drive the rack area and the guide rail to move; the rotating assembly is connected with the cutter wheel and comprises a rotating wheel, and the handle is connected with the rotating wheel and rotationally arranged on the guide rail through the rotating wheel. The gear is matched with the rack, the gear is rotated to drive the rack to move to achieve left-right movement of the rack area, the guide rail is fixed to the rack area, and therefore the cutter wheel fixed to the guide rail is finely adjusted front and back; through the rotating assembly, the handle can rotate along the guide rail while moving along the guide rail, the height of the cutter wheel connected with the handle is further adjusted, and up-down and left-right adjustment is achieved.
Owner:HUANGSHAN FUZHEN INTELLIGENT TECH CO LTD

Pixel-level polyp segmentation method based on parallel feature enhancement and attention mechanism

The invention provides a pixel-level polyp segmentation method based on parallel feature enhancement and an attention mechanism. A network model adopts HarDNet68 as an encoder to extract multi-scale feature information; in the jump connection part, a parallel feature enhancement module is embedded to extract high-level representation of features; meanwhile, the advanced features are aggregated by using a parallel partial decoder to generate a global guidance; and finally, a reverse attention module is adopted to guide information to be spread from a global range to a local range, and fusion and refinement of boundary features are enhanced.
Owner:MINJIANG UNIVERSITY