25results about How to "Good segmentation effect" patented technology

The utility model provides a kind of cut fresh steak machine, belong to meat cutting machine technical field.It solves the problem of slicer how to ensure the stable operation of machine when cutting fresh steak.The machine includes panel, cutter assembly and meat clamping assembly are provided on panel, meat clamping assembly includes the steel rope that middle part is upturned, the both ends of steel rope are connected with cylinder one and cylinder two respectively, cylinder one and cylinder two can drive the both ends of steel rope to be close to each other, at least one end of steel rope is configured to be slidable and is connected with driving element for pulling steel rope to make the middle part of steel rope arching contract.The both ends of steel rope can be moved towards the both sides of meat strip under the driving of cylinder one and cylinder two, so that steel rope can be embraced on meat block by fitting the contour of meat block, and after cutting is completed, cylinder one and cylinder two reset can drive the both ends of steel rope to be away from meat block, avoid sticking to meat block, affect subsequent cutting, so that the stability of continuously cutting out steak can be ensured.

The present application relates to a kind of forest leaf instance segmentation method and system based on deep learning, method includes: obtaining vegetation image, vegetation image is input into leaf instance segmentation model, obtains leaf instance segmentation prediction result;Leaf instance segmentation model is trained using training set;Training set includes: vegetation original image;Feature extraction and enhancement are carried out using backbone module in leaf instance segmentation model, and adaptive spatial fusion mechanism in progressive feature pyramid network is integrated to dynamically adjust feature weight, generate dynamic fusion feature;Through the dynamic asymmetric spatial perception mechanism built-in in dynamic anomaly regression head module, the corresponding multi-source deformation feature layer of dynamic fusion feature is obtained, and the feature fusion strategy of top-down cascaded decoding module is used to optimize multi-scale feature, obtain multi-source fusion feature layer, further using multi-source fusion feature layer, generate leaf instance segmentation prediction result.The present application solves the problems of data scarcity, poor adaptability and low efficiency.

The application discloses a biomass pyrolysis system for co-production of tar and fuel gas, which comprises a casing, a crushing mechanism and a crushing cylinder, the crushing mechanism is rotatably installed in the casing, the crushing cylinder is fixedly installed on the bottom of the crushing mechanism, the crushing cylinder is coaxially arranged with the casing, a crushing space is formed between the outer wall of the crushing cylinder and the inner wall of the casing, a feeding port is formed in the top of the casing, and an outer discharging port is formed in the bottom of the casing; a driving assembly is installed on one side of the casing, the output end of the driving assembly is drivingly connected with the crushing mechanism, the driving assembly drives the crushing mechanism to rotate in the casing, and a fixed gear ring is coaxially and fixedly installed in the casing. The biomass raw material can be crushed through the crushing mechanism, the biomass raw material can be finely processed to the maximum extent during crushing, and the pyrolysis speed can be improved during pyrolysis.

This invention discloses a semantic segmentation method for ocean internal wave stripes in SAR images, relating to the field of semantic segmentation of remote sensing images. The method model consists of an encoder and a decoder. The encoder comprises four Transformer modules, each containing a self-attention layer, a feedforward neural network, and an overlap patch merging module. Within each module, the input image is processed N times through a multi-head self-attention mechanism, and then the merging module generates feature maps at four scales. The decoder consists of three modules: a serpentine convolution, an EVC module, and an expectation-maximization attention network. The advantages of this invention are: the model fully utilizes the multi-scale fusion module, improving performance and robustness; the use of serpentine convolution can better extract features of linear shapes; and the use of the expectation-maximization attention network improves model accuracy while reducing computational complexity.

The invention belongs to the technical field of photovoltaic module recovery, and particularly relates to a device for segmenting photovoltaic glass and an EVA adhesive layer and a segmentation process. A photovoltaic glass heating area is used for heating the segmented photovoltaic glass and conveying the heated photovoltaic glass to be segmented to a photovoltaic glass segmentation area; the photovoltaic glass dividing area comprises an unpowered conveying roller, a pushing mechanism, a conveying belt, a dividing mechanism and a recycling box, and the pushing mechanism is used for moving the photovoltaic glass to be divided from the input end to the output end and conveying the divided photovoltaic glass to the conveying belt; an included angle is formed between a cutter of the cutting mechanism and the photovoltaic glass to be cut during cutting, and the included angle is 0-30 degrees. The photovoltaic glass cutting device has the function of heating photovoltaic glass to be cut, meanwhile, the angle of the cutter when the photovoltaic glass to be cut is cut is controlled, and the effect of removing an EVA adhesive layer is improved.

The application relates to a pulmonary embolism thrombus segmentation method and system based on a deep learning network. The method obtains a processed pulmonary arteriography image as sample data and divides a training set and a verification set; an original image is obtained by sampling the training set, tubular structure enhancement is carried out based on a Hessian matrix, and a blood vessel enhanced image is obtained; the original image and the blood vessel enhanced image are spliced into a double-channel lung image and input into a deep learning network, and a thrombus segmentation probability graph is output; a loss weight is dynamically updated through a same variance uncertainty learning strategy by combining an overlap constraint loss, a shape constraint loss and a classification constraint loss, and a pulmonary embolism thrombus segmentation model is trained to generate a thrombus three-dimensional segmentation result.

The application discloses a spine-pelvis joint segmentation method based on frequency-space cooperation and adaptive fusion, and belongs to the technical field of medical image processing. A joint segmentation dataset containing spine and pelvis structures is constructed, and standardization preprocessing is completed by supplementing pelvis annotation to public data and combining private clinical data; a multi-scale three-dimensional segmentation network is built, a frequency-space cooperation feature modeling HFSM module is introduced in the coding stage, local details and global semantic features are extracted through joint extraction in the spatial domain and the frequency domain; a selective cross adaptive fusion SCAF module is connected between the encoder and the decoder, boundary enhancement, structure perception and gate weight modulation are performed on different levels of coding features and decoding features, adaptive feature aggregation is realized, the network adopts an end-to-end training mode, a weighted combination loss function is used to optimize model parameters, and the joint segmentation result of the spine and the pelvis is output. The application can effectively improve the segmentation accuracy and integrity of the connection region, complex edge and small structure of the spine-pelvis.

The application discloses an image semantic segmentation model which is composed of a designed mixed attention focusing method, an attention rectification residual module (ARRM) and a mixed feature integration module (MFFM), is trained in a deep supervision mode as a whole, is reasonably provided with deformable convolution, is combined with a constructed multi-scale spatial attention module (MSP) and a double-pooling attention module (DPA) to be jointly optimized, and the problem of small target feature segmentation difficulty is solved. In order to reflect the excellent performance of the model on a downstream task, the training between different data sets is completed in a transfer learning mode, and the application range of the model is expanded. Finally, grouping convolution is added in the backbone network, the calculation cost is greatly reduced, and the problem of high training cost of the segmentation model is solved under the premise of guaranteeing the segmentation effect.

The application belongs to the technical field of image recognition segmentation, and discloses a medical image cell segmentation and tracking method, which comprises the following steps: step 1: data processing; feature extraction: the backbone part in the model is used to extract features from the preprocessed image, and the CSPDarknet structure is adopted in YOLOv8; step 3: FPN-PAN multi-scale feature fusion; step 4: Head prediction according to multi-scale features. The application realizes real-time tracking of the motion trajectory of cells by combining with a tracking algorithm such as deepsort. The method is mainly based on the YOLOv8 framework, and the Simam attention mechanism and the multi-scale proto method are adopted to optimize the model, so that the detection effect of YOLOv8 is further improved. The application can automatically complete the analysis and detection of medical images, is high in convenience and easy to use.

The application discloses a multi-scale intestinal polyp segmentation method fusing an attention mechanism. The basic features of the method are as follows: 1. a multi-scale effective semantic fusion module is constructed to extract more abundant and effective multi-scale semantic information; 2. a new encoding-decoding deep network segmentation model is constructed to improve polyp segmentation accuracy; the method extracts sufficient context information and global information under different receptive fields, and filters out as many features useless for the segmentation task as possible, overcomes the defects that semantic information is limited and a large amount of redundancy exists in the traditional encoding-decoding structure, and has excellent segmentation and generalization performance for two-dimensional enteroscopy images with polyp regions of different shapes and different sizes.

The application discloses an AI identification method, system and model training method for millimeter wave image overlapping targets based on a three-branch network, and solves the security target detection problem in millimeter wave images with low resolution, mutual interference or mutual overlap through collaborative work of three independent branch networks, namely, an analysis branch network, an aggregation branch network and a prediction boundary branch network. The analysis branch network saves the detailed information in a high-resolution feature map; the aggregation branch network realizes the feature position offset alignment of high and low resolution feature maps through a recursive fusion module; and the prediction boundary branch network extracts high-frequency features and enhances the perception and prediction of target edges. The multi-branch network structure effectively realizes the segmentation and identification of images through the fusion between branches. While improving the segmentation performance of the model, the model significantly reduces the calculation complexity and the detection error and missed detection probability in millimeter wave images, and finally realizes the accurate detection of overlapping objects.

The invention relates to the technical field of image processing, in particular to a tire surface barcode correction method and device based on density segmentation. The method comprises the steps of obtaining an initial barcode image; acquiring a bar code feature data set based on the initial bar code image, determining a bar code segmentation boundary position based on the bar code feature data set, and segmenting the initial bar code image based on the bar code segmentation boundary position to obtain a plurality of bar code area images; and performing correction processing based on the bar code area image to obtain a corrected bar code image. In this way, the uniformity of the bar code can be effectively recovered, and then the bar code recognition rate is remarkably improved.

The application discloses an image segmentation method and system, and relates to the technical field of medical image segmentation. The method comprises the following steps: acquiring a target medical ultrasonic image; inputting the target medical ultrasonic image into a trained image semantic segmentation model to obtain a final image segmentation map; the trained image semantic segmentation model comprises a trained first segmentation network and a trained second segmentation network; the trained first segmentation network is used for performing semantic segmentation on the target medical ultrasonic image to obtain an initial image segmentation map; the trained second segmentation network is used for performing feature extraction on the initial image segmentation map and the target medical ultrasonic image at multiple extraction scales to obtain multiple scale features, fusing all the scale features to obtain fused features, and obtaining the final image segmentation map according to the fused features. The initial image segmentation map output by the first segmentation network is input into the second segmentation network as prior knowledge for further segmentation, and the segmentation result of the tissue is improved.

The application discloses a medical image segmentation method combining selective edge aggregation and deep neural networks, first constructs a Transformer-based encoder, and replaces MSA and MLP in a standard Transformer block with a selective edge aggregation module and a densely connected feedforward network to realize feature fusion and complementation; then constructs an encoder and a decoder based on densely connected CNN, connects the two encoders in parallel, enables the network to interact information at multiple levels, and fuses multi-scale features from the double encoders and the low-to-high up-sampling path based on the decoder of the densely connected CNN to restore the spatial resolution of the feature map in a fine-grained and deep-level manner; finally, a loss function combining target edges and regions is designed to simultaneously optimize the encoder and the decoder with a multi-level optimization strategy, so that the network further learns more semantic information and boundary details to refine the segmentation result. The application can solve the medical image segmentation problem in a real scene.

The present application relates to a kind of based on battery pack reconstruction image image segmentation method, belong to computer tomography imaging technical field, solve the poor segmentation effect of battery pack reconstruction image in prior art.The image segmentation method includes: according to the preset shell size, the initial reconstruction image of battery pack is divided into shell region, air region and internal region;Pseudo detection is carried out to internal region, and pseudo region and non-pseudo region are obtained;According to the attenuation coefficient of each pixel point in internal region, preset glue layer attenuation coefficient and preset battery attenuation coefficient, non-pseudo region is segmented, and battery region and glue layer region are obtained.The segmentation effect of battery pack reconstruction image is improved.

The application discloses a radar image segmentation method and device based on THAM-ResUNet, and belongs to the technical field of ISAR image processing.The application is used to solve the problem that weak edge features of radar images relative to optical images result in difficulty in accurate segmentation.The ISAR space target image is obtained first, and then is sent to the THAM-ResUNet network for radar image segmentation; the THAM-ResUNet network is built based on the UNet network model, the THAM hybrid attention mechanism is arranged after each convolution module of the UNet network model, the output of the last THAM attention mechanism is subjected to a full connection layer to obtain the output vector of the THAM-ResUNet, and then the radar image segmentation is realized.

The application discloses a road network data processing method, obtains a bounding box corresponding to road network data, the bounding box can surround the road network structure corresponding to the road network data, and the bounding box has a starting point and an ending point corresponding to the road network structure. A set of intersections is extracted from the road network data, and the set of intersections includes the center points of the intersections. The starting point is taken as a target point, a first intersection with a center point and the target point meeting a preset condition is searched from the set of intersections, and the first intersection with a line connecting the center point and the target point not intersecting any road lane line is taken as a candidate intersection. If there is a first candidate intersection with a line connecting the center point and the ending point not intersecting any road lane line in the candidate intersection, the road network structure is divided based on the starting point, the ending point and the line connecting the center points corresponding to the first candidate intersection. Through the technical scheme provided by the application, the road network structure can be automatically divided, and the division effect is improved.

The invention discloses a ship wake extraction and segmentation method, a storage medium and terminal equipment, and belongs to the technical field of image processing and target monitoring. According to the method, accurate segmentation of different types of wakes is realized by analyzing texture features in an image. Firstly, a plurality of image features including image textures are extracted, then feature dimensions are reduced, and calculation efficiency is improved; clustering the images to realize segmentation of different wake regions; and finally, the segmentation effect is further optimized through an Otsu adaptive threshold method and a heuristic rule, and the connectivity of image regions is ensured. Experimental results show that the method can effectively distinguish the turbulence wake from other types of ship wakes, has high accuracy, and is suitable for the application fields of ship trajectory monitoring, environment monitoring and the like.

The application discloses a hook point cloud segmentation method and device, a storage medium, an electronic device and a computer program product, and belongs to the technical field of building construction. The method comprises the following steps: according to a steel cable suspension direction and a steel cable point cloud set, a hook candidate point cloud set is screened out from frame point clouds from a steel cable suspension point position to the ground; according to the steel cable suspension point position, the steel cable suspension direction and the hook candidate point cloud set, the height coordinate interval of the hook is determined; and according to the height coordinate interval, all point clouds of the hook are segmented from the hook candidate point cloud set, that is, the hook point cloud is segmented according to the actual steel cable point cloud and the steel cable suspension condition, so that the hook point cloud can be accurately segmented even in the case that the steel cable shakes, the point cloud is unevenly dense, the hook deformation form changes and the like, and the hook point cloud segmentation effect is good.

This invention proposes a method for image segmentation of head and neck tumor lesion regions and a computer-readable medium. The invention acquires multiple sets of original head and neck tumor PET-CT images, sequentially preprocesses them to obtain preprocessed images for each set, and labels them with corresponding ground truth classification tags. A lesion image segmentation network is constructed, and lesion segmentation prediction is performed using the input of each preprocessed image set to obtain a head and neck tumor prediction probability map for each preprocessed image set. Combining the ground truth classification tag of each pixel of the head and neck tumor lesion in each preprocessed image set, a cross-entropy Dessell weighted loss function is constructed, and the network is optimized and trained using a stochastic gradient descent algorithm to obtain a trained lesion image segmentation network. Real-time acquired head and neck tumor PET-CT images are then used to predict and segment the lesion region using the trained lesion image segmentation network, and probability thresholds are determined to obtain the real-time pixel range of the head and neck tumor lesion region. This invention utilizes the complementary information between multiple modalities to improve the accuracy of pixel region segmentation prediction for head and neck tumor lesions.

The utility model relates to the technical field of vegetable cutting devices, and discloses a quick-frozen vegetable cutting device which comprises a dividing and guiding frame, a conveying belt is fixedly installed on the inner surface of the dividing and guiding frame, a cutting and pressing mechanism is fixedly installed at the bottom of the dividing and guiding frame, and a dividing and guiding mechanism is fixedly installed at the top of the dividing and guiding frame. The cutting and pressing mechanism comprises a cutting box, a cutting assembly is fixedly installed on the inner surface of the cutting box and comprises a first motor, a first rotating shaft is fixedly installed at the output end of the first motor through a speed reducer, and a connecting rod is fixedly installed on the outer surface of the first rotating shaft. According to the quick-frozen vegetable cutting device, a second motor drives a second rotating shaft to rotate, the second rotating shaft drives a guide plate to rotate through a rotating frame, quick-frozen vegetables are led into cutting and pressing mechanisms on the two sides through the guide plate, and a first rotating shaft is driven by a first motor to rotate; the first rotating shaft drives the sliding block to move through the connecting rod.

The application discloses a walkable pavement detection method based on radar and vision fusion, comprising the following steps: acquiring point cloud data collected by a 3D laser radar and image information collected by a camera on a robot; performing ground segmentation on the point cloud data to obtain ground laser points and non-ground laser points; projecting the ground laser points into the image information to obtain corresponding projection points; taking a middle lower edge region of the image information as a ground region to intercept a ground reference block; comparing a projection block where the projection points are located with the ground reference block to acquire target ground points in the ground laser points. The application effectively solves the problems of poor segmentation effect, high misjudgment rate and low detection accuracy of the prior art when detecting a pavement.

This application discloses a multimodal medical image segmentation method and device with dynamic gating adaptive feature fusion, belonging to the field of image segmentation technology. The method includes: constructing a dynamic gating adaptive feature fusion architecture; the dynamic gating adaptive feature fusion architecture includes: a stochastic modality missing simulator and a medical image segmentation network connected sequentially; the medical image segmentation network includes: an independent feature encoding module, a quality-aware scoring sub-network, a dynamic gating controller, and a decoder connected sequentially; using a historical medical image dataset and the model's total loss function, the dynamic gating adaptive feature fusion architecture is trained using a five-fold cross-validation experiment, and the trained medical image segmentation network is determined as the segmentation model for multimodal medical image segmentation of target areas. This application achieves high robustness segmentation performance for modality missing and quality-impaired scenes by constructing a dynamic gating adaptive feature fusion architecture.

The application discloses a metal mesh defect detection method based on structural contrast information stacking, and steps are as follows: metal mesh images are shot by a microscope; input images are blocked, neighborhood structural contrast calculation is carried out on each sub-block image, and a difference matrix of the input image is obtained; the position of the sub-block is displaced in different sizes, neighborhood structural contrast calculation is carried out, a plurality of difference matrixes are obtained, and the results of each layer are superimposed to obtain a priori graph; a robust principal component analysis method is used in combination with the priori graph to decompose the input image, and a low-rank, sparse and noise image is obtained; a binary mask is constructed by using the priori graph, the sparse image is filtered to obtain a saliency map; and threshold segmentation is carried out on the saliency map to obtain a binary detection result. The application does not need a training process, can detect a plurality of defects of the metal mesh, can be generalized to defect detection under other periodic texture patterns, and is simple in parameter setting and high in detection efficiency.