159results about How to "Improve Segmentation Accuracy" patented technology

The invention discloses a tumor CT image segmentation method based on an SAM large model, and belongs to the field of image segmentation. The method comprises the following steps: respectively inputting a CT image to be segmented into a Unet encoder and an SAM encoder, and carrying out multi-scale cross-model fusion on output features of the Unet encoder and the SAM encoder to obtain a target fusion feature map; performing segmentation prediction based on the output characteristics of the Unet encoder by using the Unet decoder, and generating a sparse prompt point set of each category based on a segmentation prediction result; inputting the sparse prompt point set of each category into an SAM prompt encoder to obtain sparse prompt position codes and dense prompt position codes; and inputting the target fusion feature map, the sparse prompt position code and the dense prompt position code into an SAM decoder to obtain a final segmentation result. According to the scheme, the defects that in an existing segmentation method, manual prompt is relied on, and missing detection and misjudgment of small targets and multiple targets are remarkably reduced can be overcome.

The invention discloses a medical image segmentation method, system and device based on multi-attention and multi-scale fusion, and relates to the technical field of image segmentation, and the method comprises the steps: constructing an MAMF-Net model which comprises an encoder and a decoder which are in multi-layer jump connection; the encoder adopts a hybrid architecture of convolution and Transform, and is integrated with a self-adaptive expansion convolution method; the decoder integrates dual-channel attention gating and a multi-scale global channel feature enhancement method to enhance features transmitted by jump connection, and combines features extracted by the encoder to fuse and reconstruct a segmentation result; training the MAMF-Net model by adopting the historical medical image sample set to obtain a medical image segmentation model; and obtaining any medical image to be identified and inputting the medical image to the medical image segmentation model, and determining a corresponding segmentation result. The problem of insufficient fusion of global semantics and local details in medical image segmentation is solved.

The invention relates to the image processing field, and especially relates to an airborne infrared image ship target segmentation method comprising the following steps: carrying out LBP characteristic value extraction to obtain an LBP characteristic image; obtaining a mode filtering smooth LBP feature image; performing adaptive threshold segmentation; filling a hole area; multiplying the image with the filled hole region by the airborne infrared gray level image pixel by pixel to obtain a region-of-interest image; obtaining an edge detection image; extracting all boundaries of the edge detection image to create a mask image; segmenting the interest region image by using an improved firefly algorithm to obtain a highlight target segmentation image; and multiplying the highlight target segmentation image and the mask image pixel by pixel to obtain a ship target segmentation result image. The ship texture difference is accurately captured through the LBP features, the improved firefly optimization algorithm is combined, different sea conditions and noise interference can be dealt with, the error segmentation rate is reduced, multi-threshold solution is combined, and the segmentation requirements of complex images can be met.

The invention discloses a remote sensing image semantic segmentation method and device, and relates to the field of deep learning, and the method comprises the steps: inputting a category name obtained based on a pixel-level semantic tag into a semantic segmentation model, and obtaining a first optimization text feature; carrying out feature fusion on a third-layer visual feature map in the encoder multi-layer visual feature map output by the image encoder and a fourth-layer visual feature map output by the first multi-scale visual state space block in the image decoder to obtain a first fused visual feature map; performing cross-modal fusion on the first fusion visual feature map to obtain a semantic enhancement multi-modal enhancement feature map; inputting the semantic enhancement multi-modal enhancement feature map into an image decoder to obtain a semantic segmentation prediction map of the sample remote sensing image; training a semantic segmentation model based on the calculated total loss to obtain a trained semantic segmentation model; and inputting the obtained remote sensing image to be segmented into the trained semantic segmentation model for semantic segmentation, so that the segmentation precision is improved.

The invention discloses a remote sensing image segmentation method based on multi-scale wavelet transform and Mama. The method comprises the following four steps: firstly, carrying out preprocessing and division on an ISPRS Potsdam data set and a Vaihingen data set; then constructing a segmentation network, wherein the network comprises a local detail extraction branch, a spatial semantic extraction branch, a cross-branch feature fusion part and a decoder; training and optimizing the network by using the training set; and finally, performing segmentation reasoning on a test image by using the trained model. According to the method, the high-frequency detail extraction capability of the image is enhanced through multi-scale wavelet transform, the long-distance dependency relationship is modeled by using the visual state space block, and effective fusion of the features is realized through the double-branch fusion module, so that the feature extraction capability and the semantic segmentation precision are improved, and meanwhile, the training efficiency and the stability are optimized.

The invention discloses a road crack segmentation method and device based on deep learning, electronic equipment and a program product. According to the method, two collaborative and functional complementary processing paths are adopted to perform parallel processing on a to-be-segmented image so as to obtain corresponding feature information: on one hand, the to-be-segmented image is converted into a feature sequence containing spatial position information, and global semantic modeling is performed on the feature sequence; global semantic features representing the overall shape of the crack and long-range semantic dependence are obtained; and on the other hand, local texture and edge detail information of the crack is directly extracted from the to-be-segmented image, and detail enhancement features are obtained. Thirdly, fusing the global semantic features and the detail enhancement features to obtain target fusion features considering crack positioning, connectivity and boundary and texture expression; according to the segmentation result output based on the target fusion features, even tiny cracks can be effectively depicted, and then the continuity, boundary definition and robustness of tiny crack segmentation under the complex road background can be improved.

The invention provides a split-phase cooperative asphalt mixture digital image multi-component segmentation method, and relates to the field of asphalt mixture image segmentation, and the method comprises the steps: obtaining a digital image of an asphalt mixture section, converting the digital image into a gray image, and carrying out the preprocessing of the gray image, and obtaining a to-be-segmented image; performing gap segmentation on the to-be-segmented image to obtain a gap phase image mask; segmenting the to-be-segmented image by using the RAN-UNet deep learning image segmentation model to obtain an aggregate image mask; performing three-dimensional voxel reconstruction to obtain a three-dimensional digital model, and performing connectivity analysis and edge detection to obtain a connected gap mask, an open gap mask and a closed gap mask; performing critical particle size screening and structural gap identification to obtain a structural gap mask and a mortar internal gap; and carrying out particle size screening on the aggregate image mask, extracting an asphalt mortar region, and slicing and converting the asphalt mortar region again to obtain a mortar phase image. According to the invention, the segmentation precision of the asphalt mixture digital image is improved.

This invention belongs to the field of medical image processing technology, specifically relating to a method for abdominal multi-organ medical image segmentation based on a state-space model. Addressing the shortcomings of existing technologies such as the difficulty of CNNs in modeling long-distance dependencies, the high computational complexity of Transformers, and the large semantic gaps, incomplete segmentation contours, and easy organ encroachment issues in VM-UNet skip connections, this solution makes key improvements: It constructs an improved VM-UNet-Skip architecture, placing skip connections before downsampling to reduce the semantic gap between the small decoder features; it introduces a multi-scale global-local information aggregation module, capturing global anatomical dependencies through multi-head Mamba units and enhancing local detail representations with a convolutional gated feedforward network; and it relies on the VMamba encoder-decoder to achieve efficient feature extraction and reconstruction. The method flow includes: constructing initial feature representations through patch embedding layers, extracting multi-scale hierarchical features through the encoder, enhancing features through an information fusion module, and fusing and mapping the enhanced features to obtain the segmentation result through the decoder. This invention effectively improves the segmentation accuracy of abdominal multi-organs, solves the problems of insufficient contour integrity and organ encroachment, while reducing the number of model parameters and computational complexity, providing reliable technical support for clinical diagnosis and surgical planning.

The invention provides a tunnel supporting structure segmentation method and system based on flatness characteristics, and belongs to the technical field of tunnel engineering digital construction and quality detection, and the method comprises the steps: obtaining point cloud data in a tunnel, and carrying out the data preprocessing; supporting structure staged feature extraction is conducted on the tunnel internal point cloud data after data preprocessing, and the method comprises the steps of initial support contour extraction and ground segmentation, specifically, initial support contour point cloud is accurately extracted by adopting a robust model fitting method fusing point cloud normal constraint based on contour geometric features of an initial support conforming to a design line shape; meanwhile, based on plane features of the ground, segmenting and removing ground point clouds; and second lining segmentation: based on flatness characteristics of smooth surface of the second lining, through a two-stage strategy of point cloud local roughness calculation, threshold screening and region growth, second lining point clouds are segmented from residual point clouds after the primary support and the ground are removed with high precision.

The application relates to an image segmentation method and device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring an image to be segmented, and extracting multi-scale features of the image to be segmented; performing re-calibration processing on the multi-scale features to generate enhanced multi-scale features; performing feature splicing on the enhanced multi-scale features to generate unified semantic features, and generating pseudo prompts based on the unified semantic features to obtain initial pseudo prompts; if a user prompt is received, merging the user prompt and the initial pseudo prompts to generate a merged prompt; performing initial mask prediction based on the merged prompt and the enhanced multi-scale features to generate an initial segmentation mask; and performing iterative optimization based on the initial segmentation mask and the enhanced multi-scale features, and generating a target segmentation mask when the iterative optimization is completed. The application effectively improves the segmentation accuracy and interactive flexibility in a complex scene.

This invention discloses a method and system for embryo quality detection, relating to the field of embryo detection technology, including the following steps: S1: fertilized embryos are continuously cultured in an in vitro culture system containing specific metabolic marker detection components, and continuous dynamic imaging of the embryos is performed to obtain a complete dynamic developmental image sequence; S2: the dynamic developmental image sequence is segmented, and temporal developmental features are captured, identifying key time points such as pronucleus appearance and disappearance, cleavage, and blastocyst formation, and generating a segmentation mask corresponding to each frame of the dynamic developmental image sequence; this invention achieves full-process time-difference imaging to capture the temporal features of embryonic development, without trauma or interference, avoiding subjective bias in static observation; by segmenting the dynamic developmental image sequence and capturing temporal developmental features, the segmentation accuracy is high and the anti-interference ability is strong.

The invention discloses a DR focus segmentation method and system based on a dynamic loss optimization function, and the method comprises the steps: collecting image data in an IDRiD data set, and carrying out the preprocessing of the image data, and obtaining the preprocessing data; based on the preprocessed data, a visual SAM large model is constructed, a loss function weight optimization strategy is designed, and an RTSAM segmentation model is obtained; segmenting the DR eye fundus image based on an RTSAM segmentation model to obtain a DR focus segmentation result; and based on the DR focus segmentation result, providing an automatic identification and segmentation visualization result of the DR focus. Aiming at the problems of non-uniform lesion distribution, non-uniform lesion occurrence frequency and the like existing in a DR color fundus image, the segmentation effect is poor, so that a dynamic loss optimization strategy is used, weight distribution in a loss function is adaptively adjusted according to a model segmentation index, and the attention of a model to rare lesion and small lesion areas is enhanced.

The application discloses a prior feature auxiliary directional coordinate attention remote sensing road extraction method, and relates to the technical field of remote sensing image processing.The method comprises the following steps: extracting multi-source prior features representing road physical characteristics and optimizing and fusing weight to obtain a fused prior feature map; processing the RGB remote sensing image and the fused prior feature cooperatively to form a fused feature containing multi-scale semantic information and physical prior; predicting a pixel main direction angle in the feature through a directional coordinate attention mechanism, pooling the feature along the main direction and the orthogonal direction to generate an attention map and re-calibrate the original feature; performing step-by-step up-sampling on the decoder and introducing a deep supervision mechanism; and training the model by using a composite loss function containing a Dice loss, a Focal loss and a boundary perception loss.The application fully utilizes road physical characteristic prior knowledge, combines the directional coordinate attention mechanism to capture road geometric characteristics, and effectively improves the accuracy and integrity of remote sensing road extraction in a complex scene.

The invention discloses a remote sensing residential area extraction method and system based on multi-source data fusion semantic segmentation, and particularly relates to the field of remote sensing image processing and land utilization mapping. A multi-source fusion automatic labeling strategy is adopted, and a rural residential area pixel-level training label is automatically generated by using an impervious surface product, an open source map interest point and a night light learning area-brightness threshold value; the method comprises the following steps: constructing an SELPFormer lightweight Transform segmentation model, introducing Lite-PPM, SCSE and ELA feature enhancement modules and a lightweight decoder on the basis of SegFormer, and outputting a rural residential spot pixel level extraction result for regional scale rural residential spot mapping.

The invention discloses a lightweight image segmentation method and system based on NeuralODE neural network architecture, and the method comprises the steps: obtaining to-be-segmented image data, extracting an initial feature map through an initial convolution layer, and generating an intermediate feature map through a separable convolution layer; inputting the intermediate feature map into an enhanced Shenchang differential equation block, executing multi-step continuous feature evolution and introducing preorder output feature weighted fusion in each step to obtain an evolved feature map; generating a main feature map and a derived feature map, splicing the main feature map and the derived feature map in a channel dimension, and outputting a compressed feature map; a decoupling knowledge distillation strategy is adopted, teacher model probability distribution is decoupled into two types of probability distribution, corresponding loss is calculated, and total distillation loss is constructed to adjust network parameters; and inputting a feature map output by the trained network model into a segmentation prediction head, and executing pixel-level prediction operation on the feature map through the segmentation prediction head to generate a segmentation result of the to-be-segmented image. The method improves the segmentation precision, and gives consideration to the deployment efficiency and the segmentation performance.

The application discloses a brain glioma segmentation and three-dimensional visualization model training method and system based on multi-modal fusion, and comprises the following steps: inputting multi-modal medical image data into a Laplacian pyramid multi-modal fusion learning model to generate a fusion graph, then inputting the fusion graph into a U-net segmentation model comprising an encoder and a decoder to obtain a segmentation mask under the multi-modal fusion graph; and finally, based on the multi-modal fusion graph and the segmentation mask, adopting a Marching cubes (MC) algorithm to perform three-dimensional reconstruction visualization of brain regions and brain tumor region labeling. The brain glioma segmentation and three-dimensional visualization model training method and system based on multi-modal fusion provided by the application optimizes the disadvantages of insufficient information and incomplete modeling under single modal, fully utilizes the advantages of the completeness of multi-modal data, performs multi-modal fusion, segmentation and three-dimensional visualization, can more comprehensively assist surgeons in treatment, and improves the accuracy in the operation process.

The application is a medical image segmentation method based on multi-modal self-supervision. First, the multi-modal medical image of the lesion tissue is obtained, including A-mode image and B-mode image, and the image is preprocessed. Then, a cycle-consistent modal contrast domain translation network is constructed, including two generators and two discriminators. The generator is used to convert the image of one mode into the image of another mode, including an encoder, an intermediate shared module and a decoder. The discriminator is used to judge the source of the input. Then, the cycle-consistent modal contrast domain translation network is pre-trained, the training loss is calculated, and the loss function includes multi-modal semantic consistency loss, adversarial loss, cross-domain translation loss and cycle consistency loss. Finally, the A-mode segmentation network and the B-mode segmentation network are constructed, the pre-trained weights are migrated to the two segmentation networks, and the trained two segmentation networks are respectively used for medical image segmentation of the corresponding mode. The contrast cross-domain translation is used as a multi-modal self-supervised pre-training task to learn more comprehensive modal features, promote the network to better learn modal characteristics and common knowledge, and improve the segmentation ability.

This application provides a MedSAM-based dual-stream adaptive brain tumor segmentation method and apparatus, belonging to the field of image segmentation processing technology. By introducing a 2.5D dual-stream image encoder and a low-rank adaptive fine-tuning mechanism, it effectively alleviates the enormous computational overhead in 3D medical image feature extraction, while overcoming the defect of lack of interlayer continuity in traditional 2D single-slice methods. The method designs a lightweight 3D convolution and residual mechanism in the intermediate layer of the encoder for cross-slice information interaction, explicitly separating features into a clean stream for generating self-hints and a fusion stream for providing spatially perceptual features. In the mask decoding stage, a residual soft modulation mechanism based on pixel-level confidence maps is introduced to weakly intervene in the decoded features, avoiding damage to the feature distribution of fine-grained tumor subregions and improving the segmentation accuracy of the basic large model in multimodal 3D medical images.

The present application relates to a kind of heart ultrasound video semantic segmentation pseudo-label generation method based on optical flow guide, belong to computer vision and medical image processing field.The method includes: selecting two key frames in heart ultrasound video frame sequence, and obtaining the segmentation mask of two key frames by artificial labeling;Optical flow model is fine-tuned using two key frames, the frame between two key frames, the frame of first key frame left side preset quantity and the frame of second key frame right side preset quantity;Based on the fine-tuned optical flow model, the forward optical flow sequence from first key frame to second key frame and the reverse optical flow sequence from second key frame to first key frame are predicted;Based on forward optical flow sequence and reverse optical flow sequence, generate forward propagation mask sequence and reverse propagation mask sequence, and carry out position weighted fusion, obtain the pseudo-label of unlabelled frame.The technical problem that the present application aims to solve is that the label of heart ultrasound video semantic segmentation is difficult to obtain and the quality of pseudo-label obtained is poor.

This invention specifically relates to an infrared thermal imaging abnormal hotspot monitoring and alarm system for resin reactors, belonging to the field of industrial process safety monitoring technology. It includes: an infrared thermal image acquisition module; an image preprocessing module; an abnormal hotspot detection and feature extraction module; a graded alarm discrimination module; and an alarm output and linkage control module. This invention sets multi-dimensional abnormality judgment conditions such as absolute temperature threshold, temperature gradient threshold, and temperature difference threshold, and combines pixel-level semantic segmentation of a convolutional neural network with the union fusion of threshold rule detection results. This solves the technical problem of insufficient detection capability of a single threshold judgment method for abnormal hotspots of different causes, achieving the technical effect of improving the detection coverage and segmentation accuracy of abnormal hotspots.

The application belongs to the technical field of image detection, and particularly relates to a visual detection method for intelligent segmentation of components on a circuit board. The method comprises the following steps: collecting original images of the circuit board and performing manual labeling and correction to construct a component segmentation training data set; training a semantic segmentation model based on a deep convolutional neural network, adopting a cross-entropy and Dice mixed loss and dynamically adjusting the class weight to alleviate the class imbalance; inputting a to-be-detected image into the model after preprocessing to obtain a semantic segmentation mask; performing morphological post-processing on the segmentation mask to eliminate false areas and regularize the contour; and finally outputting the class, contour and position information of each component. Through standardized data set construction, preprocessing enhancement, mixed loss function and post-processing optimization, the application effectively improves the precision and stability of component segmentation under complex circuit board images, and especially improves the segmentation effect of low-frequency key components.

The present application relates to a pathological image cell segmentation method based on a U-Net model, belonging to the field of deep learning and medical image segmentation. The present application adopts an improved U-Net model, and in the preprocessing stage, converts the original point label data into a continuous density map. A multi-scale attention module is added in the decoder stage of the network. The module effectively combines multi-scale feature fusion and soft attention mechanism, can comprehensively capture global and local features in the image, and significantly enhance the representation ability of key cell features, thereby improving the accuracy of cell segmentation. In addition, the present application adds a pixel channel fusion module between each layer of the decoder, which further enhances the model's ability to identify details by integrating local information and pixel-level attention into the channel attention mechanism. The present application can effectively segment Ki-67 positive cells, Ki-67 negative cells and tumor infiltrating lymphocytes in IHC stained pathological images.

The invention discloses a convex threaded hole measurement method based on a point cloud, and the method comprises the steps: collecting a point cloud A of the surface of a workpiece, and segmenting a point cloud B of a thread from the point cloud A; obtaining a normal vector of each point in the point cloud A; reversely projecting points in the point cloud A to a two-dimensional image plane, acquiring a normal change rate of each pixel point P, and judging whether the point P is a foreground point or a background point according to the normal change rate; storing the three-dimensional points corresponding to all foreground points in the point cloud B to complete point cloud segmentation; according to the method, based on the characteristic that the normal vector change rate of the thread point cloud is high, a segmentation scheme for point cloud screening based on the normal vector change rate is designed; the thread point cloud is segmented without the help of a theoretical value, the method is not restricted by workpiece machining deviation, and the segmentation precision of the thread point cloud is improved; and the thread point clouds of the stud, the planar threaded hole and the convex threaded hole can be effectively segmented, so that the universality is high, and the application scene is wider.

This invention discloses an anisotropic sparse deconvolution enhancement method and system for ultrasound tumor image segmentation. The method includes: establishing a local convolution model for ultrasound RF images based on the anisotropic characteristics of the ultrasound xz imaging plane; constructing an axis-aligned elliptical symmetric anisotropic point spread function (PSF), whose lateral and axial spread scales are obtained through physical parameter conversion or data-driven methods; constructing an ultrasound sparse reconstruction objective function incorporating the anisotropic PSF, adding non-negativity constraints, introducing a weighted Hessian continuity term and an L1 sparse prior term in the xz plane direction, and optimizing the solution to obtain the sparse reconstruction result; using this result as input, employing an RL iterative deconvolution method based on the anisotropic PSF, and achieving image boundary sharpening and noise suppression through PSF flip kernel ratio iteration; inputting the enhanced image into a tumor segmentation network to complete training and inference, thereby achieving ultrasound tumor image segmentation.

This application belongs to the field of fetal brain age prediction technology, and relates to a method and system for predicting fetal brain age of the cerebellar vermis based on multimodal feature fusion. It employs the MST-Mamba segmentation network, and achieves synergy between local detail capture and global semantic modeling by embedding local-global aggregators at each level of the encoder. Simultaneously, a dynamic channel fusion unit is deployed at the jump connection between the encoder and decoder to avoid problems such as boundary ambiguity, missed classification, and misclassification. Through three parallel branches of a multi-granularity morphology-texture collaborative perception architecture, it simultaneously extracts two types of explicit features (macro-geometric and topological morphology) and two types of implicit features (micro-texture), achieving a comprehensive representation of the developmental features of the cerebellar vermis. After standardizing and calibrating the explicit features, they are spliced ​​and fused with the implicit features along the channel dimension to solve the problems of insufficient multimodal feature fusion and lack of calibration. Finally, prediction is performed using a multilayer perceptron regression head, ensuring the accuracy and stability of the brain age prediction results from the source.

The application provides a forest fire smoke detection method based on semantic segmentation, and belongs to the technical field of fire warning, and comprises the following steps: feeding a real forest fire data set into a feature extraction network, inputting the extracted features into an improved DeepLabV3+ network for training, and outputting detection and recognition results. According to the complex and changeable forest fire scene, the non-rigid structure, the opacity and the variable mode of smoke and other characteristics, the application deeply studies a feature fusion method, adopts an improved ASPP structure to extract multi-scale spatial features, simultaneously introduces a bottom feature extraction module and a double-path convolution aggregation module to effectively extract smoke boundary information, and uses a lightweight backbone network to replace the original feature extraction network of DeepLabV3+, so that the detection speed is accelerated by using fewer parameters. The application can solve the problem that the false alarm and missed detection rates of the smoke detection method are high, thereby providing technical support for forest ecological protection.

The application belongs to the field of intelligent medical computer-aided diagnosis application, and relates to a colon polyp segmentation method based on deep learning fusion and collaborative learning enhancement. The method comprises a feature extraction model, a fusion module and multi-view collaborative learning. The feature extraction model is divided into two branches. One branch uses DeiT-Small to extract global feature information and establish the correlation between each pixel. The other branch uses HardNet-MSEG to extract local feature information and obtain more low-level detail information. In order to improve the segmentation accuracy of small target colon polyp images, based on the public colon polyp image dataset and the initial deep learning single-branch segmentation method, a deep learning technology fusion method is proposed, and multi-view collaborative learning is used to enhance colon polyp segmentation. Compared with the feature extracted by a single deep learning method before improvement, the feature is richer, and the information omission defect of a single branch is compensated.

The application discloses a kind of equipment and control method for automatically fish slice defect finishing.The equipment includes fish slice single piece loading unit, image acquisition and processing unit and finishing unit.Fish slice single piece loading unit utilizes the action of gravity to disperse and load the fish slice overlapping to image acquisition area;Image acquisition and processing unit, image acquisition and processing unit are used to collect fish slice defect image, and real-time picture information is transmitted to industrial computer, and the fish slice defect detection network based on YOLOv8 model improved in the middle part of industrial computer is used to identify defect area and plan defect finishing track;Finishing unit receives track and posture information from industrial computer, and accurately finishes fish slice, so as to complete the process of fish slice loading, detection and finishing.The application replaces traditional manual finishing mode by automatic processing, realizes real-time finishing of fish slice defect, effectively improves the operation efficiency and product quality of fish slice processing.

This invention discloses a non-contact tire deformation recognition method based on a fine-tuned large-scale visual model. The method includes calibrating a monocular high-speed camera, fine-tuning the parameters of the mask decoder of the large-scale visual model using a tire image dataset, generating a point coordinate cue sequence based on pixel calculation using OpenCV, inputting the cue sequence into the fine-tuned large-scale model for segmentation, further processing the pixel matrix using OpenCV to generate a point cue sequence, and post-processing using iterative geometric fitting and region growing algorithms to obtain the mechanical deformation parameters of the target sample tire. This invention can achieve accurate and rapid tire deformation recognition, reaching pixel-level precise segmentation. It solves the problems of large errors, limited measurement environments, nonlinear image distortion caused by cameras, weak generalization ability, and high training costs in existing computer vision-based vehicle tire recognition methods.