906 results about "Multi feature" patented technology

The invention provides a circuit board welding fault identification method and system based on machine vision, and relates to the technical field of visual identification, and the method comprises the steps: obtaining an image of a circuit board welding region through employing a structured light projection system and a multi-camera imaging system; realizing accurate positioning of a defect region in the region of interest by utilizing three-dimensional shape information and through morphological operation and an edge detection algorithm; for the accurately positioned defect area, obtaining high-precision three-dimensional point cloud data of the defect area, extracting a multi-scale curvature feature descriptor, and fusing the multi-scale curvature feature descriptor with visual features to form a multi-feature descriptor; inputting the multi-feature descriptors into a defect classification and recognition module based on ensemble learning to obtain the types and severity of the welding defects; and according to a defect identification result, the three-dimensional space distribution and severity of the welding defects are visually displayed.

A defect prediction method based on a multi-feature parallel multi-stage neural network (MF-PMSNN), includes: obtaining a trajectory dataset, and preprocessing data of a defect of a workpiece in additive manufacturing (AM); building an MF-PMSNN, and evaluating an output classification result based on evaluation indicators; and performing real-time defect prediction, and deploying a trained MF-PMSNN model to a production environment. The present disclosure combines and effectively matches thermal imaging-based in-situ monitoring data and X-ray computed tomography (XCT)-based in-situ monitoring data to ensure temporal and spatial consistency between the thermal imaging-based in-situ monitoring data and the XCT-based in-situ monitoring data. In this way, a molten pool status and a pore of the workpiece can be captured more comprehensively. The MF-PMSNN is proposed to obtain a molten pool status and the porosity distribution in the data and perform defect prediction.

The invention provides an underwater image enhancement method combining high-frequency enhancement, space-frequency mixed feature extraction and a Mama enhancement fusion technology. The method aims at solving the problems of low contrast ratio, color distortion, detail loss and the like caused by absorption and scattering effects in the light propagation process of the underwater image, the image quality is improved, and the visual perception effect is improved. The method specifically comprises the following four main steps: firstly, acquiring and preprocessing initial data sets of different underwater scenes; secondly, extracting texture detail information of the image through a texture enhancement module; thirdly, further enhancing texture details by using a space-frequency mixed feature extraction module; and finally, in combination with the original image, the texture information and the spatial frequency domain enhancement result, realizing feature fusion of the image through a Mama enhancement fusion module, thereby effectively recovering details of the underwater image, correcting color deviation and improving the definition and visual effect of the image. According to the method, the enhancement performance of the underwater image in a complex environment can be improved, and powerful support is provided for applications such as underwater detection, target detection, object recognition and image segmentation.

The invention discloses a method for identifying impurities and bubbles in a wine bottle based on multi-feature comprehensive judgment, and belongs to the technical field of image processing and computer vision, and the method comprises the steps: employing a high-resolution industrial camera to be combined with an LED light source, and continuously shooting multiple frames of images of the wine bottle under the consistent shooting angle and illumination condition; carrying out the preprocessing of the collected image through employing a self-adaptive histogram equalization and Gaussian blur method; extracting the edges of impurities and bubbles in the wine bottle on the image by adopting a Canny edge detection algorithm to obtain an edge image; segmenting the edge image into a plurality of target areas by using a contour detection technology, and extracting possible bubble and impurity areas from the edge image; extracting target area features including circularity, gray average, gray uniformity, texture features and color space; and according to the extracted features, bubbles and impurities are distinguished by applying a comprehensive judgment rule. According to the method, the bubbles and the impurities are comprehensively judged by adopting multi-feature combination, so that the accuracy and the robustness of detection are greatly improved.

The invention provides a multi-feature information hidden document integrity verification and tampering positioning method, and relates to the field of network security and digital document protection. The multi-feature information hidden document integrity verification and tampering positioning method comprises the following steps: S1, document multi-dimensional feature extraction and encryption: based on an original Word document, adopting an SHA-3 algorithm to calculate a full-text hash value as a content feature, and extracting document object model features such as paragraph hierarchy, table structure and the like through a DOM tree analyzer; after the two types of features are combined into a feature matrix, a dynamic secret key is generated through Logistic chaotic mapping for XOR encryption, and an encrypted document feature matrix is generated. A dynamic key is generated by combining Logistic chaotic mapping encryption through a multi-dimensional extraction technology fusing document content hash values and structural features, so that the anti-cracking capability of a feature matrix is remarkably improved, the confidentiality of document features in open network transmission is ensured, the block information retention rate is simulated and predicted by adopting Monte Carlo, and the watermark embedding weight is dynamically allocated.

The invention discloses an emotion recognition method based on EEG space-time frequency feature fusion, which comprises the following steps: S1, carrying out a series of preprocessing steps on an original EEG signal, including baseline correction, standardization and time window addition; s2, performing form conversion on the electroencephalogram signals processed in the S1 to obtain spatial information and time-frequency information of the electroencephalogram signals; s3, multi-aspect feature extraction is carried out; s4, fusing the extracted emotion features, and performing multi-feature emotion recognition; s5, further extracting time features of the electroencephalogram signals by using BILSTM added with a channel attention mechanism, and performing deep fusion of the features; and S6, obtaining an emotion classification result. According to the emotion recognition method based on EEG space-time-frequency feature fusion, feature information of the time dimension, the frequency dimension and the space dimension of the EEG signals is fully considered, the highest recognition accuracy is achieved on the awakening dimension and the titer dimension, the emotion recognition accuracy and robustness are improved, and the effectiveness of the method is verified.

The invention discloses an image deblurring system and method based on Transform and multi-scale feature fusion, and relates to the technical field of image processing, the system comprises an input layer, a processing layer and an output layer, the processing layer comprises a multi-input multi-output encoder-decoder module, the multi-input multi-output encoder-decoder module is used for extracting features from blurred images of different scales through an encoder, and outputting the features to the output layer; a clear image is gradually restored based on the extracted features through a decoder; the multi-feature multi-scale fusion module is used for integrating local and global feature information and enhancing the learning ability of the system to global features; according to the improved Transform module, a self-adaptive window mechanism and a cross-channel attention mechanism are introduced, so that the system can better adapt to different types of blurred images, and the effects of feature extraction and image restoration are improved; and the attention fusion module dynamically learns and integrates useful feature information by introducing a channel attention mechanism. The image deblurring method is suitable for various image deblurring application scenes, and image detail features can be effectively recovered.

The invention relates to an extra-high voltage converter transformer OLTC fault diagnosis method fusing multi-feature information and RIME-CNN-BiLSTM-SAM, and belongs to the technical field of intelligent monitoring of power systems. The method comprises the following steps: firstly, constructing a vibration signal fault data set based on an OLTC mechanical fault simulation experiment; secondly, decomposing an OLTC vibration signal into a plurality of intrinsic mode components by adopting REMD, and preferably selecting components containing rich fault feature information based on a correlation coefficient; then, the multi-scale permutation entropy of IMFs is calculated, time / frequency statistical analysis and the multi-scale permutation entropy are combined, OLTC multi-dimensional vibration characteristic parameters are integrally and locally concerned, and principal component analysis is introduced to carry out characteristic fusion and dimension reduction of OLTC vibration information; and finally, optimizing the hyper-parameters of the CNN-BiLSTM-SAM fault diagnosis model by using the RIME, and realizing the construction of the converter transformer OLTC intelligent fault diagnosis model. The method has a remarkable effect in the aspect of extracting OLTC fault feature information, the fault type recognition rate is superior to that of an existing method, and the effectiveness of the method in converter transformer OLTC fault diagnosis is verified.

The invention relates to a target classification method based on dynamic multi-feature data fusion, and belongs to the technical field of radar signal processing. Comprising the following steps: 1) acquiring echo data of a target by a radar, preprocessing the echo data, and constructing a training data set by using time-frequency information, distance period information and distance period data of a signal; 2) constructing a dynamic multi-feature fusion network target classification model which comprises a global feature extraction module, a local feature extraction module, a dynamic feature extraction module and a feature fusion module; 3) inputting a training data set to carry out iterative optimization training on the dynamic multi-feature fusion network to obtain an optimal network parameter; and 4) preprocessing real-time radar echo signals, inputting the real-time radar echo signals into the trained dynamic multi-feature fusion network for testing, and completing target classification. According to the method, the Doppler information and the dynamic distance amplitude information of the radar signal can be subjected to feature extraction at the same time, the target classification accuracy is improved, and the actual application requirement is met.

The invention discloses a small sample radar target identification method based on multi-feature fusion. According to the invention, the natural resonant frequency characteristics of radar echo signals are introduced into a small sample learning framework, and the advantages of certain stability and simple and rapid extraction under the condition of attitude and observation angle change are fully utilized; attention multi-feature weighted fusion based on energy guidance is carried out on natural resonant frequency features and time frequency features, scattering features are described from different feature mechanisms, and the completeness of the features under the small sample condition is improved; in addition, a loss function based on combination of feature similarity measurement and classification loss is also designed, so that the model can learn feature representation with higher distinction degree while the feature space discrimination is optimized, and the performance is improved in a feature fusion-classification network. According to the method, on the premise that the reasoning time and the calculation complexity are not remarkably increased, the recognition accuracy under the condition that the observation angle changes is effectively improved.

The invention discloses a power transformer temperature prediction method and system based on multi-feature extraction and fusion, and the method comprises the steps: carrying out the time-space decoupling standardization and causal emergence clustering of all temperature variables in data, and obtaining a clustering result; extracting a common pattern from each class of the clustering result to obtain an information complemented multivariable time sequence, and performing down-sampling on the information complemented multivariable time sequence to obtain a plurality of subsequences; performing feature extraction on the multivariable time sequence and the sub-sequence after information completion through a dynamic time-frequency domain MLP mechanism to obtain overall features and local features, and fusing the overall features and the local features to obtain time sequence features; acquiring an external environment covariable, inputting the external environment covariable into the self-attention mechanism network to obtain a covariable self-feature, and performing feature fusion on the covariable self-feature and the time sequence feature through a covariable-driven causal convolution fusion mechanism to obtain a fusion feature; and inputting the fusion feature into a dynamic attention feature weighted prediction model for prediction to obtain a prediction result. And the precision and reliability of temperature prediction of the power transformer are obviously improved.

The invention discloses a multi-feature learning online video popularity prediction method based on time information perception. The method comprises the following steps: acquiring multi-feature data and playing time sequence data related to a to-be-predicted video; inputting the multi-feature data into feature sub-encoders in a preset multi-feature encoder according to categories, and determining visual, acoustic, text, social and metadata features; inputting the playing time sequence data into a hierarchical popularity sequence feature extraction network in a preset multi-feature encoder to determine popularity sequence features of the to-be-predicted video; inputting the visual, acoustic, text, social, metadata and popularity sequence features of the to-be-predicted video into a preset feature fusion network for feature fusion; and inputting the fused to-be-predicted video features into a preset popularity prediction network to obtain a prediction result. Through the technical scheme of the invention, various features related to the video popularity can be comprehensively considered, and the popularity prediction performance is improved.

The present disclosure describes methods, systems, apparatus, and media for object identification and classification, utilizing multi-feature and multi-modal data. This includes shape, material, brand, price, odor, taste, tactility, and sound. The system integrates a server space for data processing, a querying device for iterative searches, and a data interface module for refining results. It features AI-driven image optimization, feature extraction, and pattern recognition, employing novel techniques for fusing multi-feature and multi-modal embeddings utilizing multi-head attention. Additionally, a linker module powered by two active learning with feedback loops AI models consolidates scattered data into a unified object information database. The system also employs novel AI algorithms for isolating the object of interest through a saliency map and semantic analysis, as well as for enhancing raw images with a GAN-autoencoder.

The invention relates to a three-dimensional rapid modeling method based on section contour multi-feature constraint, and the method comprises the steps: extracting preset key points based on the drilling space information data of a geologic body section, and constructing a discrete point set of the geologic body section; searching a starting point pair for the discrete point set, and unifying the bypassing direction of adjacent point sets; constructing an initial adjacent contour point set based on the starting point pair and the bypassing direction, performing multi-feature constrained auxiliary point interpolation on the initial adjacent contour point set, and constructing a one-to-one corresponding point set; carrying out interlayer interpolation on the contour point set after the auxiliary point interpolation; and based on the shortest diagonal constraint, carrying out triangulation network splicing on the contour point set after interlayer interpolation. According to the method, the property and the inlaying process of the basic triangular patch can be considered, reconstruction of sparse contour line discrete points with low shape similarity and different points is realized, and the problem of complex surface reconstruction under a sparse profile is effectively solved.

The invention relates to an abdominal CT multi-organ segmentation method based on a LoRA vertical domain MedSAM large model. The method comprises the following steps: step 1, preprocessing an abdominal CT image supervised learning data set; step 2, constructing a feature selection network; step 3, constructing a LoRA layer; step 4, performing interlayer context reasoning by using a mixed prompt strategy to realize abdomen CT automatic segmentation; the method has the advantages that through multi-feature information fusion, dynamic context prompting and self-adaptive LoRA fine tuning, the precision and robustness of the MedSAM large model in the abdomen multi-organ CT segmentation task are improved, multi-feature information can comprehensively represent organ features, context information can be effectively utilized through dynamic context prompting, and the accuracy and robustness of the multi-organ CT segmentation task are improved. Limited training data can be effectively utilized by self-adaptive LoRA fine tuning; according to an image encoder based on a MedSAM large model, a learnable LoRA layer is added to each Transform layer so as to achieve efficient parameter training, and for a mask decoder of the MedSAM large model, the LoRA layers are also added to a self-attention layer and a cross-attention layer at the same time.

The invention relates to the technical field of intelligent wearable health management, in particular to a health management method and device based on multi-modal data, equipment and a storage medium. Comprising the steps of obtaining multi-feature-dimension original data to construct an original data set; performing data preprocessing and feature extraction on the original data set to generate a feature vector set; performing trend capture on the feature vector set according to a time sequence to obtain a time sequence feature vector of each modal; calculating a cross-modal association weight according to each modal time sequence feature vector, outputting a joint feature vector based on the cross-modal association weight, and generating a health index value of each evaluation target dimension according to the joint feature vector; and forming a state vector by the health index value and the historical behavior data of the user, calculating action probability distribution according to the state vector, and sampling and outputting a health intervention suggestion based on the probability distribution. The problem of health assessment deviation caused by insufficient multi-modal data fusion and insufficient time sequence association mining in the prior art can be solved.

The invention discloses a complex scene-oriented target identification method, system and device and a medium, and relates to the technical field of computer vision. The method comprises the following steps: inputting a to-be-detected image into a target recognition model for processing to obtain a target recognition result; the target identification model is constructed based on a dual-channel coding network and a weighted optimization loss function; the dual-channel coding network comprises a MobileNet channel and a wavelet channel; wherein the MobileNet channel is used for extracting multi-scale spatial features and is composed of a layered encoder and a multi-feature prediction decoder which are connected in sequence; the wavelet path is used for extracting frequency domain features and is composed of a global semantic wavelet coding module and a local wavelet fusion decoding module which are connected in sequence; and the multi-feature prediction decoder is also respectively connected with the global semantic wavelet coding module and the local wavelet fusion decoding module. According to the invention, the target identification precision and accuracy for complex scenes can be improved.

The invention discloses a short-time traffic flow prediction method and system based on a multi-feature map, and relates to the technical field of traffic flow prediction, and the method comprises the steps: respectively constructing an occupancy rate feature map, an average speed feature map and a traffic flow feature map through three kinds of data, including traffic flow, occupancy rate and average speed data, collected by a road sensor at the same time; node feature information of three feature maps is aggregated by using a GCN, supervised learning training of occupancy features and average speed features is realized by using an improved Transform encoder, and feature interaction fusion of obtained feature vectors of occupancy and average speed is realized in a multi-feature fusion traffic flow prediction model. The occupancy and average speed features are utilized to assist a multi-feature fusion traffic flow prediction model to better capture traffic flow features, and more accurate traffic flow prediction is provided.

The invention provides a user multi-feature intelligent recommendation method and system, and the method comprises the steps: obtaining the historical behavior feature data of a user, and constructing a multi-interest user portrait based on a MIND model; based on the behavior interaction frequency and behavior interaction time of the user on the candidate commodities of each category, calculating the comprehensive weight of the candidate commodities of each category; and based on the comprehensive weight, selecting candidate commodities and recommending the candidate commodities to the user. According to the method, the multi-interest user portraits are constructed based on the MIND model, through combination of the weighted model based on the behavior frequency, the time decay model and the weighted voting mechanism, the commodities of proper categories are accurately selected and recommended to the users, and diversified behaviors and demand changes of the users can be processed more flexibly. Through combination of the models and mechanisms, the accuracy and correlation of recommended contents are improved, the satisfaction degree and participation degree of users are further improved, and it is ensured that a recommendation system can still keep efficient and accurate recommendation ability when facing complex user behaviors.

The invention discloses a two-stage multi-feature-based distribution and storage user identification method, which overcomes the problems of high cost, low efficiency and poor identification precision of distribution and storage user identification in the prior art, and comprises the following steps: clustering users by using a kmeans algorithm and determining a potential distribution and storage user group in combination with a custom rule; carrying out multi-dimensional typical distribution and storage user load feature and energy consumption feature extraction on the potential distribution and storage users based on the preliminary identification result; based on the extracted multiple features, a machine learning classification model is adopted to carry out accurate identification training on the distribution and storage users; and utilizing the trained machine learning classification model to identify the storage allocation user. Through a two-stage algorithm, end-to-end classification identification is directly realized based on the power grid side data, the accuracy of distribution and storage user identification is improved, a large amount of manpower troubleshooting is not needed, the manpower cost and the troubleshooting time cost are greatly reduced, and the user distribution and storage identification accuracy is high.

The invention discloses a virtual viewpoint image quality evaluation method based on residual recovery and multi-feature fusion. The method comprises the following steps: acquiring a virtual viewpoint image to be evaluated; inputting the virtual viewpoint image into a pre-trained visual residual error recovery network model constructed based on a U-Net network, and respectively extracting multi-stage degradation features and multi-stage recovery features; the virtual viewpoint image is input into a pre-trained OfficientNet-B0 network model, and multi-level content features are extracted through the model; performing adaptive fusion on the multi-scale degradation feature map, the recovery feature map and the content feature map through a multi-feature weight adaptive fusion module to generate a multi-layer fusion feature map; performing cross-channel information interaction on the multi-layer fusion feature map by using a channel attention module based on channel-level convolution to generate a fusion channel-level feature map; and mapping the fused channel-level feature map into a corresponding predicted objective quality score through a full connection layer. According to the method, the generalization ability, robustness and accuracy of the model during virtual viewpoint image quality evaluation can be improved.

The invention discloses a gas pipeline leakage acoustic detection device and method based on CPO-VMD and multi-feature extraction, and relates to the technical field of gas pipeline leakage detection, and the device comprises a compressed air storage tank, a pressure control valve, a barometer, a pipeline, a seamless steel pipe, a broadband microphone, a data acquisition card and a data storage device. The method using the device comprises the following steps: collecting a sound wave signal of gas pipeline leakage; carrying out adaptive decomposition on the original signal in combination with a CPO algorithm and variational mode decomposition; performing reconstruction and noise reduction on the key modal component through the correlation coefficient; and multi-dimensional features of the reconstructed signals are extracted, the signal features are screened and preferentially selected, and gas pipeline leakage detection and classification are performed through a classification detector. Therefore, by adopting the method, the decomposition effect and the classification precision of the leakage sound wave signals can be effectively improved, and the strong adaptability of a method framework in different scenes is enhanced.

The invention discloses a DeepSORT pedestrian tracking method based on multi-feature space-time cooperative interaction, and belongs to the field of computer vision and intelligent video analysis. The method comprises the following steps: acquiring and processing pedestrian data, constructing a target detection and feature extraction model, detecting a test set after training to generate a candidate box, extracting appearance features to construct a cost matrix, matching and updating a trajectory by using a Hungary algorithm, and finally outputting a visual tracking result. In the detection stage, a small target feature enhancement pyramid is designed to improve the small target detection precision, PSConv, Triplet Attention and DyHead are fused to construct a multi-dimensional feature interaction mechanism, and the scale adaptability and the anti-shielding capability are enhanced; in the tracking stage, an IAU module is embedded into an Re-ID branch of DeepSORT, feature discrimination is enhanced through space-time and channel feature dynamic modeling, and ID Switch is reduced. The method effectively improves the perception recognition capability of a multi-scale and strong-shielding target, guarantees the detection accuracy and tracking robustness in a complex environment, and has a good application deployment value.

The invention discloses a three-dimensional point cloud registration method and system based on multi-feature dynamic weighting. The method comprises the following steps: firstly, acquiring a source point cloud and a target point cloud to be registered and performing down-sampling; secondly, extracting geometric features of the source point cloud and the target point cloud, including curvatures and normal angles of all points; extracting a target point from the target point cloud, performing point pair matching by using a multi-constraint weighted scoring mechanism and a dynamic weight optimization strategy, and taking a point pair with a minimum dynamic weighted difference function value as a matching point pair; screening the matching point pairs according to the normal angle difference threshold value and the curvature difference threshold value, if the normal angle difference score is smaller than or equal to the normal angle difference threshold value and the curvature difference score is smaller than or equal to the curvature difference threshold value, reserving the matching point pairs, and otherwise, rejecting the matching point pairs; and finally, solving a rotation matrix and a translation vector according to the reserved matching point pairs to realize point cloud registration. The problems that a traditional ICP algorithm is sensitive to the initial attitude of the point cloud, the anti-noise capability is weak, and feature utilization is insufficient are solved.

The invention relates to the technical field of video water flow velocity detection, and discloses a river video velocity measurement method and device based on a multi-feature fusion PSA-ResNet network, and a medium. The method comprises the following steps: constructing an STIA data set; extracting low-level textural features of the space-time image by using a CLBP multi-feature extraction algorithm, performing channel-level fusion on a feature map and an original RGB image to form a six-channel CLBP-STIA feature map, and constructing a CLBP-STIA data set according to the six-channel CLBP-STIA feature map; fusing a pyramid segmentation attention module PSA in a residual block of the residual network ResNet to construct an angle classification model, and training the model by using a CLBP-STIA data set; generating enhanced feature representation of the to-be-detected space-time image by referring to the above mode, then inputting the enhanced feature representation to the trained classification model, and outputting a corresponding texture principal direction angle; and acquiring the actual length of the velocity measurement line in the video image, and calculating the actual flow velocity of the surface flow feature on the velocity measurement line in combination with the texture main direction angle. The texture main direction is accurately estimated, so that the speed measurement precision and efficiency are improved.

The invention is suitable for the technical field of escalator monitoring, and provides an escalator safety monitoring system and method based on multi-feature data fusion decision making. The system comprises a sensor, an image acquisition device, an edge node and a cloud platform, the sensor acquires running state data of the escalator, and the image acquisition device acquires escalator video images; the edge node performs threshold detection on the operation state data, performs passenger behavior detection on the escalator video image, and sends abnormal operation state data exceeding a threshold range and abnormal behavior information to the cloud platform; and the cloud platform determines a health degree characteristic index of the escalator according to the abnormal operation state data and the abnormal behavior information, calculates the probability that the escalator is in various preset health states according to the health degree characteristic index, determines the comprehensive health degree of the escalator according to the probability, and carries out safety monitoring on the escalator according to the comprehensive health degree of the escalator. According to the invention, automatic identification and active early warning of potential safety hazards of the escalator can be realized, and various potential safety hazards are effectively avoided.

The invention discloses an OFDM radar vital sign signal separation method based on FGO-VMD and multi-feature clustering, and belongs to the technical field of radar communication integration. According to the method, an OFDM signal radar is used for carrying out human body detection, multi-subcarrier phase difference linear regression is used for estimating displacement, thoracic cavity micro-motion signals are extracted, an FGO-VMD joint optimization model is provided, the modal number and penalty factor parameters of a VMD decomposition algorithm are adaptively determined through minimum envelope entropy, and a multi-feature clustering and weighted reconstruction strategy is designed. And in combination with frequency band screening and correlation coefficient weighting, the separation robustness of the respiratory signal and the heartbeat signal is enhanced, and high-precision separation of the vital sign signal is realized. According to the method, non-contact vital sign detection based on OFDM radar signals is achieved, the problems that in a traditional algorithm, parameters of modal numbers and penalty factors need to be manually set, and signal amplitude attenuation and modal aliasing are caused under complex noise are solved, the vital sign monitoring precision is remarkably improved, and high-precision separation of vital sign signals is achieved.

The embodiment of the invention provides an emphysema CT image segmentation method based on multi-feature dynamic fusion and boundary perception, and is applied to the field of medical lung CT image segmentation, the method obtains an original image by obtaining an emphysema CT image and preprocessing the emphysema CT image, and the preprocessing comprises extraction and standardization of a lung parenchyma region of interest; inputting the original image into the trained emphysema CT image segmentation model for segmentation to obtain an image segmentation result; wherein the emphysema CT image segmentation model comprises an encoder and a decoder, the encoder comprises a convolutional neural network branch, a Transform branch and a dynamic fusion module, the convolutional neural network branch is parallel to the Transform branch, and the decoder comprises an up-sampling layer and a boundary sensing module. The method improves the accuracy and reliability of the image segmentation result of the emphysema CT image.