85 results about "Underwater image processing" patented technology

The invention discloses an end-to-end underwater three-dimensional reconstruction method and system based on an underwater imaging model, and belongs to the technical field of underwater image processing. According to the method, deep learning pose estimation is combined with an underwater imaging model; firstly, a multi-frame underwater image sequence is collected as input, a deep neural network is constructed, and the network mainly comprises two core sub-modules: a pose estimation network; secondly, a three-dimensional reconstruction network is adopted, dense point cloud or voxel reconstruction is completed according to the predicted pose and image content, pose estimation and the three-dimensional reconstruction process are integrated in the same system, and overall joint optimization is achieved; and in combination with a self-adaptive underwater imaging model, modeling is performed on physical processes such as underwater illumination attenuation and scattering, so that the reality sense and the accuracy of a reconstruction result are improved. According to the method, high-quality three-dimensional reconstruction of images in a complex underwater environment is realized, and the method can be widely applied to ocean engineering, underwater robots, submarine topography surveying and mapping and underwater cultural relic protection.

The invention relates to an underwater image processing technology in the field of underwater autonomous perception, in particular to an underwater low-quality image enhancement method based on a Laplacian pyramid and contrast learning. Comprising the following steps: S1, image input and multi-scale decomposition: decomposing an input image into a low-frequency residual layer and a plurality of high-frequency detail layers through Laplacian pyramid decomposition; s2, inputting the low-frequency residual error layer into a global illumination and color correction sub-module to obtain an enhanced low-frequency residual error layer; s3, inputting the enhanced low-frequency residual error layer and the multi-scale high-frequency detail layer into a frequency domain enhancement feature module to obtain multi-scale enhanced high-frequency detail layer output; s4, performing progressive reconstruction on the enhanced low-frequency layer output and the high-frequency enhancement layer output of each scale according to the inverse process of the Laplacian pyramid; and S5, outputting a result and applying. The method can be used for sharpening optical image data in the operation task of the autonomous underwater vehicle, and the image quality is improved.

The invention provides an underwater target detection method and system based on a multi-beam foresight sonar image, and belongs to the technical field of underwater image processing. The method comprises the following steps: acquiring a target sonar image by adopting a multi-beam foresight sonar device, extracting a multi-scale feature map by adopting an improved detection model based on a convolutional neural network, predicting and classifying bounding boxes, and outputting position coordinates and category probability result information containing each detection target. According to the invention, a dynamic perception patch attention mechanism is introduced into the improved convolutional neural network, and a multi-branch feature extraction strategy and a special small target detection head are combined, so that the detection capability of the small target is enhanced, and the purpose of improving the detection precision is achieved. In addition, sonar imaging and processing, data communication, display control and the like are integrated in an embedded platform, and portable real-time detection, data exchange and user control are achieved. According to the method, the detection precision of the small target in the underwater forward-looking multi-beam sonar image can be effectively improved.

The invention discloses an underwater image enhancement method based on cross-domain feature representation and semantic segmentation guidance, and belongs to the field of underwater image processing, and the method comprises the steps: constructing an unpaired sample data set, and dividing the unpaired sample data set into positive and negative samples; designing and initializing an image enhancement network; respectively and randomly selecting an image IH and an image IL from the positive sample and the negative sample, inputting the image IL into an image enhancement network to obtain an enhanced image IE, inputting {IL, IH, IE} into an image feature extraction model, and calculating and comparing learning loss; pre-training the semantic segmentation model on a semantic segmentation data set, then performing fine tuning on the semantic segmentation data set of the underwater image, inputting an image IH and an image IE, generating a corresponding semantic prediction map, and calculating semantic segmentation loss; training an image enhancement network by combining and comparing learning loss and semantic segmentation loss, updating parameters of the image enhancement network through end-to-end training, and generating a high-quality enhanced underwater image; the method has the effects of image precision enhancement, detail recovery, strong generalization ability and low data acquisition cost.

The invention discloses an underwater image semantic segmentation method and device based on a lightweight double-flow Mama network, and a storage medium, relates to the technical field of underwater image processing, and solves the problems of poor environmental adaptability, low modal fusion efficiency, heavy model and high calculation overhead in the existing underwater image semantic segmentation technology. According to the method, a double-branch encoder is constructed, the double-branch encoder composed of an image encoder and a text encoder is adopted, and a visual feature map and a semantic feature vector in a preprocessed underwater image and text description information are extracted respectively; a cross-modal Mama module is adopted to carry out deep fusion on a flattened image feature sequence and text features in the module, the cross-modal Mama module adopts a Mama block with linear complexity, and continuous guidance and progressive enhancement of text semantics are realized in combination with a multi-level gating fusion mechanism and residual connection. And the recognition capability of underwater fuzzy and shielded targets is remarkably improved, and meanwhile, the calculation efficiency is remarkably improved.

The invention discloses a lightweight underwater image enhancement method, device and equipment based on a semi-supervised inactive function, and a storage medium, and relates to the technical field of underwater image processing. The lightweight underwater image enhancement method based on the semi-supervised inactive function comprises the following steps: constructing an initial image enhancement model based on a teacher-student framework of semi-supervised comparative learning and a gradient inactive function network; training the initial image enhancement model through label data and label-free data to obtain a target image enhancement model; obtaining an underwater image to be enhanced; and inputting the underwater image into the target image enhancement model to obtain an enhanced image. According to the method, the image can be efficiently processed, the cross-scene adaptive capacity of underwater image enhancement can be improved, the model deployment cost is reduced, and powerful technical support is provided for applications such as smart fishery.

The invention discloses an underwater image enhancement method based on color channel unit compensation amount, and is applied to the technical field of underwater image processing. Comprising the following steps: respectively compensating and correcting color cast of attenuated red, green and blue channels of an underwater image by using a color channel compensation method of unit compensation dosage to obtain corrected images of the three channels; carrying out adaptive platform histogram equalization on the corrected image to realize gray scale extension and redistribution of pixel values; for a brightness channel, using a CLAHE algorithm to improve image contrast, using a GUM algorithm to enhance details, and using a Gamma correction algorithm to improve local brightness; and performing multi-scale fusion to obtain a final output enhanced image. According to the method, the quality of the underwater image is remarkably improved, the method has important practical significance in the application fields of underwater target tracking, recognition, positioning and the like, and more reliable visual support can be provided for ocean resource development and scientific research.

The invention discloses an underwater vision sharpening method based on a polarization information guide diffusion model, and belongs to the technical field of underwater image processing. The method comprises the following steps: constructing an underwater polarization image data set under natural conditions and laboratory conditions; constructing an underwater vision clearness network based on a polarization information guide diffusion model, wherein the underwater vision clearness network comprises a serial conditional diffusion process, a cross-modal enhancement network and a conditional denoising network; and training the underwater vision sharpness network by using the underwater polarization image data set, and outputting a clear underwater image based on the trained underwater vision sharpness network. The underwater image sharpening method can effectively avoid the problem of imaging defects caused by an existing underwater image sharpening method under the condition of high turbidity, can restore a turbid area while removing color cast, improves the underwater image quality, and has effectiveness and robustness.

The invention relates to the technical field of underwater image processing, in particular to a semi-supervised underwater image enhancement method based on multi-scale context awareness, which comprises the following steps: establishing an underwater image enhancement network model which comprises parallel image restoration branches and detail restoration branches, the image restoration branch comprises a multi-scale input-level feature fusion module, a multi-branch hybrid convolution attention residual module, a down-sampling module and an up-sampling module; the detail repair branch comprises a pixel difference convolution layer, a normalization layer and a channel perception feedforward neural network; adding the output of the image restoration branch and the output of the detail restoration branch element by element to obtain the output of the underwater image enhancement network model; training an underwater image enhancement network model through a semi-supervised learning strategy and a joint loss function; and inputting the underwater image into the trained underwater image enhancement network model to obtain an enhanced underwater image. According to the invention, the enhancement effect and the cross-scene generalization performance of the underwater image are improved.

The invention discloses an underwater target volume measurement method, device and equipment based on three-dimensional reconstruction and a medium, and belongs to the technical field of photogrammetry, underwater image processing and point cloud volume calculation cross, and the method comprises the steps: carrying out the video data collection of an underwater target through video collection equipment, and obtaining an original image with image format data; the underwater image enhancement method model based on depth estimation performs image enhancement on the original image to obtain an underwater enhanced image; reconstructing a real scene containing a target based on the underwater enhanced image; and based on the three-dimensional reconstruction point cloud, segmenting to obtain the to-be-measured target, and obtaining the volume parameter of the underwater target. According to the method, a three-dimensional reconstruction technology is utilized, a real target structure is restored, the measurement accuracy of the underwater target defect volume is improved, a reference standard is provided for later repair, the maintenance cost is reduced, and the operation safety of a hydraulic structure is guaranteed.

The invention belongs to the technical field of underwater image processing and crack detection, and particularly relates to a hydropower station dam underwater crack image positioning method, which comprises the following steps of: acquiring image data of a dam surface crack and acquiring a key image; the method comprises the following steps: preprocessing an acquired underwater image, detecting a crack region of the preprocessed image by adopting a crack target detection network based on YOLOv9, and outputting boundary frame coordinates and confidence of a crack; a post-processing algorithm is used to optimize a detection result, and classification is carried out according to fracture morphological characteristics after multi-frame fusion; storing crack detection and positioning data to a database, and displaying the spatial distribution and change trend of cracks; and establishing an early warning model based on the crack propagation rate and the morphological change, and if early warning is triggered, generating a risk assessment report. The method overcomes the defects that traditional manual inspection is low in efficiency, is greatly interfered by water quality and is difficult to cover hidden areas, and the automation level and reliability of health monitoring of the dam structure are remarkably improved.

The invention relates to the technical field of computer vision, in particular to a marine organism intelligent detection system based on multi-scale convolution fusion and YOLOv8, and the system comprises an acquisition module which is used for obtaining the original image data of underwater marine organisms, and processing the original image data to obtain a marine organism data set; the detection module is used for identifying the marine organism data set; through the VM-Unet improved multi-scale underwater image enhancement network and the deeply optimized YOLOv8 algorithm, lightweight and efficient calculation, multi-scale feature fusion and complex scene robust recognition are realized, the precision and real-time performance of underwater image processing and target detection are remarkably improved, and the method has the advantages of being high in robustness and high in robustness. And a technical support with high adaptability and high efficiency is provided for a marine organism intelligent detection system.

The invention discloses an underwater hyperspectral clustering method based on a bipartite graph, and relates to the technical field of underwater image processing. The method comprises the following steps: acquiring spectral images of a to-be-processed image in different spectral intervals, taking the spectral image of each spectral interval as a view, and constructing hyperspectral data based on the acquired views; constructing a hyperspectral clustering model based on subspace clustering learning, and processing the hyperspectral image based on the hyperspectral clustering model; the hyperspectral clustering model comprises an adaptive dynamic anchor point selection module, an anchor point centroid learning module and a bipartite graph decomposition module; and iterating the hyperspectral clustering model based on an alternative update variable strategy until an iteration stop condition is met, and outputting a clustering result based on the clustering indication index matrix. According to the method, a model based on subspace clustering learning is constructed, uniform self-adaptive anchor points are dynamically learned in all pixel points, and the optimal cluster with accurate pixel division can be directly obtained from bipartite graph decomposition.

The invention discloses an underwater hyperspectral image clustering method based on a multi-scale anchor image, and belongs to the technical field of underwater image processing. The method mainly comprises the following steps: carrying out superpixel segmentation on an underwater hyperspectral image; performing noise removal processing on the segmented hyperspectral image; learning a multi-scale anchor image of the denoised hyperspectral image; matrix decomposition is carried out on the multi-scale anchor images, and soft labels of super-pixel points are obtained; stacking the soft label matrixes into a tensor, and introducing a tensor Schatten-p norm to obtain a high-dimensional space structure of the multi-scale anchor map; constructing an optimization objective function; updating the target function variable by using an iterative updating strategy; and carrying out adaptive fusion on the learned soft label matrix. According to the method, pixel point soft labels are obtained mainly through multi-scale anchor image decomposition, label matrixes are stacked into tensors to explore a high-dimensional space structure of data, finally, self-adaptive weighted summation is conducted on the soft labels of the multi-scale anchor images to obtain a label result used for clustering analysis, and the clustering precision is remarkably improved.

The invention discloses an underwater polarization image restoration method based on Transform and depth estimation, and belongs to the technical field of underwater image processing. The method comprises the following steps: acquiring an underwater polarization image data set, and dividing the underwater polarization image data set into a training set and a test set; training an underwater polarization image restoration network based on Transform and depth estimation, the network comprising an encoder and a decoder, the encoder comprising a U-Net module, a multi-scale content guidance attention module, a depth estimation network and a multi-scale convergence attention module; the decoder comprises two feature fusion modules which are connected in series and guide attention based on multi-scale content; the trained underwater polarization image restoration network based on Transform and depth estimation is tested based on the test set; and carrying out image restoration by using the tested underwater polarization image restoration network based on Transform and depth estimation. According to the method, the restoration effect of the underwater image can be remarkably improved, the image texture information is enhanced, and the definition and detail performance of the image are improved.

The invention belongs to the technical field of underwater image processing, and discloses an underwater image comprehensive sharpening method based on exposure correction. According to the method, firstly, an underwater non-uniform illumination image and a reverse image thereof are input into a low-illumination enhancement network, a low-illumination enhancement image and an exposure reduction image are obtained at the same time, an exposure correction image is obtained through pyramid image fusion, and then a cyclic adversarial network is introduced on the basis of exposure correction to carry out underwater image enhancement processing. In the training process, the interaction of a forward generator and a backward generator is utilized, the effect of converting an underwater image into an effect consistent with the style of a real air image is learned, the generated image is ensured to be consistent with the real underwater image, and circulation consistency is kept. According to the method, various common quality problems in the underwater image can be effectively solved, so that clearer and more accurate image information is provided, and the requirements of underwater operation and underwater robot application are met.

The invention discloses an underwater light source detection method and system based on a dark channel prior defogging algorithm, a medium and a program product, and belongs to the field of underwater image processing. Firstly, a dark channel of an underwater light source image is calculated through a dark channel prior algorithm, and a depth map is constructed by combining an ambient light coefficient and a medium transmissivity coefficient; and performing feature extraction on the depth map by using a lamplight mask generation function, screening an effective light source area through double criteria of contour length and circularity in combination with OpenCV contour detection and a morphological screening mechanism, calculating a contour centroid coordinate based on an image moment algorithm, and performing pose estimation of the underwater robot. Compared with the prior art, the method can quickly and accurately calculate the position of the underwater light source, and is higher in adaptive capacity and higher in accuracy compared with normal morphological feature extraction.

This invention provides a semantically driven, frequency-consistent underwater image enhancement method, belonging to the field of underwater image processing technology. The specific steps include: acquiring both degraded and clear underwater images of the same scene; extracting the low-frequency components of both; calculating and obtaining the global low-frequency residual components; generating a semantic partition mask through semantic segmentation; dividing regions by combining gray-level variance to obtain the final degraded region; introducing semantic adaptive coefficients to output semantic enhancement features; combining the semantic adaptive coefficients and gray-level variance to obtain fusion weight coefficients; weightedly fusing the semantic enhancement features with the local low-frequency residual components to obtain fusion features; inputting the combined feature map into an image enhancement network model; outputting clear underwater image fragments; and stitching them with the original image of the non-degraded region to obtain a complete underwater enhanced image. This invention achieves accurate quantification and frequency domain compensation of global degradation differences, solves the problem of global and local enhancement imbalance, and improves the integrity and consistency of underwater image enhancement.

The invention relates to the technical field of underwater image processing, in particular to a multi-layer tensor-based incomplete underwater hyperspectral image clustering method, which comprises the following steps of: acquiring an image to be processed, and acquiring incomplete spectral data of the image to be processed in different intervals; a clustering model based on spectral clustering learning is constructed, incomplete spectral data is processed based on the clustering model, and the clustering model comprises a projection operator information extraction module, a multilayer graph learning module, an adaptive weight module, a multistage tensor learning module and a nuclear norm constraint module; and iterating the hyperspectral clustering model based on an alternative update variable strategy until an iteration stop condition is met, and outputting a clustering result based on spectral clustering. According to the method, unified similar images are dynamically learned in all pixel points, the problems of view missing and incomplete observation can be effectively solved, complementarity among multiple views and hierarchical structure characteristics of underwater targets can be fully mined, and the method is suitable for unsupervised clustering tasks of complex underwater hyperspectrums.

The application discloses an end-to-end underwater three-dimensional reconstruction method and system based on an underwater imaging model, and belongs to the technical field of underwater image processing.The application combines deep learning pose estimation with an underwater imaging model; firstly, a plurality of underwater image sequences are collected as input to construct a deep neural network, the network mainly comprises two core sub-modules: one is a pose estimation network; and the other is a three-dimensional reconstruction network, according to the predicted pose and image content, dense point cloud or voxel reconstruction is completed, the pose estimation and the three-dimensional reconstruction process are integrated in the same system to realize overall joint optimization; and the adaptive underwater imaging model is combined to model the physical processes such as underwater light attenuation and scattering, so that the realism and accuracy of the reconstruction result are improved.The application realizes high-quality three-dimensional reconstruction of images in a complex underwater environment, and can be widely applied to ocean engineering, underwater robots, seabed topographic mapping and underwater cultural relic protection.

The invention discloses a non-pairing underwater image enhancement method based on structure perception multi-mode fusion, and belongs to the technical field of underwater image processing. Comprising the following steps: constructing a generator network based on a U-shaped Transform; training a generator network by using a non-paired data set, and carrying out combined constraint by using generative adversarial loss and multi-scale Patch NCE comparison loss; and performing channel splicing on a to-be-processed underwater RGB image, the space depth image and the structure prior image, constructing a multi-modal input tensor, then feeding the multi-modal input tensor into the trained generator network, and outputting an enhanced underwater image through forward propagation. According to the method, the depth map and the structure prior map are introduced, the perceptual ability of the network to the geometric contour is enhanced, global modeling and non-pairing comparative learning of Transform are combined, high-fidelity restoration of the high-turbidity underwater image is achieved under the condition that paired data is not needed, and the method can be widely applied to the fields of ocean exploration, underwater monitoring and the like.

The application discloses a dark underwater image processing method based on color space conversion, which comprises the following steps: firstly, pre-acquired underwater images are down-sampled to reduce the image size and copied into two images; secondly, color space conversion is performed on the two parts of underwater images respectively; thirdly, an underwater optical imaging image model is established, and the first converted underwater image is processed by using an image deblurring algorithm to obtain a clear image with high contrast; fourthly, an improved white balance algorithm is used to process the deblurred image; fifthly, a nonlinear channel prior is introduced into a traditional image deblurring model to minimize the item to eliminate the motion blur problem caused by water flow fluctuation; sixthly, the obtained accurate blur kernel and potential clear image are iterated with the initial restored image to obtain a final restored image; and finally, the two images are fused, re-sampled and outputted to obtain a final clear underwater image. The application can better realize image restoration, improve the brightness and contrast of the image and improve the recognition degree.

The invention provides an underwater target detection method based on gating guidance and feature supplementation, relates to the technical field of underwater image processing, and particularly mainly adopts the idea of gating guidance feature fusion and multi-scale feature supplementation to dynamically select and weight features of different levels through a gating mechanism, so that the detection accuracy of the underwater target is improved. Redundant features are effectively filtered, significance of target information is enhanced, and expression of target related features is enhanced. And aiming at the problem that the feature information of the underwater small target is fuzzy along with the increase of the depth of the network, the method adopts the idea of multi-scale feature supplementation, improves the receptive field and semantic expression of shallow features, and improves the detection performance of the small target. And finally, training and reasoning are carried out based on the real scene underwater data set, and accurate underwater target positioning information is obtained.

The invention provides an underwater image enhancement method based on space and scale context awareness, which relates to the technical field of image processing, and comprises the following steps of: under a generative adversarial network framework, introducing a context awareness strategy, and combining a space context feature enhancement module and a scale context interaction module to obtain an underwater image enhancement result; and the detail recovery, color correction and noise suppression capabilities of the underwater image are effectively improved. According to the method, the image can be optimized on different scales, the noise problem in underwater image degradation is solved, meanwhile, the sense of reality and the visual quality of the image are enhanced, and a new solution is provided for the field of underwater image processing.

The invention discloses an underwater image processing method and device, computer equipment and a storage medium, and relates to the field of image processing. The method comprises the following steps: measuring the optical power change of laser emitted by a laser in an underwater medium transmission process by using an optical power meter to obtain an underwater optical attenuation coefficient; the method comprises the following steps: acquiring an underwater image by using a binocular camera, and extracting a background light value and depth information in the underwater image; and processing the underwater image according to the light attenuation coefficient, the background light value and the depth information in combination with a Jaffe-McGlamery model to obtain a target image. According to the invention, image processing is carried out by combining the binocular camera and the measured data of the light attenuation coefficient, so that the visual quality of the underwater image is remarkably improved; and meanwhile, the algorithm is simple, near-real-time underwater image processing can be realized, and the real-time processing requirement of a dynamic underwater environment is met.

The invention relates to the technical field of underwater image processing, in particular to an underwater image enhancement method based on double-branch complementary input and cross-branch cross-layer state transition, and the method comprises the steps: obtaining an underwater image; an underwater image enhancement network model is constructed, the underwater image enhancement network model comprises a first branch, a second branch and a state transition module, the first branch comprises a self-adaptive feature extraction module, a multi-scale spatial pyramid pooling module, a channel splicing fusion layer and a tail end self-adaptive feature extraction module, and the second branch comprises a multi-scale spatial pyramid pooling module. The second branch comprises a channel intensity inversion layer, a self-adaptive feature extraction module, a multi-scale spatial pyramid pooling module, a channel splicing fusion layer and a tail end self-adaptive feature extraction module; training an underwater image enhancement network model; and inputting the test set into the trained model, and outputting an enhanced underwater image. According to the method, the color recovery precision and the detail retention performance of the underwater image in a variable environment are improved.

This invention discloses an underwater target saliency detection method and system based on polarization multi-stage fusion, belonging to the field of computer vision and underwater image processing technology. The method acquires four-angle polarization images of turbid water and calculates the degree of linear polarization, then normalizes them to generate a polarization-enhanced image. Subsequently, high-frequency edge components are extracted through brightness enhancement and the Laplacian operator, and a preprocessed image is obtained by injecting learnable weights. A pre-trained deep neural network is then used to fuse the original image and the preprocessed image, outputting a saliency prediction map. This invention fully exploits polarization features, effectively suppresses scattering noise, and significantly improves the precision of underwater target edge segmentation.

The present invention proposes a novel underwater image processing method for brightness and color correction, belonging to the technical field of image processing. The method includes: inputting an underwater image and extracting its features, calculating the base layer and the detail layer of the image according to its features. By restoring the brightness of the detail layer, a brightness correction map is obtained. At the same time, estimating the maximum attenuation map of the underwater image, and using the maximum attenuation map to enhance the details and textures of the brightness correction map, thereby obtaining a color correction map. Then, calculating the gradient distribution map and the pixel stretching distribution map of the V channel in the HSV color model of the color correction map. Finally, fusing these two distribution maps to enhance the global contrast of the color correction map. This method significantly improves the visual quality of underwater images, making the images clearer and more realistic, and has broad application prospects.

The invention relates to an underwater image processing method based on multi-dimensional weighting, and belongs to the technical field of data processing, and the method comprises the steps: carrying out the zooming processing of an underwater target image, and obtaining a feature image after the zooming processing; adding a multi-dimensional feature enhancement module MFEM into the neck network of the neural network model to obtain an image processing model; performing feature extraction on the scaled feature image to obtain a feature image after feature extraction; dimensionality adjustment and average pooling are carried out on the feature image after feature extraction, attention weights are generated in the channel dimensionality, the height dimensionality and the width dimensionality respectively, the attention weights and the feature image after feature extraction are multiplied element by element, and then a feature image after feature fusion is obtained through connection. The problem of insufficient sensitivity of target edge and position information is solved, key target features can be self-adaptively enhanced, background interference is suppressed, and the image processing capability in a complex underwater environment is remarkably improved.

The invention discloses an underwater image enhancement method paying attention to features, and belongs to the technical field of underwater image processing. The method comprises the following steps: acquiring underwater image data to be processed; underwater image data to be processed are input into the trained underwater image enhancement network, the underwater image enhancement network realizes image denoising based on a conditional diffusion model, the underwater image enhancement network comprises a coding module, a decoding module and a local feature enhancement module, the coding module comprises four layers of Encoders, the decoding module comprises three layers of Decoders, and the local feature enhancement module comprises a local feature enhancement module. The first three layers of Encoder are sequentially connected with the input of the corresponding Decoder layers in a jumping manner; and obtaining the output of the local feature enhancement module as an underwater image enhancement result. According to the method, image enhancement is carried out based on a conditional diffusion probability model, a transformer network structure is added to a coding layer, a local enhancement module is added to a decoding layer, and then based on a local feature enhancement module with an attention mechanism, important context information is better focused, the influence of redundant information is reduced, and feature representation is enhanced.