15results about How to "Improving Semantic Segmentation Accuracy" patented technology

The invention discloses a roof photovoltaic identification and evaluation method and system based on key point detection enhanced semantic segmentation, and a storage medium. The method comprises the following steps: extracting significant feature points of a roof from a satellite image as key points; for each detected key point, generating a descriptor vector; combining the generated key point information with a pre-trained semantic segmentation network, and optimizing a preliminary segmentation result of the semantic segmentation network by using the key point information; and carrying out key point matching and similarity comparison by using the descriptor vector to identify the contour and important structural features of the roof, and classifying and identifying the roof according to a matching result to obtain a final roof segmentation result. According to the method, through combination of key point detection and semantic segmentation, high-precision identification and description of a roof in a complex environment are realized, and the method has good robustness and adaptability.

The invention relates to a 3D semantic scene completion method. The method comprises the following steps: step 1, acquiring an RGB image of a 3D scene by using a binocular camera; 2, constructing a voxel occupancy prediction network, and inputting the collected image into the voxel occupancy prediction network to obtain a voxel grid; 3, constructing an attention enhancement feature fusion module, and performing fine adjustment on the voxel grid by using the attention enhancement feature fusion module to obtain a three-dimensional voxel query set; 4, extracting two-dimensional features from the collected images, associating the three-dimensional voxel query set with the two-dimensional features through a variable cross attention mechanism, and updating voxel data; 5, introducing mask marks to supplement voxel data, and extracting voxel features from all voxel data by using a self-attention mechanism; and 6, inputting the voxel features into an AUHead semantic segmentation head for semantic segmentation, and projecting a result to an output space to obtain a 3D scene graph. According to the invention, the space occupation integrity and semantic segmentation accuracy of 3D semantic scene completion are improved.

The invention relates to the field of remote sensing image processing, and discloses a high-resolution remote sensing image semantic segmentation passive domain self-adaption method and device, and the method employs a prototype guiding consistency learning module of teacher and student knowledge distillation, optimizes pseudo label generation and quality through knowledge transmission, data enhancement and a prototype guiding mechanism, and improves the semantic segmentation precision of a high-resolution remote sensing image. Feature alignment of a source domain and a target domain is improved, and particularly, the segmentation effect is remarkably improved in small ground feature recognition; through a cross-domain feature enhancement module, the feature extraction capability of complex boundaries and small ground features is enhanced by using channel adaptive weight distribution, so that the segmentation precision of a target domain is improved; a passive domain adaptive strategy is adopted, under the condition that source domain data cannot be accessed, a target domain is optimized based on a pre-trained source domain model, the data privacy and safety problems are solved, and the generalization performance of cross-domain semantic segmentation is improved. According to the method, the condition that source domain data are unavailable is effectively handled, and the segmentation precision of the cross-domain difficult-to-classify region in the remote sensing image is remarkably improved.

The invention relates to an image processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring an electric power construction image, extracting an initial feature map from the electric power construction image, performing multi-scale coding based on the initial feature map, obtaining a global semantic feature map corresponding to the electric power construction image, performing multi-scale decoding on the global semantic feature map, obtaining a decoded feature map, and outputting the decoded feature map. Semantic segmentation is carried out on the electric power construction image based on the decoded feature map, a segmentation result corresponding to the electric power construction image is obtained, and the segmentation result comprises an image area in the electric power construction image and a category to which the image area belongs. By adopting the method, the accuracy of image semantic segmentation can be improved.

The invention discloses a wetland fine mapping method based on remote sensing images and a deep learning super-resolution algorithm, which comprises the following steps of: firstly, acquiring high-resolution and low-resolution remote sensing images of a research area, pre-processing the high-resolution and low-resolution remote sensing images, and pairing high-resolution wetland samples with low-resolution images to obtain a high-resolution wetland data set; secondly, acquiring land coverage data and extracting wetland information to obtain a low-resolution wetland data set; then, inputting the low-resolution wetland data set and the high-resolution wetland data set into a convolution transformation super-division network reconstruction feature based on a convolution block attention module, and performing segmentation by using a U-Net architecture based on Scharr convolution and fast Fourier convolution; thirdly, for a wetland mapping task, designing a weighted loss function of three loss functions, and improving the wetland mapping precision from image details, time sequence and image consistency; finally, an optimal model is selected through evaluation and used for wetland fine drawing, so that the precision of wetland fine drawing is improved, and powerful support is provided for wetland research in various fields.

The present invention belongs to the technical field of remote sensing image semantic segmentation methods, specifically a remote sensing image road segmentation method based on topology-aware neural network. The method comprises the following steps: 1) dividing a high-resolution remote sensing data set into a training set and a test set, and preprocessing the remote sensing images in the training set and the test set respectively; 2) building an image semantic segmentation network model; 3) inputting the training set into the semantic segmentation network, first initializing the semantic segmentation network, then updating the parameters in the model, and optimizing the loss function until convergence; 4) inputting the test set data into the trained generator module to obtain a high-precision semantic segmentation result. The present invention solves the problems existing in the existing remote sensing image road automatic extraction technology, such as insufficient feature expression capability, inability to accurately perceive the topological structure of the road, context information being limited to a single training sample, large loss of edge and detail information in the semantic segmentation process, and a large number of samples required for training.

The invention provides a semantic segmentation method and a semantic segmentation device for point cloud data and electronic equipment. The semantic segmentation method comprises the steps that voxels obtained through conversion based on input point cloud data are processed, and initial features are obtained; performing down-sampling processing on the initial feature for a preset number of times to obtain a down-sampling feature; global features are extracted from the down-sampling features, the global features and aerial view features are fused, fused features are obtained, and the aerial view features are obtained through conversion from the global features; performing up-sampling processing of a preset number of times on the fusion feature by combining a result of the down-sampling processing of the preset number of times to obtain an up-sampling feature; and semantic tag prediction is carried out based on the up-sampling features, so that a semantic segmentation result is obtained.

The application discloses a convex mirror reflection image generation and semantic segmentation method and device, and relates to the field of convex mirror reflection images. The generation method comprises the following steps: a world coordinate system and a camera coordinate system are constructed, and a relationship between the world coordinate system and the camera coordinate system is established based on pose parameters of a convex mirror reflection image; a radial distortion is performed on a planar image placed in the camera coordinate system; and the distorted image is rotated around the X-axis and the Y-axis of the world coordinate system to obtain a convex mirror reflection image of the planar image. The application simulates convex mirror imaging by means of a convex mirror simulation module, and makes the simulated convex mirror image and the real image close in geometric shape through adversarial learning, so that the semantic segmentation precision of the real convex mirror reflection image is improved.

The present invention relates to the field of autonomous driving technology, and in particular to a method, device and vehicle for real-time semantic segmentation of three-dimensional point clouds with multi-view fusion, including: registering and splicing the original point cloud data to obtain full-view angle point cloud data centered on the vehicle, converting the basic features of each point in the point cloud into a series of feature vectors, refining the point cloud layer by layer, capturing local details and integrating global context information, performing multi-scale fusion of features according to the point cloud attention mechanism, and outputting the semantic label prediction value of each point through the confidence filtering mechanism. Thus, the problem that the point cloud semantic segmentation method is difficult to adapt to complex and changeable road scenes, the feature expression is incomplete, and there are limitations such as quantization loss, semantic inconsistency, and low computational efficiency is solved, and the semantic segmentation accuracy of point cloud data in autonomous driving scenarios is significantly improved, and the local detail processing and global context information integration in the point cloud semantic segmentation in autonomous driving scenarios are realized.

The invention discloses a roadside parking scene analysis method and system for a night scene, and relates to the field of intelligent parking management.The method comprises the steps that firstly, connection of two different modal data of an image and an event is constructed through an image motion feature extraction model; then, a content feature extraction model is utilized to reduce the difference of data between two different domains of a daytime scene and a night scene, the requirements of model efficiency, robustness, accuracy and the like in a roadside scene are considered, and meanwhile, a semantic segmentation model structure is adopted to realize a scene analysis task of the night scene; the classification and mask output of different targets in the roadside scene is realized, the semantic segmentation precision of the night scene is improved, and the traffic management of the roadside parking scene is facilitated.

The invention discloses a remote sensing image fine-grained semantic segmentation method and device, and the method comprises the steps: constructing a neural network based on a cross-domain encoder-cross-domain decoder, obtaining a plurality of earth observation remote sensing images as a training set, training the constructed neural network, and obtaining a semantic segmentation model, the method is used for fine-grained semantic segmentation prediction of earth observation remote sensing images. According to the neural network, a cross-domain coupling layer is used for replacing a common convolution block to carry out more comprehensive modeling on fine-grained textures and periodic modes in a frequency domain and edges, shapes and wide structural elements in a spatial domain, and the neural network is used for enhancing the distinguishability of learning representation; feature representations of the encoder and the decoder are aggregated through the cross-level fusion module, and the gap between the encoder and the decoder is bridged. According to the method, the frequency domain and space domain features can be effectively combined, the distinguishability and context understanding of the learned feature representation are enhanced, the limitation of capturing fine-grained textures and periodic modes is solved, and the semantic segmentation precision is improved.

The present invention belongs to the technical field of semantic segmentation methods for surface crack images, and specifically is a surface crack detection method based on a multi-scale topological perception neural network. The method comprises the following steps: step one: dividing the surface crack data set into a training set and a test set, and preprocessing the images in the training set and the test set respectively; step two: building a semantic segmentation network for surface crack images; step three: inputting the preprocessed surface crack images of the training set in step one into the surface crack semantic segmentation network in step two for training, first initializing the surface crack segmentation network using the He Uniform method, then updating the parameters in the model, and optimizing the loss function until convergence; step four: inputting the preprocessed test set remote sensing images into the surface crack segmentation network trained in step three, and outputting the segmentation results. The present invention solves the problem of poor feature representation capability in existing crack target detection.

The invention relates to an image semantic segmentation method and electronic equipment. The method comprises the following steps: cutting a local window in a to-be-processed image, and cutting two context windows with different resolutions in a down-sampling image obtained by down-sampling the to-be-processed image; respectively carrying out feature coding on the local window and the two context windows to obtain corresponding convolution feature maps; on the basis of the convolution feature map, attention calculation is carried out on the local window and the local window, and attention calculation is carried out on the local window and the local window and the two context windows respectively, and weighted fusion is carried out to obtain an attention feature map of the local window; obtaining a fusion feature map of the local window based on the convolution feature map of the local window and the attention feature map; and performing semantic segmentation processing on the local window based on the fusion feature map of the local window. According to the method and the device, the technical problems that how to understand and fuse context semantics for an ultrahigh-resolution pathological section image local window and that accurate semantic segmentation is difficult to realize based on the local window are solved.

This invention belongs to the field of semantic segmentation technology, proposing a semantic segmentation method and system based on multi-scale semantic enhancement. The method includes: constructing a multi-scale semantic segmentation model; acquiring an input image and inputting it into a backbone network for feature extraction, obtaining a shallow feature map containing spatial structure information and a deep feature map containing high-level semantic information; inputting the deep feature map into a multi-scale semantic enhancement module for multi-scale modeling enhancement, obtaining deep enhanced features; inputting the deep enhanced features into a multi-scale context aggregation module for global semantic integration, obtaining integrated features; inputting the shallow feature map and integrated features into a feature fusion module for feature fusion, obtaining fused features; and inputting the fused features into a classification output module for classification processing and outputting pixel-level semantic segmentation results. This invention solves the problems of insufficient multi-scale modeling capability, inadequate representation of structural information, and difficulty in balancing accuracy and efficiency in existing semantic segmentation methods.

The invention discloses a multi-modal remote sensing image semantic segmentation method based on a discrete diffusion model, and relates to the field of remote sensing image semantic segmentation. The method comprises the following steps: firstly, extracting the isomorphic feature of each modal, extracting the attention weight of the isomorphic feature of each modal by using a full connection layer with non-shared parameters, performing weighting, and adding the weighted modal features to obtain a multi-modal feature after adaptive fusion; then adding random noise on the real probability distribution matrix by using a state transition matrix to obtain a probability matrix in which all types of probabilities are equal, and deriving inverse diffusion real distribution of the discrete diffusion model through a Bayesian formula; and finally, predicting an undiffused real probability matrix by taking the fused multi-modal features as conditions and the diffused real probability matrix as input. According to the method, the problems of heterogeneity and information conflict among different modes can be effectively solved, the understanding ability of the model to a complex environment is remarkably improved, and the generalization ability and robustness of the model in various scenes are enhanced.