13 results about "Wavelet coding" patented technology

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 provides a lightweight wavelet convolution guide wire segmentation network model and a double guide wire generation method, and the construction of the model comprises the steps: obtaining an input image, carrying out the feature extraction of the input image through a Stem module, obtaining a bottom-layer feature, carrying out the processing of the bottom-layer feature through five wavelet encoders in an iteration manner, and carrying out the recognition of the processed bottom-layer feature through the five wavelet encoders. And inputting the features output by the wavelet encoders into a decoder in an iteration form to carry out decoding processing so as to obtain a segmented prediction map. The method comprises the following steps of: inputting the features output by the wavelet encoders into the decoder in an iteration form to carry out decoding processing on the features output by the wavelet encoders; the wavelet transform attention convolution provided by the invention is specially used for capturing complex edge and texture nuisance features of the guide wire. A channel attention mechanism is introduced after a wavelet decomposition process to enhance feature representation. The combination of channel attention can selectively emphasize key frequency components, significantly improve the ability of the network to capture complex texture modes, and improve the precision of guide wire segmentation.

An apparatus including at least one processor; and at least one memory including computer program code. The at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to: decode, for a frame of three-dimensional object data, a base mesh of the three-dimensional object data, wherein the base mesh has been generated with a geometry component; and decode, for the frame, a displacement field, where the displacement field comprises wavelet encoded and quantized position displacements.

The invention discloses a wavelet coding method for image data compression. The method comprises the following steps: determining a pixel array P to be processed; pixel data in the pixel array P is divided to obtain m channel data of each pixel; m pieces of channel data of each pixel in the pixel array P are sent to m different data processing channels respectively, and the channel data at the same position of different pixels in the pixel array P are sent to the same data processing channel; according to an arrangement mode of pixels in the pixel array P, arranging the extracted channel data to form m channel arrays P1 to Pm; wavelet transformation is carried out on channel data in the m channel arrays P1 to Pm, pixel values are converted into pixel difference values through horizontal and vertical two-step wavelet transformation, and channel arrays PT1 to PTm after wavelet transformation are obtained. According to the method, the image / pixel data can be effectively coded, and the compression ratio of subsequent data compression is remarkably improved.

The present invention discloses a target recognition method, system, device and medium for complex scenes, and relates to the field of computer vision technology. The method comprises: inputting a test image into a target recognition model for processing to obtain a target recognition result; the target recognition model is constructed based on a dual-path coding network and a weighted optimization loss function; the dual-path coding network includes a MobileNet path and a wavelet path; wherein the MobileNet path is used to extract multi-scale spatial features and is composed of a hierarchical encoder and a multi-feature prediction decoder connected in sequence; the wavelet path is used to extract frequency domain features and is composed of a global semantic wavelet coding module and a local wavelet fusion decoding module connected in sequence; the multi-feature prediction decoder is also connected to the global semantic wavelet coding module and the local wavelet fusion decoding module, respectively. The present invention can improve the precision and accuracy of target recognition for complex scenes.

The application provides an embryo development stage classification method and system based on residual perception and wavelet coding, and belongs to the embryo development stage classification field.The method comprises the following steps: acquiring an embryo image and performing pretreatment; performing a blocking operation on the pretreated embryo image, inputting the blocked image data into a residual perception attention module, and extracting a first feature map of the embryo image; inputting the first feature map into a wavelet position coding module, and extracting a second feature map containing frequency domain information; adding the first feature map and the second feature map and inputting the sum into a trained deep neural network, performing global feature extraction and coding, and obtaining a final feature map; inputting the final feature map into a classifier for development stage classification, and outputting a classification result of the embryo development stage. The method effectively overcomes the problem of spatial information loss in the downsampling method, enhances the sensitivity of the model to the frequency domain information, and improves the accuracy of the embryo development stage classification.

The application discloses a kind of space-time prediction methods based on wavelet coding and space-frequency dual-domain feature fusion, belong to space-time prediction technical field, comprising: obtaining by multiple time steps consisting of source space-time sequence, constructs input sequence and target sequence;Through wavelet downsampling, the input sequence is encoded step by step, and the spatial semantic representation with multi-scale characteristics is extracted;The representation after coding is organized as feature sequence according to time sequence, and time series modeling is carried out;Space-time feature containing state information and change clues is input into space-time conversion network, to realize cross space-time feature interaction;Through inverse wavelet reconstruction, the features after space-time conversion are decoded step by step, and future prediction sequence is generated.The application solves the problem that key information is easy to lose due to the use of conventional convolution sampling in existing methods, solves the problem that existing methods mainly rely on single spatial domain transformation, resulting in limited feature modeling, solves the problem that existing methods mainly rely on implicit learning, resulting in indirect time series modeling.

The present invention relates to the technical field of medical image classification, and specifically discloses a medical image classification method combining wavelet transform and tensor network. A coarsening network is proposed, which combines wavelet transform and MERA, that is, encoding D4 wavelet into MERA to form a waveletMERA model with fixed internal parameters, and a tensor classification network like a fully connected layer is also constructed. The present invention uses the MNIST dataset, the Covid-19 dataset and the LIDC dataset for multi-dimensional verification. The results show that the accuracy of waveletMERA is stably high, and it has better coarsening ability than the deep neural network of CNNs, enabling waveletMERA to reduce the number of model parameters to a greater extent while ensuring accuracy. The results show that waveletMERA is not only superior to the current mainstream deep neural networks in classification, but also superior to ordinary wavelet transform in data preprocessing. Moreover, waveletMERA also has the interpretability advantage of the tensor network itself.

The application discloses an image enhancement network method based on distribution alignment prior and wavelet coding and decoding, comprising the following steps: S1, super-lens infrared image data preparation and degradation analysis; S2, constructing a VAR distribution alignment domain adaptation module; S3, constructing an instruction-guided diffusion model module; S4, constructing a wavelet-guided codec module; S5, constructing a cross-modal feature fusion module: integrating complementary information from different representation spaces, and deeply cooperating the VAR distribution alignment domain adaptation module, the instruction-guided diffusion model module and the wavelet-guided codec module to jointly constitute an infrared super-lens image enhancement network; and S6, end-to-end image enhancement and reasoning deployment. Through multi-modal feature interaction and frequency domain adaptive fusion, the application realizes physical consistent high-quality image reconstruction.

The present invention proposes a method for constructing a lightweight wavelet convolution guidewire segmentation network model and a dual guidewire generation method. The construction method includes: obtaining an input image, using a Stem module to perform feature extraction on the input image to obtain underlying features, iteratively processing the underlying features through five wavelet encoders to obtain features output by the five wavelet encoders respectively, and iteratively inputting the features output by the wavelet encoders into a decoder for decoding processing to obtain a segmentation prediction map. The wavelet transform attention convolution proposed in the present invention is specifically used to capture the complex edges and texture subtle differences of the guidewire. A channel attention mechanism is introduced after the wavelet decomposition process to enhance feature representation. The combination of channel attention can selectively emphasize key frequency components, significantly improve the network's ability to capture complex texture patterns, and improve the accuracy of guidewire segmentation.

The invention provides an embryonic development stage classification method and system based on residual perception and wavelet coding, and belongs to the field of embryonic development stage classification. The method comprises the following steps: acquiring and preprocessing an embryo image; carrying out blocking operation on the pre-processed embryo image, inputting blocked image data into a residual error perception attention module, and extracting a first feature map of the embryo image; inputting the first feature map into a wavelet position coding module, and extracting a second feature map containing frequency domain information; adding the first feature map and the second feature map, inputting the added first feature map and second feature map into a trained deep neural network, and performing global feature extraction and coding to obtain a final feature map; and inputting the final feature map into a classifier for developmental stage classification, and outputting a classification result of the embryonic developmental stage. The problem of spatial information loss in a down-sampling method is effectively solved, the sensitivity of the model to frequency domain information is enhanced, and the classification accuracy of the embryonic development stage is improved.

The invention discloses a medical image segmentation method based on wavelet condition potential diffusion, and relates to the technical field of medical image segmentation, and the method comprises the following steps: obtaining a medical input image, executing a structure-maintained color enhancement operation in a training stage, and using an original input image in a reasoning stage; the preprocessed image is embedded by adopting a multi-scale wavelet encoder extraction condition, and the encoder is realized through multi-layer discrete wavelet transform, high-frequency residual enhancement, inverse discrete wavelet transform and down-sampling splicing; encoding a segmentation target corresponding to the input image through a pre-trained and parameter-frozen auto-encoder to obtain a potential mask; inputting the semantic priori condition and the potential mask into a diffusion UNet, embedding a frequency domain sensing gating block in jump connection of the diffusion UNet, and performing potential space denoising through a regularization iterative algorithm to obtain an optimized potential mask; and decoding the optimized potential mask through a decoding function of the auto-encoder, and outputting a final medical image segmentation result.

The invention relates to the technical field of image compression, in particular to an embedded zero-tree wavelet coding method, a storage medium and computer equipment, and the method comprises the steps: carrying out the wavelet transformation of an input image, and obtaining a wavelet coefficient matrix; scanning the wavelet coefficient matrix according to a preset threshold T, and marking important coefficient nodes; if the father node is not identified as the important coefficient, but the important coefficient exists in the descendant node, dynamically adjusting the coding strategy according to the distribution condition of the difference value M between the absolute value of the descendant node coefficient and the threshold value T; and performing zero-tree coding on the dynamically adjusted wavelet coefficient, and finally outputting compressed data. By dynamically adjusting the wavelet coefficient and optimizing the zero-tree structure, the number of nodes needing to be coded can be effectively reduced, the number of codes is reduced, and the coding efficiency is improved.