6results about How to "Guaranteed reconstruction quality" patented technology

The invention provides a video coding method and device and a video decoding method and device, and relates to the technical field of video coding and decoding. Comprises: obtaining a student model; the student model is a model obtained by guiding a first network model to train through a teacher model, the teacher model is a model obtained by training a second network model, and when the same video is coded based on the first network model and the second network model respectively, the first network model and the second network model are selected; the code rate of the coding result of the first network model is smaller than that of the coding result of the second network model; and obtaining a coding result of the video to be coded according to the student model. According to some embodiments of the invention, in a video coding scheme for carrying out video coding by using a deep learning network model, the video reconstruction quality is ensured, and the code rate of a video coding result is reduced at the same time.

The application discloses a real-time leakage positioning monitoring system and method based on electrical resistance tomography, relates to the technical field of process tomography and industrial safety monitoring, and solves the technical problem that it is difficult to intelligently identify, three-dimensionally position and quantitatively evaluate leakage events; the system comprises a sensor array, a multi-channel data acquisition and excitation module, a real-time data processing and image reconstruction module, a leakage intelligent identification and positioning module, a man-machine interaction and data management module; the core lies in that a multi-layer nested annular array and a sparse measurement strategy are adopted to improve data acquisition efficiency, a physical information neural network is introduced to reconstruct an image, a measurement topological coding matrix and a physical residual correction module are used to reconstruct the image, and finally, a time-space dual-domain leakage probability field model is constructed, a virtual sensor network and an improved D-S evidence reasoning framework are combined to intelligently identify and position a leakage diffusion mode.

The application belongs to the technical field of compressed sensing reconstruction, and particularly relates to a compressed sensing reconstruction method and system based on adaptive fragmentation and dynamic resource management. Original signal data of a target scene is acquired through sparse sampling; when the total length of the original signal data is greater than a preset fragmentation length parameter, the original signal data is divided into a plurality of fragmented data to form a signal fragmented set; the memory usage of the system is monitored in real time; when the memory is greater than a preset storage threshold, dictionary elements are generated and the generated results are cached; when the memory is less than or equal to the preset storage threshold, the dictionary elements are directly used after being generated, and the storage space occupied by the dictionary elements is released after being used up; then, each fragmented data is reconstructed, and a complete reconstructed signal is obtained through linear splicing and fusion. The application is suitable for processing sparse reconstruction tasks of large-scale signal, image and video data, and can significantly reduce the demand for computing resources while ensuring the reconstruction quality.

The embodiment of the invention discloses a scene reconstruction method and device, equipment and a storage medium, and the method comprises the steps: carrying out the scene reconstruction through a preset scene reconstruction mode if a current moment is a first three-dimensional scene relative to a target scene, and obtaining a current three-dimensional scene; otherwise, acquiring a plurality of first image frames and second image frames formed by acquiring the target scene at different visual angles, and acquiring a previous three-dimensional scene reconstructed based on the target scene; according to the first image frames and the second image frames, performing pose adjustment on Gaussian points in the previous three-dimensional scene to obtain a deformed three-dimensional scene; performing Gaussian point addition and deletion and Gaussian point feature optimization processing on the deformed three-dimensional scene according to each second image frame to obtain a processed optimized three-dimensional scene; and determining the optimized three-dimensional scene as a current three-dimensional scene at the current moment. According to the method, the current three-dimensional scene with higher relevance with the previous three-dimensional scene can be obtained in the time domain, so that the smoothness and continuity from the previous three-dimensional scene to the current three-dimensional scene in the time domain are ensured.

This invention discloses a deep learning-based method for super-resolution processing of airborne optoelectronic video images. It constructs a high-order dynamic degradation model that integrates basic image degradation operations with the physical degradation mechanism of airborne optoelectronics, simulating the complex degradation process of the real imaging chain through multiple rounds of degradation loops. The dynamic degradation model generates a training dataset of low-resolution and high-resolution image pairs. A super-resolution reconstruction network is constructed based on a generative adversarial network framework. The generator uses the RRDB module for deep feature extraction and reconstructs high-resolution images through multi-stage upsampling. The discriminator adopts a U-Net structure with spectral normalization and introduces semantic consistency constraints. A two-stage course learning is performed using a domain-specific training dataset. This method can accurately simulate the complex degradation process of airborne optoelectronic imaging, improve the model's generalization ability, enhance the fidelity of tactical target details, and enable real-time inference on airborne platforms.

The invention discloses an image super-resolution reconstruction method based on a geometric transformation enhanced state space model, and belongs to the technical field of image processing and computer vision. The method solves the problem of poor reconstruction quality caused by insufficient long-range dependence modeling capability, weak geometric transformation robustness and insufficient local texture detail recovery of the existing method. The method comprises the following steps: constructing a high-resolution and low-resolution image pair data set and constructing a reconstruction network; training the network by using the training set; and inputting a to-be-processed low-resolution image into the trained network to obtain a high-resolution image. The network comprises a shallow feature extraction module, a plurality of residual state space groups connected in series and a reconstruction module. Each residual state space group comprises a plurality of visual state space layers, and each visual state space layer sequentially performs geometric transformation enhancement, double-branch parallel processing, feature fusion, double residual learning and inverse geometric transformation on input. The method is used for converting a low-resolution image into a high-resolution image.