8 results about "Multi-scale approaches" patented technology

The invention discloses a key process variable prediction method based on an InduDK-LLM model, and the method specifically separates the modeling of an industrial process variable and an operation variable, and combines historical time sequence data and industrial field knowledge. Firstly, a pre-trained LLM is introduced to process time series data of domain knowledge and operation variables so as to generate industrial prior codes rich in semantics, and the pre-trained LLM reduces the requirement for manual prompt engineering. In addition, the process variables are decomposed through a multi-scale method, and meanwhile, a learnable joint mark is designed to promote interaction between the two types of variables. And finally, designing an interaction module to model an interdependency relationship and a potential logical relationship between the two types of variables. According to the method, accurate prediction of industrial key process variables is realized, and reference and guidance are provided for actual industrial production.

The invention relates to the technical field of deep learning and image processing, in particular to a degradation robust multi-scale context sensing network for remote sensing image segmentation, which comprises the following steps: a backbone feature extraction network module receives a remote sensing image and performs multi-stage feature extraction operation on the remote sensing image to obtain an initial feature map; a multi-granularity context aggregation module performs multi-scale context processing on the initial feature map through a multi-scale sliding window to obtain multi-granularity fusion features; and the robust four-directional feature fusion module performs directional component decoupling on the multi-granularity fusion features through the four-way directional convolution kernels, and fuses the directional features output by the four-way directional convolution kernels to obtain a target feature map. According to the scheme, a serial fusion normal form of a traditional multi-scale method can be broken through, up-sampling noise is avoided, and the segmentation consistency of a complex scene is remarkably improved; and the learning difficulty of the model is reduced through structured prior, and the discrimination of objects with special structures and direction characteristics is enhanced.

The application belongs to the technical field of image recognition segmentation, and discloses a medical image cell segmentation and tracking method, which comprises the following steps: step 1: data processing; feature extraction: the backbone part in the model is used to extract features from the preprocessed image, and the CSPDarknet structure is adopted in YOLOv8; step 3: FPN-PAN multi-scale feature fusion; step 4: Head prediction according to multi-scale features. The application realizes real-time tracking of the motion trajectory of cells by combining with a tracking algorithm such as deepsort. The method is mainly based on the YOLOv8 framework, and the Simam attention mechanism and the multi-scale proto method are adopted to optimize the model, so that the detection effect of YOLOv8 is further improved. The application can automatically complete the analysis and detection of medical images, is high in convenience and easy to use.

The application discloses a key process variable prediction method based on an InduDK-LLM model, which separates the modeling of industrial process variables and operation variables, and combines historical time series data and industrial field knowledge. First, a pre-trained large model (pre-trained LLM) is introduced to process the time series data of the field knowledge and the operation variables to generate semantic-rich industrial prior encoding, wherein the former reduces the need for manual prompt engineering. In addition, the process variables are decomposed by a multi-scale method, and a learnable joint label is designed to promote the interaction between the two types of variables. Finally, an interaction module is designed to model the interdependence and potential logical relationship between the two types of variables. The method realizes accurate prediction of the key process variables of the industry, and provides reference and guidance for actual industrial production.

The present application belongs to the technical field of numerical simulation of microstructure evolution in additive manufacturing process, and provides a method for predicting microstructure morphology of alloy solidification based on a phase field-lattice Boltzmann method multi-scale model.The present application introduces laser parameters and alloy parameters into a flow and heat transfer model of a macroscopic molten pool, extracts parameters of a local position in the macroscopic molten pool that needs to be simulated, substitutes the extracted parameters into a phase field-lattice Boltzmann model, obtains microstructure simulation data packets for visual processing, and obtains the microstructure morphology of alloy solidification.The method of the present application is a multi-scale method, is directed to additive manufacturing, and can more comprehensively establish a connection between process parameters and microstructure.Based on the phase field-lattice Boltzmann model, the influence of flow is considered in the process of microstructure growth, and the result is more accurate.The present application can effectively simulate the mechanism of the effect of the flow field on the dendrite front in the process of dendrite growth, and can simulate how the flow field affects the solute distribution at the dendrite tip.

This invention discloses an image enhancement method and system based on improved MSR and CLAHE, belonging to the field of image enhancement technology. The method involves extracting the reflection components from each channel using the improved MSR algorithm, quantizing them back to 0-255 to obtain R1, G1, and B1, and then performing CLAHE on the green channel G1 and the blue channel B1 to obtain G2 and B2, resulting in a color image img2. Guided filtering is then applied to img2, and a multi-scale method is used to extract and enlarge its detail information, achieving detail preservation. Finally, the image is converted to the HSV color space, and adaptive gamma correction is performed on the V channel to improve image brightness. The image enhancement method provided by this invention solves the problems of insufficient detail highlighting, low contrast, uneven brightness, and color distortion in existing medical image enhancement methods for cervical cancer images.

The invention discloses a multi-scale radiation cascade remote sensing satellite in-orbit relative radiation calibration method and system. The method comprises the steps that S1, sequence image alignment is completed based on an SIFT algorithm or other image alignment methods; s2, completing earth surface truth value estimation based on a mean value estimation method or other probability estimation methods, and obtaining a relative radiometric calibration reference image; s3, extracting a gray value of each probe element of the area array on the sequence image; s4, constructing a radiation calibration model of the area array sensor; s5, completing radiometric calibration model calculation through a multi-scale method to obtain radiometric calibration coefficients of all scales; and S6, combining the radiation calibration coefficients of all scales. The in-orbit relative radiometric calibration work of the area array type remote sensing satellite is completed through the steps S1 to S6, the in-orbit relative radiometric calibration coefficient is obtained, and input is provided for radiometric correction of an original image. The method is suitable for in-orbit relative radiometric calibration of area array type remote sensing satellites, and has the advantages of being high in adaptability, high in frequency, high in precision, more convenient and low in cost.

This invention discloses a video instance segmentation method based on cross-frame instance association. The method inputs a sequence of video frames to be segmented into a multi-scale feature extractor to extract feature maps at different scales. A transformer encoder extracts spatiotemporal features, which are then fused using a pixel decoder. Finally, the fused spatiotemporal features are obtained through the transformer decoder, resulting in a final embedding vector. This embedding vector is then multiplied by the high-resolution spatiotemporal features to obtain the instance segmentation result. This invention learns the spatiotemporal correlation of dynamic instances and constructs more stable cross-frame instance associations through a multi-scale method oriented towards spatiotemporal features. This establishes reliable cross-frame instance associations, improving the accuracy of video instance segmentation tasks and achieving state-of-the-art performance on two popular datasets compared to recent methods.