Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

6results about How to "Effective denoising" patented technology

Geological surveying and mapping remote sensing image enhancement method

The invention relates to the field of image enhancement, in particular to a geological surveying and mapping remote sensing image enhancement method. The method comprises the following steps: firstly, acquiring a multispectral image of a geological surveying and mapping area to be measured, and performing color space conversion on the multispectral image to obtain a hue channel value and a brightness channel value of each pixel point in the multispectral image; the method comprises the following steps: segmenting a multispectral image to obtain different geological areas in the multispectral image and the category of each geological area, carrying out superpixel segmentation on the geological areas, and obtaining an unnatural feature coefficient of a superpixel block according to the edge shape features of the superpixel block, the distribution of hue channel values in the superpixel block and the change of brightness channel values in the superpixel block; and denoising the multispectral image by obtaining the ground feature classification interference index of each geological region to obtain an enhanced image. According to the invention, effective denoising of the remote sensing image can be realized, and the enhancement effect of the remote sensing image is improved.
Owner:HAINAN KAIQI SURVEY & DESIGN CONSULTING CO LTD

A method for enhancing remote sensing images in geological surveying and mapping

The present invention relates to the field of image enhancement, and specifically to a method for enhancing geological surveying and remote sensing images. The method first obtains a multispectral image of a geological surveying and mapping area to be measured, performs color space conversion on the multispectral image, and obtains the hue channel value and brightness channel value of each pixel in the multispectral image; the multispectral image is segmented to obtain different geological areas and the category of each geological area in the multispectral image, and the geological area is segmented into superpixels, and the edge shape features of the superpixel block, as well as the distribution of the hue channel value and the change of the brightness channel value inside the superpixel block, obtain the non-natural feature coefficient of the superpixel block, and then denoise the multispectral image by obtaining the interference index of the ground object classification of each geological area to obtain an enhanced image. The present invention can achieve effective denoising of remote sensing images and improve the enhancement effect of remote sensing images.
Owner:HAINAN KAIQI SURVEY & DESIGN CONSULTING CO LTD

Ultrasonic nondestructive testing A scanning signal noise reduction method and system based on improved U-NET

The invention discloses an ultrasonic non-destructive testing A scanning signal noise reduction method and system based on an improved U-NET, and belongs to the technical field of industrial ultrasonic non-destructive testing. A de-noising neural network based on U-Net is established; and training a denoising neural network based on U-Net by using the preprocessed ultrasonic A scanning defect signal, and then inputting an original signal with noise into the trained neural network to realize noise reduction processing. According to the method, the stability, robustness and universality of the noise reduction model can be improved, and various kinds of noise can be effectively denoised.
Owner:XI AN JIAOTONG UNIV

Joint space angle self-supervision denoising method for diffusion magnetic resonance data

The invention discloses a joint space angle self-supervision denoising method for diffusion magnetic resonance data. The method comprises the following steps: acquiring dispersion magnetic resonance data; processing the diffusion magnetic resonance data through an angle collector to obtain angle similar diffusion magnetic resonance data similar to the diffusion magnetic resonance data; the diffusion magnetic resonance data and the angle-similar diffusion magnetic resonance data are processed through a space sub-sampler, first sub-sampling data, second sub-sampling data and angle-similar sub-sampling data are obtained, the first sub-sampling data and the second sub-sampling data of an original space correspond to the diffusion magnetic resonance data, and the angle-similar sub-sampling data correspond to the diffusion magnetic resonance data; the angle similar sub-sampling data corresponds to the angle similar dispersion magnetic resonance data. According to the method, the problem that in the prior art, when the dispersion magnetic resonance imaging is denoised, space angle information is not fully utilized, and dispersion magnetic resonance data noise cannot be effectively eliminated is solved.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Method and device for constructing OAE signal extraction model

The present application proposes a method and device for constructing an OAE signal extraction model, including the following steps: constructing an OAE signal feature extraction model including a feature extraction module, a multi-scale noise reduction module, a timing capture module, and a result output module, and using a sound source signal to train the OAE signal feature extraction model so that it can extract features from the OAE signal. This solution constructs a multi-scale noise reduction module to use convolutional layers of different sizes to extract features in different frequency ranges in the sound signal and aggregate them, thereby achieving the effect of effective denoising and enhancing the OAE signal, and combines the scaled dot product attention mechanism for output to extract a pure OAE signal.
Owner:HANGZHOU AIHUA INSTR

An unsupervised adaptive hyperspectral remote sensing image denoising method

ActiveCN121437314BEffective denoisingImprove image quality
The application discloses a kind of unsupervised self-adapting hyperspectral remote sensing image denoising methods.The application includes the following steps: step S1.image preprocessing;Step S2.building unsupervised denoising framework and denoising model, the step S2 includes the following steps: S21.building unsupervised denoising framework;S22.building convolutional neural network denoising model;Step S3.model parameter update and stopping mechanism;Step S4.hyperparameter setting;Step S5.network inference and result output, step S1 after preprocessing hyperspectral remote sensing image and step S4 set hyperparameter input in step S2 building convolutional neural network denoising model, until it meets the stopping condition set in step S3, finally output denoising hyperspectral image.The application is applied to the technical field of remote sensing image processing.
Owner:ZHUHAI ORBIT SATELLITE BIG DATA CO LTD