4results about How to "Avoid noise effects" patented technology

This invention discloses a method for simultaneous measurement of atmospheric temperature and pressure based on Rayleigh-Brillouin scattering spectroscopy, belonging to the field of lidar. The method includes: emitting a laser in the atmospheric environment to be measured and acquiring the scattered echo signal of the laser; fitting the Rayleigh-Brillouin scattering spectrum of the scattered echo signal in the atmospheric environment to be measured; extracting the overall linewidth Γ of the Rayleigh-Brillouin scattering spectrum; and calculating the number of molecular scattered photons N. s ; will N s Substituting G1 and Γ into the inversion model yields the synchronous measurement results of atmospheric temperature T and pressure p; where G1 represents the atmospheric temperature and the overall linewidth Γ and the number of molecular scattered photons N. s The relationship between pressure and overall linewidth Γ and the number of molecular scattered photons N is expressed as follows: s The relationship between Rayleigh and Brillouin scattering spectra and atmospheric temperature and pressure is fully explored in this invention, establishing a new inversion model that enables accurate and synchronous measurement of atmospheric temperature and pressure.

The application provides a kind of unattended station personnel invasion identification method and device, the method comprises: the picture to be detected is input to personnel invasion identification model, obtains the invasion identification result of personnel invasion identification model output;Wherein, personnel invasion identification model includes image denoising network, feature extraction network, occlusion perception attention network and invasion prediction network, image denoising network is used to denoising sample picture, based on occlusion perception attention network is used to apply sample picture feature, determine the correlation between the occluded human body area and the unoccluded human body area in sample picture.The image denoising network is used to denoise the picture, so as to avoid the noise influence brought by natural environment such as wind, frost, rain, snow and fog to data source.In addition, through the occlusion perception attention network, the problem that human body occlusion caused by the invasion personnel climbing wall affects the invasion personnel identification can be avoided.

This invention provides a method for predicting lithographic imaging contours and related products. The prediction method includes acquiring a target design layout; generating a target directed distance field map corresponding to the target design layout using a pre-trained prediction model, the target directed distance field map reflecting the directed distance of any point to the nearest lithographic imaging contour; and extracting the lithographic imaging contour from the target directed distance field map to obtain a target lithographic imaging contour map. This method can effectively avoid the influence of noise in measured lithographic imaging images, enabling the prediction model to accurately obtain the mapping relationship between the input design layout and the directed distance field map of the measured lithographic imaging image, resulting in a high-precision target lithographic imaging contour map.

The application discloses a kind of based on the dual hand reconstruction method of multi-scale color information and depth information fusion.Utilize dual-flow feature extraction model respectively to extract monocular RGB-D image multi-scale color feature, left and right hand corresponding center point feature and multi-scale depth feature;Then use pyramid type depth fusion network to fuse multi-scale color feature, left and right hand corresponding center point feature and multi-scale depth feature, obtain left and right hand corresponding global fusion feature;Finally, according to left and right hand corresponding global fusion feature, using GCN decoder generates dual hand grid in camera coordinate system.The application can fully fuse color information and depth information to reconstruct both hands, reduce the blur effect in RGB image and the noise in depth image, greatly improve the reconstruction accuracy, and enhance the robustness of model;Meanwhile, the application can accurately reconstruct three-dimensional hand grid with real depth and scale in camera space, overcome the limitation of relying on root node output.