4results about How to "Short runtime" patented technology

This invention discloses a rendering optimization method, program product, and storage medium based on frame interpolation and super-resolution. The method includes: acquiring an optimized super-resolution rendering frame at time t as a first rendering frame, and acquiring a low-resolution rendering frame at time t+1 in the frame display sequence as a second rendering frame; reprojecting the first rendering frame and the upsampled second rendering frame to an intermediate frame time and correcting them together to obtain corrected data for a high-resolution intermediate frame; reprojecting the features of the first and second rendering frames to the intermediate frame time and combining them with the features of the corrected data for the high-resolution intermediate frame to reconstruct a super-resolution intermediate rendering frame; reprojecting the first rendering frame to the time of the second rendering frame and correcting it together with the upsampled second rendering frame to obtain corrected data for the second rendering frame; extracting features from the corrected data for the second rendering frame; and reconstructing the super-resolution rendering frame at time t+1 based on the features of the corrected data for the second rendering frame and the features of the second rendering frame. This invention has a short running time and good rendering effect.

This invention discloses a method and system for binocular image super-resolution reconstruction based on cross-scale disparity prior, comprising: S1: acquiring the original left feature map and the original right feature map corresponding to the low-resolution left and right binocular images; S2: using a binocular attention module to perform cross-view interaction on the original left feature map and the original right feature map respectively, to obtain the interacted left feature map and the interacted right feature map; S3: inputting the interacted left feature map and the interacted right feature map into the cross-scale disparity attention module, and fusing them to obtain an aggregated feature map; S4: inputting the aggregated feature map into a cascaded dynamic upsampling reconstruction network to obtain the reconstructed super-resolution binocular image. This invention can fully utilize disparity information and obtain more realistic and higher-quality super-resolution images in a shorter running time.

The application discloses a kind of control moment gyro high-speed bearing sliding state monitoring method based on transfer learning, belong to rolling bearing fault diagnosis technical field, comprising the following steps: S1, builds control moment gyro high-speed bearing sliding test bench, obtains motor current experimental data and bearing sliding data;S2, obtains motor current simulation data;S3, extracts current feature;S4, current feature is classified;S5, based on the current feature after classification, bearing sliding prediction model is constructed and trained, and motor current experimental data and motor current simulation data are input to the bearing sliding prediction model after training, and the classification result of bearing skidding is generated.The application has the advantages of high prediction accuracy and shorter running time in bearing sliding state prediction task based on simulation data training.

The application discloses a contour extraction method based on an adaptive ellipse edge detection and fast fitting algorithm, obtains an image region where an ellipse is located, and gives a search center, a search direction, a search frame position and size and a search space, and in the search space, from the search center to the search space boundary, according to the search direction, the whole search path of the search frame in the form of a ray is determined; all pixel values in the search frame are obtained; the gray values of all pixel points in the search frame are obtained; the obtained pixel values are clustered into two categories by using K-Means clustering; the ellipse is fitted by using a least square method; the point set far from the ellipse boundary is removed, and the point set close to the ellipse boundary, that is, the best inner point set, is left, so that the least square ellipse fitting is completed; and the last point set fitting result is drawn by using key coefficients of an ellipse equation obtained by the least square algorithm. The application can accurately find the positions of strong edges and weak edges of the ellipse, can autonomously screen inner points and can accurately fit the ellipse equation.