G06T2211/00

Perspective method for physical whiteboard and generation method for virtual whiteboard

Disclosed are a perspective method for a physical whiteboard and a generation method for a virtual whiteboard. A Hoffman straight-line detection method is used, statistics are taken on a quantity of overlapping times of a straight line, and a determining dimension of a whiteboard-related straight line is increased. On a basis of generating a high-precision virtual whiteboard, purity of a whiteboard color is improved through color enhancement, and a virtual whiteboard corresponding to each frame of a physical whiteboard image is processed based on a preset algorithm to obtain a background-color image, a motion map, and a chromatic aberration map, so as to obtain a foreground mask. A character is perspective and smoothed based on a foreground mask of a current frame, a color-enhanced image of the current frame, and a fully perspective image of a previous frame.

Systems and methods for data augmentation

Systems and methods for data augmentation are provided. One aspect of the systems and methods include receiving an image that is misclassified by a classification network; computing an augmentation image based on the image using an augmentation network; and generating an augmented image by combining the image and the augmentation image, wherein the augmented image is correctly classified by the classification network.

Systems and methods for machine learning based physiological motion measurement

A system for physiological motion measurement is provided. The system may acquire a reference image corresponding to a reference motion phase of an ROI and a target image of the ROI corresponding to a target motion phase, wherein the reference motion phase may be different from the target motion phase. The system may identify one or more feature points relating to the ROI from the reference image, and determine a motion field of the feature points from the reference motion phase to the target motion phase using a motion prediction model. An input of the motion prediction model may include at least the reference image and the target image. The system may further determine a physiological condition of the ROI based on the motion field.

Image localization using a digital twin representation of an environment
12536786 · 2026-01-27 · ·

Examples described herein provide a method that includes capturing, using a camera, a first image of an environment. The method further includes performing, by a processing system, a first positioning to establish a position of the first image in a layout of the environment. The method further includes detecting, by the processing system, a feature in the first image. The method further includes performing, by the processing system, a second positioning based at least in part on the feature to refine the position of the first image in the layout. The method further includes capturing, using the camera, a second image of the environment and automatically registering the second image to the layout. The method further includes generating a digital twin representation of the environment using the first image based at least in part on the refined position of the first image in the layout and using the second image.