Abstract: Methods, systems and apparatuses may provide for technology that trains a neural network by inputting video data to the neural network, determining a boundary loss function for the neural network, and selecting weights for the neural network based at least in part on the boundary loss function, wherein the neural network outputs a pixel-level segmentation of one or more objects depicted in the video data. The technology may also operate the neural network by accepting video data and an initial feature set, conducting a tensor decomposition on the initial feature set to obtain a reduced feature set, and outputting a pixel-level segmentation of object(s) depicted in the video data based at least in part on the reduced feature set.

Abstract: Various techniques for performing camera control techniques based on brainwave data from an electroencephalography (EEG) headset are disclosed herein. In an example, a computing system operates to receive brainwave data representing brainwave activity, process the brainwave data, and transmit a command to a camera device based on the processed brainwave data. For example, the brainwave data may correlate to raw brainwave signals (from gamma, beta, alpha, theta, or delta brainwaves), or composite brainwave signals (from multiple brainwaves, representative of attention, meditation, or like states). As a result, the computing system may transmit a command to a camera device to capture an image, a burst of images, start/stop video recording, or like commands for image and video operations, based on a human user's detected brainwave state. Further processing, detection, and training methods for brainwave control of camera operations are also disclosed.