- Full text PDF available (4)
- This year (1)
- Last five years (12)
Injuries that are caused by falls have been regarded as one of the major health threats to the independent living for the elderly. Conventional fall detection systems have various limitations. In this work, we first look for the correlations between different radio signal variations and activities by analyzing radio propagation model. Based on our… (More)
We present a novel approach to structure from motion that can deal with missing data and outliers with an affine camera. We model the corruptions as sparse error. Therefore the structure from motion problem is reduced to the problem of recovering a low-rank matrix from corrupted observations. We first decompose the matrix of trajectories of features into… (More)
As ubiquitous environments become increasingly commonplace with newer sensors and forms of computing devices (e.g. wearables, digital tabletops), researchers have continued to design and implement novel interaction possibilities. However, as the number of sensors and devices continues to rise, researchers still face numerous instrumentation, implementation… (More)
Due to the rapid growth of the smartphone applications and the fast development of the Wireless Local Area Networks (WLANs), numerous indoor location-based techniques have been proposed during the past several decades. Floorplan, which defines the structure and functionality of a specific indoor environment, becomes a hot topic nowadays. Conventional… (More)
An imaging strategy based on optical time-encoded structured illumination microscopy (TE-SIM) opens the way toward ultrafast superresolution imaging. A proof-of-principle experiment is conducted and the introduced TE-SIM accelerates the generation rate of sinusoidal fringe patterns to an unprecedented speed (dozens of megahertz). At such a high speed,… (More)
Computer vision and machine learning, currently focusing on clustering, labeling, motion analysis and structure recovery of complex scenes.
Single-pixel cameras based on the concepts of compressed sensing (CS) leverage the inherent structure of images to retrieve them with far fewer measurements and operate efficiently over a significantly broader spectral range than conventional silicon-based cameras. Recently, photonic time-stretch (PTS) technique facilitates the emergence of high-speed… (More)
We propose a framework using Google's Area Learning to create ubiquitous environments with cross-device proxemic interactions. We apply the framework to the domain of Emergency Response, and discuss the benefits and initial feedback of our framework.