July 18, 2016
Activity Recognition
We propose a framework, consisting of several algorithms, to recognize human activities that involve manipulating objects using a Kinect camera. Our algorithm identifies objects being manipulated and models high-level tasks being performed accordingly. We evaluate our approach on a challenging dataset of 12 kitchen tasks that involve 24 objects performed by 2 subjects. The entire…
3D Object Modeling Using a Kinect Camera
We investigated the use of Kinect cameras for acquiring images of an object from multiple viewpoints and building a 3D model of the object. We developed methods to take care of the problems of noisy depth data, symmetrical objects and objects with relatively few views. Simulation results show that accurate 3D models could be constructed.
Real-Time Gaze Estimation with a Kinect Camera
We developed a 3D gaze estimation system that can estimate the gaze direction using a Kinect camera. A 3D geometric eye model is constructed to determine the gaze direction. Experimental results indicate that the system can achieve an accuracy of 1.4~2.7 degree and is robust against large head movements. Two real-time applications (playing chess and…
A Street-View Video Dataset
For research in autonomous cars and robotic applications, a street view video dataset with dense semantic labels will be very useful. Semantic labeling is vital for training models for object recognition, semantic segmentation or scene understanding. We developed a large-scale street-view suburban video dataset comprising over 400k images, and a 3D-to-2D label transfer method to…
Neuromorphic Computing
Neuronal networks are capable of processing specific data and tasks optimally and in real time. Many of these problems are computationally expensive to solve with current computing systems. We are developing algorithms and architectures inspired from the design principles of neurobiological networks to solve these problems more efficiently.
Predictive Computational Modeling of Neuronal Networks
Neuronal networks are capable of fusing sensory information into activity, which encodes particular behaviors. Some of these behaviors are unique and robust, e.g., locomotion or directional flight. We are studying the design of neural circuits that facilitate sensory responses by modeling their networks and investigating the building blocks, robustness, optimality and controllability of these systems….
Wearable and Implantable Biomedical Devices
We have developed several new approaches for efficiently powering battery-free wearable and implantable devices, including the use of metamaterial lenses for near-field focusing. Additionally, we have applied backscatter communication to wearable and implantable devices to achieve extraordinary data throughput compared to conventional Medical Implant Communication Service (MICS) radios. We have developed example biomedical devices such…
Energy Efficient Modulated Backscatter Communication
We have developed several new approaches to modulated backscatter communication, including the first demonstration of quadrature amplitude modulated (QAM) backscatter at 96 megabits as well as the first demonstration of “Bluetooth Backscatter” devices that are compatible with absolutely unmodified Bluetooth devices. No hardware, firmware or software modifications are needed to receive these signals, yet their…
MIMO Wireless Power Transfer for Mobile Devices
We have developed novel strategies for exploiting multiple-input and multiple-output (MIMO) channels for wireless power transfer (WPT). Through the use of backscatter channel measurement, the channel state information for each mobile device can be rapidly acquired at minimal energy cost. We have demonstrated selective WPT enhancement of ~10X and selective WPT denial of greater than…
Millimeter-Wave Compressive Imaging with Metamaterial Antennas
We have developed novel compressive imaging approaches in the millimeter wave bands (18-26 GHz, 85-110 GHz) using metamaterial antennas. The metamaterial antennas are designed to exploit extreme frequency diversity in their radiated modes to enable rapid single-shot image reconstruction from sparse measurements. Applications include spaceborne imaging radars as well as indoor personal security.
Previous page Next page