Deep learning uses stacks of multiple processing layers to learn representations of data with different levels of abstraction. It enables machines to have the understand[...]

Abstract This article describes a technique to augment a typical RGBD sensor by integrating depth estimates obtained via Structure-from-Motion (SfM) with depth measuremen[...]

There has been an ever growing interest in leveraging state of the art deep learning techniques for tracking objects in video frames. Such works primarily focus on using [...]

This research introduces and evaluates an advanced AI-enabled Smart Video Surveillance (SVS) system designed to enhance safety across community spaces such as educational[...]

This research investigates the intersection of applied statistics, machine learning, and healthcare to leverage the quantitative approaches as a means of improving patien[...]

The limitations of transistor scaling and the rise of power-constrained compute environments have driven a new renaissance in hardware design through hardware acceleratio[...]

Indoor thermal environmental conditions play a significant role in protecting occupants’ well-being. In this regard, schedule-based and predefined environmental control i[...]

In this dissertation, I present my researches on the co-design of algorithms and architectures for deep spatial and temporal separable convolutional neural networks and t[...]

Software bugs result in a variety of issues including system crashes, loss of system performance, incorrect output and security vulnerabilities. In this thesis, we explor[...]

This thesis describes an algorithm for efficient segmentation of point cloud data into local planar surface regions. This is a problem of generic interest to researchers [...]