Matching Items (3)

151383-Thumbnail Image.png

Upper body motion analysis using kinect for stroke rehabilitation at the home

Description

Motion capture using cost-effective sensing technology is challenging and the huge success of Microsoft Kinect has been attracting researchers to uncover the potential of using this technology into computer vision applications. In this thesis, an upper-body motion analysis in a

Motion capture using cost-effective sensing technology is challenging and the huge success of Microsoft Kinect has been attracting researchers to uncover the potential of using this technology into computer vision applications. In this thesis, an upper-body motion analysis in a home-based system for stroke rehabilitation using novel RGB-D camera - Kinect is presented. We address this problem by first conducting a systematic analysis of the usability of Kinect for motion analysis in stroke rehabilitation. Then a hybrid upper body tracking approach is proposed which combines off-the-shelf skeleton tracking with a novel depth-fused mean shift tracking method. We proposed several kinematic features reliably extracted from the proposed inexpensive and portable motion capture system and classifiers that correlate torso movement to clinical measures of unimpaired and impaired. Experiment results show that the proposed sensing and analysis works reliably on measuring torso movement quality and is promising for end-point tracking. The system is currently being deployed for large-scale evaluations.

Contributors

Agent

Created

Date Created
2012

155774-Thumbnail Image.png

Computer Vision from Spatial-Multiplexing Cameras at Low Measurement Rates

Description

In UAVs and parking lots, it is typical to first collect an enormous number of pixels using conventional imagers. This is followed by employment of expensive methods to compress by throwing away redundant data. Subsequently, the compressed data is transmitted

In UAVs and parking lots, it is typical to first collect an enormous number of pixels using conventional imagers. This is followed by employment of expensive methods to compress by throwing away redundant data. Subsequently, the compressed data is transmitted to a ground station. The past decade has seen the emergence of novel imagers called spatial-multiplexing cameras, which offer compression at the sensing level itself by providing an arbitrary linear measurements of the scene instead of pixel-based sampling. In this dissertation, I discuss various approaches for effective information extraction from spatial-multiplexing measurements and present the trade-offs between reliability of the performance and computational/storage load of the system. In the first part, I present a reconstruction-free approach to high-level inference in computer vision, wherein I consider the specific case of activity analysis, and show that using correlation filters, one can perform effective action recognition and localization directly from a class of spatial-multiplexing cameras, called compressive cameras, even at very low measurement rates of 1\%. In the second part, I outline a deep learning based non-iterative and real-time algorithm to reconstruct images from compressively sensed (CS) measurements, which can outperform the traditional iterative CS reconstruction algorithms in terms of reconstruction quality and time complexity, especially at low measurement rates. To overcome the limitations of compressive cameras, which are operated with random measurements and not particularly tuned to any task, in the third part of the dissertation, I propose a method to design spatial-multiplexing measurements, which are tuned to facilitate the easy extraction of features that are useful in computer vision tasks like object tracking. The work presented in the dissertation provides sufficient evidence to high-level inference in computer vision at extremely low measurement rates, and hence allows us to think about the possibility of revamping the current day computer systems.

Contributors

Agent

Created

Date Created
2017

161274-Thumbnail Image.png

Energy Use Scaling and Alarm Spread in Social Ants: An Investigation Using Multi-agent Simulation and Object Tracking

Description

Social insect groups, such as bees, termites, and ants, epitomize the emergence of group-level behaviors from the aggregated actions and interactions of individuals. Ants have the unique advantage that whole colonies can be observed in artificial, laboratory nests, and each

Social insect groups, such as bees, termites, and ants, epitomize the emergence of group-level behaviors from the aggregated actions and interactions of individuals. Ants have the unique advantage that whole colonies can be observed in artificial, laboratory nests, and each individual's behavior can be continuously tracked using imaging software. In this dissertation, I study two group behaviors: (1) the spread of alarm signals from three agitated ants to a group of 61 quiescent nestmates, and (2) the reduction in per-capita energy use as colonies scale in size from tens of ants to thousands. For my first experiment, I track the motion of Pogonomyrmex californicus ants using an overhead camera, and I analyze how propagation of an initial alarm stimulus affects their walking speeds. I then build an agent-based model that simulates two-dimensional ant motion and the spread of the alarmed state. I find that implementing a simple set of rules for motion and alarm signal transmission reproduces the empirically observed speed dynamics. For the second experiment, I simulate social insect colony workers that collectively complete a set of tasks. By assuming that task switching is energetically costly, my model recovers a metabolic rate scaling pattern, known as hypometric metabolic scaling. This relationship, which predicts an organism's metabolic rate from its mass, is observed across a diverse set of social insect groups and animal species. The results suggest an explicit link between the degree of workers' task specialization and whole-colony energy use.

Contributors

Agent

Created

Date Created
2021