Current Research

My Master's thesis is entitled “Detection Likelihood Maps for Wilderness Search and Rescue: Assisting Search by Utilizing Ground Searcher GPS Track Logs.”

The goal of this research is to provide ground searchers and search managers with a visual representation of the quality of search coverage.

Completed tasks:

Implemented CPU and CUDA viewshed library

Created simulation environment in the C4 game engine

Implemented the ability to collect Distance to Visual Obstruction (DTVO) and Average Maximum Detection Range (AMDR) values

Current tasks include:

Create touch screen application that displays the contour map, detection likelihood maps, and lets the user place markers on identified objects (this is because the Google Earth plugin keeps crashing)

Fully populate the simulation environment with desired vegetation

Collect detection data used to build the detection likelihood Bayesian model

Create a Bayesian model for learning the detection likelihoods

Design a secondary auditory task for the user study

Validate accuracy of detection likelihood model in field experiments

Future Research

Switching to Dr. Seamon's Internet Security lab upon completion of Masters.


Cutting-edge technology

Computer and internet security

Parallel processing, especially using CUDA

Brain-computer interfaces

The great outdoors: backpacking, fishing, etc.


L. Lin, M. Roscheck, M. A. Goodrich, and B. S. Morse. Supporting Wilderness Search and Rescue with Integrated Intelligence: Autonomy and Information at the Right Time and the Right Place. In Twenty-Fourth AAAI Conference on Artificial Intelligence, Special Track on Integrated Intelligence. July, 2010, Atlanta, Georgia, USA.

hcmi/mike-roscheck.txt · Last modified: 2014/08/13 16:24 by tlund1
Back to top
CC Attribution-Share Alike 4.0 International = chi`s home Valid CSS Driven by DokuWiki do yourself a favour and use a real browser - get firefox!! Recent changes RSS feed Valid XHTML 1.0