Jeffrey Turner, Computer Science
NIST Summer Researcher
The VidAT tool was developed in conjunction with the ClearDTScorer to place bounding boxes around objects of interest. The ClearDTScorer identifies coordinates and dimensions of the boxes; as well as color coding them depending on how the system identifies them. This is a somewhat time-expensive procedure and cannot realistically be done to every frame of a video. The VidAT tool can draw bounding boxes onto the video wherever identified by the tracking log provided by the ClearDTScorer, and when one in every fifteen frames is evaluated there was a significant improvement in processing time of the video. The tradeoff of this sparse frame evaluation was poor video quality in the transitions of the bounding boxes, which appeared to “jump” every half-second. The enhancement to the VidAT tool interpolates the data in between video frames, and produces a modified tracking log that can be drawn by the filter without the costly process of evaluating every individual frame of the video. VidAT is being developed as a video filter for the open source FFMPEG project, and is being designed to conform to the specifications so that it can be used in conjunction with other video filters.
How did you find out that you could do research in your field in the summer?
I’m a rising senor computer science major/mathematics minor and I learned of the opportunity from being on a mailing list from the Shriver Center.
How did you know that research at NIST was what you wanted to do?
I have always wanted to study something that had not been studied yet, and I knew that the National Institute of Standards and Technology (NIST) was a prestigious institute, and that research and NIST would shine outstanding on my resume for grad schools or workplace.
Did you apply to other places?
Yes. I applied to about five different places for a summer internship and got acceptances from two.
Was the application difficult to do? Did you have help with this?
The application was not difficult to do, but it did take some amount of time. After I was done writing my personal statement and other essay-type questions I got my friends to proofread them for errors.
What was your summer research project?
I am working on a software that can enhance a working video filter to identify and track human facial movement in a video. Because of the complexity of the process, a human face cannot feasibly be identified every frame, so this summer I am working on a mathematical tool that can track what the person could be doing in the “in between” frames.
Who was your mentor for this project?
Dr. Jonathan Fiscus in the Information Technology Laboratory (ITL) at NIST.
How much time do you put into this work?
I worked seven to nine hours a day, five days a week for 11 weeks over the summer.
Were you paid? Where did you live?
Yes I was paid through NIST, and I chose to live at Walker Avenue apartments on campus. It is slightly less than an hour drive a day to NIST.
What academic background did you have before you started?
I was one course shy of completing a minor in mathematics, and a small handful away from completing my bachelor of science in Computer Science.
How did you learn what you needed to know for this project?
Different programming textbooks around the office were invaluable to my work, I commonly referenced the internet, and did readings assigned by my advisor to help.
What was the hardest part about your research?
Sometimes the computer has memory problems because of imperfect usage of dynamic memory allocation in the C programming language. These errors often do not show right away, but instead cause inconsistent program usage over time, so today’s errors may have been caused by last week’s mistakes.
What was the most unexpected thing?
How well I have adapted to using a Mac OSX system (I am a power Linux user, and thought I disliked Mac products.)
How does this research relate to your course work at UMBC?
Dynamic memory allocation is one of the cruxes of this project, and the computer organization practiced here at NIST is crucial to many core classes of the UMBC computer science program.
What is your advice to other students about getting involved in research?
Do it, and have an open mind if you don’t think you like the project at first. I thought I didn’t like mine at first glance.
What are your career goals?
I wish to be a computer forensics worker for the United States government.
Are you a transfer student or did you start at UMBC as a freshman?
I transferred to UMBC my sophomore year from James Madison University in Virginia.
Do you now live on campus or commute to UMBC?
I have lived in Walker Avenue apartments on campus for the past two years, going on my third year.