Photo
Matthew J. Burlick
Philadelphia, PA 19147
Email: mjburlick@yahoo.com

I am currently an Assistant Teaching Professor in the Computer Science Department at Drexel University in Philadelphia.PA.

In addition to teaching a variety of undergraduate and graduate courses, my research interests include topics in image processing, machine learning, real-time video tracking, object detection and classification, statistics/probability, and acoustics.

Working with such a wide range of datasets, my work can be generalized as real-time multi-sensor fusion for detection and classification. This work results in extensive experience choosing feature vectors, building classifiers and creating unique clustering algorithms, often relying on temporally relative data.

Below is an outline of various projects I have worked on.

Education | Research | Publications | Certifications | Awards | Relavent Skillset
Relavent Coursework | Teaching | Employment | Web Developments | Music


Education

Stevens Institute of Technology, Hoboken, NJ
9/06-Fall 2013
  • PhD in Computer Science
  • Concentration: Computer Graphics/Computer Vision/Machine Learning
  • Research: Visualization Department Graduate Research Assistant
Stevens Institute of Technology, Hoboken, NJ
9/06-05/08
  • Masters Degree in Computer Science
  • GPA: 4.0
University of Delaware, Newark, DE (Honors Program)
9/98-5/02
  • Bachelor of Electrical Engineering with concentration in Computer Engineering
  • Minor: Computer Science
  • GPA: 3.49

Research

Semantics-Based Video Indexing using Tracked Objects
Using object trackers, we discover video semantics for tasks including video segmentation, story discovery, video matching and searching. Some parts of this work are included in my current Thesis work.
Multi-Modal Fusion for Voice Activity Detection
Using classification from both acoustic and visual modalities, we provide a novel late-fusion classifier that aides in instantaneous voice activity detection (VAD) in the presence of low acoustic SNR.
SCAR Tracking
By tracking on small, salient face patches, we provide a face tracker that is more robust to noise such as illumination and occlusion. Furthermore our algorithms provide mechanisms to detection failure, resulting in object re-acquisition, dynamic model update, or true loss-of-target.
Shotgun Learning
A novel semi-supervised learning method using temporally consistent data to label streams instead of individual images to build a training set
X-Reality
Real-time visualization of tracking objects in a virual environment. This allows the user to interact with the environment in a previously impossible manner. Doing so we can build behavorial modals for environments
Homography Parameter Estimation
From a set of pre-computed planar homographies we estimate a new homography for any new camera position/orientation
Beamforming
Using hydrophone data and statistical correction methods, we determine the direction of arrival of ship traffic and establish a guarenteed capture probability.

Publications

  • George Kamberov, Matt Burlick, Lazaros Karydas, Olga Koteoglou, "Unsupervised Detection of Video Sub-scenes", International Conference on Patter Recognition (ICPR), 2014

  • Matt Burlick, "A Bottom-Up Extraction of Atomic Feature Vectors and Action Sequences for Video Representation", Ph.D. Dissertation, 2013.

  • M. Burlick, O. Koteoglou, L. Karydas, and G. Kamberov "Leveraging Crowsourced Data for Creating Temporal Segmentation Ground Truths of Subjective Tasks", CVPR Workship on Ground Truth, 2013 [pdf]

  • Matt Burlick, Dimitrios Dimitriadis, Eric Zavesky, "On the Improvement of Multimodal Voice Activity Detection", Interspeech, 2013.

  • G. Kamberov, M. Burlick, L. Karydas and O. Koteoglou, "SCAR: Dynamic adaptation for person detection and persistence analysis in unconstrained videos", International Symposium on Visual Computing (ISVC), 2012 [pdf]

  • George Kamberov, Gerda Kamberova, Matt Burlick, Lazaros Karydas, Bart Luczynski, "Track Analysis, Data Cleansing, and Labeling", International Symposium on Visual Computing (ISVC), 2011. [pdf]

  • Barry Bunin, Alexander Sutin, George Kamberov, Heui-Seol Roh, Bart Luczynski, and Matt Burlick, "Fusion of acoustic measurements with video surveillance for estuarine threat detection", Proc. SPIE, Vol 6945, 694514 (2008) [pdf]

  • George Kamberov, Matt Burlick, Bart Luczynski, and Rob Bader, "Automatic Real-Time Analysis and Anomaly Detection of Estuary Traffic Via Video-Acoustic Sensor Fusion", MSL Annual Report, Chapter 7 (2008)

  • Matt Burlick, Gerda Kamberova, George Kamberov, "Mini-max rules and estimation for scene and context description", in preparation for submission.

  • Maxim Serebrennik, Matt Burlick, Bart Luczynski, Lazaros Karydas, George Kamberov, "X-reality: fusing long range real-time sensors ", in preparation for submission.

Certifications

  • Standard Certificate to teach High School Mathematics in the state of New Jersey

Awards

  • Recipient of Robert Crooks Stanley Fellowship 2011-2012, 2012-2013
  • Recipient of full scholarship assistantship to Steven's Technical Institute for Masters/PhD
  • Recipient of ETS' "Recognition of Excellence" award for scoring in top 15% of all previous takers of the Mathematics Praxis II Teachers Exam
  • Nominated a member of "Who's Who of America's Teachers"
  • Undergraduate Dean's List (Fall 1999, Spring 2000, Fall 2000, Spring 2001, Fall 2001, Spring 2002)

Relavent Skillset

  • Programming Languages: C, C++, CUDA, Java, PHP, Python, Matlab, Javascript
  • Databaset-driven Web Programming
  • Statistical analysis and modeling
  • Computer Vision - Tracking, Clustering, Feature Representations, Classification
  • Compute Visualization: OSG, Delta3d, Half-Life 2 Mods
  • Technical Writing

Relavent Coursework

  • Applied Machine Learning
  • Image Processing & Computer Vision
  • Real-Time Rendering
  • Probability & Statistics
  • Computer Vision
  • Computer Graphics
  • Web Programming
  • Algorithms
  • Random Signals & Noise
  • Computer Systems Design
  • Solid State Electronics
  • Circuit Analysis
  • Microprocessor Based Systems
  • Differential Equations & Linear Algebra
  • Data Structures
  • Java Programming
  • C++ Programming
  • C Programming
  • Analytic Geometry & Calculus

Teaching

Drexel University
  • Comptuer Graphics
  • Machine Learning
Stevens Institute of Technology
  • Introduction to Scientific Computing
  • Discrete Structures
  • Algorithms
  • Interactive Computer Graphics
  • Senior Design
  • Intro to Computer Science (TA)
  • Computer Science in Java Honors (TA)
  • Discrete Math (TA)
  • Operating Systems (TA)
Bergen Community College
  • Introduction to Computer Science in C++
Holy Family Academy
  • Pre-Calculus Honors
  • Geometry Honors
  • Algebra 2 w/ Trig
  • Statistics and Probability
  • Intro to Computer Science in Java

Employment

Assistant Teaching Professor, Drexel University
09/15-Present
  • Teach a variety of courses within the Computer Science department.
  • Curriculum Development
Assistant Teaching Professor, Stevens Insitute of Technology
08/13-05/15
  • Teach a variety of courses within the Computer Science department.
  • Undergraduate Advisement
  • Curriculum Development
Research Assistant, Stevens Institute of Technology
06/06-08/13
  • Research multi-sensor fusion for understanding dynamic schemes (combining low-quality video and audio) using methods from signal processing, computer vision and machine learning.
  • Engineering camp (ECOES) instructor on topics of Machine Learning and Pattern Recognition
Programmer, Self
06/05-Present
  • Write PHP and ASP web applications for various clients.
Technical Research Intern, AT&T Research Labs
Summer 2012
  • Developed state-of-the-art algorithms for multi-modal voice activity detection
Adjunct Faculty, Bergen Community College
08/09-05/10
  • Taught Introduction to Computer Science
Teacher, Holy Family Academy, Bayonne, NJ
09/03-06/06
  • Taught high school mathematics and computer programming
  • Instructor and supervisor of "Fontbonne Scholar" program for gifted students
IT Specialist, Nu-Way Concessionaires, Kearny, NJ
08/02-Present
  • In collaboration with Pepperlillie, developed website.
  • Created database system with online component.
  • Perform general network maintenance and system updates and enhancements
Programmer, Aberdeen Proving Grounds, Aberdeen, MD
Summer 2001
  • Programmer in the ballistics department.
  • Developed equations for, and aided in, underwater explosion testing and analysis.
  • Wrote specialized software for video capture cards using Visual C++

Websites

My Musical Contributions

© Matt Burlick, 2012