The JHU Department of Computer Science is a department within the Whiting School of Engineering. While studies and research cover a very wide area, there are five main research interests:
Algorithms – A core area and long-standing strength of the department, dating from before the department’s formation. Robotics, Vision, and Graphics – Much of the research in these areas, which involve 3-D computer modeling, is done within the Center for Computer-Integrated Surgical Systems and Technology (CISST). Related research includes human-computer interaction, and shape recognition and shape matching. Security – This is an incredibly broad area and research, focused within the JHU Information Security Institute, involves many aspects of computer and network security. Systems – This core research area grapples with improving operating systems and data storage and defining higher standards for security evaluation. Natural Language Processing – This concerns enabling computers to work more effectively with human languages, identifying input strings and corresponding output, defining correlations between text and speech, form and content, syntax and translations. The Center for Language and Speech Processing (CLSP) is centrally involved with this work.
Over the past few years, several papers have used Linear Dynamical Systems (LDS)s for modeling, registration,
segmentation, and recognition of visual dynamical processes, such as human gaits, dynamic textures and lip
articulations. The recognition framework involves identifying the parameters of the LDSs from features extracted
from a training set of videos, using metrics on the space of dynamical systems to compare them, and combining
these metrics with different classification methods. Usually, each paper makes an ad-hoc choice for every step,
and tests the recognition framework on small data sets often involving only one application. We present a detailed
evaluation of the LDS-based recognition pipeline; comparing identification methods, metrics, and classification
techniques. We propose new metrics that have certain invariance properties and explore a number of variations to the
existing metrics. We perform experimental evaluations on well-known data sets of human gaits, dynamic textures,
and lip articulations and provide benchmark recognition results. We also analyze the robustness of the recognition
pipeline with respect to changes in observation and experimental conditions. Overall, this work represents the most
extensive to-date evaluation of the LDS-based recognition framework.