Dr. Vinayak Elangovan
Adjunct Professor, TCNJ

September 15, 2015
12:30 – 1:30 pm
Forcina 408

*Pizza will be provided.

“Human-Vehicle Interactions (HVI) Recognition Using Spatiotemporal Analysis”

Abstract: Improved Situational awareness in Persistent Surveillance Systems (PSS) is an ongoing research effort of the Department of Defense and Department of Homeland Security. Most PSS generate huge volume of raw data (imagery data) and they heavily rely on human operators to interpret and inference data in order to detect abnormal activities. Many outdoor apprehensive activities involve vehicles as their primary source of transportation to and from the scene where a plot is executed. Vehicles can be used as a disguise, hide-out, and a meeting place to carry abnormal activities. Analysis of the Human-Vehicle Interactions (HVI) helps us to identify cohesive patterns of such activities representing potential threats. In this lecture, the approach used in detection and recognition of HVI activities are discussed. A taxonomy of HVI is developed for this approach, as a means for recognizing different types of HVI activities. HVI taxonomy may comprise multiple threads of ontological patterns. By spatiotemporal linking of ontological patterns, a HVI pattern is hypothesized to pursue a potential threat situation. At start of this lecture, an introduction to computer vision and machine learning is briefed for better understanding of the approach. The practical applications of this approach in various other domains are also discussed in this lecture.

Speaker Bio: Improved Situational awareness in Persistent Surveillance Systems (PSS) is an ongoing research effort of the Department of Defense and Department of Homeland Security. Most PSS generate huge volume of raw data (imagery data) and they heavily rely on human operators to interpret and inference data in order to detect abnormal activities. Many outdoor apprehensive activities involve vehicles as their primary source of transportation to and from the scene where a plot is executed. Vehicles can be used as a disguise, hide-out, and a meeting place to carry abnormal activities. Analysis of the Human-Vehicle Interactions (HVI) helps us to identify cohesive patterns of such activities representing potential threats. In this lecture, the approach used in detection and recognition of HVI activities are discussed. A taxonomy of HVI is developed for this approach, as a means for recognizing different types of HVI activities. HVI taxonomy may comprise multiple threads of ontological patterns. By spatiotemporal linking of ontological patterns, a HVI pattern is hypothesized to pursue a potential threat situation. At start of this lecture, an introduction to computer vision and machine learning is briefed for better understanding of the approach. The practical applications of this approach in various other domains are also discussed in this lecture.