Jan Prokaj

Learn More
Recent work on multi-object tracking has shown the promise of tracklet-based methods. In this work we present a method which infers tracklets then groups them into tracks. It overcomes some of the disadvantages of existing methods, such as the use of heuristics or non-realistic constraints. The main idea is to formulate the data association problem as(More)
Wide area aerial surveillance data has recently proliferated and increased the demand for multi-object tracking algorithms. However, the limited appearance information on every target creates much ambiguity in tracking and increases the difficulty of removing false target detections. In this work we propose to learn motion patterns in wide area scenes and(More)
• Wide Area Aerial Surveillance (WAAS) imagery is captured by an array of sensors sharing an optical center • It is desirable to generate a single image (mosaic) from the array • Classic image deformation models (lens distortion) do not produce a seamless mosaic Problem • A homography model, H, registers two images captured by a rotating pinhole camera (p(More)
We present the design and implementation of an activity recognition system in wide area aerial video surveillance using Entity Relationship Models (ERM). In this approach, finding an activity is equivalent to sending a query to a Relational DataBase Management System (RDBMS). By incorporating reference imagery and Geographic Information System (GIS) data,(More)
Wide Area Aerial Surveillance (WAAS) produces very large images at 1-2 fps or more. This data needs to be processed in real time to produce semantically meaningful information , then queried efficiently. We have designed and implemented a full system to detect and track vehicles, and infer activities. We address here the scalability issues, and propose(More)
  • 1