Detecting and tracking moving targets through foliage is difficult, for many cases even impossible in regular aerial images videos. We present an initial light-weight drone-operated 1D camera array that supports parallel synthetic aperture imaging. Our main finding color anomaly detection benefits significantly from image integration when compared to conventional raw or video frames (on average...

This diploma thesis investigates the implementation of a low cost marker based infrared optical tracking system using commodity hardware. The focus is on software/algorithms. An introduction to marker based optical tracking is given, the theoretical foundations of the single componetns of such a system are covered and a software framework and single components are implemented and evaluated. Cri...

In this paper, we present an observation model to track objects using particle filter algorithms based on matching techniques for computing optical flow. Although optical flow information enables us to know the displacement of objects present in a scene, it cannot be used directly to displace an object model since flow calculation techniques lack the necessary precision. In view of the fact tha...

We present a tracking system integrating both optical and magnetic tracking which runs on low-cost hardware. This tracking system is part of the “Studierstube”, a new multi-user augmented reality system. On the one hand, two independently running tracking systems are integrated to complement each other, on the other hand by using only parts of two independent tracking systems we can obtain a un...

The main objective of my dissertation is to provide a vision-based system to automatically understands traffic patterns and analyze intersections. The system leverages the existing traffic cameras to provide safety and behavior analysis of intersection participants including behavior and safety. The first step is to provide a robust detection and tracking system for vehicles and pedestrians of ...