Proc. SPIE. 8392, Signal Processing, Sensor Fusion, and Target Recognition XXI
KEYWORDS: Maritime surveillance, Detection and tracking algorithms, Visualization, Sensors, Monte Carlo methods, Distance measurement, Optical tracking, Electronic filtering, Data integration, Process modeling
In this article, we present an evaluation of several multi-target tracking methods based on simulated scenarios in the
maritime domain. In particular, we consider variations of the Joint Integrated Probabilistic Data Association (JIPDA)
algorithm, namely the Linear Multi-Target IPDA (LMIPDA), Linear Joint IPDA (LJIPDA), and Markov Chain Monte
Carlo Data Association (MCMCDA). The algorithms are compared with respect to an extension of the Optimal
Subpattern Assignment (OSPA) metric, the Hellinger distance and further performance measures. As no single algorithm
is equally well fitted to all tested scenarios, our results show which algorithms fits best for specific scenarios.
From the advances in computer vision methods for the detection, tracking and recognition of objects in video streams,
new opportunities for video surveillance arise: In the future, automated video surveillance systems will be able to detect
critical situations early enough to enable an operator to take preventive actions, instead of using video material merely
for forensic investigations. However, problems such as limited computational resources, privacy regulations and a
constant change in potential threads have to be addressed by a practical automated video surveillance system. In this
paper, we show how these problems can be addressed using a task-oriented approach. The system architecture of the
task-oriented video surveillance system NEST and an algorithm for the detection of abnormal behavior as part of the
system are presented and illustrated for the surveillance of guests inside a video-monitored building.