A Probabilistic Logic Programming Event Calculus

Anastasios Skarlatidis1,2, Alexander Artikis1, Jason Filippou1,3 and Georgios Paliouras1

1Institute of Informatics and Telecommunications, NCSR "Demokritos"
2Department of Digital Systems, University of Piraeus
3University of Maryland, USA

We present a system for recognising human activity given a symbolic representation of video content. The input of our system is a set of time-stamped short-term activities (STA) detected on video frames. The output is a set of recognised long-term activities (LTA), which are pre-defined temporal combinations of STA. The constraints on the STA that, if satisfied, lead to the recognition of a LTA, have been expressed using a dialect of the Event Calculus. In order to handle the uncertainty that naturally occurs in human activity recognition, we adapted this dialect to a state-of-the-art probabilistic logic programming framework. We present a detailed evaluation and comparison of the crisp and probabilistic approaches through experimentation on a benchmark dataset of human surveillance videos.


Publication (DOI).
Paper (draft).

The modified version of the CAVIAR dataset, including ProbLog-EC, the high-level event definitions and the event recognition results can be downloaded from here (Compressed archive ~0.5G; md5)