A Probabilistic Logic Programming Event Calculus

TL;DR

This paper introduces a probabilistic logic programming system that recognizes long-term human activities from short-term activities detected in video, effectively handling uncertainty in surveillance video analysis.

Contribution

It extends the Event Calculus with probabilistic reasoning to improve activity recognition accuracy in uncertain video data.

Findings

Probabilistic approach outperforms crisp logic in recognition accuracy.

System effectively models uncertainty in human activity recognition.

Detailed evaluation on benchmark dataset demonstrates robustness.

Abstract

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.