A Probabilistic Logic Programming Event Calculus

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.

Accepted for publication in the Theory and Practice of Logic Programming (TPLP) journal

References in corpus (6)

• Grounding the Lexical Semantics of Verbs in Visual Perception using Force Dynamics and Event Logic
• On the Implementation of the Probabilistic Logic Programming Language ProbLog
• Inference in Probabilistic Logic Programs using Weighted CNF's
• A Probabilistic Logic Programming Event Calculus
• ECA-RuleML: An Approach combining ECA Rules with temporal interval-based KR Event/Action Logics and Transactional Update Logics
• Location-Based Reasoning about Complex Multi-Agent Behavior

Cited by in corpus (7)

• A Probabilistic Logic Programming Event Calculus
• An Event Calculus Production Rule System for Reasoning in Dynamic and Uncertain Domains
• Semirings for Probabilistic and Neuro-Symbolic Logic Programming
• Bottom-Up Stratified Probabilistic Logic Programming with Fusemate
• Event Correlation and Forecasting over Multivariate Streaming Sensor Data
• An Experimentation Platform for Explainable Coalition Situational Understanding
• A Hybrid Neuro-Symbolic Approach for Complex Event Processing