Forensic reasoning upon pre-obtained surveillance metadata using uncertain spatio-temporal rules and subjective logic

The majority of recent work in forensic analysis of visual surveillance content has been focusing on automatic information extraction aspects. However, little attention has been paid to the intelligent reuse of extracted (meta)data. For reasoning upon such pre-acquired metadata, in our previous paper [1], we proposed the use of logic programming to represent human knowledge and the use of subjective logic [2] to handle uncertainty implied in the extracted data and the logical rules. In this paper, we further explore the proposed approach for analyzing the relationship between two persons and, more specifically, for estimating whether one person could serve as a witness of another person in a public area scene. We first develop a rule based model for the likelihood of being a good witness that uses metadata extracted by a person tracker and evaluates the relationship between the tracked persons. To cope with the uncertainty in the relationship model, we develop a reputational subjective opinion function for the spatial-temporal relations. In addition, we accumulate the acquired opinions over time using subjective logic's fusion operator. To verify our approach, we finally present a preliminary experimental case study.