Subjective Logic Based Hybrid Approach to Conditional Evidence Fusion for Forensic Visual Surveillance

Abstract

In forensic analysis of visual surveillance data, condi-tional knowledge representation and inference under un-certainty play an important role for deriving new contex-tual cues by fusing relevant evidential patterns. To addressthis aspect, both rule-based (aka. extensional) and statebased (aka. intensional) approaches have been adoptedfor situation or visual event analysis. The former providesflexible expressive power and computational efficiency buttypically allows only one directional inference. The latteris computationally expensive but allows bidirectional inter-pretation of conditionals by treating antecedent and conse-quent of conditionals as mutually relevant states. In visualsurveillance, considering the varying semantics and poten-tially ambiguous causality in conditionals, it would be use-ful to combine the expressive power of rule-based systemwith the ability of bidirectional interpretation. In this paper,we propose a hybrid approach that, while relying mainly ona rule-based architecture, also provides an intensional wayof on-demand conditional modeling using conditional op-erators in subjective logic. We first show how conditionalscan be assessed via explicit representation of ignorance insubjective logic. We then describe the proposed hybrid con-ditional handling framework. Finally we present an exper-imental case study from a typical airport scene taken fromvisual surveillance data.