A Deep-structured Conditional Random Field Model for Object Silhouette Tracking

TL;DR

This paper presents a deep-structured conditional random field model that effectively tracks object silhouettes over time by integrating spatial and temporal context, handling occlusion and multiple targets in video sequences.

Contribution

The introduction of a novel deep-structured CRF model that dynamically incorporates spatial and temporal information for improved silhouette tracking.

Findings

Outperforms baseline methods like mean-shift tracking.

Achieves superior results compared to state-of-the-art methods such as context tracking.

Handles occlusion and multiple targets effectively.

Abstract

In this work, we introduce a deep-structured conditional random field (DS-CRF) model for the purpose of state-based object silhouette tracking. The proposed DS-CRF model consists of a series of state layers, where each state layer spatially characterizes the object silhouette at a particular point in time. The interactions between adjacent state layers are established by inter-layer connectivity dynamically determined based on inter-frame optical flow. By incorporate both spatial and temporal context in a dynamic fashion within such a deep-structured probabilistic graphical model, the proposed DS-CRF model allows us to develop a framework that can accurately and efficiently track object silhouettes that can change greatly over time, as well as under different situations such as occlusion and multiple targets within the scene. Experiment results using video surveillance datasets containing different scenarios such as occlusion and multiple targets showed that the proposed DS-CRF approach provides strong object silhouette tracking performance when compared to baseline methods such as mean-shift tracking, as well as state-of-the-art methods such as context tracking and boosted particle filtering.