2015/01/31 by Mohammad Javad Shafiee, Mohammad Shafiee, Zohreh Azimifar +1
Computer Science · Mathematics · #Active appearance model #Advanced Image and Video Retrieval Techniques #Anomaly Detection Techniques and Applications #Artificial intelligence #Computer science #Computer vision #Conditional random field #Context (archaeology) #Geography #Image (mathematics) #Image segmentation #Markov random field #Object (grammar) #Pattern recognition (psychology) #Probabilistic logic #Silhouette #Tracking (education) #Video Surveillance and Tracking Methods #Video tracking #cs.CV #cs.LG #stat.ML
paper · pdf · doi:10.1371/journal.pone.0133036
17 pages
arxiv created 2015/08/04 · openalex publication_date 2015/08/27 · arxiv updated 2016/02/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.