Toward Occlusion Handling in Visual Tracking via Probabilistic Finite State Machines

Chenghuan Liu, Du Q. Huynh, Mark Reynolds

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)

Abstract

Visual tracking has been an active research area in computer vision for decades. However, the performance of existing techniques is still challenged by various factors, such as occlusion and change in appearance of the target. In this paper, we propose a novel framework based on correlation filtering and probabilistic finite state machines (FSMs) to handle occlusion. In our tracking framework, the target is partitioned into several parts whose occlusion states are automatically detected. A set of states for the target is defined in terms of the combination of the parts' occlusion states. The probabilistic FSMs are then used to model the target's state transitions so as to reduce the effect of noise in the output response maps of correlation filters. Our target model's update strategy is adaptable online depending on the estimated state of the target. Extensive experiments have been performed on several public benchmarks and the proposed algorithm achieves competitive results against state-of-the-art techniques.

Original languageEnglish
Article number8584488
Pages (from-to)1726-1738
Number of pages13
JournalIEEE Transactions on Cybernetics
Volume50
Issue number4
Early online date20 Dec 2018
DOIs
Publication statusPublished - Apr 2020

Fingerprint

Dive into the research topics of 'Toward Occlusion Handling in Visual Tracking via Probabilistic Finite State Machines'. Together they form a unique fingerprint.

Cite this