Learning a Context-Aware Environmental Residual Correlation Filter via Deep Convolution Features for Visual Object Tracking

Sachin Sakthi Kuppusami Sakthivel, Sathishkumar Moorthy, Sathiyamoorthi Arthanari, Jae Hoon Jeong and Young Hoon Joo ()
Additional contact information
Sachin Sakthi Kuppusami Sakthivel: School of IT Information and Control Engineering, Kunsan National University, 588 Daehak-ro, Gunsan-si 54150, Republic of Korea
Sathishkumar Moorthy: School of IT Information and Control Engineering, Kunsan National University, 588 Daehak-ro, Gunsan-si 54150, Republic of Korea
Sathiyamoorthi Arthanari: School of IT Information and Control Engineering, Kunsan National University, 588 Daehak-ro, Gunsan-si 54150, Republic of Korea
Jae Hoon Jeong: School of IT Information and Control Engineering, Kunsan National University, 588 Daehak-ro, Gunsan-si 54150, Republic of Korea
Young Hoon Joo: School of IT Information and Control Engineering, Kunsan National University, 588 Daehak-ro, Gunsan-si 54150, Republic of Korea

Mathematics, 2024, vol. 12, issue 14, 1-18

Abstract: Visual tracking has become widespread in swarm robots for intelligent video surveillance, navigation, and autonomous vehicles due to the development of machine learning algorithms. Discriminative correlation filter (DCF)-based trackers have gained increasing attention owing to their efficiency. This study proposes “context-aware environmental residual correlation filter tracking via deep convolution features (CAERDCF)” to enhance the performance of the tracker under ambiguous environmental changes. The objective is to address the challenges posed by intensive environment variations that confound DCF-based trackers, resulting in undesirable tracking drift. We present a selective spatial regularizer in the DCF to suppress boundary effects and use the target’s context information to improve tracking performance. Specifically, a regularization term comprehends the environmental residual among video sequences, enhancing the filter’s discrimination and robustness in unpredictable tracking conditions. Additionally, we propose an efficient method for acquiring environmental data using the current observation without additional computation. A multi-feature integration method is also introduced to enhance the target’s presence by combining multiple metrics. We demonstrate the efficiency and feasibility of our proposed CAERDCF approach by comparing it with existing methods using the OTB2015, TempleColor128, UAV123, LASOT, and GOT10K benchmark datasets. Specifically, our method increased the precision score by 12.9% in OTB2015 and 16.1% in TempleColor128 compared to BACF.

Keywords: selective spatial regularizer; context-aware; object tracking; correlation filters; multi-feature fusion (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/14/2279/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/14/2279/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:14:p:2279-:d:1439685

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().