Next Article in Journal
Machine-Learning-Based Fatigue Trend Analysis on IMU Wearable Sensor Data from Construction Site Workers
Previous Article in Journal
A Control Method for Optimizing the Spectral Ratio Characteristics of LED Lighting to Provide Color Rendering Performance Comparable to Natural Light
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

SAMViTrack: A Search-Region Adaptive Mamba-ViT Tracker for Real-Time UAV Tracking

1
College of Computer Science and Engineering, Guilin University of Technology, Guilin 541006, China
2
Guangxi Guangxi Key Laboratory of Embedded Technology and Intelligent System, Guilin University of Technology, Guilin 541004, China
3
School of Computer Science, Fudan University, Shanghai 200082, China
4
School of Artificial Intelligence, Sun Yat-sen University, Zhuhai 519000, China
5
School of Electronic Information, Central South University, Changsha 410083, China
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Sensors 2025, 25(24), 7454; https://doi.org/10.3390/s25247454 (registering DOI)
Submission received: 29 October 2025 / Revised: 2 December 2025 / Accepted: 5 December 2025 / Published: 7 December 2025
(This article belongs to the Section Navigation and Positioning)

Abstract

Achieving fast and robust object tracking is critical for real-time Unmanned Aerial Vehicle (UAV) applications, where targets often move unpredictably and environmental conditions can rapidly change. In this paper, we propose the Search-Region Adaptive Mamba-ViT Tracker (SAMViTrack), a novel framework that combines the efficiency of Mamba attention with the powerful feature extraction capabilities of Vision Transformer (ViT). Our tracker dynamically adjusts the search region based on the target’s motion and environmental context, ensuring precise tracking even under challenging conditions such as occlusions, fast motion, and scale variations. By integrating an adaptive search mechanism, our SAMViTrack significantly reduces computational overhead without compromising accuracy, making it suitable for real-time deployment on UAVs with limited onboard resources. Extensive experiments on benchmark datasets demonstrate that our method outperforms both traditional and modern trackers, achieving superior accuracy and robustness with improved efficiency. The proposed tracker sets a new baseline, especially by combining Mamba and ViT, for UAV tracking by offering a balance between speed, accuracy, and adaptability in dynamic environments.
Keywords: Mamba attention; Vision Transformer; object tracking; UAV applications; adaptive search region Mamba attention; Vision Transformer; object tracking; UAV applications; adaptive search region

Share and Cite

MDPI and ACS Style

Guo, X.; Li, Y.; Zhang, H.; Wang, X.; Zeng, D.; He, F.; Li, S. SAMViTrack: A Search-Region Adaptive Mamba-ViT Tracker for Real-Time UAV Tracking. Sensors 2025, 25, 7454. https://doi.org/10.3390/s25247454

AMA Style

Guo X, Li Y, Zhang H, Wang X, Zeng D, He F, Li S. SAMViTrack: A Search-Region Adaptive Mamba-ViT Tracker for Real-Time UAV Tracking. Sensors. 2025; 25(24):7454. https://doi.org/10.3390/s25247454

Chicago/Turabian Style

Guo, Xiaoyu, Yian Li, Hao Zhang, Xucheng Wang, Dan Zeng, Feixiang He, and Shuiwang Li. 2025. "SAMViTrack: A Search-Region Adaptive Mamba-ViT Tracker for Real-Time UAV Tracking" Sensors 25, no. 24: 7454. https://doi.org/10.3390/s25247454

APA Style

Guo, X., Li, Y., Zhang, H., Wang, X., Zeng, D., He, F., & Li, S. (2025). SAMViTrack: A Search-Region Adaptive Mamba-ViT Tracker for Real-Time UAV Tracking. Sensors, 25(24), 7454. https://doi.org/10.3390/s25247454

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop