Enhancing UAV tracking: a focus on discriminative representations using contrastive instances

Addressing the core challenges of achieving both high efficiency and precision in UAV tracking is crucial due to limitations in computing resources, battery capacity, and maximum load capacity on UAVs. Discriminative correlation filter (DCF)-based trackers excel in efficiency on a single CPU but lag...

Full description

Saved in:
Bibliographic Details
Published in:Journal of real-time image processing 2024-05, Vol.21 (3), p.78, Article 78
Main Authors: Wang, Xucheng, Zeng, Dan, Li, Yongxin, Zou, Mingliang, Zhao, Qijun, Li, Shuiwang
Format: Article
Language:English
Subjects:
Accuracy
Annotations
Benchmarks
Computer Graphics
Computer Science
Deep learning
Design
Efficiency
Image Processing and Computer Vision
Innovations
Lightweight
Multimedia Information Systems
Pattern Recognition
Public safety
Representations
Signal,Image and Speech Processing
Tracking
Weight reduction
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Addressing the core challenges of achieving both high efficiency and precision in UAV tracking is crucial due to limitations in computing resources, battery capacity, and maximum load capacity on UAVs. Discriminative correlation filter (DCF)-based trackers excel in efficiency on a single CPU but lag in precision. In contrast, many lightweight deep learning (DL)-based trackers based on model compression strike a better balance between efficiency and precision. However, higher compression rates can hinder performance by diminishing discriminative representations. Given these challenges, our paper aims to enhance feature representations’ discriminative abilities through an innovative feature-learning approach. We specifically emphasize leveraging contrasting instances to achieve more distinct representations for effective UAV tracking. Our method eliminates the need for manual annotations and facilitates the creation and deployment of lightweight models. As far as our knowledge goes, we are the pioneers in exploring the possibilities of contrastive learning in UAV tracking applications. Through extensive experimentation across four UAV benchmarks, namely, UAVDT, DTB70, UAV123@10fps and VisDrone2018, We have shown that our DRCI (discriminative representation with contrastive instances) tracker outperforms current state-of-the-art UAV tracking methods, underscoring its potential to effectively tackle the persistent challenges in this field.
ISSN:1861-8200
1861-8219
DOI:10.1007/s11554-024-01456-2