Addressing single object tracking in satellite imagery through prompt-engineered solutions

TL;DR

This paper introduces a training-free, point-based tracking method for small objects in satellite videos, utilizing prompt engineering with SAM and TAPIR to improve tracking accuracy amidst satellite imagery challenges.

Contribution

It presents a novel prompt engineering approach leveraging SAM and TAPIR for satellite object tracking without training, addressing unique satellite imagery challenges.

Findings

Validated on VISO dataset with improved accuracy

Demonstrated robustness against background variations and atmospheric disturbances

Achieved reliable tracking of small-scale objects in satellite videos

Abstract

Object tracking in satellite videos remains a complex endeavor in remote sensing due to the intricate and dynamic nature of satellite imagery. Existing state-of-the-art trackers in computer vision integrate sophisticated architectures, attention mechanisms, and multi-modal fusion to enhance tracking accuracy across diverse environments. However, the challenges posed by satellite imagery, such as background variations, atmospheric disturbances, and low-resolution object delineation, significantly impede the precision and reliability of traditional Single Object Tracking (SOT) techniques. Our study delves into these challenges and proposes prompt engineering methodologies, leveraging the Segment Anything Model (SAM) and TAPIR (Tracking Any Point with per-frame Initialization and temporal Refinement), to create a training-free point-based tracking method for small-scale objects on satellite videos. Experiments on the VISO dataset validate our strategy, marking a significant advancement in robust tracking solutions tailored for satellite imagery in remote sensing applications.