Fuling Lin

Papers

Total Citations

H-Index

About

Fuling Lin has made significant contributions to visual tracking for unmanned aerial vehicles (UAVs), with a particular focus on correlation filter-based methods. Their key research areas include UAV tracking, self-localization, and discriminative correlation filter (DCF) optimization. Lin’s most notable work, “Multi-Regularized Correlation Filter for UAV Tracking and Self-Localization” (2021), has garnered 84 citations, underscoring its impact on the field. This paper addresses a critical limitation of standard DCF trackers, which rely on cyclic shift operations from a single frame for training samples, leading to boundary effects and reduced robustness. Lin introduced a multi-regularized framework that enhances filter learning by incorporating diverse regularization terms, significantly improving tracking accuracy and stability in challenging UAV scenarios. This innovation not only advances autonomous drone navigation but also enables simultaneous self-localization, a dual-purpose achievement rare in the literature. Lin’s work stands out for its practical applicability in real-time, resource-constrained environments, bridging the gap between theoretical tracking models and deployment on lightweight UAV platforms. Their research continues to inspire new directions in aerial tracking, particularly in handling fast motion, occlusion, and scale variations.