Unmanned Aerial Vehicles provide a cost-effective solution for water environment monitoring, yet detecting floating litter remains challenging due to small target scales, complex geometries, and severe surface interferences. To bridge the data deficiency in this domain, this study introduces UAV-Flow, a multi-scenario benchmark dataset wherein small-scale targets constitute 78.9%. Building upon this foundation, we propose the Floating Litter Detection Network (FLD-Net), a lightweight, real-time detection framework tailored for edge deployment. Adopting a progressive optimization paradigm, FLD-Net integrates three cascaded enhancement modules to achieve holistic performance gains across feature extraction, cross-scale fusion, and noise suppression. Specifically, the Deformation Feature Extraction Module (DFEM) enhances backbone adaptability to small targets and non-rigid deformations; the Dynamic Cross-scale Fusion Network (DCFN) facilitates efficient cross-scale semantic fusion via content-aware upsampling and an asymmetric topology; and the Dual-domain Anti-noise Attention (DANA) mechanism achieves discriminative decoupling between target semantics and structural noise through spatial-channel interaction. Experimental results on UAV-Flow demonstrate that FLD-Net achieves an mAP50 of 80.47%. Compared to the YOLOv11s baseline, it improves Recall and mAP50 by 11.66% and 8.51%, respectively, with only 9.9 M parameters. Furthermore, deployment on the NVIDIA Jetson Xavier NX yields an inference latency of 14 ms and an energy efficiency of 4.80 FPS/W, confirming the system’s robustness and viability for automated pollution monitoring.
Wang et al. (Sat,) studied this question.