海上无人机目标检测研究进展与发展趋势

钱 家琪
上海理工大学

摘要


海上无人机目标检测兼具航拍小目标、动态海面干扰与机载资源受限等特征，现有综述往往将相关方法分散归入小目标检测、海面感知或模型轻量化，难以解释不同技术之间的内在关联。本文从海上无人机检测的失效过程出发，提出“信息补偿—表征保真—背景解耦—风险感知决策—资源适配”五类方法体系，系统梳理数据集、代表算法及评价指标，并分析各类方法在精度、鲁棒性和部署效率方面的作用边界。进一步总结研究由通用模型迁移向场景与硬件协同设计的演进趋势，为后续算法研究和工程部署提供统一分析框架。

关键词


海上无人机；目标检测；失效链；复杂海况；风险感知；资源适配

全文:

PDF


参考


[1]苏润，吴峻峰，章德云.复杂海战场景小目标检测与识别技术综述[J/OL].指挥控制与仿真，2025.

[2]冷佳旭，莫梦竟成，周应华，等.无人机视角下的目标检测研究进展[J].中国图象图形学报，2023，28（9）：2563-2586.

[3]YIN J C, XU G K, WANG N, et al. A survey of small sea-surface target detection for maritime search and rescue[J]. IEEE Transactions on Intelligent Transportation Systems, 2026, 27(1): 211-231.

[4]潘晓英，贾凝心，穆元震，等.小目标检测研究综述[J].中国图象图形学报，2023，28（9）：2587-2615.

[5]DONG H T, LIU G, LIU W. UAV-based maritime search and rescue: Dataset construction and object detection evaluation[C]//2025 7th International Conference on Frontier Technologies of Information and Computer. IEEE, 2025.

[6]VARGA L A, KIEFER B, MESSMER M, et al. SeaDronesSee: A maritime benchmark for detecting humans in open water[C]//2022 IEEE/CVF Winter Conference on Applications of Computer Vision. IEEE, 2022: 2260-2270.

[7]ZHAO B G, LI J M, ZHAO J W, et al. Optimizing drone-captured maritime rescue image object detection through dataset rebalancing under sample constraints[J]. The Visual Computer, 2025, 41: 11221-11237.

[8]BAI J, DAI J C, WANG Z C, et al. A detection method of the rescue targets in the marine casualty based on improved YOLOv5s[J]. Frontiers in Neurorobotics, 2022, 16: 1053124.

[9]FU Z M, XIAO Y H, TAO F Z, et al. DLSW-YOLOv8n: A novel small maritime search and rescue object detection framework for UAV images with deformable large kernel net[J]. Drones, 2024, 8(7): 310.

[10]WANG C, LI L, LU K, et al. TPS-YOLOv8n: An advanced algorithm for small object detection in complex maritime search and rescue scenarios using unmanned aerial vehicle imagery[J]. Measurement Science and Technology, 2025, 36(7): 075404.

[11]LI S C, YI H, CHEN S Y, et al. SAQ-YOLO: An efficient small object detection model for unmanned aerial vehicle in maritime search and rescue[J]. Applied Sciences, 2026, 16(1): 131.

[12]RUAN J J, HE J, TONG Y. SeaLSOD-YOLO: A lightweight framework for maritime small object detection using YOLOv11[J]. Sensors, 2026, 26: 2017.

[13]李赛博，王晓璐，代君，等.UAV-YOLO：面向海上搜救的无人机多尺度抗干扰目标检测算法[J].海军航空大学学报，2025，40（6）：943-950.

[14]董甲东，桑飞虎，郭庆虎，等.基于深度学习的目标检测算法轻量化研究综述[J].计算机科学与探索，2025，19（8）：2057-2084.

[15]ZHENG X L, WANG H J, SHANG Y, et al. Starting from the structure: A review of small object detection based on deep learning[J]. Image and Vision Computing, 2024, 146: 105054.




DOI: http://dx.doi.org/10.12361/2661-3506-08-09-163721

Refbacks

  • 当前没有refback。