跳到正文
arXiv cs.AI· Hui Xu, Chenfei Hou, Henglai Wei, Hao Wang, Yidong Jin, Xiulin Niu, Haoyang Zhang, Hui Zhang, Tianshi Xu·· 2 小时前AI 评分35

TinyWOD:面向高空开阔水域搜救的微小目标检测数据集

A tiny object detection dataset for high-altitude open-water search and rescue

AI 导读

研究者发布 TinyWOD 数据集,针对 1.5 km 以上高空开阔水域搜救(OW-SAR)场景,以救生圈为检测目标,包含 11,359 张人工标注图像和 19,505 个标注实例。其平均等效边长(ESL)为 12.7 像素,76.96% 的实例 ESL 低于 15 像素。团队还提出 APtiny 评测指标并对主流与 SOTA 网络进行基准测试,验证了数据集的可复用性。

正文 · 原文

View PDF HTML (experimental)

Abstract:Large aerial platforms often operate above 1.5 km to improve the efficiency of open water search and rescue (OW-SAR). However, long imaging distances, wide fields of view, and limited sensor resolution reduce objects to a few pixels, increasing their susceptibility to environmental interference and making detection harder than for conventional small objects. To our knowledge, existing datasets focus on low-altitude scenarios and do not support automatic detection at 1.5-2.0 km. We therefore present TinyWOD, a tiny object detection dataset for high-altitude OW-SAR using lifebuoys as detection targets. It comprises 11,359 manually annotated images and 19,505 annotated instances spanning diverse environments, lighting conditions, water colors, and surface ripples. Compared with existing datasets, TinyWOD contains much smaller objects and a substantially higher proportion of tiny instances; its average equivalent side length (ESL) is 12.7 pixels, with 76.96% of in stances having ESLs below 15 pixels, reflecting actual high-altitude water-rescue imaging conditions. We define APtiny, a tiny object detection metric, and benchmark mainstream and state-of-the-art networks using this and conventional metrics. All evaluated networks effectively detect tiny waterborne objects, demonstrating TinyWOD's reusability and utility. We expect this dataset to support research on tiny object detection in high-altitude OW-SAR.
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.22825 [cs.CV]
  (or arXiv:2611.22825v1 [cs.CV] for this version)
  https://doi.org/10.48550/arXiv.2611.22825

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Henglai Wei Prof. [view email]
[v1] Tue, 17 Nov 2026 14:08:15 UTC (18,363 KB)

来源:arXiv cs.AI · arxiv.org