MID: A Comprehensive Shore-Based Dataset for Multi-Scale Dense Ship Occlusion and Interaction Scenarios

TL;DR

The paper introduces MID, a shore-based optical dataset designed to address multi-scale ship detection under dense occlusion and complex interactions. It curates 5,673 images with 135,884 oriented bounding box targets from 43 video sequences across open water and narrow channels, enabling supervised and semi-supervised learning. The dataset encompasses diverse weather, lighting, and occlusion conditions, and provides detailed OBB annotations to support detection, tracking, and trajectory prediction in port and coastal contexts. Baseline experiments with multiple detectors using OBB heads demonstrate MID's utility and highlight its potential to advance intelligent maritime surveillance and autonomous navigation.

Abstract

This paper introduces the Maritime Ship Navigation Behavior Dataset (MID), designed to address challenges in ship detection within complex maritime environments using Oriented Bounding Boxes (OBB). MID contains 5,673 images with 135,884 finely annotated target instances, supporting both supervised and semi-supervised learning. It features diverse maritime scenarios such as ship encounters under varying weather, docking maneuvers, small target clustering, and partial occlusions, filling critical gaps in datasets like HRSID, SSDD, and NWPU-10. MID's images are sourced from high-definition video clips of real-world navigation across 43 water areas, with varied weather and lighting conditions (e.g., rain, fog). Manually curated annotations enhance the dataset's variety, ensuring its applicability to real-world demands in busy ports and dense maritime regions. This diversity equips models trained on MID to better handle complex, dynamic environments, supporting advancements in maritime situational awareness. To validate MID's utility, we evaluated 10 detection algorithms, providing an in-depth analysis of the dataset, detection results from various models, and a comparative study of baseline algorithms, with a focus on handling occlusions and dense target clusters. The results highlight MID's potential to drive innovation in intelligent maritime traffic monitoring and autonomous navigation systems. The dataset will be made publicly available at https://github.com/VirtualNew/MID_DataSet.

Figures (18)

• Figure 1: Video capture device.
• Figure 2: Flow chart for extracting video frames.
• Figure 3: HBB annotation method.
• Figure 4: OBB annotation method.
• Figure 5: Overall file structure of MID.