Dataset for Ship Target Tracking and Trajectory Fusion in Maritime Surveillance

This dataset addresses the data requirements for technological research in target tracking and fusion, as well as the problems with currently available datasets, such as data scarcity, poor scene design specificity, uniform data formats, and incomplete data descriptions. Through simulation software, we emulate multi-sensor multi-target detection data in complex scenarios, presenting a dataset tailored for typical maritime surveillance scenarios—targeting ships using 2D radar and Electronic Support Measures (ESM) sensors. The simulation software comprises two parts: a scenario generator and a sensor simulator, forming a mature target tracking scenario simulation environment that provides realistic detection data modeling capabilities. The dataset includes 2D radar and ESM sensors, covering typical maritime ship categories, supporting configurations with radiation sources, and is designed for a variety of scenarios such as high-speed motion, dense traffic, multi-sensor data fusion, specific ship detection, and cross-positioning. The dataset contains a total of 368,155 target tracks, with 101 ships, spanning 15,000 seconds. The data format conforms to actual device reporting scenarios, and the detection error model aligns with reality, serving as foundational data for research and validation of ship target tracking and trajectory fusion algorithms.The time range of the data is 15,000 seconds, and the geographic range is 116.69751°E-121.23773°E, 22.57222°N-26.509774°N, which includes Fujian Province, Taiwan Province, and part of the East China Sea. The data volume is 80.8 MB.

本数据集旨在满足目标跟踪与融合领域技术研究的数据需求，同时针对当前公开数据集存在的诸多痛点进行优化——包括数据稀缺、场景设计针对性不足、数据格式单一以及数据描述不完备等问题。本研究通过仿真软件复现复杂场景下的多传感器多目标探测数据，构建了适配典型海上监视场景的专用数据集：面向船舶目标，采用二维雷达与电子支援措施（Electronic Support Measures, ESM）传感器进行探测。该仿真软件包含场景生成器与传感器模拟器两个核心模块，构建了成熟的目标跟踪场景仿真环境，可实现贴合实际的探测数据建模能力。本数据集涵盖二维雷达与ESM传感器数据，覆盖典型海事船舶类别，支持辐射源配置，并适配多种应用场景，包括高速运动、密集通航、多传感器数据融合、特定船舶检测以及交叉定位等。数据集总计包含368155条目标航迹，涵盖101艘船舶，总时长达15000秒。数据格式贴合实际设备上报场景，探测误差模型与真实场景相符，可为船舶目标跟踪与航迹融合算法的研究与验证提供基础数据支撑。数据时长为15000秒，地理覆盖范围为东经116.69751°至121.23773°、北纬22.57222°至26.509774°，涵盖福建省、台湾省以及东中国海部分海域。数据集总数据量为80.8 MB。

搜集汇总

背景与挑战

背景概述

该数据集是一个面向海上监视的舰船目标跟踪与航迹融合研究的数据集，包含368,155条目标航迹和101艘舰船的数据，时间跨度为15,000秒，地理范围涵盖福建省、台湾省和部分东海区域。数据集通过仿真软件模拟了2D雷达和ESM传感器的多目标检测数据，支持高速运动、密集交通、多传感器数据融合等多种场景的研究。