DroneVehicle

该数据集是一个大规模的基于无人机可见光与红外数据集，包含了953,087个车辆实例，分布在56,878张图像中，并为五个类别（轿车、公交车、卡车、货车和货运车）提供了定向边界框。此外，该数据集被划分为训练集、验证集和测试集三个部分，规模属于大型，任务类型为多模态目标检测。

This is a large-scale UAV-based visible light and infrared dataset. It contains 953,087 vehicle instances distributed across 56,878 images, and is annotated with oriented bounding boxes for five vehicle categories: sedan, bus, truck, van and freight vehicle. Additionally, this dataset is partitioned into three subsets: training set, validation set and test set, and its task type is multimodal object detection.

搜集汇总

背景与挑战

背景概述

DroneVehicle是一个大规模的无人机RGB-红外车辆检测数据集，包含28,439对图像，覆盖多种场景和光照条件，提供五类车辆的定向边界框标注。数据集旨在支持跨模态车辆检测研究，特别是在低光照条件下的性能提升。