Dronevision: A Dataset of Aerial Videos for Computer Vision Applications

With the increasing use of drones for surveillance and monitoring purposes, there is a growing need for reliable and efficient object detection algorithms that can detect and track objects in aerial images and videos. To develop and test such algorithms, datasets of aerial videos captured from drones are essential. In this context, this dataset of aerial videos captured over a college campus provides a valuable resource for researchers and developers to train and evaluate object detection models for surveillance and security applications in a campus environment. This dataset comprises aerial videos captured from a drone over a college campus. The dataset is intended for use in object detection and other surveillance applications. The videos provide a good-resolution bird's-eye view of the campus, allowing for the detection and tracking of people, trees,ground, and other objects. The dataset contains a range of scenarios, including parking lots, and open spaces. The dataset can be used to develop and evaluate object detection algorithms for surveillance and security applications in a college campus environment. The dataset is publicly available and can be used for research purposes.

随着无人机在监视与监测场景中的应用日益普及，能够在航拍图像与视频中实现可靠高效的目标检测（object detection）与跟踪的算法的需求也与日俱增。开发与测试此类算法，离不开由无人机采集的航拍视频数据集作为必要支撑。在此背景下，本数据集采集自大学校园上空的航拍视频，可为研究者与开发者提供宝贵的科研资源，用于训练和评估面向校园环境下安防监视场景的目标检测模型。本数据集由无人机在大学校园上空采集的航拍视频构成，旨在服务于目标检测及其他监视类应用。这些视频以高分辨率的鸟瞰视角覆盖校园场景，可实现对人员、树木、地面及其他各类目标的检测与跟踪。数据集涵盖停车场、开阔场地等多种典型场景，能够用于开发和评估面向大学校园安防监视场景的目标检测算法。本数据集已公开可用，可用于各类科研工作。