VisioDECT Dataset: An Aerial Dataset for Scenario-Based Multi-Drone Detection and Identification Research

The deployment of unmanned aerial vehicles (UAV) for logistics and other civil purposes is consistently disrupting airspace security. Consequently, there is a scarcity of robust datasets for the development of real-time systems that can checkmate the incessant deployment of UAVs in carrying out criminal or terrorist activities. VisioDECT is a robust vision-based drone dataset for classifying, detecting, and countering unauthorized drone deployment using visual and electro-optical infra-red detection technologies.The dataset consists of 20924 sample images and annotations from 6 drone models across 3 scenarios (cloudy, sunny, and evening), at different altitudes and distances (30m-100m), and in 3 different file formats (txt, xml, csv) that was generated at 12 different locations within a period of 1 year, 8 months by a team of domain experts.The materials used for the data capturing includes drone models (Anafi-Extended, DJI FPV, DJI Phantom, EFT-E410S, Mavic2-Air, and Mavic2-Enterprise), drone controllers, mobile phone with controller application, high-definition digital cameras, and tripod stands. Each drone model was flown at different altitudes and distances at different times of day, week, and month. The video sequence of each scenario is recorded.  Using reputable software applications, each video sequence is converted to JPEG image frames of 852 x 480 pixels and stored in repositories representing each model class and scenario sub-class. To minimize error, trained professionals carried out data cleaning on each repository by manually eliciting image frames without corresponding drones at the background. Data annotation was carried out by trained experts on each scenario sub-class in 3 file formats (txt, xml, and csv) by manually drawing bounding boxes around each image file to generate corresponding label files. To ensure consistency in naming convention and minimize error, each scenario sub-class label files are named to correspond to their image files and stored in repositories accordingly. VisioDECT dataset is arranged in 6 folders (representing the 6 drone models) with each folder having 2 sub-folders (representing the images folders and labels folders). Each image folder is made up of 3 scenario folders (representing cloudy, sunny, and evening) containing the image files stored in .JPG format. Each label folder contains 3 scenario annotation files (stored in .txt, .csv, and xml format) corresponding to the 3 scenario image folders. This makes it easy for classification, detection, and other image processing simulations on the dataset using developed models or different state-of-the-art artificial intelligence (AI) models.      

无人机（Unmanned Aerial Vehicle, UAV）在物流及其他民用领域的部署正持续干扰空域安全。因此，当前缺乏能够有效遏制无人机被用于实施犯罪或恐怖活动的实时系统开发所需的高质量可靠数据集。VisioDECT是一款基于视觉的高性能无人机数据集，可借助视觉与光电红外检测技术，实现对未经授权的无人机部署行为的分类、检测与反制。该数据集包含20924张样本图像与对应标注信息，涵盖6款无人机机型，覆盖阴天、晴天、傍晚三种拍摄场景，采集于不同高度与距离区间（30米至100米），采用三种文件格式（txt、xml、csv）存储；数据集由领域专家团队在1年8个月的周期内，于12个不同地点采集生成。数据采集所用器材包括：Anafi-Extended、DJI FPV、DJI Phantom、EFT-E410S、Mavic2-Air及Mavic2-Enterprise共6款无人机机型、无人机遥控器、搭载控制应用程序的智能手机、高清数码相机以及三脚架。每款无人机均在不同时段（每日、每周、每月的不同时刻）、不同高度与距离下完成飞行采集，各场景的视频序列均被录制留存。借助专业商用软件，各视频序列均被转换为分辨率852×480像素的JPEG图像帧，并按照机型类别与场景子类分别存储至对应数据集仓库。为最大限度降低误差，经过专业培训的人员对各数据集仓库执行数据清洗操作，手动剔除背景中无无人机的图像帧。随后，经过培训的专家针对每个场景子类，以三种文件格式（txt、xml、csv）完成数据标注：通过在每张图像上手动绘制边界框，生成对应的标签文件。为确保命名规范统一并进一步降低误差，各场景子类的标签文件均采用与对应图像文件一致的命名规则，并存储至对应数据集仓库。VisioDECT数据集共设置6个一级文件夹，分别对应6款无人机机型；每个一级文件夹下设2个子文件夹，分别为图像文件夹与标签文件夹。其中，图像文件夹包含3个场景子文件夹，分别对应阴天、晴天、傍晚三种场景，内部存储格式为.JPG的图像文件。每个标签文件夹则包含3个场景标注文件，分别对应3个场景的图像文件夹，文件格式为.txt、.csv与.xml。该数据集结构便于研究人员基于自研模型或各类前沿人工智能（Artificial Intelligence, AI）模型，完成该数据集上的分类、检测及其他图像处理仿真实验。

搜集汇总

背景与挑战

背景概述

VisioDECT是一个包含20924张图像和注释的视觉数据集，专为无人机检测和识别设计，涵盖6种无人机模型在3种天气条件下的数据。数据集结构清晰，适用于无人机分类、检测等任务，支持多种文件格式。