文章基本信息

标题：HAGDAVS: Height-Augmented Geo-Located Dataset for Detection and Semantic Segmentation of Vehicles in Drone Aerial Orthomosaics
本地全文：下载
作者：John R. Ballesteros ; German Sanchez-Torres ; John W. Branch-Bedoya 等
期刊名称：Data
印刷版ISSN：2306-5729
出版年度：2022
卷号：7
期号：4
页码：1-14
DOI：10.3390/data7040050
语种：English
出版社：MDPI Publishing
摘要：Detection and Semantic Segmentation of vehicles in drone aerial orthomosaics has applica-tions in a variety of ﬁelds such as security, trafﬁc and parking management, urban planning, logistics,and transportation, among many others. This paper presents the HAGDAVS dataset fusing RGBspectral channel and Digital Surface Model DSM for the detection and segmentation of vehicles fromaerial drone images, including three vehicle classes: cars, motorcycles, and ghosts (motorcycle or car).We supply DSM as an additional variable to be included in deep learning and computer vision modelsto increase its accuracy. RGB orthomosaic, RG-DSM fusion, and multi-label mask are provided in TagImage File Format. Geo-located vehicle bounding boxes are provided in GeoJSON vector format. Wealso describes the acquisition of drone data, the derived products, and the workﬂow to produce thedataset. Researchers would beneﬁt from using the proposed dataset to improve results in the case ofvehicle occlusion, geo-location, and the need for cleaning ghost vehicles. As far as we know, this isthe ﬁrst openly available dataset for vehicle detection and segmentation, comprising RG-DSM dronedata fusion and different color masks for motorcycles, cars, and ghosts.Dataset: https://doi.org/10.5281/zenodo.6323712.Dataset License: Licensed under Creative Commons Attribution 4.0 International.
关键词：vehicle detection;semantic segmentation;orthomosaics;Geographic Information Systems(GIS)