Road Traversing Knowledge

The Road Transverse Knowledge (RTK) dataset was specially designed to meet the emerging country infrastructure. It sums 701 densely annotated images of low-resolution quality (352x288), split into 561 and 140 samples for the training and the validation sets, respectively. The dataset presents 12 classes of road surfaces like asphalt, paved and unpaved; damages like potholes, water puddles, and cracks; and road signs like speed bumps, cat's eyes, and markings.

The images were captured in good weather and daylight conditions in the country areas of Santa Catarina in Brazil.

道路横向知识（Road Transverse Knowledge，RTK）数据集专为满足新兴乡村基础设施领域的研究需求而设计。该数据集共计包含701张经密集标注的低分辨率图像（分辨率为352×288），其中训练集与验证集分别包含561和140个样本。
该数据集涵盖12类目标：包括沥青路面、铺装路面、非铺装路面等路面类别，坑洼、水洼、裂缝等道路损坏类别，以及减速带、反光道钉、道路标线等道路标识与设施类别。
所有图像均采集于巴西圣卡塔琳娜州的乡村区域，采集时天气状况良好且处于日间光照环境中。

搜集汇总

背景与挑战

背景概述

Road Traversing Knowledge数据集包含701张低分辨率（352x288）的密集注释图像，分为561张训练集和140张验证集。该数据集特别针对新兴国家的基础设施，涵盖了12类道路表面（如沥青、铺砌和未铺砌）、损坏（如坑洞、水坑和裂缝）以及道路标志（如减速带、猫眼和标记），图像在巴西圣卡塔琳娜的乡村地区良好天气和日光条件下拍摄。