Curnis Giovanni, Fontana Simone, Sorrenti Domenico G
Dipartimento di Informatica, Sistemistica e Comunicazione, Università degli Studi di Milano - Bicocca, Italy.
Data Brief. 2022 Jun 22;43:108412. doi: 10.1016/j.dib.2022.108412. eCollection 2022 Aug.
Developing point clouds registration, SLAM or place recognition algorithms requires data with a high quality ground truth (usually composed of a position and orientation). Moreover, many machine learning algorithms require large amounts of data for training. However, acquiring this kind of data in non-urban outdoor environments poses several challenges. First of all, off-road robots are usually very expensive. Above all, producing an accurate ground truth is problematic. Even the best sensor available, RTK GPS, cannot guarantee the required accuracy in every condition. Hence the scarcity of this kind of dataset for point clouds registration or SLAM in off-road conditions. For these reasons, we propose a synthetic dataset generated using Grand Theft Auto V (GTAV), a video game that accurately simulates sensing in outdoor environments. The data production technique is based on DeepGTAV-PreSIL [1]: a simulated LiDAR and a camera are installed on a vehicle which is driven through the GTAV map. Since one of the goals of our work is to produce a large amount of data to train neural networks which will then be used with real data, we have chosen the characteristics of the sensors to accurately simulate real ones. The proposed dataset is composed of 16.207 point clouds and images, divided into five sequences representing different environments, such as fields, woods and mountains. For each pair of point clouds and images we also provide the ground truth pose of the vehicle at the acquisition.
开发点云配准、即时定位与地图构建（SLAM）或地点识别算法需要高质量的地面真值数据（通常由位置和方向组成）。此外，许多机器学习算法需要大量数据进行训练。然而，在非城市户外环境中获取此类数据存在诸多挑战。首先，越野机器人通常非常昂贵。最重要的是，生成准确的地面真值存在问题。即使是现有的最佳传感器，实时动态（RTK）全球定位系统（GPS），也无法在所有情况下保证所需的精度。因此，在越野条件下用于点云配准或SLAM的此类数据集非常稀缺。出于这些原因，我们提出了一个使用《侠盗猎车手5》（GTAV）生成的合成数据集，这是一款能精确模拟户外环境感知的视频游戏。数据生成技术基于DeepGTAV-PreSIL [1]：在一辆行驶于GTAV地图的车辆上安装一个模拟激光雷达和一个摄像头。由于我们工作的目标之一是生成大量数据来训练神经网络，然后将其与真实数据一起使用，所以我们选择了能精确模拟真实传感器的特性。所提出的数据集由16,207个点云和图像组成，分为五个序列，代表不同的环境，如田野、树林和山脉。对于每对点云和图像，我们还提供采集时车辆的地面真值姿态。
