Abstract This paper presents a novel challenging dataset that offers a new landscape of testing material for mobile robotics, autonomous driving research, and forestry operation. In contrast to common urban structures, we explore an unregulated natural environment to exemplify sub-urban and forest environment. The sequences provide two-natured data where each place is visited in summer and winter conditions. The vehicle used for recording is equipped with a sensor rig that constitutes four RGB cameras, an Inertial Measurement Unit, and a Global Navigation Satellite System receiver. The sensors are synchronized based on non-drifting timestamps. The dataset provides trajectories of varying complexity both for the state of the art visual odometry approaches and visual simultaneous localization and mapping algorithms. The full dataset and toolkits are available for download at: http://urn.fi/urn:nbn:fi:att:9b8157a7-1e0f-47c2-bd4e-a19a7e952c0d . As an alternative, you can browse for the dataset using the article title at: http://etsin.fairdata.fi .

中文翻译：

---

FinnForest 数据集：用于视觉 SLAM 的森林景观

摘要 本文提出了一个新的具有挑战性的数据集，为移动机器人、自动驾驶研究和林业运营提供了一个新的测试材料景观。与常见的城市结构相比，我们探索不受管制的自然环境，以举例说明郊区和森林环境。这些序列提供了两个性质的数据，其中每个地方都在夏季和冬季条件下被访问。用于记录的车辆配备了一个传感器装置，该装置由四个 RGB 摄像头、一个惯性测量单元和一个全球导航卫星系统接收器组成。传感器基于非漂移时间戳同步。该数据集为最先进的视觉里程计方法和视觉同时定位和映射算法提供了不同复杂性的轨迹。完整数据集和工具包可从以下网址下载：http://urn.fi/urn:nbn:fi:att:9b8157a7-1e0f-47c2-bd4e-a19a7e952c0d。作为替代方法，您可以使用位于 http://etsin.fairdata.fi 的文章标题浏览数据集。