Find research datasets worth reusing

FGI ARVO VLS-128 LiDAR Point Cloud, Käpylä, 7th of September 2020

<p>This LiDAR point cloud dataset is collected with a research platform of Finnish Geospatial Research Institute (FGI), called Autonomous Research Vehicle Observatory (ARVO). The dataset was collected with Velodyne VLS-128 Alpha Puck LiDAR, 7th of September 2020 in a suburban environment in the area of K&auml;pyl&auml; in Helsinki, the capital of Finland. The environment in the dataset consists of a straight two-way asphalt street, called Pohjolankatu, which starts from a larger controlled intersection at the crossing of Tuusulanv&auml;yl&auml; (60.213326&deg; N, 24.942908&deg; E in WGS84) and passes by three smaller uncontrolled intersections until the crossing of Metsolantie (60.215537&deg; N, 24.950065&deg; E). It is a typical suburban street with tram lines, sidewalks, small buildings, traffic signs, light poles, and cars parked on both sides of the streets. To collect a reference trajectory and to synchronize the LiDAR measurements, we have used a Novatel PwrPak7-E1 GNSS Inertial Navigation System (INS).</p> <p>The motion distortion of each individual scan has been corrected with a postprocessed GNSS INS trajectory and the scans have been registered with Normal Distributions Transform (NDT). Each point is provided with a semantic label probability vector and the final point cloud is averaged with a 1 cm voxel filter.</p> <p>The steps to create this preprocessed dataset have been described in more detail in the article &quot;<a href="https://arxiv.org/abs/2301.03956">Towards High-Definition Maps: a Framework Leveraging Semantic Segmentation to Improve NDT Map Compression and Descriptivity</a>&quot; published in IROS 2022. However, the number of points in each semantic segment in Table I in Section IV-A are different. The correct values are shown in the table below. This does not affect the results.</p> <table align="left"> <caption>TABLE I: RandLA-Net classified dataset label proportions.</caption> <tbody> <tr> <td><strong>Semantic label</strong></td> <td><strong>No. of points</strong></td> <td><strong>% of all</strong></td> <td><strong>% of used</strong></td> </tr> <tr> <td>Ground</td> <td>14,206,060</td> <td>32.3</td> <td>50.3</td> </tr> <tr> <td>Building</td> <td>7,782,757</td> <td>17.7</td> <td>27.6</td> </tr> <tr> <td>Tree Trunk</td> <td>3,736,775</td> <td>8.5</td> <td>13.2</td> </tr> <tr> <td>Fence</td> <td>2,201,851</td> <td>5.0</td> <td>7.8</td> </tr> <tr> <td>Pole</td> <td>206,983</td> <td>0.5</td> <td>0.7</td> </tr> <tr> <td>Traffic Sign</td> <td>85,316</td> <td>0.2</td> <td>0.3</td> </tr> <tr> <td>Labels used here</td> <td>28,219,742</td> <td>64.1</td> <td>100.0</td> </tr> <tr> <td>Others</td> <td>15,821,962</td> <td>35.9</td> <td>&nbsp;</td> </tr> <tr> <td>Total</td> <td>44,041,704</td> <td>100.0</td> <td>&nbsp;</td> </tr> </tbody> </table>