A new dataset was recently submitted to the SFI Offshore Mechatronics repository in Dataverse.no. Submitting data to a repository like Dataverse.no is an important effort towards Findable, Accessible, Interoperable and Reusable data. Datasets which are published in Dataverse.no gets a uniqe DOI reference which can be referenced in publications.
The dataset published was generated related to research in WP3. The data contains both the raw point cloud data from an outdoor test site, as well as generated images used for training. PhD fellow Joacim Dybedal used the data to train and test a classifier to detect people.
The research results based on the dataset are published in the paper “CNN-based People Detection in Voxel Space using Intensity Measurements and Point Cluster Flattening” (Joacim Dybedal and Geir Hovland, Modeling, Identification and Control, 2021, Vol 42, No. 2, pp. 37-46.).