Learning Occluded Branch Depth Maps in Forest Environments Using RGB-D Images
Open access
Autor(in)
Alle anzeigen
Datum
2024-03Typ
- Journal Article
ETH Bibliographie
yes
Altmetrics
Abstract
Covering over a third of all terrestrial land area, forests are crucial environments; as ecosystems, for farming, and for human leisure. However, they are challenging to access for environmental monitoring, for agricultural uses, and for search and rescue applications. To enter, aerial robots need to fly through dense vegetation, where foliage can be pushed aside, but occluded branches pose critical obstacles. Therefore, we propose pixel-wise depth regression of occluded branches using three different U-Net inspired architectures. Given RGB-D input of trees with partially occluded branches, the models estimate depth values of only the wooden parts of the tree. A large photorealistic simulation dataset comprising around 44 K images of nine different tree species is generated, on which the models are trained. Extensive evaluation and analysis of the models on this dataset is shown. To improve network generalization to real-world data, different data augmentation and transformation techniques are performed. The approaches are then also successfully demonstrated on real-world data of broadleaf trees from Swiss temperate forests and a tropical Masoala Rainforest. This work showcases the previously unexplored task of frame-by-frame pixel-based occluded branch depth reconstruction to facilitate robot traversal of forest environments. Mehr anzeigen
Persistenter Link
https://doi.org/10.3929/ethz-b-000659145Publikationsstatus
publishedExterne Links
Zeitschrift / Serie
IEEE Robotics and Automation LettersBand
Seiten / Artikelnummer
Verlag
IEEEThema
Deep learning for visual perception; Robotics and automation in agriculture and forestry; RGB-D perceptionOrganisationseinheit
09718 - Mintchev, Stefano / Mintchev, Stefano
Förderung
186865 - CYbER - CanopY Exploration Robots (SNF)
Zugehörige Publikationen und Daten
Is supplemented by: https://doi.org/10.3929/ethz-b-000634419
ETH Bibliographie
yes
Altmetrics