Trash deposits in aquatic environments have a destructive effect on marine ecosystems and pose a long-term economic and environmental threat. Autonomous underwater vehicles (AUVs) could very well contribute to the solution of this problem by finding and eventually removing trash. This paper evaluates a number of deep-learning algorithms performing the task of visually detecting trash in realistic underwater environments, with the eventual goal of exploration, mapping, and extraction of such debris by using AUVs. A large and publicly-available dataset of actual debris in open-water locations is annotated for training a number of convolutional neural network architectures for object detection. The trained networks are then evaluated on a set of images from other portions of that dataset, providing insight into approaches for developing the detection capabilities of an AUV for underwater trash removal. In addition, the evaluation is performed on three different platforms of varying processing power, which serves to assess these algorithms' fitness for real-time applications.
|Original language||English (US)|
|Title of host publication||2019 International Conference on Robotics and Automation, ICRA 2019|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||7|
|State||Published - May 2019|
|Event||2019 International Conference on Robotics and Automation, ICRA 2019 - Montreal, Canada|
Duration: May 20 2019 → May 24 2019
|Name||Proceedings - IEEE International Conference on Robotics and Automation|
|Conference||2019 International Conference on Robotics and Automation, ICRA 2019|
|Period||5/20/19 → 5/24/19|
Bibliographical noteFunding Information:
We gratefully acknowledge the support of the MnDRIVE initiative and the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research. The dataset used in this work was created based on the publicly available J-EDI dataset, provided by JAMSTEC, the Japanese Agency for Marine-Earth Science and Technology. The authors wish to thank them for providing this data for scientific endeavors. The authors also wish to thank Sophie Fulton, Marc Ho, Elliott Imhoff, Yuanzhe Liu, Julian Lagman, and Youya Xia for their tireless efforts in annotating images for training purposes.