Abstract
Manipulation tasks on subsea instalments require extremely precise detection and localization of objects of interest. This problem is referred to as “pose estimation”. In this work, we present a framework for detecting and predicting 6DoF pose for relevant objects (fish-tail, gauges, and valves) on a subsea panel under varying water turbidity. A deep learning model that takes 3D vision data as an input is developed, providing a more robust 6D pose estimate. Compared to the 2D vision deep learning model, the proposed method reduces rotation and translation prediction error by (−Δ0.39∘) and translation (−Δ6.5 mm), respectively, in high turbid waters. The proposed approach is able to provide object detection as well as 6D pose estimation with an average precision of 91%. The 6D pose estimation results show 2.59∘ and 6.49 cm total average deviation in rotation and translation as compared to the ground truth data on varying unseen turbidity levels. Furthermore, our approach runs at over 16 frames per second and does not require pose refinement steps. Finally, to facilitate the training of such model we also collected and automatically annotated a new underwater 6D pose estimation dataset spanning seven levels of turbidity.
Highlights
The performance of the network under different turbidities is evaluated based on the Relative Translation Error (RTE) and Relative Rotation Error (RRE) metrics that measures the deviations between the predicted and and ground truth pose as defined in [24]
Looking at the metrics presented for each class, the level of difficulty for object detection and pose estimation underwater varies with turbidity and the size of object of interest
We introduce an efficient automated data annotation approach to train deep learning models for underwater pose estimation
Summary
Velocity Logs (DVLs), compasses and IMUs. Velocity Logs (DVLs), compasses and IMUs Such inaccurate localization methods are not suitable for intervention, inspection and maintenance use-cases where accurate localization is key. Underwater optical (3D) imaging has opened up possibilities for providing highdensity information of the AUV surroundings, which is an enabler for accurate detection and 6DoF localization of objects. Deep learning on 3D images has revolutionized detection and localization [1]. Its application and performance for object detection and localization on underwater imagery has not been explored to the same degree. We propose a deep learning based network for 6DoF localization of known objects using underwater 3D range-gated images
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
