Accurately estimating the 3D position of underwater objects is of great interest when doing research on marine animals. An inherent problem of 3D reconstruction of underwater positions is the presence of refraction which invalidates the assumption of a single viewpoint. Three ways of performing 3D reconstruction on underwater objects are compared in this work: an approach relying solely on in-air camera calibration, an approach with the camera calibration performed under water and an approach based on ray tracing with Snell's law. As expected, the in-air camera calibration showed to be the most inaccurate as it does not take refraction into account. The precision of the estimated 3D positions based on the underwater camera calibration and the ray tracing based approach were, on the other hand, almost identical. However, the ray tracing based approach is found to be advantageous as it is far more flexible in terms of the calibration procedure due to the decoupling of the intrinsic and extrinsic camera parameters.

We propose a novel multi-pose loss function to train a neural network for 6D pose estimation, using synthetic data and evaluating it on real images. Our loss is inspired by the VSD (Visible Surface Discrepancy) metric and relies on a differentiable renderer and CAD models. This novel multipose approach produces multiple weighted pose estimates to avoid getting stuck in local minima. Our method resolves pose ambiguities without using predefined symmetries. It is trained only on synthetic data. We test on real-world RGB images from the T-LESS dataset, containing highly symmetric objects common in industrial settings. We show that our solution can be used to replace the codebook in a state-of-the-art approach. So far, the codebook approach has had the shortest inference time in the field. Our approach reduces inference time further while a) avoiding discretization, b) requiring a much smaller memory footprint and c) improving pose recall. 3

Purpose: The advances in artificial intelligence have started to reach a level where autonomous systems are becoming increasingly popular as a way to aid people in their everyday life. Such intelligent systems may especially be beneficially for people struggling to complete common everyday tasks, such as individuals with movement-related disabilities. The focus of this paper is hence to review recent work in using computer vision for semi-autonomous control of assistive robotic manipulators (ARMs).Methods: Four databases were searched using a block search, yielding 257 papers which were reduced to 14 papers after apply-ing various filtering criteria. Each paper was reviewed with focus on the hardware used, the autonomous behaviour achieved using computer vision and the scheme for semi-autonomous control of the system. Each of the reviewed systems were also sought characterized by grading their level of autonomy on a pre-defined scale.Conclusions: A re-occurring issue in the reviewed systems was the inability to handle arbitrary objects. This makes the systems unlikely to perform well outside a controlled environment, such as a lab. This issue could be addressed by having the systems recognize good grasping points or primitive shapes instead of specific pre-defined objects. Most of the reviewed systems did also use a rather simple strategy for the semi-autonomous control, where they switch either between full manual control or full automatic control. An alternative could be a control scheme relying on adaptive blending which could provide a more seamless experience for the user KEYWORDS

No abstract

No abstract