Abstract: Various embodiments include a pose estimation method for refining an initial multi-dimensional pose of an object of interest to generate a refined multi-dimensional object pose Tpr(NL) with NL?1. The method may include: providing the initial object pose Tpr(0) and at least one 2D-3D-correspondence map ?pri with i=1, . . . , I and I?1; and estimating the refined object pose Tpr(NL) using an iterative optimization procedure of a loss according to a given loss function LF(k) based on discrepancies between the one or more provided 2D-3D-correspondence maps ?pri and one or more respective rendered 2D-3D-correspondence maps ?rendk,i.

Abstract: A method and a system for object detection and pose estimation within an input image. A 6-degree-of-freedom object detection and pose estimation is performed using a trained encoder-decoder convolutional artificial neural network including an encoder head, an ID mask decoder head, a first correspondence color channel decoder head and a second correspondence color channel decoder head. The ID mask decoder head creates an ID mask for identifying objects, and the color channel decoder heads are used to create a 2D-to-3D-correspondence map. For at least one object identified by the ID mask, a pose estimation based on the generated 2D-to-3D-correspondence map and on a pre-generated bijective association of points of the object with unique value combinations in the first and the second correspondence color channels is generated.

Abstract: Armature reaction in a dynamo is reduced by constructing the main pole structure and/or the commutating pole structure with a plurality of iron lamina arranged parallel to the axis of rotation of the dynamo. The iron lamina are separated from each other by nonmagnetic or magnetically weak material of a predetermined thickness designed to cause a predetermined minimum but high reluctance to be offered to flux generated in the main or commutating pole structure as a result of armature current. The core of each pole may be split into a first and second core half at the root and in the direction of the axis of rotation. Each core half has a larger portion which extends to the adjacent core half of the neighboring pole, thereby forming a yoke. A smaller portion of each core half extends into the air gap between poles and, together with the corresponding portion of the core half of the neighboring pole which is similarly extended into the same air gap, forms a commutating pole.