Best Viewpoint Tracking for Camera Mounted on Robotic Arm with Dynamic Obstacles

The problem of finding a next best viewpoint for 3D modeling or scene mapping has been explored in computer vision over the last decade. This paper tackles a similar problem, but with different characteristics, and proposes a method for dynamic best viewpoint recovery of a target point while avoiding possible occlusions. Since the environment can change, the method has to iteratively find the next best view with a global knowledge of the free and occupied parts. We model the problem as a set of possible viewpoints which correspond to the centers of cell of a virtual tessellated hemisphere covering the scene. Taking into account occlusions, distances between current and future viewpoints, quality of the viewpoint and joint constraints (robot arm joint distances or limits), we evaluate the best next viewpoint. The proposal has been evaluated in 8 different scenarios with different occlusions and a short sequence to validate the dynamic performance.