Hierarchical Salient Object Detection for Assisted Grasping
This work addresses the challenge of reliable object grasping for robotics, but appears incremental as it builds on prior hierarchical clustering methods.
The paper tackled the problem of visual scene decomposition for object grasping by introducing a hierarchical saliency function derived from segmentation, and demonstrated its ability to detect salient objects in comprehensive experiments, with an easy-to-use pick and place system developed and tested.
Visual scene decomposition into semantic entities is one of the major challenges when creating a reliable object grasping system. Recently, we introduced a bottom-up hierarchical clustering approach which is able to segment objects and parts in a scene. In this paper, we introduce a transform from such a segmentation into a corresponding, hierarchical saliency function. In comprehensive experiments we demonstrate its ability to detect salient objects in a scene. Furthermore, this hierarchical saliency defines a most salient corresponding region (scale) for every point in an image. Based on this, an easy-to-use pick and place manipulation system was developed and tested exemplarily.