Detecting grasping points is a key problem in cloth manipulation. Most current approaches follow a multiple regrasp\udstrategy for this purpose, in which clothes are sequentially grasped from different points until one of them yields to a\uddesired configuration. In this paper, by contrast, we circumvent the need for multiple re-graspings by building a robust detector that identifies the grasping points, generally in one single step,\udeven when clothes are highly wrinkled.\udIn order to handle the large variability a deformed cloth may have, we build a Bag of Features based detector that combines\udappearance and 3D geometry features. An image is scanned using a sliding window with a linear classifier, and the candidate\udwindows are refined using a non-linear SVM and a “grasp goodness” criterion to select the best grasping point.\udWe demonstrate our approach detecting collars in deformed polo shirts, using a Kinect camera. Experimental results show\uda good performance of the proposed method not only in identifying the same trained textile object part under severe deformations and occlusions, but also the corresponding part in other clothes, exhibiting a degree of generalization.
展开▼
