A. Ramisa, G. Alenya, F. Moreno-Noguer and C. Torras
Detecting grasping points is a key problem in cloth manipulation. Most current approaches follow a multiple re-grasp strategy for this purpose, in which clothes are sequentially grasped from different points until one of them yields to a desired 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, even when clothes are highly wrinkled.
In order to handle the large variability a deformed cloth may have, we build a Bag of Features based detector that combines appearance (SIFT) and 3D geometry features (Geodesic-Depth Histogram, GDH). An image is scanned using a sliding window with a linear classifier, and the candidate windows are refined using a non-linear SVM and a "grasp goodness" criterion to select the best grasping point.
We demonstrate our approach detection collars in deformed polo shirts, using a Kinect camera. Experimental results show a 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.
Grasping known and new polo shirts
There is a short video explaining this work:
Next are additional images of the results obtained by the method in different subsets and vocabulary sizes. Green bounding boxes correspond to manually annotated ground truth, and the detected bounding boxes are colored from red to black according to its probability (red means more probable).
Blue Polo (SIFT k=128)
Mixed Subset (SIFT k=64 GDH k=32)
Others Subset (SIFT k=128 GDH k=32)