Clothes handling based on recognition by strategic observation

Kita, Yoshihiro; Kanehiro, Fumio; Ueshiba, Toshio; Kita, Naoki

doi:10.1109/humanoids.2011.6100817

Cited by 38 publications

(32 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the works referenced below perform both tasks, classification and state recognition. However, there are also some works that assume the cloth type to be known beforehand and therefore concentrate on state recognition [2,36,48,49,30], and others that only try to classify the garment piece. As for the latter, restricting to classification is either due to the application at hand (e.g.…”

Section: Cloth State Identification and Classificationmentioning

confidence: 99%

“…In [2], separated 2D visual information is used for matching right and left images, and an additional correspondence process provided the necessary 3D information to locate this point in space. State recognition and grasp point localization could be performed simultaneously in later settings [48,49,30], as their new trinocular stereo vision system allowed to attempt directly the matching of 3D observations with the 3D deformable triangular mesh models they use. Once identified, the information about the localization of the (predefined) grasping point is readily available, and the required gripper orientation can be easily computed [48].…”

Section: Node Points Of Cloth Modelsmentioning

confidence: 99%

“…This information can be gained from lateral cameras (when the cloth is lying on a table), from stereovision or from range cameras. Some authors use this information alone, like the stereovision-based methods used by [30], who combine a minimum height threshold with a verticality criterion of the surface patch, or [31], who also aim at the highest point for grasping. However, it is much more common to use image segmentation together with depth evaluation, and examples can be found for any one of the following three segmentation types:…”

Section: Segmentation and Heightmentioning

confidence: 99%

“…As for hanging clothes, in [2,36,48,49,30] grasp points are previously set on specific locations of garment models, and the image processing part is endowed with the task of matching the observed cloth with the possible shapes of the deformed mesh model, so that the point to be grasped is also located in the observed image. In [2], separated 2D visual information is used for matching right and left images, and an additional correspondence process provided the necessary 3D information to locate this point in space.…”

Section: Node Points Of Cloth Modelsmentioning

confidence: 99%

“…Histogram [28,29] Binarization [26] Graph-based [27] Height Lateral cam [28,29] Stereo [26,27,30,31] Range cam Region Centroid Max. dist.…”

Section: Cloth Features For Graspingmentioning

confidence: 99%

See 4 more Smart Citations

Visual grasp point localization, classification and state recognition in robotic manipulation of cloth: An overview

Jiménez

2017

Robotics and Autonomous Systems

View full text Add to dashboard Cite

Cloth manipulation by robots is gaining popularity among researchers because of its relevance, mainly (but not only) in domestic and assistive robotics. The required science and technologies begin to be ripe for the challenges posed by the manipulation of soft materials, and many contributions have appeared in the last years. This survey provides a systematic review of existing techniques for the basic perceptual tasks of grasp point localization, state estimation and classification of cloth items, from the perspective of their manipulation by robots. This choice is grounded on the fact that any manipulative action requires to instruct the robot where to grasp, and most garment handling activities depend on the correct recognition of the type to which the particular cloth item belongs and its state. The high inter-and intraclass variability of garments, the continuous nature of the possible deformations of cloth and the evident difficulties in predicting their localization and extension on the garment piece are challenges that have encouraged the researchers to provide a plethora of methods to confront such problems, with some promising results. The present review constitutes for the first time an effort in furnishing a structured framework of these works, with the aim of helping future contributors to gain both insight and perspective on the subject.

show abstract