シャムネットワークによる視覚的手がかりを用いたワンショット物体位置推定
One-Shot Object Localization Using Learnt Visual Cues via Siamese Networks
レーザーポインタで指し示された未知物体を、シャムネットワークを組み込んだエンドツーエンドのニューラルネットワークで認識・位置推定し、ロボットが把持・配置できることを示した研究。
著者: Sagar Gubbi Venkatesh, Bharadwaj Amrutur
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
A robot that can operate in novel and unstructured environments must be capable of recognizing new, previously unseen, objects. In this work, a visual cue is used to specify a novel object of interest which must be localized in new environments. An end-to-end neural network equipped with a Siamese network is used to learn the cue, infer the object of interest, and then to localize it in new environments. We show that a simulated robot can pick-and-place novel objects pointed to by a laser pointer. We also evaluate the performance of the proposed approach on a dataset derived from the Omniglot handwritten character dataset and on a small dataset of toys.
