Best next-viewpoint recommendation by selecting minimum pose ambiguity for category-level object pose estimation

• Main Authors: Hashim, Nik Mohd Zarifie, Kawanishi, Yasutomo, Deguchi, Daisuke, Ide, Ichiro, Murase, Hiroshi, Amma, Ayako, Kobori, Norimasa
• Format: Article
• Language: English
• Published: Japan Society for Precision Engineering 2021
• Online Access: http://eprints.utem.edu.my/id/eprint/25968/2/87_440.PDF; http://eprints.utem.edu.my/id/eprint/25968/; https://www.jstage.jst.go.jp/article/jjspe/87/5/87_440/_pdf/-char/en
• Institution: Universiti Teknikal Malaysia Melaka

Object manipulation is one of the essential tasks for a home helper robot, especially in helping a disabled person to complete everyday tasks. For handling various objects in a category, accurate pose estimation of the target objects is required. Since the pose of an object is often ambiguous from an observation, it is important to select a good next-viewpoint to make a better pose estimation. This paper introduces a metric of the object pose ambiguity based on the entropy of the pose estimation result. By using the metric, a best next-viewpoint recommendation method is proposed for accurate category-level object pose estimation. Evaluation is performed with synthetic object images of objects in five categories. It shows the proposed methods is applicable to various kind of object categories.