Title: A 3-Dimensnional Object Recognition Method Using Color-SHOT and Relationship of Distances and Angles in Feature Points

Year of Publication: Dec - 2018
Page Numbers: 13-20
Authors: Hiroyuki Kudo, Hiroki Imamura
Conference Name: THE 4TH INTERNATIONAL CONFERENCE ON COMPUTING TECHNOLOGY AND INFORMATION MANAGEMENT (ICCTIM2018)
- Greece

Abstract:


In recent years, the declining birthrate and an aging population are developing, and there is concern about the lack of labor power such as household chores and nursing care at home. In the living field, robots that support the lives of people are collectively referred to as life support robots. This robot is required to perform various tasks to support the human. Especially, objects recognition task is important when people request the robots to transport and rearrange objects. We had proposed a method focusing on SHOT, which is widely known in feature description of 3-dimensional objects. Because of SHOT being expressed only in the local area, we focused on the relationship between feature points and supplemented the weak point in SHOT feature matching. However, in the previous study, we used SHOT for feature description of shape information, so there was a weak point that it is not robust to the change of the texture of the target object. Therefore we propose a robust method for texture change by using Color-SHOT for feature description.