Title: A 3-Dimensional Object Recognition Method Using Relationships between Feature Points, and Invariance of Local Hue Histogram

Issue Number: Vol. 8, No. 1
Year of Publication: March - 2018
Page Numbers: 41-52
Authors: Tomohiro Kanda, Kazuo Ikeshiro and Hiroki Imamura
Journal Name: International Journal of New Computer Architectures and their Applications (IJNCAA)
- Hong Kong

Abstract:


In recent years, there is concern about the lack of labor power such as household chores and nursing care at home due to advancement of the declining birthrate and an aging population. Accordingly, the Life Support Robots aiming at livelihood support of people are attracting attention. In the Life Support Robot, the process of identifying objects is one of the most important tasks, and a lot of studies have been performed in order to solve it. However, there are still many subjects that must be solved for practical use. Therefore, this paper presents a novel technology focusing on the recognition process for Life Support Robot. This technology describes useful features in 3D object by using relationships between feature points, and invariance of local hue histogram, furthermore this technology performs matching by them. Thereby, this technology is demonstrated to improve the recognition accuracy in challenging object recognition scenarios such as occlusion