Kwak, Kiho Kim, Jun-Sik Huber, Daniel F. Kanade, Takeo 2024-01-19T12:08:54Z 2024-01-19T12:08:54Z 2022-03-07 2014 1050-4729 https://pubs.kist.re.kr/handle/201004/115401 Object representation is useful for many computer vision tasks, such as object detection, recognition, and tracking. Computer vision tasks must handle situations where unknown objects appear and must detect and track some object which is not in the trained database. In such cases, the system must learn or, otherwise derive, descriptions of new objects. In this paper, we investigate creating a representation of previously unknown objects that newly appear in the scene. The representation creates a viewpoint-invariant and scale-normalized model approximately describing an unknown object with multimodal sensors. Those properties of the representation facilitate 3D tracking of the object using 2D-to-2D image matching. The representation has both benefits of an implicit model (referred to as a view-based model) and an explicit model (referred to as a shape-based model). Experimental results demonstrate the viability of the proposed representation and outperform the existing approaches for 3D-pose estimation. English IEEE Online Approximate Model Representation of Unknown Objects Conference 1 IEEE International Conference on Robotics and Automation (ICRA), pp.1725 - 1732 IEEE International Conference on Robotics and Automation (ICRA) 1725 1732 US Hong Kong, PEOPLES R CHINA 2014-05-31 2014 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) 000377221101110 2-s2.0-84929180235 Proceedings Paper