RGB-D SLAM based Incremental Cuboid Modeling

Masashi Mishima, Hideaki Uchiyama, Diego Thomas, Rin-ichiro Taniguchi, Rafael Roberto, Jo ao Paulo Lima, Veronica Teichrieb; Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018, pp. 0-0

This paper present a framework for incremental 3D cuboid modeling combined with RGB-D SLAM. While performing RGB-D SLAM, planes are incrementally reconstructed from point clouds. Then, cuboids are detected in the planes by analyzing the positional relationships between the planes; orthogonality, convexity, and proximity. Finally, the position, pose and size of a cuboid are determined by computing the intersection of three perpendicular planes. In addition, the cuboid shapes are incrementally updated to suppress false detections with sequential measurements. As an application of our framework, an augmented reality based interactive cuboid modeling system is introduced. In the evaluation at a cluttered environment, the precision and recall of the cuboid detection are improved with our framework owing to stable plane detection, compared with a batch based method.