Norimasa Kobori

Deep Manifold Embedding for 3D Object Pose Estimation.

Recently, 3D object pose estimation is being focused. The Pa rametric Eigenspace method is known as one of the fundamental methods for this. It represents the appea rance change of an object caused by pose change with a manifold embedded in a low-dimensional subspace. It o btains features by Principal Component Analysis (PCA), which maximizes the appearance variation. Howe ver, there is a problem that it cannot handle a pose change with slight appearance change since there is not always a correlation between pose change and appearance change. In this paper, we propose a method that in troduces “Deep Manifold Embedding” which maximizes the pose variation directly. We construct a manif old rom features extracted from Deep Convolutional Neural Networks (DCNNs) trained with pose informati on. Pose estimation with the proposed method achieved the best accuracy in experiments using a public dat aset.

Proposal of a spectral random dots marker using local feature for posture estimation

We propose a novel marker for robots grasping task which has the following three aspects: (i) it is easy-to-find in a cluttered background, (ii) it is calculable for its posture (iii) its size is compact. The proposed marker is composed of a random dots pattern, and uses keypoint detection and a scale estimation by Spectral SIFT for dots detection and data decoding. The data is encoded by the scale size of dots, and the same dots in the marker work for both marker detection and data decoding. As a result, the proposed marker size can be compact. We confirmed the effectiveness of the proposed marker through experiments.