矢田 紀子

Recent advances in depth measurement and its utilization have made point cloud processing more critical. Additionally, the human head is essential for communication, and its three-dimensional data are expected to be utilized in this regard. However, a single RGB-Depth (RGBD) camera is prone to occlusion and depth measurement failure for dark hair colors such as black hair. Recently, point cloud completion, where an entire point cloud is estimated and generated from a partial point cloud, has been studied, but only the shape is learned, rather than the completion of colored point clouds. Thus, this paper proposes a machine learning-based completion method for colored point clouds with XYZ location information and the International Commission on Illumination (CIE) LAB (L*a*b*) color information. The proposed method uses the color difference between point clouds based on the Chamfer Distance (CD) or Earth Mover’s Distance (EMD) of point cloud shape evaluation as a color loss. In addition, an adversarial loss to L*a*b*-Depth images rendered from the output point cloud can improve the visual quality. The experiments examined networks trained using a colored point cloud dataset created by combining two 3D datasets: hairstyles and faces. Experimental results show that using the adversarial loss with the colored point cloud renderer in the proposed method improves the image domain’s evaluation.

Copyright © 2018 by ITE Transactions on Media Technology and Applications (MTA). This paper proposes a point groups-based algorithm for point cloud registration. Most of the existing algorithms align two point clouds globally; however, they are unsuitable when the overlapping ratio is low or the inputs do not have strong features. The high accuracy of matched points is conducive for a rigid transformation of point clouds. This study aims to determine the exact matching points to register point clouds. The proposed method is based on point groups that are resampled point clouds. Subsequently, we calculate the multiple average probability (MAP) for each point group and match them by a sparse representation. Finally, the coherent point drift (CPD) algorithm is used to register the matched point groups, and the same transformation is applied to register the point clouds. The experimental results show that in terms of robustness to noise and outliers, our algorithm can register point clouds with a low overlapping ratio.

Stereoscopic video technology, which enables three-dimensional (3D) images to be displayed, has been developing rapidly. However, existing devices are unable to achieve accurate color reproduction. This paper proposes a method to accurately reproduce the colors displayed by a multiband 3D projector. Previously, we proposed a stereoscopic display system with an expanded color gamut. However, we only confirmed the expansion of the color gamut of the proposed system and were unable to display stereoscopic images with accurate colors. We now propose an accurate color and spectral reproduction method for a stereoscopic image display system for which we developed an expanded color gamut by means of the covariance matrix adaptation evolution strategy (CMA-ES). The system design for optimizing the color reproduction of the multiband 3D projector is described. An experimental evaluation of the color reproducibility showed the performance of the proposed method to be superior to that of an existing method.

This paper is focused on marker-based AR technology. Existing AR markers are almost available on only flat surface. Therefore, this paper proposes an original AR marker design and processing method that can recognize the marker on the foldable and cylindrical surface.

This paper is focused on marker-based AR technology. Existing AR markers are almost available on only flat surface. Therefore, this paper proposes an original AR marker design and processing method that can recognize the marker on the foldable and cylindrical surface.

本論文では，複数の平面によって構成された物体を仮定し，照明効果による色度遷移についてのモデルを用いて，照明効果の影響による疑似輪郭線の発生を抑制した画像の領域分割手法を提案する．1 つの表面に対応する画素群の色空間中での分布を光源との位置関係や Shadow，Shade など照明効果の影響によるものと見なし，隣接する領域が同一の表面に対応しているのか，それぞれが異なる表面に対応しているのか判定を行う．また，被写体表面を平面と想定できる環境を設定し，輪郭線の特性に基づいた領域の隣接関係についての判定を行うことで，隣接関係を持つ領域群から適切な統合先の選択を行う．照明効果から生じた疑似輪郭線によって過分割された領域を色度遷移と輪郭線の特性の情報をもとに適切に統合することで，物体表面色に基づいた画像領域分割を実現する．In this paper, we propose a method to segment a color image into regions corresponding to each surface of objects. In the method, a color image is divided into lots of small regions with the clustering results in color spaces. And, using color transition model and previous knowledge about the constraint on the shape of object, all regions in the adjacency are determined whether or not they can be integrated. Integrating of regions based on the result of determination, the whole image is divided into the regions that correspond to surfaces of object.