著者
林 建一 加藤 博一 西田 正吾
出版者
特定非営利活動法人 日本バーチャルリアリティ学会
雑誌
日本バーチャルリアリティ学会論文誌 (ISSN:1344011X)
巻号頁・発行日
vol.12, no.2, pp.149-158, 2007

Many kinds of tracking for Augmented Reality had been proposed. In case of the feature point tracking, the pose is computed by minimizing the error between the observed 2D feature points and the back-projected feature points from the 3D scene model. This minimization problem is usually solved by a non-linear optimization. The main advantage of this approach is its accuracy. However, it is difficult to compute the correct pose unless an appropriate initial value is used. In addition, when some errors are included in the observation, this approach does not guarantee the correct pose even if it converged on the global minimum. So, once an incorrect pose was computed in one frame, tracking may fail in the next frame or the result will get farther from the correct one. In this paper, we propose a new tracking framework for augmented reality. Proposed method tracks features as multiple local hypotheses based on not only one pose but also multiple poses that are computed in the pose estimation in the previous frame. Since multiple poses are maintained as global hypotheses, as far as the correct pose is contained in the hypotheses, the tracking can be continued in even hard situations like a simple iterative scene with high-speed movement.
著者
田村 亮輔 天野 敏之 加藤 博一
出版者
一般社団法人情報処理学会
雑誌
情報処理学会研究報告コンピュータビジョンとイメージメディア(CVIM) (ISSN:09196072)
巻号頁・発行日
vol.2008, no.3, pp.341-342, 2008-01-17

仮想立体絵本は,拡張現実感技術を利用し,カメラで撮影した絵本の画像上に3次元 CG コンテンツを重畳表示するシステムである.絵本の各ページを予めコンピュータに登録しておき,その情報と画像を比較しカメラと絵本の相対的な位置姿勢を計算することで,幾何学的に整合性のとれた画像合成が可能となる.我々もテンプレートマッチングに基づく特徴点追跡を利用した位置姿勢計算手法について研究してきた.近年,マルチコアCPUが普及し始めており,並列処理による処理の高速化が標準的なPC環境においても比較的容易に実現できるようになった.今回は,マルチコアCPUの使用を前提に,我々のこれまでの提案手法の並列化を行い,処理を高速化,安定化を実現した.Virtual pop-up books are systems which can overlay a captured image with 3D CG objects based on augmented reality technology. 3D geometrical consistency in the composite image can be kept by estimating the relative pose of the camera from the physical book. We have been studying about this pose estimation method using feature tracking based on template matching. Since multi-core CPUs have been spread in recent years, it can be easily achieved to improve the performance speed by parallel processing on a standard PC environment. We modified our tracking codes for parallel processing by multi-core CPUs and improved the performance speed and robustness of the tracking.