Three Dimensional Shape Modeling by Multiple Sensor Information

通过多个传感器信息进行三维形状建模

• 批准号: 15500100
• 负责人: KUMAZAWA Itsuo
• 金额: $ 2.37万
• 依托单位: TOKYO INSTITUTE OF TECHNOLOGY
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2003
• 资助国家: 日本
• 起止时间: 2003 至 2004
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-15500100/
• 关键词: Three dimensional shape modeling; Multiple view images; Neural Network; Distance measurement; Stereo Matching; Learning algorithm; Infra red distance sensor; three dimensional graphics; 3次元形状モデリング; 赤外線; 3次元映像コンテンツ; Shape from Shading; 照明条件; S

Novel Artificial Neural Networks were developed for automatic modeling of three dimensional shapes. These neural networks have capabilities of learning a function of modeling three dimensional shapes from their multiple view images. To model the shapes, they use a polyhedron, models represented by the special architecture of the network and connection weights among the network. These connection weights are updated during the learning process by using multiple view images so that the views of the polyhedron models coincide with the corresponding views of the actual shapes. The performance of the proposed methods is evaluated by some experiments. By combining multiple view images in addition to other distance information measured, by infra red illumination method, the method gave improve results with robustness against noises and errors. Stereo matching based distance measurement method is also jointly applied to the method and contradicting results were fixed by error correction procedure.

新型人工神经网络被开发用于三维形状的自动建模。这些神经网络具有从它们的多视图图像学习建模三维形状的功能的能力。为了对形状进行建模，他们使用多面体，由网络的特殊架构和网络之间的连接权重表示的模型。在学习过程中，通过使用多个视图图像来更新这些连接权重，使得多面体模型的视图与实际形状的对应视图一致。通过实验对所提方法的性能进行了评估。通过结合多个视图的图像，除了其他的距离信息测量，红外照明的方法，该方法给出了改进的结果，对噪声和错误的鲁棒性。将基于立体匹配的距离测量方法应用到该方法中，并通过误差校正过程修正矛盾的结果。

项目成果

Fanany, M.I., Kumazawa, I.: "SA-Optimized Hierarchical 3D reconstruction NN"Proceeding of the Twelfth IASTED International Conference on Applied and Simulation Modelling. ASM 2003. 495-500 (2003)

Fanany, M.I.、Kumazawa, I.：“SA 优化的分层 3D 重建神经网络”第十二届 IASTED 应用与仿真建模国际会议论文集。

Fanany, M.I., Kumazawa, I.: "Multiple-View Shape Extraction from Shading as Local Regression by Analytic NN Scheme"Mathematical and Computer Modeling Journal. (採録決定).

Fanany, M.I.，Kumazawa, I.：“通过分析神经网络方案从阴影中提取多视图形状作为局部回归”数学和计算机建模期刊（已接受）。

Fanany, M.I., Kumazawa, I.: "SA-Optimized of Multiple-View Smooth Polyhedron Representation NN"Proceedings of 6^<th> International Conference on Discovery Science. Springer LNA I 2843. 306-310 (2003)

Fanany, M.I.、Kumazawa, I.：“多视图平滑多面体表示 NN 的 SA 优化”第六届国际发现科学会议论文集。

Combinatorial Transparent Surface Modeling from Polarization Images

偏振图像的组合透明表面建模

• 发表时间: 2004
• 期刊: Proc.Of 10th International Workshop, IWCIA 2004
• 作者: Mohamad Ivan Fanany;K.Kobayashi;Itsuo Kumazawa
• 通讯作者: Itsuo Kumazawa

Fanany, M.I., Kumazawa, I: "A Neural Network for Recovering 3D Shape from Erroneous and Few Depth Maps"Pattern Recognition Letters. 25・4. 377-389 (2004)

Fanany, M.I.，Kumazawa, I：“从错误和少量深度图中恢复 3D 形状的神经网络”模式识别信件 25・4 (2004)。