In the area of computer vision, deep learning has produced a variety of state-of-the-art models that rely on massive labeled data. However, collecting and annotating images from the real world is too demanding in term...In the area of computer vision, deep learning has produced a variety of state-of-the-art models that rely on massive labeled data. However, collecting and annotating images from the real world is too demanding in terms of labor and money investments, and is usually inflexible to build datasets with specific characteristics, such as small area of objects and high occlusion level. Under the framework of Parallel Vision, this paper presents a purposeful way to design artificial scenes and automatically generate virtual images with precise annotations.A virtual dataset named Parallel Eye is built, which can be used for several computer vision tasks. Then, by training the DPM(Deformable parts model) and Faster R-CNN detectors, we prove that the performance of models can be significantly improved by combining Parallel Eye with publicly available real-world datasets during the training phase. In addition, we investigate the potential of testing the trained models from a specific aspect using intentionally designed virtual datasets, in order to discover the flaws of trained models. From the experimental results, we conclude that our virtual dataset is viable to train and test the object detectors.展开更多
利用点云深度学习技术自动识别建筑构件的尺寸,并使用虚拟点云解决了3D点云数据集工作繁杂的问题.首先,提出了一种批量快速生成虚拟点云数据集的方法.通过建筑信息模型(building information modeling,BIM)技术对装配式构件参数化建模,...利用点云深度学习技术自动识别建筑构件的尺寸,并使用虚拟点云解决了3D点云数据集工作繁杂的问题.首先,提出了一种批量快速生成虚拟点云数据集的方法.通过建筑信息模型(building information modeling,BIM)技术对装配式构件参数化建模,对其进行批处理转换数据格式后生成3D点云模型,从而生成无噪声、带标注的高质量点云.然后,对点云分类网络PointNet进行改进,搭建了端对端的构件尺寸参数识别网络PointNet CE.最后,使用生成的虚拟点云数据集进行模型训练,并通过工程实例验证了方法的有效性.实验结果表明:基于BIM技术生成的虚拟点云数据集可有效拓展现实世界的数据规模;改进后的构件尺寸参数识别网络可以准确识别出构件尺寸,对训练样本的识别精度达到了毫米级,对真实构件的识别精度也达到了厘米级,可基本满足装配式结构的施工要求.展开更多
基金supported by the National Natural Science Foundation of China(61533019,71232006)
文摘In the area of computer vision, deep learning has produced a variety of state-of-the-art models that rely on massive labeled data. However, collecting and annotating images from the real world is too demanding in terms of labor and money investments, and is usually inflexible to build datasets with specific characteristics, such as small area of objects and high occlusion level. Under the framework of Parallel Vision, this paper presents a purposeful way to design artificial scenes and automatically generate virtual images with precise annotations.A virtual dataset named Parallel Eye is built, which can be used for several computer vision tasks. Then, by training the DPM(Deformable parts model) and Faster R-CNN detectors, we prove that the performance of models can be significantly improved by combining Parallel Eye with publicly available real-world datasets during the training phase. In addition, we investigate the potential of testing the trained models from a specific aspect using intentionally designed virtual datasets, in order to discover the flaws of trained models. From the experimental results, we conclude that our virtual dataset is viable to train and test the object detectors.
文摘利用点云深度学习技术自动识别建筑构件的尺寸,并使用虚拟点云解决了3D点云数据集工作繁杂的问题.首先,提出了一种批量快速生成虚拟点云数据集的方法.通过建筑信息模型(building information modeling,BIM)技术对装配式构件参数化建模,对其进行批处理转换数据格式后生成3D点云模型,从而生成无噪声、带标注的高质量点云.然后,对点云分类网络PointNet进行改进,搭建了端对端的构件尺寸参数识别网络PointNet CE.最后,使用生成的虚拟点云数据集进行模型训练,并通过工程实例验证了方法的有效性.实验结果表明:基于BIM技术生成的虚拟点云数据集可有效拓展现实世界的数据规模;改进后的构件尺寸参数识别网络可以准确识别出构件尺寸,对训练样本的识别精度达到了毫米级,对真实构件的识别精度也达到了厘米级,可基本满足装配式结构的施工要求.
