当前位置: X-MOL 学术Comput. Intell. Neurosci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A New Volumetric CNN for 3D Object Classification Based on Joint Multiscale Feature and Subvolume Supervised Learning Approaches
Computational Intelligence and Neuroscience Pub Date : 2020-05-28 , DOI: 10.1155/2020/5851465
A. A. M. Muzahid 1, 2 , Wanggen Wan 1, 2 , Li Hou 3
Affiliation  

The advancement of low-cost RGB-D and LiDAR three-dimensional (3D) sensors has permitted the obtainment of the 3D model easier in real-time. However, making intricate 3D features is crucial for the advancement of 3D object classifications. The existing volumetric voxel-based CNN approaches have achieved remarkable progress, but they generate huge computational overhead that limits the extraction of global features at higher resolutions of 3D objects. In this paper, a low-cost 3D volumetric deep convolutional neural network is proposed for 3D object classification based on joint multiscale hierarchical and subvolume supervised learning strategies. Our proposed deep neural network inputs 3D data, which are preprocessed by implementing memory-efficient octree representation, and we propose to limit the full layer octree depth to a certain level based on the predefined input volume resolution for storing high-precision contour features. Multiscale features are concatenated front multilevel octree depths inside the network, aiming to adaptively generate high-level global features. The strategy of the subvolume supervision approach is to train the network on subparts of the 3D object in order to learn local features. Our framework has been evaluated with two publicly available 3D repositories. Experimental results demonstrate the effectiveness of our proposed method where the classification accuracy is improved in comparison to existing volumetric approaches, and the memory consumption ratio and run-time are significantly reduced.

中文翻译:

基于联合多尺度特征和子量监督学习方法的新型3D对象分类体积CNN

低成本RGB-D和LiDAR三维(3D)传感器的发展使实时3D模型的获取变得更加容易。但是,制作复杂的3D特征对于3D对象分类的发展至关重要。现有的基于体积体素的CNN方法已经取得了显着进展,但是它们产生了巨大的计算开销,从而限制了在3D对象的高分辨率下提取全局特征的能力。本文提出了一种基于联合多尺度分层和子体积监督学习策略的低成本3D体积深度卷积神经网络,用于3D对象分类。我们建议的深度神经网络输入3D数据,这些数据通过实现记忆有效的八叉树表示进行预处理,并且我们建议基于预定义的输入体积分辨率将整个八叉树深度限制在一定水平,以存储高精度轮廓特征。多尺度特征是连接在网络内部的前端多级八叉树深度,旨在自适应地生成高级全局特征。子体积监督方法的策略是在3D对象的子部分上训练网络,以学习局部特征。我们的框架已经通过两个公开的3D存储库进行了评估。实验结果证明了我们提出的方法的有效性,与现有的体积方法相比,该方法提高了分类精度,并且显着减少了内存消耗率和运行时间。多尺度特征是连接在网络内部的前端多级八叉树深度,旨在自适应地生成高级全局特征。子体积监督方法的策略是在3D对象的子部分上训练网络,以学习局部特征。我们的框架已经通过两个公开的3D存储库进行了评估。实验结果证明了我们提出的方法的有效性,与现有的体积方法相比,该方法提高了分类精度,并且显着减少了内存消耗率和运行时间。多尺度特征是连接在网络内部的前端多级八叉树深度,旨在自适应地生成高级全局特征。子体积监督方法的策略是在3D对象的子部分上训练网络,以学习局部特征。我们的框架已经通过两个公开的3D存储库进行了评估。实验结果证明了我们提出的方法的有效性,与现有的体积方法相比,该方法提高了分类精度,并且显着减少了内存消耗率和运行时间。子体积监督方法的策略是在3D对象的子部分上训练网络,以学习局部特征。我们的框架已经通过两个公开的3D存储库进行了评估。实验结果证明了我们提出的方法的有效性,与现有的体积方法相比,该方法提高了分类精度,并且显着减少了内存消耗率和运行时间。子体积监督方法的策略是在3D对象的子部分上训练网络,以学习局部特征。我们的框架已经通过两个公开的3D存储库进行了评估。实验结果证明了我们提出的方法的有效性,与现有的体积方法相比,该方法提高了分类精度,并且显着减少了内存消耗率和运行时间。
更新日期:2020-05-28
down
wechat
bug