CAJ | 학술논문

三维形状特征在三维物体分类、检索和语义分析中起着关键的作用. 传统的三维特征设计过程繁复, 而且不能从已有的大量三维数据中自动学习而得. 在深度神经网络的研究领域中, 卷积神经网络和自动编码机是比较流行的 2 种网络结构. 在超限学习机的框架之下, 将两者结合起来, 提出一种基于卷积-自动编码机的三维特征自动学习方法. 实验结果表明, 文中方法的特征学习速度比其他深度学习方法提高约2个数量级, 且提取的特征在三维模型分类、三维物体检测等任务中都取得了良好的结果.
삼유형상특정재삼유물체분류、검색화어의분석중기착관건적작용. 전통적삼유특정설계과정번복, 이차불능종이유적대량삼유수거중자동학습이득. 재심도신경망락적연구영역중, 권적신경망락화자동편마궤시비교류행적 2 충망락결구. 재초한학습궤적광가지하, 장량자결합기래, 제출일충기우권적-자동편마궤적삼유특정자동학습방법. 실험결과표명, 문중방법적특정학습속도비기타심도학습방법제고약2개수량급, 차제취적특정재삼유모형분류、삼유물체검측등임무중도취득료량호적결과.
3D shape features play a crucial role in graphics applications like 3D shape matching, recognition, and retrieval. Traditional 3D descriptors are hand-crafted features which are labor-intensively designed and are unable to extract discriminative information from existing large-scale 3D data. Convolutional neuron networks and auto-encoders are two most popular neuron networks in the field of deep learning. Based on the framework of extreme learning machines, we propose a rapid 3D feature learning method—convolutional extreme learning machine auto-encoder, which could automatically learn shape features from 3D shape dataset. Our method runs faster than existing deep learning methods by approximately two orders of magnitude. Experiments show that our method is superior to traditional machine learning methods based on hand-crafted features and other deep learning methods in tasks of 3D shape classification and 3D object detection.