计算机应用研究2017，Vol.34Issue(9)：2834-2837,2870,5.DOI:10.3969/j.issn.1001-3695.2017.09.060
多尺度卷积递归神经网络的RGB-D物体识别
Multi-scale convolutional-recursive neural networks for RGB-D object recognition
摘要
Abstract
In order to fully utilize potential feature information of RGB-D images,this paper proposed a new algorithm called Ms-CRNN.It applied the multi-scale block operation to RGB image,gray imge,depth image and 3D surface normal map from input RGB-D image to form several channels,and convolved each channel with corresponding size of filter.Then,it performed local contrast normalization and subsampling oft the extracted feature maps to obtain low-level invariant features,which were given as inputs to recursive neural networks in order to compose higher order features.It sent vectors combining multi-scale features from all the channels to a SVM classifier for classification.It evaluated the proposed method on RGB-D dataset.Experimental results show that the recognition accuracy of the proposed method for RGB-D objects can reach 88.2％,and has certainly increased the recognition accuracy.关键词
多尺度/3D曲面法线/递归神经网络/RGB-D物体识别Key words
multi-scale/3D surface normal/recursive neural networks/RGB-D object recognition分类
信息技术与安全科学引用本文复制引用
骆健,蒋旻,刘星,周龙..多尺度卷积递归神经网络的RGB-D物体识别[J].计算机应用研究,2017,34(9):2834-2837,2870,5.基金项目
国家自然科学基金面上项目(41571396) （41571396）
国家创新训练项目(201410488017) （201410488017）
