基于混合卷积自编码极限学习机的RGB-D物体识别

殷云华; 李会方

doi:10.3788/IRLA201847.0203008

基于混合卷积自编码极限学习机的RGB-D物体识别

doi: 10.3788/IRLA201847.0203008

殷云华^1,2,
李会方¹

1.
西北工业大学电子信息学院,陕西西安 710072;
2.
瞬态冲击技术重点实验室,北京 102202

基金项目:

国家自然科学基金青年科学基金（61402368）;瞬态冲击技术重点实验室基金（61426060103162606007）

详细信息

作者简介:
殷云华(1979-),男,博士生,主要从事深度学习、物体识别方面的研究。Email:yinyunhua@nuc.edu.cn

中图分类号: TP391.4

RGB-D object recognition based on hybrid convolutional auto-encoder extreme learning machine

Yin Yunhua^1,2,
Li Huifang¹

1.
School of Electronics and Information,Northwestern Polytechnical University,Xi'an 710072,China;
2.
Science and Technology on Transient Impact Laboratory,Beijing 102202,China

摘要: 有效学习丰富的表征信息在RGB-D目标识别任务中至关重要，是实现高泛化性能的关键。针对卷积神经网络训练时间长的问题，提出了一种混合卷积自编码极限学习机（HCAE-ELM）结构，包括卷积神经网络（CNN）和自编码极限学习机（AE-ELM），该结构合并了CNN的有效性和AE-ELM快速性的优点。它使用卷积层和池化层分别从RGB和深度图来有效提取低阶特征，然后在共享层合并两种模型特征，输入到自编码极限学习机中以得到高层次的特征，最终的特征使用极限学习机（ELM）进行分类，以获得更好的快速泛化能力。文中在标准的RGB-D数据集上进行了评估测试，其实验结果表明，相比较深度学习和其他的ELM方法，文中的混合卷积自编码极限学习机模型取得了良好的测试准确率，并且有效地缩减了训练时间。
- 极限学习机 /
- 卷积神经网络 /
- 自编码极限学习机 /
- 物体识别
Abstract: Learning rich representations efficiently plays an important role in RGB-D object recognition task, which is crucial to achieve high generalization performance. For the long training time of convolutional neural networks, a Hybrid Convolutional Auto-Encoder Extreme Learning Machine Structure (HCAE-ELM) was put forward which included Convolutional Neural Network (CNN) and Auto-Encoder Extreme Learning Machine (AE-ELM), which combined the power of CNN and fast training of AE-ELM. It used convolution layers and pooling layers to effectively abstract lower level features from RGB and depth images separately. And then, the shared layer was developed by combining these features from each modality and fed to an AE-ELM for higher level features. The final abstracted features were fed to an ELM classifier, which led to better generalization performance with faster learning speed. The performance of HCAE-ELM was evaluated on RGB-D object dataset. Experimental results show that the proposed method achieves better testing accuracy with significantly shorter training time in comparison with deep learning methods and other ELM methods.
- ELM /
- CNN /
- AE-ELM /
- object recognition

[1]	Cao Chuqing, Li Ruifeng, Zhao Lijun. Hand posture recognition method based on depth image technoloy[J]. Computer Engineering, 2012, 38(8):16-21. (in Chinese)曹雏清, 李瑞峰, 赵立军. 基于深度图像技术的手势识别方法[J]. 计算机工程, 2012, 38(8):16-21.
[2]	Wang Xin, Wo Bohai, Guan Qiu, et al. Human action recognition based on manifold learning[J]. Journal of Image and Graphics, 2014, 19(6):914-923. (in Chinese)王鑫, 沃波海, 管秋, 等. 基于流形学习的人体动作识别[J]. 中国图象图形学报, 2014, 19(6):914-923.
[3]	Li Changyong, Cao Qixin. Extraction method of shape feature for vegetables based on depth image[J]. Transactions of the Chinese Society for Agricultural Machinery, 2012, 43(Z1):242-245. (in Chinese)李长勇, 曹其新. 基于深度图像的蔬果形状特征提取[J]. 农业机械学报, 2012, 43(Z1):242-245.
[4]	Xu Ke. Study of convolutional neural network applied on image recognition[D]. Hangzhou:Zhejiang University, 2012. (in Chinese)许可. 卷积神经网络在图像识别的应用研究[D]. 杭州:浙江大学, 2012.
[5]	Blum M, Springenberg J T, Wulfing J, et al. A learned feature descriptor for object recognition in RGB-D data[C]//IEEE International Conference on Robotics Automation, 2012, 44(8):1298-1303.
[6]	Socher R, Huval B, Bath B P, et al. Convolutional-recursive deep learning for 3D object classification[C]//NIPS, 2012:665-673.
[7]	Niun Xiaoxiao, Suen Ching Y. A novel hybrid CNN-SVM classifier for recognizing handwritten digits[J]. Pattern Recognition, 2012, 45(4):1318-1325.
[8]	Liu Tianhua, Yang Shaoqing, Liu Songtao. Research of sea-aero target detection from photoelectricity image based on cellular neural networks[J]. Infrared and Laser Engineering, 2008, 37(S2):310-313. (in Chinese)刘天华, 杨绍清, 刘松涛. 基于CNN的海空光电目标检测技术研究[J]. 红外与激光工程, 2008, 37(S2):310-313.
[9]	Li Junmei, Hu Yihua, Tao Xiaohong. Recognition method based on principal component analysis and back-propagation neural network[J]. Infrared and Laser Engineering, 2005, 34(6):719-723. (in Chinese)李军梅, 胡以华, 陶小红. 基于主成分分析与BP神经网络的识别方法研究[J]. 红外与激光工程, 2005, 34(6):719-723.
[10]	Wang Yong, Xu Haisong. Spectral characterization of scanner based on PCA and BP ANN[J]. Chinese Optics Letters, 2005, 3(12):725-728.
[11]	Huang G B, Zhu Q Y, Siew C K. Extreme learning machine:a new learning scheme of feedforward neural networks[C]//IEEE International Joint Conference on Neural Networks, 2004, 2:985-990.
[12]	Huang G B, Zhu Q Y, Siew C K:Extreme learning machine:theory and applications[J]. Neurocomputing, 2006:70(1-3):489-501.
[13]	Arel I, Rose D C, Karnowski T P. Deep machine learning-a new frontier in artificial intelligence research[J]. IEEE Computational Intelligence Magazine, 2010, 5(4):13-18.
[14]	Boureau Y L, Ponce J, Lecun Y. A theoretical analysis of feature pooling in visual recognition[C]//International Conference on Machine Learning, 2010, 32(4):111-118.
[15]	Kasun L L C, Zhou H, Huang G B, et al. Representational learning with ELMs for big data[C]//Intelligent Systems IEEE, 2013, 28(6):31-34.
[16]	Lai K, Bo L, Ren X, et al. A large-scale hierarchical multi-view RGB-D object dataset[C]//IEEE International Conference on Robotics and Automation, 2011:1817-1824.
[17]	Bo L, Lai K, Ren X, et al. Object recognition with hierarchical kernel descriptors[C]//IEEE Int Conf on Computer Vision and Pattern Recognition, 2011:1729-1736.
[18]	Schwarz M, Schulz H, Behnke S. RGB-D object recognition and pose estimation based on pre-trained convolutional neural network features[C]//IEEE Int Conf on Robotics Automation, 2015:1329-1335.
[19]	Cheng Y, Zhao X, Huang K, et al. Semi-supervised learning and feature evaluation for RGB-D object recognition[J]. Computer Vision Image Understanding, 2015, 139(C):149-160.
[20]	Li F, Liu H, Xu X, et al. Multi-modal local receptive field extreme learning machine for object recognition[C]//International Joint Conference on Neural Networks, 2016:1696-1701.

[1]	卢毅伟, 骆永洁, 刘维, 孔明, 王道档. 深度学习点衍射干涉三维坐标定位技术 . 红外与激光工程, 2023, 52(2): 20220593-1-20220593-7. doi: 10.3788/IRLA20220593
[2]	宦克为, 李向阳, 曹宇彤, 陈笑. 卷积神经网络结合NSST的红外与可见光图像融合 . 红外与激光工程, 2022, 51(3): 20210139-1-20210139-8. doi: 10.3788/IRLA20210139
[3]	姚姝含, 官莉. 基于星载红外高光谱观测用机器学习算法反演大气温湿廓线 . 红外与激光工程, 2022, 51(8): 20210707-1-20210707-12. doi: 10.3788/IRLA20210707
[4]	夏信, 何传亮, 吕英杰, 王守志, 张博, 陈晨, 陈海鹏, 李美萱. 深度学习驱动的智能电网运行图像数据压缩技术 . 红外与激光工程, 2022, 51(12): 20220097-1-20220097-6. doi: 10.3788/IRLA20220097
[5]	李霖, 王红梅, 李辰凯. 红外与可见光图像深度学习融合方法综述 . 红外与激光工程, 2022, 51(12): 20220125-1-20220125-20. doi: 10.3788/IRLA20220125
[6]	王鹏翔, 张兆基, 杨怀. 结合多特征融合和极限学习机的红外图像目标分类方法 . 红外与激光工程, 2022, 51(6): 20210597-1-20210597-6. doi: 10.3788/IRLA20210597
[7]	高泽宇, 李新阳, 叶红卫. 流场测速中基于深度卷积神经网络的光学畸变校正技术 . 红外与激光工程, 2020, 49(10): 20200267-1-20200267-10. doi: 10.3788/IRLA20200267
[8]	邱学晶, 赵旺, 杨超, 程涛, 王帅, 许冰. 基于离焦光栅的单帧深度学习相位反演算法 . 红外与激光工程, 2020, 49(10): 20200273-1-20200273-8. doi: 10.3788/IRLA20200273
[9]	盛家川, 陈雅琦, 王君, 韩亚洪. 深度学习结构优化的图像情感分类 . 红外与激光工程, 2020, 49(11): 20200269-1-20200269-10. doi: 10.3788/IRLA20200269
[10]	徐云飞, 张笃周, 王立, 华宝成. 非合作目标局部特征识别轻量化特征融合网络设计 . 红外与激光工程, 2020, 49(7): 20200170-1-20200170-7. doi: 10.3788/IRLA20200170
[11]	裴晓敏, 范慧杰, 唐延东. 多通道时空融合网络双人交互行为识别 . 红外与激光工程, 2020, 49(5): 20190552-20190552-6. doi: 10.3788/IRLA20190552
[12]	薛珊, 张振, 吕琼莹, 曹国华, 毛逸维. 基于卷积神经网络的反无人机系统图像识别方法 . 红外与激光工程, 2020, 49(7): 20200154-1-20200154-8. doi: 10.3788/IRLA20200154
[13]	张秀, 周巍, 段哲民, 魏恒璐. 基于卷积稀疏自编码的图像超分辨率重建 . 红外与激光工程, 2019, 48(1): 126005-0126005(7). doi: 10.3788/IRLA201948.0126005
[14]	张腊梅, 陈泽茜, 邹斌. 基于3D卷积神经网络的PolSAR图像精细分类 . 红外与激光工程, 2018, 47(7): 703001-0703001(8). doi: 10.3788/IRLA201847.0703001
[15]	郭强, 芦晓红, 谢英红, 孙鹏. 基于深度谱卷积神经网络的高效视觉目标跟踪算法 . 红外与激光工程, 2018, 47(6): 626005-0626005(6). doi: 10.3788/IRLA201847.0626005
[16]	姚旺, 刘云鹏, 朱昌波. 基于人眼视觉特性的深度学习全参考图像质量评价方法 . 红外与激光工程, 2018, 47(7): 703004-0703004(8). doi: 10.3788/IRLA201847.0703004
[17]	杨楠, 南琳, 张丁一, 库涛. 基于深度学习的图像描述研究 . 红外与激光工程, 2018, 47(2): 203002-0203002(8). doi: 10.3788/IRLA201847.0203002
[18]	谢冰, 段哲民, 郑宾, 殷云华. 基于迁移学习SAE的无人机目标识别算法研究 . 红外与激光工程, 2018, 47(6): 626001-0626001(7). doi: 10.3788/IRLA201847.0626001
[19]	贾鑫, 张惊雷, 温显斌. 双监督信号深度学习的电气设备红外故障识别 . 红外与激光工程, 2018, 47(7): 703003-0703003(7). doi: 10.3788/IRLA201847.0703003
[20]	杨宏韬, 高慧斌, 张淑梅. 极限学习机方法在经纬仪空间配准中的应用 . 红外与激光工程, 2013, 42(12): 3517-3521.

点击查看大图

计量

文章访问数: 551
HTML全文浏览量: 131
PDF下载量: 91
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

基于混合卷积自编码极限学习机的RGB-D物体识别

doi: 10.3788/IRLA201847.0203008

作者简介:
殷云华(1979-),男,博士生,主要从事深度学习、物体识别方面的研究。Email:yinyunhua@nuc.edu.cn

RGB-D object recognition based on hybrid convolutional auto-encoder extreme learning machine

计量

基于混合卷积自编码极限学习机的RGB-D物体识别

doi: 10.3788/IRLA201847.0203008

1. 西北工业大学电子信息学院,陕西西安 710072;

2. 瞬态冲击技术重点实验室,北京 102202

作者简介:
殷云华(1979-),男,博士生,主要从事深度学习、物体识别方面的研究。Email:yinyunhua@nuc.edu.cn

English Abstract

RGB-D object recognition based on hybrid convolutional auto-encoder extreme learning machine

1. School of Electronics and Information,Northwestern Polytechnical University,Xi'an 710072,China;

2. Science and Technology on Transient Impact Laboratory,Beijing 102202,China

全文HTML

目录

留言板

基于混合卷积自编码极限学习机的RGB-D物体识别

doi: 10.3788/IRLA201847.0203008

作者简介: 殷云华(1979-),男,博士生,主要从事深度学习、物体识别方面的研究。Email:yinyunhua@nuc.edu.cn

RGB-D object recognition based on hybrid convolutional auto-encoder extreme learning machine

计量

出版历程

基于混合卷积自编码极限学习机的RGB-D物体识别

doi: 10.3788/IRLA201847.0203008

1. 西北工业大学 电子信息学院,陕西 西安 710072; 2. 瞬态冲击技术重点实验室,北京 102202

作者简介: 殷云华(1979-),男,博士生,主要从事深度学习、物体识别方面的研究。Email:yinyunhua@nuc.edu.cn

English Abstract

RGB-D object recognition based on hybrid convolutional auto-encoder extreme learning machine

1. School of Electronics and Information,Northwestern Polytechnical University,Xi'an 710072,China; 2. Science and Technology on Transient Impact Laboratory,Beijing 102202,China

全文HTML

目录

作者简介:
殷云华(1979-),男,博士生,主要从事深度学习、物体识别方面的研究。Email:yinyunhua@nuc.edu.cn

1. 西北工业大学电子信息学院,陕西西安 710072;

2. 瞬态冲击技术重点实验室,北京 102202

作者简介:
殷云华(1979-),男,博士生,主要从事深度学习、物体识别方面的研究。Email:yinyunhua@nuc.edu.cn

1. School of Electronics and Information,Northwestern Polytechnical University,Xi'an 710072,China;

2. Science and Technology on Transient Impact Laboratory,Beijing 102202,China