基于深度卷积神经网络的物体识别算法

doi:10.11772/j.issn.1001-9081.2016.12.3333

计算机应用 ›› 2016, Vol. 36 ›› Issue (12): 3333-3340.DOI: 10.11772/j.issn.1001-9081.2016.12.3333

基于深度卷积神经网络的物体识别算法

黄斌, 卢金金, 王建华, 吴星明, 陈伟海

北京航空航天大学自动化科学与电气工程学院, 北京 100191

收稿日期:2016-04-26 修回日期:2016-07-11 出版日期:2016-12-10 发布日期:2016-12-08
通讯作者: 陈伟海
作者简介:黄斌(1989-),男,安徽安庆人,博士研究生,主要研究方向:计算机视觉、深度学习、机器学习;卢金金(1990-),女,安徽安庆人,硕士研究生,主要研究方向:计算机视觉、深度学习、机器学习;王建华(1962-),男,北京人,副教授,博士,主要研究方向:智能机器人检测和控制、计算机视觉;吴星明(1962-),男,北京人,副教授,博士,主要研究方向:智能机器人检测和控制、计算机视觉;陈伟海(1955-),男,浙江象山人,教授,博士,主要研究方向:康复机器人、计算机视觉。
基金资助:
国家自然科学基金资助项目（61573048）；重点国际（地区）合作研究项目（61620106012）；国家国际科技合作专项（2015DFG12650）。

Object recognition algorithm based on deep convolution neural networks

HUANG Bin, LU Jinjin, WANG Jianhua, WU Xingming, CHEN Weihai

School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China

Received:2016-04-26 Revised:2016-07-11 Online:2016-12-10 Published:2016-12-08
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61573048), the Major International (Regional) Joint Research Project (61620106012), the International Scientific and Technological Cooperation Projects of China under Grant (2015DFG12650).

摘要/Abstract

摘要： 针对传统物体识别算法中人工设计出来的特征易受物体形态多样性、光照和背景的影响，提出了一种基于深度卷神经网络的物体识别算法。该算法基于NYU Depth V2场景数据库，首先将单通道深度信息转换为三通道；再用训练集中的彩色图片和转换后的三通道深度图片分别微调两个深度卷积神经网络模型；然后用训练好的模型对重采样训练集中的彩色和深度图片提取模型第一个全连接层的特征，并将两种模态的特征串联起来，训练线性支持向量机（LinSVM）；最后将所提算法应用到场景理解任务中的超像素特征提取。所提方法在测试集上的物体分类准确度可达到91.4%，比SAE-RNN方法提高4.1个百分点。实验结果表明所提方法可提取彩色和深度图片高层特征，有效提高物体分类准确度。

关键词: 计算机视觉, 卷积神经网络, 特征提取, 线性支持向量机, 物体识别, 场景理解

Abstract: Focused on the problem of traditional object recognition algorithm that the artificially designed features were more susceptible to diversity of object shapes, illumination and background, a deep convolutional neural network algorithm was proposed for object recognition. Firstly, this algorithm was trained with NYU Depth V2 dataset, and single depth information was transformed into three channels. Then color images and transformed depth images in the training set were used to fine-tune two deep convolutional neural networks, respectively. Next, color and depth image features were extracted from the first fully connected layers of the two trained models, and the two features from the resampling training set were combined to train a Linear Support Vector Machine (LinSVM) classifier. Finally, the proposed object recognition algorithm was used to extract super-pixel features in scene understanding task. The proposed method can achieve a classification accuracy of 91.4% on the test set which is 4.1 percentage points higher than SAE-RNN (Sparse Auto-Encoder with the Recursive Neural Networks). The experimental results show that the proposed method is effective in extracting color and depth image features, and can effectively improve classification accuracy.

Key words: computer vision, Convolutional Neural Network (CNN), feature extraction, Linear Support Vector Machine (LinSVM), object recognition, scene understanding

中图分类号:

TP391.4

黄斌, 卢金金, 王建华, 吴星明, 陈伟海. 基于深度卷积神经网络的物体识别算法[J]. 计算机应用, 2016, 36(12): 3333-3340.

HUANG Bin, LU Jinjin, WANG Jianhua, WU Xingming, CHEN Weihai. Object recognition algorithm based on deep convolution neural networks[J]. Journal of Computer Applications, 2016, 36(12): 3333-3340.

参考文献

[1] CHATFIELD K, SIMONYAN K, VEDALDI A, et al. Return of the devil in the details:Delving deep into convolutional nets[EB/OL].[2016-01-20]. http://arxiv.org/pdf/1405.3531v4.pdf.
[2] LIN M, CHEN Q, YAN S. Network in network[EB/OL].[2016-01-20]. http://arxiv.org/pdf/1312.4400v3.pdf.
[3] RAZAVIAN A S, AZIZPOUR H, SULLIVAN J, et al. CNN features off-the-shelf:an astounding baseline for recognition[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Washington, DC:IEEE Computer Society, 2014:512-519.
[4] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2014:580-587.
[5] HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[C]//Proceedings of the 13th European Conference on Computer Vision. Berlin:Springer, 2014:346-361.
[6] GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2015:1440-1448.
[7] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, PP(99):1-9.
[8] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once:unified, real-time object detection[EB/OL].[2016-01-20]. http://ai2-website.s3.amazonaws.com/publications/YOLO.pdf.
[9] LAI K, BO L, REN X, et al. A large-scale hierarchical multi-view RGB-D object dataset[C]//Proceedings of the 28th IEEE International Conference on Robotics and Automation. Piscataway, NJ:IEEE, 2011:1817-1824.
[10] BO L, REN X, FOX D. Depth kernel descriptors for object recognition[C]//Proceedings of the 23th IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, NJ:IEEE, 2011:821-826.
[11] BO L, REN X, FOX D. Unsupervised feature learning for RGB-D based object recognition[C]//Proceedings of the 13th International Symposium on Experimental Robotics. Berlin:Springer, 2013:387-402.
[12] SOCHER R, HUVAL B, BATH B, et al. Convolutional-recursive deep learning for 3D object classification[EB/OL].[2016-01-20]. http://machinelearning.wustl.edu/mlpapers/paper_files/NIPS2012_0304.pdf.
[13] BAI J, WU Y. SAE-RNN deep learning for RGB-D based object recognition[C]//Proceedings of the 10th International Conference on Intelligent Computing Theory. Berlin:Springer, 2014:235-240.
[14] LIANG M, HU X. Recurrent convolutional neural network for object recognition[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2015:3367-3375.
[15] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J/OL]. ArXiv.[2016-01-20]. http://www.robots.ox.ac.uk:5000/~vgg/publications/2015/Simonyan15/simonyan15.pdf
[16] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems 25. Piscataway, NJ:IEEE:1106-1114.
[17] HINTON G E, SRIVASTAVA N, KRIZHEVSKY A, et al. Improving neural networks by preventing co-adaptation of feature detectors[J]. Computer Science, 2012, 3(4):212-223.
[18] JIA Y, SHELHAMER E, DONAHUE J, et al. Caffe:convolutional architecture for fast feature embedding[C]//Proceedings of the 22th ACM International Conference on Multimedia. New York:ACM, 2014:675-678.
[19] GUPTA S, GIRSHICK R, ARBELÁEZ P, et al. Learning rich features from RGB-D images for object detection and segmentation[C]//Proceedings of the 15th European Conference on Computer Vision. Berlin:Springer, 2014:345-360.
[20] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE International Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2014:580-587.
[21] SILBERMAN, N, HOIEM, D, KOHLI, P, et al. Indoor segmentation and support inference from RGB-D images[C]//Proceedings of the 13th European Conference on Computer Vision. Berlin:Springer, 2012:746-760
[22] REN X, BO L, FOX D. RGB-(D) scene labeling:features and algorithms[C]//Proceedings of the 2012 IEEE International Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2012:2759-2766.
[23] ARBELÁEZ P, MAIRE M, FOWLKES C, et al. Contour detection and hierarchical image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5):898-916.
[24] GUPTA S, ARBELAEZ P, MALIK J. Perceptual organization and recognition of indoor scenes from RGB-D images[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2013:564-571.
[25] BLUM M, SPRINGENBERG J T, WVLFING J, et al. A learned feature descriptor for object recognition in RGB-D data[C]//Proceedings of the 2012 IEEE International Conference on Robotics and Automation. Piscataway, NJ:IEEE, 2012:1298-1303.

基于深度卷积神经网络的物体识别算法

Object recognition algorithm based on deep convolution neural networks

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[2]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[3]	马佳良, 陈斌, 孙晓飞. 基于改进的Faster R-CNN的通用目标检测框架[J]. 计算机应用, 2021, 41(9): 2712-2719.
[4]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[5]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[6]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[7]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[8]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[9]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[10]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[11]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[12]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[13]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.
[14]	武光利, 李雷霆, 郭振洲, 王成祥. 基于改进的双向长短期记忆网络的视频摘要生成模型[J]. 计算机应用, 2021, 41(7): 1908-1914.
[15]	谭道强, 曾诚, 乔金霞, 张俊. 基于混合注意力模型的阴影检测方法[J]. 计算机应用, 2021, 41(7): 2076-2081.