›› 2018,Vol. 33 ›› Issue (2): 335-350.doi: 10.1007/s11390-018-1822-7

所属专题: Artificial Intelligence and Pattern Recognition

• Artificial Intelligence and Pattern Recognition • 上一篇    下一篇

基于局部加强PCAnet神经网络的细粒度车型识别方法

Qian Wang1,2,3, You-Dong Ding3,4, Senior Member, CCF   

  1. 1 School of Computer Engineering and Science, Shanghai University, Shanghai 200072, China;
    2 Information Center, Criminal Investigation Department of Shanghai Public Security Bureau, Shanghai 200083, China;
    3 Shanghai Engineering Research Center of Motion Picture Special Effects, Shanghai 200072, China;
    4 Shanghai Film Academy, Shanghai University, Shanghai 200072, China
  • 收稿日期:2016-10-11 修回日期:2017-11-20 出版日期:2018-03-05 发布日期:2018-03-05
  • 作者简介:Qian Wang is a senior engineer in Information Center of Criminal Investigation Department of Shanghai Public Security Bureau, Shanghai, and also a Ph.D. candidate of School of Computer Engineering and Science, Shanghai University, Shanghai. Her research interests mainly include intelligent surveillance analysis, deep learning neural network, and intelligent human biological characteristic identification

A Novel Fine-Grained Method for Vehicle Type Recognition Based on the Locally Enhanced PCANet Neural Network

Qian Wang1,2,3, You-Dong Ding3,4, Senior Member, CCF   

  1. 1 School of Computer Engineering and Science, Shanghai University, Shanghai 200072, China;
    2 Information Center, Criminal Investigation Department of Shanghai Public Security Bureau, Shanghai 200083, China;
    3 Shanghai Engineering Research Center of Motion Picture Special Effects, Shanghai 200072, China;
    4 Shanghai Film Academy, Shanghai University, Shanghai 200072, China
  • Received:2016-10-11 Revised:2017-11-20 Online:2018-03-05 Published:2018-03-05
  • Contact: 10.1007/s11390-018-1822-7
  • About author:Qian Wang is a senior engineer in Information Center of Criminal Investigation Department of Shanghai Public Security Bureau, Shanghai, and also a Ph.D. candidate of School of Computer Engineering and Science, Shanghai University, Shanghai. Her research interests mainly include intelligent surveillance analysis, deep learning neural network, and intelligent human biological characteristic identification

本文立足于图像分类中的细粒度分类问题,提出了能实现车辆细分类的基于局部加强PCANET神经网络算法。该算法使用层级少、参数简单的PCANET无监督网络,实现了算法简单、人工标记简便、训练时间少的车型识别应用。经实验测试表明,PCANET方法较之传统法模式识别和多层级CNN神经网络,在样本库量级变化、角度偏移、训练速度各方面测试中获得了最佳平衡;正确局部特征的选取、加入与整体特征不同尺度的局部特征对识别率上升起到了很重要的加成作用;而7(12角度)角度样本建模方案,被证明是解决实践中角度偏移导致识别率下降问题行之有效的方案。

Abstract: In this paper, we propose a locally enhanced PCANet neural network for fine-grained classification of vehicles. The proposed method adopts the PCANet unsupervised network with a smaller number of layers and simple parameters compared with the majority of state-of-the-art machine learning methods. It simplifies calculation steps and manual labeling, and enables vehicle types to be recognized without time-consuming training. Experimental results show that compared with the traditional pattern recognition methods and the multi-layer CNN methods, the proposed method achieves optimal balance in terms of varying scales of sample libraries, angle deviations, and training speed. It also indicates that introducing appropriate local features that have different scales from the general feature is very instrumental in improving recognition rate. The 7-angle in 180° (12-angle in 360°) classification modeling scheme is proven to be an effective approach, which can solve the problem of suffering decrease in recognition rate due to angle deviations, and add the recognition accuracy in practice.

[1] Simonyan K, Parkhi O, Vedaldi A et al. Fisher vector faces in the wild. In Proc. Conf. British Machine Vision, September 2013.

[2] Berg T, Belhumeur P N. POOF:Part-based one-vs-one features for fine-grained categorization, face verification, and attribute estimation. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2013, pp.955-962.

[3] Cao Q, Ying Y, Li P. Similarity metric learning for face recognition. In Proc. IEEE Int. Conf. Computer Vision, January 2013, pp.2408-2415.

[4] Sun Y, Wang X, Tang X. Deep learning face representation from predicting 10000 classes. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2014, pp.1891-1898.

[5] Sun Y, Chen Y, Wang X et al. Deep learning face representation by joint identification-verification. In Proc. Int. Conf. Neural Information Processing Systems, November 2015, pp.1988-1996.

[6] Feris R S, Siddiquie B, Petterson J et al. Large-scale vehicle detection, indexing, and search in urban surveillance videos. IEEE Trans. Multimedia, 2012, 14(1):28-42.

[7] Hu C, Bai X, Qi L et al. Learning discriminative pattern for real-time car brand recognition. IEEE Trans. Intelligent Transportation Systems, 2015, 16(6):3170-3181.

[8] Grauman K, Crandall D, Parikh D et al. Discovering localized attributes for fine-grained recognition. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2012, pp.3474-3481.

[9] Wah C, Horn G V, Branson S et al. Similarity comparisons for interactive fine-grained categorization. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2014, pp.859-866.

[10] Goering C, Rodner E, Freytag A et al. Nonparametric part transfer for fine-grained recognition. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2014, pp.2489-2496.

[11] Krause J, Deng J, Stark M et al. Collecting a large-scale dataset of fine-grained cars. In Proc. the 2nd Fine-Grained Visual Categorization Workshop, June 2013.

[12] Yang L, Luo P, Chen C L et al. A large-scale car dataset for fine-grained categorization and verification. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2015, pp.3973-3981.

[13] Krause J, Stark M, Deng J et al. 3D object representations for fine-grained categorization. In Proc. IEEE Int. Conf. Computer Vision, June 2013, pp.554-561.

[14] Lin Y L, Morariu V I, Hsu W et al. Jointly optimizing 3D model fitting and fine-grained classification. In Proc. European Conference on Computer Vision, September 2014, pp.466-480.

[15] Stark M, Krause J, Pepik B et al. Fine-grained categorization for 3D scene understanding. In Proc. Conf. British Machine Vision, September 2012, pp.228-236.

[16] Sochor J, Herout A, Havel J. BoxCars:3D boxes as CNN input for improved fine-grained vehicle recognition. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2016, pp.3006-3015.

[17] Zhang X, Zhou F, Lin Y et al. Embedding label structures for fine-grained feature representation. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2016, pp.1114-1123.

[18] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. In Proc. Int. Conf. Neural Information Processing Systems, November 2012, pp.1097-1105.

[19] He H, Shao Z, Tan J. Recognition of car makes and models from a single traffic-camera image. IEEE Trans. Intelligent Transportation Systems, 2015, 16(6):3182-3192.

[20] Chan T H, Jia K, Gao S et al. PCANet:A simple deep learning baseline for image classification? IEEE Trans. Image Processing, 2014, 24(12):5017-5032.

[21] Dong Z, Wu Y, Pei M et al. Vehicle type classification using a semi supervised convolutional neural network. IEEE Trans. Intelligent Transportation Systems, 2015, 16(4):2247-2256.

[22] Xie S, Yang T, Wang X et al. Hyper-class augmented and regularized deep learning for fine-grained image classification. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2015, pp.2645-2654.

[23] Zhao B, Wu X, Feng J et al. Diversified visual attention networks for fine-grained object classification. IEEE Trans. Multimedia, 2017, 19(6):1245-1256.

[24] Zia M Z, Stark M, Schindler K. Towards scene understanding with detailed 3D object representations. International Journal of Computer Vision, 2015, 112(2):188-203.

[25] Arandjelovic R, Zisserman A. Three things everyone should know to improve object retrieval. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2012, pp.2911-2918.

[26] Dalal N, Triggs B. Histograms of oriented gradients for human detection. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2005, pp.886-893.

[27] Chen T, Chen Z, Shi Q et al. Road marking detection and classification using machine learning algorithms. In Proc. Intelligent Vehicles Symp., June 2015, pp.617-621.

[28] Wang X S, Cai C. Weed seeds classification based on PCANet deep learning baseline. In Proc. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, December 2015, pp.408-415.

[29] Wu J, Shi J, Li Y et al. Histopathological image classification using random binary hashing based PCANet and bilinear classifier. In Proc. Conf. European Signal Processing, August 2016, pp.2050-2054.

[30] Xia Y, Li J, Qi L et al. Loop closure detection for visual SLAM using PCANet features. In Proc. Int. Conf. Neural Networks, July 2016, pp.2274-2281.

[31] Jia H, Sun Q, Wang T. PCANet for blind image quality assessment. In Proc. Int. Conf. Computational Intelligence and Security, December 2015, pp.195-198.

[32] Kwang K, Keechul J, Hang J K. Face recognition using kernel principal component analysis. IEEE Signal Processing Letters, 2002, 9(2):40-42.

[33] Szegedy C, Liu W, Jia Y et al. Going deeper with convolutions. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2014.
No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 李卫东; 魏道政;. Test Derivation Through Critical Path Transitions[J]. , 1992, 7(1): 12 -18 .
[2] 张钹; 张铃;. On Memory Capacity of the Probabilistic Logic Neuron Network[J]. , 1993, 8(3): 62 -66 .
[3] 王晖; 刘大有; 王亚飞;. Sequential Back-Propagation[J]. , 1994, 9(3): 252 -260 .
[4] 熊志国; 徐曦; 董士海;. CX11: A Chinese Language Supporting Interface for X Window Environment[J]. , 1995, 10(1): 15 -22 .
[5] 应明生;. Putting Consistent Theories Together in Institutions[J]. , 1995, 10(3): 260 -266 .
[6] 虞慧群; 孙永强;. Hybridity in Embedded Computing Systems[J]. , 1996, 11(1): 90 -96 .
[7] 章寅; 许卓群;. Concurrent Manipulation of Expanded AVL Trees[J]. , 1998, 13(4): 325 -336 .
[8] Gerard Boudol;. Calculi for Concurrent Processes[J]. , 1998, 13(6): 509 .
[9] 詹永照; 宋顺林; 谢立;. Demand Priority Protocol Simulation and Evaluation[J]. , 1999, 14(6): 599 -605 .
[10] 陶仁骥; 陈世华;. Constructing Finite Automata with Invertibility by transformation Method[J]. , 2000, 15(1): 10 -26 .
版权所有 © 《计算机科学技术学报》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn
总访问量: