车辆图像稀疏特征表示及其监控视频应用

doi:10.13190/j.jbupt.2016.s.019

北京邮电大学学报 ›› 2016, Vol. 39 ›› Issue (s1): 81-86.doi: 10.13190/j.jbupt.2016.s.019

车辆图像稀疏特征表示及其监控视频应用

陈湘军^1,2, 阮雅端¹, 陈启美¹, 叶飞跃²

1. 南京大学电子科学与工程学院, 南京 210046;
2. 江苏理工学院计算机工程学院, 江苏常州 213001

收稿日期:2015-09-06 出版日期:2016-06-28 发布日期:2016-06-28
作者简介:陈湘军(1977-),男,博士生,E-mail:xiangba@21cn.com;陈启美(1949-),男,教授,博士生导师.
基金资助:
国家自然科学基金项目（61472166，61105015）；江苏省科技厅项目（BE2011747）；常州市应用基础研究基金项目（CJ20120021）

Sparse Representation of Vehicle Image and Its' Application in Surveillance Video

CHEN Xiang-jun^1,2, RUAN Ya-duan¹, CHEN Qi-mei¹, YE Fei-yue²

1. School of Electronic Science and Engineering, Nanjing University, Nanjing 210046, China;
2. School of Computer Engineering, Jiangsu University of Technology, Jiangsu Changzhou 213001, China

Received:2015-09-06 Online:2016-06-28 Published:2016-06-28

摘要/Abstract

摘要：

针对传统车辆图像特征在复杂场景下响鲁棒性和泛化能力低的问题，提出了车辆图像稀疏特征表示方法，并实现了基于稀疏特征的车辆图像支持向量机线性分类器，构建了基于稀疏特征和背景建模的监控车辆分类识别应用框架.与传统方法相比，该方法将车辆图像表示成字典集的低维稀疏线性组合，提高了特征表示泛化能力，能适应实时性监控视频分析的需求.实验结果表明，基于稀疏特征的车辆识别准确率比传统方法明显提升，并在低分辨率、阴影、遮挡等复杂场景下有较好的鲁棒性.

关键词: 特征表示, 稀疏学习, 车辆分类与识别, 鲁棒性与泛化性, 智能交通系统

Abstract:

Typical vehicle image feature will lost robustness and generalization ability under complex scene. To deal with this problem, sparse based vehicle images feature representation was introduced and a linear vehicles support vector machine classifier based on the sparse representation was proposed. Then, a framework of vehicle classification and recognition on surveillance video was constructed based on the background subtraction and sparse represented feature. Compared with traditional methods, vehicle images are represented as linear combination of the sparse coefficient of a learned dictionary (atom or base) in low dimension in our method, and sparse represented feature gains higher generalization capability with less computational complexity. Experiment shows that this work exhibits better classification accuracy and robustness under complex real environment with decrease image quality of low resolution, shadow and occlusion.

Key words: feature representation, sparse learning, vehicle classification and recognition, robustness and generalization, intelligent transportation system

中图分类号:

TP391.4

陈湘军, 阮雅端, 陈启美, 叶飞跃. 车辆图像稀疏特征表示及其监控视频应用[J]. 北京邮电大学学报, 2016, 39(s1): 81-86.

CHEN Xiang-jun, RUAN Ya-duan, CHEN Qi-mei, YE Fei-yue. Sparse Representation of Vehicle Image and Its' Application in Surveillance Video[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2016, 39(s1): 81-86.

参考文献

[1] Pang Yanwei, Yuan Yuan, Li Xuelong, et al. Efficient HOG human detection[J]. Signal Processing, 2011, 91(4):773-781.
[2] Yang Jianchao, Yu Kai, Gong Yihong, et al. Linear spatial pyramid matching using sparse coding for image classification[C]//Computer Vision and Pattern Recognition, 2009. IEEE Conference on. 2009:1794-1801.
[3] Wang Jinjun, Yang Jianchao, Yu Kai, et al. Locality-constrained linear coding for image classification[C]//Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on. 2010:3360-3367.
[4] Zhuang Bohan, Lu Huchuan, Xiao Ziyang, et al. Visual tracking via discriminative sparse similarity map[J]. 2014,23(4):1872-1881.
[5] Sivaraman, Sayanan, Mohan M Trivedi. A general active-learning framework for on-road vehicle recognition and tracking[J]. Intelligent Transportation Systems, IEEE Transactions on, 2010, 11(2):267-276.
[6] Aharon Michal, Michael Elad, Alfred Bruckstein. K-svd:an algorithm for designing overcomplete dictionaries for sparse representation[J]. Signal Processing, IEEE Transactions on, 2006, 54(11):4311-4322.
[7] Mairal Julien, Francis Bach, Jean Ponce, et al. Online learning for matrix factorization and sparse coding[J]. The Journal of Machine Learning Research, 2010(11):19-60.
[8] Stauffer, Chris, W Eric L Grimson. Adaptive background mixture models for real-time tracking[C]//Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on. 1999:242-252.
[9] Zivkovic, Zoran. Improved adaptive Gaussian mixture model for background subtraction[C]//Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17^th International Conference on. 2004:28-31.
[10] KaewTraKul Pong, Pakorn, Richard Bowden. An improved adaptive background mixture model for real-time tracking with shadow detection[M]. Video-Based Surveillance Systems. US:Springer, 2002:135-144.
[11] Comaniciu Dorin, Visvanathan Ramesh, Peter Meer. Real-time tracking of non-rigid objects using mean shift[C]//Computer Vision and Pattern Recognition, 2000. Proceedings of IEEE Conference on. 2000:142-149.
[12] Ristic Branko, Sanjeev Arulampalam, Neil James Gordon. Beyond the Kalman filter:particle filters for tracking applications[M]. US:Artech House, 2004.
[13] Okuma Kenji, Ali Taleghani, Nando De Freitas, et al. A boosted particle filter:Multitarget detection and tracking[M]. Computer Vision-ECCV 2004. Berlin Heidelberg:Springer, 2004:28-39.
[14] Zivkovic, Zoran, Ferdinand van der Heijden. Efficient adaptive density estimation per image pixel for the task of background subtraction[J]. Pattern recognition letters, 2006, 27(7):773-780.
[15] Chang Chih-Chung, Lin Chih-Jen. LIBSVM:a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3):27.

车辆图像稀疏特征表示及其监控视频应用

Sparse Representation of Vehicle Image and Its' Application in Surveillance Video

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

本文评价

[1]	张小乾, 王潇, 薛旭倩, 谈振, 蒲磊. 基于加权多核子空间聚类的图像分割方法[J]. 北京邮电大学学报, 2023, 46(3): 78-83.
[2]	王铭, 林贝贝, 张顺利. 基于帧级-时空双分支网络的步态识别方法[J]. 北京邮电大学学报, 2023, 46(3): 73-77.
[3]	常霄, 黄智濒, 禹旻, 杨武兵. 一种适用于航天大数据的深度决策树算法[J]. 北京邮电大学学报, 2023, 46(3): 1-6.
[4]	李超然谢磊. 基于振动感知的按键识别技术[J]. 北京邮电大学学报, 0, (): 0-0.
[5]	叶洪滨林政宽程红举. 基于多相机特征融合的行人检测算法研究[J]. 北京邮电大学学报, 0, (): 0-0.
[6]	胡敏熊思黄宏程张光华王春芳. 基于RAPNet的脑肿瘤MRI图像三维分割[J]. 北京邮电大学学报, 2023, 46(2): 91-97.
[7]	于天河柳梦瑶. 基于人眼视觉系统的图像质量评价方法[J]. 北京邮电大学学报, 2023, 46(2): 129-136.
[8]	荣震宇刘建毅. 基于Transformer和MLP的眼底血管分割算法[J]. 北京邮电大学学报, 2023, 46(1): 26-31.
[9]	李海燕晁艳静余鹏飞李海江张榆锋. 上下文信息多样聚合的图像修复算法[J]. 北京邮电大学学报, 2023, 46(1): 19-25.
[10]	李锦珑陈琼琼丁志杰刘振宇. 基于面部行为与语音融合特征的重度抑郁识别[J]. 北京邮电大学学报, 2023, 46(1): 32-37.
[11]	宋宇博高嘉振. 改进YOLOv3算法的交通多目标检测方法[J]. 北京邮电大学学报, 2022, 45(5): 103-108.
[12]	张小乾谈振王潇梁芹万黎明. 基于正交投影学习的图像特征提取算法[J]. 北京邮电大学学报, 2022, 45(5): 85-90,128.
[13]	叶康张淑军郭淇李辉崔雪红. 基于CM-Transformer的连续手语识别[J]. 北京邮电大学学报, 2022, 45(5): 49-53,78.
[14]	李阳, 高轼奇. 基于数据增强及注意力机制的肺结节检测系统[J]. 北京邮电大学学报, 2022, 45(4): 25-30.
[15]	王俊洁, 徐聪聪, 赵增瑞, 徐军, 姜祎群. 多分支压缩和激励网络的蕈样肉芽肿细胞分类[J]. 北京邮电大学学报, 2022, 45(4): 31-36.