基于特征融合的车型检测新算法

doi:10.13229/j.cnki.jdxbgxb20170934

摘要/Abstract

摘要： 为提高车型检测速度与精确度,本文首先通过对HOG特征进行改进,提出了分层HOG对称算法,得到了分层的HOG对称特征,并将该特征与LBP特征结合,获得二者的融合特征;然后,将融合特征作为支持向量机(SVM)分类器的训练样本,采用主成分分析(PCA)法约减维数降低分类器的复杂程度;最后,使用SVM对车辆外型特征进行检测,获得检测结果。仿真实验数据表明:该算法提高了特征提取的速度,并改善了特征检测的精度,使原始车辆图像的检测实时性得到提升;处理速度均值为26.2帧/s,准确率均值达到94.58%,比传统的HOG特征提高了7.98%。本文方法能有效提高车型检测检测的正确率,减少高维特征带来的计算时间消耗。

关键词: 计算机应用, 车型检测, HOG特征, LBP特征, 特征提取, 主成分分析, 支持向量机

Abstract: To increase the speed and accuracy of vehicle recognition, an improved hierarchical Histogram of Oriented Gradient (HOG) symmetry algorithm was proposed. First, the HOG features are improved to get the hierarchical HOG symmetry features which are fused with Local Binary Pattern (LPB) features to get the fusion features. Second, the fusion features are taken as the training sample of Support Vector Machine (SVM) classifier. Meanwhile, the Principal Component Analysis (PCA) is used to reduce the dimensions for decreasing the complexity of the classifier. Finally, the SVM is used to recognize the appearance features of the vehicle. Simulation results show that the proposed vehicle type recognition algorithm can not only increase the feature extraction speed but also improve the detection accuracy, enhancing the real-time recognition of original vehicle images. The mean processing speed is about 26.2 frames/s and the accuracy is about 94.58%, increasing by 7.98% in comparison to traditional HOG feature extraction algorithm. The method can effectively increase the accuracy of vehicle recognition and also reduce the computing time caused by high dimensional features.

Key words: computer application, vehicle type recognition, HOG feature, LBP feature, feature extraction, principal component analysis(PCA), support vector machine(SVM)

中图分类号:

TP391.4

耿庆田, 于繁华, 王宇婷, 高琦坤. 基于特征融合的车型检测新算法[J]. 吉林大学学报(工学版), 2018, 48(3): 929-935.

GENG Qing-tian, YU Fan-hua, WANG Yu-ting, GAO Qi-kun. New algorithm for vehicle type detection based on feature fusion[J]. 吉林大学学报(工学版), 2018, 48(3): 929-935.

参考文献

[1] He H, Mao C Q, Pan H Y, et al.Vehicle detection system based on magnetoresistive sensor[J]. App- lied Mechanics & Materials, 2015, 743:277-280.
[2] Wang P, Li X, Lv Z, et al.Vehicle outline detect- ion based on improved SIFT algorithm[J]. Intern- ational Journal of Earth Sciences & Engineering, 2015, 8(1): 396-400.
[3] Mu K, Hui F, Zhao X, et al.Multiple vehicle de- tection and tracking in highway traffic surveyance video based on SIFT feature matching[J]. Journal of Information Processing Systems, 2016,12(2): 183-195.
[4] Abadi E A J, Amiri S A, Goharimanesh M, et al. Vehicle model recognition based on using image processing and wavelet analysis[J]. International Journal on Smart Sensing & Intelligent Systems, 2015,29(9): 156-161.
[5] Song M.Vehicle model recognition based on SURF[J]. Journal of Information & Computational Science, 2015,12(17): 6249-6256.
[6] 魏小鹏, 于万波, 金一粟. 奇异值方法用于汽车车型识别[J].中国图象图形学报, 2003, 8(1): 50-53.
Wei Xiao-peng, Yu Wan-bo, Jin Yi-su, et al.Car shape recognition based on matrix singular value[J]. Journal of Image & Graphics, 2003, 8(1): 50-53.
[7] He D, Lang C, Zhang C, et al.Vehicle detection and classification based on convolutional neural network[C]∥ACM International Conference on Internet Multimedia Computing and Service, New York, 2015: 3-8.
[8] Hsieh J W, Chen L C, Chen D Y, et al.Symmetrical SURF and its applications to vehicle detect- ion and vehicle make and model recognition[J]. Transactions on Intelligent Transportation Systems,IEEE, 2014, 15(1): 6-20.
[9] Mejia-Inigo R, Barilla-Perez M E, Montes-Ven- egas H A, et al. Color-based texture image seg- mentation for vehicle detection[C]∥IEEE International Conference on Electrical Engineering, Computing Science and Automatic Control, cce. New York, 2011:1-6.
[10] 王丹, 张祥合. 基于HOG和SVM的人体行为仿生识别方法[J]. 吉林大学学报:工学版, 2013, 43(增刊1):489-492.
Wang Dan, Zhang Xiang-he.Biomimetic recognition method of human behavior based on HOG and SVM[J]. Journal of Jilin University(Engineering and Technology Edition), 2013, 43(Sup.1): 489-492.
[11] 李宗民, 公绪超, 刘玉杰,等. 多特征联合建模的视频对象分割技术研究[J]. 计算机学报, 2013, 36(11): 2356-2363.
Li Zong-min,Gong Xu-chao,Liu Yu-jie, et al.Video object segmentation research based on features joint modeling[J]. Chinse Journal of Computers, 2013, 36(11): 2356-2363.
[12] 王莹, 李文辉, 傅博,等. 基于水平分量优先原则的RDW-LBP人脸识别算法[J]. 吉林大学学报:工学版, 2011, 41(3): 750-757.
Wang Ying, Li Wen-hui, Fu Bo, et al.Face recognition algorithm using RDW-LBP based on horizontal component prior principle[J]. Journal of Jilin University(Engineering and Technology Edition), 2011, 41(3): 750-757.
[13] 于海琦, 刘真, 田全慧, 等. 一种基于GA-BP神经网络结合PCA的LCD显示器光谱特征化模型[J]. 液晶与显示, 2016, 31(2): 201-207.
Yu Hai-qi, Liu Zhen, Tian Quan-hui, et al.Spectral characterization model of liquid crystal display based on GA-BP neural network and PCA[J]. Chinese Journal of Liquid Crystals and Displays, 2016, 31(2): 201-207.
[14] 黄璇, 郭立红, 李姜, 等. 磷虾群算法优化支持向量机的威胁估计[J]. 光学精密工程, 2016, 24(6): 1448-1454.
Huang Xuan, Guo Li-hong, Li Jiang, et al.Threat assessment of SVM optimized by Krill Herd algorithm[J].Opt Precision Eng, 2016, 24(6): 1448-1454.
[15] 林琳, 陈虹, 陈建, 等. 基于多核SVM-GMM的短语音说话人识别[J]. 吉林大学学报:工学版, 2013, 43(2): 504-509.
Lin Lin, Chen Hong, Chen Jian, et al.Speaker recognition with short utterances based on multiple kernel SVM-GMM[J]. Journal of Jilin University(Engineering and Technology Edition), 2013, 43(2): 504-509.
[16] 孙轶轩, 邵春福, 岳昊,等. 基于SVM灵敏度的城市交通事故严重程度影响因素分析[J]. 吉林大学学报:工学版, 2014, 44(5): 1315-1320.
Sun Yi-xuan, Shao Chun-fu,Yue Hao, et al.Urban traffic accident severity analysis based on sensitivity analysis of SVM[J]. Journal of Jilin University(Engineering and Technology Edition), 2014, 44(5): 1315-1320.
[17] 代琨,于宏毅,仇文博,等. 基于SVM的网络数据无监督特征选择算法[J]. 吉林大学学报:工学版, 2015, 45(2): 576-582.
Dai Kun, Yu Hong-yi, Qiu Wen-bo, et al.Unsupervised feature selection algorithm based on support vector machine for network data[J]. Journal of Jilin University(Engineering and Technology Edition),2015,45(2):576-582.

相关文章 15

[1]	刘富,宗宇轩,康冰,张益萌,林彩霞,赵宏伟. 基于优化纹理特征的手背静脉识别系统[J]. 吉林大学学报(工学版), 2018, 48(6): 1844-1850.
[2]	王利民,刘洋,孙铭会,李美慧. 基于Markov blanket的无约束型K阶贝叶斯集成分类模型[J]. 吉林大学学报(工学版), 2018, 48(6): 1851-1858.
[3]	金顺福,王宝帅,郝闪闪,贾晓光,霍占强. 基于备用虚拟机同步休眠的云数据中心节能策略及性能[J]. 吉林大学学报(工学版), 2018, 48(6): 1859-1866.
[4]	赵东,孙明玉,朱金龙,于繁华,刘光洁,陈慧灵. 结合粒子群和单纯形的改进飞蛾优化算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1867-1872.
[5]	刘恩泽,吴文福. 基于机器视觉的农作物表面多特征决策融合病变判断算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1873-1878.
[6]	隗海林, 包翠竹, 李洪雪, 李明达. 基于最小二乘支持向量机的怠速时间预测[J]. 吉林大学学报(工学版), 2018, 48(5): 1360-1365.
[7]	欧阳丹彤, 范琪. 子句级别语境感知的开放信息抽取方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1563-1570.
[8]	刘富, 兰旭腾, 侯涛, 康冰, 刘云, 林彩霞. 基于优化k-mer频率的宏基因组聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1593-1599.
[9]	刘哲, 徐涛, 宋余庆, 徐春艳. 基于NSCT变换和相似信息鲁棒主成分分析模型的图像融合技术[J]. 吉林大学学报(工学版), 2018, 48(5): 1614-1620.
[10]	车翔玖, 王利, 郭晓新. 基于多尺度特征融合的边界检测算法[J]. 吉林大学学报(工学版), 2018, 48(5): 1621-1628.
[11]	桂春, 黄旺星. 基于改进的标签传播算法的网络聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1600-1605.
[12]	刘元宁, 刘帅, 朱晓冬, 陈一浩, 郑少阁, 沈椿壮. 基于高斯拉普拉斯算子与自适应优化伽柏滤波的虹膜识别[J]. 吉林大学学报(工学版), 2018, 48(5): 1606-1613.
[13]	张曼, 施树明. 典型汽车运行工况的状态转移特征分析[J]. 吉林大学学报(工学版), 2018, 48(4): 1008-1015.
[14]	曹洁, 苏哲, 李晓旭. 基于Corr-LDA模型的图像标注方法[J]. 吉林大学学报(工学版), 2018, 48(4): 1237-1243.
[15]	赵宏伟, 刘宇琦, 董立岩, 王玉, 刘陪. 智能交通混合动态路径优化算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1214-1223.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed