Traffic sign recognition method based on HOG-Gabor feature fusion and Softmax classifier
-
摘要: 为了提高交通标志识别的正确率和实时性, 提出了一种基于HOG-Gabor特征融合与Softmax分类器的交通标志识别方法。采用Gamma矫正方法提取HOG特征, 采用对比度受限的自适应直方图均衡化方法提取Gabor特征, 基于线性特征融合原理, 将提取的HOG和Gabor特征向量直接串联, 得到刻画交通标志的融合特征向量, 采用Softmax分类器对融合特征向量进行分类, 采用德国交通标志识别基准(GTSRB) 数据库测试了所提方法的有效性, 比较了基于单特征与融合特征的交通标志识别效果。试验结果表明: 在图像增强过程中, 针对HOG特征, 采用Gamma矫正方法的分类正确率最大, 为97.11%, 针对Gabor特征, 采用限制对比度的直方图均衡化方法的分类正确率最大, 为97.54%;采用Softmax分类器的最小分类正确率为97.11%, 耗时小于2s;针对HOG-Gabor融合特征, 采Softmax分类器的识别率高达97.68%, 因此, 基于HOG-Gabor特征融合与Softmax分类器的交通标志识别方法的识别率高, 实时性强。Abstract: In order to improve the accuracy and real-time performance of traffic sign recognition, a traffic sign recognition method was proposed based on HOG-Gabor feature fusion and Softmax classifier. HOG (histogram of oriented gradient) feature was extracted by using the Gamma correction method, and Gabor feature was extracted by using the contrast limited adaptive histogram equalization method. According to the linear feature fusion principle, HOG and Gabor feature vectors were connected to constitute the fusional feature vector for depicting the traffic signs. Theeffectiveness of the proposed method was verified based on the GTSRB (German Traffic Sign Recognition Benchmark) data set. The recognition effects of traffic sign based on single feature and fusional feature were compared. Experimental result shows that in image enhancement, the classification accuracy based on HOG feature is 97.11% and is largest by the Gamma correction method, and the classification accuracy based on Gabor feature is 97.54% and is largest by the contrast limited adaptive histogram equalization method. The minimum classification accuracy is 97.11% by using Softmax classifier, and classification time is only 2 s. The correct recognition rate of traffic sign reaches 97.68% by using the proposed method based on HOG-Gabor fusional features, so the traffic sign recognition method based on HOG-Gabor fusional features and Softmax classifier has high recognition rate and real-time performance.
-
[1] FLEYEH H, DAVAMI E. Eigen-based traffic sign recognition[J]. IET Intelligent Transport Systems, 2011, 5 (3): 190-196. doi: 10.1049/iet-its.2010.0159 [2] LIM K, HONG Y, CHOI Y, et al. Real-time traffic sign recognition based on a general purpose GPU and deeplearning[J]. Plos One, 2017, 12 (3): 1-22. [3] ZAKLOUTA F, STANCIULESCU B. Real-time traffic sign recognition in three stages[J]. Robotics and Autonomous Systems, 2014, 62 (1): 16-24. doi: 10.1016/j.robot.2012.07.019 [4] HUANG Zhi-yong, YU Yuan-long, GU J, et al. An efficient method for traffic sign recognition based on extreme learning machine[J]. IEEE Transactions on Cybernetics, 2017, 47 (4): 920-933. doi: 10.1109/TCYB.2016.2533424 [5] ZENG Yu-jun, XU Xin, SHEN Da-yong, et al. Traffic sign recognition using kernel extreme learning machines with deep perceptual features[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18 (6): 1647-1653. [6] GREENHALGH J, MIRMEHDI M. Real-time detection and recognition of road traffic signs[J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13 (4): 1498-1506. doi: 10.1109/TITS.2012.2208909 [7] WANG Xiao-yu, HAN T X, YAN Shui-cheng. An HOG-LBP human detector with partial occlusion handling[C]∥IEEE. The2009 IEEE 12th International Conference on Computer Vision. New York: IEEE, 2009: 32-39. [8] STALLKAMP J, SCHLIPSING M, SALMEN J, et al. Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition[J]. Neural Networks, 2012, 32 (2): 323-332. [9] WANG Gang-yi, REN Guang-hui, WU Zhi-lu, et al. A hierarchical method for traffic sign classification with support vector machines[C]∥IEEE. The 2013 International Joint Conference on Neural Networks. New York: IEEE, 2013: 1-6. [10] SERMANET P, LECUN Y. Traffic sign recognition with multi-scale convolutional networks[C]∥IEEE. The 2011International Joint Conference on Neural Networks. New York: IEEE, 2011: 2809-2813. [11] SUN Zhan-li, WANG Han, LAU W S, et al. Application of BW-ELM model on traffic sign recognition[J]. Neurocomputing, 2013, 128: 153-159. [12] TANG Sui-sui, HUANG Lin-lin. Traffic sign recognition using complementary features[C]∥IEEE. 2013 2nd IAPR Asian Conference on Pattern Recognition. New York: IEEE, 2013: 210-214. [13] ZHU Ying-ying, WANG Xing-gang, YAO Cong, et al. Traffic sign classification using two-layer image representation[C]∥IEEE. 2013 20th IEEE International Conference on Image Processing. New York: IEEE, 2013: 3755-3759. [14] LU Ke, DING Zheng-ming, GE S. Sparse-representationbased graph embedding for traffic sign recognition[J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13 (4): 1515-1524. doi: 10.1109/TITS.2012.2220965 [15] CIRESAN D, MEIER U, MASCI J, et al. Multi-column deep neural network for traffic sign classification[J]. Neural Networks, 2012, 32: 333-338. doi: 10.1016/j.neunet.2012.02.023 [16] 刘占文, 赵祥模, 李强, 等. 基于图模型与卷积神经网络的交通标志识别方法[J]. 交通运输工程学报, 2016, 16 (5): 122-131. doi: 10.3969/j.issn.1671-1637.2016.05.014LIU Zhan-wen, ZHAO Xiang-mo, LI Qiang, et al. Traffic sign recognition method based on graphical model and convolutional neural network[J]. Journal of Traffic and Transportation Engineering, 2016, 16 (5): 122-131. (in Chinese). doi: 10.3969/j.issn.1671-1637.2016.05.014 [17] 梁琳, 何卫平, 雷蕾, 等. 光照不均图像增强方法综述[J]. 计算机应用研究, 2010, 27 (5): 1625-1628. doi: 10.3969/j.issn.1001-3695.2010.05.006LIANG Lin, HE Wei-ping, LEI Lei, et al. Survey on enhancement methods for non-uniform illumination image[J]. Application Research of Computers, 2010, 27 (5): 1625-1628. (in Chinese). doi: 10.3969/j.issn.1001-3695.2010.05.006 [18] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]∥IEEE. 2005IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2005: 886-893. [19] HYUN J, BAEK J, KIM J, et al. Proposing a fast circular HOG descriptor for detecting rotated objects[C]∥IEEE. The 2015 International Joint Conference on Neural Networks. New York: IEEE, 2015: 1-6. [20] HAGHIGHAT M, ZONOUZ S, ABDEL-MOTTALEB M. CloudID: trustworthy cloud-based and cross-enterprise biometric identification[J]. Expert Systems with Applications, 2015, 42 (21): 7905-7916. doi: 10.1016/j.eswa.2015.06.025 [21] YAO Chang, WU Feng, CHEN Hou-jin, et al. Traffic sign recognition using HOG-SVM and grid search[C]∥IEEE. 12th International Conference on Signal Processing. New York: IEEE, 2014: 962-965. [22] MARTINEZ A M, KAK A C. PCA versus LDA[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23 (2): 228-233. doi: 10.1109/34.908974 [23] MATHIAS M, TIMOFTE R, BENENSON R, et al. Traffic Sign Recognition-How far are we from the solution?[C]∥IEEE. The 2013International Joint Conference on Neural Networks. New York: IEEE, 2013: 1-8. [24] 宋青松, 田正鑫, 孙文磊, 等. 用于孤立数字语音识别的一种组合降维方法[J]. 西安交通大学学报, 2016, 50 (6): 42-46. https://www.cnki.com.cn/Article/CJFDTOTAL-XAJT201606007.htmSONG Qing-song, TIAN Zheng-xin, SUN Wen-lei, et al. Combined dimension reduction method for isolated digital speech recognition[J]. Journal of Xi'an Jiaotong University, 2016, 50 (6): 42-46. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-XAJT201606007.htm [25] STALLKAMP J, SCHLIPSING M, SALMEN J. The german traffic sign recognition benchmark: a multi-class classification competition[C]∥IEEE. The 2011 International Joint Conference on Neural Networks. New York: IEEE, 2011: 2161-4393. [26] CHANG C C, LIN C J. LIBSVM: a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2 (3): 1-27. -
下载:
点击查看大图
图(10) / 表(4)
计量
- 文章访问数: 1007
- HTML全文浏览量: 418
- PDF下载量: 629
- 被引次数: 0
