基于感興趣區(qū)域和HOG-MBLBP特征的交通標識檢測
doi: 10.11999/JEIT150918 cstr: 32379.14.JEIT150918
基金項目:
國家自然科學基金(61273277, 61203261)，山東省自然科學基金(ZR2011FM032, ZR2012FQ003)，高等學校博士學科點專項科研基金(20130131110038)
Traffic Sign Detection Based on Regions of Interest and HOG-MBLBP Features
Funds:
The National Natural Science Foundation of China (61273277, 61203261), Shandong Province Natural Science Foundation (ZR2011FM032, ZR2012FQ003), Specialized Research Fund for the Doctoral Program of Higher Education (20130131110038)
-
摘要: 交通標識檢測中樣本類別間的不平衡常常導致分類器的檢測性能弱化，為了克服這一問題，該文提出一種基于感興趣區(qū)域和HOG-MBLBP融合特征的交通標識檢測方法。首先采用顏色增強技術(shù)分割提取出自然背景中交通標識所在的感興趣區(qū)域；然后對標識樣本庫提取HOG-MBLBP融合特征，并用遺傳算法對SVM交叉驗證進行參數(shù)的優(yōu)化選取，以此來訓練和提升SVM分類器性能；最后將提取的感興趣區(qū)域圖像的HOG-MBLBP特征送入訓練好的SVM多分類器，進行進一步的精確檢測和定位，剔除誤檢區(qū)域。在自建的中國交通標識樣本庫上進行了實驗，結(jié)果表明所提方法能達到99.2%的分類準確度，混淆矩陣結(jié)果也表明了該方法的優(yōu)越性。
-
關(guān)鍵詞:
- 交通標識檢測 /
- 感興趣區(qū)域 /
- HOG描述子 /
- LBP描述子 /
- 支持向量機(SVM)
Abstract: The imbalance between sample categories in traffic sign detection often results in the weakening of classification detection performance. To overcome this problem, a traffic sign detection method is proposed based on regions of interest and Histogram of Oriented Gradient and Multi-radius Block Local Binary Pattern (HOG-MBLBP) features. First, the color enhancement technology is used to segment and extract the regions of interest of the traffic signs captured in the natural background. Then HOG-MBLBP fusion features are extracted from traffic signs sample library. Moreover, genetic algorithm is used to optimize the parameters of Support Vector Machine (SVM) through cross-validation so as to train and promote SVM classifier performance. Finally, extracted HOG-MBLBP features of interest region images are put into the trained SVM multi-classifiers for further accurate detection and localization. By this method, the paper achieves the purpose of excluding false positives area. The experiments are carried out on the self-built Chinese traffic sign sample library, experimental results show that the proposed method can achieve 99.2% of classification accuracy, and the confusion matrix results also show the superiority of the proposed method. -
劉華平, 李建民, 胡曉林, 等. 動態(tài)場景下的交通標識檢測與識別研究進展[J]. 中國圖象圖形學報, 2013, 18(5): 493-503. LIU Huaping, LI Jianmin, HU Xiaolin, et al. Recent progress in detection and recognition of the traffic signs in dynamic scenes[J]. Journal of Image and Graphics, 2013, 18(5): 493-503. 常發(fā)亮, 黃翠, 劉成云, 等. 基于高斯顏色模型和SVM的交通標志檢測[J]. 儀器儀表學報, 2014, 35(1): 43-49. CHANG Faliang, HUANG Cui, LIU Chengyun, et al. Traffic sign detection based on Gaussian color model and SVM[J]. Chinese Journal of Scientific Instrument, 2014, 35(1): 43-49. MALDONADO-BASCON S, LAFUENTE-ARROYO S, GIL-JIMENEZ P, et al. Road-sign detection and recognition based on support vector machines[J]. IEEE Transactions on Intelligent Transportation Systems, 2007, 8(2): 264-278. doi: 10.1109/TITS.2007.895311. 徐迪紅, 唐爐亮. 基于顏色和標志邊緣特征的交通標志檢測[J].武漢大學學報(信息科學版), 2008, 33(4): 433-436. XU Dihong and TANG Luliang. Traffic sign detection based on color and boundary feature[J].Geomatics and Information Science of Wuhan University, 2008, 33(4): 433-436. GARCIA-GARRIDO M A, SOTELO M A, and MARTIN- GOROSTIZA E. Fast road sign detection using hough transform for assisted driving of road vehicles[C]. Proceedings of 10th International Conference on Computer Aided Systems Theory, Berlin, 2005: 543-548. HOFERLIN B and ZIMMERMANN K. Towards reliable traffic sign recognition[C]. Proceedings of the IEEE Intelligent Vehicles Symposium, Xian, 2009: 324-329. KHAN J F, BHUIYAN S, and ADHAMI R R. Image segmentation and shape analysis for road-sign detection[J]. IEEE Transactions on Intelligent Transportation Systems, 2011, 12(1): 83-96. doi: 10.1109/TITS.2010.2073466. CARAFFI C, CARDARELLI E, MEDICI P, et al. An algorithm for Italian de-restriction signs detection[C]. Proceedings of the IEEE Intelligent Vehicles Symposium, Eindhoven, 2008: 834-840. ZAKLOUTA F and STANCIULESCU B. Real-time traffic sign recognition in three stages[J]. Robotics and Autonomous System, 2014, 62(1): 16-24. doi: 10.1016/j.robot.2012.07.019. LIU C, CHANG F, and CHEN Z. Rapid multiclass traffic sign detection in high-resolution images[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(6): 2394-2403. doi: 10.1109/TITS.2014.2314711. 潘泓, 李曉兵, 金立左, 等. 一種基于二值粒子群優(yōu)化和支持向量機的目標檢測算法[J]. 電子與信息學報, 2011, 33(1): 117-121. doi: 10.3724/SP.J.1146.2010.00260. PAN Hong, LI Xiaobing, JIN Lizuo, et al. A binary particle swarm optimization and support vector machine-based algorithm for object detection[J]. Journal of Electronics Information Technology, 2011, 33(1): 117-121. doi: 10.3724/ SP.J.1146.2010.00260. 李駿揚, 金立左, 費樹岷, 等. 基于多尺度特征表示的城市道路檢測[J]. 電子與信息學報, 2014, 36(11): 2578-2585. doi: 10.3724/SP.J.1146.2014.00271. LI Junyang, JIN Lizuo, FEI Shumin, et al. Urban road detection based on multi-scale feature representation[J]. Journal of Electronics Information Technology, 2014, 36(11): 2578-2585. doi: 10.3724/SP.J.1146.2014.00271. LILLO-CASTELLANO J M, MORA-JIMENEZ I, FIGUERA- POZUELO C, et al. Traffic sign segmentation and classification using statistical learning methods[J]. Neurocomputing, 2015, 153: 286-299. doi: 10.1016/ j.neucom. 2014. 11.026. SALTI S, PETRELLI A, TOMBARI F, et al. Traffic sign detection via interest region extraction[J]. Pattern Recognition, 2015, 48(4): 1039-1049. doi: 10.1016/ j.patcog. 2014.05.017. RUTA A, LI Y, and LIU X. Real-time traffic sign recognition from video by class-specific discriminative features[J]. Pattern Recognition, 2010, 43(1): 416-430. doi: 10.1016/j. patcog.2009.05.018. RUTA A, PORIKLI F, WATANABE S, et al. In-vehicle camera traffic sign detection and recognition[J]. Machine Vision and Applications, 2011, 22(2): 359-375. doi: 10.1007/ s00138-009-0231-x. DALAL N and TRIGGS B. Histograms of oriented gradients for human detection[C]. Proceedings of the International Conference on Computer Vision and Pattern Recognition, Beijing, 2005: 886-893. OJALA T, PIETIKAINEN M, and MAENPAA T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987. doi: 10.1109/TPAMI.2002.1017623. WANG X, HAN T X, and YAN S. An HOG-LBP human detector with partial occlusion handling[C]. Proceedings of 12th IEEE International Conference on Computer Vision, Kyoto, 2009: 32-39. 陳龍, 潘志敏, 毛慶洲, 等. 利用HOG-LBP自適應融合特征實現(xiàn)禁令交通標志檢測[J]. 武漢大學學報(信息科學版), 2013, 38(2): 191-194. CHEN Long, PAN Zhimin, MAO Qingzhou, et al. HOG-LBP adaptable fused features based method for forbidden traffic signs detection[J]. Geomatics and Information Science of Wuhan University, 2013, 38(2): 191-194. CORTES C and VAPNIK V. Support-vector network[J]. Machine Learning, 1995, 20(3): 273-297. doi: 10.1023/ A:1022627411411. 劉志強, 呂學, 張利. 基于多分類GA-SVM的高速公路AID模型[J]. 系統(tǒng)工程理論與實踐, 2013, 33(8): 2110-2115. LIU Zhiqiang, L Xue, and ZHANG Li. Highway automatic incident detection based on multi-class classification and GA-SVM[J]. Systems Engineering-Theory Practice, 2013, 33(8): 2110-2115. -
計量
- 文章訪問數(shù): 1814
- HTML全文瀏覽量: 138
- PDF下載量: 393
- 被引次數(shù): 0
下載:
