-
摘要: 针对现有车辆检测算法在实际复杂道路情况下对车辆有效检测率不高的问题, 提出了融合多模式弱分类器, 并以AdaBoost-Bagging集成为强分类器的车辆检测算法。结合判别式模型善于利用较多的特征形成较好决策边界和生成式模型善于利用较少的特征排除大量负样本的优点, 以Haar特征训练判别式弱分类器, 以HOG特征训练生成式弱分类器, 以AdaBoost算法为桥梁, 采用泛化能力强的Bagging学习器集成算法得到AdaBoost-Bagging强分类器, 利用Caltech1999数据库和实际道路图像对检测算法进行了验证。验证结果表明: 相比于单模式弱分类器, AdaBoostBagging强分类器在分类能力和处理时间上均具有优越性, 表现为较高的检测率与较低的误检率, 分别为95.7%、0.000 27%, 每帧图像的检测时间较少, 为25ms; 与传统级联AdaBoost分类器相比, AdaBoost-Bagging强分类器虽然增加了12%的检测时间和30%的训练时间, 但检测率提升了1.8%, 误检率降低了0.000 06%;本文算法的检测性能显著优于基于Haar特征的AdaBoost分类器算法、基于HOG特征的SVM分类器算法、基于HOG特征的DPM分类器算法, 具有较佳的车辆检测效果。
-
关键词:
- 车辆检测 /
- 判别式模型 /
- 生成式模型 /
- 多模式弱分类器 /
- AdaBoost-Bagging分类器
Abstract: Focusing on the problem that the vehicle detection rate of existed vehicle detection algorithms is lower in real complex road environment, a vehicle detection algorithm was proposed, in which multi-model weak classifiers were integrated into strong classifier by using AdaBoost-Bagging method.In the algorithm, discriminative model could generate a fine decision boundary by using more features, and generative model could eliminate negative examples by using fewer features.To combine the advantages of discriminative model and generative model, discriminative classifier with Haar feature and generative classifier with HOG feature were built.Combined with AdaBoost algorithm, AdaBoost-Bagging strong classifier was obtained by using Bagging algorithm that is an integrated learning algorithm with strong generalization ability.Vehicle detection algorithm was tested based on Caltech1999 dataset and real road images.Test result indicates that compared with sole mode weak classifier, AdaBoost-Bagging strong classifier maintains superiority in classification ability and processing time, its high detection rate and low false detection rate are 95.7%, 0.000 27% respectively, and the detection time of each frame is 25 ms that is less.Compared with the traditional cascade AdaBoost classifier, the detection time of the AdaBoost-Bagging strong classifier increases 12%, the training time increases 30%, but the detection rate increases 1.8%, and the false detection rate decreases 0.000 06%.The proposed algorithm is better than other vehicle detection algorithms, including Haar featurebased AdaBoost classifier, HOG feature-based SVM classifier, HOG feature-based DPM classifier, and has better vehicle detection effect. -
图 5 基于弱分类器融合的Bagging强分类器
Figure 5. Bagging strong classifier fused with weak classifiers
表 1 试验1结果
Table 1. Result of test 1
表 2 试验2结果
Table 2. Result of test 2
表 3 试验3结果
Table 3. Result of test 3
-
[1] YOO H, YANG U, SOHN K. Gradient-enhancing conversion for illumination-robust lane detection[J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 14(3): 1083-1094. doi: 10.1109/TITS.2013.2252427 [2] PEDERSOLI M, GONZÀLEZ J, HU X, et al. Toward real-time pedestrian detection based on a deformable template model[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(1): 355-364. doi: 10.1109/TITS.2013.2281207 [3] LIU Qing-hua, CHUNG E, ZHAI Liu-jia. Fusing moving average model and stationary wavelet decomposition for automatic incident detection: case study of Tokyo expressway[J]. Journal of Traffic and Transportation Engineering: English Edition, 2014, 1(6): 404-414. doi: 10.1016/S2095-7564(15)30290-7 [4] VÁZQUEZ D, LÓPEZ A M, MARÍN J, et al. Virtual and real world adaptation for pedestrian detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(4): 797-809. doi: 10.1109/TPAMI.2013.163 [5] 马雷, 臧俊杰, 张润生. 不同光照条件下前方车辆识别方法[J]. 汽车工程, 2012, 34(4): 360-366, 332. doi: 10.3969/j.issn.1000-680X.2012.04.017MA Lei, ZANG Jun-jie, ZHANG Run-sheng. Front vehicle identification under different lighting conditions[J]. Automotive Engineering, 2012, 34(4): 360-366, 332. (in Chinese). doi: 10.3969/j.issn.1000-680X.2012.04.017 [6] SHAW A A, GOPALAN N P. Finding frequent trajectories by clustering and sequential pattern mining[J]. Journal of Traffic and Transportation Engineering: English Edition, 2014, 1(6): 393-403. doi: 10.1016/S2095-7564(15)30289-0 [7] 许庆, 高峰, 徐国艳. 基于Haar特征的前车识别算法[J]. 汽车工程, 2013, 35(4): 381-384. doi: 10.3969/j.issn.1000-680X.2013.04.018XU Qing, GAO Feng, XU Guo-yan. An algorithm for frontvehicle detection based on Haar-like feature[J]. Automotive Engineering, 2013, 35(4): 381-384. (in Chinese). doi: 10.3969/j.issn.1000-680X.2013.04.018 [8] HSIEH J W, CHEN L C, CHEN D Y. Symmetrical SURF and its applications to vehicle detection and vehicle make and model recognition[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(1): 6-20. doi: 10.1109/TITS.2013.2294646 [9] CHEON M, LEE W, YOON C, et al. Vision-based vehicle detection system with consideration of the detecting location[J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13(3): 1243-1252. doi: 10.1109/TITS.2012.2188630 [10] SUN Z, BEBIS G, MILLER R. On-road vehicle detection: a review[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(5): 694-711. doi: 10.1109/TPAMI.2006.104 [11] VIOLA P, JONES M. Robust real-time face detection[J]. International Journal of Computer Vision, 2004, 57(2): 137-154. doi: 10.1023/B:VISI.0000013087.49260.fb [12] VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features[C]∥IEEE. Proceedings of the2001IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2001: 511-518. [13] SUN Z, BEBIS G, MILLER R. Monocular precrash vehicle detection: features and classifiers[J]. IEEE Transactions on Image Processing, 2006, 15(7): 2019-2034. doi: 10.1109/TIP.2006.877062 [14] PONSA D, LOPEZ A. Cascade of classifiers for vehicle detection[C]∥BLANC-TALON J, PHILIPS W, POPESCU D, et al. Proceedings of the 9th International Conference on Advanced Concepts for Intelligent Vision Systems. Heidelberg: Springer, 2007: 980-989. [15] WITHOPF D, JÄHNE B. Improved training algorithm for tree-like classifiers and its application to vehicle detection[C]∥IEEE. Proceedings of the 2007IEEE Intelligent Transportation Systems Conference. New York: IEEE, 2007: 642-647. [16] KAÂNICHE M B, BRÉMOND F. Recognizing gestures by learning local motion signatures of HOG descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2247-2258. doi: 10.1109/TPAMI.2012.19 [17] MORANDUZZO T, MELGANI F. A SIFT-SVM method for detecting cars in UAV images[C]∥IEEE. 2012IEEE International Geoscience and Remote Sensing Symposium. New York: IEEE, 2012: 6868-6871. [18] 孙锐, 陈军, 高隽. 基于显著性检测与HOG-NMF特征的快速行人检测方法[J]. 电子与信息学报, 2013, 35(8): 1921-1926. https://www.cnki.com.cn/Article/CJFDTOTAL-DZYX201308023.htmSUN Rui, CHEN Jun, GAO Jun. Fast pedestrian detection based on saliency detection and HOG-NMF features[J]. Journal of Electronics and Information Technology, 2013, 35(8): 1921-1926. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-DZYX201308023.htm [19] 蔡益红. 多特征融合的道路车辆检测方法[J]. 计算技术与自动化, 2013, 32(1): 98-102. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJH201301024.htmCAI Yi-hong. Fusing multiple features to detect on-road vehicles[J]. Computing Technology and Automation, 2013, 32(1): 98-102. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JSJH201301024.htm [20] GEISMANN P, SCHNEIDER G. A two-staged approach to vision-based pedestrian recognition using Haar and HOG features[C]∥IEEE. 2008IEEE Intelligent Vehicles Symposium. New York: IEEE, 2008: 554-559. [21] PORIKLI F. Integral histogram: a fast way to extract histograms in Cartesian spaces[C]∥IEEE. Proceedings of the2005IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2005: 829-836. [22] JU Yu-cui, ZHANG Hua, XUE Yan-bing. Research of feature selection and comparison in AdaBoost based object detection system[J]. Journal of Computational Information Systems, 2013, 9(22): 8947-8954. [23] CHANG W C, CHO C W. Online boosting for vehicle detection[J]. IEEE Transactions on Systems, Man, and Cybernetics Part B: Cybernetics, 2010, 40(3): 892-902. doi: 10.1109/TSMCB.2009.2032527 [24] YUAN Q, THANGALI A, ABLAVSKY V, et al. Learning a family of detectors via multiplicative kernels[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(3): 514-530. doi: 10.1109/TPAMI.2010.117 [25] NIKNEJAD H T, TAKEUCHI A, MITA S, et al. On-road multivehicle tracking using deformable object model and particle filter with improved likelihood estimation[J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13(2): 748-758. -
下载:
点击查看大图
图(8) / 表(3)
计量
- 文章访问数: 619
- HTML全文浏览量: 76
- PDF下载量: 1084
- 被引次数: 0
