一种基于多特征和机器学习的分级行人检测方法

种衍文; 匡湖林; 李清泉

doi:10.3724/SP.J.1004.2012.00375

一种基于多特征和机器学习的分级行人检测方法

doi: 10.3724/SP.J.1004.2012.00375

1.
武汉大学测绘遥感信息工程国家重点实验室武汉 430079

详细信息

通讯作者:
种衍文, 武汉大学测绘遥感信息工程国家重点实验室副研究员. 主要研究方向为计算机视觉,数字视频处理和模式识别. E-mail: apollobest@126.com

计量
- 文章访问数: 2459
- HTML全文浏览量: 35
- PDF下载量: 2267
- 被引次数: 0
出版历程
- 收稿日期: 2011-07-11
- 修回日期: 2011-09-14
- 刊出日期: 2012-03-20

Two-stage Pedestrian Detection Based on Multiple Features and Machine Learning

1.
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079

摘要

摘要: 针对单幅图像中的行人检测问题,提出了基于自适应增强算法(Adaboost)和支持向量机(Support vector machine, SVM)的两级检测方法, 应用粗细结合的思想有效提高检测的精度.粗级行人检测器通过提取四方向特征(Four direction features, FDF)和GAB (Gentle Adaboost)级联训练得到,精密级行人检测器用熵梯度直方图(Entropy-histograms of oriented gradients, EHOG)作为特征, 通过支持向量机学习得到.本文提出的EHOG特征考虑到熵, 通过分布的混乱程度描述,具有分辨行人和类似人的物体能力. 实验结果表明,本文提出的EHOG、粗细结合的两级检测方法能准确地检测出复杂背景下不同姿势的直立行人, 检测精度优于以往Adaboost方法.
- 四方向特征 /
- 熵梯度直方图 /
- 自适应增强算法 /
- GAB级联 /
- 支持向量机 /
- 两级检测
Abstract: A two-stage detection method based on Adaboost and support vector machine (SVM) is proposed for the pedestrian detection problem in a single image, which uses the combination of coarse level and fine level detection to improve the accuracy of the detector. The coarse level pedestrian detector makes use of the four direction features (FDF) and the gentle Adaboost (GAB) cascade training; the fine level pedestrian detector uses entropy-histograms of oriented gradients (EHOG) as features and the SVM as classifier. The proposed EHOG features considering entropy and the distribution of chaos have the ability to distinguish between the pedestrians and the objects similar to people. Experimental results show that the proposed two-stage pedestrian detection method with the combination of the coarse-fine level and EHOG feature can accurately detect upright bodies with different postures in the complex background, at the same time the precision is better than the classic Adaboost methods.
- Four direction features (FDF) /
- entropy-histograms of oriented gradients (EHOG) /
- Adaboost /
- gentle Adaboost (GAB) cascade /
- support vector machine (SVM) /
- two-stage detection

HTML全文

参考文献(1)

[1]

Liu Wen-Jing. Human Detection System Based on ADABOOST Algorithm [Master dissertation], Jilin University, China, 2009(刘文静. 基于ADABOOST算法的人体检测系统 [硕士学位论文], 吉林大学, 中国, 2009)[2] Geronimo D. A Global Approach to Vision-Based Pedestrian Detection for Advanced Driver Assistance Systems [Ph.D. dissertation], Universitat Autonoma de Barcelona, Spain, 2010[3] Viola P, Jones M J. Robust real-time face detection. International Journal of Computer Vision, 2004, 57(2): 137-154[4] Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA: IEEE, 2005. 886-893[5] Zeng Chun, Li Xiao-Hua, Zhou Ji-Liu. Pedestrian detection based on HOG of ROI. Computer Engineering, 2009, 35(24): 182-184(曾春, 李晓华, 周激流. 基于感兴趣区梯度方向直方图的行人检测. 计算机工程, 2009, 35(24): 182-184)[6] Freund Y, Schapire R E. A decision-theoretic generalization of on-line learning and an application to boosting. In: Proceedings of the 2nd European Conference on Computational Learning Theory. Barcelona, Spain: Springer, 1995. 23-37[7] Zhao L, Thorpe C. Stereo- and neural network-based pedestrian detection. IEEE Transactions on Intelligent Transportation Systems, 2000, 1(3): 148-154[8] Cheng H, Zheng N N, Qin J J. Pedestrian detection using sparse Gabor filter and support vector machine. In: Proceedings of the IEEE Intelligent Vehicles Symposium. Las Vegas, USA: IEEE, 2005. 583-587[9] Tian Guang. Study of Visual Based Pedestrian Detection and Tracking Algorithm [Ph.D. dissertation], Shanghai Jiao Tong University, China, 2007(田广. 基于视觉的行人检测和跟踪技术的研究 [博士学位论文], 上海交通大学, 中国, 2007)[10] Soga M, Hiratsuka S, Fukamachi H, Ninomiya Y. Pedestrian detection for a near infrared imaging system. In: Proceedings of the 11th IEEE International Conference on Intelligent Transportation Systems. Beijing, China: IEEE, 2008. 1167-1172[11] Iwata K, Hongo H, Yamamoto K, Niwa Y. Robust facial parts detection by using four directional features and relaxation matching. In: Proceedings of the 7th International Conference on Knowledge-Based Intelligent Information and Engineering Systems. Oxford, UK: Springer, 2003. 882-889[12] Zhou Ke. Research and Implementation of HOG Based Human Detection of Image [Master dissertation], Huazhong University of Science and Technology, China, 2008(周柯. 基于HOG特征的图像人体检测技术的研究与实现 [硕士学位论文], 华中科技大学, 中国, 2008)[13] Wang Jian-Hong, Zhang Pin-Zheng, Luo Li-Min. Improved fast pedestrian detection method. Computer Engineering and Applications, 2009, 45(28): 160-163(王健弘, 章品正, 罗立民. 改进的快速行人检测方法. 计算机工程与应用, 2009, 45(28): 160-163)[14] Friedman J, Hastie T, Tibshirani R. Additive logistic regression: a statistical view of boosting. The Annals of Statistics, 2000, 28(2): 337-407[15] Vapnik V N. The Nature of Statistical Learning Theory. New York: Springer, 1995[16] Zhang Xiao-Chuan. Human-Targets Tracking Based on Histogram of Oriented Gradient and Support Vector Machine [Master dissertation], Dalian University of Technology, China, 2009(张小川. 基于梯度直方图和支持向量机的人体目标跟踪 [硕士学位论文], 大连理工大学, 中国, 2009)[17] Pan Feng, Wang Xuan-Yin. Support vector machine-based human cetection under complex background. Journal of Image and Graphics, 2005, 10(2): 181-186(潘峰, 王宣银. 基于支持向量机的复杂背景下的人体检测. 中国图象图形学报, 2005, 10(2): 181-186)[18] Hu Jian-Hua, Xu Jian-Jian. Detection and recognition of vehicle and pedestrian in intelligent traffic surveillance. Electronic Measurement Technology, 2007, 30(1): 16-17, 71(胡建华, 徐健健. 交通监控系统中车辆和行人的检测与识别. 电子测量技术, 2007, 30(1): 16-17, 71)[19] Viola P A, Jones M J. Rapid object detection using a boosted cascade of simple feature. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai, USA: IEEE, 2001. 551-518[20] Zhang W, Zelinsky G, Samaras D. Real-time accurate object detection using multiple resolutions. In: Proceedings of the 11th IEEE International Conference on Computer Vision. Rio de Janeiro, Brazil: IEEE, 2007. 1-8[21] Li Z, Wei Z Q, Yin B, Ji X P, Shan R B. Pedestrian detection based on a new two-step framework. In: Proceedings of the 2nd International Workshop on Education Technology and Computer Science. Wuhan, China: IEEE, 2010. 56-59[22] Wu B, Nevatia R. Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors. In: Proceedings of the 10th IEEE International Conference on Computer Vision. Beijing, China: IEEE, 2005. 90-97[23] Ye Q X, Jiao J B, Zhang B C. Fast pedestrian detection with multi-scale orientation features and two-stage classifiers. In: Proceedings of the 17th IEEE International Conference on Image Processing. Hong Kong, China: IEEE, 2010. 881-884

施引文献

资源附件(0)

访问统计