Two-stage pedestrian detection based on multiple features and machine learning

被引：0
|
作者：
机构：
[1] State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University
来源：
Chong, Y.-W. (apollobest@126.com) | 1600年 / Science Press卷 / 38期
关键词：
Adaboost; Entropy-histograms of oriented gradients (EHOG); Four direction features (FDF); Gentle Adaboost (GAB) cascade; Support vector machine (SVM); Two-stage detection;
D O I：
10.3724/SP.J.1004.2012.00375
中图分类号：
学科分类号：
摘要：
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. Copyright © 2012 Acta Automatica Sinica. All rights reserved.
引用
收藏
页码：375 / 381
页数：6
相关论文
共 23 条
  • [1] Liu W.-J., Human detection system based on AD-ABOOST algorithm, (2009)
  • [2] Geronimo D., A global approach to vision-based pedestrian detection for advanced driver assistance systems, (2010)
  • [3] Viola P., Jones M.J., Robust real-time face detection, International Journal of Computer Vision, 57, 2, pp. 137-154, (2004)
  • [4] Dalai N., Triggs B., Histograms of oriented gradients for human detection, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 886-893, (2005)
  • [5] Zeng C., Li X.-H., Zhou J.-L., Pedestrian detection based on HOG of ROI, Computer Engineering, 35, 24, pp. 182-184, (2009)
  • [6] Freund Y., Schapire R.E., A decision-theoretic generalization of on-line learning and an application to boosting, Proceedings of the 2nd European Conference on Computational Learning Theory, pp. 23-37, (1995)
  • [7] Zhao L., Thorpe C., Stereo- and neural network-based pedestrian detection, IEEE Transactions on Intelligent Transportation Systems, 1, 3, pp. 148-154, (2000)
  • [8] Cheng H., Zheng N.N., Qin J.J., Pedestrian detection using sparse Gabor filter and support vector machine, Proceedings of the IEEE Intelligent Vehicles Symposium, pp. 583-587, (2005)
  • [9] Tian G., Study of visual based pedestrian detection and tracking algorithm, (2007)
  • [10] Soga M., Hiratsuka S., Fukamachi H., Ninomiya Y., Pedestrian detection for a near infrared imaging system, Proceedings of the 11th IEEE International Conference on Intelligent Transportation Systems, pp. 1167-1172, (2008)
123