A RELIABLE FUSION METHOD USING BACKGROUND SUBTRACTION TECHNIQUE AND CASCADE-ADABOOST CLASSIFIER FOR REAL-TIME PEDESTRIAN DETECTION

Hong-Son Vu; Ngoc-Thang Pham

Hong-Son Vu Hung Yen University of Technology and Education
Ngoc-Thang Pham Hung Yen University of Technology and Education

Keywords: Fusion method, Moving object detection, Pedestrian detection

Abstract

Moving objects recognition plays an important role in camera-only active safety systems and intelligent autonomous vehicles. For these applications, reliable detection performance is required; however, pedestrian detection is challenging due to their divergent dressing and action variety. Besides, real-time detection and recognition performance is also critical. In this paper, we take advantage of Background Subtraction (BS) technique to extract moving objects region on whole natural scene images in complicated environments. Then, Haar-like features are used to classify the detected moving objects to the categories they belong to. The proposed fusion method achieves a speedup of 14x compared to conventional approaches based on Haar-Like descriptor only, and can speed up at least 2x faster computing speed as compared to previous works for high resolution images (768 x 576), with detection rate of 97.76% and a minor false detection rate of 2.66%.

References

P. Dollar, C. Wojek, B. Schiele, and P. Perona, “Pedestrian detection: An evaluation of the state of the art,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no 4, pp. 743–761, 2012.

P. Viola, M. Jones, “Rapid object detection using a boosted cascade of simple features,” in Proc. Comput. Vis. Patt. Recognit. (CVPR), pp. 511–518, 2001.

N. Dalal, B. Triggs, “Histograms of oriented gradients for human detection,” in Proc. Comput. Vis. Patt. Recognit. (CVPR), pp. 886–893, 2005.

Q. Zhu, M. C. Yeh, K. T. Cheng, and S. Avidan, “Fast human detection using a cascade of histograms of oriented gradients,” in Proc. Comput. Vis. Patt. Recognit. (CVPR), pp. 1491–1498, 2006.

S. J. Noh, M. Jeon, “A new framework for background subtraction using multiple cues,” in Proc. 11th Asian Conf. on Comput. Vis., pp. 493–506, 2013.

H. S. Vu, J. X. Gou, K. H. Chen, S. J. Hsieh, and D. S. Chen, “A real-time moving objects detection and classification approach for static cameras,” in Proc. IEEE Int. Conf. on Consumer Electronics-

Taiwan (ICCE-TW), pp. 1–2, 2016.

PETS 2009: Eleventh IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, (2009), Available: http://www_ .cvg.reading.ac.uk/PETS2009/

Y. Xu, L. Xu, and Y. Wu, “Pedestrian detection using background subtraction assisted support vector machine,” in Proc. IEEE 11th Int. Conf. on Intelligent Systems Design and Applications, pp. 837–842, 2011.

M. Jin, K. Jeong, S. Yoon, and D. S. Park, “Real-time Pedestrian Detection based on GMM and HOG Cascade,” in Pro. Sixth Int. Conf. on Machine Vision (ICMV 2013), 9067, pp. 1–5, 2013.

H. S. Vu, V. T. Doan, T. D. Nguyen, “Real-Time Pedestrian Detection Using Motion Segmentation and Cascade-AdaBoost Classifier”, Journal of Military Science and Technology, Special Issue, No.54A, pp. 10 – 19, 2018.

H. S. Vu, “A high dynamic range imaging algorithm: implementation and evaluation”, Science and Technology Development Journal, 22(3), pp. 293-307, 2019.