Vehicle and Pedestrian Detection and Tracking

Abstract:

Vehicle and pedestrian detection plays a critical role in the intelligent transportation system. The paper proposes an algorithm which can solve the problem effectively by Histograms of Oriented Gradients (HOG) features extraction and Support Vector Machine (SVM). This detection system is based on Histograms of Oriented Gradients features combined with Support Vector Machine for the recognition stage which is insensitive to lightings and noises. We use Kalman filter to track the objects. As shown in experiments, the method has high detection rate and can also satisfy the real-time intelligent transportation system.

• Periodical: Applied Mechanics and Materials (Volumes 401-403)
• Pages: 1432-1435
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.401-403.1432
• Online since: September 2013
• Authors: Qing Tian, Wen Hua Zhao, Long Zhang, Yun Wei
• Keywords: Histograms of Oriented Gradient (HOG), Kalman Filter (KF), Pedestrian Identification, Support Vector Machine (SVM), Vehicle Identification

References

[1] N. Dalal, B. Triggs, Histograms of Oriented Gradients for Human Detection, Computer Vision and Pattern Recognition, 1 (2005) 886-893.

DOI: 10.1109/cvpr.2005.177

[2] C. Cortes,V. Vapnik, Support-vector networks, Machine Learning, (1995) 273-297.

[3] WANG Fei jie, Real-time Detection and Tracking of Human Based on Head and Shoulder Feature, Master thesis, The software department of jilin university, (2010).

[4] CHENG Guang-tao, CHEN Xue, GUO Zhao-zhuang, Pedestrian detection method of vision based on HOG features, Transducer and Microsystem Technologies, 30 (2011) 7.

[5] G. Welch, G. Bishop, An Introduction to the Kalman Filter, UNC-Chapel Hill, TR95-041, (2006).

[6] Zhigang Liu, Hua Yang, A new vehicle tracking method with region matching based on Kalman forecasting model, Networking, Sensing and Control(ICNSC), (2010) 559-563.

DOI: 10.1109/icnsc.2010.5461600

[7] Shenghua Huang, Jingxin Hong, Moving object tracking system based on camshift and Kalman filter, Consumer Electronics, Communications and Networks(CECNet), (2011) 1423-1426.

DOI: 10.1109/cecnet.2011.5769081

[8] Blythe, P. T, Video-based vehicle and pedestrian tracking and motion modelling, Road Transport Information and Control, (2002) 35-40.

DOI: 10.1049/cp:20020201

[9] Vigus, S.A., Bull, D.R. and Canagarajah, C.N., Video object tracking using region split and merge and a Kalman filter tracking algorithm, Image Processing, 1 (2001) 650-653.

DOI: 10.1109/icip.2001.959129

[10] Mori, H., Charkari, N.M., Matsushita, T., On-line vehicle and pedestrian detections based on sign pattern, Industrial Electronics, 41 (1994) 384-391.

DOI: 10.1109/41.303788

[11] Soojin Kim, Sangkyun Park, seonyoung Lee, Seungsang Park and Kyeongsoon Cho, Design of high-performance pedestrian and vehicle detection circuit using Haar-like features, TENCON 2012-2012 IEEE Region 10 Conference, (2012) 1-5.

DOI: 10.1109/tencon.2012.6412165

[12] Xuehua Song, Liguo Wang, Hong Wang and Yuhua Zhang, Detection and identification in the intelligent traffic video monitoring system for pedestrians and vehicles, Networked Computing and Advanced Information management (NCM), (2011) 181-185.

[13] ZHANG Jianfei, CHEN Shuyue, LIU Huiming and HU Nan, Recognition of Vehicle and Pedestrian in Traffic Video Based on SVM, Video application & project, 35 (2011) 1-3.