Vehicles Detection Based on Background Modeling

Vehicles Detection Based on Background Modeling

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2018 by IJETT Journal
Volume-66 Number-2
Year of Publication : 2018
Authors : Mohamed Shehata, Reda Abo-Al-Ez, Farid Zaghlool, and Mohamed Taha Abou-Kreisha
DOI :  10.14445/22315381/IJETT-V66P216

Citation 

MLA Style: Mohamed Shehata, Reda Abo-Al-Ez, Farid Zaghlool, and Mohamed Taha Abou-Kreisha "Vehicles Detection Based on Background Modeling" International Journal of Engineering Trends and Technology 66.2 (2018): 92-95.

APA Style:Mohamed Shehata, Reda Abo-Al-Ez, Farid Zaghlool, and Mohamed Taha Abou-Kreisha (2018). Vehicles Detection Based on Background Modeling. International Journal of Engineering Trends and Technology, 66(2), 92-95.

Abstract
Background image subtraction algorithm is a common approach which detects moving objects in a video sequence by finding the significant difference between the video frames and the static background model. This paper presents a developed system which achieves vehicle detection by using background image subtraction algorithm based on blocks followed by deep learning data validation algorithm. The main idea is to segment the image into equal size blocks, to model the static reference background image (SRBI), by calculating the variance between each block pixels and each counterpart block pixels in the adjacent frame, the system implemented into four different methods: Absolute Difference, Image Entropy, Exclusive OR (XOR) and Discrete Cosine Transform (DCT). The experimental results showed that the DCT method has the highest vehicle detection accuracy.

Reference
[1] G. Bhosle, et al., “Vehicle Tracking Using Image Processing,” IJRASET, vol. 6, no. 1, pp. 1235–1238, 2018.
[2] E. M. Martin and A. P. Pobil, “Robust Motion Detection in Real-Life Scenarios,” Ed., Springer, 2012.
[3] S. Jain1, G. Vishwakarma and Y. Kumar, “An Artificial Approach of Video Object Action Detection by Using Gaussian Mixture Model,” IJETT, vol. 42, no. 2, pp. 49–55, 2016.
[4] Y. Zhang and L. Luo, “Background Subtraction Method Based on Block-Wise Mixture Models,” Proc. Chinese Conference on Pattern Recognition, pp. 211–218, China, 2012.
[5] D. Riahi, P. St-Onge, and G. Bilodeau, “RECTGAUSS-Tex: Block-based Background Subtraction,” Technical Report EPM-RT-2012-03, Ecole Polytechnique de Montreal, Canada, 2012.
[6] J. Guo, and C. Hsu “Cascaded Background Subtraction Using Block-Based and Pixel-Based Codebooks,” Proc. International Conference on Pattern Recognition, China, 2010.
[7] I. Lipovac, et al., “Experimental Evaluation of Vehicle Detection Based on Background Modelling in Day-time and Night-Time Video,” Proc. Croatian Computer Vision Workshop, Zagreb Universty, Croatia, 2017.
[8] P. Nagabhushan, M. Javed and B. B. Chaudhuri, “Entropy Computation of Document Images in Run – length Compressed Domain”, Proc. Fifth International Conference on Signal and Image Processing, India, 2014.
[9] K. Teknomo, and P. Fernandez, “Background Image Generation Using Boolean Operations,” Philippine Computing Journal, vol. 4, no. 2, pp. 43–49, 2009.
[10] A. M. Raid, et al., “Jpeg Image Compression Using Discrete Cosine Transform – A Survey,” IJCSES, vol. 5, no.2, pp. 39–47, 2014.
[11] K. Verma, I. K. Singh and A. S. Thoke “An Enhancement in Adaptive Median filter for Edge Preservation”, Proc. International Conference on Intelligent Computing, Communication & Convergence, pp. 29–36, India, 2015.
[12] Y. LeCun, Y. Bengio and G. Hinton, “Deep learning,” NATURE, Macmillan Publishers, Vol. 521, pp. 436–444, 2015.

Keywords
video processing, object detection, DCT, image entropy