Highway Background Identification and Background Modeling Based on Projection Statistics

Background images are identified by analyzing the changes in texture of the image sequences. According to the characteristics of highway traffic scenes, in this paper, the author presents a new algorithm for identifying background image based on the gradient projection statistics of the binary image. First, the images are blocked by road lane, and the background is identified by projection statistics and projection gradient statistics of the sub-images. Second, the background is reconstructed according to the results of each sub-image. Experimental results show that the proposed method exhibits high accuracy for background identification and modeling. In addition, the proposed method has a good anti-interference to the low intensity vehicles, and the processing time is less as well. The speed ??and accuracy of the proposed algorithm meets the needs of video surveillance system requirements for highway traffic scenes.

[1]  Apostolos Malatras.  Pervasive Computing and Communications Design and Deployment: Technologies, Trends and Applications , 2011 .

[2]  Yasuyo Kita,et al.  Background Modeling by Combining Joint Intensity Histogram with Time-sequential Data , 2010, 2010 20th International Conference on Pattern Recognition.

[3]  Liu Hongcong.  Bio Diesel Oil of Mustard: Small Diesel a Renewable Alternative Fuel , 2013, Int. J. Adv. Pervasive Ubiquitous Comput..

[4]  Phillip W. J. Brook.  Knowledge sharing and pervasive computing : the need for trust and a sense of history , 2009 .

[5]  Sun Jian-fen.  New Method for Moving Object Detection Based on Gaussian Kernel Density Estimation , 2010 .

[6]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[7]  Wendy Powley,et al.  An Adaptable Context Management Framework for Pervasive Computing , 2009, Context-Aware Mobile and Ubiquitous Computing for Enhanced Usability.

[8]  T. Charoenpong,et al.  Adaptive background modeling from an image sequence by using K-Means clustering , 2010, ECTI-CON2010: The 2010 ECTI International Confernce on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology.

[9]  Francisco Milton Mendes Neto.  Technology Platform Innovations and Forthcoming Trends in Ubiquitous Learning , 2013 .

[10]  Zhou Zhi-yuan.  Approach for Locating Vehicle License Plates Based on Gradient Difference of the Morphology , 2008 .

[11]  Hongxun Yao,et al.  Robust background modeling via standard variance feature , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[12]  M Ai.  Moving object detection based on Gaussian kernel density model , 2007 .

[13]  Hadi Alasti.  Level Crossing Sampling for Energy Conservation in Wireless Sensor Networks: A Design Framework , 2012 .

[14]  Mehdi Khosrow-Pour,et al.  Ubiquitous and Pervasive Computing: Concepts, Methodologies, Tools, and Applications , 2009 .

[15]  Chen Yan,et al.  Adaptive Narration in Multiplayer Ubiquitous Games , 2009, Int. J. Cogn. Informatics Nat. Intell..

[16]  JI Zhi-cheng.  Kernel density estimation background model method based on key frame , 2008 .

[17]  Rita Cucchiara,et al.  Detecting Moving Objects, Ghosts, and Shadows in Video Streams , 2003, IEEE Trans. Pattern Anal. Mach. Intell..