Algorithm Research on Main Motion Direction Feature Extraction for Initial Rising Smoke

Abstract:

This paper proposes rapid extraction algorithm for identifying the main direction of smoke, according to internal small local movement feature of initial rising smoke and the overall presentation presents upward and both sides diffusion trend. The algorithm adopts Meanshift Kernel function of histogram to model movement characteristics and estimates the smoke pieces of motion vector direction by using Bhattachyarya coefficient. Smoke data block motion accumulation are analyzed statistically to estimate the proportion of each suspected smoke region in main movement to realize the identification of inside smoke moving direction. The obtained results from the thick black smoke experiment, gray smog experiment, human body movement interference experiment show that the algorithm is better able to extract the main direction features of smoke and has a strong ability to eliminate interference. It provides criterion for the further study of smoke recognition algorithm.

• Periodical: Applied Mechanics and Materials (Volumes 58-60)
• Pages: 495-500
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.58-60.495
• Online since: June 2011
• Authors: Qing Liu, Xiao Hui Zhang, Na Li
• Keywords: Accumulation, Initial Rising Smoke, Main Motion Direction, Mean-Shift

References

[1] B. UgurTin, Yigithan Dedeoglu, et al, in: Wavelet based real-time Smoke Detection in Video, edtied by Antalya, Turkey : 13th European Signal Processing Conference EUSIPCO (2005).

[2] Po L. M, Ma W. C, in: A Novel Four-step Search Algorithm for Fast Block Motion Estimation, edtied by IEEE Trans. on Circuits Systems for Video Technology, Vol. 313-317(1996).

DOI: 10.1109/76.499840

[3] Liu L. K, Feig E, in: A Block-based Gradient Descent Search Algorithm for Block Motion Estimation in Video Coding, edtied by IEEE Transactions on Circuits Systems for Video Technology, Vol. 419-422(1996).

DOI: 10.1109/76.510936

[5] Zhu S, Ma K. K, in: A New Diamond Search Algorithm for Fast Block-matching Motion Estimation, edtied by IEEE Transactions. on Image Processing, Vol. 287-290(2000).

DOI: 10.1109/83.821744

[6] Ding G. G, Guo B. L, in: Motion Vector Estimation Using Line Square Search Block Matching Algorithm, edtied by EURASIP Journal on Applied Signal Processing, Vol. 1750-1756(2004).

DOI: 10.1155/s1110865704402273

[7] Tu J. L, Tao H, Huang T, in: Online Updating Appearance Generative Mixture Model for Meanshift Tracking, edtied by Machine Vision and Applications, Vol. 163-173(2009).

DOI: 10.1007/s00138-007-0115-x

[8] Yuan F. N, Zhang Y. M, et. al, in: Video Smoke Detection Based on Accumulation and Main Motion Orientation, edtied by Journal of Image and Graphics, Vol. 808-814(2008).