The ship detection in infrared video has wide application value in fishery administration, port monitoring and other fields. Traditional background modeling methods, such as GMM(Gaussian mixture model), Codebook, and ViBe, will make more false detection in the ship detection from the infrared ocean video because of the impact of the waves. The paper proposes a new algorithm to detect ships in the infrared ocean video. The algorithm framework adopts the Top-Hat operation to preprocess the infrared image to filter the clutter effectively, then improves Vibe algorithm to detect the moving ship target. Experimental results show that the method can effectively suppress the background noise and get better detection results.
Ship detection from infrared video
First published at:Jun 01, 2018
1 Gao F, Jiang J G, An H X, et al. A fast detection algorithm for moving object[J]. Journal of Hefei University of Technology (Natural Science), 2012, 35(2): 180-183.
2 Bathia H V P K. An efficient algorithm for real time moving object detection using GMM and optical flow[J]. International Journal of Innovative Research in Computer and Communication Engineering, 2015, 3(6): 5096-5101. DOI:10.15680/ijircce
3 Zhang S S, Jiang T, Peng Y X, et al. A new pixel-level background subtraction algorithm in machine vision[C]//Proceedings of the 10th International Conference on Intelligent Robotics and Applications, 2017: 520-531.
4 St-Charles P L, Bilodeau G A. Improving background subtraction using Local Binary Similarity Patterns[C]//Proceedings of 2014 IEEE Winter Conference on Applications of Computer Vision, 2014: 509-515.
5 Ge W F, Dong Y H, Guo Z H, et al. Background subtraction with dynamic noise sampling and complementary learning[C]//Proceedings of the 2014 22nd International Conference on Pattern Recognition, 2014: 2341-2346.
6 Lee H, Kim H S, Kim J I. Background subtraction using background sets with image- and color-space reduction[J]. IEEE Transactions on Multimedia, 2016, 18(10): 2093-2103. DOI:10.1109/TMM.2016.2595262
7 Xu Y, Dong J X, Zhang B, et al. Background modeling methods in video analysis: a review and comparative evaluation[J]. CAAI Transactions on Intelligence Technology, 2016, 1(1): 43-60. DOI:10.1016/j.trit.2016.03.005
8 Wang H, Gao J, Yu L J, et al. Combined improved Frequency-Tuned with GMM algorithm for moving target detection[C]//Proceedings of 2017 International Conference on Mechatronics and Automation, 2017: 1848-1852.
9 Kim K, Chalidabhongse T H, Harwood D, et al. Real-time foreground-background segmentation using codebook model[J]. Real-Time Imaging, 2005, 11(3): 172-185. DOI:10.1016/j.rti.2004.12.004
10 Xu X H, Xiao G, Yun X, et al. Moving object tracking in complex background and occlusion conditions[J]. Opto-Electronic Engineering, 2013, 40(1): 23-30.
11 Barnich O, Van Droogenbroeck M. ViBe: a powerful random technique to estimate the background in video sequences[C]//Proceedings of 2009 IEEE International Conference on Acoustics, Speech and Signal Processing, 2009: 945-948.
12 Barnich O, Van Droogenbroeck M. ViBe: a universal background subtraction algorithm for video sequences[J]. IEEE Transactions on Image Processing, 2011, 20(6): 1709-1724. DOI:10.1109/TIP.2010.2101613
13 Van Droogenbroeck M, Paquot O. Background subtraction: experiments and improvements for ViBe[C]//Proceedings of 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2012: 32-37.
14 Elgammal A, Harwood D, Davis L. Non-parametric model for background subtraction[C]//Proceedings of the 6th European Conference on Computer Vision, 2000: 751-767.
Supported by National Natural Science Foundation (61331021), the Key Science and Technology Program of Henan Province(152102310294), and the Industry-University-Research Collaboration Program of Henan Province(162107000023)
Get Citation: Shi Chao, Chen Enqing, Qi Lin. Ship detection from infrared video[J]. Opto-Electronic Engineering, 2018, 45(6): 170748.
Previous: Research on ESPRIT estimation algorithm for the central frequency of gain spectrum in Brillouin optical time-domain reflectrometry