基于混合高斯模型的红外图像自适应校正算法

贾俊涛

贾俊涛. 基于混合高斯模型的红外图像自适应校正算法[J]. 应用光学, 2014, 35(4): 701-706.
引用本文: 贾俊涛. 基于混合高斯模型的红外图像自适应校正算法[J]. 应用光学, 2014, 35(4): 701-706.
Jia Jun-tao. New scene-based nonuniformity correction algorithm based onGaussian mixture model[J]. Journal of Applied Optics, 2014, 35(4): 701-706.
Citation: Jia Jun-tao. New scene-based nonuniformity correction algorithm based onGaussian mixture model[J]. Journal of Applied Optics, 2014, 35(4): 701-706.

基于混合高斯模型的红外图像自适应校正算法

详细信息
    通讯作者:

    贾俊涛(1980-),男,河南洛阳人,工程师,主要从事光电系统设计研究。 Email: icecoffeehust@163.com

  • 中图分类号: TN216

New scene-based nonuniformity correction algorithm based onGaussian mixture model

  • 摘要: 针对传统时域高通滤波校正算法存在的鬼影问题,提出一种新的基于混合高斯模型的红外图像自适应校正算法。新算法利用混合高斯模型对场景进行建模,只有在像元输出值满足一定条件的时候,才将其更新到校正系数中,实现有选择性地更新校正系数。通过一组仿真和真实的红外图像序列评价算法的性能,仿真图像采用峰值信噪比指标进行定量评价,新算法比传统时域高通滤波校正算法的峰值信噪比提高了约9 dB。真实图像采用主观的定性评价,传统算法校正结果中存在着明显的鬼影,而新算法校正结果中不存在鬼影。
    Abstract: A new self-adaptive calibration algorithm for infrared images based on Gaussian mixed model (GMM) was put forward according to traditional temporal highpass filter (THPF). GMM is applied in the new algorithm for background modeling, and only the pixels whose output values satisfy certain conditions can be updated to the correction coefficient, and the background is updated selectively so as to avoid the influence of the foreground target on the update of the background. The performance of the proposed algorithm was evaluated through infrared image sequences with simulated and real fixed-pattern noise, and the simulated sequences quantitative evaluation was carried out by using the peak signal noise ratio (PSNR). Results show that the PSNR of the new algorithm increases by about 9 dB compared with the THPF. The subjective qualitative evaluation was adopted for real images, the correction results in the traditional method show obvious ghosting artifact while the results of the new algorithm are in the absence of ghosting artifact.
  • [1]Chang Benkang, Cai Yi. Infrared imaging array and system[M]. Beijing:Science Press, 2006.
    常本康, 蔡毅. 红外成像阵列与系统[M]. 北京:科学出版社, 2006.
    [2]Cheng Yao, Wang Yuhan, Yuan Xianghui. Nonuniformity correction experiment system of pyroelectric IRFPA[J]. Journal of Applied Optics, 2014, 35(1):106-110.
    程瑶, 王玉菡, 袁祥辉. 热释电IRFPA非均匀性校正实验系统研究[J]. 应用光学, 2014, 35(1):106-110.
    [3]Dong Liquan, Jin Weiqi, Sui Jing. Summarize on the scene-based nonuniformity correction algorithms for IRFPA[C]. USA: SPIE, 2005.
    [4]Scribner D, Sarkady K,Kruer M, et al. Adaptive retina-like preprocessing for image detector arrays[J].  IEEE Conference on Neural Network, 1993, 3: 1955-1960.
    [5]Harris J G, Chiang Y M.Nonuniformity correction of infrared image sequences using the constant-statistics constraint[J]. IEEE Transactions on Image Processing, 1999, 8(8): 1148-1151.
    [6]He Ming, Wang Xinsai, Lu Jianfang, et al. New algebraic scene-based non-uniformity correction in infrared focal plane array[J]. Journal of Applied Optics, 2011, 32(6):1217-1221.
    贺明, 王新赛, 路建方,等. 一种新的红外焦平面阵列非均匀性代数校正算法[J]. 应用光学, 2011, 32(6): 1217-1221.
    [7]Torres S N, Hayat M M. Kalman filtering for adaptive nonuniformity correction in infrared focal-plane arrays[J]. Journal of the Optical Society of America, 2003, 20(3): 470-480.
    [8]Oelmaier W R.Third gen focal plane array IR detection modules at AIM[J]. Infrared Physics & Technology, 2002, 43: 257-263.
    [9]Harris J G, Chiang Y M.Minimizing the ghosting artifact in scene-based nonuniformity correction[J]. SPIE, 1998, 3377: 106-113.
    [10]Power P W, Schoonees J A.Understanding background mixture models for foreground segmentation[C].  Australia: Proceedings of Image and Vision Computing, 2002.
    [11]Cucchiara R,Grana C, Piccardi M, et al. Detecting moving objects, ghosts, and shadows in video streams[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2003, 25(10): 1337-1342.
计量
  • 文章访问数:  1554
  • HTML全文浏览量:  130
  • PDF下载量:  191
  • 被引次数: 0
出版历程
  • 刊出日期:  2014-07-14

目录

    /

    返回文章
    返回