LIANG Jincheng, WANG Xiaopeng, WANG Qingsheng
（School of Electronic and Information Engineering， Lanzhou Jiaotong University, Lanzhou 730070, China）
Abstract：The visual background extractor(Vibe) algorithm can lead to a large area of false detection in the extracted foreground target when the illumination is mutated. An improved Vibe method based on the YCbCr color space and improved three-frame difference is proposed in this paper. The algorithm detects the illumination mutation frames accurately based on the difference between the luminance components of two frames adjacent to a video frame. If there exists a foreground moving target in the previous frame of the mutated frame, three-frame difference method is utilized; otherwise, Vibe method using current frame is used to initialize background. Improved three-frame differential method based on the difference in brightness between two frames of the video changes the size of the threshold adaptively to reduce the interference of noise on the foreground extraction. Experiment results show that the improved Vibe algorithm can not only suppress the “ghost” phenomenon effectively but also improve the accuracy and completeness of target detection, as well as reduce error rate of detection when the illumination is mutated.
Key words：moving target detection； visual background extractor (Vibe) algorithm； YCbCr color space； three-frame difference method
References
［1］CAI N, ZHOU Y, LIU G, et al. Survey of robust principal component analysis methods for moving-object detection. Journal of Image and Graphics, 2016, 21(10)：1265-1275.
［2］LIPTON A J, FUJIYOSHI H, PATIL R S. Moving target classification and tracking from real-time video//The Fourth Workshop on Applications of Computer Vision, Oct. 19-21, 1998, IEEE, Princeton, NJ, USA. Washington: IEEE Computer Society, 1998：8-14.
［3］BARRON J L, FLEET D J, BEAUCHEMIN S S. Performance of optical flow techniques. International Journal of Computer Vision, 2002, 12(1)：43-77.
［4］BENEZETH Y, JODOIN P M, EMILE B, et al. Review and evaluation of commonly-implemented background subtraction algorithms//International Conference on Pattern Recognition, Dec. 8-11, 2008, IEEE, Tampa, Florida, USA. Washington: IEEE Computer Society, 2008：1-4.
［5］BARNICH O, VAN DROOGENBROECK M. Vibe：A powerful random technique to estimate the background in video sequences//International Conference on Acoustics, Speech and Signal Processing, Apr. 19-24, 2009, IEEE, Taipei, China. Washington: IEEE Computer Society, 2009: 945-948.
［6］YU Y, CAO M W, YUE F E. Vibe：an improved Vibe algorithm for detecting moving objects. Chinese Journal of Scientific Instrument, 2014, 35(4)：924-931.
［7］MIN W D, GUO X G, HAN Q. An improved Vibe algorithm and its application in traffic video processing. Optics and Precision Engineering, 2017, 25(3)：806-811.
［8］SU Y Z, LI A H, JIANG K, et al. Improved visual background extractor model for moving objecting algorithm. Journal of Computer-Aided Design & Computer Graphics, 2014, 26(2)：232-240.
［9］FU J, MU X Q, JI W B. A correction method for saturated images based on separation of luminance and chrominance. Journal of Xi’an Jiaotong University, 2014, 48(10)：101-107.
［10］BARNICH O, DROOGENBROECK M V. ViBe：A universal background subtraction algorithm for video sequences. IEEE Transactions on Image Processing, 2011, 20(6)：1709-1724.
［11］WANG W, WANG X P, LIANG J C. An improved vibe algorithm based on adaptive detection of moving targets. Journal of Measurement Science and Instrumentation, 2020, 11(2)：126-134.
［12］JIN M, ZHANG J, HUANG T F, et al. A foreground target detection algorithm considering adaptive parameter and shadow removal. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2021, 49(1)：73-79.
［13］YANG D, DAI F. Improved ViBe algorithm for detection of moving objects. Journal of Image and Graphics, 2018, 23(12)：1813-1828.
［14］MO S W, DENG X P, WANG S, et al. Moving object detection algorithm based on improved visual background extractor. Acta Optica Sinica, 2016, 36(6)：204-213.
［15］GAN M G, CHEN J, LIU J, et al. Moving object detection algorithm based on three-frame-differencing and edge information. Journal of Electronics & Information Technology, 2010, 32(4)：894-897.
［16］HAO X L, LIU W, NIU B N, et al. High-efficiency detection algorithm for moving targets based on adaptive learning rate. Journal of University of Electronic Science and Technology of China, 2020, 49(1)：123-130.
［17］WANG C D, XIE H W, LI Y X, et al. Motion object detection with improved three-frame difference and Vibe algorithm. Computer Engineering and Applications, 2020, 56(13)：199-203.
［18］SUN T, QI Y C, GENG G H. Moving object detection algorithm based on frame difference and background subtraction. Journal of Jilin University (Engineering and Technology Edition), 2016, 46(4)：1325-1329.
［19］YU X M, LI S Y, SHI S N. An improved algorithm for moving target detection using a gaussion mixture with three-frame difference. Infrared Technology, 2019, 41(3)：256-261.
一种面向光照突变的改进Vibe算法
梁金诚， 王小鹏， 王庆圣
（兰州交通大学 电子与信息工程学院， 甘肃 兰州 730070）
摘 要: 针对视觉背景提取（Visual background extractor, Vibe）算法在光照突变时容易导致提取的前景目标存在大面积误检的问题， 提出一种基于YCbCr彩色空间和改进三帧差分的改进Vibe算法。 该算法根据视频前后帧亮度值在YCbCr彩色空间的差值对光照突变帧进行精准检测， 并通过判断当前帧与前一帧是否存在前景运动目标来判断采用改进三帧差分法还是Vibe初始化当前帧进行运动目标提取。 改进三帧差分法通过视频前后的帧亮度差值自适应调节阈值大小， 从而减小噪声对前景提取的影响。 实验结果表明， 改进的Vibe算法能够在光照突变的环境下提高检测目标的准确度和完整性， 并有效抑制“鬼影”现象的产生， 降低了误检率。
关键词： 运动目标检测； Vibe算法； YCbCr彩色空间； 三帧差分法
引用格式：LIANG Jincheng, WANG Xiaopeng, WANG Qingsheng. An improved Vibe algorithm for illumination mutations. Journal of Measurement Science and Instrumentation， 2022， 13（2）：184-191. DOI：10.3969／j.issn.1674-8042.2022.02.007
[full text view]
