计算机科学 ›› 2022, Vol. 49 ›› Issue (11A): 210800195-8.doi: 10.11896/jsjkx.210800195
刘新富, 蒋慕蓉, 黄亚群, 张占伟, 周莹瑛
LIU Xin-fu, JIANG Mu-rong, HUANG Ya-qun, ZHANG Zhan-wei, ZHOU Ying-ying
摘要: 在动态场景下进行目标检测与跟踪处理时,提取的前景目标往往会因受到背景抖动干扰而出现目标误判、轮廓不完整等问题,为此提出结合稳像与补帧、VIBE算法与连通域修正的抖动视频前景目标提取方法。首先利用ORB对相邻两帧图像进行特征匹配,使用RANSAC剔除误匹配点,以运动目标为中心调整图像边距,裁剪与修补不重合的部分,通过统计法求相邻两帧的偏移均值,完成视频稳像处理;其次利用稠密光流法计算相邻两帧图像的位移,通过位置重映射生成中间帧,实现视频补帧;然后将VIBE算法增加形态学处理与连通域修正,结合Canny算子进行边缘检测,增加目标轮廓的完整性;最后使用视频实例进行测试,与其他视频目标提取算法进行比较分析,精度、召回率至少提高10%,漏检率、错分率至少降低15%。实验结果表明,所提方法能有效去除抖动带来的影响,提取的目标完整性较高。
中图分类号:
[1]XIN Y X,SHI P F,XUE RY.Moving Object Detection Based on Region Extraction and Improved LBP Features[J].Computer Science,2021,48(7):233-237. [2]RAJ R,RAJIV P,KUMAR P,et.al.Feature based video stabilization based on boosted HAAR Cascade and representative point matching algorithm[J].Image and Vision Computing,2020,101(1):1-8. [3]WU H C,XIAO L,WEI Z H.Simultaneous Video Stabilization and Rolling Shutter Removal[J].IEEE transactions on image processing:a publication of the IEEE Signal Processing Society,2021,30:4637-4652. [4]LIN S S,LE T N H,WU P Y,et al.Content-and-disparity-aware stereoscopic video stabilization[J].Multimedia Tools and Applications,2020,80(1):1545-1564. [5]MOHAMMED A,FARUP I,YILDIRIM S,et al.Variational approach for capsule video frame interpolation[J].EURASIP Journal on Image and Video Processing,2018,30(1):1-13. [6]ZHANG Q,JIANG F.Video interpolation algorithm based on deep learning[J].Intelligent Computer and Applications,2019,9(4):252-257,262. [7]LIN C J,DENG W,TONG T,et al.Fuzzy video frame interpolation method based on deep voxel stream[J].Journal of Compu-ter Applications,2020,40(3):819-824. [8]WANG T,WANG W,CUI Y H,et al.Improved ViBe algo-rithm based on color layout descriptor[J].Journal of Computer Applications,2020,40(3):812-818. [9]HE L F,LIU Y L,ZHONG Y,et al.Video foreground targetextraction algorithm under complex background[J].Laser & Optoelectronics Progress,2020,57(16):160-166. [10]JIN M,ZHANG J,HUANG T F,et al.Parameter adaptive de-shading foreground target detection algorithm[J].Journal of Huazhong University of Science and Technology(Natural Science Edition),2021,49(1):73-79. [11]BARNICH O,VAN DROOGENBROECK M.ViBe:a powerful random technique to estimate the background in video sequences[C]//2009 IEEE International Conference on Acoustics,Speech and Signal Processing.IEEE,2009:945-948. [12]XU H Y,ZHANG B,YANG S.An infrared image registration algorithm combined with FAST algorithm[J].Journal of Shen-yang Institute of Aeronautical Engineering,2017,34(5):57-62. [13]YANG X Y,CHEN B.Feature matching optimization algorithm based on ORB detection[J].Journal of Computer Applications,2019,39(S2):81-84. [14]DAI W H,LIU S C,ZHAO S,et al.Improved random sampling consensus algorithm using local pixel matching[J].Journal of National University of Defense Technology,2021,43(4):38-43. [15]ZHANG L.Design and implementation of facial expression re-cognition system based on sparse optical flow method and HMM[D].Xiamen:Xiamen University,2019. [16]LIN C Z,ZHANG W,WANG X,et al.Smoke detection algo-rithm based on dense optical flow and edge features[J].Computer Engineering and Science,2018,40(7):1213-1220. [17]WANG X R,WANG X G.OpenCV and Visual Studio image recognition application development[M].Beijing:Posts& Telecom Press,2017:124-127. [18]QIN X P.MATLAB image processing and interface programming[M].Beijing:Publishing House of Electronics Industry,2009:310-327,445-447. [19]ZHOU Z H.Machine learning[M].Beijing:Tsinghua University Press,2016:30-32. |
[1] | 张文雅,徐华中,罗杰. 基于ViBe的复杂背景下的运动目标检测 Moving Objects Detection under Complex Background Based on ViBe 计算机科学, 2017, 44(9): 304-307. https://doi.org/10.11896/j.issn.1002-137X.2017.09.057 |
[2] | 易盟,楚岩. 基于仿射不变约束与快速EKF滤波的航拍图像稳像 Aerial Video Image Stabilization Based on Affine Invariant Constraint and Fast EKF Adaptive Filter 计算机科学, 2016, 43(8): 313-317. https://doi.org/10.11896/j.issn.1002-137X.2016.08.064 |
[3] | 姬莉霞,李学相. 基于相邻帧补偿的高速运动目标图像稳像算法及仿真 Algorithm and Simulation of Image Stabilization for High Speed Moving Target Images Based on Adjacent Frames Compensation 计算机科学, 2014, 41(7): 310-312. https://doi.org/10.11896/j.issn.1002-137X.2014.07.064 |
[4] | 李鹏杰 杨树元. 运动目标自动特征提取与跟踪 计算机科学, 2002, 29(z2): 174-178. |
|