计算机科学 ›› 2015, Vol. 42 ›› Issue (2): 283-286.doi: 10.11896/j.issn.1002-137X.2015.02.060
曹倩霞,罗大庸,王正武
CAO Qian-xia, LUO Da-yong and WANG Zheng-wu
摘要： 针对前景检测中光照突变问题和非平稳背景扰动问题,提出一种块级-像素级分层背景差分结合Phong模型的前景检测方法。首先,利用块级Sigma-delta背景差分算法快速检测前景区域且有效处理非平稳背景,然后利用Phong模型对前景区域进行光照突变处理提取出粗目标,最后利用像素级Sigma-delta算法对粗目标执行像素级前景提纯操作和对背景进行更新。实验表明,该方法在光照突变场景中及非平稳背景中能鲁棒实现前景检测。
| [1] Reddy V,Sanderson C,Lovell B C.Improved foreground detection via block-based classifier cascade with probabilistic decision integration[J].IEEE Transactions on Circuits and System for Video Technology, 2013,3(1) [2] 程全,马军勇.基于改进高斯混合模型的运动目标检测方法[J].计算机科学,2014,1(7):318-321 [3] Zhu Q,Shao L,Li Q,et al.Recursive Kernel Density Estimation for modeling the background and segmenting moving objects[C]∥2013 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).IEEE,2013:1769-1772 [4] Pal A,Schaefer G.Robust background modelling using region–based codebooks[J].International Journal of Advanced Media and Communication,2014,5(2):233-244 [5] Manzanera A,Richefeu J C.A new motion detection algorithm based on sigma-delta background estimation[J].Pattern Recognition Letters,2007,8(3):320-328 [6] 原春锋,王传旭,张祥光,等.光照突变环境下基于高斯混合模型和梯度信息的视频分割[J].中国图象图形学报,2007,2(11):2068-2072 [7] 李加佳,彭启民.适应光照突变的运动目标检测算法[J].计算机辅助设计与图形学学报,2012,4(11):1405-1409 [8] Choi J M,Chang H J,Yoo Y J,et al.Robust moving object detection against fast illumination change[J].Computer Vision and Image Understanding,2012,6(2):179-193 [9] Phong B.Illumination for computer generated pictures[J].Communications of the ACM Commun.ACM, 1975,18(6):311-317 [10] Davis J,Sharma V.Background-Subtraction using Contour-based Fusion of Thermal and Visible Imagery[J].Computer Vision and Image Understanding,2007,106(2/3) [11] PETS 2001 Benchmark Data.http://www.cvg.rdg.ac.uk/PETS2001/ |
| No related articles found! |
|
||
首页