计算机科学 ›› 2017, Vol. 44 ›› Issue (5): 294-298.doi: 10.11896/j.issn.1002-137X.2017.05.054
汪荣琪,郑林,王标
WANG Rong-qi, ZHENG Lin and WANG Biao
摘要： 针对像素层自适应分割算法(Pixel Based Adaptive Segmenter,PBAS)在动态背景下检测准确率低、静止或运动缓慢的前景目标被更新为背景以及出现鬼影干扰的问题,提出了一种 结合 像素级信息和区域级信息的改进的前景检测算法。首先,提出一种融合区域结构信息和区域颜色信息的背景复杂度衡量方式；然后,采用改进的背景复杂度来控制判定阈值和学习率,并检测前景；其次,对像素层的检测结果使用区域窗口进行空间邻域对比,以消除鬼影；最后,引入前景计数机制来保证静止前景不被更新为背景。实验结果表明,该算法对光照条件和前景运动速度不敏感,能有效地从背景中检测出完整的前景目标,并迅速地消除鬼影干扰,准确率达到了92.7%。
| [1] SOBRAL A,VACAVANT A.A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos[J].Computer Vision & Image Understanding,2014,122(5):4-21. [2] YE F F,XU L.Real-time detection and discrimination of staticobjects and ghosts[J].Journal of Zhejiang University(Enginee-ring Science),2015,49(1):181-185.(in Chinese) 叶芳芳,许力.实时的静止目标与鬼影检测及判别方法[J].浙江大学学报(工学版),2015,49(1):181-185. [3] WU D P,CHENG W P,YU S L.Camshift Object Tracking Algorithm Based on inter-frame Difference and Motion Prediction[J].Opto-Electronic Engineering,2010,37(1):55-60.(in Chinese) 邬大鹏,程卫平,于盛林.基于帧间差分和运动估计的Camshift目标跟踪算法[J].光电工程,2010,37(1):55-60. [4] BARNICH O,VAN DROOGENBROECK M.ViBe:a universal background subtraction algorithm for video sequences[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2011,20(6):1709-1724. [5] CRISTANI M,MURINO V.Background Subtraction with A-daptive Spatio-Temporal Neighborhood Analysis[C]∥The 3rd International Conference on Computer Vision Theory and Applications.2008:484-489. [6] WEI G J,HOU Z Q,LI W,et al.Objecet tracking algorithmfused with optical flow detection and template matching[J].Application Reasearch of Computer,2014,31(11):3498-3501(in Chinese) 魏国剑,侯志强,李武,等.融合光流检测与模板匹配的目标跟踪算法[J].计算机应用研究,2014,31(11):3498-3501 [7] DALAL N,TRIGGS B.Histograms of Oriented Gradients for Human Detection[C]∥IEEE Conference on Computer Vision & Pattern Recognition.2005:886-893. [8] LIU X,LIU H,QIANG Z P,et al.Adaptive Background Mode-ling Based on Mixture Gaussian Model[J].Journal of Image and Graphics,2008,3(4):729-734.(in Chinese) 刘鑫,刘辉,强振平,等.混合高斯模型和帧间差分相融合的自适应背景模型[J].中国图象图形学报,2008,3(4):729-734. [9] FAN W C,LI X Y,WEI K,et al.Moving Target Detection Based On Improved Gaussion Mixture Model[J].Computer Science,2015,42(5):286-288,319.(in Chinese) 范文超,李晓宇,魏凯,等.基于改进的高斯混合模型的运动目标检测[J].计算机科学,2015,2(5):286-288,319. [10] ILYAS A,SCUTURICI M,MIGUET S.Real Time Foreground-Background Segmentation Using a Modified Codebook Model[C]∥Proceedings of the 2009 Sixth IEEE International Confe-rence on Advanced Video and Signal Based Surveillance.IEEE Computer Society,2009:454-459. [11] HOFMANN M,TIEFENBACHER P,RIGOLL G.Backgroundsegmentation with feedback:The Pixel-Based Adaptive Segmenter[C]∥IEEE Computer Society Conference on Computer Vision & Pattern Recognition Workshops.IEEE,2012:38-43. [12] WANG H,SUTER D.Background Subtraction Based on a Robust Consensus Method[C]∥International Conference on Pattern Recognition.2006:223-226. [13] BARNICH O,VAN DROOGENBROEK M.Vibe:A universal background subtraction algorithm for video sequences[J].IEEE Transactions on Image Processing,2011,20(6):1709-1724. [14] LI P,WU X H,HE X H,et al.An Improved PBAS For Moving Object Detection[J].Science Technology and Eiginee-ring,2015,15(27):48-53.(in Chinese) 李棚,吴晓红,何小海,等.一种改进的PBAS运动目标检测算法[J].科学技术与工程,2015,15(27):48-53. [15] KRYJAK T,KOMORKIEWICZ M,GORGON M.Real-timeForeground Object Detection Combining the PBAS Background Modelling Algorithm and Feedback from Scene Analysis Mo-dule[J].International Journal of Electronics & Telecommunications,2014,60(1):53-64. [16] WANG H,SUTER D.Background Subtraction Based on a Robust Consensus Method[C]∥International Conference on Pattern Recognition.IEEE Computer Society,2006:223-226. |
| No related articles found! |
|
||
首页