Moving object detection method based on complementary multi resolution background models

Abstract

A novel moving object detection method was proposed in order to adapt the difficulties caused by intermittent object motion, thermal and dynamic background sequences. Two groups of complementary Gaussian mixture models were used. The ghost and real static object could be classified by comparing the similarity of the edge images further. In each group, the multi resolution Gaussian mixture models were used and dual thresholds were applied in every resolution in order to get a complete object mask without much noise. The computational color model was also used to depress illustration variations and light shadows. The proposed method was verified by the public test sequences provided by the IEEE Change Detection Workshop and compared with three state-of-the-art methods. Experimental results demonstrate that the proposed method is better than others for all of the evaluation parameters in intermittent object motion sequences. Four and two in the seven evaluation parameters are better than the others in thermal and dynamic background sequences, respectively. The proposed method shows a relatively good performance, especially for the intermittent object motion sequences.

Keywords

moving object detection / complementary Gaussian mixture models / intermittent object motion / thermal and dynamic background

References

[1] CheungS S, KamathC. Robust background subtraction with foreground validation for urban traffic video [J]. Eurasip Journal on Applied Signal Processing, 2005, 2005(14): 2330-2340

[2] ZhuQ, LiuH-l, ChenB-q, LiJ-j, WanQ, SunM, YuanX-fang. An improved method for multiple targets tracking [J]. Journal of Central South University, 2012, 19(10): 2852-2859

[3] WeiL, NguyenA V, LeeE J. Real-time recognition of humans by their walk [J]. International Journal of Intelligent Information and Database Systems, 2011, 5(1): 24-38

[4] GoyetteN, JodoinP M, PorikliF, KonradJ, IshwarP. Changedetection.net: A new change detection benchmark dataset [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2012, Piscataway, NJ, USA, IEEE: 1-8

[5] 1st IEEE Change Detection Workshop. Change Detection.net Video Database [EB/OL]. [2013-1-9]. http://www.changedetection.net/.

[6] HerasE R, SikoraT. Complementary background models for the detection of static and moving objects in crowded environments [C]. IEEE International Conference on Advanced Video and Signal Based Surveillance, 2011, Piscataway, NJ, USA, IEEE: 71-76

[7] HofmannM, TiefenbacherP, RigollG. Background segmentation with feedback: The pixel-based adaptive segmenter [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2012, Piscataway, NJ, USA, IEEE: 38-43

[8] HainesT S F, XiangTao. Background subtraction with Dirichlet processes [C]. European Conference on Computer Vision, 2012, Heidelberg, Germany, Springer Verlag: 99-113

[9] VanD M, PaquotO. Background subtraction: Experiments and improvements for ViBe [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2012, Piscataway, NJ, USA, IEEE: 32-37

[10] SchickA, BaumlM, StiefelhagenR. Improving foreground segmentations with probabilistic superpixel Markov random fields [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2012, Piscataway, NJ, USA, IEEE: 27-31

[11] KaewtrakulpongP, BowdenR. An improved adaptive background mixture model for real-time tracking with shadow detection [C]. Processing of Workshop on Advanced Video Based Surveillance Systems, 2001, Dordrecht, Netherlands, Kluwer Academic Publishers: 1-5

[12] ParksD H, FelsS. Evaluation of background subtraction algorithms with post-processing [C]. IEEE 5th International Conference on Advanced Video and Signal Based Surveillance, 2008, Piscataway, NJ, USA, IEEE: 192-199

[13] PiccardM. Background subtraction techniques: A review [C]. IEEE International Conference on Systems, Man and Cybernetics, 2004, Piscataway, NJ, USA, IEEE: 3099-3104

[14] TuL-f, ZhongS-d, PengQ, MeiT-can. Moving object detection based on Gaussian pyramid [J]. Journal of Central South University (Science and Technology), 2013, 44(7): 2778-2786

[15] HorprasertT, HarwoodD, DavisL S. A statistical approach for real-time robust background subtraction and shadow detection [C]. IEEE International Conference on Computer Vision, 1999, Piscataway, NJ, USA, IEEE: 1-19

[16] DongX, WangK-d, JiaG-hua. Moving object and shadow detection based on RGB color space and edge ratio [C]. Proceedings of the 2009 2nd International Congress on Image and Signal Processing, 2009, Piscataway, NJ, USA, IEEE: 1-5

[17] BRADSKI G, KAEBLER A. Learning OpenCV [M]. YU Shi-qi, LIU Rui-zhen. Beijing: Tsinghua University Press, 2009: 259–268. (in Chinese)

[18] SuzukiS, AbeK. Topological structural analysis of digitized binary images by border following [J]. Computer Vision, Graphics, and Image Processing, 1985, 30(1): 32-46

[19] CannyJ. A computational approach to edge detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698

[20] PengQ, ZhongS-d, TuL-fen. Cast shadow detection for moving objects based on binocular stereo vision [J]. Journal of Central South University, 2014, 21(2): 651-658