Abstract
This paper proposes a moving target detection scheme suitable for camera motion. Firstly, the background model is initialized by a Gaussian mixture model algorithm. Then Kanade-Lucas-Tomasi Feature Tracker (KLT) method is used to detect optical flow feature points of two adjacent frames, RANdom SAmple Consensus (RANSAC) algorithm is used to filter out the correct matching points and obtain a homography matrix, which can recover the background model matching the current frame, the new background model is used to detect moving target of the current frame. In the foreground detection stage, the current pixel is first compared with its own background model, and then compared with the background model of its 8 neighborhood pixels, the algorithm is speeded up without reducing the detection accuracy in this way; In the update stage of the background model, in order to adapt to the background changes caused by camera motion, an age value variable is set for each pixel. The experimental results show that the improved algorithm has a significant improvement in detection accuracy and running time compared to Gaussian mixture background modeling.
Similar content being viewed by others
References
Luan QL, Zhao WS (2011) Moving object detection algorithm based on three-frame-difference of moving background and edge information. Opto Electron Eng 38(10):77–83
Xin Y, Jie H, Dong L et al (2014) A self-adaptive optical flow method for the moving object detection in the video sequences. Optik Int J Light Electron Optics 125(19):5690–5694
Yuan GW, Chen ZQ, Gong J et al (2013) A moving object detection algorithm based on a combination of optical flow and three-frame difference. J Chin Comput Syst 34(3):668–671
Motai Y, Jha SK, Kruse D (2012) Human tracking from a mobile agent: optical flow and Kalman filter arbitration. Signal Process Image Commun 27(1):83–95
Zeng ZY, Jiang ZQ, Chen Q et al (2012) An improved corner detection algorithm based on Harris. Comput Simul 6-7(11):717–721
Zhong QU, Zhang K, Qiao GY (2013) Research on algorithm of moving target detection and tracking based on MB-LBP feature extraction and particle filter. Comput Sci 659(12):75–78
Xue W, Jiang T (2018) An adaptive algorithm for target recognition using Gaussian mixture models. Measurement 124(1):233–240
Zivkovic Z (2004) Improved adaptive Gaussian mixture model for background subtraction. Pattern recognition, international conference on IEEE Computer Society, pp. 28–31.
Hu X, Zheng J (2016) An improved moving object detection algorithm based on Gaussian mixture models. Open J Appl Sci 06(7):449–456
Chen X, Xi C, Cao J (2015) Research on moving object detection based on improved mixture Gaussian model. J Image Graph 126(20):2256–2259
Liu G, You Y, Zheng S et al (2012) Moving target detection based on improved mixture gauss model. Commun Comput Inform 346:261–266
Azzam R, Kemouche MS, Aouf N et al (2016) Efficient visual object detection with spatially global Gaussian mixture models and uncertainties. J Vis Commun Image Represent 36(C):90–106
Yin C, Kan R, Gu G et al (2014) Moving object detection based on improved single Gaussian background model. Chin J Lasers 41(11):239–247
Xu H, Qian C, Qian W (2016) Target detection algorithm based on improved single Gaussian background model. Laser Optoelectron Prog 53(4):040401
Kai XU, Chen SX, Yan G (2012) Moving object detection based on improved Gaussian model. Laser Infrared 42(7):821–824
Li YF, Liu L, Song JX et al (2018) Combination of local binary pattern operator with sample consensus model for moving objects detection. Infrared Phys Technol 92(1):44–52
Wang H, Suter D (2007) A consensus-based method for tracking: modelling background scenario and foreground appearance. Pattern Recogn 40(3):1091–1105
Barnich O, Droogenbroeck MV (2011) ViBe: a universal background subtraction algorithm for video sequences. IEEE Trans Image Process Publ IEEE Signal Process Soc 20(6):1709–1724
Huang W, Liu L, Yue C et al (2015) The moving target detection algorithm based on the improved visual background extraction. Infrared Phys Technol 71(1):518–525
Hofmann M, Tiefenbacher P, Rigoll G (2012) Background segmentation with feedback: the pixel-based adaptive segmenter. Computer Vision and Pattern Recognition Workshops. IEEE, pp 38–43.
Mstafa RJ, Elleithy KM (2016) A video steganography algorithm based on Kanade-Lucas-Tomasi tracking algorithm and error correcting codes. Multimed Tools Appl 75(17):10311–10333
Schnabel R, Wahl R, Klein R (2010) Efficient RANSAC for point-cloud shape detection. Comput Graph Forum 26(2):214–226
Gao D, Yin F (2013) Computing a complete camera lens distortion model by planar homography. Opt Laser Technol 49(7):95–107
Guo X, Jiang G, Cui Z et al (2016) Homography-based block motion estimation for video coding of PTZ cameras. J Vis Commun Image Represent 39(1):164–171
Mstafa RJ, Elleithy KM (2016) A video steganography algorithm based on Kanade-Lucas-Tomasi tracking algorithm and error correcting codes. Multimed Tools Appl 75(17):10311–10333
Xue S, Yu L, Xiaoli L et al (2017) Gaussian mixture model with neighbor relationship for image segmentation and simplified solving method. J Image Graph 22(12):1758-1768
Brutzer S, Hoferlin B, Heidemann G (2011) Evaluation of background subtraction techniques for video surveillance. IEEE conference on computer vision and pattern recognition. IEEE Computer Society, pp. 1937–1944.
Liu B, Wu H, Su W et al (2017) Sector-ring HOG for rotation-invariant human detection. Signal Process Image Commun 54(1):1–10
Bouwmans T, Silva C, Marghes C et al (2018) On the role and the importance of features for background modeling and foreground detection. Comput Sci Rev 28(1):26–91
Zhang S, Yao H, Liu S (2009) Spatial-temporal nonparametric background subtraction in dynamic scenes. IEEE international conference on multimedia and expo, pp 518–521.
Zhang S, Yao H, Liu S (2009) Dynamic background subtraction based on local dependency histogram. Int J Pattern Recognit Artif Intell 23(7):1397–1419
Zhang S, Lan X, Yao H, Zhou H, Tao D, Li X (2017) A biologically inspired appearance model for robust visual tracking. IEEE Trans Neural Netw Learn Syst 28(10):2357–2370
Acknowledgements
The research was partly supported by the National Natural Science Foundation of China (No.61502340), the Natural Science Foundation of Tianjin (No.18JCYBJC87700), the South African National Research Foundation Incentive Grant (No.114911) and the Tertiary Education Support Programme (TESP) of South African ESKOM.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Dong, E., Han, B., Jian, H. et al. Moving target detection based on improved Gaussian mixture model considering camera motion. Multimed Tools Appl 79, 7005–7020 (2020). https://doi.org/10.1007/s11042-019-08534-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-08534-9