Moving Object Detection Based on Deep Convolutional Neural Network

doi:10.16182/j.issn1004731x.joss.19-FZ0368

Abstract

Abstract: A deep convolution neural network MONet is designed for the intermittent motion problem in moving objects detection. In the absence of training data sets, a synthetic dataset GoChairs is generated by affine transformation, and on this basis the network training and testing are performed. The results show that the trained MONet can effectively detect the moving objects based on the correspondence between the pixels. The traditional datasets CDnet and I2R are also tested to verify the generalization performance of the network. In addition, MONet is compared qualitatively and quantitatively with classical methods for the intermittent motion problem of the objects. The experimental results demonstrate the superiority of the network in detecting the objects with intermittent motion.

Key words: moving object detection, intermittent motion, deep convolutional neural network, synthetic dataset

CLC Number:

TP391.4

Lu Yuqiu, Sun Jinyu, Ma Shiwei. Moving Object Detection Based on Deep Convolutional Neural Network[J]. Journal of System Simulation, 2019, 31(11): 2275-2280.

References

[1] Pankaj D.Real-Time Surveillance for Critical Activity Detection in ICUs[C]. Proceedings of the Second International Conference on Computer and Communication Technologies. New Delhi: Springer, 2016.
[2] Tian B, Morris B T, Tang M, et al.Hierarchical and Networked Vehicle Surveillance in ITS: A Survey[J]. IEEE Transactions on Intelligent Transportation Systems (S1558-0016), 2017, 18(1): 25-48.
[3] Robertson N, Reid I.A general method for human activity recognition in video[J]. Computer Vision and Image Understanding (S1077-3142), 2006, 104(2/3): 232-248.
[4] Nait-Charif H, Mc Kenna S J. Head Tracking and Action Recognition in a Smart Meeting Room[J]. IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (S2157-491X), 2003.
[5] C H Anderson, P J Burt, G S van der Wal. Change detection and tracking using pyramid transform techniques[C]. Cambridge: Proc. SPIE, 1985.
[6] Wren C, Azarbayejani A, Darrell T, et al.Pfinder: real-time tracking of the human body[J]. Transaction on Pattern Analysis and Machine Intelligence (S1939-3539), 1996.
[7] Stauffer C, Grimson W E L. Adaptive Background Mixture Models for Real-Time Tracking[C]. Proc Computer Vision & Pattern Recognition, IEEE, 1999.
[8] Elgammal A, Harwood D, Davis L.Non-parametric Model for Background Subtraction[C]. European Conference on Computer Vision. Berlin: Springer, 2000.
[9] Barnich O, Droogenbroeck M V.VIBE: A powerful random technique to estimate the background in video sequences[C]. International Conference on Acoustics, Speech and Signal Processing. Taipei: IEEE, 2009.
[10] Candes E, Li X, Ma Y, et al.Robust principal component analysis[J]. Journal of the ACM (S1557-735X), 2011, 58(3): 11.
[11] Ding X.Bayesian Robust Principal Component Analysis[J]. IEEE Transactions on Image Processing (S1941-0042), 2011, 20(12): 3419.
[12] Jun He.Incremental gradient on the Grassmannian for online foreground and background separation in subsampled video[C]. CVPR. Providence: IEEE, 2012, 157: 1568-1575.
[13] Horn B K P, Schunck B G. Determining Optical Flow[C]. Artificial Intelligence, Washington, 1981.
[14] Lucas B D, Kanade T.An iterative image registration technique with an application to stereo vision[C]. International Joint Conference on Artificial Intelligence. San Francisco: Morgan Kaufmann Publishers, 1981.
[15] Bouguet J Y.Pyramidal implementation of the affine Lucas-Kanade feature tracker description of the algorithm[R]. Intel Corporation, 2001.
[16] Dosovitskiy A.Flownet: Learning optical ?ow with convolutional networks[C]. ICCV, 2015.
[17] Ranjan A, Black M J.Optical Flow Estimation using a Spatial Pyramid Network[C]. CVPR, 2016.
[18] Ahmadi A, Patras I.Unsupervised convolutional neural networks for motion estimation[C]. ICIP. Phoenix: IEEE, 2016.
[19] Aubry M.Seeing 3D Chairs: Exemplar Part-Based 2D-3D Alignment Using a Large Dataset of CAD Models[C]. CVPR. Columbus: IEEE, 2014.
[20] Goyette N, Jodoin P M, Porikli F, et al.Changedetection. net: A new change detection benchmark dataset[C]. CVPR. Providence: IEEE, 2012.
[21] Li L.Statistical modeling of complex backgrounds for foreground object detection[J]. IEEE Transactions on Image Processing (S1941-0042), 2004, 13(11): 1459.
[22] Zhou X, Yang C, Yu W.Moving Object Detection by Detecting Contiguous Outliers in the Low-Rank Representation[J]. Transactions on Pattern Analysis and Machine Intelligence (S1939-3539), 2013, 35(3): 597-610.