Visual Object Tracking Algorithm Based on Deep Denoising Autoencoder over RGB-D Data

doi:10.16182/j.issn1004731x.joss.201811028

Abstract

Abstract: A visual object tracking algorithm based on cross-modality features deep learning over RGB-D data is proposed. A sparse denoising autoencoder deep learning network is constructed, which can extract cross-modal features of the samples in RGB-D video data. The cross-modal features of the samples are input to the logistic regression classifier, the observation likelihood model is established according to the confidence score of the classifier, and the reasonable state transition model is established. The object tracking results over RGB-D data are obtained using particle filtering algorithm. Experimental results show that the proposed method has strong robustness to abnormal changes. The algorithm can steadily track multiple targets with higher accuracy.

Key words: Cross-modal features, sparse denoising autoencoder, deep learning, visual object tracking over RGB-D data

CLC Number:

TP391

Jiang Mingxin, Pan Zhigeng, WangLanfang, Hu Taoxin. Visual Object Tracking Algorithm Based on Deep Denoising Autoencoder over RGB-D Data[J]. Journal of System Simulation, 2018, 30(11): 4276-4283.

References

[1] 姜明新, 王培昌, 王洪玉. 基于视频多目标跟踪的高度测量算法[J]. 电子学报, 2015, 43(3): 591-596.
Jiang M X, Wang P C, Wang H Y.Height Estimation Algorithm Based on Visual Multi-Object Tracking[J]. Acta Electronica Sinica, 2015, 43(3): 591-596.
[2] Fan H, Xiang J.Robust Visual Tracking With Multitask Joint Dictionary Learning[J]. IEEE Transactions on Circuits & Systems for Video Technology (S1051-8215), 2017, 27(5): 1018-1030.
[3] Shao L, Han J, Xu D, et al.Computer vision for RGB-D sensors: Kinect and its applications[J]. IEEE Transactions on Cybernetics (S2168-2267), 2013, 43(5): 1314-1317.
[4] Jiang M X, Pan Z G, Tang Z Z.Visual Object Tracking Based on Cross-Modality Gaussian-Bernoulli Deep Boltzmann Machines with RGB-D Sensors[J]. Sensors (S1424-8220), 2017, 17(1): 121-138.
[5] Song S, Xiao J X.Tracking revisited using RGBD camera: unified benchmark and baselines[C]// Proceedings of the International Conference on Computer Vision (ICCV), Sydney, 2013: 233-240.
[6] Wang Ning-bo, Gong Xiao-jin, Liu Ji-lin.A new depth descriptor for pedestrian detection in RGB-D images[C]. 21st International Conference on Pattern Recognition (ICPR), Japan, 2012: 3688-3691.
[7] Munaro M, Basso F, Menegatti E.Tracking People within Groups with RGB-D Data[C]. IEEE International Conference on Intelligent Robots and Systems (IROS), Portugal, 2012: 2101-2107.
[8] Spinello L, Arras K O.People Detection in RGB-D Data[C]. IEEE International Conference on Intelligent Robots and Systems, Germany, 2011: 3838-3843.
[9] 姜明新, 邱天爽, 迟宏波. 基于颜色与深度信息特征融合的一种多目标跟踪新算法[J]. 光电子·激光, 2015, 26(7): 1342-1348.
Jiang M X, Qiu T S, Chi H B.An novel multi-object tracking algorithm based on RJMCMC with RGB and depth information fusion[J]. Journal of Optoelectronics·Laser, 2015, 26(7): 1342-1348.
[10] 高义鹏, 郑彬, 曾宪华. 基于RGB-D的在线多实例学习目标跟踪算法[J]. 计算机工程与设计, 2015, 36(7): 1865-1870.
Gao Y P, Zheng B, Zeng X H.Real-time object tracking via online RGB-D multiple instance learning[J]. Computer Engineering and Design, 2015, 36(7): 1865-1870.
[11] Wongun Choi, Caroline Pantofaru, Silvio Savarese.Detecting and tracking people using an RGB-D camera via multiple detector fusion[C]. IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, 2011: 1076-1083.
[12] Matthias Luber, Luciano Spinello, Kai Oliver Arras.People tracking in RGB-D Data with on-line boosted target models[C]. IEEE International Conference on Intelligent Robots and Systems (IROS), San Francisco, USA, 2011: 3844-3849.
[13] Luciano Spinello, Kai Oliver Arras.Leveraging RGB-D Data: Adaptive Fusion and Domain Adaptation for Object Detection[C]. IEEE International Conference on Robotics and Automation (ICRA), Minnesota, USA, 2012: 4469-4474.
[14] Hinton G E, Salakhutdinov R R.Reducing the dimensionality of data with neural networks[J]. Science (S0036-8075), 2006, 313(5786): 504-507.
[15] Jason Kuen, Kian Ming Lim, Chin Poo Lee.Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle[J]. Pattern Recognition (S0031-3203), 2015, 48: 2964-2982.
[16] Tang Yi-chuan.Deep learning using linear support vector machines[C]. Proceedings of International Conference on Machine Learning(ICML), Atlanta, USA, 2013: 266-272.
[17] 刘建伟, 刘媛, 罗雄麟. 深度学习研究进展[J]. 计算机应用研究, 2014, 31(7): 1921-1930.
Liu J W, Liu Y, Luo X L.Research and development on deep learning[J]. Application Research of Computers, 2014, 31(7): 1921-1930.
[18] Vincent P, Larochelle H, BengioY, et al. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations[C]. Proceedings of the International Conference on Machine Learning(ICML), New York, USA, 2009: 609-616.
[19] Yang Jun-lan, Schonfeld D, Mohamed M.Robust Video Stabilization Based on Particle Filter Tracking of Projected Camera Motion[J]. IEEE Transactions on Circuits And Systems For Video Technology, 2009, 19(7): 945-954.
[20] Nihat Kabaoglu.Target Tracking Using Particle Filters With Support Vector Regression[J]. IEEE Transactions on Vehicular Technology (S0018-9545), 2009, 58(5): 2569-2573.
[21] Kalal Z, Mikolajczyk K, Matas J.Tracking- Learning-Detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2012, 34(7): 1409-1422.
[22] Zhang Kai-hua, Zhang Lei, Yang Ming-Hsuan.Real-Time Compressive Tracking[C]. The European Conference on Computer Vision (ECCV), Firenze, Italy, 2012: 864-877.
[23] Kwon J, Lee K M.Visual tracking decomposition[C]. IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, USA, 2010: 1269-1276.
[24] Sam Hare, Amir Saffari, Philip H S Torr. Struck: Structured output tracking with kernels[C]. IEEE International Conference on Computer Vision (ICCV) , Barcelona, Spain, 2011: 263-270.
[25] Babenko B, Yang M H, Belongie S.Visual tracking with online multiple instance learning[C]. IEEE Conference on Computer Vision and Pattern Recognition, Miami Beach, USA, 2009: 983-990.