Journal of System Simulation ›› 2018, Vol. 30 ›› Issue (11): 4276-4283.doi: 10.16182/j.issn1004731x.joss.201811028

Previous Articles     Next Articles

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

Jiang Mingxin1, Pan Zhigeng2,3, WangLanfang4, Hu Taoxin5, *   

  1. 1. Faculty of Electronic information Engineering, Huaiyin Institute of Technology, Huaian 223003, China;
    2. Nine D virtual reality research institute, Guangzhou Nine D digital technology co., Ltd. Guangzhou 510623, China;
    3. Digital Media &Interaction Research Center, Hangzhou Normal University, Hangzhou 310012, China;
    4. Faculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian 223003, China;
    5. College of Techer Education, Wenzhou University, Wenzhou 325035, China
  • Received:2018-04-17 Revised:2018-05-31 Published:2019-01-04

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: