A Novel Simple Visual Tracking Algorithm Based on Hashing and Deep Learning. Issue 5 (1st September 2017)

• Record Type: Journal Article
• Authors: Zhu, Suguo; Du, Junping; Ren, Nan
• Is Part Of: Chinese journal of electronics. Volume 26:Issue 5(2017)
• Page Start: 1073
• Page End: 1078
• Publication Date: 2017-09-01
• Subjects: Visual tracking -- Image perceptual hashing -- Deep learning -- Neural network.; backpropagation -- learning (artificial intelligence) -- neural nets -- object detection -- visual perception; visual tracking algorithm -- deep learning -- deep network -- object features -- object classification -- object detection -- six‐layer feed‐forward backpropagation neural network -- image perceptual hashing -- word length 64 bit; Electronics -- Periodicals; Electronics -- China -- Periodicals; Electronics; China; Periodicals; 621.38105
• DOI: 10.1049/cje.2016.06.026
• Languages: English
• ISSNs: 1022-4653

Abstract

Abstract : Deep network has been proven efficient and robust to capture object features in some conditions. It still remains in the stage of classifying or detecting objects. In the field of visual tracking, deep network has not been applied widely. One of the reasons is that its time consuming made the strong method could not meet the speed need of visual tracking. A novel simple tracker is proposed to complete tracking task. A simple six‐layer feed‐forward backpropagation neural network is applied to capture object features. Nevertheless, this representation is not robust enough when illumination changes or drastic scale changes in dynamic condition. To improve the performance and not to increase much time spent, image perceptual hashing method is employed, which extracts low frequency information of object as its fingerprint to recognize the object from its structure. 64‐bit characters are calculated by it, and they are utilized to be the bias terms of the neutral network. This leads more significant improvement for performance of extracting sufficient object features. Then we take particle filter to complete the tracking process with the proposed representation. The experimental results demonstrate that the proposed algorithm is efficient and robust compared with the state‐of‐the‐art tracking methods.