DOI: 10.14704/nq.2018.16.6.1664

A Visual Tracking Algorithm in Large-Scale Video with Convolutional Neural Networks

Ying Wang, Xiaoju Ning

Abstract


Convolutional Neural Networks (CNNs) had become a powerful model for solving many problems. In this paper, a novel visual tracking algorithm in large scale video based a trained CNN is proposed. The algorithm can track the trajectory of a moving object in a video with complex background quite precisely. Different from the most existing algorithms, we offline pre-trained a CNN through massive images data to obtain generic image features, which can be used the online tracking process. The trained CNN consists of shared layers and multiple branches of domain-specific layers, each branch is used for classification to identify target in each domain. When tracking a moving object in a new video sequence, a new network by combining the shared layers in the pre-trained CNN with a new classification layer is constructed. Experiment results show that performance of the proposed algorithm is excellent for some representative tracking benchmarks.

Keywords


Convolutional Neural Networks, Visual Tracking, Classification Layer, Offline Training

Full Text:

PDF

References


Avidan S. Ensemble Tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence 2007; 29(2): 261-71.

Cai Z, Han J, Liu L. RGB-D datasets using microsoft kinect or similar sensors: a survey. Multimedia Tools & Applications 2017; 76(3): 4313-55.

Chen S, Zhu S, Yan Y. Robust visual tracking via online semi-supervised co-boosting. Multimedia Systems 2016; 22(3): 297-313.

Kalal Z, Mikolajczyk K, Matas J. Tracking-Learning-Detection. IEEE Transactions on Pattern Analysis & Machine Intelligence 2012; 34(7): 1409-22.

Kumar PV, Kumar AVS. A novel framework for specific object tracking in the multiple moving objects environment. International Journal of Applied Engineering Research 2015; 10(16): 37445-50.

Lecun Y, Bottou L, Bengio Y. Gradient-based learning applied to document recognition. Proceedings of the IEEE 1998; 86(11): 2278-324.

Mahadevan V, Vasconcelos N. Biologically inspired object tracking using center-surround saliency mechanisms. IEEE Transactions on Pattern Analysis & Machine Intelligence 2013; 35(3): 541-54.

Shi H, Lin Z, Tang W. A robust hand tracking approach based on modified tracking-learning-detection algorithm. Lecture Notes in Electrical Engineering 2014; 30(8): 9-15.

Sun G, Bin S. Router-level internet topology evolution model based on multi-subnet composited complex network model. Journal of Internet Technology 2017; 18(6): 1275-83.

Sun G, Bin S. A new opinion leaders detecting algorithm in multi-relationship online social networks. Multimedia Tools & Applications 2018; 77(4): 4295–307.

Wang P, Qian W, Chen Q. Robust visual tracking with contiguous occlusion constraint. Optical Review 2016; 23(1): 40-52.

Xie Y, Qu Y, Li C. Online multiple instance gradient feature selection for robust visual tracking. Pattern Recognition Letters 2012; 33(9): 1075-82.


Supporting Agencies





| NeuroScience + QuantumPhysics> NeuroQuantology :: Copyright 2001-2017