摘要
Recently,deep learning has achieved great success in visual tracking tasks,particularly in single-object tracking.This paper provides a comprehensive review of state-of-the-art single-object tracking algorithms based on deep learning.First,we introduce basic knowledge of deep visual tracking,including fundamental concepts,existing algorithms,and previous reviews.Second,we briefly review existing deep learning methods by categorizing them into data-invariant and data-adaptive methods based on whether they can dynamically change their model parameters or architectures.Then,we conclude with the general components of deep trackers.In this way,we systematically analyze the novelties of several recently proposed deep trackers.Thereafter,popular datasets such as Object Tracking Benchmark(OTB)and Visual Object Tracking(VOT)are discussed,along with the performances of several deep trackers.Finally,based on observations and experimental results,we discuss three different characteristics of deep trackers,i.e.,the relationships between their general components,exploration of more effective tracking frameworks,and interpretability of their motion estimation components.
基金
supported by National Natural Science Foundation of China(Nos.61922064 and U2033210)
Zhejiang Provincial Natural Science Foundation(Nos.LR17F030001 and LQ19F020005)
the Project of Science and Technology Plans of Wenzhou City(Nos.C20170008 and ZG2017016)。