Reliable Patch Trackers: Robust visual tracking by exploiting reliable patches

A Comprehensive Performance Evaluation of Deformable Face Tracking “In-the-Wild”

“…In contrast to the linear regression commonly used to learn DCFs, Henriques et al (2015) apply a kernel regression and propose its multi-channel extension to enable to the use of features such as HOG Dalal and Triggs (2005). Li et al (2015b) propose a new use for particle filters in order to choose reliables patches to consider part of the object. These patches are modelled using a variant of the method proposed by Henriques et al (2015).…”

“…SPOT (Zhang and van der Maaten 2014) is a strong performing part based tracker, CMT (Nebehay and Pflugfelder 2015) is a strong performing keypoint based tracker, LRST (Zhang et al 2014d) and ORIA (Wu et al 2012) are recent generative trackers. RPT (Li et al 2015b) is a recently proposed technique that reported state-of-the-art results on the Online Object Tracking benchmark . TLD (Kalal et al 2012), MIL (Babenko et al 2011), FCT (Zhang et al 2014c), DF (Sevilla-Lara and Learned-Miller 2012) and IVT (Ross et al 2008) were included as baseline tracking methods with publicly available implementations.…”

Consistent multi-layer subtask tracker via hyper-graph regularization

“…Recently, an efficient tracking algorithm [7] based on compressive sensing theory is proposed. Correlation filter has been widely used in object tracking area with good performance and high speed [38][39][40][41][42] . Henriques et al [41] introduce a fast tracking algorithm, which exploits the circular structure of the kernel matrix that can be efficiently computed by the fast fourier transform algorithm.…”

“…Henriques et al [41] introduce a fast tracking algorithm, which exploits the circular structure of the kernel matrix that can be efficiently computed by the fast fourier transform algorithm. Li et al [42] propose reliable patch trackers (RPT), which attempts to identify and exploits the reliable patches that can be tracked effectively through the whole tracking process. Based on the framework of correlation filter tracker and Bayesian inference, Liu et al [43] develop a real-time part-based tracker by using adaptive weighing, updating and structure masking method.…”

Combining Color Features for Real-Time Correlation Tracking

“…We compare our approach with 11 state-of-the-art trackers: CN [9], CSK [3], DSST [6], KCF [4], PCOM [10], RPT [11], SAMF [12], SRDCF [13], STC [14], Struck [15] and TGPR [16]. For fair evaluations, all the trackers are tested under the same experimental conditions.…”