Please enable JavaScript.
Coggle requires JavaScript to display documents.
Visual Object Tracking (Challenges (Deformation, Illumination variation,…
Visual Object Tracking
Methods
Discriminative
CF: Correlation Filter
CSK
KCF: Kernelized Correlation Filters (TPAMI 2015)
CN: Adaptive Color Attributes for Real-Time Visual Tracking (CVPR 2014)
fDSST: Discriminative Scale Space Tracking (TPAMI 2017)
TLD: Tracking-learning-detection (TPAMI 2012)
Struck: Structured output tracking with kernels (TPAMI 2016)
Deep Learning
MDNet: Learning multi-domain convolutional neural networks for visual tracking (CVPR 2016)
TCNN: Modeling and propagating cnns in a tree structure for visual tracking (CVPR 2017)
SiamFC: Fully-convolutional siamese networks for object tracking (ECCV 2016)
GOTURN: Generic Object Tracking Using Regression Networks (ECCV 2016)
ECO: Efficient Convolution Operators for Tracking (CVPR 2017)
概觀
Generative
Kalman Filter
Particle Filter
Mean-shift
ASMS
: Scale Adaptive Mean-Shift (125fps)
Optical flow
Benchmark
OTB
VOT
王強
visual tracker benchmark results
Hakase
CF benchmark
Researchers
[US UCM]
Ming-Hsuan Yang (楊明玄)
[SE Linköping]
Martin Danelljan
[GB Oxford]
Torr Vision Group
[Korea]
POSTECH Computer Vision Lab
[GB Oxford]
João F. Henriques
Challenges
Deformation
Illumination variation
Blur & fast motion
Background clutter
Out-of-plane rotation
In-plane rotation
Scale variation
Occlusion
Out-of-view