Dual-scale structural local sparse appearance model for robust object tracking

2017 ◽  
Vol 237 ◽  
pp. 101-113 ◽  
Author(s):  
Zhiqiang Zhao ◽  
Ping Feng ◽  
Tianjiang Wang ◽  
Fang Liu ◽  
Caihong Yuan ◽  
...  
Keyword(s):  
Object Tracking ◽  
Appearance Model ◽  
Dual Scale

scholarly journals Dual‐scale weighted structural local sparse appearance model for object tracking

2019 ◽  
Vol 13 (2) ◽  
pp. 146-156 ◽  
Author(s):  
Xianyou Zeng ◽  
Long Xu ◽  
Yigang Cen ◽  
Ruizhen Zhao ◽  
Wanli Feng
Keyword(s):  
Object Tracking ◽  
Appearance Model ◽  
Dual Scale

scholarly journals Self-balance Motion and Appearance Model for Multi-object Tracking in UAV

2019 ◽  
Author(s):  
Hongyang Yu ◽  
Guorong Li ◽  
Weigang Zhang ◽  
Hongxun Yao ◽  
Qingming Huang
Keyword(s):  
Object Tracking ◽  
Appearance Model

scholarly journals Adaptive Channel Selection for Robust Visual Object Tracking with Discriminative Correlation Filters

2021 ◽  
Author(s):  
Tianyang Xu ◽  
Zhenhua Feng ◽  
Xiao-Jun Wu ◽  
Josef Kittler
Keyword(s):  
Object Tracking ◽  
Augmented Lagrangian Method ◽  
Channel Selection ◽  
Image Feature ◽  
Superior Performance ◽  
Appearance Model ◽  
Visual Object ◽  
Correlation Filters ◽  
Visual Object Tracking ◽  
Feature Representations

AbstractDiscriminative Correlation Filters (DCF) have been shown to achieve impressive performance in visual object tracking. However, existing DCF-based trackers rely heavily on learning regularised appearance models from invariant image feature representations. To further improve the performance of DCF in accuracy and provide a parsimonious model from the attribute perspective, we propose to gauge the relevance of multi-channel features for the purpose of channel selection. This is achieved by assessing the information conveyed by the features of each channel as a group, using an adaptive group elastic net inducing independent sparsity and temporal smoothness on the DCF solution. The robustness and stability of the learned appearance model are significantly enhanced by the proposed method as the process of channel selection performs implicit spatial regularisation. We use the augmented Lagrangian method to optimise the discriminative filters efficiently. The experimental results obtained on a number of well-known benchmarking datasets demonstrate the effectiveness and stability of the proposed method. A superior performance over the state-of-the-art trackers is achieved using less than $$10\%$$ 10 % deep feature channels.

Appearance Model Based Moving Object Matching across Disjoint Camera Views

2013 ◽  
Vol 760-762 ◽  
pp. 1322-1326
Author(s):  
Kong Shuai Yu ◽  
Dong Hu
Keyword(s):  
Principal Component Analysis ◽  
Transfer Function ◽  
Object Tracking ◽  
Real World ◽  
Principal Component ◽  
Appearance Model ◽  
Color Spectrum ◽  
Probabilistic Principal Component Analysis ◽  
Camera Surveillance ◽  
Disjoint Camera Views

A new object tracking scheme for multi-camera surveillance with non-overlapping views is proposed in this paper. Brightness transfer function (BTF) is used to establish relative appearance correspondence between different views. Mixtures of probabilistic principal component analysis (MPPCA) is incooperated to learn the subspace of brightness transfer function with the concern to deal with multiple different brightness areas in a scene. The incremental major color spectrum histogram (IMCSH) is used as similarity measure for reliable matching. Experimental results with real world videos show the effectiveness of the proposed algorithm.

Robust object tracking based on local region sparse appearance model

2016 ◽  
Vol 184 ◽  
pp. 145-167 ◽  
Author(s):  
Guang Han ◽  
Xingyue Wang ◽  
Jixin Liu ◽  
Ning Sun ◽  
Cailing Wang
Keyword(s):  
Object Tracking ◽  
Local Region ◽  
Appearance Model
Sign in / Sign up

Export Citation Format

Share Document