Visual tracking and recognition using appearance-adaptive models in particle filters

By Shaohua Kevin Zhou, Ramalingam Chellappa, Baback Moghaddam. IEEE Transactions on Image Processing, 2004

743 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/88e91ef20f508b07862ac01253c2514c48ab9315

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Robust Visual Tracking via Structured Multi-Task Sparse Learning (2012, methodology): “In Zhou et al. (2004), the number of particle samples is adjusted according to an adaptive noise component.”
Shadow detection: A survey and comparative evaluation of recent methods (2012, background): “for initialisation of particle filters [51]) or during tracking (eg.”
A survey of appearance models in visual object tracking (2013, methodology): “…Wu 2006] [Wang et al. 2007] Spatio-color GMM — — Spatial-color appearance model using GMM Spatial-color mixture of Gaussians (SMOG) 3 [Jepson et al. 2003; Zhou et al. 2004] WSL — — three-component mixture models: W-component, S-component, L-component 4 [Comaniciu et al. 2003] [Leichter et al.…”
Minimum error bounded efficient ℓ1 tracker with occlusion detection (2011, background): “In [28], it adjusts the number of particle samples based on the noise variance.”
Recent advances and trends in visual tracking: A review (2011, methodology): “Zhou et al. [71] embedded appearance adaptive models into a particle ﬁlter to achieve a robust visual tracking.”
Multi-task Correlation Particle Filter for Robust Object Tracking (2017, methodology): “Consequently, numerous techniques have been presented to improve the sampling efficiency of particle filtering [19, 6, 20, 48].”
Robust visual tracking using ℓ1 minimization (2009, methodology): “The proposed approach shows excellent performance in comparison with three previously proposed trackers, including the Mean Shift (MS) tracker [9], the covariance (CV) tracker [27], and the appearance adaptive particle filter (AAPF) tracker [34].”
Robust tracking using local sparse appearance model and K-selection (2011, methodology): “The generative models formulate the tracking problem as searching for the regions with the highest likelihood [5] [7] [16] [18] [19] [25] [28] [15], either using a single appearance model or multiple appearance models [27].”
Robust Visual Tracking using 1 Minimization (2009, methodology): “In our experiments, we compare the tracking results of our proposed method with those of state-of-the-art standard Mean Shift (MS) tracker [9], covariance (CV) tracker [27], and appearance adaptive particle filter (AAPF) tracker [34].”
Robust Visual Tracking and Vehicle Classification via Sparse Representation (2011, methodology): “There are also recent studies using particle filters similar to our method [19], [47].”