Fast multiple object tracking via a hierarchical particle filter

By Changjiang Yang, Ramani Duraiswami, Larry S. Davis. Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2005

412 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/0959fb8ea234bc396a2e2a7ff38374dd7d9a5193

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

1. Ming-Hsuan Yang
2. Luc Van Gool
3. Dacheng Tao
4. Xiaogang Wang
5. Andrea Vedaldi
6. Yi Yang
7. Chunhua Shen
8. Philip H. S. Torr

In Media Technology

1. Ming-Hsuan Yang
2. Thomas S. Huang
3. Narendra Ahuja
4. Bernard Ghanem
5. Wei Han
6. Shuicheng Yan
7. Wenhan Luo
8. Mehrtash Manafifard

Citations in the corpus

• Robust Visual Tracking using 1 Minimization (2009, methodology): “A hierarchical particle filter is used for multiple object tracking in [31].”
• Multiple Object Tracking Using K-Shortest Paths Optimization (2011, positive): “Particle filtering can address some of the limitations of Kalman filtering by exploring multiple hypotheses [13], [1], [14], [15], [16], [17].”
• Robust Visual Tracking via Structured Multi-Task Sparse Learning (2012, background): “In Yang et al. (2005), tracked objects are described using color and edge orientation histogram features, and the observation likelihood is computed in a coarse-to-fine manner, which allows the computation to quickly focus on the more promising regions.”
• A survey on player tracking in soccer videos (2017, methodology): “…( Manafifard et al., 2015 ), PF Dearden et al., 2006 ; Choi et al., 2004 ; Ok et al., 2002 ; Chai et al., 011 ; Davis, 2008 ), hierarchical PF ( Yang et al., 2005 ; Wang et al., 008 ), support vector regression PF ( Zhu et al., 2006 ), PF incororated by MCMC ( Zhang et al., 2008 ), boosted…”
• Multiple object tracking: A literature review (2014, background): “Monte Carlo sampling based models have also become popular in tracking, especially after the introduction of the particle filter [10], [32], [33], [52], [93], [119], [120], [121].”
• Seq-NMS for Video Object Detection (2016, methodology): “Particle filter techniques [12, 3] further improved on Kalman filters by being able to handle multiple hypotheses.”
• Robust visual tracking using ℓ1 minimization (2009, methodology): “A hierarchical particle filter is used for multiple object tracking in [31].”
• Minimum error bounded efficient ℓ1 tracker with occlusion detection (2011, background): “In [24], the observation likelihood based on multiple features is computed in a coarse-to-fine manner so that the computation can quickly focus on the more promising regions.”
• 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].”