Probabilistic Data Association Methods for Tracking Complex Visual Objects

By Christopher Rasmussen, Gregory Hager. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001

456 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/86d8adbb1b6389860f0de14217c2f364da9eac8a

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

Kernel-Based Object Tracking (2003, unknown): “The data association problem for multiple target particle filtering is presented in [62], [38].”
Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera (2011, methodology): “To overcome these problems, most methods employ one particle filter per target using a small state space and deal with interacting targets separately [21], [24], [38].”
MCMC-based particle filtering for tracking a variable number of interacting targets (2005, methodology): “These multitarget tracking algorithms have been used extensively in the context of computer vision, e.g., nearest neighbor tracking in [5], the MHT in [6], and the JPDAF in [7] and [8].”
Fifty Years of MIMO Detection: The Road to Large-Scale MIMOs (2015, methodology): “In addition to their wide applications in radar, sonar, electro-optical sensor networks and navigation systems [466]–[480], the PDA techniques have also been applied in the field of computer vision for solving the visual target tracking problem [481]–[484].”
Visual tracking and recognition using appearance-adaptive models in particle filters (2004, methodology): “One way is to use joi nt probabilistic data associative filter (JPDAF) [34], [35]; and the other one is to use robust st a i ics [12].”
Segmentation and Tracking of Multiple Humans in Crowded Environments (2008, background): “When objects are highly interoccluded, their image observations are far from independent; hence, a joint likelihood for multiple objects is necessary [46], [27], [19], [35], [30], [51].”
Decentralized multiple target tracking using netted collaborative autonomous trackers (2005, methodology): “Therefore existing approaches dealing with the dynamic background scenarios are either assuming to track fixed number of targets [6, 11, 13 , 20], which obviously limits its generalization, or adopting an target detector to help determine if any new target appears in the scene [12].”