A Boosted Particle Filter: Multitarget Detection and Tracking

By Kenji Okuma, Ali Taleghani, Nando de Freitas, James J. Little, David G. Lowe. European Conference on Computer Vision, 2004

1,227 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/197c7b40c4f5ceb6b1d862de0bfc27b57e61d19d

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Multi-target tracking by learning local-to-global trajectory models (2015, background): “And last but not least, it is difficult to distinguish targets with similar appearances, especially when they are close to, or partially occlude each other.”
Crowd analysis: a survey (2008, methodology): “[72] combine mixture particle filters and Adaboost algorithm.”
Unsupervised Bayesian Detection of Independent Motion in Crowds (2006, methodology): “See [9] for interesting examples of using related techniques to track more sparse “crowds” of ants, or hockey players in the case of [15]’s impressive boosted particle filter.”
Decentralized multiple target tracking using netted collaborative autonomous trackers (2005, background): “However, in [12] it stays unclear how the coalescence problem can be reliably solved under their single particle filtering framework.”
A Linear Programming Approach for Multiple Object Tracking (2007, background): “Particle filtering has also been studied for tracking hockey players [ 3 ] in which object interaction is not explicitly modeled.”
People-tracking-by-detection and people-detection-by-tracking (2008, background): “Tracking by detection has been a focus of recent work [18, 8, 27, 1].”
Model-based hand tracking using a hierarchical Bayesian filter (2006, methodology): “The ideas of tree-based filtering and particle filtering can also be combined by using the posterior distribution estimated with the tree-based filter as an importance distribution for a particle filter in a way similar to [30].”
Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles (2008, background): “While many approaches rely on background subtraction from a static camera for the former (e.g., [2], [26], [42]), several recent approaches have started to explore the possibilities of combining tracking with detection [1], [17], [37], [46].”
Improving Data Association by Joint Modeling of Pedestrian Trajectories and Groupings (2010, neutral): “This thus means some latency as opposed to typical online trackers [15, 18, 19].”
Robust Object Tracking by Hierarchical Association of Detection Responses (2008, background): “Multi-Hypothesis Tracking (MHT) [11], Joint Probabilistic Data Association Filters (JPDAFs) [12], and the particle filter based trackers [14,9] solve this problem by maintaining multiple hypotheses until enough evidence can be collected to resolve the ambiguity.”
A mobile vision system for robust multi-person tracking (2008, background): “In such cases, background subtraction is no longer a viable option, and tracking-bydetection approaches seem to be the most promising alternative [22] [10] [15] [28].”
Tracking-Learning-Detection (2012, methodology): “Such techniques have been applied to tracking of faces in lowframe-rate video [52], multiple hockey players [53], or pedestrians [54], [55].”
Multiple Object Tracking Using K-Shortest Paths Optimization (2011, neutral): “This technique has been used to great effect to follow multiple hockey players [18] or to track multiple people in the ground and image planes simultaneously [19].”
Robust Object Tracking with Online Multiple Instance Learning (2011, neutral): “It is plausible that the ideas presented here can be applied to other types of tracking problems like tracking multiple objects (e.g., [19]), tracking contours (e.g., [20], [21]), or tracking deformable objects (e.g., [22]), but this is outside the scope of our work.”