MCMC-based particle filtering for tracking a variable number of interacting targets

By Zia Khan, Tucker R. Balch, Frank Dellaert. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005

930 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Oceanography

View Paper: https://www.semanticscholar.org/paper/4831bafed66417a353530e3cd6d9dbee6516499c

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 Oceanography

Citations in the corpus

Multiple Hypothesis Tracking Revisited (2015, background): “Classical solutions to multidimensional assignment are MHT [36, 12, 17, 34] and Markov Chain Monte Carlo (MCMC) data association [19, 32].”
3D Traffic Scene Understanding From Movable Platforms (2014, neutral): “Conclusions are drawn in Section 6.”
Density-aware person detection and tracking in crowds (2011, background): “In the area of tracking, [4, 16, 22, 23] demonstrate how the tracking accuracy can be improved by the joint modeling of motion of multiple people in the scene.”
Learning to associate: HybridBoosted multi-target tracker for crowded scene (2009, background): “In such situations, tracking approaches that make online decisions on a frameby-frame basis [1][2] may yield identity switches and trajectory fragmentations due to ambiguous and noisy observation.”
Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor (2015, methodology): “But once more observation is provided at t3, our algorithm is capable of fixing the error made in t2.”
Recent advances and trends in visual tracking: A review (2011, methodology): “The Markov Chain Monte Carlo method is well applied to multi-object tracking problems while rigorously formulating the entrance and exit of an object [116,117].”
High-throughput Ethomics in Large Groups of Drosophila (2009, background): “The problem of tracking individuals in groups has been researched for studies of eusocial insects (ants and bees”
Monocular Pedestrian Detection: Survey and Experiments (2009, background): “Extensions that are especially relevant for pedestrian tracking involve hybrid discrete/continuous state-spaces [26], [50] and efficient sampling strategies [13], [32], [36], [44].”
Particle Belief Propagation (2009, methodology): “However, the fact that the belief estimate B t (x t ) can be computed at any value of x t allows us to use another approach, which has also been applied to particle filters with success (Doucet et al., 2001; Khan et al., 2005).”
Automated home-cage behavioural phenotyping of mice. (2010, background): “In fact, the use of vision-based approaches is already bearing fruit for the automated trackin”
Learning by Tracking: Siamese CNN for Robust Target Association (2016, background): “The data association can then be formulated as maximum flow [4] or, equivalently, minimum cost problem [28, 35, 45, 64], both efficiently solved to (near-)global optimality with LP, with a superior performance compared to frame-by-frame [29] or track-by-track [3] methods.”
Tracking by Sampling Trackers (2011, methodology): “Markov Chain Monte Carlo (MCMC) based methods were proposed by Khan et al. [9] and Zhao et al. [25] to reduce the computational cost especially in a high-dimensional state space.”
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].”
Multiple object tracking: A literature review (2014, background): “Table 4 lists the differences between the two processing modes.”
Object Detection and Tracking for Autonomous Navigation in Dynamic Environments (2010, background): “Few authors have investigated higher-order models for erratic motions, e.g. in sports (Okuma et al. 2004), or for interacting targets (Khan et al. 2005).”
Crowd analysis: a survey (2008, methodology): “[49] propose to use Markov Chain Monte Carlo (MCMC) and the particle filter.”
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (2013, background): “Particle filters have been applied with great success to a variety of state estimation problems including object tracking [60], [61], mobile robot localization [62], [63], people tracking [64], etc.”
Segmentation and Tracking of Multiple Humans in Crowded Environments (2008, methodology): “They have been used for various applications, including segmenting multiple cells [38], image parsing [48], multiobject tracking [21], estimating articulated structures [23], and so forth.”
Visual tracking decomposition (2010, methodology): “We compared the proposed algorithm (VTD) with four different tracking methods: standard MCMC (MC) based on [9][16]; Mean Shift (MS) [2] based on the implemented function in OpenCV; On-line Appearance Learning (OAL) in [17]; and Multiple Instance Learning (MIL) in [1].”