Tracking multiple humans in crowded environment

By Tao Zhao, Ramkant Nevatia. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., 2004

424 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/d8c8e1c7a1b0de2827ce00a2fb10a57eca629d98

How researchers see this paper

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

Citations in the corpus

Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors (2007, unknown): “In Zhao and Nevatia (2004a), a part-based representation is used for segmenting motion blobs by considering various articulations and their appearances but parts are not tracked explicitly.”
Visual tracking decomposition (2010, methodology): “The Markov Chain Monte Carlo method is well applied to multiobject tracking problems while rigorously formulating the entrance and exit of an object [9, 20].”
Counting People With Low-Level Features and Bayesian Regression (2012, unknown): “, via a Bayesian approach [28] or boosting [29], or by using stochastic spatial models to simultaneously detect and count people as foreground shapes [30].”
Optimized Pedestrian Detection for Multiple and Occluded People (2013, methodology): “One line of work proposes to segment foreground blobs into human shapes using an MCMC-based optimization approach to determine the number and configuration of overlapping shapes [23, 24, 10].”
Unsupervised Bayesian Detection of Independent Motion in Crowds (2006, methodology): “Example results from Zhao and Nevatia’s multiple-human tracker [32] (above) on their Commons01 sequence, and the results of our independent-motion detection.”
Multicamera People Tracking with a Probabilistic Occupancy Map (2008, methodology): “More recently, multiple humans have been simultaneously detected and tracked in crowded scenes [1] using Monte-Carlo-based methods to estimate their number and positions.”
MCMC-based particle filtering for tracking a variable number of interacting targets (2005, methodology): “Due to the limitations of importance sampling in highdimensional state spaces, researchers have applied Markov chain Monte Carlo (MCMC) methods to tracking problems [27], [28].”
CoTracker: It is Better to Track Together (2023, background): “We show that, by training the network by unrolling several sliding windows, CoTracker achieves excellent long-term tracking performance as well.”
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.”
Dynamic Human Pose Estimation using Markov Chain Monte Carlo Approach (2005, methodology): “2. The candidates can be generated from the current observation, t I . This is an adaptation of a bottom-up datadriven approach [15] that has now been used for a number of computer vision tasks [12][16][ 17 ].”
You'll never walk alone: Modeling social behavior for multi-target tracking (2009, background): “Others have developed approaches specifically for crowded scenes [1, 6, 24].”
Segmentation and Tracking of Multiple Humans in Crowded Environments (2008, methodology): “Parts of our system have been partially described in [53] and [55]; this paper provides a unified presentation of the methodology, additional results, and discussions.”
Decentralized multiple target tracking using netted collaborative autonomous trackers (2005, methodology): “Based on Monte Carlo sampling techniques, non-parametric methods [6, 7, 11, 16, 21] can tackle the coalescence problem in a top-down process that generates and evaluates a large number of hypotheses, thus also confronted by a similar high computational cost due to the exponential demand of the…”