Floor Fields for Tracking in High Density Crowd Scenes

By Saad Ali, Mubarak Shah. European Conference on Computer Vision, 2008

439 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/c4c5b3995f14fcb85affde0164addbbd4d962914

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

In Ocean Engineering

Citations in the corpus

Crowded Scene Analysis: A Survey (2015, background): “Besides, several tracking algorithms [38], [51], [59], [77], [78] also have interests in how to learn scene-speciﬁc motion patterns to improve the effect of tracking.”
Multi-target tracking by learning local-to-global trajectory models (2015, methodology): “In each temporal window, the trajectory models are initialized by the local information to link those easy-to-connect detections into a set of tracklets.”
Abnormal crowd behavior detection using social force model (2009, background): “However, tracking of individuals in a high density crowd is still a challenging problem in computer vision [3].”
People tracking with human motion predictions from social forces (2010, methodology): “Ali and Shah [12] combine a floor field approach with an evacuation model to improve 978-1-4244-5040-4/10/$26.00 ©2010 IEEE 464 people tracking.”
Visual Tracking: an Experimental Survey (2013, neutral): “Prediction of motion under the guidance of optical flow [96], [97], [98] to stabilize the search is an attractive alternative.”
Object Detection and Tracking for Autonomous Navigation in Dynamic Environments (2010, background): “A recent development is to learn image flow fields as dynamic models for densely crowded scenarios (Ali and Shah 2008).”
Understanding collective crowd behaviors: Learning a Mixture model of Dynamic pedestrian-Agents (2012, methodology): “For example, Ali et al. [1] and Lin et al. [10] computed the flow fields and segmented the patterns of crowd flows using Lagrangian coherent structures or Lie algebra.”
Automated Textual Descriptions for a Wide Range of Video Events with 48 Human Actions (2012, background): “The UCF Sports [4], Hollywood2 [5] and YouTube [6] datasets are much more challenging as they involve interactions with other people and items and the recording conditions are harder.”
Density-aware person detection and tracking in crowds (2011, background): “In [2] global motion patterns are learned and participants of the crowd are assumed to behave in a similar manner.”
Multiple object tracking: A literature review (2014, methodology): “One special application of optical flow is to discover crowd motion patterns in extremely crowded scenarios [35], [69], where ordinary features are not reliable.”
Video anomaly detection based on local statistical aggregates (2012, background): “Recently, anomaly detection for video surveillance has gained importance [2, 7, 15, 8, 5, 14, 9, 11, 3, 21, 13, 16].”
Egocentric Future Localization (2016, background): “In computer vision, Ali and Shah [3] developed a flow field model that predicts spatial crowd behaviors for tracking extremely cluttered crowd scenes.”
Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies (2017, methodology): “Many models are based on raw pixel template representation for simplicity [80, 5, 77, 57, 56], while a color histogram is the most popular representation for appearance modeling in MTT approaches [10, 40, 71, 37].”
You'll never walk alone: Modeling social behavior for multi-target tracking (2009, methodology): “Such points have been used to influence tracking [1, 12, 14].”
Improving Data Association by Joint Modeling of Pedestrian Trajectories and Groupings (2010, background): “Only some researchers use social structures to improve tracking, most notably in crowded scenarios [7], or by modeling of collision avoidance-behavior [8, 11].”
Abnormal event detection in crowded scenes using sparse representation (2013, background): “Due to the object template can be initialized in the uncrowded scene, there are also some trajectory-based approaches by tracking the objects, such as [32], [12], [32], [28] and [15].”
Sparse reconstruction cost for abnormal event detection (2011, background): “There are also some trajectory-based approaches to locate objects by tracking or frame-difference, such as [10], [24], [21] and [13].”
Anomaly detection in crowded scenes (2010, background): “Problems such as segmenting video into crowd components [3], estimating crowd size [17], determining the goal of individuals within a crowd [4] have all been subjects of research.”